bootstrapping.py

import numpy as np

def bootstrap_ci(df, variable, classes, repetitions = 1000, alpha = 0.05, random_state=None):
    # df: a data frame that includes observations of the two sample
    # variable: the column name of the column that includes observations
    # classes: the column name of the column that includes group assignment (This column should contain two different group names)
    # repetitions: number of times you want the bootstrapping to repeat. Default is 1000.
    # alpha: likelihood that the true population parameter lies outside the confidence interval. Default is 0.05. 
    # random_stata: enable users to set their own random_state, default is None. 
    
    df = df[[variable, classes]]
    bootstrap_sample_size = len(df) 
    
    mean_diffs = []

    for i in range(repetitions):
        bootstrap_sample = df.sample(n = bootstrap_sample_size, replace = True, random_state = random_state)
        mean_diff = bootstrap_sample.groupby(classes).mean().iloc[1,0] - bootstrap_sample.groupby(classes).mean().iloc[0,0]
        mean_diffs.append(mean_diff)

    # confidence interval
    left = np.percentile(mean_diffs, alpha/2*100)
    right = np.percentile(mean_diffs, 100-alpha/2*100)

    # point estimate
    point_est = df.groupby(classes).mean().iloc[1,0] - df.groupby(classes).mean().iloc[0,0]

    print('Point estimate of difference between means:', round(point_est,2))
    print((1-alpha)*100,'%','confidence interval for the difference between means:', (round(left,2), round(right,2)))