Normality assessment tools

Normality.py

from scipy.stats import shapiro, normaltest, anderson, norm
from statsmodels.graphics.gofplots import qqplot
import seaborn as sns
from colorama import Fore
import matplotlib.pyplot as plt
import numpy as np

sns.set(color_codes=True)

def check_shapiro(data, alpha=0.05):
    """ Check Shapiro-Wilk test. If p > alpha, reject H0 => it's Gaussian """
    stat, p = shapiro(data)
    return True if p > alpha else False


def check_dagostino(data, alpha=0.05):
    """ Check D’Agostino K^2 test. If p > alpha, reject H0 => it's Gaussian """
    stat, p = normaltest(data)
    return True if p > alpha else False


def check_anderson(data):
    """ Check Anderson-Darling test for normal distribution.
        Returns True if it can't reject H0 to 15%, 10% or 5%. => it's Gaussian
        Returns False otherwise
    """
    result = anderson(data, dist="norm")
    return next(
        (
            True
            for sig_value, crit_value in zip(
                result.significance_level[0:3], result.critical_values[0:3]
            )
            if result.statistic < crit_value
        ),
        False,
    )


def is_normal(data):
    """ Check for normality.
    Returns True if 2 out of 3 statistical tests result in normality
    Returns False otherwise
    """
    return (
        True
        if [check_shapiro(data), check_dagostino(data), check_anderson(data)].count(True) >= 2
        else False
    )

def analyze_normality(df):
    """ Visual aid for normality check.
    For every numeric column in df:
     - distribution plot with kde and fit to normal
     - qq plot
     - results of all three statistical tests
    """
    si = Fore.GREEN + "NORMAL" + Fore.RESET
    no = Fore.RED + "NO NORMAL" + Fore.RESET
    for column in [i for i in df.columns if df[i].dtype.kind in 'biufc']:
        data = df[column].dropna()
        print(f"{column}: {len(data)} puntos")
        fig, ax = plt.subplots(1, 2, figsize=(7, 5))
        sns.distplot(data, ax=ax[0], fit=norm)
        qqplot(data, line="s", ax=ax[1])
        plt.show()

        print(f"\tSHAPIRO:\t{si if check_shapiro(data,0.05) else no}")
        print(f"\tD'AGOSTINO:\t{si if check_dagostino(data,0.05) else no}")
        print(f"\tANDERSON:\t{si if check_anderson(data) else no}")
        print("\n")