[1/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

Repository: spark-website
Updated Branches:
  refs/heads/asf-site 8857572df -> 26b527127


http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/searchindex.js
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/searchindex.js b/site/docs/2.2.1/api/python/searchindex.js
index b40aeb8..345db45 100644
--- a/site/docs/2.2.1/api/python/searchindex.js
+++ b/site/docs/2.2.1/api/python/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["index","pyspark","pyspark.ml","pyspark.mllib","pyspark.sql","pyspark.streaming"],envversion:52,filenames:["index.rst","pyspark.rst","pyspark.ml.rst","pyspark.mllib.rst","pyspark.sql.rst","pyspark.streaming.rst"],objects:{"":{pyspark:[1,0,0,"-"]},"pyspark.Accumulator":{add:[1,2,1,""],value:[1,3,1,""]},"pyspark.AccumulatorParam":{addInPlace:[1,2,1,""],zero:[1,2,1,""]},"pyspark.BasicProfiler":{profile:[1,2,1,""],stats:[1,2,1,""]},"pyspark.Broadcast":{destroy:[1,2,1,""],dump:[1,2,1,""],load:[1,2,1,""],unpersist:[1,2,1,""],value:[1,3,1,""]},"pyspark.MarshalSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.PickleSerializer":{dumps:[1,2,1,""],loads:[1,2,1,""]},"pyspark.Profiler":{dump:[1,2,1,""],profile:[1,2,1,""],show:[1,2,1,""],stats:[1,2,1,""]},"pyspark.RDD":{aggregate:[1,2,1,""],aggregateByKey:[1,2,1,""],cache:[1,2,1,""],cartesian:[1,2,1,""],checkpoint:[1,2,1,""],coalesce:[1,2,1,""],cogroup:[1,2,1,""],collect:[1,2,1,""],collectAsMap:[1,2,1,""],combine
 ByKey:[1,2,1,""],context:[1,3,1,""],count:[1,2,1,""],countApprox:[1,2,1,""],countApproxDistinct:[1,2,1,""],countByKey:[1,2,1,""],countByValue:[1,2,1,""],distinct:[1,2,1,""],filter:[1,2,1,""],first:[1,2,1,""],flatMap:[1,2,1,""],flatMapValues:[1,2,1,""],fold:[1,2,1,""],foldByKey:[1,2,1,""],foreach:[1,2,1,""],foreachPartition:[1,2,1,""],fullOuterJoin:[1,2,1,""],getCheckpointFile:[1,2,1,""],getNumPartitions:[1,2,1,""],getStorageLevel:[1,2,1,""],glom:[1,2,1,""],groupBy:[1,2,1,""],groupByKey:[1,2,1,""],groupWith:[1,2,1,""],histogram:[1,2,1,""],id:[1,2,1,""],intersection:[1,2,1,""],isCheckpointed:[1,2,1,""],isEmpty:[1,2,1,""],isLocallyCheckpointed:[1,2,1,""],join:[1,2,1,""],keyBy:[1,2,1,""],keys:[1,2,1,""],leftOuterJoin:[1,2,1,""],localCheckpoint:[1,2,1,""],lookup:[1,2,1,""],map:[1,2,1,""],mapPartitions:[1,2,1,""],mapPartitionsWithIndex:[1,2,1,""],mapPartitionsWithSplit:[1,2,1,""],mapValues:[1,2,1,""],max:[1,2,1,""],mean:[1,2,1,""],meanApprox:[1,2,1,""],min:[1,2,1,""],name:[1,2,1,""],parti
 tionBy:[1,2,1,""],persist:[1,2,1,""],pipe:[1,2,1,""],randomSplit:[1,2,1,""],reduce:[1,2,1,""],reduceByKey:[1,2,1,""],reduceByKeyLocally:[1,2,1,""],repartition:[1,2,1,""],repartitionAndSortWithinPartitions:[1,2,1,""],rightOuterJoin:[1,2,1,""],sample:[1,2,1,""],sampleByKey:[1,2,1,""],sampleStdev:[1,2,1,""],sampleVariance:[1,2,1,""],saveAsHadoopDataset:[1,2,1,""],saveAsHadoopFile:[1,2,1,""],saveAsNewAPIHadoopDataset:[1,2,1,""],saveAsNewAPIHadoopFile:[1,2,1,""],saveAsPickleFile:[1,2,1,""],saveAsSequenceFile:[1,2,1,""],saveAsTextFile:[1,2,1,""],setName:[1,2,1,""],sortBy:[1,2,1,""],sortByKey:[1,2,1,""],stats:[1,2,1,""],stdev:[1,2,1,""],subtract:[1,2,1,""],subtractByKey:[1,2,1,""],sum:[1,2,1,""],sumApprox:[1,2,1,""],take:[1,2,1,""],takeOrdered:[1,2,1,""],takeSample:[1,2,1,""],toDebugString:[1,2,1,""],toLocalIterator:[1,2,1,""],top:[1,2,1,""],treeAggregate:[1,2,1,""],treeReduce:[1,2,1,""],union:[1,2,1,""],unpersist:[1,2,1,""],values:[1,2,1,""],variance:[1,2,1,""],zip:[1,2,1,""],zipWithIndex
 :[1,2,1,""],zipWithUniqueId:[1,2,1,""]},"pyspark.SparkConf":{contains:[1,2,1,""],get:[1,2,1,""],getAll:[1,2,1,""],set:[1,2,1,""],setAll:[1,2,1,""],setAppName:[1,2,1,""],setExecutorEnv:[1,2,1,""],setIfMissing:[1,2,1,""],setMaster:[1,2,1,""],setSparkHome:[1,2,1,""],toDebugString:[1,2,1,""]},"pyspark.SparkContext":{PACKAGE_EXTENSIONS:[1,3,1,""],accumulator:[1,2,1,""],addFile:[1,2,1,""],addPyFile:[1,2,1,""],applicationId:[1,3,1,""],binaryFiles:[1,2,1,""],binaryRecords:[1,2,1,""],broadcast:[1,2,1,""],cancelAllJobs:[1,2,1,""],cancelJobGroup:[1,2,1,""],defaultMinPartitions:[1,3,1,""],defaultParallelism:[1,3,1,""],dump_profiles:[1,2,1,""],emptyRDD:[1,2,1,""],getConf:[1,2,1,""],getLocalProperty:[1,2,1,""],getOrCreate:[1,4,1,""],hadoopFile:[1,2,1,""],hadoopRDD:[1,2,1,""],newAPIHadoopFile:[1,2,1,""],newAPIHadoopRDD:[1,2,1,""],parallelize:[1,2,1,""],pickleFile:[1,2,1,""],range:[1,2,1,""],runJob:[1,2,1,""],sequenceFile:[1,2,1,""],setCheckpointDir:[1,2,1,""],setJobGroup:[1,2,1,""],setLocalPropert
 y:[1,2,1,""],setLogLevel:[1,2,1,""],setSystemProperty:[1,4,1,""],show_profiles:[1,2,1,""],sparkUser:[1,2,1,""],startTime:[1,3,1,""],statusTracker:[1,2,1,""],stop:[1,2,1,""],textFile:[1,2,1,""],uiWebUrl:[1,3,1,""],union:[1,2,1,""],version:[1,3,1,""],wholeTextFiles:[1,2,1,""]},"pyspark.SparkFiles":{get:[1,4,1,""],getRootDirectory:[1,4,1,""]},"pyspark.StatusTracker":{getActiveJobsIds:[1,2,1,""],getActiveStageIds:[1,2,1,""],getJobIdsForGroup:[1,2,1,""],getJobInfo:[1,2,1,""],getStageInfo:[1,2,1,""]},"pyspark.StorageLevel":{DISK_ONLY:[1,3,1,""],DISK_ONLY_2:[1,3,1,""],MEMORY_AND_DISK:[1,3,1,""],MEMORY_AND_DISK_2:[1,3,1,""],MEMORY_AND_DISK_SER:[1,3,1,""],MEMORY_AND_DISK_SER_2:[1,3,1,""],MEMORY_ONLY:[1,3,1,""],MEMORY_ONLY_2:[1,3,1,""],MEMORY_ONLY_SER:[1,3,1,""],MEMORY_ONLY_SER_2:[1,3,1,""],OFF_HEAP:[1,3,1,""]},"pyspark.TaskContext":{attemptNumber:[1,2,1,""],get:[1,4,1,""],partitionId:[1,2,1,""],stageId:[1,2,1,""],taskAttemptId:[1,2,1,""]},"pyspark.ml":{Estimator:[2,1,1,""],Model:[2,1,1,""],P
 ipeline:[2,1,1,""],PipelineModel:[2,1,1,""],Transformer:[2,1,1,""],classification:[2,0,0,"-"],clustering:[2,0,0,"-"],evaluation:[2,0,0,"-"],feature:[2,0,0,"-"],fpm:[2,0,0,"-"],linalg:[2,0,0,"-"],param:[2,0,0,"-"],recommendation:[2,0,0,"-"],regression:[2,0,0,"-"],stat:[2,0,0,"-"],tuning:[2,0,0,"-"],util:[2,0,0,"-"]},"pyspark.ml.Estimator":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.Model":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],transform:[2,2,1,""]},"pyspark.ml.Pipeline":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],
 getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getStages:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setParams:[2,2,1,""],setStages:[2,2,1,""],stages:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.PipelineModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.Transformer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],transform:[2,2,1,""]},"pyspark.ml.classification":{BinaryLogisticRegressionSummary:[2,1,1,""],Binar
 yLogisticRegressionTrainingSummary:[2,1,1,""],DecisionTreeClassificationModel:[2,1,1,""],DecisionTreeClassifier:[2,1,1,""],GBTClassificationModel:[2,1,1,""],GBTClassifier:[2,1,1,""],LinearSVC:[2,1,1,""],LinearSVCModel:[2,1,1,""],LogisticRegression:[2,1,1,""],LogisticRegressionModel:[2,1,1,""],LogisticRegressionSummary:[2,1,1,""],LogisticRegressionTrainingSummary:[2,1,1,""],MultilayerPerceptronClassificationModel:[2,1,1,""],MultilayerPerceptronClassifier:[2,1,1,""],NaiveBayes:[2,1,1,""],NaiveBayesModel:[2,1,1,""],OneVsRest:[2,1,1,""],OneVsRestModel:[2,1,1,""],RandomForestClassificationModel:[2,1,1,""],RandomForestClassifier:[2,1,1,""]},"pyspark.ml.classification.BinaryLogisticRegressionSummary":{areaUnderROC:[2,3,1,""],fMeasureByThreshold:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],pr:[2,3,1,""],precisionByThreshold:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],recallByThreshold:[2,3,1,""],roc:[2,3,1,""]},"pyspark.ml.classification.BinaryLogisticRegressionTrai
 ningSummary":{areaUnderROC:[2,3,1,""],fMeasureByThreshold:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],objectiveHistory:[2,3,1,""],pr:[2,3,1,""],precisionByThreshold:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],recallByThreshold:[2,3,1,""],roc:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.classification.DecisionTreeClassificationModel":{copy:[2,2,1,""],depth:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.DecisionTreeClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],
 extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabel
 Col:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.GBTClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.GBTClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,
 ""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getLossType:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""]
 ,setLossType:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setSubsamplingRate:[2,2,1,""],stepSize:[2,3,1,""],subsamplingRate:[2,3,1,""],supportedLossTypes:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LinearSVC":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getStandardization:[2,2,1,""],getThreshold:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam
 :[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,2,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setStandardization:[2,2,1,""],setThreshold:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],standardization:[2,3,1,""],threshold:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LinearSVCModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numClasses:[2,3,1,
 ""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegression":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],elasticNetParam:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],family:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getElasticNetParam:[2,2,1,""],getFamily:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getStandardization:[2,2,1,""],getThreshold:[2,2,1,""],getThresholds:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,"
 "],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,2,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setElasticNetParam:[2,2,1,""],setFamily:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setStandardization:[2,2,1,""],setThreshold:[2,2,1,""],setThresholds:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],standardization:[2,3,1,""],threshold:[2,3,1,""],thresholds:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegressionModel":{coefficientMatrix:[2,3,1,""],coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],ha
 sSummary:[2,3,1,""],intercept:[2,3,1,""],interceptVector:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.LogisticRegressionSummary":{featuresCol:[2,3,1,""],labelCol:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""]},"pyspark.ml.classification.LogisticRegressionTrainingSummary":{featuresCol:[2,3,1,""],labelCol:[2,3,1,""],objectiveHistory:[2,3,1,""],predictions:[2,3,1,""],probabilityCol:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.classification.MultilayerPerceptronClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],layers:[2,3,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],rea
 d:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],weights:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.MultilayerPerceptronClassifier":{blockSize:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getBlockSize:[2,2,1,""],getFeaturesCol:[2,2,1,""],getInitialWeights:[2,2,1,""],getLabelCol:[2,2,1,""],getLayers:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSolver:[2,2,1,""],getStepSize:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],initialWeights:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],layers:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBlockSize:[2,2,1,""],setFeaturesCol:[2,2,1,""],setInitialWeights:[2,2,1,""],setLabelCol:[2,2,1,""],setLayers:[2,2,1,""],setMaxIt
 er:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSolver:[2,2,1,""],setStepSize:[2,2,1,""],setTol:[2,2,1,""],solver:[2,3,1,""],stepSize:[2,3,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.NaiveBayes":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getModelType:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSmoothing:[2,2,1,""],getThresholds:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],modelType:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setModelType:[2,2,1
 ,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSmoothing:[2,2,1,""],setThresholds:[2,2,1,""],setWeightCol:[2,2,1,""],smoothing:[2,3,1,""],thresholds:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.NaiveBayesModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],pi:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],theta:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.classification.OneVsRest":{classifier:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getClassifier:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,"
 "],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setClassifier:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.OneVsRestModel":{classifier:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],getClassifier:[2,2,1,""],getFeaturesCol:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],set
 Classifier:[2,2,1,""],setFeaturesCol:[2,2,1,""],setLabelCol:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],transform:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.RandomForestClassificationModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.classification.RandomForestClassifier":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[
 2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatureSubsetStrategy:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getNumTrees:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getRawPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],numTrees:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval
 :[2,2,1,""],setFeatureSubsetStrategy:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setNumTrees:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setRawPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],subsamplingRate:[2,3,1,""],supportedFeatureSubsetStrategies:[2,3,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering":{BisectingKMeans:[2,1,1,""],BisectingKMeansModel:[2,1,1,""],BisectingKMeansSummary:[2,1,1,""],DistributedLDAModel:[2,1,1,""],GaussianMixture:[2,1,1,""],GaussianMixtureModel:[2,1,1,""],GaussianMixtureSummary:[2,1,1,""],KMeans:[2,1,1,""],KMeansModel:[2,1,1,""],LDA:[2,1,1,""],LDAModel:[2,1,1,""],LocalLDAModel:[2,1,1,""]},"pyspark.ml.clustering.BisectingKMeans":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2
 ,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getMinDivisibleClusterSize:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],minDivisibleClusterSize:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setMinDivisibleClusterSize:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.BisectingKMeansModel":{clusterCenters:[2,2,1,""],computeCost:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1
 ,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.BisectingKMeansSummary":{cluster:[2,3,1,""],clusterSizes:[2,3,1,""],featuresCol:[2,3,1,""],k:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""]},"pyspark.ml.clustering.DistributedLDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getCheckpointFiles:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],logPrior:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],toLocal:[2,2,1,""],topicsMatrix:[2,2,1,""],trainingLogLikelihood:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""],write:[2,2,1,""]},"py
 spark.ml.clustering.GaussianMixture":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getProbabilityCol:[2,2,1,""],getSeed:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setProbabilityCol:[2,2,1,""],setSeed:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixtureModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],gaussiansDF:[2,3,1,""],getOrDefa
 ult:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],weights:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.GaussianMixtureSummary":{cluster:[2,3,1,""],clusterSizes:[2,3,1,""],featuresCol:[2,3,1,""],k:[2,3,1,""],logLikelihood:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],probability:[2,3,1,""],probabilityCol:[2,3,1,""]},"pyspark.ml.clustering.KMeans":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeaturesCol:[2,2,1,""],getInitMode:[2,2,1,""],getInitSteps:[2,2,1,""],getK:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],initMode:[2,3,1,""],initSteps:[2,3,1,""],is
 Defined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setFeaturesCol:[2,2,1,""],setInitMode:[2,2,1,""],setInitSteps:[2,2,1,""],setK:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.KMeansModel":{clusterCenters:[2,2,1,""],computeCost:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.LDA":{checkpointInterval:[2,3,1,""],copy:[2,2,1,""],docConcentration:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,
 2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getDocConcentration:[2,2,1,""],getFeaturesCol:[2,2,1,""],getK:[2,2,1,""],getKeepLastCheckpoint:[2,2,1,""],getLearningDecay:[2,2,1,""],getLearningOffset:[2,2,1,""],getMaxIter:[2,2,1,""],getOptimizeDocConcentration:[2,2,1,""],getOptimizer:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],getTopicConcentration:[2,2,1,""],getTopicDistributionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],keepLastCheckpoint:[2,3,1,""],learningDecay:[2,3,1,""],learningOffset:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],optimizeDocConcentration:[2,3,1,""],optimizer:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCheckpointInterval:[2,2,1,""],setDocConcentration:[2,2,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setKeepLastCheckpoint:[2,2,1,""],setLearning
 Decay:[2,2,1,""],setLearningOffset:[2,2,1,""],setMaxIter:[2,2,1,""],setOptimizeDocConcentration:[2,2,1,""],setOptimizer:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],setTopicConcentration:[2,2,1,""],setTopicDistributionCol:[2,2,1,""],subsamplingRate:[2,3,1,""],topicConcentration:[2,3,1,""],topicDistributionCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.clustering.LDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],topicsMatrix:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""]},"pyspark.ml.clustering.LocalLDAModel":{copy:[2,2,1,""],describeTopics:[2,2,1,""],estimatedDocConcentration:[2,2,1,""],explainParam:[2,2,1,""],explai
 nParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isDistributed:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],topicsMatrix:[2,2,1,""],transform:[2,2,1,""],vocabSize:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation":{BinaryClassificationEvaluator:[2,1,1,""],Evaluator:[2,1,1,""],MulticlassClassificationEvaluator:[2,1,1,""],RegressionEvaluator:[2,1,1,""]},"pyspark.ml.evaluation.BinaryClassificationEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getRawPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],metric
 Name:[2,3,1,""],params:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setRawPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation.Evaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.evaluation.MulticlassClassificationEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],metricName:[2,3,1,""],params:[2,3,1,
 ""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.evaluation.RegressionEvaluator":{copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getLabelCol:[2,2,1,""],getMetricName:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isLargerBetter:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],metricName:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setLabelCol:[2,2,1,""],setMetricName:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature":{Binarizer:[2,1,1,""],BucketedRandomProjectionLSH:[2,1,1,""],BucketedRandomProjectionLSHModel:[2,1,1,""],Bucketizer:[2,1,1,""],ChiSqSelector:[2,1,1,""],ChiSqSelectorMode
 l:[2,1,1,""],CountVectorizer:[2,1,1,""],CountVectorizerModel:[2,1,1,""],DCT:[2,1,1,""],ElementwiseProduct:[2,1,1,""],HashingTF:[2,1,1,""],IDF:[2,1,1,""],IDFModel:[2,1,1,""],Imputer:[2,1,1,""],ImputerModel:[2,1,1,""],IndexToString:[2,1,1,""],MaxAbsScaler:[2,1,1,""],MaxAbsScalerModel:[2,1,1,""],MinHashLSH:[2,1,1,""],MinHashLSHModel:[2,1,1,""],MinMaxScaler:[2,1,1,""],MinMaxScalerModel:[2,1,1,""],NGram:[2,1,1,""],Normalizer:[2,1,1,""],OneHotEncoder:[2,1,1,""],PCA:[2,1,1,""],PCAModel:[2,1,1,""],PolynomialExpansion:[2,1,1,""],QuantileDiscretizer:[2,1,1,""],RFormula:[2,1,1,""],RFormulaModel:[2,1,1,""],RegexTokenizer:[2,1,1,""],SQLTransformer:[2,1,1,""],StandardScaler:[2,1,1,""],StandardScalerModel:[2,1,1,""],StopWordsRemover:[2,1,1,""],StringIndexer:[2,1,1,""],StringIndexerModel:[2,1,1,""],Tokenizer:[2,1,1,""],VectorAssembler:[2,1,1,""],VectorIndexer:[2,1,1,""],VectorIndexerModel:[2,1,1,""],VectorSlicer:[2,1,1,""],Word2Vec:[2,1,1,""],Word2VecModel:[2,1,1,""]},"pyspark.ml.feature.Binarizer"
 :{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getThreshold:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setThreshold:[2,2,1,""],threshold:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.BucketedRandomProjectionLSH":{bucketLength:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getBucketLength:[2,2,1,""],getInputCol:[2,2,1,""],getNumHashTables:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],loa
 d:[2,2,1,""],numHashTables:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBucketLength:[2,2,1,""],setInputCol:[2,2,1,""],setNumHashTables:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.BucketedRandomProjectionLSHModel":{approxNearestNeighbors:[2,2,1,""],approxSimilarityJoin:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Bucketizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSplits:[2,2,1,""],handl
 eInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSplits:[2,2,1,""],splits:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ChiSqSelector":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fdr:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fpr:[2,3,1,""],fwe:[2,3,1,""],getFdr:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFpr:[2,2,1,""],getFwe:[2,2,1,""],getLabelCol:[2,2,1,""],getNumTopFeatures:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getPercentile:[2,2,1,""],getSelectorType:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],numTopFeatures:[2,3,1,""],outputCol:[
 2,3,1,""],params:[2,3,1,""],percentile:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],selectorType:[2,3,1,""],setFdr:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFpr:[2,2,1,""],setFwe:[2,2,1,""],setLabelCol:[2,2,1,""],setNumTopFeatures:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setPercentile:[2,2,1,""],setSelectorType:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ChiSqSelectorModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],selectedFeatures:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.CountVectorizer":{binary:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getBinary:[2,2,1,""],getInputCol:[2,2,1,""],getMinDF:[2,2,1,""],getMinTF:[2,2,1,""],getOrDe
 fault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getVocabSize:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],minDF:[2,3,1,""],minTF:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setBinary:[2,2,1,""],setInputCol:[2,2,1,""],setMinDF:[2,2,1,""],setMinTF:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setVocabSize:[2,2,1,""],vocabSize:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.CountVectorizerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],vocabulary:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.DCT":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1
 ,""],getInputCol:[2,2,1,""],getInverse:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],inverse:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setInverse:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ElementwiseProduct":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getScalingVec:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],scalingVec:[2,3,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setScalingVec:[2,2
 ,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.HashingTF":{binary:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getBinary:[2,2,1,""],getInputCol:[2,2,1,""],getNumFeatures:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setBinary:[2,2,1,""],setInputCol:[2,2,1,""],setNumFeatures:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IDF":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMinDocFreq:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,
 ""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],minDocFreq:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMinDocFreq:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IDFModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],idf:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Imputer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCols:[2,2,1,""],getMissingValue:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCols:[2,2,1,""],getParam:[2,2,1,""],getStrategy:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCols:[2,3,1,""],isDefined:[2,2,1,""],isSe
 t:[2,2,1,""],load:[2,2,1,""],missingValue:[2,3,1,""],outputCols:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCols:[2,2,1,""],setMissingValue:[2,2,1,""],setOutputCols:[2,2,1,""],setParams:[2,2,1,""],setStrategy:[2,2,1,""],strategy:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.ImputerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],surrogateDF:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.IndexToString":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getLabels:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1
 ,""],labels:[2,3,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setLabels:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MaxAbsScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MaxAbsScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,"
 "],load:[2,2,1,""],maxAbs:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinHashLSH":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getNumHashTables:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numHashTables:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInputCol:[2,2,1,""],setNumHashTables:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinHashLSHModel":{approxNearestNeighbors:[2,2,1,""],approxSimilarityJoin:[2,2,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,
 2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinMaxScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMax:[2,2,1,""],getMin:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],max:[2,3,1,""],min:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMax:[2,2,1,""],setMin:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.MinMaxScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""
 ],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],originalMax:[2,3,1,""],originalMin:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.NGram":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getN:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],n:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setN:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Normalizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getP:[2,2,1,""],getParam:[2,2,1,""],hasD
