Skip to content

[SPARK-18110][PYTHON][ML] add missing parameter in Python for RandomForest regression and classification #15638

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
felixcheung wants to merge 1 commit into from
Closed

[SPARK-18110][PYTHON][ML] add missing parameter in Python for RandomForest regression and classification #15638

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions python/pyspark/ml/classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -758,20 +758,21 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
probabilityCol="probability", rawPredictionCol="rawPrediction",
maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini",
numTrees=20, featureSubsetStrategy="auto", seed=None):
numTrees=20, featureSubsetStrategy="auto", seed=None, subsamplingRate=1.0):
Copy link
Contributor

@wangmiao1981 wangmiao1981 Oct 26, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add some doc string tests?

Copy link
Member Author

@felixcheung felixcheung Oct 26, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

generally spark avoid having too many verbose tests in python doc string, so I think we are ok here.

"""
__init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
probabilityCol="probability", rawPredictionCol="rawPrediction", \
maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", \
numTrees=20, featureSubsetStrategy="auto", seed=None)
numTrees=20, featureSubsetStrategy="auto", seed=None, subsamplingRate=1.0)
"""
super(RandomForestClassifier, self).__init__()
self._java_obj = self._new_java_obj(
"org.apache.spark.ml.classification.RandomForestClassifier", self.uid)
self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
impurity="gini", numTrees=20, featureSubsetStrategy="auto")
impurity="gini", numTrees=20, featureSubsetStrategy="auto",
subsamplingRate=1.0)
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)

Expand All @@ -781,13 +782,13 @@ def setParams(self, featuresCol="features", labelCol="label", predictionCol="pre
probabilityCol="probability", rawPredictionCol="rawPrediction",
maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None,
impurity="gini", numTrees=20, featureSubsetStrategy="auto"):
impurity="gini", numTrees=20, featureSubsetStrategy="auto", subsamplingRate=1.0):
"""
setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
probabilityCol="probability", rawPredictionCol="rawPrediction", \
maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None, \
impurity="gini", numTrees=20, featureSubsetStrategy="auto")
impurity="gini", numTrees=20, featureSubsetStrategy="auto", subsamplingRate=1.0)
Sets params for linear classification.
"""
kwargs = self.setParams._input_kwargs
Expand Down
12 changes: 6 additions & 6 deletions python/pyspark/ml/regression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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):
Expand Down Expand Up @@ -828,7 +828,7 @@ def featureImportances(self):
@inherit_doc
class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol, HasSeed,
RandomForestParams, TreeRegressorParams, HasCheckpointInterval,
JavaMLWritable, JavaMLReadable):
JavaMLWritable, JavaMLReadable, HasVarianceCol):
Copy link
Contributor

@wangmiao1981 wangmiao1981 Oct 26, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would you like to group all the Has* parameters? Just a minor comment on the style.

Copy link
Member Author

@felixcheung felixcheung Oct 26, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

that doesn't seem to be the existing style, so adding to the end instead

"""
`Random Forest <http://en.wikipedia.org/wiki/Random_forest>`_
learning algorithm for regression.
Expand Down Expand Up @@ -876,13 +876,13 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
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(
Expand All @@ -900,13 +900,13 @@ def setParams(self, featuresCol="features", labelCol="label", predictionCol="pre
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
Expand Down