d614967b0b
As described in [SPARK-2627](https://issues.apache.org/jira/browse/SPARK-2627), we'd like Python code to automatically be checked for PEP 8 compliance by Jenkins. This pull request aims to do that. Notes: * We may need to install [`pep8`](https://pypi.python.org/pypi/pep8) on the build server. * I'm expecting tests to fail now that PEP 8 compliance is being checked as part of the build. I'm fine with cleaning up any remaining PEP 8 violations as part of this pull request. * I did not understand why the RAT and scalastyle reports are saved to text files. I did the same for the PEP 8 check, but only so that the console output style can match those for the RAT and scalastyle checks. The PEP 8 report is removed right after the check is complete. * Updates to the ["Contributing to Spark"](https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark) guide will be submitted elsewhere, as I don't believe that text is part of the Spark repo. Author: Nicholas Chammas <nicholas.chammas@gmail.com> Author: nchammas <nicholas.chammas@gmail.com> Closes #1744 from nchammas/master and squashes the following commits: 274b238 [Nicholas Chammas] [SPARK-2627] [PySpark] minor indentation changes 983d963 [nchammas] Merge pull request #5 from apache/master 1db5314 [nchammas] Merge pull request #4 from apache/master 0e0245f [Nicholas Chammas] [SPARK-2627] undo erroneous whitespace fixes bf30942 [Nicholas Chammas] [SPARK-2627] PEP8: comment spacing 6db9a44 [nchammas] Merge pull request #3 from apache/master 7b4750e [Nicholas Chammas] merge upstream changes 91b7584 [Nicholas Chammas] [SPARK-2627] undo unnecessary line breaks 44e3e56 [Nicholas Chammas] [SPARK-2627] use tox.ini to exclude files b09fae2 [Nicholas Chammas] don't wrap comments unnecessarily bfb9f9f [Nicholas Chammas] [SPARK-2627] keep up with the PEP 8 fixes 9da347f [nchammas] Merge pull request #2 from apache/master aa5b4b5 [Nicholas Chammas] [SPARK-2627] follow Spark bash style for if blocks d0a83b9 [Nicholas Chammas] [SPARK-2627] check that pep8 downloaded fine dffb5dd [Nicholas Chammas] [SPARK-2627] download pep8 at runtime a1ce7ae [Nicholas Chammas] [SPARK-2627] space out test report sections 21da538 [Nicholas Chammas] [SPARK-2627] it's PEP 8, not PEP8 6f4900b [Nicholas Chammas] [SPARK-2627] more misc PEP 8 fixes fe57ed0 [Nicholas Chammas] removing merge conflict backups 9c01d4c [nchammas] Merge pull request #1 from apache/master 9a66cb0 [Nicholas Chammas] resolving merge conflicts a31ccc4 [Nicholas Chammas] [SPARK-2627] miscellaneous PEP 8 fixes beaa9ac [Nicholas Chammas] [SPARK-2627] fail check on non-zero status 723ed39 [Nicholas Chammas] always delete the report file 0541ebb [Nicholas Chammas] [SPARK-2627] call Python linter from run-tests 12440fa [Nicholas Chammas] [SPARK-2627] add Scala linter 61c07b9 [Nicholas Chammas] [SPARK-2627] add Python linter 75ad552 [Nicholas Chammas] make check output style consistent
138 lines
4.8 KiB
Python
138 lines
4.8 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
|
|
import random
|
|
|
|
|
|
class RDDSamplerBase(object):
|
|
|
|
def __init__(self, withReplacement, seed=None):
|
|
try:
|
|
import numpy
|
|
self._use_numpy = True
|
|
except ImportError:
|
|
print >> sys.stderr, (
|
|
"NumPy does not appear to be installed. "
|
|
"Falling back to default random generator for sampling.")
|
|
self._use_numpy = False
|
|
|
|
self._seed = seed if seed is not None else random.randint(0, sys.maxint)
|
|
self._withReplacement = withReplacement
|
|
self._random = None
|
|
self._split = None
|
|
self._rand_initialized = False
|
|
|
|
def initRandomGenerator(self, split):
|
|
if self._use_numpy:
|
|
import numpy
|
|
self._random = numpy.random.RandomState(self._seed)
|
|
else:
|
|
self._random = random.Random(self._seed)
|
|
|
|
for _ in range(0, split):
|
|
# discard the next few values in the sequence to have a
|
|
# different seed for the different splits
|
|
self._random.randint(0, sys.maxint)
|
|
|
|
self._split = split
|
|
self._rand_initialized = True
|
|
|
|
def getUniformSample(self, split):
|
|
if not self._rand_initialized or split != self._split:
|
|
self.initRandomGenerator(split)
|
|
|
|
if self._use_numpy:
|
|
return self._random.random_sample()
|
|
else:
|
|
return self._random.uniform(0.0, 1.0)
|
|
|
|
def getPoissonSample(self, split, mean):
|
|
if not self._rand_initialized or split != self._split:
|
|
self.initRandomGenerator(split)
|
|
|
|
if self._use_numpy:
|
|
return self._random.poisson(mean)
|
|
else:
|
|
# here we simulate drawing numbers n_i ~ Poisson(lambda = 1/mean) by
|
|
# drawing a sequence of numbers delta_j ~ Exp(mean)
|
|
num_arrivals = 1
|
|
cur_time = 0.0
|
|
|
|
cur_time += self._random.expovariate(mean)
|
|
|
|
if cur_time > 1.0:
|
|
return 0
|
|
|
|
while(cur_time <= 1.0):
|
|
cur_time += self._random.expovariate(mean)
|
|
num_arrivals += 1
|
|
|
|
return (num_arrivals - 1)
|
|
|
|
def shuffle(self, vals):
|
|
if self._random is None:
|
|
self.initRandomGenerator(0) # this should only ever called on the master so
|
|
# the split does not matter
|
|
|
|
if self._use_numpy:
|
|
self._random.shuffle(vals)
|
|
else:
|
|
self._random.shuffle(vals, self._random.random)
|
|
|
|
|
|
class RDDSampler(RDDSamplerBase):
|
|
|
|
def __init__(self, withReplacement, fraction, seed=None):
|
|
RDDSamplerBase.__init__(self, withReplacement, seed)
|
|
self._fraction = fraction
|
|
|
|
def func(self, split, iterator):
|
|
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(split, mean=self._fraction)
|
|
for _ in range(0, count):
|
|
yield obj
|
|
else:
|
|
for obj in iterator:
|
|
if self.getUniformSample(split) <= self._fraction:
|
|
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):
|
|
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(split, mean=self._fractions[key])
|
|
for _ in range(0, count):
|
|
yield key, val
|
|
else:
|
|
for key, val in iterator:
|
|
if self.getUniformSample(split) <= self._fractions[key]:
|
|
yield key, val
|