 efault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],p:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setP:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.OneHotEncoder":{copy:[2,2,1,""],dropLast:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getDropLast:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setDropLast:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PCA":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractP
 aramMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getK:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setK:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PCAModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],explainedVariance:[2,3,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],pc:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.PolynomialExpansion":{copy:[2,2,1,""],degree:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getDegr
 ee:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setDegree:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.QuantileDiscretizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getNumBuckets:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getRelativeError:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numBuckets:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],relativeError:[2,3,1,""],save:[2,2,1,"
 "],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setNumBuckets:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setRelativeError:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RFormula":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],forceIndexLabel:[2,3,1,""],formula:[2,3,1,""],getFeaturesCol:[2,2,1,""],getForceIndexLabel:[2,2,1,""],getFormula:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setFeaturesCol:[2,2,1,""],setForceIndexLabel:[2,2,1,""],setFormula:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RFormulaModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,"
 "],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.RegexTokenizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],gaps:[2,3,1,""],getGaps:[2,2,1,""],getInputCol:[2,2,1,""],getMinTokenLength:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getPattern:[2,2,1,""],getToLowercase:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],minTokenLength:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],pattern:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setGaps:[2,2,1,""],setInputCol:[2,2,1,""],setMinTokenLength:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setPattern:[2,2,1,""],setToLowercase:[2,2,1,""],toLowercase:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature
 .SQLTransformer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getStatement:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setParams:[2,2,1,""],setStatement:[2,2,1,""],statement:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StandardScaler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getWithMean:[2,2,1,""],getWithStd:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setWithMean:[2,2,1,""],setWithStd
 :[2,2,1,""],withMean:[2,3,1,""],withStd:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StandardScalerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],mean:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],std:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StopWordsRemover":{caseSensitive:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getCaseSensitive:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getStopWords:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],loadDefaultStopWords:[2,5,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setCaseSensitive
 :[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setStopWords:[2,2,1,""],stopWords:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StringIndexer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getHandleInvalid:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],handleInvalid:[2,3,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StringIndexerModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet
 :[2,2,1,""],labels:[2,3,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Tokenizer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCol:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorAssembler":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getInputCols:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCols:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],outputCol:[2,3
 ,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCols:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorIndexer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMaxCategories:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],maxCategories:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setInputCol:[2,2,1,""],setMaxCategories:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorIndexerModel":{categoryMaps:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],i
 sDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.VectorSlicer":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getIndices:[2,2,1,""],getInputCol:[2,2,1,""],getNames:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],indices:[2,3,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],names:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setIndices:[2,2,1,""],setInputCol:[2,2,1,""],setNames:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Word2Vec":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getInputCol:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxSentenceLen
 gth:[2,2,1,""],getMinCount:[2,2,1,""],getNumPartitions:[2,2,1,""],getOrDefault:[2,2,1,""],getOutputCol:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getVectorSize:[2,2,1,""],getWindowSize:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],maxSentenceLength:[2,3,1,""],minCount:[2,3,1,""],numPartitions:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInputCol:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxSentenceLength:[2,2,1,""],setMinCount:[2,2,1,""],setNumPartitions:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setVectorSize:[2,2,1,""],setWindowSize:[2,2,1,""],stepSize:[2,3,1,""],vectorSize:[2,3,1,""],windowSize:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.feature.Word2VecModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],
 findSynonyms:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getVectors:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.fpm":{FPGrowth:[2,1,1,""],FPGrowthModel:[2,1,1,""]},"pyspark.ml.fpm.FPGrowth":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getItemsCol:[2,2,1,""],getMinConfidence:[2,2,1,""],getMinSupport:[2,2,1,""],getNumPartitions:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemsCol:[2,3,1,""],load:[2,2,1,""],minConfidence:[2,3,1,""],minSupport:[2,3,1,""],numPartitions:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setItemsCol:[2,2,1,""],setMinConfidence:[2,2,1,""],setMinSupport:[2,2,1,""],setNumPar
 titions:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.fpm.FPGrowthModel":{associationRules:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],freqItemsets:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.linalg":{DenseMatrix:[2,1,1,""],DenseVector:[2,1,1,""],Matrices:[2,1,1,""],Matrix:[2,1,1,""],SparseMatrix:[2,1,1,""],SparseVector:[2,1,1,""],Vector:[2,1,1,""],Vectors:[2,1,1,""]},"pyspark.ml.linalg.DenseMatrix":{toArray:[2,2,1,""],toSparse:[2,2,1,""]},"pyspark.ml.linalg.DenseVector":{dot:[2,2,1,""],norm:[2,2,1,""],numNonzeros:[2,2,1,""],squared_distance:[2,2,1,""],toArray:[2,2,1,""],values:[2,3,1,""]},"pyspark.ml.linalg.Matrices":{dense:[2,5,1,""],sparse:[2,5,1,""]},"pyspark.ml.linalg.Matr
 ix":{toArray:[2,2,1,""]},"pyspark.ml.linalg.SparseMatrix":{toArray:[2,2,1,""],toDense:[2,2,1,""]},"pyspark.ml.linalg.SparseVector":{dot:[2,2,1,""],indices:[2,3,1,""],norm:[2,2,1,""],numNonzeros:[2,2,1,""],size:[2,3,1,""],squared_distance:[2,2,1,""],toArray:[2,2,1,""],values:[2,3,1,""]},"pyspark.ml.linalg.Vector":{toArray:[2,2,1,""]},"pyspark.ml.linalg.Vectors":{dense:[2,5,1,""],norm:[2,5,1,""],sparse:[2,5,1,""],squared_distance:[2,5,1,""],zeros:[2,5,1,""]},"pyspark.ml.param":{Param:[2,1,1,""],Params:[2,1,1,""],TypeConverters:[2,1,1,""]},"pyspark.ml.param.Params":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""]},"pyspark.ml.param.TypeConverters":{identity:[2,5,1,""],toBoolean:[2,5,1,""],toFloat:[2,5,1,""],toInt:[2,5,1,""],toList:[2,5,1,""],toListFloat:[2,5,1,""],toListInt:[2,5,1,""],toListString:[2,5,
 1,""],toString:[2,5,1,""],toVector:[2,5,1,""]},"pyspark.ml.recommendation":{ALS:[2,1,1,""],ALSModel:[2,1,1,""]},"pyspark.ml.recommendation.ALS":{alpha:[2,3,1,""],checkpointInterval:[2,3,1,""],coldStartStrategy:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],finalStorageLevel:[2,3,1,""],fit:[2,2,1,""],getAlpha:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getColdStartStrategy:[2,2,1,""],getFinalStorageLevel:[2,2,1,""],getImplicitPrefs:[2,2,1,""],getIntermediateStorageLevel:[2,2,1,""],getItemCol:[2,2,1,""],getMaxIter:[2,2,1,""],getNonnegative:[2,2,1,""],getNumItemBlocks:[2,2,1,""],getNumUserBlocks:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRank:[2,2,1,""],getRatingCol:[2,2,1,""],getRegParam:[2,2,1,""],getSeed:[2,2,1,""],getUserCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],implicitPrefs:[2,3,1,""],intermediateStorageLevel:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemCol:[2
 ,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],nonnegative:[2,3,1,""],numItemBlocks:[2,3,1,""],numUserBlocks:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],rank:[2,3,1,""],ratingCol:[2,3,1,""],read:[2,2,1,""],regParam:[2,3,1,""],save:[2,2,1,""],seed:[2,3,1,""],setAlpha:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setColdStartStrategy:[2,2,1,""],setFinalStorageLevel:[2,2,1,""],setImplicitPrefs:[2,2,1,""],setIntermediateStorageLevel:[2,2,1,""],setItemCol:[2,2,1,""],setMaxIter:[2,2,1,""],setNonnegative:[2,2,1,""],setNumBlocks:[2,2,1,""],setNumItemBlocks:[2,2,1,""],setNumUserBlocks:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRank:[2,2,1,""],setRatingCol:[2,2,1,""],setRegParam:[2,2,1,""],setSeed:[2,2,1,""],setUserCol:[2,2,1,""],userCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.recommendation.ALSModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:
 [2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],itemFactors:[2,3,1,""],load:[2,2,1,""],params:[2,3,1,""],rank:[2,3,1,""],read:[2,2,1,""],recommendForAllItems:[2,2,1,""],recommendForAllUsers:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],userFactors:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression":{AFTSurvivalRegression:[2,1,1,""],AFTSurvivalRegressionModel:[2,1,1,""],DecisionTreeRegressionModel:[2,1,1,""],DecisionTreeRegressor:[2,1,1,""],GBTRegressionModel:[2,1,1,""],GBTRegressor:[2,1,1,""],GeneralizedLinearRegression:[2,1,1,""],GeneralizedLinearRegressionModel:[2,1,1,""],GeneralizedLinearRegressionSummary:[2,1,1,""],GeneralizedLinearRegressionTrainingSummary:[2,1,1,""],IsotonicRegression:[2,1,1,""],IsotonicRegressionModel:[2,1,1,""],LinearRegression:[2,1,1,""],LinearRegressionModel:[2,1,1,""],LinearRegressionSummary:[2,1,1,""],LinearRegressionTrainingSummary:[2,1,1,""],RandomForestRegressionModel:[2,1,1,""],RandomForestRegressor:[2,1,1,""]},"pyspark.ml.regression.AFTSurvivalR
 egression":{aggregationDepth:[2,3,1,""],censorCol:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getCensorCol:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getQuantileProbabilities:[2,2,1,""],getQuantilesCol:[2,2,1,""],getTol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],quantileProbabilities:[2,3,1,""],quantilesCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setCensorCol:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setQuan
 tileProbabilities:[2,2,1,""],setQuantilesCol:[2,2,1,""],setTol:[2,2,1,""],tol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.AFTSurvivalRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],predict:[2,2,1,""],predictQuantiles:[2,2,1,""],read:[2,2,1,""],save:[2,2,1,""],scale:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.DecisionTreeRegressionModel":{copy:[2,2,1,""],depth:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""]
 ,save:[2,2,1,""],toDebugString:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.DecisionTreeRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getVarianceCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[
 2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setVarianceCol:[2,2,1,""],supportedImpurities:[2,3,1,""],varianceCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GBTRegressionModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,
 1,""]},"pyspark.ml.regression.GBTRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getLossType:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxIter:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getStepSize:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],pre
 dictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setLossType:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxIter:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setStepSize:[2,2,1,""],setSubsamplingRate:[2,2,1,""],stepSize:[2,3,1,""],subsamplingRate:[2,3,1,""],supportedImpurities:[2,3,1,""],supportedLossTypes:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegression":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],family:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getFamily:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getLink:[2,2,1,""],getLinkPower:[2,2,1,""],getLi
 nkPredictionCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getSolver:[2,2,1,""],getTol:[2,2,1,""],getVariancePower:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],link:[2,3,1,""],linkPower:[2,3,1,""],linkPredictionCol:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setFamily:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setLink:[2,2,1,""],setLinkPower:[2,2,1,""],setLinkPredictionCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setSolver:[2,2,1,""],setTol:[2,2,1,""],setVariancePower:[2,2,1,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],tol:[2,3,1,""],variancePower:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.
 regression.GeneralizedLinearRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionSummary":{aic:[2,3,1,""],degreesOfFreedom:[2,3,1,""],deviance:[2,3,1,""],dispersion:[2,3,1,""],nullDeviance:[2,3,1,""],numInstances:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],rank:[2,3,1,""],residualDegreeOfFreedom:[2,3,1,""],residualDegreeOfFreedomNull:[2,3,1,""],residuals:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionTrainingSummary":{aic:[2,3,1,""],coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],
 deviance:[2,3,1,""],dispersion:[2,3,1,""],nullDeviance:[2,3,1,""],numInstances:[2,3,1,""],numIterations:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],rank:[2,3,1,""],residualDegreeOfFreedom:[2,3,1,""],residualDegreeOfFreedomNull:[2,3,1,""],residuals:[2,2,1,""],solver:[2,3,1,""],tValues:[2,3,1,""]},"pyspark.ml.regression.IsotonicRegression":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureIndex:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getFeatureIndex:[2,2,1,""],getFeaturesCol:[2,2,1,""],getIsotonic:[2,2,1,""],getLabelCol:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],isotonic:[2,3,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],setFeatureIndex:[2,2,1,""],setFeaturesCol:[2,2,1,""],setIsoton
 ic:[2,2,1,""],setLabelCol:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setWeightCol:[2,2,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.IsotonicRegressionModel":{boundaries:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],params:[2,3,1,""],predictions:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegression":{aggregationDepth:[2,3,1,""],copy:[2,2,1,""],elasticNetParam:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fitIntercept:[2,3,1,""],getAggregationDepth:[2,2,1,""],getElasticNetParam:[2,2,1,""],getFeaturesCol:[2,2,1,""],getFitIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxIter:[2,2,1,""],getOrDefault:[2,2,1,""]
 ,getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getRegParam:[2,2,1,""],getSolver:[2,2,1,""],getStandardization:[2,2,1,""],getTol:[2,2,1,""],getWeightCol:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],regParam:[2,3,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setElasticNetParam:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setRegParam:[2,2,1,""],setSolver:[2,2,1,""],setStandardization:[2,2,1,""],setTol:[2,2,1,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],standardization:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionModel":{coefficients:[2,3,1,""],copy:[2,2,1,""],evaluate:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,
 ""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionSummary":{coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],devianceResiduals:[2,3,1,""],explainedVariance:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],meanAbsoluteError:[2,3,1,""],meanSquaredError:[2,3,1,""],numInstances:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],r2:[2,3,1,""],residuals:[2,3,1,""],rootMeanSquaredError:[2,3,1,""],tValues:[2,3,1,""]},"pyspark.ml.regression.LinearRegressionTrainingSummary":{coefficientStandardErrors:[2,3,1,""],degreesOfFreedom:[2,3,1,""],devianceResiduals:[2,3,1,""],explainedVariance:[2,3,1,""],featuresCol:[2,3,1,""],labelCol:[2,3,1,""],meanAb
 soluteError:[2,3,1,""],meanSquaredError:[2,3,1,""],numInstances:[2,3,1,""],objectiveHistory:[2,3,1,""],pValues:[2,3,1,""],predictionCol:[2,3,1,""],predictions:[2,3,1,""],r2:[2,3,1,""],residuals:[2,3,1,""],rootMeanSquaredError:[2,3,1,""],tValues:[2,3,1,""],totalIterations:[2,3,1,""]},"pyspark.ml.regression.RandomForestRegressionModel":{copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],featureImportances:[2,3,1,""],getNumTrees:[2,3,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,2,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],totalNumNodes:[2,3,1,""],transform:[2,2,1,""],treeWeights:[2,3,1,""],trees:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.RandomForestRegressor":{cacheNodeIds:[2,3,1,""],checkpointInterval:[2,3,1,""],copy:[2,2,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extract
 ParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatureSubsetStrategy:[2,2,1,""],getFeaturesCol:[2,2,1,""],getImpurity:[2,2,1,""],getLabelCol:[2,2,1,""],getMaxBins:[2,2,1,""],getMaxDepth:[2,2,1,""],getMaxMemoryInMB:[2,2,1,""],getMinInfoGain:[2,2,1,""],getMinInstancesPerNode:[2,2,1,""],getNumTrees:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getPredictionCol:[2,2,1,""],getSeed:[2,2,1,""],getSubsamplingRate:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],impurity:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,2,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],numTrees:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,2,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCacheNodeIds:[2,2,1,""],setCheckpointInterval:[2,2,1,""],setFeatureSubsetStrategy:[2,2,1,""],
 setFeaturesCol:[2,2,1,""],setImpurity:[2,2,1,""],setLabelCol:[2,2,1,""],setMaxBins:[2,2,1,""],setMaxDepth:[2,2,1,""],setMaxMemoryInMB:[2,2,1,""],setMinInfoGain:[2,2,1,""],setMinInstancesPerNode:[2,2,1,""],setNumTrees:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setSeed:[2,2,1,""],setSubsamplingRate:[2,2,1,""],subsamplingRate:[2,3,1,""],supportedFeatureSubsetStrategies:[2,3,1,""],supportedImpurities:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.stat":{ChiSquareTest:[2,1,1,""],Correlation:[2,1,1,""]},"pyspark.ml.stat.ChiSquareTest":{test:[2,5,1,""]},"pyspark.ml.stat.Correlation":{corr:[2,5,1,""]},"pyspark.ml.tuning":{CrossValidator:[2,1,1,""],CrossValidatorModel:[2,1,1,""],ParamGridBuilder:[2,1,1,""],TrainValidationSplit:[2,1,1,""],TrainValidationSplitModel:[2,1,1,""]},"pyspark.ml.tuning.CrossValidator":{copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,
 1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getNumFolds:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],numFolds:[2,3,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setNumFolds:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""]},"pyspark.ml.tuning.CrossValidatorModel":{avgMetrics:[2,3,1,""],bestModel:[2,3,1,""],copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorPar
 amMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setSeed:[2,2,1,""],transform:[2,2,1,""]},"pyspark.ml.tuning.ParamGridBuilder":{addGrid:[2,2,1,""],baseOn:[2,2,1,""],build:[2,2,1,""]},"pyspark.ml.tuning.TrainValidationSplit":{copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],fit:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],getTrainRatio:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setParams:[2,2,1,""],setSeed:[2,2,1,""],setTrainRatio:[2,2,1,""],trainRatio:[2,3,1,""]},"pyspark.ml.tuning.TrainValidationSplitModel":{bestModel:[2,3,1,""],copy:[2,2,1,""],estimator:[2,3,1,""],estimatorParamMaps:[2,3,1,""],evaluator:[2,
 3,1,""],explainParam:[2,2,1,""],explainParams:[2,2,1,""],extractParamMap:[2,2,1,""],getEstimator:[2,2,1,""],getEstimatorParamMaps:[2,2,1,""],getEvaluator:[2,2,1,""],getOrDefault:[2,2,1,""],getParam:[2,2,1,""],getSeed:[2,2,1,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],params:[2,3,1,""],seed:[2,3,1,""],setEstimator:[2,2,1,""],setEstimatorParamMaps:[2,2,1,""],setEvaluator:[2,2,1,""],setSeed:[2,2,1,""],transform:[2,2,1,""],validationMetrics:[2,3,1,""]},"pyspark.ml.util":{Identifiable:[2,1,1,""],JavaMLReadable:[2,1,1,""],JavaMLReader:[2,1,1,""],JavaMLWritable:[2,1,1,""],JavaMLWriter:[2,1,1,""],JavaPredictionModel:[2,1,1,""],MLReadable:[2,1,1,""],MLReader:[2,1,1,""],MLWritable:[2,1,1,""],MLWriter:[2,1,1,""]},"pyspark.ml.util.Identifiable":{uid:[2,3,1,""]},"pyspark.ml.util.JavaMLReadable":{load:[2,2,1,""],read:[2,4,1,""]},"pyspark.ml.util.JavaMLReader":{context:[2,2,1,""],load:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.JavaMLWritable":{save:[2,2
 ,1,""],write:[2,2,1,""]},"pyspark.ml.util.JavaMLWriter":{context:[2,2,1,""],overwrite:[2,2,1,""],save:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.JavaPredictionModel":{numFeatures:[2,3,1,""]},"pyspark.ml.util.MLReadable":{load:[2,4,1,""],read:[2,4,1,""]},"pyspark.ml.util.MLReader":{context:[2,2,1,""],load:[2,2,1,""],session:[2,2,1,""]},"pyspark.ml.util.MLWritable":{save:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.util.MLWriter":{context:[2,2,1,""],overwrite:[2,2,1,""],save:[2,2,1,""],session:[2,2,1,""]},"pyspark.mllib":{classification:[3,0,0,"-"],clustering:[3,0,0,"-"],evaluation:[3,0,0,"-"],feature:[3,0,0,"-"],fpm:[3,0,0,"-"],linalg:[3,0,0,"-"],random:[3,0,0,"-"],recommendation:[3,0,0,"-"],regression:[3,0,0,"-"],stat:[3,0,0,"-"],tree:[3,0,0,"-"],util:[3,0,0,"-"]},"pyspark.mllib.classification":{LogisticRegressionModel:[3,1,1,""],LogisticRegressionWithLBFGS:[3,1,1,""],LogisticRegressionWithSGD:[3,1,1,""],NaiveBayes:[3,1,1,""],NaiveBayesModel:[3,1,1,""],SVMModel:[3,1,1,""],SVMWithSG
 D:[3,1,1,""],StreamingLogisticRegressionWithSGD:[3,1,1,""]},"pyspark.mllib.classification.LogisticRegressionModel":{clearThreshold:[3,2,1,""],intercept:[3,3,1,""],load:[3,4,1,""],numClasses:[3,3,1,""],numFeatures:[3,3,1,""],predict:[3,2,1,""],save:[3,2,1,""],setThreshold:[3,2,1,""],threshold:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.classification.LogisticRegressionWithLBFGS":{train:[3,4,1,""]},"pyspark.mllib.classification.LogisticRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.classification.NaiveBayes":{train:[3,4,1,""]},"pyspark.mllib.classification.NaiveBayesModel":{load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.classification.SVMModel":{clearThreshold:[3,2,1,""],intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],setThreshold:[3,2,1,""],threshold:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.classification.SVMWithSGD":{train:[3,4,1,""]},"pyspark.mllib.classification.StreamingLogisticRegressionWithSGD":{latestModel:[3,2,1,""],pre
 dictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setInitialWeights:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.clustering":{BisectingKMeans:[3,1,1,""],BisectingKMeansModel:[3,1,1,""],GaussianMixture:[3,1,1,""],GaussianMixtureModel:[3,1,1,""],KMeans:[3,1,1,""],KMeansModel:[3,1,1,""],LDA:[3,1,1,""],LDAModel:[3,1,1,""],PowerIterationClustering:[3,1,1,""],PowerIterationClusteringModel:[3,1,1,""],StreamingKMeans:[3,1,1,""],StreamingKMeansModel:[3,1,1,""]},"pyspark.mllib.clustering.BisectingKMeans":{train:[3,4,1,""]},"pyspark.mllib.clustering.BisectingKMeansModel":{clusterCenters:[3,3,1,""],computeCost:[3,2,1,""],k:[3,3,1,""],predict:[3,2,1,""]},"pyspark.mllib.clustering.GaussianMixture":{train:[3,4,1,""]},"pyspark.mllib.clustering.GaussianMixtureModel":{gaussians:[3,3,1,""],k:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],predictSoft:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.clustering.KMeans":{train:[3,4,1,""]},"pyspark.mllib.clustering.KMeansModel":{clusterCenters:[3,3,1,""],computeCo
 st:[3,2,1,""],k:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.clustering.LDA":{train:[3,4,1,""]},"pyspark.mllib.clustering.LDAModel":{describeTopics:[3,2,1,""],load:[3,4,1,""],topicsMatrix:[3,2,1,""],vocabSize:[3,2,1,""]},"pyspark.mllib.clustering.PowerIterationClustering":{Assignment:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.clustering.PowerIterationClusteringModel":{assignments:[3,2,1,""],k:[3,3,1,""],load:[3,4,1,""]},"pyspark.mllib.clustering.StreamingKMeans":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setDecayFactor:[3,2,1,""],setHalfLife:[3,2,1,""],setInitialCenters:[3,2,1,""],setK:[3,2,1,""],setRandomCenters:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.clustering.StreamingKMeansModel":{clusterWeights:[3,3,1,""],update:[3,2,1,""]},"pyspark.mllib.evaluation":{BinaryClassificationMetrics:[3,1,1,""],MulticlassMetrics:[3,1,1,""],RankingMetrics:[3,1,1,""],RegressionMetrics:[3,1,1,""]},"pyspark.mllib.evaluation.BinaryClas
 sificationMetrics":{areaUnderPR:[3,3,1,""],areaUnderROC:[3,3,1,""],unpersist:[3,2,1,""]},"pyspark.mllib.evaluation.MulticlassMetrics":{accuracy:[3,3,1,""],confusionMatrix:[3,2,1,""],fMeasure:[3,2,1,""],falsePositiveRate:[3,2,1,""],precision:[3,2,1,""],recall:[3,2,1,""],truePositiveRate:[3,2,1,""],weightedFMeasure:[3,2,1,""],weightedFalsePositiveRate:[3,3,1,""],weightedPrecision:[3,3,1,""],weightedRecall:[3,3,1,""],weightedTruePositiveRate:[3,3,1,""]},"pyspark.mllib.evaluation.RankingMetrics":{meanAveragePrecision:[3,3,1,""],ndcgAt:[3,2,1,""],precisionAt:[3,2,1,""]},"pyspark.mllib.evaluation.RegressionMetrics":{explainedVariance:[3,3,1,""],meanAbsoluteError:[3,3,1,""],meanSquaredError:[3,3,1,""],r2:[3,3,1,""],rootMeanSquaredError:[3,3,1,""]},"pyspark.mllib.feature":{ChiSqSelector:[3,1,1,""],ChiSqSelectorModel:[3,1,1,""],ElementwiseProduct:[3,1,1,""],HashingTF:[3,1,1,""],IDF:[3,1,1,""],IDFModel:[3,1,1,""],Normalizer:[3,1,1,""],StandardScaler:[3,1,1,""],StandardScalerModel:[3,1,1,""],W
 ord2Vec:[3,1,1,""],Word2VecModel:[3,1,1,""]},"pyspark.mllib.feature.ChiSqSelector":{fit:[3,2,1,""],setFdr:[3,2,1,""],setFpr:[3,2,1,""],setFwe:[3,2,1,""],setNumTopFeatures:[3,2,1,""],setPercentile:[3,2,1,""],setSelectorType:[3,2,1,""]},"pyspark.mllib.feature.ChiSqSelectorModel":{transform:[3,2,1,""]},"pyspark.mllib.feature.ElementwisePr

