diff options
author | Reynold Xin <rxin@apache.org> | 2014-05-25 17:15:01 -0700 |
---|---|---|
committer | Reynold Xin <rxin@apache.org> | 2014-05-25 17:15:01 -0700 |
commit | d33d3c61ae9e4551aed0217e525a109e678298f2 (patch) | |
tree | 109ffeeaf31ae267bbe791051fd39f490af04aa4 /python/pyspark/mllib/clustering.py | |
parent | 14f0358b2a0a9b92526bdad6d501ab753459eaa0 (diff) | |
download | spark-d33d3c61ae9e4551aed0217e525a109e678298f2.tar.gz spark-d33d3c61ae9e4551aed0217e525a109e678298f2.tar.bz2 spark-d33d3c61ae9e4551aed0217e525a109e678298f2.zip |
Fix PEP8 violations in Python mllib.
Author: Reynold Xin <rxin@apache.org>
Closes #871 from rxin/mllib-pep8 and squashes the following commits:
848416f [Reynold Xin] Fixed a typo in the previous cleanup (c -> sc).
a8db4cd [Reynold Xin] Fix PEP8 violations in Python mllib.
Diffstat (limited to 'python/pyspark/mllib/clustering.py')
-rw-r--r-- | python/pyspark/mllib/clustering.py | 15 |
1 files changed, 7 insertions, 8 deletions
diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py index f65088c917..b380e8f6c8 100644 --- a/python/pyspark/mllib/clustering.py +++ b/python/pyspark/mllib/clustering.py @@ -30,7 +30,8 @@ class KMeansModel(object): """A clustering model derived from the k-means method. >>> data = array([0.0,0.0, 1.0,1.0, 9.0,8.0, 8.0,9.0]).reshape(4,2) - >>> model = KMeans.train(sc.parallelize(data), 2, maxIterations=10, runs=30, initializationMode="random") + >>> model = KMeans.train( + ... sc.parallelize(data), 2, maxIterations=10, runs=30, initializationMode="random") >>> model.predict(array([0.0, 0.0])) == model.predict(array([1.0, 1.0])) True >>> model.predict(array([8.0, 9.0])) == model.predict(array([9.0, 8.0])) @@ -76,18 +77,17 @@ class KMeansModel(object): class KMeans(object): @classmethod - def train(cls, data, k, maxIterations=100, runs=1, - initializationMode="k-means||"): + def train(cls, data, k, maxIterations=100, runs=1, initializationMode="k-means||"): """Train a k-means clustering model.""" sc = data.context dataBytes = _get_unmangled_double_vector_rdd(data) - ans = sc._jvm.PythonMLLibAPI().trainKMeansModel(dataBytes._jrdd, - k, maxIterations, runs, initializationMode) + ans = sc._jvm.PythonMLLibAPI().trainKMeansModel( + dataBytes._jrdd, k, maxIterations, runs, initializationMode) if len(ans) != 1: raise RuntimeError("JVM call result had unexpected length") elif type(ans[0]) != bytearray: raise RuntimeError("JVM call result had first element of type " - + type(ans[0]) + " which is not bytearray") + + type(ans[0]) + " which is not bytearray") matrix = _deserialize_double_matrix(ans[0]) return KMeansModel([row for row in matrix]) @@ -96,8 +96,7 @@ def _test(): import doctest globs = globals().copy() globs['sc'] = SparkContext('local[4]', 'PythonTest', batchSize=2) - (failure_count, test_count) = doctest.testmod(globs=globs, - optionflags=doctest.ELLIPSIS) + (failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS) globs['sc'].stop() if failure_count: exit(-1) |