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 2019/07/20 15:45:10 UTC
[spark] branch master updated: [SPARK-28243][PYSPARK][ML] Remove
setFeatureSubsetStrategy and setSubsamplingRate from Python
TreeEnsembleParams
This is an automated email from the ASF dual-hosted git repository.
srowen pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 72c80ee [SPARK-28243][PYSPARK][ML] Remove setFeatureSubsetStrategy and setSubsamplingRate from Python TreeEnsembleParams
72c80ee is described below
commit 72c80ee81ca4c3c9569749b54e2db0ec91b128a5
Author: Huaxin Gao <hu...@us.ibm.com>
AuthorDate: Sat Jul 20 10:44:33 2019 -0500
[SPARK-28243][PYSPARK][ML] Remove setFeatureSubsetStrategy and setSubsamplingRate from Python TreeEnsembleParams
## What changes were proposed in this pull request?
Remove deprecated setFeatureSubsetStrategy and setSubsamplingRate from Python TreeEnsembleParams
## How was this patch tested?
Use existing tests.
Closes #25046 from huaxingao/spark-28243.
Authored-by: Huaxin Gao <hu...@us.ibm.com>
Signed-off-by: Sean Owen <se...@databricks.com>
---
python/pyspark/ml/classification.py | 157 +++++++++++++++++++++++++++++--
python/pyspark/ml/param/shared.py | 36 --------
python/pyspark/ml/regression.py | 180 ++++++++++++++++++++++++++++++------
3 files changed, 300 insertions(+), 73 deletions(-)
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py
index c257ace..ce65439 100644
--- a/python/pyspark/ml/classification.py
+++ b/python/pyspark/ml/classification.py
@@ -875,13 +875,6 @@ class TreeClassifierParams(object):
super(TreeClassifierParams, self).__init__()
@since("1.6.0")
- def setImpurity(self, value):
- """
- Sets the value of :py:attr:`impurity`.
- """
- return self._set(impurity=value)
-
- @since("1.6.0")
def getImpurity(self):
"""
Gets the value of impurity or its default value.
@@ -1003,6 +996,49 @@ class DecisionTreeClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasWeig
def _create_model(self, java_model):
return DecisionTreeClassificationModel(java_model)
+ def setMaxDepth(self, value):
+ """
+ Sets the value of :py:attr:`maxDepth`.
+ """
+ return self._set(maxDepth=value)
+
+ def setMaxBins(self, value):
+ """
+ Sets the value of :py:attr:`maxBins`.
+ """
+ return self._set(maxBins=value)
+
+ def setMinInstancesPerNode(self, value):
+ """
+ Sets the value of :py:attr:`minInstancesPerNode`.
+ """
+ return self._set(minInstancesPerNode=value)
+
+ def setMinInfoGain(self, value):
+ """
+ Sets the value of :py:attr:`minInfoGain`.
+ """
+ return self._set(minInfoGain=value)
+
+ def setMaxMemoryInMB(self, value):
+ """
+ Sets the value of :py:attr:`maxMemoryInMB`.
+ """
+ return self._set(maxMemoryInMB=value)
+
+ def setCacheNodeIds(self, value):
+ """
+ Sets the value of :py:attr:`cacheNodeIds`.
+ """
+ return self._set(cacheNodeIds=value)
+
+ @since("1.4.0")
+ def setImpurity(self, value):
+ """
+ Sets the value of :py:attr:`impurity`.
+ """
+ return self._set(impurity=value)
+
@inherit_doc
class DecisionTreeClassificationModel(DecisionTreeModel, JavaClassificationModel, JavaMLWritable,
@@ -1133,6 +1169,63 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred
def _create_model(self, java_model):
return RandomForestClassificationModel(java_model)
+ def setMaxDepth(self, value):
+ """
+ Sets the value of :py:attr:`maxDepth`.
+ """
+ return self._set(maxDepth=value)
+
+ def setMaxBins(self, value):
+ """
+ Sets the value of :py:attr:`maxBins`.
+ """
+ return self._set(maxBins=value)
+
+ def setMinInstancesPerNode(self, value):
+ """
+ Sets the value of :py:attr:`minInstancesPerNode`.
