Created
November 19, 2020 09:55
-
-
Save yuvalta/ab420b080897fd741e424bc63253ec98 to your computer and use it in GitHub Desktop.
Fit distributions and check goodness of fiting
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
from scipy import stats | |
def fitDist(list_of_data): | |
list_of_dists = ['dweibull', 'erlang', 'expon', 'gamma','lognorm', 'norm', 'pareto','uniform', 'weibull_min', 'weibull_max'] | |
results = [] | |
for i in list_of_dists: | |
dist = getattr(stats, i) | |
param = dist.fit(list_of_data) | |
a = stats.kstest(list_of_data, i, args=param) | |
results.append((i, a[0], a[1])) | |
results.sort(key=lambda x: float(x[2]), reverse=True) | |
for j in results: | |
print("{}: statistic={}, pvalue={}".format(j[0], j[1], j[2])) | |
# OUTPUT: the results are sorted based on the highest p-value - most fitting distribution | |
# | |
# lognorm: statistic=0.08151809053646897, pvalue=0.7099384232837425 | |
# weibull_min: statistic=0.1433543643561933, pvalue=0.10186497830108568 | |
# pareto: statistic=0.17285038643818018, pvalue=0.026768835378203133 | |
# erlang: statistic=0.21420242876681705, pvalue=0.0026817745586541486 | |
# gamma: statistic=0.3863965456262737, pvalue=6.453380068067353e-10 | |
# expon: statistic=0.3880651672810395, pvalue=5.308769005172491e-10 | |
# norm: statistic=0.4136814145992531, pvalue=2.342556004002841e-11 | |
# dweibull: statistic=0.4322169930468518, pvalue=2.113211201836775e-12 | |
# weibull_max: statistic=0.8801135189665196, pvalue=7.067801597034558e-65 | |
# uniform: statistic=0.9042039833453933, pvalue=9.988248721291695e-72 | |
# | |
# | |
# https://medium.com/@amirarsalan.rajabi/distribution-fitting-with-python-scipy-bb70a42c0aed |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment