Last active
December 5, 2022 16:59
-
-
Save odinokov/16243213f588d5db64445bd75838c49c to your computer and use it in GitHub Desktop.
An efficient way to calculate weighted Gini coefficient in Python
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 numba | |
import numpy as np | |
@numba.jit | |
def gini(x, w=None): | |
# from https://stackoverflow.com/questions/48999542/more-efficient-weighted-gini-coefficient-in-python | |
# The rest of the code requires numpy arrays. | |
# x = np.asarray(x) | |
if w is not None: | |
# w = np.asarray(w) | |
sorted_indices = np.argsort(x) | |
sorted_x = x[sorted_indices] | |
sorted_w = w[sorted_indices] | |
# Force float dtype to avoid overflows | |
cumw = np.cumsum(sorted_w) | |
cumxw = np.cumsum(sorted_x * sorted_w) | |
return (np.sum(cumxw[1:] * cumw[:-1] - cumxw[:-1] * cumw[1:]) / | |
(cumxw[-1] * cumw[-1])) | |
else: | |
# x = np.asarray(x) | |
sorted_x = np.sort(x) | |
n = x.size | |
cumx = np.cumsum(sorted_x) | |
# The above formula, with all weights equal to 1 simplifies to: | |
return (n + 1 - 2 * np.sum(cumx) / cumx[-1]) / n | |
gini(np.asarray([1,2,3,4,5])) | |
# 0.2666666666666666 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment