From 3f67382e7c9c3f6a8f6ce124ab3fcb1a9c1a264f Mon Sep 17 00:00:00 2001 From: "Joseph K. Bradley" Date: Sat, 2 Aug 2014 13:07:17 -0700 Subject: [SPARK-2478] [mllib] DecisionTree Python API Added experimental Python API for Decision Trees. API: * class DecisionTreeModel ** predict() for single examples and RDDs, taking both feature vectors and LabeledPoints ** numNodes() ** depth() ** __str__() * class DecisionTree ** trainClassifier() ** trainRegressor() ** train() Examples and testing: * Added example testing classification and regression with batch prediction: examples/src/main/python/mllib/tree.py * Have also tested example usage in doc of python/pyspark/mllib/tree.py which tests single-example prediction with dense and sparse vectors Also: Small bug fix in python/pyspark/mllib/_common.py: In _linear_predictor_typecheck, changed check for RDD to use isinstance() instead of type() in order to catch RDD subclasses. CC mengxr manishamde Author: Joseph K. Bradley Closes #1727 from jkbradley/decisiontree-python-new and squashes the following commits: 3744488 [Joseph K. Bradley] Renamed test tree.py to decision_tree_runner.py Small updates based on github review. 6b86a9d [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new affceb9 [Joseph K. Bradley] * Fixed bug in doc tests in pyspark/mllib/util.py caused by change in loadLibSVMFile behavior. (It used to threshold labels at 0 to make them 0/1, but it now leaves them as they are.) * Fixed small bug in loadLibSVMFile: If a data file had no features, then loadLibSVMFile would create a single all-zero feature. 67a29bc [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new cf46ad7 [Joseph K. Bradley] Python DecisionTreeModel * predict(empty RDD) returns an empty RDD instead of an error. * Removed support for calling predict() on LabeledPoint and RDD[LabeledPoint] * predict() does not cache serialized RDD any more. aa29873 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new bf21be4 [Joseph K. Bradley] removed old run() func from DecisionTree fa10ea7 [Joseph K. Bradley] Small style update 7968692 [Joseph K. Bradley] small braces typo fix e34c263 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 4801b40 [Joseph K. Bradley] Small style update to DecisionTreeSuite db0eab2 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix2' into decisiontree-python-new 6873fa9 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 225822f [Joseph K. Bradley] Bug: In DecisionTree, the method sequentialBinSearchForOrderedCategoricalFeatureInClassification() indexed bins from 0 to (math.pow(2, featureCategories.toInt - 1) - 1). This upper bound is the bound for unordered categorical features, not ordered ones. The upper bound should be the arity (i.e., max value) of the feature. 93953f1 [Joseph K. Bradley] Likely done with Python API. 6df89a9 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 4562c08 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 665ba78 [Joseph K. Bradley] Small updates towards Python DecisionTree API 188cb0d [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 6622247 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new b8fac57 [Joseph K. Bradley] Finished Python DecisionTree API and example but need to test a bit more. 2b20c61 [Joseph K. Bradley] Small doc and style updates 1b29c13 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 584449a [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new dab0b67 [Joseph K. Bradley] Added documentation for DecisionTree internals 8bb8aa0 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix 978cfcf [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix 6eed482 [Joseph K. Bradley] In DecisionTree: Changed from using procedural syntax for functions returning Unit to explicitly writing Unit return type. 376dca2 [Joseph K. Bradley] Updated meaning of maxDepth by 1 to fit scikit-learn and rpart. * In code, replaced usages of maxDepth <-- maxDepth + 1 * In params, replace settings of maxDepth <-- maxDepth - 1 e06e423 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new bab3f19 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 59750f8 [Joseph K. Bradley] * Updated Strategy to check numClassesForClassification only if algo=Classification. * Updates based on comments: ** DecisionTreeRunner *** Made dataFormat arg default to libsvm ** Small cleanups ** tree.Node: Made recursive helper methods private, and renamed them. 52e17c5 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix f5a036c [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new da50db7 [Joseph K. Bradley] Added one more test to DecisionTreeSuite: stump with 2 continuous variables for binary classification. Caused problems in past, but fixed now. 8e227ea [Joseph K. Bradley] Changed Strategy so it only requires numClassesForClassification >= 2 for classification cd1d933 [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 8ea8750 [Joseph K. Bradley] Bug fix: Off-by-1 when finding thresholds for splits for continuous features. 