multilayer_perceptron.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 MultilayerPerceptronClassifier
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
# $example off$
from pyspark.sql import SparkSession
import sys
if __name__ == "__main__":
    spark = SparkSession\
        .builder.appName("multilayer_perceptron_text").getOrCreate()

    # $example on$
    # Load training data
    data = spark.read.format("libsvm")\
        .load(sys.argv[1])
    print("------------------------------")
    print(data)
    # Split the data into train and test
    splits = data.randomSplit([0.8, 0.2], 1234)
    train = splits[0]
    test = splits[1]

    # specify layers for the neural network:
    # input layer of size 4 (features), two intermediate of size 5 and 4
    # and output of size 3 (classes)
    layers = [114, 4]

    # create the trainer and set its parameters
    trainer = MultilayerPerceptronClassifier(maxIter=100, layers=layers, blockSize=128, seed=1234)

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

    # compute accuracy on the test set
    result = model.transform(test)
    predictionAndLabels = result.select("prediction", "label")
    evaluator = MulticlassClassificationEvaluator(metricName="accuracy")
    print("Test set accuracy = " + str(evaluator.evaluate(predictionAndLabels)))
    # $example off$

    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()