<TRUNCATED>

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org

[6/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/rdd.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/rdd.html b/site/docs/2.2.1/api/python/_modules/pyspark/rdd.html
index ee22d01..17adf92 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/rdd.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/rdd.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.rdd &#8212; PySpark  documentation</title>
+    <title>pyspark.rdd &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -2560,7 +2560,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/serializers.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/serializers.html b/site/docs/2.2.1/api/python/_modules/pyspark/serializers.html
index 0b6fbd4..ad41bcc 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/serializers.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/serializers.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.serializers &#8212; PySpark  documentation</title>
+    <title>pyspark.serializers &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -669,7 +669,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/column.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/column.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/column.html
index 629944b..652476d 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/column.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/column.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.column &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.column &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -615,7 +615,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/context.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/context.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/context.html
index 5c5cc7a..18bd088 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/context.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/context.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.context &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.context &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -664,7 +664,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/dataframe.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/dataframe.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/dataframe.html
index 1b998c1..e6cd799 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/dataframe.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/dataframe.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.dataframe &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.dataframe &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1901,7 +1901,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/functions.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/functions.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/functions.html
index be7a6d6..5d30ceb 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/functions.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/functions.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.functions &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.functions &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -2073,7 +2073,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/group.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/group.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/group.html
index 93280d6..3191ab1 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/group.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/group.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.group &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.group &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -300,7 +300,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/readwriter.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/readwriter.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/readwriter.html
index ad7c2f3..3d5d739 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/readwriter.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/readwriter.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.readwriter &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.readwriter &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -926,7 +926,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/session.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/session.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/session.html
index 6401ebc..1487600 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/session.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/session.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.session &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.session &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -776,7 +776,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/streaming.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/streaming.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/streaming.html
index 23ab54d..9d1f341 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/streaming.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/streaming.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.streaming &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.streaming &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -953,7 +953,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/types.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/types.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/types.html
index 01b9f93..89bbe72 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/types.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/types.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.types &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.types &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1644,7 +1644,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/sql/window.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/sql/window.html b/site/docs/2.2.1/api/python/_modules/pyspark/sql/window.html
index 1962dbb..e53e10d 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/sql/window.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/sql/window.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql.window &#8212; PySpark  documentation</title>
+    <title>pyspark.sql.window &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -308,7 +308,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/status.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/status.html b/site/docs/2.2.1/api/python/_modules/pyspark/status.html
index cb68131..464cd63 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/status.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/status.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.status &#8212; PySpark  documentation</title>
+    <title>pyspark.status &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -167,7 +167,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/storagelevel.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/storagelevel.html b/site/docs/2.2.1/api/python/_modules/pyspark/storagelevel.html
index 08352d3..7b28354 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/storagelevel.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/storagelevel.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.storagelevel &#8212; PySpark  documentation</title>
+    <title>pyspark.storagelevel &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -142,7 +142,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/streaming/context.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/context.html b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/context.html
index 21a687f..57d3b40 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/context.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/context.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming.context &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming.context &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -441,7 +441,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/streaming/dstream.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/dstream.html b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/dstream.html
index d5b058e..d5f1e2e 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/dstream.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/dstream.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming.dstream &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming.dstream &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -716,7 +716,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/streaming/flume.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/flume.html b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/flume.html
index 5c88b3d..a452ed9 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/flume.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/flume.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming.flume &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming.flume &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -211,7 +211,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kafka.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kafka.html b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kafka.html
index e0e701f..ad3614f 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kafka.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kafka.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming.kafka &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming.kafka &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -506,7 +506,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kinesis.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kinesis.html b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kinesis.html
index 0c5a44a..3209bf5 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kinesis.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/kinesis.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming.kinesis &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming.kinesis &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -191,7 +191,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/streaming/listener.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/listener.html b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/listener.html
index 841cd96..1c2195e 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/streaming/listener.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/streaming/listener.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming.listener &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming.listener &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -146,7 +146,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/taskcontext.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/taskcontext.html b/site/docs/2.2.1/api/python/_modules/pyspark/taskcontext.html
index e14ba84..796a37e 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/taskcontext.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/taskcontext.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.taskcontext &#8212; PySpark  documentation</title>
+    <title>pyspark.taskcontext &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -161,7 +161,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/index.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/index.html b/site/docs/2.2.1/api/python/index.html
index 7282a51..87f2742 100644
--- a/site/docs/2.2.1/api/python/index.html
+++ b/site/docs/2.2.1/api/python/index.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>Welcome to Spark Python API Docs! &#8212; PySpark  documentation</title>
+    <title>Welcome to Spark Python API Docs! &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -35,7 +35,7 @@
           <a href="pyspark.html" title="pyspark package"
              accesskey="N">next</a></li>
     
-        <li class="nav-item nav-item-0"><a href="#">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="#">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>  
@@ -177,7 +177,7 @@
           <a href="pyspark.html" title="pyspark package"
              >next</a></li>
     
-        <li class="nav-item nav-item-0"><a href="#">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="#">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/pyspark.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/pyspark.html b/site/docs/2.2.1/api/python/pyspark.html
index d4dd36a..dc0baa5 100644
--- a/site/docs/2.2.1/api/python/pyspark.html
+++ b/site/docs/2.2.1/api/python/pyspark.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark package &#8212; PySpark  documentation</title>
+    <title>pyspark package &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -39,7 +39,7 @@
           <a href="index.html" title="Welcome to Spark Python API Docs!"
              accesskey="P">previous</a> |</li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>  
@@ -273,7 +273,7 @@ Its format depends on the scheduler implementation.</p>
 <li>in case of YARN something like ‘application_1433865536131_34483’</li>
 </ul>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sc</span><span class="o">.</span><span class="n">applicationId</span>  
-<span class="go">u&#39;local-...&#39;</span>
+<span class="go">&#39;local-...&#39;</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -752,7 +752,7 @@ Spark 1.2)</p>
 <span class="gp">... </span>   <span class="n">_</span> <span class="o">=</span> <span class="n">testFile</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">&quot;Hello world!&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">textFile</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[u&#39;Hello world!&#39;]</span>
+<span class="go">[&#39;Hello world!&#39;]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -775,10 +775,10 @@ serializer:</p>
 <span class="gp">... </span>   <span class="n">_</span> <span class="o">=</span> <span class="n">testFile</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">&quot;Hello&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">textFile</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[u&#39;Hello&#39;]</span>
+<span class="go">[&#39;Hello&#39;]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">parallelized</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="s2">&quot;World!&quot;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">union</span><span class="p">([</span><span class="n">textFile</span><span class="p">,</span> <span class="n">parallelized</span><span class="p">])</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[u&#39;Hello&#39;, &#39;World!&#39;]</span>
+<span class="go">[&#39;Hello&#39;, &#39;World!&#39;]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -828,7 +828,7 @@ fully in memory.</p>
 <span class="gp">... </span>   <span class="n">_</span> <span class="o">=</span> <span class="n">file2</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="s2">&quot;2&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">textFiles</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">wholeTextFiles</span><span class="p">(</span><span class="n">dirPath</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">textFiles</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[(u&#39;.../1.txt&#39;, u&#39;1&#39;), (u&#39;.../2.txt&#39;, u&#39;2&#39;)]</span>
+<span class="go">[(&#39;.../1.txt&#39;, &#39;1&#39;), (&#39;.../2.txt&#39;, &#39;2&#39;)]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -1693,7 +1693,7 @@ If no storage level is specified defaults to (<code class="xref py py-class docu
 <code class="descname">pipe</code><span class="sig-paren">(</span><em>command</em>, <em>env=None</em>, <em>checkCode=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/rdd.html#RDD.pipe"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.RDD.pipe" title="Permalink to this definition">¶</a></dt>
 <dd><p>Return an RDD created by piping elements to a forked external process.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="s1">&#39;1&#39;</span><span class="p">,</span> <span class="s1">&#39;2&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="s1">&#39;3&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">pipe</span><span class="p">(</span><span class="s1">&#39;cat&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[u&#39;1&#39;, u&#39;2&#39;, u&#39;&#39;, u&#39;3&#39;]</span>
+<span class="go">[&#39;1&#39;, &#39;2&#39;, &#39;&#39;, &#39;3&#39;]</span>
 </pre></div>
 </div>
 <table class="docutils field-list" frame="void" rules="none">
@@ -1808,7 +1808,7 @@ using <cite>coalesce</cite>, which can avoid performing a shuffle.</p>
 
