Created
November 20, 2014 09:33
-
-
Save canard0328/e8c5ccaa67fc3426ac9b to your computer and use it in GitHub Desktop.
クラメールの連関係数の計算 ref: http://qiita.com/canard0328/items/5ea4115d964b448903ba
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
# -*- coding: utf-8 -*- | |
import numpy as np | |
def cramersV(x, y): | |
""" | |
Calc Cramer's V. | |
Parameters | |
---------- | |
x : {numpy.ndarray, pandas.Series} | |
y : {numpy.ndarray, pandas.Series} | |
""" | |
table = np.array(pd.crosstab(x, y)).astype(np.float32) | |
n = table.sum() | |
colsum = table.sum(axis=0) | |
rowsum = table.sum(axis=1) | |
expect = np.outer(rowsum, colsum) / n | |
chisq = np.sum((table - expect) ** 2 / expect) | |
return np.sqrt(chisq / (n * (np.min(table.shape) - 1))) | |
if __name__ == "__main__": | |
import pandas as pd | |
data = pd.DataFrame( | |
{'science': ['like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'dislike', 'dislike', 'dislike', | |
'dislike', 'dislike', 'dislike', 'dislike', 'dislike', | |
'dislike', 'dislike', 'dislike', 'dislike', 'dislike', | |
'dislike', 'dislike', 'dislike', 'dislike', 'dislike', | |
'dislike'], | |
'math': ['like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'like', 'like', 'like', 'like', | |
'like', 'like', 'like', 'dislike', 'dislike', 'dislike', | |
'dislike', 'dislike', 'dislike', 'dislike', 'like', 'like', | |
'like', 'like', 'like', 'like', 'dislike', 'dislike', | |
'dislike', 'dislike', 'dislike', 'dislike', 'dislike', | |
'dislike', 'dislike', 'dislike', 'dislike', 'dislike', | |
'dislike']}) | |
print cramersV(data['science'], data['math']) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment