При этом мои образцы и мои коды для подгонки CDF.
import numpy as np
import pandas as pd
import scipy.stats as st
samples = [2,3,10,7,9,6,1,3,7,2,5,4,6,3,4,1,4,6,3,10,3,7,5,6,6,5,4,2,2,5,4,5,6,4,4,6,3,3,3,2,2,2,4,2,6,2,7,4,3,2,2,1,4,2,2,5,3,9,6,8,3,6,6,3,9,2,3,3,3,5,4,4,5,4,1,8,5,8,6,6,7,6,3,2,4,2,16,6,2,3,4,2,2,9,9,5,5,5,1,5,2,8,5,3,5,8,11,4,7,4,11,3,7,3,6,6,1,4,2,1,1,1,9,4,15,2,1,3,4,9,3,3,4,3,6,3,3,5,5,6,3,3,4,8,4,4,2,5,6,7,3,5,5,2,5,9,7,6,1,3,4,9,3,2,4,8,5,8,4,4,5,6,5,8,6,1,3,7,9,6,7,12,4,1,4,5,5,7,1,7,1,15,3,3,2,3,7,7,15,6,5,1,7,4,2,10,1,3,3,8,3,8,1,5,4,7,4,2,9,2,1,3,6,1,6,10,6,3,4,7,5,7,3,3,7,4,4,3,5,3,5,2,2,1,2,3,1,1,2,1,1,2,3,10,7,3,2,6,5,6,5,11,1,7,5,2,9,5,12,6,3,9,9,4,3,4,6,4,10,4,8,6,1,7,2,5,8,3,1,3,1,1,3,3,2,2,6,3,3,2,6,6,6,4,2,4,1,10,5,3,5,6,3,4,1,1,7,6,6,5,7,6,3,4,6,6,5,3,2,3,2,1,2,4,1,1,1,3,7,1,6,3,4,3,3,6,7,3,7,4,1,1,7,1,4,4,3,4,2,4,2,6,6,2,2,6,5,4,6,5,6,3,5,1,5,3,3,2,2,2,2,3,3,3,2,2,1,4,2,3,5,7,2,5,1,2,2,5,6,5,2,1,2,4,5,2,3,2,4,9,3,5,2,2,5,4,2,3,4,2,3,1,3,6,7,2,6,3,5,4,2,2,2,2,1,2,5,2,2,3,4,2,5,2,2,3,5,3,2,4,3,2,5,4,1,4,8,6,8,2,2,3,1,2,3,8,2,3,4,3,3,2,1,1,1,3,3,4,3,4,1,2,8,2,2,7,3,1,2,3,3,2,3,1,2,1,1,1,3,2,2,2,4,7,2,1,2,3,1,3,1,1,6,2,1,1,3,1,4,4,1,3,1,1,4,1,1,2,4,4,3,2,3,2,1,2,1,4,2,5,3,4,2,1,1,1,3,1,2,1,1,4,2,1,3,2,1,3,2,1,1,1,2,1,1,1,1,2,1,1,1,1,1,1,1]
bins=np.arange(1, 18, 0.1)
#Because min(samples) = 1, so I start from 1.
y, x = np.histogram(samples, bins=bins, density=True)
params = st.lognorm.fit(samples)
# Separate parts of parameters
arg = params[:-2]
loc = params[-2]
scale = params[-1]
ccdf = st.lognorm.cdf(x, loc=loc, scale=scale, *arg)
cdf = pd.Series(ccdf, x)
#cdf[1.0] is not 0... That is the issue...
Когда я распечатываю первое значение cdf [1.0], оно не равно 0. Согласно теории, оно должно быть 0. Как показано на рисунке ниже, первый CDF не равен 0. Я проверяю свой код снова и снова. Однако я не могу решить проблему. Если какие-либо предложения мне, я очень ценю это.
