[1/6] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.1.3

[gu...@apache.org]

Repository: spark-website
Updated Branches:
  refs/heads/asf-site 6bbac4966 -> da71a5c1d


http://git-wip-us.apache.org/repos/asf/spark-website/blob/da71a5c1/site/docs/2.1.3/api/python/searchindex.js
----------------------------------------------------------------------
diff --git a/site/docs/2.1.3/api/python/searchindex.js b/site/docs/2.1.3/api/python/searchindex.js
index cfc547a..b57a96a 100644
--- a/site/docs/2.1.3/api/python/searchindex.js
+++ b/site/docs/2.1.3/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.ml":{Estimator:[2,1,1,""],Model:[2,1,1,""],Pipeline:[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,"-"],linalg:[2,0,0,"-"],param:[2,0,0,"-"],recommendation:[2,0,0,"-"],regression:[2,0,0,"-"],tuning:[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:[2,4,1,""],params:[2,3,1,""],re
 ad:[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:[2,4,1,""],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,""],BinaryLogisticRegressionTrainingSummary:[2,1,1,""],DecisionTreeClassificationModel:[2,1,1,""],DecisionTreeClassifier:[2,1,1,""],GBTClassificationModel:[2,1,1,""],GBTClassifier:[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.BinaryLogisticRegressionTrainingSummary":{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:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],getMaxDep
 th:[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:[2,4,1,""],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:[2,4,1,""],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,""],setProbabilityCol:[2,2,1,""],se
 tRawPredictionCol:[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:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],ge
 tMaxBins:[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:[2,4,1,""],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:[2,4,1,""],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.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:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],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,""],hasSummary:[2,3,1,""],intercept:[2,3,1,""],interceptVector:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4
 ,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setBlockSize:[2,2,1,""],setFeaturesCol:[2,2,1,""],setInitialWeights:[2,2,1,""],s
 etLabelCol:[2,2,1,""],setLayers:[2,2,1,""],setMaxIter:[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:[2,4,1,""],modelType:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],pi:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],predictio
 nCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setClassifier:[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:[2,4,1,""],numClasses:[2,3,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],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:[2,4,1,""],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:[2,4,1,""],maxIter:[2,3,1,""],minDivisibleClusterSize:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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,""],hasDefau
 lt:[2,2,1,""],hasParam:[2,2,1,""],hasSummary:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],logPrior:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""]},"pyspark.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:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],probabilityCol:[2,3,1,""],read:[2,4,1,""],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,""],extractP
 aramMap:[2,2,1,""],gaussiansDF:[2,3,1,""],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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],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,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],k:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],maxIter:[2,3,1,""],optimizeDocConcentration:[2,3,1,""],optimizer:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setCheckpointInterval:[2,2,1,""],setDocConcentration:[2,2,1,""],setFeaturesCol:[2,2,1,""],setK:[2,2,1,""],setKeepLastCheckpo
 int:[2,2,1,""],setLearningDecay:[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,""],expl
 ainParam:[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,""],load:[2,4,1,""],logLikelihood:[2,2,1,""],logPerplexity:[2,2,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],rawPredictionCol:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],metricName
 :[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],metricName:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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,""],Bucketizer:[2,1,1,""],ChiSqSelector:[2,1,1,""],ChiSqSelectorModel:[2,1,1,""],CountVectorizer:[2,1,1,""],CountVectorizerMo
 del:[2,1,1,""],DCT:[2,1,1,""],ElementwiseProduct:[2,1,1,""],HashingTF:[2,1,1,""],IDF:[2,1,1,""],IDFModel:[2,1,1,""],IndexToString:[2,1,1,""],MaxAbsScaler:[2,1,1,""],MaxAbsScalerModel:[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,""],getOutpu
 tCol:[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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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.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,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setHandleInvalid:[2,2,1,""],setInputCol:[2,2,1,""],setOutputCol:[2,2,1,""],setParams:[2,2,1,""],setSplits:[2,2,1,""],spli
