A simple implementation for a confidence interval using bootstrapping

bootstrapping.py

import random
import numpy as np

population = np.random.uniform(size = 5000)

def confidence_interval(population, confidence = 95, aggregation = np.mean, samples = 500, sample_n = 500):
	if population.shape[0] < sample_n:
		sample_n = population.shape[0]//2
	aggs = []
	for _ in range(samples):
		aggs.append(aggregation(
			np.random.choice(population, sample_n)))
	lower, higher = (100 - confidence)/2, confidence/2 + 50
	
	return np.percentile(np.asarray(aggs), [lower, 50, higher])


for _ in range(5):
	print(confidence_interval(population, samples =100, sample_n = 1000, aggregation= np.median))

print(np.median(population))