diff --git a/examples/src/main/python/mllib/naive_bayes_example.py b/examples/src/main/python/mllib/naive_bayes_example.py index f5e120c678fcfc512f34c8726829575aa1a233c6..e7d5893d67413535ec93368edd801bb194d8523e 100644 --- a/examples/src/main/python/mllib/naive_bayes_example.py +++ b/examples/src/main/python/mllib/naive_bayes_example.py @@ -17,9 +17,15 @@ """ NaiveBayes Example. + +Usage: + `spark-submit --master local[4] examples/src/main/python/mllib/naive_bayes_example.py` """ + from __future__ import print_function +import shutil + from pyspark import SparkContext # $example on$ from pyspark.mllib.classification import NaiveBayes, NaiveBayesModel @@ -50,8 +56,15 @@ if __name__ == "__main__": # Make prediction and test accuracy. predictionAndLabel = test.map(lambda p: (model.predict(p.features), p.label)) accuracy = 1.0 * predictionAndLabel.filter(lambda (x, v): x == v).count() / test.count() + print('model accuracy {}'.format(accuracy)) # Save and load model - model.save(sc, "target/tmp/myNaiveBayesModel") - sameModel = NaiveBayesModel.load(sc, "target/tmp/myNaiveBayesModel") + output_dir = 'target/tmp/myNaiveBayesModel' + shutil.rmtree(output_dir, ignore_errors=True) + model.save(sc, output_dir) + sameModel = NaiveBayesModel.load(sc, output_dir) + predictionAndLabel = test.map(lambda p: (sameModel.predict(p.features), p.label)) + accuracy = 1.0 * predictionAndLabel.filter(lambda (x, v): x == v).count() / test.count() + print('sameModel accuracy {}'.format(accuracy)) + # $example off$