diff options
author | Sandeep <sandeep@techaddict.me> | 2014-05-06 17:27:52 -0700 |
---|---|---|
committer | Matei Zaharia <matei@databricks.com> | 2014-05-06 17:27:52 -0700 |
commit | a000b5c3b0438c17e9973df4832c320210c29c27 (patch) | |
tree | 446bbe902ecd6de05072357f7ef25aaeb0687b73 /examples/src/main/python/mllib/kmeans.py | |
parent | 39b8b1489ff92697e4aeec997cdc436c7079d6f8 (diff) | |
download | spark-a000b5c3b0438c17e9973df4832c320210c29c27.tar.gz spark-a000b5c3b0438c17e9973df4832c320210c29c27.tar.bz2 spark-a000b5c3b0438c17e9973df4832c320210c29c27.zip |
SPARK-1637: Clean up examples for 1.0
- [x] Move all of them into subpackages of org.apache.spark.examples (right now some are in org.apache.spark.streaming.examples, for instance, and others are in org.apache.spark.examples.mllib)
- [x] Move Python examples into examples/src/main/python
- [x] Update docs to reflect these changes
Author: Sandeep <sandeep@techaddict.me>
This patch had conflicts when merged, resolved by
Committer: Matei Zaharia <matei@databricks.com>
Closes #571 from techaddict/SPARK-1637 and squashes the following commits:
47ef86c [Sandeep] Changes based on Discussions on PR, removing use of RawTextHelper from examples
8ed2d3f [Sandeep] Docs Updated for changes, Change for java examples
5f96121 [Sandeep] Move Python examples into examples/src/main/python
0a8dd77 [Sandeep] Move all Scala Examples to org.apache.spark.examples (some are in org.apache.spark.streaming.examples, for instance, and others are in org.apache.spark.examples.mllib)
Diffstat (limited to 'examples/src/main/python/mllib/kmeans.py')
-rwxr-xr-x | examples/src/main/python/mllib/kmeans.py | 44 |
1 files changed, 44 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/kmeans.py b/examples/src/main/python/mllib/kmeans.py new file mode 100755 index 0000000000..dec82ff34f --- /dev/null +++ b/examples/src/main/python/mllib/kmeans.py @@ -0,0 +1,44 @@ +# +# 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. +# + +""" +A K-means clustering program using MLlib. + +This example requires NumPy (http://www.numpy.org/). +""" + +import sys + +import numpy as np +from pyspark import SparkContext +from pyspark.mllib.clustering import KMeans + + +def parseVector(line): + return np.array([float(x) for x in line.split(' ')]) + + +if __name__ == "__main__": + if len(sys.argv) < 4: + print >> sys.stderr, "Usage: kmeans <master> <file> <k>" + exit(-1) + sc = SparkContext(sys.argv[1], "KMeans") + lines = sc.textFile(sys.argv[2]) + data = lines.map(parseVector) + k = int(sys.argv[3]) + model = KMeans.train(data, k) + print "Final centers: " + str(model.clusterCenters) |