 ts:[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,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],fpr:[2,3,1,""],getFeaturesCol:[2,2,1,""],getFpr:[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:[2,4,1,""],numTopFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],percentile:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],selectorType:[2,3,1,""],setFeaturesCol:[2,2,1,""],setFpr:[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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],getOrDefault:[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:[2,4,1,""],minDF:[2,3,1,""],minTF:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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
 :[2,4,1,""],numFeatures:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],minDocFreq:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],h
 asDefault:[2,2,1,""],hasParam:[2,2,1,""],idf:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],maxAbs:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],isDefi
 ned:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],max:[2,3,1,""],min:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],originalMax:[2,3,1,""],originalMin:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],n:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],hasDefault:[2,2,1,""],hasParam:[2,2,1,""],inputCol:[2,3,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],outputCol:[2,3,1,""],p:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],extractParamMap:[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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],pc:[2,3,1,""],read:[2,4,1,""],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,""],getDegree:[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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],ext
 ractParamMap:[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:[2,4,1,""],numBuckets:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],hasDefau
 lt:[2,2,1,""],hasParam:[2,2,1,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],labelCol:[2,3,1,""],load:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],minTokenLength:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],pattern:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],mean:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],std:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.feature.StopWordsRemover":{caseSensitive:[2,3,1,""],cop
 y:[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:[2,4,1,""],loadDefaultStopWords:[2,5,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],loa
 d:[2,4,1,""],maxCategories:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],isDefined:[2,2,1,""],isSet:[2,2,1,""],load:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],isS
 et:[2,2,1,""],load:[2,4,1,""],names:[2,3,1,""],outputCol:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],getMaxSentenceLength:[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:[2,4,1,""],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:[2,4,1,""],save:[2,2,1,""],seed:[2,3,1,""],setInput
 Col:[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:[2,4,1,""],params:[2,3,1,""],read:[2,4,1,""],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.Matrix":{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,""],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,""],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,""],ge
 tSeed:[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:[2,4,1,""],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:[2,4,1,""],regParam:[2,3,1,""],save:[2,2,1,""],seed:[2,3,1,""],setAlpha:[2,2,1,""],setCheckpointInterval:[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:[2,4,1,""],params:[2,3,1,""],rank:[2,3,1,""],read:[2,4,1,""],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,""],RandomForestRe
 gressionModel:[2,1,1,""],RandomForestRegressor:[2,1,1,""]},"pyspark.ml.regression.AFTSurvivalRegression":{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:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],quantileProbabilities:[2,3,1,""],quantilesCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setAggregationDepth:[2,2,1,""],setCensorCol:[2,2,1,""],setFeaturesCol:[2,2,1,""],setFitIntercept:[2,2,1,""],setLabe
 lCol:[2,2,1,""],setMaxIter:[2,2,1,""],setParams:[2,2,1,""],setPredictionCol:[2,2,1,""],setQuantileProbabilities:[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:[2,4,1,""],params:[2,3,1,""],predict:[2,2,1,""],predictQuantiles:[2,2,1,""],read:[2,4,1,""],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:[2,4,1,""],numFeatures:[2,3,1,""],numNodes:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxMemoryInMB:[2,3,1,""],minInfoGa
 in:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],toDebugString:[2,3,1,""],tot
 alNumNodes:[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:[2,4,1,""],lossType:[2,3,1,""],maxBins:[2,3,1,""],maxDepth:[2,3,1,""],maxIter:[2,3,1,""],maxMem
 oryInMB:[2,3,1,""],minInfoGain:[2,3,1,""],minInstancesPerNode:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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,""],getF
 itIntercept:[2,2,1,""],getLabelCol:[2,2,1,""],getLink:[2,2,1,""],getLinkPredictionCol:[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,""],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,""],linkPredictionCol:[2,3,1,""],load:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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,""],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,""],setWeightCol:[2,2,1,""],solver:[2,3,1,""],tol:[2,3,1,""],weightCol:[2,3,1,""],write:[2,2,1,""]},"pyspark.ml.regression.GeneralizedLinearRegressionModel":{coefficien
