Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/1727#discussion_r15725411
--- Diff: python/pyspark/mllib/tree.py ---
@@ -0,0 +1,219 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from py4j.java_collections import MapConverter
+
+from pyspark import SparkContext, RDD
+from pyspark.mllib._common import \
+ _get_unmangled_rdd, _get_unmangled_double_vector_rdd,
_serialize_double_vector, \
+ _deserialize_labeled_point, _get_unmangled_labeled_point_rdd, \
+ _deserialize_double
+from pyspark.mllib.regression import LabeledPoint
+from pyspark.serializers import NoOpSerializer
+
+class DecisionTreeModel(object):
+ """
+ A decision tree model for classification or regression.
+
+ WARNING: This is an experimental API. It will probably be modified
for Spark v1.2.
+ """
+
+ def __init__(self, sc, java_model):
+ """
+ :param sc: Spark context
+ :param java_model: Handle to Java model object
+ """
+ self._sc = sc
+ self._java_model = java_model
+
+ def __del__(self):
+ self._sc._gateway.detach(self._java_model)
+
+ def predict(self, x):
+ """
+ Predict the label of one or more examples.
+ NOTE: This currently does NOT support batch prediction.
+
+ :param x: Data point: feature vector, or a LabeledPoint (whose
label is ignored).
+ """
+ pythonAPI = self._sc._jvm.PythonMLLibAPI()
+ if isinstance(x, RDD):
+ # Bulk prediction
+ if x.count() == 0:
+ raise RuntimeError("DecisionTreeModel.predict(x) given
empty RDD x.")
+ elementType = type(x.take(1)[0])
+ if elementType == LabeledPoint:
+ x = x.map(lambda x: x.features)
+ dataBytes = _get_unmangled_double_vector_rdd(x)
+ jSerializedPreds =
pythonAPI.predictDecisionTreeModel(self._java_model, dataBytes._jrdd)
+ dataBytes.unpersist()
+ serializedPreds = RDD(jSerializedPreds, self._sc,
NoOpSerializer())
+ return serializedPreds.map(lambda bytes:
_deserialize_double(bytearray(bytes)))
+ else:
+ if type(x) == LabeledPoint:
+ x_ = _serialize_double_vector(x.features)
+ else:
+ # Assume x is a single data point.
+ x_ = _serialize_double_vector(x)
+ return pythonAPI.predictDecisionTreeModel(self._java_model, x_)
+
+ def numNodes(self):
+ return self._java_model.numNodes()
+
+ def depth(self):
+ return self._java_model.depth()
+
+ def __str__(self):
+ return self._java_model.toString()
+
+
+class DecisionTree(object):
+ """
+ Learning algorithm for a decision tree model for classification or
regression.
+
+ WARNING: This is an experimental API. It will probably be modified
for Spark v1.2.
+
+ Example usage:
+ >>> from numpy import array, ndarray
+ >>> from pyspark.mllib.regression import LabeledPoint
+ >>> from pyspark.mllib.tree import DecisionTree
+ >>> from pyspark.mllib.linalg import SparseVector
+ >>>
+ >>> data = [
+ ... LabeledPoint(0.0, [0.0]),
+ ... LabeledPoint(1.0, [1.0]),
+ ... LabeledPoint(1.0, [2.0]),
+ ... LabeledPoint(1.0, [3.0])
+ ... ]
+ >>>
+ >>> model = DecisionTree.trainClassifier(sc.parallelize(data),
numClasses=2)
+ >>> print(model)
+ DecisionTreeModel classifier
+ If (feature 0 <= 0.5)
+ Predict: 0.0
+ Else (feature 0 > 0.5)
+ Predict: 1.0
+
+ >>> model.predict(array([1.0])) > 0
+ True
+ >>> model.predict(array([0.0])) == 0
+ True
+ >>> sparse_data = [
+ ... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),
+ ... LabeledPoint(1.0, SparseVector(2, {1: 1.0})),
+ ... LabeledPoint(0.0, SparseVector(2, {0: 0.0})),
+ ... LabeledPoint(1.0, SparseVector(2, {1: 2.0}))
+ ... ]
+ >>>
+ >>> model = DecisionTree.trainRegressor(sc.parallelize(sparse_data))
+ >>> model.predict(array([0.0, 1.0])) == 1
+ True
+ >>> model.predict(array([0.0, 0.0])) == 0
+ True
+ >>> model.predict(SparseVector(2, {1: 1.0})) == 1
+ True
+ >>> model.predict(SparseVector(2, {1: 0.0})) == 0
+ True
+ """
+
+ @staticmethod
+ def trainClassifier(data, numClasses, categoricalFeaturesInfo={},
+ impurity="gini", maxDepth=4, maxBins=100):
+ """
+ Train a DecisionTreeModel for classification.
+
+ :param data: RDD of NumPy vectors, one per element, where the first
+ coordinate is the label and the rest is the feature
vector.
+ Labels are integers {0,1,...,numClasses}.
+ :param numClasses: Number of classes for classification.
+ :param categoricalFeaturesInfo: Map from categorical feature index
to number of categories.
--- End diff --
a line in python doc should not have more than 80 (or 78 to be safe) chars.
This is for people running python's help() under traditional terminals (80 x
24?)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
