Skip to content
Snippets Groups Projects
  • Davies Liu's avatar
    04e44b37
    [SPARK-4897] [PySpark] Python 3 support · 04e44b37
    Davies Liu authored
    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.
    04e44b37
    History
    [SPARK-4897] [PySpark] Python 3 support
    Davies Liu authored
    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.
rddsampler.py 4.15 KiB
#
# 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
import random
import math


class RDDSamplerBase(object):

    def __init__(self, withReplacement, seed=None):
        self._seed = seed if seed is not None else random.randint(0, sys.maxsize)
        self._withReplacement = withReplacement
        self._random = None

    def initRandomGenerator(self, split):
        self._random = random.Random(self._seed ^ split)

        # mixing because the initial seeds are close to each other
        for _ in range(10):
            self._random.randint(0, 1)

    def getUniformSample(self):
        return self._random.random()

    def getPoissonSample(self, mean):
        # Using Knuth's algorithm described in
        # http://en.wikipedia.org/wiki/Poisson_distribution
        if mean < 20.0:
            # one exp and k+1 random calls
            l = math.exp(-mean)
            p = self._random.random()
            k = 0
            while p > l:
                k += 1
                p *= self._random.random()
        else:
            # switch to the log domain, k+1 expovariate (random + log) calls
            p = self._random.expovariate(mean)
            k = 0
            while p < 1.0:
                k += 1
                p += self._random.expovariate(mean)
        return k

    def func(self, split, iterator):
        raise NotImplementedError


class RDDSampler(RDDSamplerBase):

    def __init__(self, withReplacement, fraction, seed=None):
        RDDSamplerBase.__init__(self, withReplacement, seed)
        self._fraction = fraction

    def func(self, split, iterator):
        self.initRandomGenerator(split)
        if self._withReplacement:
            for obj in iterator:
                # For large datasets, the expected number of occurrences of each element in
                # a sample with replacement is Poisson(frac). We use that to get a count for
                # each element.
                count = self.getPoissonSample(self._fraction)
                for _ in range(0, count):
                    yield obj
        else:
            for obj in iterator:
                if self.getUniformSample() < self._fraction:
                    yield obj


class RDDRangeSampler(RDDSamplerBase):

    def __init__(self, lowerBound, upperBound, seed=None):
        RDDSamplerBase.__init__(self, False, seed)
        self._lowerBound = lowerBound
        self._upperBound = upperBound

    def func(self, split, iterator):
        self.initRandomGenerator(split)
        for obj in iterator:
            if self._lowerBound <= self.getUniformSample() < self._upperBound:
                yield obj


class RDDStratifiedSampler(RDDSamplerBase):

    def __init__(self, withReplacement, fractions, seed=None):
        RDDSamplerBase.__init__(self, withReplacement, seed)
        self._fractions = fractions

    def func(self, split, iterator):
        self.initRandomGenerator(split)
        if self._withReplacement:
            for key, val in iterator:
                # For large datasets, the expected number of occurrences of each element in
                # a sample with replacement is Poisson(frac). We use that to get a count for
                # each element.
                count = self.getPoissonSample(self._fractions[key])
                for _ in range(0, count):
                    yield key, val
        else:
            for key, val in iterator:
                if self.getUniformSample() < self._fractions[key]:
                    yield key, val