Created
March 21, 2012 19:29
-
-
Save alexalemi/2151722 to your computer and use it in GitHub Desktop.
Python Welford Algorithm
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import math | |
class Welford(object): | |
""" Implements Welford's algorithm for computing a running mean | |
and standard deviation as described at: | |
http://www.johndcook.com/standard_deviation.html | |
can take single values or iterables | |
Properties: | |
mean - returns the mean | |
std - returns the std | |
meanfull- returns the mean and std of the mean | |
Usage: | |
>>> foo = Welford() | |
>>> foo(range(100)) | |
>>> foo | |
<Welford: 49.5 +- 29.0114919759> | |
>>> foo([1]*1000) | |
>>> foo | |
<Welford: 5.40909090909 +- 16.4437417146> | |
>>> foo.mean | |
5.409090909090906 | |
>>> foo.std | |
16.44374171455467 | |
>>> foo.meanfull | |
(5.409090909090906, 0.4957974674244838) | |
""" | |
def __init__(self,lst=None): | |
self.k = 0 | |
self.M = 0 | |
self.S = 0 | |
self.__call__(lst) | |
def update(self,x): | |
if x is None: | |
return | |
self.k += 1 | |
newM = self.M + (x - self.M)*1./self.k | |
newS = self.S + (x - self.M)*(x - newM) | |
self.M, self.S = newM, newS | |
def consume(self,lst): | |
lst = iter(lst) | |
for x in lst: | |
self.update(x) | |
def __call__(self,x): | |
if hasattr(x,"__iter__"): | |
self.consume(x) | |
else: | |
self.update(x) | |
@property | |
def mean(self): | |
return self.M | |
@property | |
def meanfull(self): | |
return self.mean, self.std/math.sqrt(self.k) | |
@property | |
def std(self): | |
if self.k==1: | |
return 0 | |
return math.sqrt(self.S/(self.k-1)) | |
def __repr__(self): | |
return "<Welford: {} +- {}>".format(self.mean, self.std) |
Beautiful! You'd be surprised at how many incorrect versions of Welford are online, thanks!
Nice code! One minor thing: not sure if returning an std of 0 is appropriate in the case of k=1 though as this is confusing when k != 0 but std = 0?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Great gist! moving
self.k += 1
until afternewM
andnewS
are calculated adds robustness for cases where someone tries to use this with strings or other non-numeric types....the function will then throw an error before incrementingk
, thus preserving the accuracy of the data within their Welford instance.