1 files changed, 58 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/random_forest_classification_example.py b/examples/src/main/python/mllib/random_forest_classification_example.py
new file mode 100644
index 0000000000..324ba50625
--- /dev/null
+++ b/examples/src/main/python/mllib/random_forest_classification_example.py
@@ -0,0 +1,58 @@
+#
+# 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.
+#
+
+"""
+Random Forest Classification Example.
+"""
+from __future__ import print_function
+
+import sys
+
+from pyspark import SparkContext
+# $example on$
+from pyspark.mllib.tree import RandomForest, RandomForestModel
+from pyspark.mllib.util import MLUtils
+# $example off$
+
+if __name__ == "__main__":
+    sc = SparkContext(appName="PythonRandomForestClassificationExample")
+    # $example on$
+    # Load and parse the data file into an RDD of LabeledPoint.
+    data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt')
+    # Split the data into training and test sets (30% held out for testing)
+    (trainingData, testData) = data.randomSplit([0.7, 0.3])
+
+    # Train a RandomForest model.
+    #  Empty categoricalFeaturesInfo indicates all features are continuous.
+    #  Note: Use larger numTrees in practice.
+    #  Setting featureSubsetStrategy="auto" lets the algorithm choose.
+    model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
+                                         numTrees=3, featureSubsetStrategy="auto",
+                                         impurity='gini', maxDepth=4, maxBins=32)
+
+    # Evaluate model on test instances and compute test error
+    predictions = model.predict(testData.map(lambda x: x.features))
+    labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
+    testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
+    print('Test Error = ' + str(testErr))
+    print('Learned classification forest model:')
+    print(model.toDebugString())
+
+    # Save and load model
+    model.save(sc, "target/tmp/myRandomForestClassificationModel")
+    sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestClassificationModel")
+    # $example off$