diff options
author | Joseph K. Bradley <joseph.kurata.bradley@gmail.com> | 2014-08-02 13:07:17 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2014-08-02 13:07:17 -0700 |
commit | 3f67382e7c9c3f6a8f6ce124ab3fcb1a9c1a264f (patch) | |
tree | 1a39b613599d552f2fbdd1679f78f205887d1698 /examples/src/main/python/mllib | |
parent | e09e18b3123c20e9b9497cf606473da500349d4d (diff) | |
download | spark-3f67382e7c9c3f6a8f6ce124ab3fcb1a9c1a264f.tar.gz spark-3f67382e7c9c3f6a8f6ce124ab3fcb1a9c1a264f.tar.bz2 spark-3f67382e7c9c3f6a8f6ce124ab3fcb1a9c1a264f.zip |
[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 <joseph.kurata.bradley@gmail.com>
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.
Diffstat (limited to 'examples/src/main/python/mllib')
-rwxr-xr-x | examples/src/main/python/mllib/decision_tree_runner.py | 133 | ||||
-rwxr-xr-x | examples/src/main/python/mllib/logistic_regression.py | 4 |
2 files changed, 136 insertions, 1 deletions
diff --git a/examples/src/main/python/mllib/decision_tree_runner.py b/examples/src/main/python/mllib/decision_tree_runner.py new file mode 100755 index 0000000000..8efadb5223 --- /dev/null +++ b/examples/src/main/python/mllib/decision_tree_runner.py @@ -0,0 +1,133 @@ +# +# 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. +# + +""" +Decision tree classification and regression using MLlib. +""" + +import numpy, os, sys + +from operator import add + +from pyspark import SparkContext +from pyspark.mllib.regression import LabeledPoint +from pyspark.mllib.tree import DecisionTree +from pyspark.mllib.util import MLUtils + + +def getAccuracy(dtModel, data): + """ + Return accuracy of DecisionTreeModel on the given RDD[LabeledPoint]. + """ + seqOp = (lambda acc, x: acc + (x[0] == x[1])) + predictions = dtModel.predict(data.map(lambda x: x.features)) + truth = data.map(lambda p: p.label) + trainCorrect = predictions.zip(truth).aggregate(0, seqOp, add) + if data.count() == 0: + return 0 + return trainCorrect / (0.0 + data.count()) + + +def getMSE(dtModel, data): + """ + Return mean squared error (MSE) of DecisionTreeModel on the given + RDD[LabeledPoint]. + """ + seqOp = (lambda acc, x: acc + numpy.square(x[0] - x[1])) + predictions = dtModel.predict(data.map(lambda x: x.features)) + truth = data.map(lambda p: p.label) + trainMSE = predictions.zip(truth).aggregate(0, seqOp, add) + if data.count() == 0: + return 0 + return trainMSE / (0.0 + data.count()) + + +def reindexClassLabels(data): + """ + Re-index class labels in a dataset to the range {0,...,numClasses-1}. + If all labels in that range already appear at least once, + then the returned RDD is the same one (without a mapping). + Note: If a label simply does not appear in the data, + the index will not include it. + Be aware of this when reindexing subsampled data. + :param data: RDD of LabeledPoint where labels are integer values + denoting labels for a classification problem. + :return: Pair (reindexedData, origToNewLabels) where + reindexedData is an RDD of LabeledPoint with labels in + the range {0,...,numClasses-1}, and + origToNewLabels is a dictionary mapping original labels + to new labels. + """ + # classCounts: class --> # examples in class + classCounts = data.map(lambda x: x.label).countByValue() + numExamples = sum(classCounts.values()) + sortedClasses = sorted(classCounts.keys()) + numClasses = len(classCounts) + # origToNewLabels: class --> index in 0,...,numClasses-1 + if (numClasses < 2): + print >> sys.stderr, \ + "Dataset for classification should have at least 2 classes." + \ + " The given dataset had only %d classes." % numClasses + exit(1) + origToNewLabels = dict([(sortedClasses[i], i) for i in range(0, numClasses)]) + + print "numClasses = %d" % numClasses + print "Per-class example fractions, counts:" + print "Class\tFrac\tCount" + for c in sortedClasses: + frac = classCounts[c] / (numExamples + 0.0) + print "%g\t%g\t%d" % (c, frac, classCounts[c]) + + if (sortedClasses[0] == 0 and sortedClasses[-1] == numClasses - 1): + return (data, origToNewLabels) + else: + reindexedData = \ + data.map(lambda x: LabeledPoint(origToNewLabels[x.label], x.features)) + return (reindexedData, origToNewLabels) + + +def usage(): + print >> sys.stderr, \ + "Usage: decision_tree_runner [libsvm format data filepath]\n" + \ + " Note: This only supports binary classification." + exit(1) + + +if __name__ == "__main__": + if len(sys.argv) > 2: + usage() + sc = SparkContext(appName="PythonDT") + + # Load data. + dataPath = 'data/mllib/sample_libsvm_data.txt' + if len(sys.argv) == 2: + dataPath = sys.argv[1] + if not os.path.isfile(dataPath): + usage() + points = MLUtils.loadLibSVMFile(sc, dataPath) + + # Re-index class labels if needed. + (reindexedData, origToNewLabels) = reindexClassLabels(points) + + # Train a classifier. + model = DecisionTree.trainClassifier(reindexedData, numClasses=2) + # Print learned tree and stats. + print "Trained DecisionTree for classification:" + print " Model numNodes: %d\n" % model.numNodes() + print " Model depth: %d\n" % model.depth() + print " Training accuracy: %g\n" % getAccuracy(model, reindexedData) + print model diff --git a/examples/src/main/python/mllib/logistic_regression.py b/examples/src/main/python/mllib/logistic_regression.py index 6e0f7a4ee5..9d547ff77c 100755 --- a/examples/src/main/python/mllib/logistic_regression.py +++ b/examples/src/main/python/mllib/logistic_regression.py @@ -30,8 +30,10 @@ from pyspark.mllib.regression import LabeledPoint from pyspark.mllib.classification import LogisticRegressionWithSGD -# Parse a line of text into an MLlib LabeledPoint object def parsePoint(line): + """ + Parse a line of text into an MLlib LabeledPoint object. + """ values = [float(s) for s in line.split(' ')] if values[0] == -1: # Convert -1 labels to 0 for MLlib values[0] = 0 |