[SPARK-4897] [PySpark] Python 3 support

This PR update PySpark to support Python 3 (tested with 3.4).

Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped.

TODO: ec2/spark-ec2.py is not fully tested with python3.

Author: Davies Liu <davies@databricks.com>
Author: twneale <twneale@gmail.com>
Author: Josh Rosen <joshrosen@databricks.com>

Closes #5173 from davies/python3 and squashes the following commits:

d7d6323 [Davies Liu] fix tests
6c52a98 [Davies Liu] fix mllib test
99e334f [Davies Liu] update timeout
b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
cafd5ec [Davies Liu] adddress comments from @mengxr
bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
179fc8d [Davies Liu] tuning flaky tests
8c8b957 [Davies Liu] fix ResourceWarning in Python 3
5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
4006829 [Davies Liu] fix test
2fc0066 [Davies Liu] add python3 path
71535e9 [Davies Liu] fix xrange and divide
5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ed498c8 [Davies Liu] fix compatibility with python 3
820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ad7c374 [Davies Liu] fix mllib test and warning
ef1fc2f [Davies Liu] fix tests
4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
59bb492 [Davies Liu] fix tests
1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ca0fdd3 [Davies Liu] fix code style
9563a15 [Davies Liu] add imap back for python 2
0b1ec04 [Davies Liu] make python examples work with Python 3
d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
a716d34 [Davies Liu] test with python 3.4
f1700e8 [Davies Liu] fix test in python3
671b1db [Davies Liu] fix test in python3
692ff47 [Davies Liu] fix flaky test
7b9699f [Davies Liu] invalidate import cache for Python 3.3+
9c58497 [Davies Liu] fix kill worker
309bfbf [Davies Liu] keep compatibility
5707476 [Davies Liu] cleanup, fix hash of string in 3.3+
8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
f53e1f0 [Davies Liu] fix tests
70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3
a39167e [Davies Liu] support customize class in __main__
814c77b [Davies Liu] run unittests with python 3
7f4476e [Davies Liu] mllib tests passed
d737924 [Davies Liu] pass ml tests
375ea17 [Davies Liu] SQL tests pass
6cc42a9 [Davies Liu] rename
431a8de [Davies Liu] streaming tests pass
78901a7 [Davies Liu] fix hash of serializer in Python 3
24b2f2e [Davies Liu] pass all RDD tests
35f48fe [Davies Liu] run future again
1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py
6e3c21d [Davies Liu] make cloudpickle work with Python3
2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run
1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out
7354371 [twneale] buffer --> memoryview  I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work.
b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?).
f40d925 [twneale] xrange --> range
e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206
79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper
2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3
854be27 [Josh Rosen] Run `futurize` on Python code:
7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.

1 files changed, 28 insertions, 20 deletions

diff --git a/python/pyspark/mllib/linalg.py b/python/pyspark/mllib/linalg.py
index a80320c52d..38b3aa3ad4 100644
--- a/python/pyspark/mllib/linalg.py
+++ b/python/pyspark/mllib/linalg.py
@@ -25,7 +25,13 @@ SciPy is available in their environment.
 
 import sys
 import array
-import copy_reg
+
+if sys.version >= '3':
+    basestring = str
+    xrange = range
+    import copyreg as copy_reg
+else:
+    import copy_reg
 
 import numpy as np
 
@@ -57,7 +63,7 @@ except:
 def _convert_to_vector(l):
     if isinstance(l, Vector):
         return l
-    elif type(l) in (array.array, np.array, np.ndarray, list, tuple):
+    elif type(l) in (array.array, np.array, np.ndarray, list, tuple, xrange):
         return DenseVector(l)
     elif _have_scipy and scipy.sparse.issparse(l):
         assert l.shape[1] == 1, "Expected column vector"
@@ -88,7 +94,7 @@ def _vector_size(v):
     """
     if isinstance(v, Vector):
         return len(v)
-    elif type(v) in (array.array, list, tuple):
+    elif type(v) in (array.array, list, tuple, xrange):
         return len(v)
     elif type(v) == np.ndarray:
         if v.ndim == 1 or (v.ndim == 2 and v.shape[1] == 1):
@@ -193,7 +199,7 @@ class DenseVector(Vector):
     DenseVector([1.0, 0.0])
     """
     def __init__(self, ar):
-        if isinstance(ar, basestring):
+        if isinstance(ar, bytes):
             ar = np.frombuffer(ar, dtype=np.float64)
         elif not isinstance(ar, np.ndarray):
             ar = np.array(ar, dtype=np.float64)
@@ -321,11 +327,13 @@ class DenseVector(Vector):
     __sub__ = _delegate("__sub__")
     __mul__ = _delegate("__mul__")
     __div__ = _delegate("__div__")
+    __truediv__ = _delegate("__truediv__")
     __mod__ = _delegate("__mod__")
     __radd__ = _delegate("__radd__")
     __rsub__ = _delegate("__rsub__")
     __rmul__ = _delegate("__rmul__")
     __rdiv__ = _delegate("__rdiv__")
+    __rtruediv__ = _delegate("__rtruediv__")
     __rmod__ = _delegate("__rmod__")
 