+ """
+ return self._set(minInstancesPerNode=value)
+
+ def setMinInfoGain(self, value):
+ """
+ Sets the value of :py:attr:`minInfoGain`.
+ """
+ return self._set(minInfoGain=value)
+
+ def setMaxMemoryInMB(self, value):
+ """
+ Sets the value of :py:attr:`maxMemoryInMB`.
+ """
+ return self._set(maxMemoryInMB=value)
+
+ def setCacheNodeIds(self, value):
+ """
+ Sets the value of :py:attr:`cacheNodeIds`.
+ """
+ return self._set(cacheNodeIds=value)
+
+ @since("1.4.0")
+ def setImpurity(self, value):
+ """
+ Sets the value of :py:attr:`impurity`.
+ """
+ return self._set(impurity=value)
+
+ @since("1.4.0")
+ def setNumTrees(self, value):
+ """
+ Sets the value of :py:attr:`numTrees`.
+ """
+ return self._set(numTrees=value)
+
+ @since("1.4.0")
+ def setSubsamplingRate(self, value):
+ """
+ Sets the value of :py:attr:`subsamplingRate`.
+ """
+ return self._set(subsamplingRate=value)
+
@since("2.4.0")
def setFeatureSubsetStrategy(self, value):
"""
@@ -1317,6 +1410,49 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
def _create_model(self, java_model):
return GBTClassificationModel(java_model)
+ def setMaxDepth(self, value):
+ """
+ Sets the value of :py:attr:`maxDepth`.
+ """
+ return self._set(maxDepth=value)
+
+ def setMaxBins(self, value):
+ """
+ Sets the value of :py:attr:`maxBins`.
+ """
+ return self._set(maxBins=value)
+
+ def setMinInstancesPerNode(self, value):
+ """
+ Sets the value of :py:attr:`minInstancesPerNode`.
+ """
+ return self._set(minInstancesPerNode=value)
+
+ def setMinInfoGain(self, value):
+ """
+ Sets the value of :py:attr:`minInfoGain`.
+ """
+ return self._set(minInfoGain=value)
+
+ def setMaxMemoryInMB(self, value):
+ """
+ Sets the value of :py:attr:`maxMemoryInMB`.
+ """
+ return self._set(maxMemoryInMB=value)
+
+ def setCacheNodeIds(self, value):
+ """
+ Sets the value of :py:attr:`cacheNodeIds`.
+ """
+ return self._set(cacheNodeIds=value)
+
+ @since("1.4.0")
+ def setImpurity(self, value):
+ """
+ Sets the value of :py:attr:`impurity`.
+ """
+ return self._set(impurity=value)
+
@since("1.4.0")
def setLossType(self, value):
"""
@@ -1324,6 +1460,13 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
"""
return self._set(lossType=value)
+ @since("1.4.0")
+ def setSubsamplingRate(self, value):
+ """
+ Sets the value of :py:attr:`subsamplingRate`.
+ """
+ return self._set(subsamplingRate=value)
+
@since("2.4.0")
def setFeatureSubsetStrategy(self, value):
"""
diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py
index 6405b9f..56d6190 100644
--- a/python/pyspark/ml/param/shared.py
+++ b/python/pyspark/ml/param/shared.py
@@ -765,72 +765,36 @@ class DecisionTreeParams(Params):
def __init__(self):
super(DecisionTreeParams, self).__init__()
- def setMaxDepth(self, value):
- """
- Sets the value of :py:attr:`maxDepth`.
- """
- return self._set(maxDepth=value)
-
def getMaxDepth(self):
"""
Gets the value of maxDepth or its default value.
"""
return self.getOrDefault(self.maxDepth)
- def setMaxBins(self, value):
- """
- Sets the value of :py:attr:`maxBins`.
- """
- return self._set(maxBins=value)
-
def getMaxBins(self):
"""
Gets the value of maxBins or its default value.
"""
return self.getOrDefault(self.maxBins)
- def setMinInstancesPerNode(self, value):
- """
- Sets the value of :py:attr:`minInstancesPerNode`.
