examples/src/main/r/ml/fpm.R

#
# 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.
#

# To run this example use
# ./bin/spark-submit examples/src/main/r/ml/fpm.R

# Load SparkR library into your R session
library(SparkR)

# Initialize SparkSession
sparkR.session(appName = "SparkR-ML-fpm-example")

# $example on$
# Load training data

df <- selectExpr(createDataFrame(data.frame(rawItems = c(
  "1,2,5", "1,2,3,5", "1,2"
))), "split(rawItems, ',') AS items")

fpm <- spark.fpGrowth(df, itemsCol="items", minSupport=0.5, minConfidence=0.6)

# Extracting frequent itemsets

spark.freqItemsets(fpm)

# Extracting association rules

spark.associationRules(fpm)

# Predict uses association rules to and combines possible consequents

predict(fpm, df)

# $example off$

sparkR.session.stop()