 ts:[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:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],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,""],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:[2,4,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],setFeatureIndex:[2,2,1,""],setFeaturesCol:[2,2,1,""],setIsotonic:[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:[2,4,1,""],params:[2,3,1,""],predictions:[2,3,1,""],read:[2,4,1,""],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,""],getStandard
 ization:[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:[2,4,1,""],maxIter:[2,3,1,""],params:[2,3,1,""],predictionCol:[2,3,1,""],read:[2,4,1,""],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:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],save:[2,2,1,""],summary:[2,3,1,""],transform:[2,2,1,""],write:[2,2,1,""]},"pyspark.ml.regression.LinearRegressionSummary":{coefficientStandardErrors:[2,3,1,""],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,""],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,""],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:[2,4,1,""],numFeatures:[2,3,1,""],params:[2,3,1,""],read:[2,4,1,""],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,""],extractParamMap:[2,2,1,""],featureSubsetStrategy:[2,3,1,""],featuresCol:[2,3,1,""],fit:[2,2,1,""],getCacheNodeIds:[2,2,1,""],getCheckpointInterval:[2,2,1,""],getFeatur
 eSubsetStrategy:[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:[2,4,1,""],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:[2,4,1,""],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.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,""],setEstimatorParamMaps:[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.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,""],SVMWithSGD:[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.clas
 sification.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,""],predictOn:[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,""],computeCost:[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.BinaryClassificationMetrics":{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,""],weightedFalsePosi
 tiveRate:[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,""],Word2Vec:[3,1,1,""],Word2VecModel:[3,1,1,""]},"pyspark.mllib.feature.ChiSqSelector":{fit:[3,2,1,""],setFpr:[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.ElementwiseProduct":{transform:[3,2,1,""]},"pyspark.mll
 ib.feature.HashingTF":{indexOf:[3,2,1,""],setBinary:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.IDF":{fit:[3,2,1,""]},"pyspark.mllib.feature.IDFModel":{idf:[3,2,1,""],transform:[3,2,1,""]},"pyspark.mllib.feature.Normalizer":{transform:[3,2,1,""]},"pyspark.mllib.feature.StandardScaler":{fit:[3,2,1,""]},"pyspark.mllib.feature.StandardScalerModel":{mean:[3,3,1,""],setWithMean:[3,2,1,""],setWithStd:[3,2,1,""],std:[3,3,1,""],transform:[3,2,1,""],withMean:[3,3,1,""],withStd:[3,3,1,""]},"pyspark.mllib.feature.Word2Vec":{fit:[3,2,1,""],setLearningRate:[3,2,1,""],setMinCount:[3,2,1,""],setNumIterations:[3,2,1,""],setNumPartitions:[3,2,1,""],setSeed:[3,2,1,""],setVectorSize:[3,2,1,""],setWindowSize:[3,2,1,""]},"pyspark.mllib.feature.Word2VecModel":{findSynonyms:[3,2,1,""],getVectors:[3,2,1,""],load:[3,4,1,""],transform:[3,2,1,""]},"pyspark.mllib.fpm":{FPGrowth:[3,1,1,""],FPGrowthModel:[3,1,1,""],PrefixSpan:[3,1,1,""],PrefixSpanModel:[3,1,1,""]},"pyspark.mllib.fpm.FPGrowth":{FreqIt
 emset:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.fpm.FPGrowthModel":{freqItemsets:[3,2,1,""],load:[3,4,1,""]},"pyspark.mllib.fpm.PrefixSpan":{FreqSequence:[3,1,1,""],train:[3,4,1,""]},"pyspark.mllib.fpm.PrefixSpanModel":{freqSequences:[3,2,1,""]},"pyspark.mllib.linalg":{DenseMatrix:[3,1,1,""],DenseVector:[3,1,1,""],Matrices:[3,1,1,""],Matrix:[3,1,1,""],QRDecomposition:[3,1,1,""],SparseMatrix:[3,1,1,""],SparseVector:[3,1,1,""],Vector:[3,1,1,""],Vectors:[3,1,1,""],distributed:[3,0,0,"-"]},"pyspark.mllib.linalg.DenseMatrix":{asML:[3,2,1,""],toArray:[3,2,1,""],toSparse:[3,2,1,""]},"pyspark.mllib.linalg.DenseVector":{asML:[3,2,1,""],dot:[3,2,1,""],norm:[3,2,1,""],numNonzeros:[3,2,1,""],parse:[3,5,1,""],squared_distance:[3,2,1,""],toArray:[3,2,1,""],values:[3,3,1,""]},"pyspark.mllib.linalg.Matrices":{dense:[3,5,1,""],fromML:[3,5,1,""],sparse:[3,5,1,""]},"pyspark.mllib.linalg.Matrix":{asML:[3,2,1,""],toArray:[3,2,1,""]},"pyspark.mllib.linalg.QRDecomposition":{Q:[3,3,1,""],R:[3,3,1,""]},"p
 yspark.mllib.linalg.SparseMatrix":{asML:[3,2,1,""],toArray:[3,2,1,""],toDense:[3,2,1,""]},"pyspark.mllib.linalg.SparseVector":{asML:[3,2,1,""],dot:[3,2,1,""],indices:[3,3,1,""],norm:[3,2,1,""],numNonzeros:[3,2,1,""],parse:[3,5,1,""],size:[3,3,1,""],squared_distance:[3,2,1,""],toArray:[3,2,1,""],values:[3,3,1,""]},"pyspark.mllib.linalg.Vector":{asML:[3,2,1,""],toArray:[3,2,1,""]},"pyspark.mllib.linalg.Vectors":{dense:[3,5,1,""],fromML:[3,5,1,""],norm:[3,5,1,""],parse:[3,5,1,""],sparse:[3,5,1,""],squared_distance:[3,5,1,""],stringify:[3,5,1,""],zeros:[3,5,1,""]},"pyspark.mllib.linalg.distributed":{BlockMatrix:[3,1,1,""],CoordinateMatrix:[3,1,1,""],DistributedMatrix:[3,1,1,""],IndexedRow:[3,1,1,""],IndexedRowMatrix:[3,1,1,""],MatrixEntry:[3,1,1,""],RowMatrix:[3,1,1,""]},"pyspark.mllib.linalg.distributed.BlockMatrix":{add:[3,2,1,""],blocks:[3,3,1,""],cache:[3,2,1,""],colsPerBlock:[3,3,1,""],multiply:[3,2,1,""],numColBlocks:[3,3,1,""],numCols:[3,2,1,""],numRowBlocks:[3,3,1,""],numRows:[3
