outlier.py

import numpy as np
import scipy.stats as stats
x = np.array([12,13,14,19,21,23])
y = np.array([12,13,14,19,21,23,45])
def grubbs_test(x):
    n = len(x)
    mean_x = np.mean(x)
    sd_x = np.std(x)
    numerator = max(abs(x-mean_x))
    g_calculated = numerator/sd_x
    print("Grubbs Calculated Value:",g_calculated)
    t_value = stats.t.ppf(1 - 0.05 / (2 * n), n - 2)
    g_critical = ((n - 1) * np.sqrt(np.square(t_value))) / (np.sqrt(n) * np.sqrt(n - 2 + np.square(t_value)))
    print("Grubbs Critical Value:",g_critical)
    if g_critical > g_calculated:
        print("From grubbs_test we observe that calculated value is lesser than critical value, Accept null hypothesis and conclude that there is no outliers\n")
    else:
        print("From grubbs_test we observe that calculated value is greater than critical value, Reject null hypothesis and conclude that there is an outliers\n")
grubbs_test(x)
grubbs_test(y)