Updated based on davies recommendation

python/docs/pyspark.mllib.rst

@@ -36,10 +36,10 @@ pyspark.mllib.linalg module
     :undoc-members:
     :show-inheritance:
 
-pyspark.mllib.rand module
+pyspark.mllib.random module
 ---------------------------
 
-.. automodule:: pyspark.mllib.rand
+.. automodule:: pyspark.mllib.random
     :members:
     :undoc-members:
     :show-inheritance:

python/pyspark/mllib/__init__.py

@@ -32,29 +32,4 @@
 import rand as random
 random.__name__ = 'random'
 random.RandomRDDs.__module__ = __name__ + '.random'
-
-
-class RandomModuleHook(object):
-    """
-    Hook to import pyspark.mllib.random
-    """
-    fullname = __name__ + '.random'
-
-    def find_module(self, name, path=None):
-        # skip all other modules
-        if not name.startswith(self.fullname):
-            return
-        return self
-
-    def load_module(self, name):
-        if name == self.fullname:
-            return random
-
-        cname = name.rsplit('.', 1)[-1]
-        try:
-            return getattr(random, cname)
-        except AttributeError:
-            raise ImportError
-
-
-sys.meta_path.append(RandomModuleHook())
+sys.modules[__name__ + '.random'] = random

python/pyspark/mllib/tests.py

@@ -36,7 +36,7 @@
 from pyspark.mllib.linalg import Vector, SparseVector, DenseVector, VectorUDT, _convert_to_vector,\
     DenseMatrix
 from pyspark.mllib.regression import LabeledPoint
-from pyspark.mllib.rand import RandomRDDs
+from pyspark.mllib.random import RandomRDDs
 from pyspark.mllib.stat import Statistics
 from pyspark.serializers import PickleSerializer
 from pyspark.sql import SQLContext