diff options
author | Josh Rosen <joshrosen@eecs.berkeley.edu> | 2013-01-09 21:21:23 -0800 |
---|---|---|
committer | Josh Rosen <joshrosen@eecs.berkeley.edu> | 2013-01-09 21:21:23 -0800 |
commit | d55f2b98822faa7d71f5fce2bfa980f8265e0610 (patch) | |
tree | 60600cbc73ed0b676e394fb9bc442b0da0461aa2 /python | |
parent | 1a64432ba50904c3933d8a9539a619fc94b3b30b (diff) | |
download | spark-d55f2b98822faa7d71f5fce2bfa980f8265e0610.tar.gz spark-d55f2b98822faa7d71f5fce2bfa980f8265e0610.tar.bz2 spark-d55f2b98822faa7d71f5fce2bfa980f8265e0610.zip |
Use take() instead of takeSample() in PySpark kmeans example.
This is a temporary change until we port takeSample().
Diffstat (limited to 'python')
-rw-r--r-- | python/examples/kmeans.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/python/examples/kmeans.py b/python/examples/kmeans.py index ad2be21178..72cf9f88c6 100644 --- a/python/examples/kmeans.py +++ b/python/examples/kmeans.py @@ -33,7 +33,9 @@ if __name__ == "__main__": K = int(sys.argv[3]) convergeDist = float(sys.argv[4]) - kPoints = data.takeSample(False, K, 34) + # TODO: change this after we port takeSample() + #kPoints = data.takeSample(False, K, 34) + kPoints = data.take(K) tempDist = 1.0 while tempDist > convergeDist: |