[SPARK-18110][PYTHON][ML] add missing parameter in Python for RandomForest regression and classification

## What changes were proposed in this pull request?

Add subsmaplingRate to randomForestClassifier
Add varianceCol to randomForestRegressor
In Python

## How was this patch tested?

manual tests

Author: Felix Cheung <felixcheung_m@hotmail.com>

Closes #15638 from felixcheung/pyrandomforest.

1 files changed, 6 insertions, 6 deletions

diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
index 55d38033ef..9233d2e7e1 100644
--- a/python/pyspark/ml/regression.py
+++ b/python/pyspark/ml/regression.py
@@ -594,7 +594,7 @@ class RandomForestParams(TreeEnsembleParams):
     featureSubsetStrategy = \
         Param(Params._dummy(), "featureSubsetStrategy",
               "The number of features to consider for splits at each tree node. Supported " +
-              "options: " + ", ".join(supportedFeatureSubsetStrategies) + " (0.0-1.0], [1-n].",
+              "options: " + ", ".join(supportedFeatureSubsetStrategies) + ", (0.0-1.0], [1-n].",
               typeConverter=TypeConverters.toString)
 
     def __init__(self):
@@ -828,7 +828,7 @@ class DecisionTreeRegressionModel(DecisionTreeModel, JavaMLWritable, JavaMLReada
 @inherit_doc
 class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol, HasSeed,
                             RandomForestParams, TreeRegressorParams, HasCheckpointInterval,
-                            JavaMLWritable, JavaMLReadable):
+                            JavaMLWritable, JavaMLReadable, HasVarianceCol):
     """
     `Random Forest <http://en.wikipedia.org/wiki/Random_forest>`_
     learning algorithm for regression.
@@ -876,13 +876,13 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
                  impurity="variance", subsamplingRate=1.0, seed=None, numTrees=20,
-                 featureSubsetStrategy="auto"):
+                 featureSubsetStrategy="auto", varianceCol=None):
         """
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
                  impurity="variance", subsamplingRate=1.0, seed=None, numTrees=20, \
-                 featureSubsetStrategy="auto")
+                 featureSubsetStrategy="auto", varianceCol=None)
         """
         super(RandomForestRegressor, self).__init__()
         self._java_obj = self._new_java_obj(
@@ -900,13 +900,13 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                   maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
                   impurity="variance", subsamplingRate=1.0, seed=None, numTrees=20,
-                  featureSubsetStrategy="auto"):
+                  featureSubsetStrategy="auto", varianceCol=None):
         """
         setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                   maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
                   impurity="variance", subsamplingRate=1.0, seed=None, numTrees=20, \
-                  featureSubsetStrategy="auto")
+                  featureSubsetStrategy="auto", varianceCol=None)
         Sets params for linear regression.
         """
         kwargs = self.setParams._input_kwargs