 <dl class="method">
 <dt id="pyspark.RDD.repartitionAndSortWithinPartitions">
-<code class="descname">repartitionAndSortWithinPartitions</code><span class="sig-paren">(</span><em>numPartitions=None</em>, <em>partitionFunc=&lt;function portable_hash&gt;</em>, <em>ascending=True</em>, <em>keyfunc=&lt;function &lt;lambda&gt;&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/rdd.html#RDD.repartitionAndSortWithinPartitions"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.RDD.repartitionAndSortWithinPartitions" title="Permalink to this definition">¶</a></dt>
+<code class="descname">repartitionAndSortWithinPartitions</code><span class="sig-paren">(</span><em>numPartitions=None</em>, <em>partitionFunc=&lt;function portable_hash&gt;</em>, <em>ascending=True</em>, <em>keyfunc=&lt;function RDD.&lt;lambda&gt;&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/rdd.html#RDD.repartitionAndSortWithinPartitions"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.RDD.repartitionAndSortWithinPartitions" title="Permalink to this definition">¶</a></dt>
 <dd><p>Repartition the RDD according to the given partitioner and, within each resulting partition,
 sort records by their keys.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">5</span><span class="p">),</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">8</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">6</span><span class="p">),</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">8</span><span class="p">),</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">8</span><span class="p">),</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)])</span>
@@ -2098,7 +2098,7 @@ RDD’s key and value types. The mechanism is as follows:</p>
 <span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">fileinput</span> <span class="k">import</span> <span class="nb">input</span><span class="p">,</span> <span class="n">hook_compressed</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">result</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">(</span><span class="nb">input</span><span class="p">(</span><span class="n">glob</span><span class="p">(</span><span class="n">tempFile3</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;/part*.gz&quot;</span><span class="p">),</span> <span class="n">openhook</span><span class="o">=</span><span class="n">hook_compressed</span><span class="p">))</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="sa">b</span><span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">result</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">&#39;utf-8&#39;</span><span class="p">)</span>
-<span class="go">u&#39;bar\nfoo\n&#39;</span>
+<span class="go">&#39;bar\nfoo\n&#39;</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -2109,7 +2109,7 @@ RDD’s key and value types. The mechanism is as follows:</p>
 <dd><p>Assign a name to this RDD.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">rdd1</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">rdd1</span><span class="o">.</span><span class="n">setName</span><span class="p">(</span><span class="s1">&#39;RDD1&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">name</span><span class="p">()</span>
-<span class="go">u&#39;RDD1&#39;</span>
+<span class="go">&#39;RDD1&#39;</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -2129,7 +2129,7 @@ RDD’s key and value types. The mechanism is as follows:</p>
 
 <dl class="method">
 <dt id="pyspark.RDD.sortByKey">
-<code class="descname">sortByKey</code><span class="sig-paren">(</span><em>ascending=True</em>, <em>numPartitions=None</em>, <em>keyfunc=&lt;function &lt;lambda&gt;&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/rdd.html#RDD.sortByKey"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.RDD.sortByKey" title="Permalink to this definition">¶</a></dt>
+<code class="descname">sortByKey</code><span class="sig-paren">(</span><em>ascending=True</em>, <em>numPartitions=None</em>, <em>keyfunc=&lt;function RDD.&lt;lambda&gt;&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/rdd.html#RDD.sortByKey"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.RDD.sortByKey" title="Permalink to this definition">¶</a></dt>
 <dd><p>Sorts this RDD, which is assumed to consist of (key, value) pairs.
 # noqa</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">tmp</span> <span class="o">=</span> <span class="p">[(</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="p">(</span><span class="s1">&#39;b&#39;</span><span class="p">,</span> <span class="mi">2</span><span class="p">),</span> <span class="p">(</span><span class="s1">&#39;1&#39;</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span> <span class="p">(</span><span class="s1">&#39;d&#39;</span><span class="p">,</span> <span class="mi">4</span><span class="p">),</span> <span class="p">(</span><span class="s1">&#39;2&#39;</span><span class="p">,</span> <span class="mi">5</span><span class="p">)]</span>
@@ -2668,7 +2668,7 @@ not be as fast as more specialized serializers.</p>
 
 <dl class="method">
 <dt id="pyspark.PickleSerializer.loads">
-<code class="descname">loads</code><span class="sig-paren">(</span><em>obj</em>, <em>encoding=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/serializers.html#PickleSerializer.loads"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.PickleSerializer.loads" title="Permalink to this definition">¶</a></dt>
+<code class="descname">loads</code><span class="sig-paren">(</span><em>obj</em>, <em>encoding='bytes'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/serializers.html#PickleSerializer.loads"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.PickleSerializer.loads" title="Permalink to this definition">¶</a></dt>
 <dd></dd></dl>
 
 </dd></dl>
@@ -2925,7 +2925,7 @@ TaskAttemptID.</p>
           <a href="index.html" title="Welcome to Spark Python API Docs!"
              >previous</a> |</li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org

[7/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

Fix signature description broken in PySpark API documentation in 2.2.1


Project: http://git-wip-us.apache.org/repos/asf/spark-website/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark-website/commit/26b52712
Tree: http://git-wip-us.apache.org/repos/asf/spark-website/tree/26b52712
Diff: http://git-wip-us.apache.org/repos/asf/spark-website/diff/26b52712

Branch: refs/heads/asf-site
Commit: 26b5271279a72e7d78948abf96f69ea3a99db209
Parents: 8857572
Author: hyukjinkwon <gu...@apache.org>
Authored: Tue Jul 3 01:53:07 2018 +0800
Committer: hyukjinkwon <gu...@apache.org>
Committed: Wed Jul 4 12:40:02 2018 +0800

----------------------------------------------------------------------
 site/docs/2.2.1/api/python/_modules/index.html  |   8 +-
 .../python/_modules/pyspark/accumulators.html   |   8 +-
 .../api/python/_modules/pyspark/broadcast.html  |   8 +-
 .../2.2.1/api/python/_modules/pyspark/conf.html |   8 +-
 .../api/python/_modules/pyspark/context.html    |   8 +-
 .../api/python/_modules/pyspark/files.html      |   8 +-
 .../api/python/_modules/pyspark/ml/base.html    |   8 +-
 .../_modules/pyspark/ml/classification.html     |   8 +-
 .../python/_modules/pyspark/ml/clustering.html  |   8 +-
 .../python/_modules/pyspark/ml/evaluation.html  |   8 +-
 .../api/python/_modules/pyspark/ml/feature.html |   8 +-
 .../api/python/_modules/pyspark/ml/fpm.html     |   8 +-
 .../api/python/_modules/pyspark/ml/linalg.html  |   8 +-
 .../api/python/_modules/pyspark/ml/param.html   |   8 +-
 .../_modules/pyspark/ml/param/shared.html       |   8 +-
 .../python/_modules/pyspark/ml/pipeline.html    |   8 +-
 .../_modules/pyspark/ml/recommendation.html     |   8 +-
 .../python/_modules/pyspark/ml/regression.html  |   8 +-
 .../api/python/_modules/pyspark/ml/stat.html    |   8 +-
 .../api/python/_modules/pyspark/ml/tuning.html  |   8 +-
 .../api/python/_modules/pyspark/ml/util.html    |   8 +-
 .../api/python/_modules/pyspark/ml/wrapper.html |   8 +-
 .../_modules/pyspark/mllib/classification.html  |   8 +-
 .../_modules/pyspark/mllib/clustering.html      |   8 +-
 .../python/_modules/pyspark/mllib/common.html   |   8 +-
 .../_modules/pyspark/mllib/evaluation.html      |   8 +-
 .../python/_modules/pyspark/mllib/feature.html  |   8 +-
 .../api/python/_modules/pyspark/mllib/fpm.html  |   8 +-
 .../python/_modules/pyspark/mllib/linalg.html   |   8 +-
 .../pyspark/mllib/linalg/distributed.html       |   8 +-
 .../python/_modules/pyspark/mllib/random.html   |   8 +-
 .../_modules/pyspark/mllib/recommendation.html  |   8 +-
 .../_modules/pyspark/mllib/regression.html      |   8 +-
 .../pyspark/mllib/stat/KernelDensity.html       |   8 +-
 .../pyspark/mllib/stat/distribution.html        |   8 +-
 .../_modules/pyspark/mllib/stat/test.html       |   8 +-
 .../api/python/_modules/pyspark/mllib/tree.html |   8 +-
 .../api/python/_modules/pyspark/mllib/util.html |   8 +-
 .../api/python/_modules/pyspark/profiler.html   |   8 +-
 .../2.2.1/api/python/_modules/pyspark/rdd.html  |   8 +-
 .../python/_modules/pyspark/serializers.html    |   8 +-
 .../api/python/_modules/pyspark/sql/column.html |   8 +-
 .../python/_modules/pyspark/sql/context.html    |   8 +-
 .../python/_modules/pyspark/sql/dataframe.html  |   8 +-
 .../python/_modules/pyspark/sql/functions.html  |   8 +-
 .../api/python/_modules/pyspark/sql/group.html  |   8 +-
 .../python/_modules/pyspark/sql/readwriter.html |   8 +-
 .../python/_modules/pyspark/sql/session.html    |   8 +-
 .../python/_modules/pyspark/sql/streaming.html  |   8 +-
 .../api/python/_modules/pyspark/sql/types.html  |   8 +-
 .../api/python/_modules/pyspark/sql/window.html |   8 +-
 .../api/python/_modules/pyspark/status.html     |   8 +-
 .../python/_modules/pyspark/storagelevel.html   |   8 +-
 .../_modules/pyspark/streaming/context.html     |   8 +-
 .../_modules/pyspark/streaming/dstream.html     |   8 +-
 .../_modules/pyspark/streaming/flume.html       |   8 +-
 .../_modules/pyspark/streaming/kafka.html       |   8 +-
 .../_modules/pyspark/streaming/kinesis.html     |   8 +-
 .../_modules/pyspark/streaming/listener.html    |   8 +-
 .../python/_modules/pyspark/taskcontext.html    |   8 +-
 site/docs/2.2.1/api/python/index.html           |   8 +-
 site/docs/2.2.1/api/python/pyspark.html         |  30 +-
 site/docs/2.2.1/api/python/pyspark.ml.html      | 164 +++++------
 site/docs/2.2.1/api/python/pyspark.mllib.html   |  36 +--
 site/docs/2.2.1/api/python/pyspark.sql.html     | 272 +++++++++----------
 .../2.2.1/api/python/pyspark.streaming.html     |  11 +-
 site/docs/2.2.1/api/python/search.html          |   8 +-
 site/docs/2.2.1/api/python/searchindex.js       |   2 +-
 68 files changed, 506 insertions(+), 505 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/index.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/index.html b/site/docs/2.2.1/api/python/_modules/index.html
index 6324538..e4360a8 100644
--- a/site/docs/2.2.1/api/python/_modules/index.html
+++ b/site/docs/2.2.1/api/python/_modules/index.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>Overview: module code &#8212; PySpark  documentation</title>
+    <title>Overview: module code &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>  
@@ -130,7 +130,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/accumulators.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/accumulators.html b/site/docs/2.2.1/api/python/_modules/pyspark/accumulators.html
index 760cdeb..d757988 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/accumulators.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/accumulators.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.accumulators &#8212; PySpark  documentation</title>
+    <title>pyspark.accumulators &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -340,7 +340,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/broadcast.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/broadcast.html b/site/docs/2.2.1/api/python/_modules/pyspark/broadcast.html
index ccc1941..52afa92 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/broadcast.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/broadcast.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.broadcast &#8212; PySpark  documentation</title>
+    <title>pyspark.broadcast &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -236,7 +236,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/conf.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/conf.html b/site/docs/2.2.1/api/python/_modules/pyspark/conf.html
index 0e7d896..9d1505a 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/conf.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/conf.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.conf &#8212; PySpark  documentation</title>
+    <title>pyspark.conf &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -295,7 +295,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/context.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/context.html b/site/docs/2.2.1/api/python/_modules/pyspark/context.html
index 0e60fbf..9b8e446 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/context.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/context.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.context &#8212; PySpark  documentation</title>
+    <title>pyspark.context &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1104,7 +1104,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/files.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/files.html b/site/docs/2.2.1/api/python/_modules/pyspark/files.html
index a19e179..2f53fc7 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/files.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/files.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.files &#8212; PySpark  documentation</title>
+    <title>pyspark.files &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -130,7 +130,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/base.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/base.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/base.html
index aadc915..5a01f5b 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/base.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/base.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.base &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.base &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -189,7 +189,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/classification.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/classification.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/classification.html
index 3658eb1..c06cc50 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/classification.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/classification.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.classification &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.classification &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1895,7 +1895,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/clustering.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/clustering.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/clustering.html
index c20cd0c..cfede87 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/clustering.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/clustering.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.clustering &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.clustering &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1227,7 +1227,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/evaluation.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/evaluation.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/evaluation.html
index 6ee3ab2..cfb4af2 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/evaluation.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/evaluation.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.evaluation &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.evaluation &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -427,7 +427,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/feature.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/feature.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/feature.html
index 494508e..b30cc69 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/feature.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/feature.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.feature &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.feature &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -3415,7 +3415,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/fpm.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/fpm.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/fpm.html
index 9e92426..3182693 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/fpm.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/fpm.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.fpm &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.fpm &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -316,7 +316,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/linalg.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/linalg.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/linalg.html
index b2e47d4..a3fc2da 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/linalg.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/linalg.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.linalg &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.linalg &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1235,7 +1235,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/param.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/param.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/param.html
index e46000e..800eb92 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/param.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/param.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.param &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.param &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -562,7 +562,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/param/shared.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/param/shared.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/param/shared.html
index 3c78413..3d32a9d 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/param/shared.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/param/shared.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.param.shared &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.param.shared &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li>
           <li class="nav-item nav-item-2"><a href="../param.html" accesskey="U">pyspark.ml.param</a> &#187;</li> 
@@ -770,7 +770,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li>
           <li class="nav-item nav-item-2"><a href="../param.html" >pyspark.ml.param</a> &#187;</li> 

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/pipeline.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/pipeline.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/pipeline.html
index 3a71e08..53074cc 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/pipeline.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/pipeline.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.pipeline &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.pipeline &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -325,7 +325,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/recommendation.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/recommendation.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/recommendation.html
index 907c3bb..f9bc4a6 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/recommendation.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/recommendation.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.recommendation &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.recommendation &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -516,7 +516,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/regression.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/regression.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/regression.html
index 9dbc411..1033ed1 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/regression.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/regression.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.regression &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.regression &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1820,7 +1820,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/stat.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/stat.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/stat.html
index cd0bb65..aec0f1b 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/stat.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/stat.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.stat &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.stat &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -225,7 +225,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/tuning.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/tuning.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/tuning.html
index 640aa6a..afc60eb 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/tuning.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/tuning.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.tuning &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.tuning &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -549,7 +549,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/util.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/util.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/util.html
index 39446cb..5948a53 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/util.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/util.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.util &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.util &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -356,7 +356,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/ml/wrapper.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/ml/wrapper.html b/site/docs/2.2.1/api/python/_modules/pyspark/ml/wrapper.html
index 5a3ee58..dacc35f 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/ml/wrapper.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/ml/wrapper.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml.wrapper &#8212; PySpark  documentation</title>
+    <title>pyspark.ml.wrapper &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -381,7 +381,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/classification.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/classification.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/classification.html
index ea274cc..1098c1e 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/classification.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/classification.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.classification &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.classification &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -838,7 +838,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/clustering.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/clustering.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/clustering.html
index afb4722..d9290d2 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/clustering.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/clustering.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.clustering &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.clustering &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1126,7 +1126,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/common.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/common.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/common.html
index 5a5cfbf..20ec4bb 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/common.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/common.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.common &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.common &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -234,7 +234,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/evaluation.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/evaluation.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/evaluation.html
index 087be7a..f8e9aaf 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/evaluation.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/evaluation.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.evaluation &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.evaluation &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -620,7 +620,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/feature.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/feature.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/feature.html
index 3ec122c..b83ccef 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/feature.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/feature.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.feature &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.feature &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -897,7 +897,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/fpm.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/fpm.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/fpm.html
index 280493c..79c85c4 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/fpm.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/fpm.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.fpm &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.fpm &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -275,7 +275,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg.html
index 3b05643..6efadb6 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.linalg &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.linalg &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -1447,7 +1447,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg/distributed.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg/distributed.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg/distributed.html
index 88425fb..04a9f01 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg/distributed.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/linalg/distributed.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.linalg.distributed &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.linalg.distributed &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li>
           <li class="nav-item nav-item-2"><a href="../linalg.html" accesskey="U">pyspark.mllib.linalg</a> &#187;</li> 
@@ -1455,7 +1455,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li>
           <li class="nav-item nav-item-2"><a href="../linalg.html" >pyspark.mllib.linalg</a> &#187;</li> 

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/random.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/random.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/random.html
index 4618fdf..30ff31c 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/random.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/random.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.random &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.random &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -499,7 +499,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/recommendation.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/recommendation.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/recommendation.html
index a172234..4b3810c 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/recommendation.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/recommendation.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.recommendation &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.recommendation &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -404,7 +404,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/regression.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/regression.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/regression.html
index 64f1484..88dca75 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/regression.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/regression.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.regression &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.regression &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -912,7 +912,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/KernelDensity.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/KernelDensity.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/KernelDensity.html
index cb16ea5..05d02c0 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/KernelDensity.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/KernelDensity.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.stat.KernelDensity &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.stat.KernelDensity &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -130,7 +130,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/distribution.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/distribution.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/distribution.html
index 8f0a208..aeeb95b 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/distribution.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/distribution.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.stat.distribution &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.stat.distribution &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -103,7 +103,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/test.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/test.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/test.html
index ac64b34..e9ffd37 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/test.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/stat/test.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.stat.test &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.stat.test &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -153,7 +153,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/tree.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/tree.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/tree.html
index 3ee3b89..65be092 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/tree.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/tree.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.tree &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.tree &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -731,7 +731,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/mllib/util.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/util.html b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/util.html
index 3eb77a3..358a5a3 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/mllib/util.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/mllib/util.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib.util &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib.util &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -599,7 +599,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/_modules/pyspark/profiler.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/_modules/pyspark/profiler.html b/site/docs/2.2.1/api/python/_modules/pyspark/profiler.html
index 5dc090b..ff5034e 100644
--- a/site/docs/2.2.1/api/python/_modules/pyspark/profiler.html
+++ b/site/docs/2.2.1/api/python/_modules/pyspark/profiler.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.profiler &#8212; PySpark  documentation</title>
+    <title>pyspark.profiler &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="../../_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="../../_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../../',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -31,7 +31,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li> 
       </ul>
@@ -247,7 +247,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="../../index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="../index.html" >Module code</a> &#187;</li> 
       </ul>