- """
- return self._set(minInstancesPerNode=value)
-
def getMinInstancesPerNode(self):
"""
Gets the value of minInstancesPerNode or its default value.
"""
return self.getOrDefault(self.minInstancesPerNode)
- def setMinInfoGain(self, value):
- """
- Sets the value of :py:attr:`minInfoGain`.
- """
- return self._set(minInfoGain=value)
-
def getMinInfoGain(self):
"""
Gets the value of minInfoGain or its default value.
"""
return self.getOrDefault(self.minInfoGain)
- def setMaxMemoryInMB(self, value):
- """
- Sets the value of :py:attr:`maxMemoryInMB`.
- """
- return self._set(maxMemoryInMB=value)
-
def getMaxMemoryInMB(self):
"""
Gets the value of maxMemoryInMB or its default value.
"""
return self.getOrDefault(self.maxMemoryInMB)
- def setCacheNodeIds(self, value):
- """
- Sets the value of :py:attr:`cacheNodeIds`.
- """
- return self._set(cacheNodeIds=value)
-
def getCacheNodeIds(self):
"""
Gets the value of cacheNodeIds or its default value.
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
index 927cc77..349130f 100644
--- a/python/pyspark/ml/regression.py
+++ b/python/pyspark/ml/regression.py
@@ -610,13 +610,6 @@ class TreeEnsembleParams(DecisionTreeParams):
super(TreeEnsembleParams, self).__init__()
@since("1.4.0")
- def setSubsamplingRate(self, value):
- """
- Sets the value of :py:attr:`subsamplingRate`.
- """
- return self._set(subsamplingRate=value)
-
- @since("1.4.0")
def getSubsamplingRate(self):
"""
Gets the value of subsamplingRate or its default value.
@@ -624,15 +617,6 @@ class TreeEnsembleParams(DecisionTreeParams):
return self.getOrDefault(self.subsamplingRate)
@since("1.4.0")
- def setFeatureSubsetStrategy(self, value):
- """
- Sets the value of :py:attr:`featureSubsetStrategy`.
-
- .. note:: Deprecated in 2.4.0 and will be removed in 3.0.0.
- """
- return self._set(featureSubsetStrategy=value)
-
- @since("1.4.0")
def getFeatureSubsetStrategy(self):
"""
Gets the value of featureSubsetStrategy or its default value.
@@ -656,13 +640,6 @@ class HasVarianceImpurity(Params):
super(HasVarianceImpurity, self).__init__()
@since("1.4.0")
- def setImpurity(self, value):
- """
- Sets the value of :py:attr:`impurity`.
- """
- return self._set(impurity=value)
-
- @since("1.4.0")
def getImpurity(self):
"""
Gets the value of impurity or its default value.
@@ -686,13 +663,6 @@ class RandomForestParams(TreeEnsembleParams):
super(RandomForestParams, self).__init__()
@since("1.4.0")
- def setNumTrees(self, value):
- """
- Sets the value of :py:attr:`numTrees`.
- """
- return self._set(numTrees=value)
-
- @since("1.4.0")
def getNumTrees(self):
"""
Gets the value of numTrees or its default value.
@@ -843,6 +813,49 @@ class DecisionTreeRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasWeigh
def _create_model(self, java_model):
return DecisionTreeRegressionModel(java_model)
+ def setMaxDepth(self, value):
+ """
+ Sets the value of :py:attr:`maxDepth`.
+ """
+ return self._set(maxDepth=value)
+
+ def setMaxBins(self, value):
+ """
+ Sets the value of :py:attr:`maxBins`.
+ """
+ return self._set(maxBins=value)
+
+ def setMinInstancesPerNode(self, value):
+ """
+ Sets the value of :py:attr:`minInstancesPerNode`.
+ """
+ return self._set(minInstancesPerNode=value)
+
+ def setMinInfoGain(self, value):
+ """
+ Sets the value of :py:attr:`minInfoGain`.
+ """
+ return self._set(minInfoGain=value)
+
+ def setMaxMemoryInMB(self, value):
+ """
+ Sets the value of :py:attr:`maxMemoryInMB`.
