naive_bayes.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.
#

from __future__ import print_function

# $example on$
from pyspark.ml.classification import NaiveBayes
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
# $example off$
from pyspark.sql import SparkSession
import sys

if __name__ == "__main__":
    spark = SparkSession\
        .builder\
        .appName("NaiveBayesExample")\
        .getOrCreate()

    # $example on$
    # Load training data
    data = spark.read.format("libsvm") \
        .load(sys.argv[1])

    # Split the data into train and test
    splits = data.randomSplit([0.8, 0.2], 1234)
    train = splits[0]
    test = splits[1]

    # create the trainer and set its parameters
    nb = NaiveBayes(smoothing=1.0, modelType="multinomial")

    # train the model
    model = nb.fit(train)

    # select example rows to display.
    predictions = model.transform(test)
    predictions.show()

    # compute accuracy on the test set
    evaluator = MulticlassClassificationEvaluator(labelCol="label", predictionCol="prediction",
                                                  metricName="accuracy")
    accuracy = evaluator.evaluate(predictions)
    print("Test set accuracy = " + str(accuracy))
    # $example off$

    if sys.argv[2] == "Test":
        classify_file = spark.read.format("libsvm") \
            .load(sys.argv[3])
        predictions = model.transform(classify_file)
        print("Unknow data")
        predictions.show()

    spark.stop()