[python] Fitting empirical distribution to theoretical ones with Scipy (Python)?

The following code is the version of the general answer but with corrections and clarity.

import numpy as np
import pandas as pd
import scipy.stats as st
import statsmodels.api as sm
import matplotlib as mpl
import matplotlib.pyplot as plt
import math
import random

mpl.style.use("ggplot")

def danoes_formula(data):
    """
    DANOE'S FORMULA
    https://en.wikipedia.org/wiki/Histogram#Doane's_formula
    """
    N = len(data)
    skewness = st.skew(data)
    sigma_g1 = math.sqrt((6*(N-2))/((N+1)*(N+3)))
    num_bins = 1 + math.log(N,2) + math.log(1+abs(skewness)/sigma_g1,2)
    num_bins = round(num_bins)
    return num_bins

def plot_histogram(data, results, n):
    ## n first distribution of the ranking
    N_DISTRIBUTIONS = {k: results[k] for k in list(results)[:n]}

    ## Histogram of data
    plt.figure(figsize=(10, 5))
    plt.hist(data, density=True, ec='white', color=(63/235, 149/235, 170/235))
    plt.title('HISTOGRAM')
    plt.xlabel('Values')
    plt.ylabel('Frequencies')

    ## Plot n distributions
    for distribution, result in N_DISTRIBUTIONS.items():
        # print(i, distribution)
        sse = result[0]
        arg = result[1]
        loc = result[2]
        scale = result[3]
        x_plot = np.linspace(min(data), max(data), 1000)
        y_plot = distribution.pdf(x_plot, loc=loc, scale=scale, *arg)
        plt.plot(x_plot, y_plot, label=str(distribution)[32:-34] + ": " + str(sse)[0:6], color=(random.uniform(0, 1), random.uniform(0, 1), random.uniform(0, 1)))
    
    plt.legend(title='DISTRIBUTIONS', bbox_to_anchor=(1.05, 1), loc='upper left')
    plt.show()

def fit_data(data):
    ## st.frechet_r,st.frechet_l: are disbled in current SciPy version
    ## st.levy_stable: a lot of time of estimation parameters
    ALL_DISTRIBUTIONS = [        
        st.alpha,st.anglit,st.arcsine,st.beta,st.betaprime,st.bradford,st.burr,st.cauchy,st.chi,st.chi2,st.cosine,
        st.dgamma,st.dweibull,st.erlang,st.expon,st.exponnorm,st.exponweib,st.exponpow,st.f,st.fatiguelife,st.fisk,
        st.foldcauchy,st.foldnorm, st.genlogistic,st.genpareto,st.gennorm,st.genexpon,
        st.genextreme,st.gausshyper,st.gamma,st.gengamma,st.genhalflogistic,st.gilbrat,st.gompertz,st.gumbel_r,
        st.gumbel_l,st.halfcauchy,st.halflogistic,st.halfnorm,st.halfgennorm,st.hypsecant,st.invgamma,st.invgauss,
        st.invweibull,st.johnsonsb,st.johnsonsu,st.ksone,st.kstwobign,st.laplace,st.levy,st.levy_l,
        st.logistic,st.loggamma,st.loglaplace,st.lognorm,st.lomax,st.maxwell,st.mielke,st.nakagami,st.ncx2,st.ncf,
        st.nct,st.norm,st.pareto,st.pearson3,st.powerlaw,st.powerlognorm,st.powernorm,st.rdist,st.reciprocal,
        st.rayleigh,st.rice,st.recipinvgauss,st.semicircular,st.t,st.triang,st.truncexpon,st.truncnorm,st.tukeylambda,
        st.uniform,st.vonmises,st.vonmises_line,st.wald,st.weibull_min,st.weibull_max,st.wrapcauchy
    ]
    
    MY_DISTRIBUTIONS = [st.beta, st.expon, st.norm, st.uniform, st.johnsonsb, st.gennorm, st.gausshyper]

    ## Calculae Histogram
    num_bins = danoes_formula(data)
    frequencies, bin_edges = np.histogram(data, num_bins, density=True)
    central_values = [(bin_edges[i] + bin_edges[i+1])/2 for i in range(len(bin_edges)-1)]

    results = {}
    for distribution in MY_DISTRIBUTIONS:
        ## Get parameters of distribution
        params = distribution.fit(data)
        
        ## Separate parts of parameters
        arg = params[:-2]
        loc = params[-2]
        scale = params[-1]
    
        ## Calculate fitted PDF and error with fit in distribution
        pdf_values = [distribution.pdf(c, loc=loc, scale=scale, *arg) for c in central_values]
        
        ## Calculate SSE (sum of squared estimate of errors)
        sse = np.sum(np.power(frequencies - pdf_values, 2.0))
        
        ## Build results and sort by sse
        results[distribution] = [sse, arg, loc, scale]
        
    results = {k: results[k] for k in sorted(results, key=results.get)}
    return results
        
def main():
    ## Import data
    data = pd.Series(sm.datasets.elnino.load_pandas().data.set_index('YEAR').values.ravel())
    results = fit_data(data)
    plot_histogram(data, results, 5)

if __name__ == "__main__":
    main()
    
    

enter image description here

Examples related to python

programming a servo thru a barometer Is there a way to view two blocks of code from the same file simultaneously in Sublime Text? python variable NameError Why my regexp for hyphenated words doesn't work? Comparing a variable with a string python not working when redirecting from bash script is it possible to add colors to python output? Get Public URL for File - Google Cloud Storage - App Engine (Python) Real time face detection OpenCV, Python xlrd.biffh.XLRDError: Excel xlsx file; not supported Could not load dynamic library 'cudart64_101.dll' on tensorflow CPU-only installation

Examples related to numpy

Unable to allocate array with shape and data type How to fix 'Object arrays cannot be loaded when allow_pickle=False' for imdb.load_data() function? Numpy, multiply array with scalar TypeError: only integer scalar arrays can be converted to a scalar index with 1D numpy indices array Could not install packages due to a "Environment error :[error 13]: permission denied : 'usr/local/bin/f2py'" Pytorch tensor to numpy array Numpy Resize/Rescale Image what does numpy ndarray shape do? How to round a numpy array? numpy array TypeError: only integer scalar arrays can be converted to a scalar index

Examples related to statistics

Function to calculate R2 (R-squared) in R pandas: find percentile stats of a given column What exactly does numpy.exp() do? Find p-value (significance) in scikit-learn LinearRegression How to plot ROC curve in Python Pandas - Compute z-score for all columns Calculating percentile of dataset column How to normalize an array in NumPy to a unit vector? How to find row number of a value in R code np.mean() vs np.average() in Python NumPy?

Examples related to scipy

Reading images in python Numpy Resize/Rescale Image How to get the indices list of all NaN value in numpy array? ImportError: cannot import name NUMPY_MKL numpy.where() detailed, step-by-step explanation / examples Scikit-learn train_test_split with indices Matplotlib: Specify format of floats for tick labels Installing NumPy and SciPy on 64-bit Windows (with Pip) Can't install Scipy through pip Plotting a fast Fourier transform in Python

Examples related to distribution

How to draw a standard normal distribution in R Fitting empirical distribution to theoretical ones with Scipy (Python)? Generate random numbers following a normal distribution in C/C++