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.
114 lines
3.9 KiB
Python
114 lines
3.9 KiB
Python
"""
|
|
Copyright (c) 2011, Douban Inc. <http://www.douban.com/>
|
|
All rights reserved.
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions are
|
|
met:
|
|
|
|
* Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
* Redistributions in binary form must reproduce the above
|
|
copyright notice, this list of conditions and the following disclaimer
|
|
in the documentation and/or other materials provided with the
|
|
distribution.
|
|
|
|
* Neither the name of the Douban Inc. nor the names of its
|
|
contributors may be used to endorse or promote products derived from
|
|
this software without specific prior written permission.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
"""
|
|
|
|
from pyspark.resultiterable import ResultIterable
|
|
from functools import reduce
|
|
|
|
|
|
def _do_python_join(rdd, other, numPartitions, dispatch):
|
|
vs = rdd.mapValues(lambda v: (1, v))
|
|
ws = other.mapValues(lambda v: (2, v))
|
|
return vs.union(ws).groupByKey(numPartitions).flatMapValues(lambda x: dispatch(x.__iter__()))
|
|
|
|
|
|
def python_join(rdd, other, numPartitions):
|
|
def dispatch(seq):
|
|
vbuf, wbuf = [], []
|
|
for (n, v) in seq:
|
|
if n == 1:
|
|
vbuf.append(v)
|
|
elif n == 2:
|
|
wbuf.append(v)
|
|
return ((v, w) for v in vbuf for w in wbuf)
|
|
return _do_python_join(rdd, other, numPartitions, dispatch)
|
|
|
|
|
|
def python_right_outer_join(rdd, other, numPartitions):
|
|
def dispatch(seq):
|
|
vbuf, wbuf = [], []
|
|
for (n, v) in seq:
|
|
if n == 1:
|
|
vbuf.append(v)
|
|
elif n == 2:
|
|
wbuf.append(v)
|
|
if not vbuf:
|
|
vbuf.append(None)
|
|
return ((v, w) for v in vbuf for w in wbuf)
|
|
return _do_python_join(rdd, other, numPartitions, dispatch)
|
|
|
|
|
|
def python_left_outer_join(rdd, other, numPartitions):
|
|
def dispatch(seq):
|
|
vbuf, wbuf = [], []
|
|
for (n, v) in seq:
|
|
if n == 1:
|
|
vbuf.append(v)
|
|
elif n == 2:
|
|
wbuf.append(v)
|
|
if not wbuf:
|
|
wbuf.append(None)
|
|
return ((v, w) for v in vbuf for w in wbuf)
|
|
return _do_python_join(rdd, other, numPartitions, dispatch)
|
|
|
|
|
|
def python_full_outer_join(rdd, other, numPartitions):
|
|
def dispatch(seq):
|
|
vbuf, wbuf = [], []
|
|
for (n, v) in seq:
|
|
if n == 1:
|
|
vbuf.append(v)
|
|
elif n == 2:
|
|
wbuf.append(v)
|
|
if not vbuf:
|
|
vbuf.append(None)
|
|
if not wbuf:
|
|
wbuf.append(None)
|
|
return [(v, w) for v in vbuf for w in wbuf]
|
|
return _do_python_join(rdd, other, numPartitions, dispatch)
|
|
|
|
|
|
def python_cogroup(rdds, numPartitions):
|
|
def make_mapper(i):
|
|
return lambda v: (i, v)
|
|
vrdds = [rdd.mapValues(make_mapper(i)) for i, rdd in enumerate(rdds)]
|
|
union_vrdds = reduce(lambda acc, other: acc.union(other), vrdds)
|
|
rdd_len = len(vrdds)
|
|
|
|
def dispatch(seq):
|
|
bufs = [[] for _ in range(rdd_len)]
|
|
for n, v in seq:
|
|
bufs[n].append(v)
|
|
return tuple(ResultIterable(vs) for vs in bufs)
|
|
|
|
return union_vrdds.groupByKey(numPartitions).mapValues(dispatch)
|