 ,2,1,""],persist:[3,2,1,""],rowsPerBlock:[3,3,1,""],subtract:[3,2,1,""],toCoordinateMatrix:[3,2,1,""],toIndexedRowMatrix:[3,2,1,""],toLocalMatrix:[3,2,1,""],transpose:[3,2,1,""],validate:[3,2,1,""]},"pyspark.mllib.linalg.distributed.CoordinateMatrix":{entries:[3,3,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],toBlockMatrix:[3,2,1,""],toIndexedRowMatrix:[3,2,1,""],toRowMatrix:[3,2,1,""],transpose:[3,2,1,""]},"pyspark.mllib.linalg.distributed.DistributedMatrix":{numCols:[3,2,1,""],numRows:[3,2,1,""]},"pyspark.mllib.linalg.distributed.IndexedRowMatrix":{columnSimilarities:[3,2,1,""],computeGramianMatrix:[3,2,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],rows:[3,3,1,""],toBlockMatrix:[3,2,1,""],toCoordinateMatrix:[3,2,1,""],toRowMatrix:[3,2,1,""]},"pyspark.mllib.linalg.distributed.RowMatrix":{columnSimilarities:[3,2,1,""],computeColumnSummaryStatistics:[3,2,1,""],computeCovariance:[3,2,1,""],computeGramianMatrix:[3,2,1,""],numCols:[3,2,1,""],numRows:[3,2,1,""],rows:[3,3,1,""],tallSkinnyQR:[
 3,2,1,""]},"pyspark.mllib.random":{RandomRDDs:[3,1,1,""]},"pyspark.mllib.random.RandomRDDs":{exponentialRDD:[3,5,1,""],exponentialVectorRDD:[3,5,1,""],gammaRDD:[3,5,1,""],gammaVectorRDD:[3,5,1,""],logNormalRDD:[3,5,1,""],logNormalVectorRDD:[3,5,1,""],normalRDD:[3,5,1,""],normalVectorRDD:[3,5,1,""],poissonRDD:[3,5,1,""],poissonVectorRDD:[3,5,1,""],uniformRDD:[3,5,1,""],uniformVectorRDD:[3,5,1,""]},"pyspark.mllib.recommendation":{ALS:[3,1,1,""],MatrixFactorizationModel:[3,1,1,""],Rating:[3,1,1,""]},"pyspark.mllib.recommendation.ALS":{train:[3,4,1,""],trainImplicit:[3,4,1,""]},"pyspark.mllib.recommendation.MatrixFactorizationModel":{load:[3,4,1,""],predict:[3,2,1,""],predictAll:[3,2,1,""],productFeatures:[3,2,1,""],rank:[3,3,1,""],recommendProducts:[3,2,1,""],recommendProductsForUsers:[3,2,1,""],recommendUsers:[3,2,1,""],recommendUsersForProducts:[3,2,1,""],userFeatures:[3,2,1,""]},"pyspark.mllib.regression":{IsotonicRegression:[3,1,1,""],IsotonicRegressionModel:[3,1,1,""],LabeledPoint
 :[3,1,1,""],LassoModel:[3,1,1,""],LassoWithSGD:[3,1,1,""],LinearModel:[3,1,1,""],LinearRegressionModel:[3,1,1,""],LinearRegressionWithSGD:[3,1,1,""],RidgeRegressionModel:[3,1,1,""],RidgeRegressionWithSGD:[3,1,1,""],StreamingLinearAlgorithm:[3,1,1,""],StreamingLinearRegressionWithSGD:[3,1,1,""]},"pyspark.mllib.regression.IsotonicRegression":{train:[3,4,1,""]},"pyspark.mllib.regression.IsotonicRegressionModel":{load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""]},"pyspark.mllib.regression.LassoModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LassoWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.LinearModel":{intercept:[3,3,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LinearRegressionModel":{intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.LinearRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.RidgeRegressionModel":{
 intercept:[3,3,1,""],load:[3,4,1,""],predict:[3,2,1,""],save:[3,2,1,""],weights:[3,3,1,""]},"pyspark.mllib.regression.RidgeRegressionWithSGD":{train:[3,4,1,""]},"pyspark.mllib.regression.StreamingLinearAlgorithm":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""]},"pyspark.mllib.regression.StreamingLinearRegressionWithSGD":{latestModel:[3,2,1,""],predictOn:[3,2,1,""],predictOnValues:[3,2,1,""],setInitialWeights:[3,2,1,""],trainOn:[3,2,1,""]},"pyspark.mllib.stat":{ChiSqTestResult:[3,1,1,""],KernelDensity:[3,1,1,""],MultivariateGaussian:[3,1,1,""],MultivariateStatisticalSummary:[3,1,1,""],Statistics:[3,1,1,""]},"pyspark.mllib.stat.ChiSqTestResult":{method:[3,3,1,""]},"pyspark.mllib.stat.KernelDensity":{estimate:[3,2,1,""],setBandwidth:[3,2,1,""],setSample:[3,2,1,""]},"pyspark.mllib.stat.MultivariateStatisticalSummary":{count:[3,2,1,""],max:[3,2,1,""],mean:[3,2,1,""],min:[3,2,1,""],normL1:[3,2,1,""],normL2:[3,2,1,""],numNonzeros:[3,2,1,""],variance:[3,2,1,""]},"pys
 park.mllib.stat.Statistics":{chiSqTest:[3,5,1,""],colStats:[3,5,1,""],corr:[3,5,1,""],kolmogorovSmirnovTest:[3,5,1,""]},"pyspark.mllib.tree":{DecisionTree:[3,1,1,""],DecisionTreeModel:[3,1,1,""],GradientBoostedTrees:[3,1,1,""],GradientBoostedTreesModel:[3,1,1,""],RandomForest:[3,1,1,""],RandomForestModel:[3,1,1,""]},"pyspark.mllib.tree.DecisionTree":{trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.DecisionTreeModel":{call:[3,2,1,""],depth:[3,2,1,""],load:[3,4,1,""],numNodes:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""]},"pyspark.mllib.tree.GradientBoostedTrees":{trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pyspark.mllib.tree.GradientBoostedTreesModel":{call:[3,2,1,""],load:[3,4,1,""],numTrees:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""],totalNumNodes:[3,2,1,""]},"pyspark.mllib.tree.RandomForest":{supportedFeatureSubsetStrategies:[3,3,1,""],trainClassifier:[3,4,1,""],trainRegressor:[3,4,1,""]},"pys
 park.mllib.tree.RandomForestModel":{call:[3,2,1,""],load:[3,4,1,""],numTrees:[3,2,1,""],predict:[3,2,1,""],save:[3,2,1,""],toDebugString:[3,2,1,""],totalNumNodes:[3,2,1,""]},"pyspark.mllib.util":{JavaLoader:[3,1,1,""],JavaSaveable:[3,1,1,""],LinearDataGenerator:[3,1,1,""],Loader:[3,1,1,""],MLUtils:[3,1,1,""],Saveable:[3,1,1,""]},"pyspa

