diff options
author | Nicholas Chammas <nicholas.chammas@gmail.com> | 2014-07-21 22:30:53 -0700 |
---|---|---|
committer | Reynold Xin <rxin@apache.org> | 2014-07-21 22:30:53 -0700 |
commit | 5d16d5bbfd242c16ee0d6952c48dcd90651f8ae2 (patch) | |
tree | 61352aa954fb1fb2001586c8795a959421eb3c6f /python/pyspark/rddsampler.py | |
parent | c3462c65684885299cf037d56c88bd53c08c6348 (diff) | |
download | spark-5d16d5bbfd242c16ee0d6952c48dcd90651f8ae2.tar.gz spark-5d16d5bbfd242c16ee0d6952c48dcd90651f8ae2.tar.bz2 spark-5d16d5bbfd242c16ee0d6952c48dcd90651f8ae2.zip |
[SPARK-2470] PEP8 fixes to PySpark
This pull request aims to resolve all outstanding PEP8 violations in PySpark.
Author: Nicholas Chammas <nicholas.chammas@gmail.com>
Author: nchammas <nicholas.chammas@gmail.com>
Closes #1505 from nchammas/master and squashes the following commits:
98171af [Nicholas Chammas] [SPARK-2470] revert PEP 8 fixes to cloudpickle
cba7768 [Nicholas Chammas] [SPARK-2470] wrap expression list in parentheses
e178dbe [Nicholas Chammas] [SPARK-2470] style - change position of line break
9127d2b [Nicholas Chammas] [SPARK-2470] wrap expression lists in parentheses
22132a4 [Nicholas Chammas] [SPARK-2470] wrap conditionals in parentheses
24639bc [Nicholas Chammas] [SPARK-2470] fix whitespace for doctest
7d557b7 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to tests.py
8f8e4c0 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to storagelevel.py
b3b96cf [Nicholas Chammas] [SPARK-2470] PEP8 fixes to statcounter.py
d644477 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to worker.py
aa3a7b6 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to sql.py
1916859 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to shell.py
95d1d95 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to serializers.py
a0fec2e [Nicholas Chammas] [SPARK-2470] PEP8 fixes to mllib
c85e1e5 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to join.py
d14f2f1 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to __init__.py
81fcb20 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to resultiterable.py
1bde265 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to java_gateway.py
7fc849c [Nicholas Chammas] [SPARK-2470] PEP8 fixes to daemon.py
ca2d28b [Nicholas Chammas] [SPARK-2470] PEP8 fixes to context.py
f4e0039 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to conf.py
a6d5e4b [Nicholas Chammas] [SPARK-2470] PEP8 fixes to cloudpickle.py
f0a7ebf [Nicholas Chammas] [SPARK-2470] PEP8 fixes to rddsampler.py
4dd148f [nchammas] Merge pull request #5 from apache/master
f7e4581 [Nicholas Chammas] unrelated pep8 fix
a36eed0 [Nicholas Chammas] name ec2 instances and security groups consistently
de7292a [nchammas] Merge pull request #4 from apache/master
2e4fe00 [nchammas] Merge pull request #3 from apache/master
89fde08 [nchammas] Merge pull request #2 from apache/master
69f6e22 [Nicholas Chammas] PEP8 fixes
2627247 [Nicholas Chammas] broke up lines before they hit 100 chars
6544b7e [Nicholas Chammas] [SPARK-2065] give launched instances names
69da6cf [nchammas] Merge pull request #1 from apache/master
Diffstat (limited to 'python/pyspark/rddsampler.py')
-rw-r--r-- | python/pyspark/rddsampler.py | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/python/pyspark/rddsampler.py b/python/pyspark/rddsampler.py index 122bc38b03..7ff1c316c7 100644 --- a/python/pyspark/rddsampler.py +++ b/python/pyspark/rddsampler.py @@ -18,13 +18,16 @@ import sys import random + class RDDSampler(object): def __init__(self, withReplacement, fraction, 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." + 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) @@ -61,7 +64,7 @@ class RDDSampler(object): 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: @@ -80,30 +83,27 @@ class RDDSampler(object): 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) def func(self, split, iterator): - if self._withReplacement: + 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 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 - - - - |