 
@@ -344,12 +352,12 @@ class SparseVector(Vector):
         :param args: Non-zero entries, as a dictionary, list of tupes,
                or two sorted lists containing indices and values.
 
-        >>> print SparseVector(4, {1: 1.0, 3: 5.5})
-        (4,[1,3],[1.0,5.5])
-        >>> print SparseVector(4, [(1, 1.0), (3, 5.5)])
-        (4,[1,3],[1.0,5.5])
-        >>> print SparseVector(4, [1, 3], [1.0, 5.5])
-        (4,[1,3],[1.0,5.5])
+        >>> SparseVector(4, {1: 1.0, 3: 5.5})
+        SparseVector(4, {1: 1.0, 3: 5.5})
+        >>> SparseVector(4, [(1, 1.0), (3, 5.5)])
+        SparseVector(4, {1: 1.0, 3: 5.5})
+        >>> SparseVector(4, [1, 3], [1.0, 5.5])
+        SparseVector(4, {1: 1.0, 3: 5.5})
         """
         self.size = int(size)
         assert 1 <= len(args) <= 2, "must pass either 2 or 3 arguments"
@@ -361,8 +369,8 @@ class SparseVector(Vector):
             self.indices = np.array([p[0] for p in pairs], dtype=np.int32)
             self.values = np.array([p[1] for p in pairs], dtype=np.float64)
         else:
-            if isinstance(args[0], basestring):
-                assert isinstance(args[1], str), "values should be string too"
+            if isinstance(args[0], bytes):
+                assert isinstance(args[1], bytes), "values should be string too"
                 if args[0]:
                     self.indices = np.frombuffer(args[0], np.int32)
                     self.values = np.frombuffer(args[1], np.float64)
@@ -591,12 +599,12 @@ class Vectors(object):
         :param args: Non-zero entries, as a dictionary, list of tupes,
                      or two sorted lists containing indices and values.
 
-        >>> print Vectors.sparse(4, {1: 1.0, 3: 5.5})
-        (4,[1,3],[1.0,5.5])
-        >>> print Vectors.sparse(4, [(1, 1.0), (3, 5.5)])
-        (4,[1,3],[1.0,5.5])
-        >>> print Vectors.sparse(4, [1, 3], [1.0, 5.5])
-        (4,[1,3],[1.0,5.5])
+        >>> Vectors.sparse(4, {1: 1.0, 3: 5.5})
+        SparseVector(4, {1: 1.0, 3: 5.5})
+        >>> Vectors.sparse(4, [(1, 1.0), (3, 5.5)])
+        SparseVector(4, {1: 1.0, 3: 5.5})
+        >>> Vectors.sparse(4, [1, 3], [1.0, 5.5])
+        SparseVector(4, {1: 1.0, 3: 5.5})
         """
         return SparseVector(size, *args)
 
@@ -645,7 +653,7 @@ class Matrix(object):
         """
         Convert Matrix attributes which are array-like or buffer to array.
         """
-        if isinstance(array_like, basestring):
+        if isinstance(array_like, bytes):
             return np.frombuffer(array_like, dtype=dtype)
         return np.asarray(array_like, dtype=dtype)
 
@@ -677,7 +685,7 @@ class DenseMatrix(Matrix):
     def toSparse(self):
         """Convert to SparseMatrix"""
         indices = np.nonzero(self.values)[0]
-        colCounts = np.bincount(indices / self.numRows)
+        colCounts = np.bincount(indices // self.numRows)
         colPtrs = np.cumsum(np.hstack(
             (0, colCounts, np.zeros(self.numCols - colCounts.size))))
         values = self.values[indices]