<TRUNCATED>

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

[6/6] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.1.3

[gu...@apache.org]

Fix signature description broken in PySpark API documentation in 2.1.3


Project: http://git-wip-us.apache.org/repos/asf/spark-website/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark-website/commit/da71a5c1
Tree: http://git-wip-us.apache.org/repos/asf/spark-website/tree/da71a5c1
Diff: http://git-wip-us.apache.org/repos/asf/spark-website/diff/da71a5c1

Branch: refs/heads/asf-site
Commit: da71a5c1d80c963901b0f15c64ef18ee5b0a0bd8
Parents: 6bbac49
Author: hyukjinkwon <gu...@apache.org>
Authored: Tue Jul 3 02:08:45 2018 +0800
Committer: hyukjinkwon <gu...@apache.org>
Committed: Wed Jul 4 02:12:13 2018 +0800

----------------------------------------------------------------------
 site/docs/2.1.3/api/python/pyspark.html         |  22 +-
 site/docs/2.1.3/api/python/pyspark.ml.html      | 144 +++++------
 site/docs/2.1.3/api/python/pyspark.mllib.html   |  28 +--
 site/docs/2.1.3/api/python/pyspark.sql.html     | 248 +++++++++----------
 .../2.1.3/api/python/pyspark.streaming.html     |   3 +-
 site/docs/2.1.3/api/python/searchindex.js       |   2 +-
 6 files changed, 224 insertions(+), 223 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark-website/blob/da71a5c1/site/docs/2.1.3/api/python/pyspark.html
----------------------------------------------------------------------
diff --git a/site/docs/2.1.3/api/python/pyspark.html b/site/docs/2.1.3/api/python/pyspark.html
index 18248bc..068ac7d 100644
--- a/site/docs/2.1.3/api/python/pyspark.html
+++ b/site/docs/2.1.3/api/python/pyspark.html
@@ -259,7 +259,7 @@ Its format depends on the scheduler implementation.</p>
 <li>in case of YARN something like ‘application_1433865536131_34483’</li>
 </ul>
 <div class="highlight-default notranslate"><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>
@@ -738,7 +738,7 @@ 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>
@@ -761,10 +761,10 @@ 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>
@@ -814,7 +814,7 @@ 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>
@@ -1666,7 +1666,7 @@ 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 notranslate"><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">
@@ -1781,7 +1781,7 @@ 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 notranslate"><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>
@@ -2071,7 +2071,7 @@ 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>
@@ -2082,7 +2082,7 @@ 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 notranslate"><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>
@@ -2102,7 +2102,7 @@ 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 notranslate"><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>
@@ -2646,7 +2646,7 @@ When batching is used, this will be called with an array of objects.</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><p>Deserialize an object from a byte array.</p>
 </dd></dl>
 


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

[2/6] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.1.3

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/da71a5c1/site/docs/2.1.3/api/python/pyspark.streaming.html
----------------------------------------------------------------------
diff --git a/site/docs/2.1.3/api/python/pyspark.streaming.html b/site/docs/2.1.3/api/python/pyspark.streaming.html
index 18dcf63..37a5466 100644
--- a/site/docs/2.1.3/api/python/pyspark.streaming.html
+++ b/site/docs/2.1.3/api/python/pyspark.streaming.html
@@ -754,7 +754,8 @@ 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 notranslate"><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>


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

[4/6] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.1.3

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/da71a5c1/site/docs/2.1.3/api/python/pyspark.mllib.html
----------------------------------------------------------------------
diff --git a/site/docs/2.1.3/api/python/pyspark.mllib.html b/site/docs/2.1.3/api/python/pyspark.mllib.html
index 705c126..fcb1b09 100644
--- a/site/docs/2.1.3/api/python/pyspark.mllib.html
+++ b/site/docs/2.1.3/api/python/pyspark.mllib.html
@@ -2624,7 +2624,7 @@ Compositionality.</p>
 <p>Querying for synonyms of a word will not return that word:</p>
 <div class="highlight-default notranslate"><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
@@ -2632,7 +2632,7 @@ representation is that vector:</p>
 <div class="highlight-default notranslate"><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 notranslate"><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>
@@ -2643,7 +2643,7 @@ 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>
@@ -3034,7 +3034,7 @@ 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>
@@ -3132,7 +3132,7 @@ 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">
@@ -4884,7 +4884,7 @@ 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">
@@ -4970,7 +4970,7 @@ 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">
@@ -5060,7 +5060,7 @@ 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">
@@ -5146,7 +5146,7 @@ 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">
@@ -5224,7 +5224,7 @@ 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">
@@ -5308,7 +5308,7 @@ 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">
@@ -6579,9 +6579,9 @@ 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 notranslate"><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>
@@ -6761,7 +6761,7 @@ 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 notranslate"><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>