+ """
+ return self._set(maxMemoryInMB=value)
+
+ def setCacheNodeIds(self, value):
+ """
+ Sets the value of :py:attr:`cacheNodeIds`.
+ """
+ return self._set(cacheNodeIds=value)
+
+ @since("1.4.0")
+ def setImpurity(self, value):
+ """
+ Sets the value of :py:attr:`impurity`.
+ """
+ return self._set(impurity=value)
+
@inherit_doc
class DecisionTreeModel(JavaModel, JavaPredictionModel):
@@ -1036,6 +1049,63 @@ class RandomForestRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredi
def _create_model(self, java_model):
return RandomForestRegressionModel(java_model)
+ def setMaxDepth(self, value):
+ """
+ Sets the value of :py:attr:`maxDepth`.
+ """
+ return self._set(maxDepth=value)
+
+ def setMaxBins(self, value):
+ """
+ Sets the value of :py:attr:`maxBins`.
+ """
+ return self._set(maxBins=value)
+
+ def setMinInstancesPerNode(self, value):
+ """
+ Sets the value of :py:attr:`minInstancesPerNode`.
+ """
+ return self._set(minInstancesPerNode=value)
+
+ def setMinInfoGain(self, value):
+ """
+ Sets the value of :py:attr:`minInfoGain`.
+ """
+ return self._set(minInfoGain=value)
+
+ def setMaxMemoryInMB(self, value):
+ """
+ Sets the value of :py:attr:`maxMemoryInMB`.
+ """
+ return self._set(maxMemoryInMB=value)
+
+ def setCacheNodeIds(self, value):
+ """
+ Sets the value of :py:attr:`cacheNodeIds`.
+ """
+ return self._set(cacheNodeIds=value)
+
+ @since("1.4.0")
+ def setImpurity(self, value):
+ """
+ Sets the value of :py:attr:`impurity`.
+ """
+ return self._set(impurity=value)
+
+ @since("1.4.0")
+ def setNumTrees(self, value):
+ """
+ Sets the value of :py:attr:`numTrees`.
+ """
+ return self._set(numTrees=value)
+
+ @since("1.4.0")
+ def setSubsamplingRate(self, value):
+ """
+ Sets the value of :py:attr:`subsamplingRate`.
+ """
+ return self._set(subsamplingRate=value)
+
@since("2.4.0")
def setFeatureSubsetStrategy(self, value):
"""
@@ -1180,6 +1250,49 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol,
def _create_model(self, java_model):
return GBTRegressionModel(java_model)
+ def setMaxDepth(self, value):
+ """
+ Sets the value of :py:attr:`maxDepth`.
+ """
+ return self._set(maxDepth=value)
+
+ def setMaxBins(self, value):
+ """
+ Sets the value of :py:attr:`maxBins`.
+ """
+ return self._set(maxBins=value)
+
+ def setMinInstancesPerNode(self, value):
+ """
+ Sets the value of :py:attr:`minInstancesPerNode`.
+ """
+ return self._set(minInstancesPerNode=value)
+
+ def setMinInfoGain(self, value):
+ """
+ Sets the value of :py:attr:`minInfoGain`.
+ """
+ return self._set(minInfoGain=value)
+
+ def setMaxMemoryInMB(self, value):
+ """
+ Sets the value of :py:attr:`maxMemoryInMB`.
+ """
+ return self._set(maxMemoryInMB=value)
+
+ def setCacheNodeIds(self, value):
+ """
+ Sets the value of :py:attr:`cacheNodeIds`.
+ """
+ return self._set(cacheNodeIds=value)
+
+ @since("1.4.0")
+ def setImpurity(self, value):
+ """
+ Sets the value of :py:attr:`impurity`.
+ """
+ return self._set(impurity=value)
+
@since("1.4.0")
def setLossType(self, value):
"""
@@ -1187,6 +1300,13 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol,
"""
return self._set(lossType=value)
+ @since("1.4.0")
+ def setSubsamplingRate(self, value):
+ """
+ Sets the value of :py:attr:`subsamplingRate`.
+ """
+ return self._set(subsamplingRate=value)
+
@since("2.4.0")
def setFeatureSubsetStrategy(self, value):
"""
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org