naive_bayes_example.py

#
# 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.
#

"""
NaiveBayes Example.

Usage:
  `spark-submit --master local[4] examples/src/main/python/mllib/naive_bayes_example.py`
"""

import shutil

from pyspark import SparkContext
# $example on$
from pyspark.mllib.classification import NaiveBayes, NaiveBayesModel
from pyspark.mllib.util import MLUtils


# $example off$

if __name__ == "__main__":

    sc = SparkContext(appName="PythonNaiveBayesExample")

    # $example on$
    # Load and parse the data file.
    data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

    # Split data approximately into training (60%) and test (40%)
    training, test = data.randomSplit([0.6, 0.4])

    # Train a naive Bayes model.
    model = NaiveBayes.train(training, 1.0)

    # Make prediction and test accuracy.
    predictionAndLabel = test.map(lambda p: (model.predict(p.features), p.label))
    accuracy = 1.0 * predictionAndLabel.filter(lambda pl: pl[0] == pl[1]).count() / test.count()
    print('model accuracy {}'.format(accuracy))

    # Save and load model
    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 pl: pl[0] == pl[1]).count() / test.count()
    print('sameModel accuracy {}'.format(accuracy))

    # $example off$