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

[5/6] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.1.3

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/da71a5c1/site/docs/2.1.3/api/python/pyspark.ml.html
----------------------------------------------------------------------
diff --git a/site/docs/2.1.3/api/python/pyspark.ml.html b/site/docs/2.1.3/api/python/pyspark.ml.html
index f37f2df..206a8b1 100644
--- a/site/docs/2.1.3/api/python/pyspark.ml.html
+++ b/site/docs/2.1.3/api/python/pyspark.ml.html
@@ -555,7 +555,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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 notranslate"><span class="pre">Transformer</span></code></a>. When
@@ -1238,7 +1238,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 <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 notranslate"><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>
@@ -1508,7 +1508,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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>
@@ -1812,7 +1812,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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><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>
@@ -2387,7 +2387,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><span class="pre">CountVectorizerModel</span></code></a>.</p>
 <div class="highlight-default notranslate"><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>
@@ -2940,7 +2940,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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.
@@ -3218,7 +3218,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -3489,7 +3489,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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.
@@ -3781,7 +3781,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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>
@@ -4260,7 +4260,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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,
@@ -4518,7 +4518,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -4976,7 +4976,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -5502,7 +5502,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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
@@ -5513,15 +5513,15 @@ returned.</p>
 <div class="highlight-default notranslate"><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>
@@ -5786,7 +5786,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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>
@@ -6059,7 +6059,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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.
@@ -6349,7 +6349,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><span class="pre">k</span></code></a> principal components.</p>
 <div class="highlight-default notranslate"><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>
@@ -6839,7 +6839,7 @@ 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:
@@ -7110,7 +7110,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -7448,7 +7448,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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).
@@ -7458,15 +7458,15 @@ It returns an array of strings that can be empty.</p>
 <div class="highlight-default notranslate"><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>
@@ -7802,7 +7802,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -8334,7 +8334,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -8568,7 +8568,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>,
@@ -9082,7 +9082,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -9387,7 +9387,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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.
@@ -9865,21 +9865,21 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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>
@@ -10121,7 +10121,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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 notranslate"><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>
@@ -10368,7 +10368,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -10933,7 +10933,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>)
@@ -11192,7 +11192,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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">
@@ -11234,7 +11234,7 @@ 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 notranslate"><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>
@@ -11889,7 +11889,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 <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.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 notranslate"><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>
@@ -13180,7 +13180,7 @@ 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
@@ -13938,7 +13938,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -14723,7 +14723,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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
@@ -15557,7 +15557,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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
@@ -16192,7 +16192,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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.
@@ -16869,7 +16869,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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>
@@ -17168,7 +17168,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <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">
@@ -17509,7 +17509,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 <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.
@@ -18162,7 +18162,7 @@ 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 notranslate"><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>
@@ -18782,7 +18782,7 @@ 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
@@ -19498,7 +19498,7 @@ 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>
@@ -20019,7 +20019,7 @@ 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">
@@ -21344,7 +21344,7 @@ 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="descclassname">pyspark.ml.recommendation.</code><code class="descname">ALS</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/recommendation.html#ALS"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.recommendation.ALS" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.recommendation.</code><code class="descname">ALS</code><span class="sig-paren">(</span><em>rank=10</em>, <em>maxIter=10</em>, <em>regParam=0.1</em>, <em>numUserBlocks=10</em>, <em>numItemBlocks=10</em>, <em>implicitPrefs=False</em>, <em>alpha=1.0</em>, <em>userCol='user'</em>, <em>itemCol='item'</em>, <em>seed=None</em>, <em>ratingCol='rating'</em>, <em>nonnegative=False</em>, <em>checkpointInterval=10</em>, <em>intermediateStorageLevel='MEMORY_AND_DISK'</em>, <em>finalStorageLevel='MEMORY_AND_DISK'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/recommendation.html#ALS"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.recommendation.ALS" title="Permalink to this definition">¶</a></dt>
 <dd><p>Alternating Least Squares (ALS) matrix factorization.</p>
 <p>ALS attempts to estimate the ratings matrix <cite>R</cite> as the product of
 two lower-rank matrices, <cite>X</cite> and <cite>Y</cite>, i.e. <cite>X * Yt = R</cite>. Typically
@@ -22172,7 +22172,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 <span id="pyspark-ml-regression-module"></span><h2>pyspark.ml.regression module<a class="headerlink" href="#module-pyspark.ml.regression" title="Permalink to this headline">¶</a></h2>
 <dl class="class">
 <dt id="pyspark.ml.regression.AFTSurvivalRegression">
-<em class="property">class </em><code class="descclassname">pyspark.ml.regression.</code><code class="descname">AFTSurvivalRegression</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/regression.html#AFTSurvivalRegression"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.AFTSurvivalRegression" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.regression.</code><code class="descname">AFTSurvivalRegression</code><span class="sig-paren">(</span><em>featuresCol='features', labelCol='label', predictionCol='prediction', fitIntercept=True, maxIter=100, tol=1e-06, censorCol='censor', quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99], quantilesCol=None, aggregationDepth=2</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/regression.html#AFTSurvivalRegression"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.AFTSurvivalRegression" title="Permalink to this definition">¶</a></dt>
 <dd><div class="admonition note">
 <p class="first admonition-title">Note</p>
 <p class="last">Experimental</p>
@@ -22551,7 +22551,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <dl class="method">
 <dt id="pyspark.ml.regression.AFTSurvivalRegression.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/regression.html#AFTSurvivalRegression.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.AFTSurvivalRegression.setParams" title="Permalink to this definition">¶</a></dt>
+<code class="descname">setParams</code><span class="sig-paren">(</span><em>featuresCol='features', labelCol='label', predictionCol='prediction', fitIntercept=True, maxIter=100, tol=1e-06, censorCol='censor', quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99], quantilesCol=None, aggregationDepth=2</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/regression.html#AFTSurvivalRegression.setParams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.AFTSurvivalRegression.setParams" title="Permalink to this definition">¶</a></dt>
 <dd><p>setParams(self, featuresCol=”features”, labelCol=”label”, predictionCol=”prediction”,                   fitIntercept=True, maxIter=100, tol=1E-6, censorCol=”censor”,                   quantileProbabilities=[0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99],                   quantilesCol=None, aggregationDepth=2):</p>
 <div class="versionadded">
 <p><span class="versionmodified">New in version 1.6.0.</span></p>
@@ -22840,7 +22840,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <dl class="class">
 <dt id="pyspark.ml.regression.DecisionTreeRegressor">
-<em class="property">class </em><code class="descclassname">pyspark.ml.regression.</code><code class="descname">DecisionTreeRegressor</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/regression.html#DecisionTreeRegressor"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.DecisionTreeRegressor" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.regression.</code><code class="descname">DecisionTreeRegressor</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>impurity='variance'</em>, <em>seed=None</em>, <em>varianceCol=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/regression.html#DecisionTreeRegressor"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.DecisionTreeRegressor" 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 regression.
 It supports both continuous and categorical features.</p>
@@ -23560,7 +23560,7 @@ uses <code class="xref py py-func docutils literal notranslate"><span class="pre
 
 <dl class="class">
 <dt id="pyspark.ml.regression.GBTRegressor">
-<em class="property">class </em><code class="descclassname">pyspark.ml.regression.</code><code class="descname">GBTRegressor</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/regression.html#GBTRegressor"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.GBTRegressor" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><code class="descclassname">pyspark.ml.regression.</code><code class="descname">GBTRegressor</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>subsamplingRate=1.0</em>, <em>checkpointInterval=10</em>, <em>lossType='squared'</em>, <em>maxIter=20</em>, <em>stepSize=0.1</em>, <em>seed=None</em>, <em>impurity='variance'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/ml/regression.html#GBTRegressor"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.ml.regression.GBTRegressor" title="Permalink to this definition">¶</a></dt>
 <dd><p><a class="reference external" href="http://en.wikipedia.org/wiki/Gradi

<TRUNCATED>

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

[3/6] spark-website git commit: Fix signature description broken in PySpark API documentation in 2.1.3

