A/B testing & experimentation

import random
import json

def generate_mock_bandit_report(num_arms=5, num_rounds=100, seed=42):
    random.seed(seed)
    arms = ["A", "B", "C", "D", "E"][:num_arms]
    true_means = {arm: random.uniform(0.3, 0.7) for arm in arms}
    pulls = {arm: 0 for arm in arms}
    rewards = {arm: 0 for arm in arms}

    for _ …

import numpy as np

def two_sample_t_test(sample1, sample2):
    """Perform Welch's t-test for two independent samples."""
    n1, n2 = len(sample1), len(sample2)
    mean1, mean2 = np.mean(sample1), np.mean(sample2)
    var1, var2 = np.var(sample1, ddof=1), np.var(sample2, ddof=1)

    # Standard error of difference
…