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/statcounter.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/statcounter.py')
-rw-r--r-- | python/pyspark/statcounter.py | 25 |
1 files changed, 13 insertions, 12 deletions
diff --git a/python/pyspark/statcounter.py b/python/pyspark/statcounter.py index 080325061a..e287bd3da1 100644 --- a/python/pyspark/statcounter.py +++ b/python/pyspark/statcounter.py @@ -20,18 +20,19 @@ import copy import math + class StatCounter(object): - + def __init__(self, values=[]): self.n = 0L # Running count of our values self.mu = 0.0 # Running mean of our values self.m2 = 0.0 # Running variance numerator (sum of (x - mean)^2) self.maxValue = float("-inf") self.minValue = float("inf") - + for v in values: self.merge(v) - + # Add a value into this StatCounter, updating the internal statistics. def merge(self, value): delta = value - self.mu @@ -42,7 +43,7 @@ class StatCounter(object): self.maxValue = value if self.minValue > value: self.minValue = value - + return self # Merge another StatCounter into this one, adding up the internal statistics. @@ -50,7 +51,7 @@ class StatCounter(object): if not isinstance(other, StatCounter): raise Exception("Can only merge Statcounters!") - if other is self: # reference equality holds + if other is self: # reference equality holds self.merge(copy.deepcopy(other)) # Avoid overwriting fields in a weird order else: if self.n == 0: @@ -59,8 +60,8 @@ class StatCounter(object): self.n = other.n self.maxValue = other.maxValue self.minValue = other.minValue - - elif other.n != 0: + + elif other.n != 0: delta = other.mu - self.mu if other.n * 10 < self.n: self.mu = self.mu + (delta * other.n) / (self.n + other.n) @@ -68,10 +69,10 @@ class StatCounter(object): self.mu = other.mu - (delta * self.n) / (self.n + other.n) else: self.mu = (self.mu * self.n + other.mu * other.n) / (self.n + other.n) - + self.maxValue = max(self.maxValue, other.maxValue) self.minValue = min(self.minValue, other.minValue) - + self.m2 += other.m2 + (delta * delta * self.n * other.n) / (self.n + other.n) self.n += other.n return self @@ -94,7 +95,7 @@ class StatCounter(object): def max(self): return self.maxValue - + # Return the variance of the values. def variance(self): if self.n == 0: @@ -124,5 +125,5 @@ class StatCounter(object): return math.sqrt(self.sampleVariance()) def __repr__(self): - return "(count: %s, mean: %s, stdev: %s, max: %s, min: %s)" % (self.count(), self.mean(), self.stdev(), self.max(), self.min()) - + return ("(count: %s, mean: %s, stdev: %s, max: %s, min: %s)" % + (self.count(), self.mean(), self.stdev(), self.max(), self.min())) |