[gu...@apache.org]

http://git-wip-us.apache.org/repos/asf/spark-website/blob/da71a5c1/site/docs/2.1.3/api/python/pyspark.sql.html
----------------------------------------------------------------------
diff --git a/site/docs/2.1.3/api/python/pyspark.sql.html b/site/docs/2.1.3/api/python/pyspark.sql.html
index 329ea36..446f743 100644
--- a/site/docs/2.1.3/api/python/pyspark.sql.html
+++ b/site/docs/2.1.3/api/python/pyspark.sql.html
@@ -201,7 +201,7 @@ cluster.</p>
 
 <dl class="attribute">
 <dt id="pyspark.sql.SparkSession.builder">
-<code class="descname">builder</code><em class="property"> = &lt;pyspark.sql.session.Builder object&gt;</em><a class="headerlink" href="#pyspark.sql.SparkSession.builder" title="Permalink to this definition">¶</a></dt>
+<code class="descname">builder</code><em class="property"> = &lt;pyspark.sql.session.SparkSession.Builder object&gt;</em><a class="headerlink" href="#pyspark.sql.SparkSession.builder" title="Permalink to this definition">¶</a></dt>
 <dd></dd></dl>
 
 <dl class="attribute">
@@ -270,22 +270,22 @@ omit the <code class="docutils literal notranslate"><span class="pre">struct&lt;
 </div>
 <div class="highlight-default notranslate"><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 notranslate"><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 notranslate"><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 notranslate"><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>
@@ -293,7 +293,7 @@ omit the <code class="docutils literal notranslate"><span class="pre">struct&lt;
 <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 notranslate"><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>
@@ -302,17 +302,17 @@ omit the <code class="docutils literal notranslate"><span class="pre">struct&lt;
 <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 notranslate"><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 notranslate"><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>
@@ -439,7 +439,7 @@ as a streaming <a class="reference internal" href="#pyspark.sql.DataFrame" title
 <div class="highlight-default notranslate"><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">
@@ -620,22 +620,22 @@ If it’s not a <a class="reference internal" href="#pyspark.sql.types.StructTyp
 </div>
 <div class="highlight-default notranslate"><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 notranslate"><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 notranslate"><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 notranslate"><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>
@@ -643,7 +643,7 @@ 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 notranslate"><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>
@@ -652,17 +652,17 @@ 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 notranslate"><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 notranslate"><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>
@@ -721,12 +721,12 @@ 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 notranslate"><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">
@@ -880,7 +880,7 @@ be done.  For any other return type, the produced object must match the specifie
 </table>
 <div class="highlight-default notranslate"><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 notranslate"><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>
@@ -948,7 +948,7 @@ When the return type is not specified we would infer it via reflection.
 <div class="highlight-default notranslate"><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">
@@ -1039,7 +1039,7 @@ When the return type is not specified we would infer it via reflection.
 <div class="highlight-default notranslate"><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">
@@ -1137,7 +1137,7 @@ be done.  For any other return type, the produced object must match the specifie
 </table>
 <div class="highlight-default notranslate"><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 notranslate"><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>
@@ -1212,7 +1212,7 @@ 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">
@@ -1329,7 +1329,7 @@ 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 notranslate"><span class="pre">Row</span></code></a>.</p>
 <div class="highlight-default notranslate"><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">
@@ -1489,12 +1489,12 @@ catalog.</p>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -1621,23 +1621,23 @@ This is a no-op if schema doesn’t contain the given column name(s).</p>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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 notranslate"><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 notranslate"><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 notranslate"><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 notranslate"><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">
@@ -1834,15 +1834,15 @@ or a string of SQL expression.</td>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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 notranslate"><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">
@@ -1855,7 +1855,7 @@ 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 notranslate"><span class="pre">Row</span></code></a>.</p>
 <div class="highlight-default notranslate"><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">
@@ -1944,11 +1944,11 @@ Each element should be a column name (string) or an expression (<a class="refere
 <div class="highlight-default notranslate"><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">
@@ -1986,9 +1986,9 @@ If n is 1, return a single Row.</td>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -2059,24 +2059,24 @@ 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 notranslate"><span class="pre">df1</span></code> and <code class="docutils literal notranslate"><span class="pre">df2</span></code>.</p>
 <div class="highlight-default notranslate"><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 notranslate"><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 notranslate"><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 notranslate"><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 notranslate"><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">
@@ -2089,7 +2089,7 @@ 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 notranslate"><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>
@@ -2127,18 +2127,18 @@ If a list is specified, length of the list must equal length of the <cite>cols</
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -2455,11 +2455,11 @@ in the current DataFrame.</td>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -2541,18 +2541,18 @@ If a list is specified, length of the list must equal length of the <cite>cols</
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -2634,7 +2634,7 @@ 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 notranslate"><span class="pre">num</span></code> rows as a <code class="xref py py-class docutils literal notranslate"><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 notranslate"><span class="pre">Row</span></code></a>.</p>
 <div class="highlight-default notranslate"><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">
@@ -2655,7 +2655,7 @@ but not in another frame.</p>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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>
@@ -2666,7 +2666,7 @@ 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 notranslate"><span class="pre">DataFrame</span></code></a> into a <code class="xref py py-class docutils literal notranslate"><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 notranslate"><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">
@@ -2680,7 +2680,7 @@ 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 notranslate"><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 notranslate"><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">