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org

[4/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/pyspark.mllib.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/pyspark.mllib.html b/site/docs/2.2.1/api/python/pyspark.mllib.html
index cd27d38..baf0804 100644
--- a/site/docs/2.2.1/api/python/pyspark.mllib.html
+++ b/site/docs/2.2.1/api/python/pyspark.mllib.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.mllib package &#8212; PySpark  documentation</title>
+    <title>pyspark.mllib package &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -35,7 +35,7 @@
           <a href="pyspark.ml.html" title="pyspark.ml package"
              accesskey="P">previous</a></li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="pyspark.html" accesskey="U">pyspark package</a> &#187;</li> 
       </ul>
@@ -2633,7 +2633,7 @@ Compositionality.</p>
 <p>Querying for synonyms of a word will not return that word:</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">syms</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">syms</span><span class="p">]</span>
-<span class="go">[u&#39;b&#39;, u&#39;c&#39;]</span>
+<span class="go">[&#39;b&#39;, &#39;c&#39;]</span>
 </pre></div>
 </div>
 <p>But querying for synonyms of a vector may return the word whose
@@ -2641,7 +2641,7 @@ representation is that vector:</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">vec</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">syms</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="n">vec</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">syms</span><span class="p">]</span>
-<span class="go">[u&#39;a&#39;, u&#39;b&#39;]</span>
+<span class="go">[&#39;a&#39;, &#39;b&#39;]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">os</span><span class="o">,</span> <span class="nn">tempfile</span>
@@ -2652,7 +2652,7 @@ representation is that vector:</p>
 <span class="go">True</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">syms</span> <span class="o">=</span> <span class="n">sameModel</span><span class="o">.</span><span class="n">findSynonyms</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">syms</span><span class="p">]</span>
-<span class="go">[u&#39;b&#39;, u&#39;c&#39;]</span>
+<span class="go">[&#39;b&#39;, &#39;c&#39;]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">shutil</span> <span class="k">import</span> <span class="n">rmtree</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="k">try</span><span class="p">:</span>
 <span class="gp">... </span>    <span class="n">rmtree</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
@@ -3073,7 +3073,7 @@ using the Parallel FP-Growth algorithm.</p>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">model</span> <span class="o">=</span> <span class="n">FPGrowth</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="mf">0.6</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">freqItemsets</span><span class="p">()</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[FreqItemset(items=[u&#39;a&#39;], freq=4), FreqItemset(items=[u&#39;c&#39;], freq=3), ...</span>
+<span class="go">[FreqItemset(items=[&#39;a&#39;], freq=4), FreqItemset(items=[&#39;c&#39;], freq=3), ...</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">model_path</span> <span class="o">=</span> <span class="n">temp_path</span> <span class="o">+</span> <span class="s2">&quot;/fpm&quot;</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">model_path</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sameModel</span> <span class="o">=</span> <span class="n">FPGrowthModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">model_path</span><span class="p">)</span>
@@ -3171,7 +3171,7 @@ another iteration of distributed prefix growth is run.
 <span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">model</span> <span class="o">=</span> <span class="n">PrefixSpan</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">freqSequences</span><span class="p">()</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[FreqSequence(sequence=[[u&#39;a&#39;]], freq=3), FreqSequence(sequence=[[u&#39;a&#39;], [u&#39;a&#39;]], freq=1), ...</span>
+<span class="go">[FreqSequence(sequence=[[&#39;a&#39;]], freq=3), FreqSequence(sequence=[[&#39;a&#39;], [&#39;a&#39;]], freq=1), ...</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -5178,7 +5178,7 @@ distribution with the input mean.</p>
 
 <dl class="staticmethod">
 <dt id="pyspark.mllib.random.RandomRDDs.exponentialVectorRDD">
-<em class="property">static </em><code class="descname">exponentialVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>*a</em>, <em>**kw</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.exponentialVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.exponentialVectorRDD" title="Permalink to this definition">¶</a></dt>
+<em class="property">static </em><code class="descname">exponentialVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>mean</em>, <em>numRows</em>, <em>numCols</em>, <em>numPartitions=None</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.exponentialVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.exponentialVectorRDD" title="Permalink to this definition">¶</a></dt>
 <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the Exponential distribution with the input mean.</p>
 <table class="docutils field-list" frame="void" rules="none">
@@ -5264,7 +5264,7 @@ distribution with the input shape and scale.</p>
 
 <dl class="staticmethod">
 <dt id="pyspark.mllib.random.RandomRDDs.gammaVectorRDD">
-<em class="property">static </em><code class="descname">gammaVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>*a</em>, <em>**kw</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.gammaVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.gammaVectorRDD" title="Permalink to this definition">¶</a></dt>
+<em class="property">static </em><code class="descname">gammaVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>shape</em>, <em>scale</em>, <em>numRows</em>, <em>numCols</em>, <em>numPartitions=None</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.gammaVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.gammaVectorRDD" title="Permalink to this definition">¶</a></dt>
 <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the Gamma distribution.</p>
 <table class="docutils field-list" frame="void" rules="none">
@@ -5354,7 +5354,7 @@ distribution with the input mean and standard distribution.</p>
 
 <dl class="staticmethod">
 <dt id="pyspark.mllib.random.RandomRDDs.logNormalVectorRDD">
-<em class="property">static </em><code class="descname">logNormalVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>*a</em>, <em>**kw</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.logNormalVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.logNormalVectorRDD" title="Permalink to this definition">¶</a></dt>
+<em class="property">static </em><code class="descname">logNormalVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>mean</em>, <em>std</em>, <em>numRows</em>, <em>numCols</em>, <em>numPartitions=None</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.logNormalVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.logNormalVectorRDD" title="Permalink to this definition">¶</a></dt>
 <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the log normal distribution.</p>
 <table class="docutils field-list" frame="void" rules="none">
@@ -5440,7 +5440,7 @@ to some other normal N(mean, sigma^2), use
 
 <dl class="staticmethod">
 <dt id="pyspark.mllib.random.RandomRDDs.normalVectorRDD">
-<em class="property">static </em><code class="descname">normalVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>*a</em>, <em>**kw</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.normalVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.normalVectorRDD" title="Permalink to this definition">¶</a></dt>
+<em class="property">static </em><code class="descname">normalVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>numRows</em>, <em>numCols</em>, <em>numPartitions=None</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.normalVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.normalVectorRDD" title="Permalink to this definition">¶</a></dt>
 <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the standard normal distribution.</p>
 <table class="docutils field-list" frame="void" rules="none">
@@ -5518,7 +5518,7 @@ distribution with the input mean.</p>
 
 <dl class="staticmethod">
 <dt id="pyspark.mllib.random.RandomRDDs.poissonVectorRDD">
-<em class="property">static </em><code class="descname">poissonVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>*a</em>, <em>**kw</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.poissonVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.poissonVectorRDD" title="Permalink to this definition">¶</a></dt>
+<em class="property">static </em><code class="descname">poissonVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>mean</em>, <em>numRows</em>, <em>numCols</em>, <em>numPartitions=None</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.poissonVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.poissonVectorRDD" title="Permalink to this definition">¶</a></dt>
 <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the Poisson distribution with the input mean.</p>
 <table class="docutils field-list" frame="void" rules="none">
@@ -5602,7 +5602,7 @@ to U(a, b), use
 
 <dl class="staticmethod">
 <dt id="pyspark.mllib.random.RandomRDDs.uniformVectorRDD">
-<em class="property">static </em><code class="descname">uniformVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>*a</em>, <em>**kw</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.uniformVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.uniformVectorRDD" title="Permalink to this definition">¶</a></dt>
+<em class="property">static </em><code class="descname">uniformVectorRDD</code><span class="sig-paren">(</span><em>sc</em>, <em>numRows</em>, <em>numCols</em>, <em>numPartitions=None</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/mllib/random.html#RandomRDDs.uniformVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.uniformVectorRDD" title="Permalink to this definition">¶</a></dt>
 <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn
 from the uniform distribution U(0.0, 1.0).</p>
 <table class="docutils field-list" frame="void" rules="none">
@@ -6873,9 +6873,9 @@ of freedom, p-value, the method used, and the null hypothesis.</p>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">pearson</span><span class="o">.</span><span class="n">pValue</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span>
 <span class="go">0.8187</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">pearson</span><span class="o">.</span><span class="n">method</span>
-<span class="go">u&#39;pearson&#39;</span>
+<span class="go">&#39;pearson&#39;</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">pearson</span><span class="o">.</span><span class="n">nullHypothesis</span>
-<span class="go">u&#39;observed follows the same distribution as expected.&#39;</span>
+<span class="go">&#39;observed follows the same distribution as expected.&#39;</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">observed</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">21</span><span class="p">,</span> <span class="mi">38</span><span class="p">,</span> <span class="mi">43</span><span class="p">,</span> <span class="mi">80</span><span class="p">])</span>
@@ -7055,7 +7055,7 @@ the method used, and the null hypothesis.</p>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">ksmodel</span><span class="o">.</span><span class="n">statistic</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
 <span class="go">0.175</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ksmodel</span><span class="o">.</span><span class="n">nullHypothesis</span>
-<span class="go">u&#39;Sample follows theoretical distribution&#39;</span>
+<span class="go">&#39;Sample follows theoretical distribution&#39;</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="mf">2.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">,</span> <span class="mf">4.0</span><span class="p">])</span>
@@ -8453,7 +8453,7 @@ this method throws an exception.</li>
           <a href="pyspark.ml.html" title="pyspark.ml package"
              >previous</a></li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="pyspark.html" >pyspark package</a> &#187;</li> 
       </ul>


