diff options
author | jyotiska <jyotiska123@gmail.com> | 2014-02-08 23:36:48 -0800 |
---|---|---|
committer | Reynold Xin <rxin@apache.org> | 2014-02-08 23:36:48 -0800 |
commit | 2ef37c93664d74de6d7f6144834883a4a4ef79b7 (patch) | |
tree | d261c255d7729b241247ad63fe7447cf84b1d14a /python | |
parent | b6d40b782327188a25ded5b22790552121e5271f (diff) | |
download | spark-2ef37c93664d74de6d7f6144834883a4a4ef79b7.tar.gz spark-2ef37c93664d74de6d7f6144834883a4a4ef79b7.tar.bz2 spark-2ef37c93664d74de6d7f6144834883a4a4ef79b7.zip |
Merge pull request #562 from jyotiska/master. Closes #562.
Added example Python code for sort
I added an example Python code for sort. Right now, PySpark has limited examples for new people willing to use the project. This example code sorts integers stored in a file. I was able to sort 5 million, 10 million and 25 million integers with this code.
Author: jyotiska <jyotiska123@gmail.com>
== Merge branch commits ==
commit 8ad8faf6c8e02ae1cd68565d98524edf165f54df
Author: jyotiska <jyotiska123@gmail.com>
Date: Sun Feb 9 11:00:41 2014 +0530
Added comments in code on collect() method
commit 6f98f1e313f4472a7c2207d36c4f0fbcebc95a8c
Author: jyotiska <jyotiska123@gmail.com>
Date: Sat Feb 8 13:12:37 2014 +0530
Updated python example code sort.py
commit 945e39a5d68daa7e5bab0d96cbd35d7c4b04eafb
Author: jyotiska <jyotiska123@gmail.com>
Date: Sat Feb 8 12:59:09 2014 +0530
Added example python code for sort
Diffstat (limited to 'python')
-rwxr-xr-x | python/examples/sort.py | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/python/examples/sort.py b/python/examples/sort.py new file mode 100755 index 0000000000..5de20a6d98 --- /dev/null +++ b/python/examples/sort.py @@ -0,0 +1,36 @@ +# +# 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. +# + +import sys + +from pyspark import SparkContext + + +if __name__ == "__main__": + if len(sys.argv) < 3: + print >> sys.stderr, "Usage: sort <master> <file>" + exit(-1) + sc = SparkContext(sys.argv[1], "PythonSort") + lines = sc.textFile(sys.argv[2], 1) + sortedCount = lines.flatMap(lambda x: x.split(' ')) \ + .map(lambda x: (int(x), 1)) \ + .sortByKey(lambda x: x) + # This is just a demo on how to bring all the sorted data back to a single node. + # In reality, we wouldn't want to collect all the data to the driver node. + output = sortedCount.collect() + for (num, unitcount) in output: + print num |