04e44b37cc
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.
159 lines
4.7 KiB
Python
159 lines
4.7 KiB
Python
#
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
import sys
|
|
if sys.version >= '3':
|
|
long = int
|
|
unicode = str
|
|
|
|
import py4j.protocol
|
|
from py4j.protocol import Py4JJavaError
|
|
from py4j.java_gateway import JavaObject
|
|
from py4j.java_collections import ListConverter, JavaArray, JavaList
|
|
|
|
from pyspark import RDD, SparkContext
|
|
from pyspark.serializers import PickleSerializer, AutoBatchedSerializer
|
|
|
|
|
|
# Hack for support float('inf') in Py4j
|
|
_old_smart_decode = py4j.protocol.smart_decode
|
|
|
|
_float_str_mapping = {
|
|
'nan': 'NaN',
|
|
'inf': 'Infinity',
|
|
'-inf': '-Infinity',
|
|
}
|
|
|
|
|
|
def _new_smart_decode(obj):
|
|
if isinstance(obj, float):
|
|
s = str(obj)
|
|
return _float_str_mapping.get(s, s)
|
|
return _old_smart_decode(obj)
|
|
|
|
py4j.protocol.smart_decode = _new_smart_decode
|
|
|
|
|
|
_picklable_classes = [
|
|
'LinkedList',
|
|
'SparseVector',
|
|
'DenseVector',
|
|
'DenseMatrix',
|
|
'Rating',
|
|
'LabeledPoint',
|
|
]
|
|
|
|
|
|
# this will call the MLlib version of pythonToJava()
|
|
def _to_java_object_rdd(rdd):
|
|
""" Return an JavaRDD of Object by unpickling
|
|
|
|
It will convert each Python object into Java object by Pyrolite, whenever the
|
|
RDD is serialized in batch or not.
|
|
"""
|
|
rdd = rdd._reserialize(AutoBatchedSerializer(PickleSerializer()))
|
|
return rdd.ctx._jvm.SerDe.pythonToJava(rdd._jrdd, True)
|
|
|
|
|
|
def _py2java(sc, obj):
|
|
""" Convert Python object into Java """
|
|
if isinstance(obj, RDD):
|
|
obj = _to_java_object_rdd(obj)
|
|
elif isinstance(obj, SparkContext):
|
|
obj = obj._jsc
|
|
elif isinstance(obj, list):
|
|
obj = ListConverter().convert([_py2java(sc, x) for x in obj], sc._gateway._gateway_client)
|
|
elif isinstance(obj, JavaObject):
|
|
pass
|
|
elif isinstance(obj, (int, long, float, bool, bytes, unicode)):
|
|
pass
|
|
else:
|
|
data = bytearray(PickleSerializer().dumps(obj))
|
|
obj = sc._jvm.SerDe.loads(data)
|
|
return obj
|
|
|
|
|
|
def _java2py(sc, r, encoding="bytes"):
|
|
if isinstance(r, JavaObject):
|
|
clsName = r.getClass().getSimpleName()
|
|
# convert RDD into JavaRDD
|
|
if clsName != 'JavaRDD' and clsName.endswith("RDD"):
|
|
r = r.toJavaRDD()
|
|
clsName = 'JavaRDD'
|
|
|
|
if clsName == 'JavaRDD':
|
|
jrdd = sc._jvm.SerDe.javaToPython(r)
|
|
return RDD(jrdd, sc)
|
|
|
|
if clsName in _picklable_classes:
|
|
r = sc._jvm.SerDe.dumps(r)
|
|
elif isinstance(r, (JavaArray, JavaList)):
|
|
try:
|
|
r = sc._jvm.SerDe.dumps(r)
|
|
except Py4JJavaError:
|
|
pass # not pickable
|
|
|
|
if isinstance(r, (bytearray, bytes)):
|
|
r = PickleSerializer().loads(bytes(r), encoding=encoding)
|
|
return r
|
|
|
|
|
|
def callJavaFunc(sc, func, *args):
|
|
""" Call Java Function """
|
|
args = [_py2java(sc, a) for a in args]
|
|
return _java2py(sc, func(*args))
|
|
|
|
|
|
def callMLlibFunc(name, *args):
|
|
""" Call API in PythonMLLibAPI """
|
|
sc = SparkContext._active_spark_context
|
|
api = getattr(sc._jvm.PythonMLLibAPI(), name)
|
|
return callJavaFunc(sc, api, *args)
|
|
|
|
|
|
class JavaModelWrapper(object):
|
|
"""
|
|
Wrapper for the model in JVM
|
|
"""
|
|
def __init__(self, java_model):
|
|
self._sc = SparkContext._active_spark_context
|
|
self._java_model = java_model
|
|
|
|
def __del__(self):
|
|
self._sc._gateway.detach(self._java_model)
|
|
|
|
def call(self, name, *a):
|
|
"""Call method of java_model"""
|
|
return callJavaFunc(self._sc, getattr(self._java_model, name), *a)
|
|
|
|
|
|
def inherit_doc(cls):
|
|
"""
|
|
A decorator that makes a class inherit documentation from its parents.
|
|
"""
|
|
for name, func in vars(cls).items():
|
|
# only inherit docstring for public functions
|
|
if name.startswith("_"):
|
|
continue
|
|
if not func.__doc__:
|
|
for parent in cls.__bases__:
|
|
parent_func = getattr(parent, name, None)
|
|
if parent_func and getattr(parent_func, "__doc__", None):
|
|
func.__doc__ = parent_func.__doc__
|
|
break
|
|
return cls
|