Percentiles from frequency distribution

distrib_from_freqs.py

import numpy as np
import scipy.stats

# some mapping from a value to the frequency
freqs = np.array([
    [1, 3],
    [2, 10],
    [3, 13],
    [4, 12],
    [5, 9],
    [6, 4],
])

def distrib_from_freqs(arr: np.ndarray) -> scipy.stats.rv_discrete:
    pmf = arr[:, 1] / arr[:, 1].sum()
    distrib = scipy.stats.rv_discrete(values=(arr[:, 0], pmf))
    return distrib

distrib = distrib_from_freqs(freqs)

print(distrib.pmf(freqs[:, 0]))
print(distrib.cdf(freqs[:, 0]))
print(distrib.ppf(distrib.cdf(freqs[:, 0])))  # percentiles

# [0.05882353 0.19607843 0.25490196 0.23529412 0.17647059 0.07843137]
# [0.05882353 0.25490196 0.50980392 0.74509804 0.92156863 1.        ]
# [1. 2. 3. 4. 5. 6.]