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org

[3/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/pyspark.sql.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/pyspark.sql.html b/site/docs/2.2.1/api/python/pyspark.sql.html
index 8b349cc..2174c25 100644
--- a/site/docs/2.2.1/api/python/pyspark.sql.html
+++ b/site/docs/2.2.1/api/python/pyspark.sql.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.sql module &#8212; PySpark  documentation</title>
+    <title>pyspark.sql module &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -39,7 +39,7 @@
           <a href="pyspark.html" title="pyspark package"
              accesskey="P">previous</a> |</li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="pyspark.html" accesskey="U">pyspark package</a> &#187;</li> 
       </ul>
@@ -280,22 +280,22 @@ omit the <code class="docutils literal"><span class="pre">struct&lt;&gt;</span><
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">l</span> <span class="o">=</span> <span class="p">[(</span><span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">l</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(_1=u&#39;Alice&#39;, _2=1)]</span>
+<span class="go">[Row(_1=&#39;Alice&#39;, _2=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">l</span><span class="p">,</span> <span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">d</span> <span class="o">=</span> <span class="p">[{</span><span class="s1">&#39;name&#39;</span><span class="p">:</span> <span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">}]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=1, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=1, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">l</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(_1=u&#39;Alice&#39;, _2=1)]</span>
+<span class="go">[Row(_1=&#39;Alice&#39;, _2=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="k">import</span> <span class="n">Row</span>
@@ -303,7 +303,7 @@ omit the <code class="docutils literal"><span class="pre">struct&lt;&gt;</span><
 <span class="gp">&gt;&gt;&gt; </span><span class="n">person</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">r</span><span class="p">:</span> <span class="n">Person</span><span class="p">(</span><span class="o">*</span><span class="n">r</span><span class="p">))</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">person</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="k">import</span> <span class="o">*</span>
@@ -312,17 +312,17 @@ omit the <code class="docutils literal"><span class="pre">struct&lt;&gt;</span><
 <span class="gp">... </span>   <span class="n">StructField</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">True</span><span class="p">)])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df3</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df3</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">toPandas</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>  
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">([[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">]]))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>  
 <span class="go">[Row(0=1, 1=2)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="s2">&quot;a: string, b: int&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(a=u&#39;Alice&#39;, b=1)]</span>
+<span class="go">[Row(a=&#39;Alice&#39;, b=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">row</span><span class="p">:</span> <span class="n">row</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="s2">&quot;int&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
 <span class="go">[Row(value=1)]</span>
@@ -449,7 +449,7 @@ as a streaming <a class="reference internal" href="#pyspark.sql.DataFrame" title
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">createOrReplaceTempView</span><span class="p">(</span><span class="s2">&quot;table1&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="s2">&quot;SELECT field1 AS f1, field2 as f2 from table1&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(f1=1, f2=u&#39;row1&#39;), Row(f1=2, f2=u&#39;row2&#39;), Row(f1=3, f2=u&#39;row3&#39;)]</span>
+<span class="go">[Row(f1=1, f2=&#39;row1&#39;), Row(f1=2, f2=&#39;row2&#39;), Row(f1=3, f2=&#39;row3&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -630,22 +630,22 @@ If it’s not a <a class="reference internal" href="#pyspark.sql.types.StructTyp
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">l</span> <span class="o">=</span> <span class="p">[(</span><span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">l</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(_1=u&#39;Alice&#39;, _2=1)]</span>
+<span class="go">[Row(_1=&#39;Alice&#39;, _2=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">l</span><span class="p">,</span> <span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">d</span> <span class="o">=</span> <span class="p">[{</span><span class="s1">&#39;name&#39;</span><span class="p">:</span> <span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">}]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=1, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=1, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">l</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(_1=u&#39;Alice&#39;, _2=1)]</span>
+<span class="go">[Row(_1=&#39;Alice&#39;, _2=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="k">import</span> <span class="n">Row</span>
@@ -653,7 +653,7 @@ If it’s not a <a class="reference internal" href="#pyspark.sql.types.StructTyp
 <span class="gp">&gt;&gt;&gt; </span><span class="n">person</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">r</span><span class="p">:</span> <span class="n">Person</span><span class="p">(</span><span class="o">*</span><span class="n">r</span><span class="p">))</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">person</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="k">import</span> <span class="o">*</span>
@@ -662,17 +662,17 @@ If it’s not a <a class="reference internal" href="#pyspark.sql.types.StructTyp
 <span class="gp">... </span>   <span class="n">StructField</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">True</span><span class="p">)])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df3</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df3</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">toPandas</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>  
-<span class="go">[Row(name=u&#39;Alice&#39;, age=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">([[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">]]))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>  
 <span class="go">[Row(0=1, 1=2)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="s2">&quot;a: string, b: int&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(a=u&#39;Alice&#39;, b=1)]</span>
+<span class="go">[Row(a=&#39;Alice&#39;, b=1)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">row</span><span class="p">:</span> <span class="n">row</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="s2">&quot;int&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
 <span class="go">[Row(value=1)]</span>
@@ -731,12 +731,12 @@ created external table.</p>
 defaultValue. If the key is not set and defaultValue is None, return
 the system default value.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">getConf</span><span class="p">(</span><span class="s2">&quot;spark.sql.shuffle.partitions&quot;</span><span class="p">)</span>
-<span class="go">u&#39;200&#39;</span>
+<span class="go">&#39;200&#39;</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">getConf</span><span class="p">(</span><span class="s2">&quot;spark.sql.shuffle.partitions&quot;</span><span class="p">,</span> <span class="sa">u</span><span class="s2">&quot;10&quot;</span><span class="p">)</span>
-<span class="go">u&#39;10&#39;</span>
+<span class="go">&#39;10&#39;</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">setConf</span><span class="p">(</span><span class="s2">&quot;spark.sql.shuffle.partitions&quot;</span><span class="p">,</span> <span class="sa">u</span><span class="s2">&quot;50&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">getConf</span><span class="p">(</span><span class="s2">&quot;spark.sql.shuffle.partitions&quot;</span><span class="p">,</span> <span class="sa">u</span><span class="s2">&quot;10&quot;</span><span class="p">)</span>
-<span class="go">u&#39;50&#39;</span>
+<span class="go">&#39;50&#39;</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -890,7 +890,7 @@ be done.  For any other return type, the produced object must match the specifie
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">registerFunction</span><span class="p">(</span><span class="s2">&quot;stringLengthString&quot;</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="s2">&quot;SELECT stringLengthString(&#39;test&#39;)&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(stringLengthString(test)=u&#39;4&#39;)]</span>
+<span class="go">[Row(stringLengthString(test)=&#39;4&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="k">import</span> <span class="n">IntegerType</span>
@@ -958,7 +958,7 @@ When the return type is not specified we would infer it via reflection.
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">registerDataFrameAsTable</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="s2">&quot;table1&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="s2">&quot;SELECT field1 AS f1, field2 as f2 from table1&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(f1=1, f2=u&#39;row1&#39;), Row(f1=2, f2=u&#39;row2&#39;), Row(f1=3, f2=u&#39;row3&#39;)]</span>
+<span class="go">[Row(f1=1, f2=&#39;row1&#39;), Row(f1=2, f2=&#39;row2&#39;), Row(f1=3, f2=&#39;row3&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1049,7 +1049,7 @@ When the return type is not specified we would infer it via reflection.
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">registerDataFrameAsTable</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="s2">&quot;table1&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">tables</span><span class="p">()</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="s2">&quot;tableName = &#39;table1&#39;&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">first</span><span class="p">()</span>
-<span class="go">Row(database=u&#39;&#39;, tableName=u&#39;table1&#39;, isTemporary=True)</span>
+<span class="go">Row(database=&#39;&#39;, tableName=&#39;table1&#39;, isTemporary=True)</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1147,7 +1147,7 @@ be done.  For any other return type, the produced object must match the specifie
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">registerFunction</span><span class="p">(</span><span class="s2">&quot;stringLengthString&quot;</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sqlContext</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="s2">&quot;SELECT stringLengthString(&#39;test&#39;)&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(stringLengthString(test)=u&#39;4&#39;)]</span>
+<span class="go">[Row(stringLengthString(test)=&#39;4&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="k">import</span> <span class="n">IntegerType</span>
@@ -1222,7 +1222,7 @@ and can be created using various functions in <a class="reference internal" href
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df_as2</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">&quot;df_as2&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">joined_df</span> <span class="o">=</span> <span class="n">df_as1</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df_as2</span><span class="p">,</span> <span class="n">col</span><span class="p">(</span><span class="s2">&quot;df_as1.name&quot;</span><span class="p">)</span> <span class="o">==</span> <span class="n">col</span><span class="p">(</span><span class="s2">&quot;df_as2.name&quot;</span><span class="p">),</span> <span class="s1">&#39;inner&#39;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">joined_df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s2">&quot;df_as1.name&quot;</span><span class="p">,</span> <span class="s2">&quot;df_as2.name&quot;</span><span class="p">,</span> <span class="s2">&quot;df_as2.age&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Bob&#39;, name=u&#39;Bob&#39;, age=5), Row(name=u&#39;Alice&#39;, name=u&#39;Alice&#39;, age=2)]</span>
+<span class="go">[Row(name=&#39;Bob&#39;, name=&#39;Bob&#39;, age=5), Row(name=&#39;Alice&#39;, name=&#39;Alice&#39;, age=2)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1349,7 +1349,7 @@ the current partitioning is).</p>
 <code class="descname">collect</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/dataframe.html#DataFrame.collect"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.DataFrame.collect" title="Permalink to this definition">¶</a></dt>
 <dd><p>Returns all the records as a list of <a class="reference internal" href="#pyspark.sql.Row" title="pyspark.sql.Row"><code class="xref py py-class docutils literal"><span class="pre">Row</span></code></a>.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1528,12 +1528,12 @@ catalog.</p>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="s2">&quot;name&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s2">&quot;name&quot;</span><span class="p">,</span> <span class="s2">&quot;height&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Tom&#39;, height=80), Row(name=u&#39;Bob&#39;, height=85)]</span>
+<span class="go">[Row(name=&#39;Tom&#39;, height=80), Row(name=&#39;Bob&#39;, height=85)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">crossJoin</span><span class="p">(</span><span class="n">df2</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s2">&quot;height&quot;</span><span class="p">))</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="s2">&quot;name&quot;</span><span class="p">,</span> <span class="s2">&quot;height&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;, height=80), Row(age=2, name=u&#39;Alice&#39;, height=85),</span>
-<span class="go"> Row(age=5, name=u&#39;Bob&#39;, height=80), Row(age=5, name=u&#39;Bob&#39;, height=85)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;, height=80), Row(age=2, name=&#39;Alice&#39;, height=85),</span>
+<span class="go"> Row(age=5, name=&#39;Bob&#39;, height=80), Row(age=5, name=&#39;Bob&#39;, height=85)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1660,23 +1660,23 @@ This is a no-op if schema doesn’t contain the given column name(s).</p>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="s1">&#39;age&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;), Row(name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;), Row(name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;), Row(name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;), Row(name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="n">df2</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="s1">&#39;inner&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, height=85, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=5, height=85, name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="n">df2</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="s1">&#39;inner&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="n">df2</span><span class="o">.</span><span class="n">name</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;, height=85)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;, height=85)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;inner&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="s1">&#39;age&#39;</span><span class="p">,</span> <span class="s1">&#39;height&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1878,15 +1878,15 @@ or a string of SQL expression.</td>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span> <span class="o">&gt;</span> <span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span> <span class="o">==</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="s2">&quot;age &gt; 3&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="s2">&quot;age = 2&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1899,7 +1899,7 @@ or a string of SQL expression.</td>
 <code class="descname">first</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/dataframe.html#DataFrame.first"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.DataFrame.first" title="Permalink to this definition">¶</a></dt>
 <dd><p>Returns the first row as a <a class="reference internal" href="#pyspark.sql.Row" title="pyspark.sql.Row"><code class="xref py py-class docutils literal"><span class="pre">Row</span></code></a>.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">first</span><span class="p">()</span>
-<span class="go">Row(age=2, name=u&#39;Alice&#39;)</span>
+<span class="go">Row(age=2, name=&#39;Alice&#39;)</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -1988,11 +1988,11 @@ Each element should be a column name (string) or an expression (<a class="refere
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">()</span><span class="o">.</span><span class="n">avg</span><span class="p">()</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
 <span class="go">[Row(avg(age)=3.5)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="s1">&#39;name&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">agg</span><span class="p">({</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="s1">&#39;mean&#39;</span><span class="p">})</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, avg(age)=2.0), Row(name=u&#39;Bob&#39;, avg(age)=5.0)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, avg(age)=2.0), Row(name=&#39;Bob&#39;, avg(age)=5.0)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">)</span><span class="o">.</span><span class="n">avg</span><span class="p">()</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, avg(age)=2.0), Row(name=u&#39;Bob&#39;, avg(age)=5.0)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, avg(age)=2.0), Row(name=&#39;Bob&#39;, avg(age)=5.0)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">([</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="p">])</span><span class="o">.</span><span class="n">count</span><span class="p">()</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=2, count=1), Row(name=u&#39;Bob&#39;, age=5, count=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=2, count=1), Row(name=&#39;Bob&#39;, age=5, count=1)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2030,9 +2030,9 @@ If n is 1, return a single Row.</td>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(age=2, name=u&#39;Alice&#39;)</span>
+<span class="go">Row(age=2, name=&#39;Alice&#39;)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">head</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2135,24 +2135,24 @@ the column(s) must exist on both sides, and this performs an equi-join.</li>
 </table>
 <p>The following performs a full outer join between <code class="docutils literal"><span class="pre">df1</span></code> and <code class="docutils literal"><span class="pre">df2</span></code>.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="n">df2</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="s1">&#39;outer&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">df2</span><span class="o">.</span><span class="n">height</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=None, height=80), Row(name=u&#39;Bob&#39;, height=85), Row(name=u&#39;Alice&#39;, height=None)]</span>
+<span class="go">[Row(name=None, height=80), Row(name=&#39;Bob&#39;, height=85), Row(name=&#39;Alice&#39;, height=None)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;outer&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;height&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Tom&#39;, height=80), Row(name=u&#39;Bob&#39;, height=85), Row(name=u&#39;Alice&#39;, height=None)]</span>
+<span class="go">[Row(name=&#39;Tom&#39;, height=80), Row(name=&#39;Bob&#39;, height=85), Row(name=&#39;Alice&#39;, height=None)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">cond</span> <span class="o">=</span> <span class="p">[</span><span class="n">df</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="n">df3</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">age</span> <span class="o">==</span> <span class="n">df3</span><span class="o">.</span><span class="n">age</span><span class="p">]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df3</span><span class="p">,</span> <span class="n">cond</span><span class="p">,</span> <span class="s1">&#39;outer&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">df3</span><span class="o">.</span><span class="n">age</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=2), Row(name=u&#39;Bob&#39;, age=5)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=2), Row(name=&#39;Bob&#39;, age=5)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="s1">&#39;name&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">df2</span><span class="o">.</span><span class="n">height</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Bob&#39;, height=85)]</span>
+<span class="go">[Row(name=&#39;Bob&#39;, height=85)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df4</span><span class="p">,</span> <span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Bob&#39;, age=5)]</span>
+<span class="go">[Row(name=&#39;Bob&#39;, age=5)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2165,7 +2165,7 @@ the column(s) must exist on both sides, and this performs an equi-join.</li>
 <code class="descname">limit</code><span class="sig-paren">(</span><em>num</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/dataframe.html#DataFrame.limit"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.DataFrame.limit" title="Permalink to this definition">¶</a></dt>
 <dd><p>Limits the result count to the number specified.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">limit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">limit</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
 <span class="go">[]</span>
 </pre></div>
@@ -2203,18 +2203,18 @@ If a list is specified, length of the list must equal length of the <cite>cols</
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">desc</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="n">ascending</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">desc</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="k">import</span> <span class="o">*</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">asc</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">desc</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">),</span> <span class="s2">&quot;name&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">orderBy</span><span class="p">([</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="s2">&quot;name&quot;</span><span class="p">],</span> <span class="n">ascending</span><span class="o">=</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">])</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2537,11 +2537,11 @@ in the current DataFrame.</td>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s1">&#39;*&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=2), Row(name=u&#39;Bob&#39;, age=5)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=2), Row(name=&#39;Bob&#39;, age=5)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span> <span class="o">+</span> <span class="mi">10</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;age&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, age=12), Row(name=u&#39;Bob&#39;, age=15)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, age=12), Row(name=&#39;Bob&#39;, age=15)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2623,18 +2623,18 @@ If a list is specified, length of the list must equal length of the <cite>cols</
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">desc</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="n">ascending</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">desc</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="k">import</span> <span class="o">*</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">asc</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">desc</span><span class="p">(</span><span class="s2">&quot;age&quot;</span><span class="p">),</span> <span class="s2">&quot;name&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">orderBy</span><span class="p">([</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="s2">&quot;name&quot;</span><span class="p">],</span> <span class="n">ascending</span><span class="o">=</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">])</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;), Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;), Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2716,7 +2716,7 @@ but not in another frame.</p>
 <code class="descname">take</code><span class="sig-paren">(</span><em>num</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/dataframe.html#DataFrame.take"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.DataFrame.take" title="Permalink to this definition">¶</a></dt>
 <dd><p>Returns the first <code class="docutils literal"><span class="pre">num</span></code> rows as a <code class="xref py py-class docutils literal"><span class="pre">list</span></code> of <a class="reference internal" href="#pyspark.sql.Row" title="pyspark.sql.Row"><code class="xref py py-class docutils literal"><span class="pre">Row</span></code></a>.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2737,7 +2737,7 @@ but not in another frame.</p>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">toDF</span><span class="p">(</span><span class="s1">&#39;f1&#39;</span><span class="p">,</span> <span class="s1">&#39;f2&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(f1=2, f2=u&#39;Alice&#39;), Row(f1=5, f2=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(f1=2, f2=&#39;Alice&#39;), Row(f1=5, f2=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -2748,7 +2748,7 @@ but not in another frame.</p>
 <dd><p>Converts a <a class="reference internal" href="#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal"><span class="pre">DataFrame</span></code></a> into a <code class="xref py py-class docutils literal"><span class="pre">RDD</span></code> of string.</p>
 <p>Each row is turned into a JSON document as one element in the returned RDD.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">toJSON</span><span class="p">()</span><span class="o">.</span><span class="n">first</span><span class="p">()</span>
-<span class="go">u&#39;{&quot;age&quot;:2,&quot;name&quot;:&quot;Alice&quot;}&#39;</span>
+<span class="go">&#39;{&quot;age&quot;:2,&quot;name&quot;:&quot;Alice&quot;}&#39;</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2762,7 +2762,7 @@ but not in another frame.</p>
 <dd><p>Returns an iterator that contains all of the rows in this <a class="reference internal" href="#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal"><span class="pre">DataFrame</span></code></a>.
 The iterator will consume as much memory as the largest partition in this DataFrame.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="nb">list</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">toLocalIterator</span><span class="p">())</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;), Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;), Row(age=5, name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2860,7 +2860,7 @@ existing column that has the same name.</p>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">withColumn</span><span class="p">(</span><span class="s1">&#39;age2&#39;</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">age</span> <span class="o">+</span> <span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;, age2=4), Row(age=5, name=u&#39;Bob&#39;, age2=7)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;, age2=4), Row(age=5, name=&#39;Bob&#39;, age2=7)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -2886,7 +2886,7 @@ This is a no-op if schema doesn’t contain the given column name.</p>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">withColumnRenamed</span><span class="p">(</span><span class="s1">&#39;age&#39;</span><span class="p">,</span> <span class="s1">&#39;age2&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age2=2, name=u&#39;Alice&#39;), Row(age2=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age2=2, name=&#39;Alice&#39;), Row(age2=5, name=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -3013,12 +3013,12 @@ or a list of <a class="reference internal" href="#pyspark.sql.Column" title="pys
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">gdf</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">gdf</span><span class="o">.</span><span class="n">agg</span><span class="p">({</span><span class="s2">&quot;*&quot;</span><span class="p">:</span> <span class="s2">&quot;count&quot;</span><span class="p">})</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, count(1)=1), Row(name=u&#39;Bob&#39;, count(1)=1)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, count(1)=1), Row(name=&#39;Bob&#39;, count(1)=1)]</span>
 </pre></div>
 </div>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="k">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="nb">sorted</span><span class="p">(</span><span class="n">gdf</span><span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span>
-<span class="go">[Row(name=u&#39;Alice&#39;, min(age)=2), Row(name=u&#39;Bob&#39;, min(age)=5)]</span>
+<span class="go">[Row(name=&#39;Alice&#39;, min(age)=2), Row(name=&#39;Bob&#39;, min(age)=5)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -3291,9 +3291,9 @@ expression is between the given columns.</p>
 <code class="descname">cast</code><span class="sig-paren">(</span><em>dataType</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/column.html#Column.cast"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.Column.cast" title="Permalink to this definition">¶</a></dt>
 <dd><p>Convert the column into type <code class="docutils literal"><span class="pre">dataType</span></code>.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s2">&quot;string&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;ages&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(ages=u&#39;2&#39;), Row(ages=u&#39;5&#39;)]</span>
+<span class="go">[Row(ages=&#39;2&#39;), Row(ages=&#39;5&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">StringType</span><span class="p">())</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;ages&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(ages=u&#39;2&#39;), Row(ages=u&#39;5&#39;)]</span>
+<span class="go">[Row(ages=&#39;2&#39;), Row(ages=&#39;5&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -3326,7 +3326,7 @@ expression is between the given columns.</p>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;ice&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;ice$&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
 <span class="go">[]</span>
 </pre></div>
@@ -3389,9 +3389,9 @@ or gets an item by key out of a dict.</p>
 <dd><p>True if the current expression is null. Often combined with
 <a class="reference internal" href="#pyspark.sql.DataFrame.filter" title="pyspark.sql.DataFrame.filter"><code class="xref py py-func docutils literal"><span class="pre">DataFrame.filter()</span></code></a> to select rows with non-null values.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="k">import</span> <span class="n">Row</span>
-<span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">u</span><span class="s1">&#39;Tom&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="mi">80</span><span class="p">),</span> <span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">u</span><span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="kc">None</span><span class="p">)])</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;Tom&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="mi">80</span><span class="p">),</span> <span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="kc">None</span><span class="p">)])</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df2</span><span class="o">.</span><span class="n">height</span><span class="o">.</span><span class="n">isNotNull</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(height=80, name=u&#39;Tom&#39;)]</span>
+<span class="go">[Row(height=80, name=&#39;Tom&#39;)]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -3402,9 +3402,9 @@ or gets an item by key out of a dict.</p>
 <dd><p>True if the current expression is null. Often combined with
 <a class="reference internal" href="#pyspark.sql.DataFrame.filter" title="pyspark.sql.DataFrame.filter"><code class="xref py py-func docutils literal"><span class="pre">DataFrame.filter()</span></code></a> to select rows with null values.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="k">import</span> <span class="n">Row</span>
-<span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">u</span><span class="s1">&#39;Tom&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="mi">80</span><span class="p">),</span> <span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">u</span><span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="kc">None</span><span class="p">)])</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;Tom&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="mi">80</span><span class="p">),</span> <span class="n">Row</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;Alice&#39;</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="kc">None</span><span class="p">)])</span><span class="o">.</span><span class="n">toDF</span><span class="p">()</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df2</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df2</span><span class="o">.</span><span class="n">height</span><span class="o">.</span><span class="n">isNull</span><span class="p">())</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(height=None, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(height=None, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -3415,9 +3415,9 @@ or gets an item by key out of a dict.</p>
 <dd><p>A boolean expression that is evaluated to true if the value of this
 expression is contained by the evaluated values of the arguments.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="p">[</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="s2">&quot;Bob&quot;</span><span class="p">,</span> <span class="s2">&quot;Mike&quot;</span><span class="p">)]</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=5, name=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(age=5, name=&#39;Bob&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="p">[</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="o">.</span><span class="n">isin</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">])]</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -3439,7 +3439,7 @@ expression is contained by the evaluated values of the arguments.</p>
 </table>
 <p>See <a class="reference internal" href="#pyspark.sql.Column.rlike" title="pyspark.sql.Column.rlike"><code class="xref py py-func docutils literal"><span class="pre">rlike()</span></code></a> for a regex version</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">like</span><span class="p">(</span><span class="s1">&#39;Al%&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -3520,7 +3520,7 @@ If <a class="reference internal" href="#pyspark.sql.Column.otherwise" title="pys
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">rlike</span><span class="p">(</span><span class="s1">&#39;ice$&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 </pre></div>
 </div>
 </dd></dl>
@@ -3538,7 +3538,7 @@ If <a class="reference internal" href="#pyspark.sql.Column.otherwise" title="pys
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;Al&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(age=2, name=u&#39;Alice&#39;)]</span>
+<span class="go">[Row(age=2, name=&#39;Alice&#39;)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;^Al&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
 <span class="go">[]</span>
 </pre></div>
@@ -3562,7 +3562,7 @@ If <a class="reference internal" href="#pyspark.sql.Column.otherwise" title="pys
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">substr</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">&quot;col&quot;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(col=u&#39;Ali&#39;), Row(col=u&#39;Bob&#39;)]</span>
+<span class="go">[Row(col=&#39;Ali&#39;), Row(col=&#39;Bob&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -4143,12 +4143,12 @@ any value greater than or equal to 9223372036854775807.</li>
 
 <dl class="attribute">
 <dt id="pyspark.sql.Window.unboundedFollowing">
-<code class="descname">unboundedFollowing</code><em class="property"> = 9223372036854775807L</em><a class="headerlink" href="#pyspark.sql.Window.unboundedFollowing" title="Permalink to this definition">¶</a></dt>
+<code class="descname">unboundedFollowing</code><em class="property"> = 9223372036854775807</em><a class="headerlink" href="#pyspark.sql.Window.unboundedFollowing" title="Permalink to this definition">¶</a></dt>
 <dd></dd></dl>
 
 <dl class="attribute">
 <dt id="pyspark.sql.Window.unboundedPreceding">
-<code class="descname">unboundedPreceding</code><em class="property"> = -9223372036854775808L</em><a class="headerlink" href="#pyspark.sql.Window.unboundedPreceding" title="Permalink to this definition">¶</a></dt>
+<code class="descname">unboundedPreceding</code><em class="property"> = -9223372036854775808</em><a class="headerlink" href="#pyspark.sql.Window.unboundedPreceding" title="Permalink to this definition">¶</a></dt>
 <dd></dd></dl>
 
 </dd></dl>
@@ -4685,7 +4685,7 @@ are any.</p>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">read</span><span class="o">.</span><span class="n">text</span><span class="p">(</span><span class="s1">&#39;python/test_support/sql/text-test.txt&#39;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(value=u&#39;hello&#39;), Row(value=u&#39;this&#39;)]</span>
+<span class="go">[Row(value=&#39;hello&#39;), Row(value=&#39;this&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -5779,7 +5779,7 @@ given value, and false otherwise.</p>
 <code class="descclassname">pyspark.sql.functions.</code><code class="descname">bin</code><span class="sig-paren">(</span><em>col</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/functions.html#bin"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.functions.bin" title="Permalink to this definition">¶</a></dt>
 <dd><p>Returns the string representation of the binary value of the given column.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="nb">bin</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">age</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;c&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(c=u&#39;10&#39;), Row(c=u&#39;101&#39;)]</span>
+<span class="go">[Row(c=&#39;10&#39;), Row(c=&#39;101&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -5919,7 +5919,7 @@ or at integral part when <cite>scale</cite> &lt; 0.</p>
 <dd><p>Concatenates multiple input string columns together into a single string column.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="s1">&#39;abcd&#39;</span><span class="p">,</span><span class="s1">&#39;123&#39;</span><span class="p">)],</span> <span class="p">[</span><span class="s1">&#39;s&#39;</span><span class="p">,</span> <span class="s1">&#39;d&#39;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">concat</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">s</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;s&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(s=u&#39;abcd123&#39;)]</span>
+<span class="go">[Row(s=&#39;abcd123&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -5934,7 +5934,7 @@ or at integral part when <cite>scale</cite> &lt; 0.</p>
 using the given separator.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="s1">&#39;abcd&#39;</span><span class="p">,</span><span class="s1">&#39;123&#39;</span><span class="p">)],</span> <span class="p">[</span><span class="s1">&#39;s&#39;</span><span class="p">,</span> <span class="s1">&#39;d&#39;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">concat_ws</span><span class="p">(</span><span class="s1">&#39;-&#39;</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">s</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;s&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(s=u&#39;abcd-123&#39;)]</span>
+<span class="go">[Row(s=&#39;abcd-123&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -5948,7 +5948,7 @@ using the given separator.</p>
 <dd><p>Convert a number in a string column from one base to another.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="s2">&quot;010101&quot;</span><span class="p">,)],</span> <span class="p">[</span><span class="s1">&#39;n&#39;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">conv</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">n</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">16</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;hex&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(hex=u&#39;15&#39;)]</span>
+<span class="go">[Row(hex=&#39;15&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -6079,9 +6079,9 @@ as key-value pairs, e.g. (key1, value1, key2, value2, …).</td>
 </tbody>
 </table>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">create_map</span><span class="p">(</span><span class="s1">&#39;name&#39;</span><span class="p">,</span> <span class="s1">&#39;age&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">&quot;map&quot;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(map={u&#39;Alice&#39;: 2}), Row(map={u&#39;Bob&#39;: 5})]</span>
+<span class="go">[Row(map={&#39;Alice&#39;: 2}), Row(map={&#39;Bob&#39;: 5})]</span>
 <span

<TRUNCATED>

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org

[2/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/pyspark.streaming.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/pyspark.streaming.html b/site/docs/2.2.1/api/python/pyspark.streaming.html
index 6254899..f5543b5 100644
--- a/site/docs/2.2.1/api/python/pyspark.streaming.html
+++ b/site/docs/2.2.1/api/python/pyspark.streaming.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.streaming module &#8212; PySpark  documentation</title>
+    <title>pyspark.streaming module &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -39,7 +39,7 @@
           <a href="pyspark.sql.html" title="pyspark.sql module"
              accesskey="P">previous</a> |</li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="pyspark.html" accesskey="U">pyspark package</a> &#187;</li> 
       </ul>
@@ -763,7 +763,8 @@ DStream’s batching interval</li>
 <dl class="class">
 <dt id="pyspark.streaming.StreamingListener.Java">
 <em class="property">class </em><code class="descname">Java</code><a class="reference internal" href="_modules/pyspark/streaming/listener.html#StreamingListener.Java"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.streaming.StreamingListener.Java" title="Permalink to this definition">¶</a></dt>
-<dd><dl class="attribute">
+<dd><p>Bases: <code class="xref py py-class docutils literal"><span class="pre">object</span></code></p>
+<dl class="attribute">
 <dt id="pyspark.streaming.StreamingListener.Java.implements">
 <code class="descname">implements</code><em class="property"> = ['org.apache.spark.streaming.api.java.PythonStreamingListener']</em><a class="headerlink" href="#pyspark.streaming.StreamingListener.Java.implements" title="Permalink to this definition">¶</a></dt>
 <dd></dd></dl>
@@ -1187,7 +1188,7 @@ will result in this stream using more threads</li>
           <a href="pyspark.sql.html" title="pyspark.sql module"
              >previous</a> |</li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="pyspark.html" >pyspark package</a> &#187;</li> 
       </ul>

