diff options
| author | Josh Rosen <joshrosen@eecs.berkeley.edu> | 2013-01-01 13:52:14 -0800 |
|---|---|---|
| committer | Josh Rosen <joshrosen@eecs.berkeley.edu> | 2013-01-01 13:52:14 -0800 |
| commit | 170e451fbdd308ae77065bd9c0f2bd278abf0cb7 (patch) | |
| tree | da3df59e2262dac4b381227d5bc712502249d746 /pyspark/examples/kmeans.py | |
| parent | 6f6a6b79c4c3f3555f8ff427c91e714d02afe8fa (diff) | |
| download | spark-170e451fbdd308ae77065bd9c0f2bd278abf0cb7.tar.gz spark-170e451fbdd308ae77065bd9c0f2bd278abf0cb7.tar.bz2 spark-170e451fbdd308ae77065bd9c0f2bd278abf0cb7.zip | |
Minor documentation and style fixes for PySpark.
Diffstat (limited to 'pyspark/examples/kmeans.py')
| -rw-r--r-- | pyspark/examples/kmeans.py | 13 |
1 files changed, 8 insertions, 5 deletions
diff --git a/pyspark/examples/kmeans.py b/pyspark/examples/kmeans.py index 9cc366f03c..ad2be21178 100644 --- a/pyspark/examples/kmeans.py +++ b/pyspark/examples/kmeans.py @@ -1,18 +1,21 @@ +""" +This example requires numpy (http://www.numpy.org/) +""" import sys -from pyspark.context import SparkContext -from numpy import array, sum as np_sum +import numpy as np +from pyspark import SparkContext def parseVector(line): - return array([float(x) for x in line.split(' ')]) + return np.array([float(x) for x in line.split(' ')]) def closestPoint(p, centers): bestIndex = 0 closest = float("+inf") for i in range(len(centers)): - tempDist = np_sum((p - centers[i]) ** 2) + tempDist = np.sum((p - centers[i]) ** 2) if tempDist < closest: closest = tempDist bestIndex = i @@ -41,7 +44,7 @@ if __name__ == "__main__": newPoints = pointStats.map( lambda (x, (y, z)): (x, y / z)).collect() - tempDist = sum(np_sum((kPoints[x] - y) ** 2) for (x, y) in newPoints) + tempDist = sum(np.sum((kPoints[x] - y) ** 2) for (x, y) in newPoints) for (x, y) in newPoints: kPoints[x] = y |