Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/6499#discussion_r32784725
--- Diff: python/pyspark/mllib/clustering.py ---
@@ -21,14 +21,17 @@
if sys.version > '3':
xrange = range
-from numpy import array
+from math import exp, log
+
+from numpy import array, random, tile
-from pyspark import RDD
from pyspark import SparkContext
+from pyspark.rdd import RDD, ignore_unicode_prefix
from pyspark.mllib.common import callMLlibFunc, callJavaFunc, _py2java,
_java2py
-from pyspark.mllib.linalg import SparseVector, _convert_to_vector
+from pyspark.mllib.linalg import SparseVector, _convert_to_vector,
DenseVector
from pyspark.mllib.stat.distribution import MultivariateGaussian
from pyspark.mllib.util import Saveable, Loader, inherit_doc
+from pyspark.streaming import DStream
__all__ = ['KMeansModel', 'KMeans', 'GaussianMixtureModel',
'GaussianMixture']
--- End diff --
import `StreamingKMeans` and `StreamingKMeansModel`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