@@ -2776,7 +2776,7 @@ existing column that has the same name.</p>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -2802,7 +2802,7 @@ This is a no-op if schema doesn’t contain the given column name.</p>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -2929,12 +2929,12 @@ or a list of <a class="reference internal" href="#pyspark.sql.Column" title="pys
 </table>
 <div class="highlight-default notranslate"><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 notranslate"><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">
@@ -3189,9 +3189,9 @@ 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 notranslate"><span class="pre">dataType</span></code>.</p>
 <div class="highlight-default notranslate"><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">
@@ -3279,9 +3279,9 @@ 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 notranslate"><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">
@@ -3387,7 +3387,7 @@ If <a class="reference internal" href="#pyspark.sql.Column.otherwise" title="pys
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -3950,12 +3950,12 @@ 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>
@@ -4463,7 +4463,7 @@ are any.</p>
 </table>
 <div class="highlight-default notranslate"><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">
@@ -5544,7 +5544,7 @@ elements and value must be of the same type.</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 notranslate"><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">
@@ -5684,7 +5684,7 @@ 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 notranslate"><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">
@@ -5699,7 +5699,7 @@ or at integral part when <cite>scale</cite> &lt; 0.</p>
 using the given separator.</p>
 <div class="highlight-default notranslate"><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">
@@ -5713,7 +5713,7 @@ using the given separator.</p>
 <dd><p>Convert a number in a string column from one base to another.</p>
 <div class="highlight-default notranslate"><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">
@@ -5844,9 +5844,9 @@ as key-value pairs, e.g. (key1, value1, key2, value2, …).</td>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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 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="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">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>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -5907,7 +5907,7 @@ specialized implementation.</p>
 </div>
 <div class="highlight-default notranslate"><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;2015-04-08&#39;</span><span class="p">,)],</span> <span class="p">[</span><span class="s1">&#39;a&#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">date_format</span><span class="p">(</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="s1">&#39;MM/dd/yyy&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;date&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(date=u&#39;04/08/2015&#39;)]</span>
+<span class="go">[Row(date=&#39;04/08/2015&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -6130,7 +6130,7 @@ and returns the result as a string.</p>
 </tbody>
 </table>
 <div class="highlight-default notranslate"><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="mi">5</span><span class="p">,)],</span> <span class="p">[</span><span class="s1">&#39;a&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">format_number</span><span class="p">(</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;v&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(v=u&#39;5.0000&#39;)]</span>
+<span class="go">[Row(v=&#39;5.0000&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -6156,7 +6156,7 @@ and returns the result as a string.</p>
 </table>
 <div class="highlight-default notranslate"><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">5</span><span class="p">,</span> <span class="s2">&quot;hello&quot;</span><span class="p">)],</span> <span class="p">[</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="s1">&#39;b&#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">format_string</span><span class="p">(</span><span class="s1">&#39;</span><span class="si">%d</span><span class="s1"> </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">a</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s1">&#39;v&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(v=u&#39;5 hello&#39;)]</span>
+<span class="go">[Row(v=&#39;5 hello&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -6242,7 +6242,7 @@ of the extracted json object. It will return null if the input json string is in
 <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">data</span><span class="p">,</span> <span class="p">(</span><span class="s2">&quot;key&quot;</span><span class="p">,</span> <span class="s2">&quot;jstring&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">select</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">key</span><span class="p">,</span> <span class="n">get_json_object</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">jstring</span><span class="p">,</span> <span class="s1">&#39;$.f1&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">&quot;c0&quot;</span><span class="p">),</span> \
 <span class="gp">... </span>                  <span class="n">get_json_object</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">jstring</span><span class="p">,</span> <span class="s1">&#39;$.f2&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">&quot;c1&quot;</span><span class="p">)</span> <span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(key=u&#39;1&#39;, c0=u&#39;value1&#39;, c1=u&#39;value2&#39;), Row(key=u&#39;2&#39;, c0=u&#39;value12&#39;, c1=None)]</span>
+<span class="go">[Row(key=&#39;1&#39;, c0=&#39;value1&#39;, c1=&#39;value2&#39;), Row(key=&#39;2&#39;, c0=&#39;value12&#39;, c1=None)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -6331,7 +6331,7 @@ the grouping columns).</p>
 <a class="reference internal" href="#pyspark.sql.types.BinaryType" title="pyspark.sql.types.BinaryType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.BinaryType</span></code></a>, <a class="reference internal" href="#pyspark.sql.types.IntegerType" title="pyspark.sql.types.IntegerType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.IntegerType</span></code></a> or
 <a class="reference internal" href="#pyspark.sql.types.LongType" title="pyspark.sql.types.LongType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.LongType</span></code></a>.</p>
 <div class="highlight-default notranslate"><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="s1">&#39;ABC&#39;</span><span class="p">,</span> <span class="mi">3</span><span class="p">)],</span> <span class="p">[</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="s1">&#39;b&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="nb">hex</span><span class="p">(</span><span class="s1">&#39;a&#39;</span><span class="p">),</span> <span class="nb">hex</span><span class="p">(</span><span class="s1">&#39;b&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span>
-<span class="go">[Row(hex(a)=u&#39;414243&#39;, hex(b)=u&#39;3&#39;)]</span>
+<span class="go">[Row(hex(a)=&#39;414243&#39;, hex(b)=&#39;3&#39;)]</span>
 </pre></div>
 </div>
 <div class="versionadded">
@@ -6367,7 +6367,7 @@ the grouping columns).</p>
 <code class="descclassname">pyspark.sql.functions.</code><code class="descname">initcap</code><span class="sig-paren">(</span><em>col</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/pyspark/sql/functions.html#initcap"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.functions.initcap" title="Permalink to this definition">¶</a></dt>
 <dd><p>Translate the first letter of each word to upper case in the sentence.</p>
 <div class="highlight-default notranslate"><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="s1">&#39;ab cd&#39;</span><span class="p">,)],</span> <span class="p">[</span><span class="s1">&#39;a&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">initcap</span><span class="p">(</span><span class="s2">&quot;a&quot;</span><span class="p">)</span><span class="o">.</span><spa

<TRUNCATED>

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