[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, 10 insertions, 10 deletions

diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py
index 8eaddcf8b9..c6ed5acd17 100644
--- a/python/pyspark/mllib/tests.py
+++ b/python/pyspark/mllib/tests.py
@@ -72,11 +72,11 @@ class VectorTests(PySparkTestCase):
     def _test_serialize(self, v):
         self.assertEqual(v, ser.loads(ser.dumps(v)))
         jvec = self.sc._jvm.SerDe.loads(bytearray(ser.dumps(v)))
-        nv = ser.loads(str(self.sc._jvm.SerDe.dumps(jvec)))
+        nv = ser.loads(bytes(self.sc._jvm.SerDe.dumps(jvec)))
         self.assertEqual(v, nv)
         vs = [v] * 100
         jvecs = self.sc._jvm.SerDe.loads(bytearray(ser.dumps(vs)))
-        nvs = ser.loads(str(self.sc._jvm.SerDe.dumps(jvecs)))
+        nvs = ser.loads(bytes(self.sc._jvm.SerDe.dumps(jvecs)))
         self.assertEqual(vs, nvs)
 
     def test_serialize(self):
@@ -412,11 +412,11 @@ class StatTests(PySparkTestCase):
         self.assertEqual(10, len(summary.normL1()))
         self.assertEqual(10, len(summary.normL2()))
 
-        data2 = self.sc.parallelize(xrange(10)).map(lambda x: Vectors.dense(x))
+        data2 = self.sc.parallelize(range(10)).map(lambda x: Vectors.dense(x))
         summary2 = Statistics.colStats(data2)
         self.assertEqual(array([45.0]), summary2.normL1())
         import math
-        expectedNormL2 = math.sqrt(sum(map(lambda x: x*x, xrange(10))))
+        expectedNormL2 = math.sqrt(sum(map(lambda x: x*x, range(10))))
         self.assertTrue(math.fabs(summary2.normL2()[0] - expectedNormL2) < 1e-14)
 
 
@@ -438,11 +438,11 @@ class VectorUDTTests(PySparkTestCase):
     def test_infer_schema(self):
         sqlCtx = SQLContext(self.sc)
         rdd = self.sc.parallelize([LabeledPoint(1.0, self.dv1), LabeledPoint(0.0, self.sv1)])
-        srdd = sqlCtx.inferSchema(rdd)
-        schema = srdd.schema
+        df = rdd.toDF()
+        schema = df.schema
         field = [f for f in schema.fields if f.name == "features"][0]
         self.assertEqual(field.dataType, self.udt)
-        vectors = srdd.map(lambda p: p.features).collect()
+        vectors = df.map(lambda p: p.features).collect()
         self.assertEqual(len(vectors), 2)
         for v in vectors:
             if isinstance(v, SparseVector):
@@ -695,7 +695,7 @@ class ChiSqTestTests(PySparkTestCase):
 
 class SerDeTest(PySparkTestCase):
     def test_to_java_object_rdd(self):  # SPARK-6660
-        data = RandomRDDs.uniformRDD(self.sc, 10, 5, seed=0L)
+        data = RandomRDDs.uniformRDD(self.sc, 10, 5, seed=0)
         self.assertEqual(_to_java_object_rdd(data).count(), 10)
 
 
@@ -771,7 +771,7 @@ class StandardScalerTests(PySparkTestCase):
 
 if __name__ == "__main__":
     if not _have_scipy:
-        print "NOTE: Skipping SciPy tests as it does not seem to be installed"
+        print("NOTE: Skipping SciPy tests as it does not seem to be installed")
     unittest.main()
     if not _have_scipy:
-        print "NOTE: SciPy tests were skipped as it does not seem to be installed"
+        print("NOTE: SciPy tests were skipped as it does not seem to be installed")