Workerman を使用して協調フィルタリングに基づく映画推奨システムを実装する方法

UserID | MovieID | Rating | Timestamp
---------------------------------------
   196  |    242  |      3 | 881250949
   186  |    302  |      3 | 891717742
   196  |    377  |      1 | 878887116
...

class UserModel
{
    public static function getRatings($userId)
    {
        $ratings = array();
        $file = fopen('u.data', 'r');
        while (($line = fgets($file)) !== false) {
            $data = explode("    ", trim($line));
            if ($userId == $data[0]) {
                $ratings[$data[1]] = $data[2]; // 记录该用户对该电影的评分
            }
        }
        fclose($file);
        return $ratings;
    }
}

class CFModel
{
    public static function predictRating($userId, $movieId)
    {
        $simUsers = array(); // 相似用户ID列表
        $simValues = array(); // 相似值列表
        $ratings1 = UserModel::getRatings($userId);
        if (empty($ratings1)) {
            return 0;
        }
        $file = fopen('u.data', 'r');
        while (($line = fgets($file)) !== false) {
            $data = explode("    ", trim($line));
            if ($userId != $data[0] && $movieId == $data[1]) { // 如果不是当前用户且电影相同
                $ratings2 = UserModel::getRatings($data[0]);
                if (!empty($ratings2)) { // 如果相似用户有评分记录
                    $sim = self::similarity($ratings1, $ratings2); // 计算相似度
                    if ($sim > 0) { // 如果相似度大于0
                        $simUsers[] = $data[0];
                        $simValues[] = $sim;
                    }
                }
            }
        }
        fclose($file);
        if (empty($simUsers)) {
            return 0;
        }
        arsort($simValues); // 按相似度从高到低排序
        $simUsers = array_slice($simUsers, 0, 10); // 取相似度最高的10个用户
        $simValues = array_slice($simValues, 0, 10); // 取相似度最高的10个用户的相似度值
        $sum = 0;
        $weight = 0;
        foreach ($simUsers as $k => $simUser) {
            $rating = UserModel::getRatings($simUser)[$movieId]; // 获取相似用户对该电影的评分
            $sum += $simValues[$k] * $rating; // 计算评分总和
            $weight += $simValues[$k]; // 计算权重总和
        }
        return round($sum / $weight); // 计算平均评分
    }

    public static function similarity($ratings1, $ratings2)
    {
        $commonKeys = array_keys(array_intersect_key($ratings1, $ratings2));
        if (empty($commonKeys)) {
            return 0;
        }
        $diff1 = $diff2 = 0;
        foreach ($commonKeys as $key) {
            $diff1 += ($ratings1[$key] - $ratings2[$key]) ** 2;
            $diff2 += ($ratings1[$key] - $ratings2[$key]) ** 2;
        }
        return $diff1 / sqrt($diff2);
    }
}

use WorkermanProtocolsHttpRequest;
use WorkermanProtocolsHttpResponse;
use WorkermanWorker;

require_once __DIR__ . '/vendor/autoload.php';

$http_worker = new Worker("http://0.0.0.0:8888");

$http_worker->onMessage = function(Request $request, Response $response) {
    $userId = $request->get('userId');
    $movieId = $request->get('movieId');
    $rating = CFModel::predictRating($userId, $movieId);
    $response->header('Content-Type', 'application/json');
    $response->end(json_encode(array('rating' => $rating)));
};

Worker::runAll();

http://localhost:8888?userId=1&movieId=1