#!/usr/bin/env python3
# Source: t6-practitioner-toolkit.html
import numpy as np

class ThompsonBernoulli:
    """Beta-Bernoulli Thompson sampling for click/no-click arms."""
    def __init__(self, n_arms, seed=0):
        self.a = np.ones(n_arms)   # successes + 1
        self.b = np.ones(n_arms)   # failures + 1
        self.rng = np.random.default_rng(seed)

    def choose(self):
        return int(np.argmax(self.rng.beta(self.a, self.b)))

    def update(self, arm, reward):
        self.a[arm] += reward
        self.b[arm] += 1 - reward

def ucb1_choose(counts, sums, t):
    """counts, sums: arrays per arm. t: total pulls so far."""
    if (counts == 0).any():
        return int(np.argmin(counts))           # try every arm once
    means = sums / counts
    bonus = np.sqrt(2 * np.log(t) / counts)
    return int(np.argmax(means + bonus))

def eps_greedy_choose(means, eps, rng):
    return int(rng.integers(len(means))) if rng.random() < eps else int(np.argmax(means))
