examples/src/main/python/mllib/recommendation_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.
#

"""
Collaborative Filtering Classification Example.
"""
from __future__ import print_function

import sys

from pyspark import SparkContext

# $example on$
from pyspark.mllib.recommendation import ALS, MatrixFactorizationModel, Rating
# $example off$

if __name__ == "__main__":
    sc = SparkContext(appName="PythonCollaborativeFilteringExample")
    # $example on$
    # Load and parse the data
    data = sc.textFile("data/mllib/als/test.data")
    ratings = data.map(lambda l: l.split(','))\
        .map(lambda l: Rating(int(l[0]), int(l[1]), float(l[2])))

    # Build the recommendation model using Alternating Least Squares
    rank = 10
    numIterations = 10
    model = ALS.train(ratings, rank, numIterations)

    # Evaluate the model on training data
    testdata = ratings.map(lambda p: (p[0], p[1]))
    predictions = model.predictAll(testdata).map(lambda r: ((r[0], r[1]), r[2]))
    ratesAndPreds = ratings.map(lambda r: ((r[0], r[1]), r[2])).join(predictions)
    MSE = ratesAndPreds.map(lambda r: (r[1][0] - r[1][1])**2).mean()
    print("Mean Squared Error = " + str(MSE))

    # Save and load model
    model.save(sc, "target/tmp/myCollaborativeFilter")
    sameModel = MatrixFactorizationModel.load(sc, "target/tmp/myCollaborativeFilter")
    # $example off$