numpy - Fitting empirical distribution to theoretical ones with Scipy (Python)?

Question

INTRODUCTION: I have a list of more than 30,000 integer values ranging from 0 to 47, inclusive, e.g.[0,0,0,0,..,1,1,1,1,...,2,2,2,2,...,47,47,47,...] sampled from some continuous distribution. The values in the list are not necessarily in order, but order doesn't matter for this problem.

PROBLEM: Based on my distribution I would like to calculate p-value (the probability of seeing greater values) for any given value. For example, as you can see p-value for 0 would be approaching 1 and p-value for higher numbers would be tending to 0.

I don't know if I am right, but to determine probabilities I think I need to fit my data to a theoretical distribution that is the most suitable to describe my data. I assume that some kind of goodness of fit test is needed to determine the best model.

Is there a way to implement such an analysis in Python (Scipy or Numpy)? Could you present any examples?

Thank you!

Answer 1

Distribution Fitting with Sum of Square Error (SSE)

This is an update and modification to Saullo's answer, that uses the full list of the current scipy.stats distributions and returns the distribution with the least SSE between the distribution's histogram and the data's histogram.

Example Fitting

Using the El Ni?o dataset from statsmodels, the distributions are fit and error is determined. The distribution with the least error is returned.

All Distributions

Best Fit Distribution

Example Code

%matplotlib inline

import warnings
import numpy as np
import pandas as pd
import scipy.stats as st
import statsmodels.api as sm
from scipy.stats._continuous_distns import _distn_names
import matplotlib
import matplotlib.pyplot as plt

matplotlib.rcParams['figure.figsize'] = (16.0, 12.0)
matplotlib.style.use('ggplot')

# Create models from data
def best_fit_distribution(data, bins=200, ax=None):
    """Model data by finding best fit distribution to data"""
    # Get histogram of original data
    y, x = np.histogram(data, bins=bins, density=True)
    x = (x + np.roll(x, -1))[:-1] / 2.0

    # Best holders
    best_distributions = []

    # Estimate distribution parameters from data
    for ii, distribution in enumerate([d for d in _distn_names if not d in ['levy_stable', 'studentized_range']]):

        print("{:>3} / {:<3}: {}".format( ii+1, len(_distn_names), distribution ))

        distribution = getattr(st, distribution)

        # Try to fit the distribution
        try:
            # Ignore warnings from data that can't be fit
            with warnings.catch_warnings():
                warnings.filterwarnings('ignore')
                
                # fit dist to data
                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 = distribution.pdf(x, loc=loc, scale=scale, *arg)
                sse = np.sum(np.power(y - pdf, 2.0))
                
                # if axis pass in add to plot
                try:
                    if ax:
                        pd.Series(pdf, x).plot(ax=ax)
                    end
                except Exception:
                    pass

                # identify if this distribution is better
                best_distributions.append((distribution, params, sse))
        
        except Exception:
            pass

    
    return sorted(best_distributions, key=lambda x:x[2])

def make_pdf(dist, params, size=10000):
    """Generate distributions's Probability Distribution Function """

    # Separate parts of parameters
    arg = params[:-2]
    loc = params[-2]
    scale = params[-1]

    # Get sane start and end points of distribution
    start = dist.ppf(0.01, *arg, loc=loc, scale=scale) if arg else dist.ppf(0.01, loc=loc, scale=scale)
    end = dist.ppf(0.99, *arg, loc=loc, scale=scale) if arg else dist.ppf(0.99, loc=loc, scale=scale)

    # Build PDF and turn into pandas Series
    x = np.linspace(start, end, size)
    y = dist.pdf(x, loc=loc, scale=scale, *arg)
    pdf = pd.Series(y, x)

    return pdf

# Load data from statsmodels datasets
data = pd.Series(sm.datasets.elnino.load_pandas().data.set_index('YEAR').values.ravel())

# Plot for comparison
plt.figure(figsize=(12,8))
ax = data.plot(kind='hist', bins=50, density=True, alpha=0.5, color=list(matplotlib.rcParams['axes.prop_cycle'])[1]['color'])

# Save plot limits
dataYLim = ax.get_ylim()

# Find best fit distribution
best_distibutions = best_fit_distribution(data, 200, ax)
best_dist = best_distibutions[0]

# Update plots
ax.set_ylim(dataYLim)
ax.set_title(u'El Ni?o sea temp.
 All Fitted Distributions')
ax.set_xlabel(u'Temp (°C)')
ax.set_ylabel('Frequency')

# Make PDF with best params 
pdf = make_pdf(best_dist[0], best_dist[1])

# Display
plt.figure(figsize=(12,8))
ax = pdf.plot(lw=2, label='PDF', legend=True)
data.plot(kind='hist', bins=50, density=True, alpha=0.5, label='Data', legend=True, ax=ax)

param_names = (best_dist[0].shapes + ', loc, scale').split(', ') if best_dist[0].shapes else ['loc', 'scale']
param_str = ', '.join(['{}={:0.2f}'.format(k,v) for k,v in zip(param_names, best_dist[1])])
dist_str = '{}({})'.format(best_dist[0].name, param_str)

ax.set_title(u'El Ni?o sea temp. with best fit distribution 
' + dist_str)
ax.set_xlabel(u'Temp. (°C)')
ax.set_ylabel('Frequency')