diff options
author | Pravin Gadakh <pravingadakh177@gmail.com> | 2015-11-04 08:32:08 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-11-04 08:32:08 -0800 |
commit | 820064e613609bbf7edd726d982da1de60bf417a (patch) | |
tree | 93fce4b0355c6a3dd82ff30315a3419f8af30b4b /examples/src/main/python/mllib | |
parent | e328b69c31821e4b27673d7ef6182ab3b7a05ca8 (diff) | |
download | spark-820064e613609bbf7edd726d982da1de60bf417a.tar.gz spark-820064e613609bbf7edd726d982da1de60bf417a.tar.bz2 spark-820064e613609bbf7edd726d982da1de60bf417a.zip |
[SPARK-11380][DOCS] Replace example code in mllib-frequent-pattern-mining.md using include_example
Author: Pravin Gadakh <pravingadakh177@gmail.com>
Author: Pravin Gadakh <prgadakh@in.ibm.com>
Closes #9340 from pravingadakh/SPARK-11380.
Diffstat (limited to 'examples/src/main/python/mllib')
-rw-r--r-- | examples/src/main/python/mllib/fpgrowth_example.py | 33 |
1 files changed, 33 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/fpgrowth_example.py b/examples/src/main/python/mllib/fpgrowth_example.py new file mode 100644 index 0000000000..715f526820 --- /dev/null +++ b/examples/src/main/python/mllib/fpgrowth_example.py @@ -0,0 +1,33 @@ +# +# 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. +# + +# $example on$ +from pyspark.mllib.fpm import FPGrowth +# $example off$ +from pyspark import SparkContext + +if __name__ == "__main__": + sc = SparkContext(appName="FPGrowth") + + # $example on$ + data = sc.textFile("data/mllib/sample_fpgrowth.txt") + transactions = data.map(lambda line: line.strip().split(' ')) + model = FPGrowth.train(transactions, minSupport=0.2, numPartitions=10) + result = model.freqItemsets().collect() + for fi in result: + print(fi) + # $example off$ |