diff options
Diffstat (limited to 'examples/src/main/python/mllib/svm_with_sgd_example.py')
-rw-r--r-- | examples/src/main/python/mllib/svm_with_sgd_example.py | 47 |
1 files changed, 47 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/svm_with_sgd_example.py b/examples/src/main/python/mllib/svm_with_sgd_example.py new file mode 100644 index 0000000000..309ab09cc3 --- /dev/null +++ b/examples/src/main/python/mllib/svm_with_sgd_example.py @@ -0,0 +1,47 @@ +# +# 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 pyspark import SparkContext +# $example on$ +from pyspark.mllib.classification import SVMWithSGD, SVMModel +from pyspark.mllib.regression import LabeledPoint +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="PythonSVMWithSGDExample") + + # $example on$ + # Load and parse the data + def parsePoint(line): + values = [float(x) for x in line.split(' ')] + return LabeledPoint(values[0], values[1:]) + + data = sc.textFile("data/mllib/sample_svm_data.txt") + parsedData = data.map(parsePoint) + + # Build the model + model = SVMWithSGD.train(parsedData, iterations=100) + + # Evaluating the model on training data + labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features))) + trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count()) + print("Training Error = " + str(trainErr)) + + # Save and load model + model.save(sc, "target/tmp/pythonSVMWithSGDModel") + sameModel = SVMModel.load(sc, "target/tmp/pythonSVMWithSGDModel") + # $example off$ |