python/ml/prefixspan_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 PrefixSpan.
0020 Run with:
0021   bin/spark-submit examples/src/main/python/ml/prefixspan_example.py
0022 """
0023 # $example on$
0024 from pyspark.ml.fpm import PrefixSpan
0025 # $example off$
0026 from pyspark.sql import Row, SparkSession
0027
0028 if __name__ == "__main__":
0029     spark = SparkSession\
0030         .builder\
0031         .appName("PrefixSpanExample")\
0032         .getOrCreate()
0033     sc = spark.sparkContext
0034
0035     # $example on$
0036     df = sc.parallelize([Row(sequence=[[1, 2], [3]]),
0037                          Row(sequence=[[1], [3, 2], [1, 2]]),
0038                          Row(sequence=[[1, 2], [5]]),
0039                          Row(sequence=[[6]])]).toDF()
0040
0041     prefixSpan = PrefixSpan(minSupport=0.5, maxPatternLength=5,
0042                             maxLocalProjDBSize=32000000)
0043
0044     # Find frequent sequential patterns.
0045     prefixSpan.findFrequentSequentialPatterns(df).show()
0046     # $example off$
0047
0048     spark.stop()