Calculating lognormal fit about powerlaw

[jeffalstott]

distribution_fit is ancient, unadvertised code that really shouldn't be used, and is evidently buggy. I'm surprised you even found it. From the code itself:

#What follows are functional programming forms of the above code, which are more
#clunky and have somewhat less functionality. However, they are here if your
#really want them.

This should be revised with:

#And it doesn't work!

For your use case, you want the class Lognormal:

import powerlaw

X = powerlaw.Power_Law(parameters=[1.5], xmin=10).generate_random(1000)

fit=powerlaw.Fit(X)
print("power law:alpha=%s, D=%s, sigma=%s, xmin=%s" %(fit.alpha,fit.D,fit.sigma,fit.xmin))
# power law:alpha=1.49667016064, D=0.0164184126544, sigma=0.0212360825904, xmin=29.5707256239
print("lognormal: mu=%s, sigma=%s" %(fit.lognormal.mu,fit.lognormal.sigma))
# lognormal: mu=-453.445219074, sigma=30.4608351679

lognormal_fit = powerlaw.Lognormal(data=X, xmin=fit.xmin)
print("lognormal: mu=%s, sigma=%s" %(lognormal_fit.mu,lognormal_fit.sigma))
# lognormal: mu=-453.444231277, sigma=30.46080239