You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by sr...@apache.org on 2018/11/29 14:53:15 UTC
spark git commit: [MINOR][ML] add missing params to Instr
Repository: spark
Updated Branches:
refs/heads/master 06a87711b -> e3ea93ab6
[MINOR][ML] add missing params to Instr
## What changes were proposed in this pull request?
add following param to instr:
GBTC: validationTol
GBTR: validationTol, validationIndicatorCol
colnames in LiR, LinearSVC, etc
## How was this patch tested?
existing tests
Closes #23122 from zhengruifeng/instr_append_missing_params.
Authored-by: zhengruifeng <ru...@foxmail.com>
Signed-off-by: Sean Owen <se...@databricks.com>
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e3ea93ab
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e3ea93ab
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e3ea93ab
Branch: refs/heads/master
Commit: e3ea93ab6c8e434faa360af831947e682206d50d
Parents: 06a8771
Author: zhengruifeng <ru...@foxmail.com>
Authored: Thu Nov 29 08:53:12 2018 -0600
Committer: Sean Owen <se...@databricks.com>
Committed: Thu Nov 29 08:53:12 2018 -0600
----------------------------------------------------------------------
.../apache/spark/ml/classification/DecisionTreeClassifier.scala | 3 ++-
.../org/apache/spark/ml/classification/GBTClassifier.scala | 2 +-
.../scala/org/apache/spark/ml/classification/LinearSVC.scala | 4 ++--
.../org/apache/spark/ml/classification/LogisticRegression.scala | 5 +++--
.../ml/classification/MultilayerPerceptronClassifier.scala | 4 ++--
.../scala/org/apache/spark/ml/classification/OneVsRest.scala | 3 ++-
.../scala/org/apache/spark/ml/regression/GBTRegressor.scala | 3 ++-
7 files changed, 14 insertions(+), 10 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
index bcf8976..d9292a5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
@@ -115,7 +115,8 @@ class DecisionTreeClassifier @Since("1.4.0") (
val oldDataset: RDD[LabeledPoint] = extractLabeledPoints(dataset, numClasses)
val strategy = getOldStrategy(categoricalFeatures, numClasses)
- instr.logParams(this, maxDepth, maxBins, minInstancesPerNode, minInfoGain, maxMemoryInMB,
+ instr.logParams(this, labelCol, featuresCol, predictionCol, rawPredictionCol,
+ probabilityCol, maxDepth, maxBins, minInstancesPerNode, minInfoGain, maxMemoryInMB,
cacheNodeIds, checkpointInterval, impurity, seed)
val trees = RandomForest.run(oldDataset, strategy, numTrees = 1, featureSubsetStrategy = "all",
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
index 09a9df6..abe2d1f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
@@ -194,7 +194,7 @@ class GBTClassifier @Since("1.4.0") (
instr.logParams(this, labelCol, featuresCol, predictionCol, impurity, lossType,
maxDepth, maxBins, maxIter, maxMemoryInMB, minInfoGain, minInstancesPerNode,
seed, stepSize, subsamplingRate, cacheNodeIds, checkpointInterval, featureSubsetStrategy,
- validationIndicatorCol)
+ validationIndicatorCol, validationTol)
instr.logNumClasses(numClasses)
val (baseLearners, learnerWeights) = if (withValidation) {
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
index 1b5c02f..ff801ab 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LinearSVC.scala
@@ -173,8 +173,8 @@ class LinearSVC @Since("2.2.0") (
instr.logPipelineStage(this)
instr.logDataset(dataset)
- instr.logParams(this, regParam, maxIter, fitIntercept, tol, standardization, threshold,
- aggregationDepth)
+ instr.logParams(this, labelCol, weightCol, featuresCol, predictionCol, rawPredictionCol,
+ regParam, maxIter, fitIntercept, tol, standardization, threshold, aggregationDepth)
val (summarizer, labelSummarizer) = {
val seqOp = (c: (MultivariateOnlineSummarizer, MultiClassSummarizer),
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
index 6f0804f..27a7db0 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
@@ -503,8 +503,9 @@ class LogisticRegression @Since("1.2.0") (
instr.logPipelineStage(this)
instr.logDataset(dataset)
- instr.logParams(this, regParam, elasticNetParam, standardization, threshold,
- maxIter, tol, fitIntercept)
+ instr.logParams(this, labelCol, weightCol, featuresCol, predictionCol, rawPredictionCol,
+ probabilityCol, regParam, elasticNetParam, standardization, threshold, maxIter, tol,
+ fitIntercept)
val (summarizer, labelSummarizer) = {
val seqOp = (c: (MultivariateOnlineSummarizer, MultiClassSummarizer),
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
index 4feddce..47b8a8d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/MultilayerPerceptronClassifier.scala
@@ -205,8 +205,8 @@ class MultilayerPerceptronClassifier @Since("1.5.0") (
dataset: Dataset[_]): MultilayerPerceptronClassificationModel = instrumented { instr =>
instr.logPipelineStage(this)
instr.logDataset(dataset)
- instr.logParams(this, labelCol, featuresCol, predictionCol, layers, maxIter, tol,
- blockSize, solver, stepSize, seed)
+ instr.logParams(this, labelCol, featuresCol, predictionCol, rawPredictionCol, layers, maxIter,
+ tol, blockSize, solver, stepSize, seed)
val myLayers = $(layers)
val labels = myLayers.last
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
index 2f42a59..e1fceb1 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
@@ -377,7 +377,8 @@ final class OneVsRest @Since("1.4.0") (
instr.logPipelineStage(this)
instr.logDataset(dataset)
- instr.logParams(this, labelCol, featuresCol, predictionCol, parallelism, rawPredictionCol)
+ instr.logParams(this, labelCol, weightCol, featuresCol, predictionCol,
+ rawPredictionCol, parallelism)
instr.logNamedValue("classifier", $(classifier).getClass.getCanonicalName)
// determine number of classes either from metadata if provided, or via computation.
http://git-wip-us.apache.org/repos/asf/spark/blob/e3ea93ab/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
index 9b386ef..9a5b7d5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
@@ -171,7 +171,8 @@ class GBTRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String)
instr.logDataset(dataset)
instr.logParams(this, labelCol, featuresCol, predictionCol, impurity, lossType,
maxDepth, maxBins, maxIter, maxMemoryInMB, minInfoGain, minInstancesPerNode,
- seed, stepSize, subsamplingRate, cacheNodeIds, checkpointInterval, featureSubsetStrategy)
+ seed, stepSize, subsamplingRate, cacheNodeIds, checkpointInterval, featureSubsetStrategy,
+ validationIndicatorCol, validationTol)
val (baseLearners, learnerWeights) = if (withValidation) {
GradientBoostedTrees.runWithValidation(trainDataset, validationDataset, boostingStrategy,
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org