8a758db [Joseph K. Bradley] Merge branch 'decisiontree-bugfix' into decisiontree-python-new 5fe44ed [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-python-new 2283df8 [Joseph K. Bradley] 2 bug fixes. 73fbea2 [Joseph K. Bradley] Merge remote-tracking branch 'upstream/master' into decisiontree-bugfix 5f920a1 [Joseph K. Bradley] Demonstration of bug before submitting fix: Updated DecisionTreeSuite so that 3 tests fail. Will describe bug in next commit. f825352 [Joseph K. Bradley] Wrote Python API and example for DecisionTree. Also added toString, depth, and numNodes methods to DecisionTreeModel. --- python/pyspark/mllib/tree.py | 225 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 225 insertions(+) create mode 100644 python/pyspark/mllib/tree.py (limited to 'python/pyspark/mllib/tree.py') diff --git a/python/pyspark/mllib/tree.py b/python/pyspark/mllib/tree.py new file mode 100644 index 0000000000..1e0006df75 --- /dev/null +++ b/python/pyspark/mllib/tree.py @@ -0,0 +1,225 @@ +# +# 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. + + EXPERIMENTAL: 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. + :param x: Data point (feature vector), + or an RDD of data points (feature vectors). + """ + pythonAPI = self._sc._jvm.PythonMLLibAPI() + if isinstance(x, RDD): + # Bulk prediction + if x.count() == 0: + return self._sc.parallelize([]) + dataBytes = _get_unmangled_double_vector_rdd(x, cache=False) + jSerializedPreds = \ + pythonAPI.predictDecisionTreeModel(self._java_model, + dataBytes._jrdd) + serializedPreds = RDD(jSerializedPreds, self._sc, NoOpSerializer()) + return serializedPreds.map(lambda bytes: _deserialize_double(bytearray(bytes))) + 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. + + EXPERIMENTAL: 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: Training data: RDD of LabeledPoint. + Labels are integers {0,1,...,numClasses}. + :param numClasses: Number of classes for classification. + :param categoricalFeaturesInfo: Map from categorical feature index + to number of categories. + Any feature not in this map + is treated as continuous. + :param impurity: Supported values: "entropy" or "gini" + :param maxDepth: Max depth of tree. + E.g., depth 0 means 1 leaf node. + Depth 1 means 1 internal node + 2 leaf nodes. + :param maxBins: Number of bins used for finding splits at each node. + :return: DecisionTreeModel + """ + return DecisionTree.train(data, "classification", numClasses, + categoricalFeaturesInfo, + impurity, maxDepth, maxBins) + + @staticmethod + def trainRegressor(data, categoricalFeaturesInfo={}, + impurity="variance", maxDepth=4, maxBins=100): + """ + Train a DecisionTreeModel for regression. + + :param data: Training data: RDD of LabeledPoint. + Labels are real numbers. + :param categoricalFeaturesInfo: Map from categorical feature index + to number of categories. + Any feature not in this map + is treated as continuous. + :param impurity: Supported values: "variance" + :param maxDepth: Max depth of tree. + E.g., depth 0 means 1 leaf node. + Depth 1 means 1 internal node + 2 leaf nodes. + :param maxBins: Number of bins used for finding splits at each node. + :return: DecisionTreeModel + """ + return DecisionTree.train(data, "regression", 0, + categoricalFeaturesInfo, + impurity, maxDepth, maxBins) + + + @staticmethod + def train(data, algo, numClasses, categoricalFeaturesInfo, + impurity, maxDepth, maxBins=100): + """ + Train a DecisionTreeModel for classification or regression. + + :param data: Training data: RDD of LabeledPoint. + For classification, labels are integers + {0,1,...,numClasses}. + For regression, labels are real numbers. + :param algo: "classification" or "regression" + :param numClasses: Number of classes for classification. + :param categoricalFeaturesInfo: Map from categorical feature index + to number of categories. + Any feature not in this map + is treated as continuous. + :param impurity: For classification: "entropy" or "gini". + For regression: "variance". + :param maxDepth: Max depth of tree. + E.g., depth 0 means 1 leaf node. + Depth 1 means 1 internal node + 2 leaf nodes. + :param maxBins: Number of bins used for finding splits at each node. + :return: DecisionTreeModel + """ + sc = data.context + dataBytes = _get_unmangled_labeled_point_rdd(data) + categoricalFeaturesInfoJMap = \ + MapConverter().convert(categoricalFeaturesInfo, + sc._gateway._gateway_client) + model = sc._jvm.PythonMLLibAPI().trainDecisionTreeModel( + dataBytes._jrdd, algo, + numClasses, categoricalFeaturesInfoJMap, + impurity, maxDepth, maxBins) + dataBytes.unpersist() + return DecisionTreeModel(sc, model) + + +def _test(): + import doctest + globs = globals().copy() + globs['sc'] = SparkContext('local[4]', 'PythonTest', batchSize=2) + (failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS) + globs['sc'].stop() + if failure_count: + exit(-1) + +if __name__ == "__main__": + _test() -- cgit v1.2.3