python/ml/fpgrowth_example.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 """
0019 An example demonstrating FPGrowth.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/fpgrowth_example.py
0022 """
0023 # $example on$
0024 from pyspark.ml.fpm import FPGrowth
0025 # $example off$
0026 from pyspark.sql import SparkSession
0027
0028 if __name__ == "__main__":
0029     spark = SparkSession\
0030         .builder\
0031         .appName("FPGrowthExample")\
0032         .getOrCreate()
0033
0034     # $example on$
0035     df = spark.createDataFrame([
0036         (0, [1, 2, 5]),
0037         (1, [1, 2, 3, 5]),
0038         (2, [1, 2])
0039     ], ["id", "items"])
0040
0041     fpGrowth = FPGrowth(itemsCol="items", minSupport=0.5, minConfidence=0.6)
0042     model = fpGrowth.fit(df)
0043
0044     # Display frequent itemsets.
0045     model.freqItemsets.show()
0046
0047     # Display generated association rules.
0048     model.associationRules.show()
0049
0050     # transform examines the input items against all the association rules and summarize the
0051     # consequents as prediction
0052     model.transform(df).show()
0053     # $example off$
0054
0055     spark.stop()