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/search.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/search.html b/site/docs/2.2.1/api/python/search.html
index 147493e..8988c1a 100644
--- a/site/docs/2.2.1/api/python/search.html
+++ b/site/docs/2.2.1/api/python/search.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>Search &#8212; PySpark  documentation</title>
+    <title>Search &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -39,7 +39,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>  
@@ -89,7 +89,7 @@
       <h3>Navigation</h3>
       <ul>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
  
       </ul>
     </div>


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org

[5/7] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.2.1

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/26b52712/site/docs/2.2.1/api/python/pyspark.ml.html
----------------------------------------------------------------------
diff --git a/site/docs/2.2.1/api/python/pyspark.ml.html b/site/docs/2.2.1/api/python/pyspark.ml.html
index 1398703..a5757cd 100644
--- a/site/docs/2.2.1/api/python/pyspark.ml.html
+++ b/site/docs/2.2.1/api/python/pyspark.ml.html
@@ -5,14 +5,14 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
   <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-    <title>pyspark.ml package &#8212; PySpark  documentation</title>
+    <title>pyspark.ml package &#8212; PySpark 2.2.1 documentation</title>
     <link rel="stylesheet" href="_static/nature.css" type="text/css" />
     <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="stylesheet" href="_static/pyspark.css" type="text/css" />
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    './',
-        VERSION:     '',
+        VERSION:     '2.2.1',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true,
@@ -39,7 +39,7 @@
           <a href="pyspark.streaming.html" title="pyspark.streaming module"
              accesskey="P">previous</a> |</li>
     
-        <li class="nav-item nav-item-0"><a href="index.html">PySpark  documentation</a> &#187;</li>
+        <li class="nav-item nav-item-0"><a href="index.html">PySpark 2.2.1 documentation</a> &#187;</li>
 
           <li class="nav-item nav-item-1"><a href="pyspark.html" accesskey="U">pyspark package</a> &#187;</li> 
       </ul>
@@ -465,7 +465,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.Pipeline">
-<em class="property">class </em><code class="descclassname">pyspark.ml.</code><code class="descname">Pipeline</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/pipeline.html#Pipeline"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.Pipeline" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.</code><code class="descname">Pipeline</code><span class="sig-paren">(</span><em>stages=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/pipeline.html#Pipeline"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.Pipeline" title="Permalink to this definition">¶</a></dt>
 <dd><p>A simple pipeline, which acts as an estimator. A Pipeline consists
 of a sequence of stages, each of which is either an
 <a class="reference internal" href="#pyspark.ml.Estimator" title="pyspark.ml.Estimator"><code class="xref py py-class docutils literal"><span class="pre">Estimator</span></code></a> or a <a class="reference internal" href="#pyspark.ml.Transformer" title="pyspark.ml.Transformer"><code class="xref py py-class docutils literal"><span class="pre">Transformer</span></code></a>. When
@@ -1055,7 +1055,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 <span id="pyspark-ml-feature-module"></span><h2>pyspark.ml.feature module<a class="headerlink" href="#module-pyspark.ml.feature" title="Permalink to this headline">¶</a></h2>
 <dl class="class">
 <dt id="pyspark.ml.feature.Binarizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Binarizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Binarizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Binarizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Binarizer</code><span class="sig-paren">(</span><em>threshold=0.0</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Binarizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Binarizer" title="Permalink to this definition">¶</a></dt>
 <dd><p>Binarize a column of continuous features given a threshold.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="mf">0.5</span><span class="p">,)],</span> <span class="p">[</span><span class="s2">&quot;values&quot;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">binarizer</span> <span class="o">=</span> <span class="n">Binarizer</span><span class="p">(</span><span class="n">threshold</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">inputCol</span><span class="o">=</span><span class="s2">&quot;values&quot;</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;features&quot;</span><span class="p">)</span>
@@ -1295,7 +1295,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.BucketedRandomProjectionLSH">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">BucketedRandomProjectionLSH</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#BucketedRandomProjectionLSH"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.BucketedRandomProjectionLSH" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">BucketedRandomProjectionLSH</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>seed=None</em>, <em>numHashTables=1</em>, <em>bucketLength=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#BucketedRandomProjectionLSH"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.BucketedRandomProjectionLSH" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -1838,7 +1838,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.Bucketizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Bucketizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Bucketizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Bucketizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Bucketizer</code><span class="sig-paren">(</span><em>splits=None</em>, <em>inputCol=None</em>, <em>outputCol=None</em>, <em>handleInvalid='error'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Bucketizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Bucketizer" title="Permalink to this definition">¶</a></dt>
 <dd><p>Maps a column of continuous features to a column of feature buckets.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">values</span> <span class="o">=</span> <span class="p">[(</span><span class="mf">0.1</span><span class="p">,),</span> <span class="p">(</span><span class="mf">0.4</span><span class="p">,),</span> <span class="p">(</span><span class="mf">1.2</span><span class="p">,),</span> <span class="p">(</span><span class="mf">1.5</span><span class="p">,),</span> <span class="p">(</span><span class="nb">float</span><span class="p">(</span><span class="s2">&quot;nan&quot;</span><span class="p">),),</span> <span class="p">(</span><span class="nb">float</span><span class="p">(</span><span class="s2">&quot;nan&quot;</span><span class="p">),)]</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">values</span><span class="p">,</span> <span class="p">[</span><span class="s2">&quot;values&quot;</span><span class="p">])</span>
@@ -2112,7 +2112,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.ChiSqSelector">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">ChiSqSelector</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#ChiSqSelector"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.ChiSqSelector" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">ChiSqSelector</code><span class="sig-paren">(</span><em>numTopFeatures=50</em>, <em>featuresCol='features'</em>, <em>outputCol=None</em>, <em>labelCol='label'</em>, <em>selectorType='numTopFeatures'</em>, <em>percentile=0.1</em>, <em>fpr=0.05</em>, <em>fdr=0.05</em>, <em>fwe=0.05</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#ChiSqSelector"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.ChiSqSelector" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -2692,7 +2692,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.CountVectorizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">CountVectorizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#CountVectorizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.CountVectorizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">CountVectorizer</code><span class="sig-paren">(</span><em>minTF=1.0</em>, <em>minDF=1.0</em>, <em>vocabSize=262144</em>, <em>binary=False</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#CountVectorizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.CountVectorizer" title="Permalink to this definition">¶</a></dt>
 <dd><p>Extracts a vocabulary from document collections and generates a <a class="reference internal" href="#pyspark.ml.feature.CountVectorizerModel" title="pyspark.ml.feature.CountVectorizerModel"><code class="xref py py-attr docutils literal"><span class="pre">CountVectorizerModel</span></code></a>.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span>
 <span class="gp">... </span>   <span class="p">[(</span><span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">]),</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">,</span> <span class="s2">&quot;a&quot;</span><span class="p">])],</span>
@@ -3185,7 +3185,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.DCT">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">DCT</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#DCT"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.DCT" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">DCT</code><span class="sig-paren">(</span><em>inverse=False</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#DCT"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.DCT" title="Permalink to this definition">¶</a></dt>
 <dd><p>A feature transformer that takes the 1D discrete cosine transform
 of a real vector. No zero padding is performed on the input vector.
 It returns a real vector of the same length representing the DCT.
@@ -3433,7 +3433,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.ElementwiseProduct">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">ElementwiseProduct</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#ElementwiseProduct"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.ElementwiseProduct" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">ElementwiseProduct</code><span class="sig-paren">(</span><em>scalingVec=None</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#ElementwiseProduct"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.ElementwiseProduct" title="Permalink to this definition">¶</a></dt>
 <dd><p>Outputs the Hadamard product (i.e., the element-wise product) of each input vector
 with a provided “weight” vector. In other words, it scales each column of the dataset
 by a scalar multiplier.</p>
@@ -3674,7 +3674,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.HashingTF">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">HashingTF</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#HashingTF"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.HashingTF" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">HashingTF</code><span class="sig-paren">(</span><em>numFeatures=262144</em>, <em>binary=False</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#HashingTF"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.HashingTF" title="Permalink to this definition">¶</a></dt>
 <dd><p>Maps a sequence of terms to their term frequencies using the hashing trick.
 Currently we use Austin Appleby’s MurmurHash 3 algorithm (MurmurHash3_x86_32)
 to calculate the hash code value for the term object.
@@ -3936,7 +3936,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.IDF">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">IDF</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#IDF"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.IDF" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">IDF</code><span class="sig-paren">(</span><em>minDocFreq=0</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#IDF"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.IDF" title="Permalink to this definition">¶</a></dt>
 <dd><p>Compute the Inverse Document Frequency (IDF) given a collection of documents.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="k">import</span> <span class="n">DenseVector</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="n">DenseVector</span><span class="p">([</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">2.0</span><span class="p">]),),</span>
@@ -4355,7 +4355,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.Imputer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Imputer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Imputer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Imputer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Imputer</code><span class="sig-paren">(</span><em>strategy='mean'</em>, <em>missingValue=nan</em>, <em>inputCols=None</em>, <em>outputCols=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Imputer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Imputer" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -4832,7 +4832,7 @@ which are used to replace the missing values in the input DataFrame.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.feature.IndexToString">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">IndexToString</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#IndexToString"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.IndexToString" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">IndexToString</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>labels=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#IndexToString"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.IndexToString" title="Permalink to this definition">¶</a></dt>
 <dd><p>A <code class="xref py py-class docutils literal"><span class="pre">Transformer</span></code> that maps a column of indices back to a new column of
 corresponding string values.
 The index-string mapping is either from the ML attributes of the input column,
@@ -5060,7 +5060,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.MaxAbsScaler">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">MaxAbsScaler</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#MaxAbsScaler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.MaxAbsScaler" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">MaxAbsScaler</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#MaxAbsScaler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.MaxAbsScaler" title="Permalink to this definition">¶</a></dt>
 <dd><p>Rescale each feature individually to range [-1, 1] by dividing through the largest maximum
 absolute value in each feature. It does not shift/center the data, and thus does not destroy
 any sparsity.</p>
@@ -5458,7 +5458,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.MinHashLSH">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">MinHashLSH</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#MinHashLSH"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.MinHashLSH" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">MinHashLSH</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>seed=None</em>, <em>numHashTables=1</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#MinHashLSH"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.MinHashLSH" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -5978,7 +5978,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.MinMaxScaler">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">MinMaxScaler</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#MinMaxScaler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.MinMaxScaler" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">MinMaxScaler</code><span class="sig-paren">(</span><em>min=0.0</em>, <em>max=1.0</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#MinMaxScaler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.MinMaxScaler" title="Permalink to this definition">¶</a></dt>
 <dd><p>Rescale each feature individually to a common range [min, max] linearly using column summary
 statistics, which is also known as min-max normalization or Rescaling. The rescaled value for
 feature E is calculated as,</p>
@@ -6444,7 +6444,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.NGram">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">NGram</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#NGram"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.NGram" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">NGram</code><span class="sig-paren">(</span><em>n=2</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#NGram"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.NGram" title="Permalink to this definition">¶</a></dt>
 <dd><p>A feature transformer that converts the input array of strings into an array of n-grams. Null
 values in the input array are ignored.
 It returns an array of n-grams where each n-gram is represented by a space-separated string of
@@ -6455,15 +6455,15 @@ returned.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([</span><span class="n">Row</span><span class="p">(</span><span class="n">inputTokens</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">,</span> <span class="s2">&quot;d&quot;</span><span class="p">,</span> <span class="s2">&quot;e&quot;</span><span class="p">])])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ngram</span> <span class="o">=</span> <span class="n">NGram</span><span class="p">(</span><span class="n">n</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">inputCol</span><span class="o">=</span><span class="s2">&quot;inputTokens&quot;</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;nGrams&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ngram</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(inputTokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;, u&#39;d&#39;, u&#39;e&#39;], nGrams=[u&#39;a b&#39;, u&#39;b c&#39;, u&#39;c d&#39;, u&#39;d e&#39;])</span>
+<span class="go">Row(inputTokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;, &#39;d&#39;, &#39;e&#39;], nGrams=[&#39;a b&#39;, &#39;b c&#39;, &#39;c d&#39;, &#39;d e&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Change n-gram length</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ngram</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="n">n</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(inputTokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;, u&#39;d&#39;, u&#39;e&#39;], nGrams=[u&#39;a b c d&#39;, u&#39;b c d e&#39;])</span>
+<span class="go">Row(inputTokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;, &#39;d&#39;, &#39;e&#39;], nGrams=[&#39;a b c d&#39;, &#39;b c d e&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Temporarily modify output column.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ngram</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="p">{</span><span class="n">ngram</span><span class="o">.</span><span class="n">outputCol</span><span class="p">:</span> <span class="s2">&quot;output&quot;</span><span class="p">})</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(inputTokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;, u&#39;d&#39;, u&#39;e&#39;], output=[u&#39;a b c d&#39;, u&#39;b c d e&#39;])</span>
+<span class="go">Row(inputTokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;, &#39;d&#39;, &#39;e&#39;], output=[&#39;a b c d&#39;, &#39;b c d e&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ngram</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(inputTokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;, u&#39;d&#39;, u&#39;e&#39;], nGrams=[u&#39;a b c d&#39;, u&#39;b c d e&#39;])</span>
+<span class="go">Row(inputTokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;, &#39;d&#39;, &#39;e&#39;], nGrams=[&#39;a b c d&#39;, &#39;b c d e&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Must use keyword arguments to specify params.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">ngram</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="s2">&quot;text&quot;</span><span class="p">)</span>
 <span class="gt">Traceback (most recent call last):</span>
@@ -6698,7 +6698,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.Normalizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Normalizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Normalizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Normalizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Normalizer</code><span class="sig-paren">(</span><em>p=2.0</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Normalizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Normalizer" title="Permalink to this definition">¶</a></dt>
 <dd><blockquote>
 <div>Normalize a vector to have unit norm using the given p-norm.</div></blockquote>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="k">import</span> <span class="n">Vectors</span>
@@ -6941,7 +6941,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.OneHotEncoder">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">OneHotEncoder</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#OneHotEncoder"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.OneHotEncoder" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">OneHotEncoder</code><span class="sig-paren">(</span><em>dropLast=True</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#OneHotEncoder"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.OneHotEncoder" title="Permalink to this definition">¶</a></dt>
 <dd><p>A one-hot encoder that maps a column of category indices to a
 column of binary vectors, with at most a single one-value per row
 that indicates the input category index.
@@ -7201,7 +7201,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.PCA">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">PCA</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#PCA"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.PCA" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">PCA</code><span class="sig-paren">(</span><em>k=None</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#PCA"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.PCA" title="Permalink to this definition">¶</a></dt>
 <dd><p>PCA trains a model to project vectors to a lower dimensional space of the
 top <a class="reference internal" href="#pyspark.ml.feature.PCA.k" title="pyspark.ml.feature.PCA.k"><code class="xref py py-attr docutils literal"><span class="pre">k</span></code></a> principal components.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="k">import</span> <span class="n">Vectors</span>
@@ -7631,7 +7631,7 @@ Each column is one principal component.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.feature.PolynomialExpansion">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">PolynomialExpansion</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#PolynomialExpansion"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.PolynomialExpansion" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">PolynomialExpansion</code><span class="sig-paren">(</span><em>degree=2</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#PolynomialExpansion"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.PolynomialExpansion" title="Permalink to this definition">¶</a></dt>
 <dd><p>Perform feature expansion in a polynomial space. As said in <a class="reference external" href="http://en.wikipedia.org/wiki/Polynomial_expansion">wikipedia of Polynomial Expansion</a>, “In mathematics, an
 expansion of a product of sums expresses it as a sum of products by using the fact that
 multiplication distributes over addition”. Take a 2-variable feature vector as an example:
@@ -7872,7 +7872,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.QuantileDiscretizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">QuantileDiscretizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#QuantileDiscretizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.QuantileDiscretizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">QuantileDiscretizer</code><span class="sig-paren">(</span><em>numBuckets=2</em>, <em>inputCol=None</em>, <em>outputCol=None</em>, <em>relativeError=0.001</em>, <em>handleInvalid='error'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#QuantileDiscretizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.QuantileDiscretizer" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -8188,7 +8188,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.RegexTokenizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">RegexTokenizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#RegexTokenizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.RegexTokenizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">RegexTokenizer</code><span class="sig-paren">(</span><em>minTokenLength=1</em>, <em>gaps=True</em>, <em>pattern='\s+'</em>, <em>inputCol=None</em>, <em>outputCol=None</em>, <em>toLowercase=True</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#RegexTokenizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.RegexTokenizer" title="Permalink to this definition">¶</a></dt>
 <dd><p>A regex based tokenizer that extracts tokens either by using the
 provided regex pattern (in Java dialect) to split the text
 (default) or repeatedly matching the regex (if gaps is false).
@@ -8198,15 +8198,15 @@ It returns an array of strings that can be empty.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="s2">&quot;A B  c&quot;</span><span class="p">,)],</span> <span class="p">[</span><span class="s2">&quot;text&quot;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">reTokenizer</span> <span class="o">=</span> <span class="n">RegexTokenizer</span><span class="p">(</span><span class="n">inputCol</span><span class="o">=</span><span class="s2">&quot;text&quot;</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;words&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">reTokenizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;A B  c&#39;, words=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;A B  c&#39;, words=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Change a parameter.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">reTokenizer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;tokens&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;A B  c&#39;, tokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;A B  c&#39;, tokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Temporarily modify a parameter.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">reTokenizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="p">{</span><span class="n">reTokenizer</span><span class="o">.</span><span class="n">outputCol</span><span class="p">:</span> <span class="s2">&quot;words&quot;</span><span class="p">})</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;A B  c&#39;, words=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;A B  c&#39;, words=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">reTokenizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;A B  c&#39;, tokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;A B  c&#39;, tokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Must use keyword arguments to specify params.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">reTokenizer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="s2">&quot;text&quot;</span><span class="p">)</span>
 <span class="gt">Traceback (most recent call last):</span>
@@ -8512,7 +8512,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.RFormula">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">RFormula</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#RFormula"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.RFormula" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">RFormula</code><span class="sig-paren">(</span><em>formula=None</em>, <em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>forceIndexLabel=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#RFormula"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.RFormula" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -8984,7 +8984,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.SQLTransformer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">SQLTransformer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#SQLTransformer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.SQLTransformer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">SQLTransformer</code><span class="sig-paren">(</span><em>statement=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#SQLTransformer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.SQLTransformer" title="Permalink to this definition">¶</a></dt>
 <dd><p>Implements the transforms which are defined by SQL statement.
 Currently we only support SQL syntax like ‘SELECT … FROM __THIS__’
 where ‘__THIS__’ represents the underlying table of the input dataset.</p>
@@ -9188,7 +9188,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.StandardScaler">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">StandardScaler</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#StandardScaler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.StandardScaler" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">StandardScaler</code><span class="sig-paren">(</span><em>withMean=False</em>, <em>withStd=True</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#StandardScaler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.StandardScaler" title="Permalink to this definition">¶</a></dt>
 <dd><p>Standardizes features by removing the mean and scaling to unit variance using column summary
 statistics on the samples in the training set.</p>
 <p>The “unit std” is computed using the <a class="reference external" href="https://en.wikipedia.org/wiki/Standard_deviation#Corrected_sample_standard_deviation">corrected sample standard deviation</a>,
@@ -9642,7 +9642,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.StopWordsRemover">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">StopWordsRemover</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#StopWordsRemover"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.StopWordsRemover" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">StopWordsRemover</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>stopWords=None</em>, <em>caseSensitive=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#StopWordsRemover"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.StopWordsRemover" title="Permalink to this definition">¶</a></dt>
 <dd><p>A feature transformer that filters out stop words from input.</p>
 <div class="admonition note">
 <p class="first admonition-title">Note</p>
@@ -9917,7 +9917,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.StringIndexer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">StringIndexer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#StringIndexer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.StringIndexer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">StringIndexer</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>handleInvalid='error'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#StringIndexer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.StringIndexer" title="Permalink to this definition">¶</a></dt>
 <dd><p>A label indexer that maps a string column of labels to an ML column of label indices.
 If the input column is numeric, we cast it to string and index the string values.
 The indices are in [0, numLabels), ordered by label frequencies.
@@ -10335,21 +10335,21 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.Tokenizer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Tokenizer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Tokenizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Tokenizer</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Tokenizer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Tokenizer" title="Permalink to this definition">¶</a></dt>
 <dd><p>A tokenizer that converts the input string to lowercase and then
 splits it by white spaces.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="s2">&quot;a b c&quot;</span><span class="p">,)],</span> <span class="p">[</span><span class="s2">&quot;text&quot;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">tokenizer</span> <span class="o">=</span> <span class="n">Tokenizer</span><span class="p">(</span><span class="n">inputCol</span><span class="o">=</span><span class="s2">&quot;text&quot;</span><span class="p">,</span> <span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;words&quot;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;a b c&#39;, words=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;a b c&#39;, words=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Change a parameter.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;tokens&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;a b c&#39;, tokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;a b c&#39;, tokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Temporarily modify a parameter.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="p">{</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">outputCol</span><span class="p">:</span> <span class="s2">&quot;words&quot;</span><span class="p">})</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;a b c&#39;, words=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;a b c&#39;, words=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-<span class="go">Row(text=u&#39;a b c&#39;, tokens=[u&#39;a&#39;, u&#39;b&#39;, u&#39;c&#39;])</span>
+<span class="go">Row(text=&#39;a b c&#39;, tokens=[&#39;a&#39;, &#39;b&#39;, &#39;c&#39;])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="c1"># Must use keyword arguments to specify params.</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">tokenizer</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="s2">&quot;text&quot;</span><span class="p">)</span>
 <span class="gt">Traceback (most recent call last):</span>
@@ -10561,7 +10561,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.VectorAssembler">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">VectorAssembler</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorAssembler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorAssembler" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">VectorAssembler</code><span class="sig-paren">(</span><em>inputCols=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorAssembler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorAssembler" title="Permalink to this definition">¶</a></dt>
 <dd><p>A feature transformer that merges multiple columns into a vector column.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">3</span><span class="p">)],</span> <span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">])</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">vecAssembler</span> <span class="o">=</span> <span class="n">VectorAssembler</span><span class="p">(</span><span class="n">inputCols</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">],</span> <span class="n">outputCol</span><span class="o">=</span><span class="s2">&quot;features&quot;</span><span class="p">)</span>
@@ -10778,7 +10778,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.VectorIndexer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">VectorIndexer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorIndexer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">VectorIndexer</code><span class="sig-paren">(</span><em>maxCategories=20</em>, <em>inputCol=None</em>, <em>outputCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorIndexer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorIndexer" title="Permalink to this definition">¶</a></dt>
 <dd><p>Class for indexing categorical feature columns in a dataset of <cite>Vector</cite>.</p>
 <dl class="docutils">
 <dt>This has 2 usage modes:</dt>
@@ -11283,7 +11283,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.feature.VectorSlicer">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">VectorSlicer</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorSlicer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorSlicer" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">VectorSlicer</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>indices=None</em>, <em>names=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorSlicer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorSlicer" title="Permalink to this definition">¶</a></dt>
 <dd><p>This class takes a feature vector and outputs a new feature vector with a subarray
 of the original features.</p>
 <p>The subset of features can be specified with either indices (<cite>setIndices()</cite>)
@@ -11512,7 +11512,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="method">
 <dt id="pyspark.ml.feature.VectorSlicer.setParams">
-<code class="descname">setParams</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorSlicer.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorSlicer.setParams" title="Permalink to this definition">¶</a></dt>
+<code class="descname">setParams</code><span class="sig-paren">(</span><em>inputCol=None</em>, <em>outputCol=None</em>, <em>indices=None</em>, <em>names=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#VectorSlicer.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.VectorSlicer.setParams" title="Permalink to this definition">¶</a></dt>
 <dd><p>setParams(self, inputCol=None, outputCol=None, indices=None, names=None):
 Sets params for this VectorSlicer.</p>
 <div class="versionadded">
@@ -11554,7 +11554,7 @@ Sets params for this VectorSlicer.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.feature.Word2Vec">
-<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Word2Vec</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Word2Vec"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Word2Vec" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.feature.</code><code class="descname">Word2Vec</code><span class="sig-paren">(</span><em>vectorSize=100</em>, <em>minCount=5</em>, <em>numPartitions=1</em>, <em>stepSize=0.025</em>, <em>maxIter=1</em>, <em>seed=None</em>, <em>inputCol=None</em>, <em>outputCol=None</em>, <em>windowSize=5</em>, <em>maxSentenceLength=1000</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/feature.html#Word2Vec"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.feature.Word2Vec" title="Permalink to this definition">¶</a></dt>
 <dd><p>Word2Vec trains a model of <cite>Map(String, Vector)</cite>, i.e. transforms a word into a code for further
 natural language processing or machine learning process.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">sent</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;a b &quot;</span> <span class="o">*</span> <span class="mi">100</span> <span class="o">+</span> <span class="s2">&quot;a c &quot;</span> <span class="o">*</span> <span class="mi">10</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot; &quot;</span><span class="p">)</span>
@@ -12149,7 +12149,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 <span id="pyspark-ml-classification-module"></span><h2>pyspark.ml.classification module<a class="headerlink" href="#module-pyspark.ml.classification" title="Permalink to this headline">¶</a></h2>
 <dl class="class">
 <dt id="pyspark.ml.classification.LinearSVC">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">LinearSVC</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#LinearSVC"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.LinearSVC" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">LinearSVC</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>maxIter=100</em>, <em>regParam=0.0</em>, <em>tol=1e-06</em>, <em>rawPredictionCol='rawPrediction'</em>, <em>fitIntercept=True</em>, <em>standardization=True</em>, <em>threshold=0.0</em>, <em>weightCol=None</em>, <em>aggregationDepth=2</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#LinearSVC"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.LinearSVC" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -12484,7 +12484,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="method">
 <dt id="pyspark.ml.classification.LinearSVC.setParams">
-<code class="descname">setParams</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#LinearSVC.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.LinearSVC.setParams" title="Permalink to this definition">¶</a></dt>
+<code class="descname">setParams</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>maxIter=100</em>, <em>regParam=0.0</em>, <em>tol=1e-06</em>, <em>rawPredictionCol='rawPrediction'</em>, <em>fitIntercept=True</em>, <em>standardization=True</em>, <em>threshold=0.0</em>, <em>weightCol=None</em>, <em>aggregationDepth=2</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#LinearSVC.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.LinearSVC.setParams" title="Permalink to this definition">¶</a></dt>
 <dd><p>setParams(self, featuresCol=”features”, labelCol=”label”, predictionCol=”prediction”,                   maxIter=100, regParam=0.0, tol=1e-6, rawPredictionCol=”rawPrediction”,                   fitIntercept=True, standardization=True, threshold=0.0, weightCol=None,                   aggregationDepth=2):
 Sets params for Linear SVM Classifier.</p>
 <div class="versionadded">
@@ -12762,7 +12762,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.classification.LogisticRegression">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">LogisticRegression</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#LogisticRegression"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.LogisticRegression" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">LogisticRegression</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>maxIter=100</em>, <em>regParam=0.0</em>, <em>elasticNetParam=0.0</em>, <em>tol=1e-06</em>, <em>fitIntercept=True</em>, <em>threshold=0.5</em>, <em>thresholds=None</em>, <em>probabilityCol='probability'</em>, <em>rawPredictionCol='rawPrediction'</em>, <em>standardization=True</em>, <em>weightCol=None</em>, <em>aggregationDepth=2</em>, <em>family='auto'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#LogisticRegression"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.LogisticRegression" title="Permalink to this definition">¶</a></dt>
 <dd><p>Logistic regression.
 This class supports multinomial logistic (softmax) and binomial logistic regression.</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="k">import</span> <span class="n">Row</span>
@@ -13990,7 +13990,7 @@ versions.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.classification.DecisionTreeClassifier">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">DecisionTreeClassifier</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#DecisionTreeClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.DecisionTreeClassifier" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">DecisionTreeClassifier</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>probabilityCol='probability'</em>, <em>rawPredictionCol='rawPrediction'</em>, <em>maxDepth=5</em>, <em>maxBins=32</em>, <em>minInstancesPerNode=1</em>, <em>minInfoGain=0.0</em>, <em>maxMemoryInMB=256</em>, <em>cacheNodeIds=False</em>, <em>checkpointInterval=10</em>, <em>impurity='gini'</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#DecisionTreeClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.DecisionTreeClassifier" title="Permalink to this definition">¶</a></dt>
 <dd><p><a class="reference external" href="http://en.wikipedia.org/wiki/Decision_tree_learning">Decision tree</a>
 learning algorithm for classification.
 It supports both binary and multiclass labels, as well as both continuous and categorical
@@ -14688,7 +14688,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.classification.GBTClassifier">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">GBTClassifier</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#GBTClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.GBTClassifier" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">GBTClassifier</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>maxDepth=5</em>, <em>maxBins=32</em>, <em>minInstancesPerNode=1</em>, <em>minInfoGain=0.0</em>, <em>maxMemoryInMB=256</em>, <em>cacheNodeIds=False</em>, <em>checkpointInterval=10</em>, <em>lossType='logistic'</em>, <em>maxIter=20</em>, <em>stepSize=0.1</em>, <em>seed=None</em>, <em>subsamplingRate=1.0</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#GBTClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.GBTClassifier" title="Permalink to this definition">¶</a></dt>
 <dd><p><a class="reference external" href="http://en.wikipedia.org/wiki/Gradient_boosting">Gradient-Boosted Trees (GBTs)</a>
 learning algorithm for classification.
 It supports binary labels, as well as both continuous and categorical features.</p>
@@ -15413,7 +15413,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.classification.RandomForestClassifier">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">RandomForestClassifier</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#RandomForestClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.RandomForestClassifier" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">RandomForestClassifier</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>probabilityCol='probability'</em>, <em>rawPredictionCol='rawPrediction'</em>, <em>maxDepth=5</em>, <em>maxBins=32</em>, <em>minInstancesPerNode=1</em>, <em>minInfoGain=0.0</em>, <em>maxMemoryInMB=256</em>, <em>cacheNodeIds=False</em>, <em>checkpointInterval=10</em>, <em>impurity='gini'</em>, <em>numTrees=20</em>, <em>featureSubsetStrategy='auto'</em>, <em>seed=None</em>, <em>subsamplingRate=1.0</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#RandomForestClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.RandomForestClassifier" title="Permalink to this definition">¶</a></dt>
 <dd><p><a class="reference external" href="http://en.wikipedia.org/wiki/Random_forest">Random Forest</a>
 learning algorithm for classification.
 It supports both binary and multiclass labels, as well as both continuous and categorical
@@ -16187,7 +16187,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.classification.NaiveBayes">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">NaiveBayes</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#NaiveBayes"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.NaiveBayes" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">NaiveBayes</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>probabilityCol='probability'</em>, <em>rawPredictionCol='rawPrediction'</em>, <em>smoothing=1.0</em>, <em>modelType='multinomial'</em>, <em>thresholds=None</em>, <em>weightCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#NaiveBayes"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.NaiveBayes" title="Permalink to this definition">¶</a></dt>
 <dd><p>Naive Bayes Classifiers.
 It supports both Multinomial and Bernoulli NB. <a class="reference external" href="http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html">Multinomial NB</a>
 can handle finitely supported discrete data. For example, by converting documents into
@@ -16762,7 +16762,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.classification.MultilayerPerceptronClassifier">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">MultilayerPerceptronClassifier</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#MultilayerPerceptronClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.MultilayerPerceptronClassifier" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">MultilayerPerceptronClassifier</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>maxIter=100</em>, <em>tol=1e-06</em>, <em>seed=None</em>, <em>layers=None</em>, <em>blockSize=128</em>, <em>stepSize=0.03</em>, <em>solver='l-bfgs'</em>, <em>initialWeights=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#MultilayerPerceptronClassifier"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.MultilayerPerceptronClassifier" title="Permalink to this definition">¶</a></dt>
 <dd><p>Classifier trainer based on the Multilayer Perceptron.
 Each layer has sigmoid activation function, output layer has softmax.
 Number of inputs has to be equal to the size of feature vectors.
@@ -17379,7 +17379,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="class">
 <dt id="pyspark.ml.classification.OneVsRest">
-<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">OneVsRest</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#OneVsRest"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.OneVsRest" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.classification.</code><code class="descname">OneVsRest</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>labelCol='label'</em>, <em>predictionCol='prediction'</em>, <em>classifier=None</em>, <em>weightCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#OneVsRest"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.OneVsRest" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -17655,7 +17655,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 
 <dl class="method">
 <dt id="pyspark.ml.classification.OneVsRest.setParams">
-<code class="descname">setParams</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#OneVsRest.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.OneVsRest.setParams" title="Permalink to this definition">¶</a></dt>
+<code class="descname">setParams</code><span class="sig-paren">(</span><em>featuresCol=None</em>, <em>labelCol=None</em>, <em>predictionCol=None</em>, <em>classifier=None</em>, <em>weightCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/classification.html#OneVsRest.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.classification.OneVsRest.setParams" title="Permalink to this definition">¶</a></dt>
 <dd><p>setParams(self, featuresCol=None, labelCol=None, predictionCol=None,                   classifier=None, weightCol=None):
 Sets params for OneVsRest.</p>
 <div class="versionadded">
@@ -17966,7 +17966,7 @@ uses <code class="xref py py-func docutils literal"><span class="pre">dir()</spa
 <span id="pyspark-ml-clustering-module"></span><h2>pyspark.ml.clustering module<a class="headerlink" href="#module-pyspark.ml.clustering" title="Permalink to this headline">¶</a></h2>
 <dl class="class">
 <dt id="pyspark.ml.clustering.BisectingKMeans">
-<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">BisectingKMeans</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#BisectingKMeans"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.BisectingKMeans" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">BisectingKMeans</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>predictionCol='prediction'</em>, <em>maxIter=20</em>, <em>seed=None</em>, <em>k=4</em>, <em>minDivisibleClusterSize=1.0</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#BisectingKMeans"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.BisectingKMeans" title="Permalink to this definition">¶</a></dt>
 <dd><p>A bisecting k-means algorithm based on the paper “A comparison of document clustering
 techniques” by Steinbach, Karypis, and Kumar, with modification to fit Spark.
 The algorithm starts from a single cluster that contains all points.
@@ -18559,7 +18559,7 @@ training set. An exception is thrown if no summary exists.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.clustering.KMeans">
-<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">KMeans</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#KMeans"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.KMeans" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">KMeans</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>predictionCol='prediction'</em>, <em>k=2</em>, <em>initMode='k-means||'</em>, <em>initSteps=2</em>, <em>tol=0.0001</em>, <em>maxIter=20</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#KMeans"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.KMeans" title="Permalink to this definition">¶</a></dt>
 <dd><p>K-means clustering with a k-means++ like initialization mode
 (the k-means|| algorithm by Bahmani et al).</p>
 <div class="highlight-default"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.ml.linalg</span> <span class="k">import</span> <span class="n">Vectors</span>
@@ -19119,7 +19119,7 @@ training set. An exception is thrown if no summary exists.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.clustering.GaussianMixture">
-<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">GaussianMixture</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#GaussianMixture"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.GaussianMixture" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">GaussianMixture</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>predictionCol='prediction'</em>, <em>k=2</em>, <em>probabilityCol='probability'</em>, <em>tol=0.01</em>, <em>maxIter=100</em>, <em>seed=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#GaussianMixture"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.GaussianMixture" title="Permalink to this definition">¶</a></dt>
 <dd><p>GaussianMixture clustering.
 This class performs expectation maximization for multivariate Gaussian
 Mixture Models (GMMs).  A GMM represents a composite distribution of
@@ -19776,7 +19776,7 @@ where weights[i] is the weight for Gaussian i, and weights sum to 1.</p>
 
