change the default value of featureSubsetStrategy to "all" in GBTClassifier and GBTRegressor

Author: huaxingao

python/pyspark/ml/classification.py

@@ -1201,7 +1201,7 @@ class GBTClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol
     >>> td = si_model.transform(df)
     >>> gbt = GBTClassifier(maxIter=5, maxDepth=2, labelCol="indexed", seed=42)
     >>> gbt.getFeatureSubsetStrategy()
-    'auto'
+    'all'
     >>> model = gbt.fit(td)
     >>> model.featureImportances
     SparseVector(1, {0: 1.0})
@@ -1256,21 +1256,21 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, lossType="logistic",
                  maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0,
-                 featureSubsetStrategy="auto"):
+                 featureSubsetStrategy="all"):
         """
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                  maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
                  lossType="logistic", maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0, \
-                 featureSubsetStrategy="auto")
+                 featureSubsetStrategy="all")
         """
         super(GBTClassifier, self).__init__()
         self._java_obj = self._new_java_obj(
             "org.apache.spark.ml.classification.GBTClassifier", self.uid)
         self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                          maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
                          lossType="logistic", maxIter=20, stepSize=0.1, subsamplingRate=1.0,
-                         featureSubsetStrategy="auto")
+                         featureSubsetStrategy="all")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1280,13 +1280,13 @@ def setParams(self, featuresCol="features", labelCol="label", predictionCol="pre
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                   maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10,
                   lossType="logistic", maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0,
-                  featureSubsetStrategy="auto"):
+                  featureSubsetStrategy="all"):
         """
         setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                   maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, \
                   lossType="logistic", maxIter=20, stepSize=0.1, seed=None, subsamplingRate=1.0, \
-                  featureSubsetStrategy="auto")
+                  featureSubsetStrategy="all")
         Sets params for Gradient Boosted Tree Classification.
         """
         kwargs = self._input_kwargs

python/pyspark/ml/regression.py

@@ -1041,7 +1041,7 @@ class GBTRegressor(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol,
     >>> print(gbt.getImpurity())
     variance
     >>> print(gbt.getFeatureSubsetStrategy())
-    auto
+    all
     >>> model = gbt.fit(df)
     >>> model.featureImportances
     SparseVector(1, {0: 1.0})
@@ -1092,20 +1092,20 @@ def __init__(self, featuresCol="features", labelCol="label", predictionCol="pred
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                  maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0,
                  checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1, seed=None,
-                 impurity="variance", featureSubsetStrategy="auto"):
+                 impurity="variance", featureSubsetStrategy="all"):
         """
         __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                  maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                  maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0, \
                  checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1, seed=None, \
-                 impurity="variance", featureSubsetStrategy="auto")
+                 impurity="variance", featureSubsetStrategy="all")
         """
         super(GBTRegressor, self).__init__()
         self._java_obj = self._new_java_obj("org.apache.spark.ml.regression.GBTRegressor", self.uid)
         self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                          maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0,
                          checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1,
-                         impurity="variance", featureSubsetStrategy="auto")
+                         impurity="variance", featureSubsetStrategy="all")
         kwargs = self._input_kwargs
         self.setParams(**kwargs)
 
@@ -1115,13 +1115,13 @@ def setParams(self, featuresCol="features", labelCol="label", predictionCol="pre
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0,
                   maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0,
                   checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1, seed=None,
-                  impuriy="variance", featureSubsetStrategy="auto"):
+                  impuriy="variance", featureSubsetStrategy="all"):
         """
         setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \
                   maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \
                   maxMemoryInMB=256, cacheNodeIds=False, subsamplingRate=1.0, \
                   checkpointInterval=10, lossType="squared", maxIter=20, stepSize=0.1, seed=None, \
-                  impurity="variance", featureSubsetStrategy="auto")
+                  impurity="variance", featureSubsetStrategy="all")
         Sets params for Gradient Boosted Tree Regression.
         """
         kwargs = self._input_kwargs