PHP code example of cleatsquad / php-bandit

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

cleatsquad / php-bandit example snippets

use CleatSquad\Bandit\ArmState;
use CleatSquad\Bandit\ThompsonSamplingPolicy;

$policy = new ThompsonSamplingPolicy();

$arms = [
    'variant_a' => new ArmState(successes: 12, failures: 4),
    'variant_b' => new ArmState(successes: 30, failures: 1),
];

$result = $policy->select($arms);

$result->selectedArm; // 'variant_b' — usually, but not always
$result->sample;      // 0.9412... the draw that won
$result->samples;     // every draw: ['variant_a' => 0.7318..., 'variant_b' => 0.9412...]

$policy->selectArm($arms); // 'variant_b'

$means = array_map(
    static fn (ArmState $s): float => $policy->posteriorMean($s->successes, $s->failures),
    $arms,
);

$frontRunner = array_search(max($means), $means, strict: true);
$exploredAway = $frontRunner !== $result->selectedArm;

// 1. select — the library decides, from state you hand it
$arms   = $yourStorage->loadArms();          // array<string, ArmState>
$result = $policy->select($arms);

// 2. execute — outside the library: serve the variant, call the provider…
$outcome = $yourSystem->run($result->selectedArm);

// 3. observe — reduce the outcome to a binary success or failure
$succeeded = $outcome->isSuccess();

// 4. update — immutable transition, always on the arm that played
$updated = $succeeded
    ? $arms[$result->selectedArm]->withSuccess()
    : $arms[$result->selectedArm]->withFailure();

// 5. persist — outside the library: yours to write (see below)
$yourStorage->save($result->selectedArm, $updated);

$state = ArmState::fromTrials(trials: 100, successes: 63); // 63 successes, 37 failures
$state->trials();                                          // 100

$policy->posteriorMean(10, 2);     // 0.846 — expected success rate
$policy->posteriorVariance(10, 2); // how unsure that estimate is
$policy->posteriorWeight(10, 2);   // 0.0..1.0 confidence, 0 when uninformed
$policy->sample(10, 2);            // one random draw from Beta(11, 3)

$policy = ThompsonSamplingPolicy::withSeed(42);
$policy->sample(5, 2); // same value on every run, for tests and simulations

$policy->selectBestArm($arms); // gone in 1.0.0
$policy->selectArm($arms);     // same decision, honest name

bash
composer