 <dl class="class">
 <dt id="pyspark.ml.clustering.LDA">
-<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">LDA</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#LDA"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.LDA" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.clustering.</code><code class="descname">LDA</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>maxIter=20</em>, <em>seed=None</em>, <em>checkpointInterval=10</em>, <em>k=10</em>, <em>optimizer='online'</em>, <em>learningOffset=1024.0</em>, <em>learningDecay=0.51</em>, <em>subsamplingRate=0.05</em>, <em>optimizeDocConcentration=True</em>, <em>docConcentration=None</em>, <em>topicConcentration=None</em>, <em>topicDistributionCol='topicDistribution'</em>, <em>keepLastCheckpoint=True</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#LDA"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.LDA" title="Permalink to this definition">¶</a></dt>
 <dd><p>Latent Dirichlet Allocation (LDA), a topic model designed for text documents.</p>
 <p>Terminology:</p>
 <blockquote>
@@ -20267,7 +20267,7 @@ Currenlty only support ‘em’ and ‘online’.</p>
 
 <dl class="method">
 <dt id="pyspark.ml.clustering.LDA.setParams">
-<code class="descname">setParams</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#LDA.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.LDA.setParams" title="Permalink to this definition">¶</a></dt>
+<code class="descname">setParams</code><span class="sig-paren">(</span><em>featuresCol='features'</em>, <em>maxIter=20</em>, <em>seed=None</em>, <em>checkpointInterval=10</em>, <em>k=10</em>, <em>optimizer='online'</em>, <em>learningOffset=1024.0</em>, <em>learningDecay=0.51</em>, <em>subsamplingRate=0.05</em>, <em>optimizeDocConcentration=True</em>, <em>docConcentration=None</em>, <em>topicConcentration=None</em>, <em>topicDistributionCol='topicDistribution'</em>, <em>keepLastCheckpoint=True</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/clustering.html#LDA.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.clustering.LDA.setParams" title="Permalink to this definition">¶</a></dt>
 <dd><p>setParams(self, featuresCol=”features”, maxIter=20, seed=None, checkpointInterval=10,                  k=10, optimizer=”online”, learningOffset=1024.0, learningDecay=0.51,                  subsamplingRate=0.05, optimizeDocConcentration=True,                  docConcentration=None, topicConcentration=None,                  topicDistributionCol=”topicDistribution”, keepLastCheckpoint=True):</p>
 <p>Sets params for LDA.</p>
 <div class="versionadded">
@@ -21502,7 +21502,7 @@ or array.array.</p>
 <span id="pyspark-ml-recommendation-module"></span><h2>pyspark.ml.recommendation module<a class="headerlink" href="#module-pyspark.ml.recommendation" title="Permalink to this headline">¶</a></h2>
 <dl class="class">
 <dt id="pyspark.ml.recommendation.ALS">
-<em class="property">class </em><code class="descclassn

<TRUNCATED>

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org