怎样在PHP项目中实现多维缩放？

wen java案例 2026-07-22 184

本文目录导读：

怎样在PHP项目中实现多维缩放？

使用PHP科学计算库
手动实现经典MDS算法
通过外部工具集成
性能优化建议
完整示例：客户相似度分析
注意事项

在PHP项目中实现多维缩放（Multidimensional Scaling, MDS）通常需要借助数值计算库或自己实现算法，以下是几种常见方法：

使用PHP科学计算库

使用 `math-php` 库

use MathPHP\LinearAlgebra\Matrix;
use MathPHP\Statistics\Multivariate\MDS;
// 安装: composer require markrogoyski/math-php
// 准备距离矩阵 (欧几里得距离示例)
$distances = [
    [0, 2, 3, 4],
    [2, 0, 5, 6],
    [3, 5, 0, 7],
    [4, 6, 7, 0]
];
// 创建距离矩阵
$distanceMatrix = new Matrix($distances);
// 执行经典MDS
$mds = new MDS($distanceMatrix);
$coordinates = $mds->classical(); // 返回降维后的坐标
// 输出结果 (通常2D或3D坐标系)
foreach ($coordinates as $point) {
    echo "X: " . $point[0] . ", Y: " . $point[1] . "\n";
}

手动实现经典MDS算法

class ClassicMDS {
    /**
     * 执行经典多维缩放
     * @param array $distanceMatrix 距离矩阵 (对称)
     * @param int $dimensions 目标维度
     * @return array 降维后的坐标
     */
    public static function compute(array $distanceMatrix, int $dimensions = 2): array {
        $n = count($distanceMatrix);
        // 1. 距离平方矩阵
        $squared = [];
        for ($i = 0; $i < $n; $i++) {
            for ($j = 0; $j < $n; $j++) {
                $squared[$i][$j] = $distanceMatrix[$i][$j] ** 2;
            }
        }
        // 2. 双中心化
        $rowMeans = array_map(function($row) { 
            return array_sum($row) / count($row); 
        }, $squared);
        $colMeans = [];
        for ($j = 0; $j < $n; $j++) {
            $colMeans[$j] = array_sum(array_column($squared, $j)) / $n;
        }
        $totalMean = array_sum($rowMeans) / $n;
        // 计算内积矩阵 B
        $B = [];
        for ($i = 0; $i < $n; $i++) {
            for ($j = 0; $j < $n; $j++) {
                $B[$i][$j] = -0.5 * ($squared[$i][$j] - $rowMeans[$i] - $colMeans[$j] + $totalMean);
            }
        }
        // 3. 特征值分解 (使用幂迭代法近似)
        $eigenvalues = [];
        $eigenvectors = [];
        self::powerIteration($B, $dimensions, $eigenvalues, $eigenvectors);
        // 4. 计算坐标
        $coordinates = [];
        for ($i = 0; $i < $n; $i++) {
            $point = [];
            for ($k = 0; $k < $dimensions; $k++) {
                $point[] = sqrt(max(0, $eigenvalues[$k])) * $eigenvectors[$k][$i];
            }
            $coordinates[] = $point;
        }
        return $coordinates;
    }
    private static function powerIteration(array $matrix, int $k, array &$eigenvalues, array &$eigenvectors): void {
        $n = count($matrix);
        for ($iter = 0; $iter < $k; $iter++) {
            $vector = array_fill(0, $n, 1.0);
            // 幂迭代
            for ($power = 0; $power < 100; $power++) {
                $newVector = array_fill(0, $n, 0);
                for ($i = 0; $i < $n; $i++) {
                    for ($j = 0; $j < $n; $j++) {
                        $newVector[$i] += $matrix[$i][$j] * $vector[$j];
                    }
                }
                // 归一化
                $norm = sqrt(array_sum(array_map(function($x) { return $x ** 2; }, $newVector)));
                $vector = array_map(function($x) use ($norm) { 
                    return $norm > 0 ? $x / $norm : 0; 
                }, $newVector);
            }
            $eigenvectors[$iter] = $vector;
            // 计算特征值
            $eigenvalues[$iter] = 0;
            for ($i = 0; $i < $n; $i++) {
                $sum = 0;
                for ($j = 0; $j < $n; $j++) {
                    $sum += $matrix[$i][$j] * $vector[$j];
                }
                $eigenvalues[$iter] += $sum * $vector[$i];
            }
            // 去相关 (从矩阵中移除该特征向量)
            for ($i = 0; $i < $n; $i++) {
                for ($j = 0; $j < $n; $j++) {
                    $matrix[$i][$j] -= $eigenvalues[$iter] * $vector[$i] * $vector[$j];
                }
            }
        }
    }
}
// 使用示例
$distances = [
    [0, 2.5, 3.7],
    [2.5, 0, 4.2],
    [3.7, 4.2, 0]
];
$coordinates = ClassicMDS::compute($distances, 2);
print_r($coordinates);

通过外部工具集成

使用Python脚本 (推荐)

// Python MDS脚本
exec("python3 mds_script.py " . escapeshellarg(json_encode($distanceMatrix)), $output);
$result = json_decode($output[0], true);
// mds_script.py 内容:
// import sys, json
// from sklearn.manifold import MDS
// distances = np.array(json.loads(sys.argv[1]))
// mds = MDS(n_components=2, dissimilarity="precomputed")
// coords = mds.fit_transform(distances)
// print(json.dumps(coords.tolist()))

使用R语言

// 同样可以通过system()调用R脚本
$command = "Rscript mds_script.R " . escapeshellarg(json_encode($distanceMatrix));
exec($command, $output);

性能优化建议

// 1. 对大矩阵使用缓存
$cacheKey = md5(serialize($distanceMatrix));
if ($cached = apcu_fetch($cacheKey)) {
    return $cached;
}
// 2. 使用SVD分解替代特征值分解（更稳定）
// 3. 对大型数据集使用批处理
function batchMDS(array $data, int $batchSize = 1000): array {
    $result = [];
    foreach (array_chunk($data, $batchSize) as $batch) {
        $result = array_merge($result, processBatch($batch));
    }
    return $result;
}
// 4. 使用内存高效的数据结构
$matrix = new SplFixedArray($n);
for ($i = 0; $i < $n; $i++) {
    $matrix[$i] = new SplFixedArray($n);
}

完整示例：客户相似度分析

class CustomerMDS {
    private $customers = [];
    private $distanceMatrix = [];
    private $coordinates = [];
    public function addCustomers(array $customers): void {
        $this->customers = $customers;
    }
    public function computeSimilarity(array $metrics = ['purchase_amount', 'visit_frequency', 'category_preference']): void {
        $n = count($this->customers);
        // 标准化数据
        $normalized = $this->normalize($metrics);
        // 计算欧几里得距离
        for ($i = 0; $i < $n; $i++) {
            for ($j = $i; $j < $n; $j++) {
                $distance = 0;
                foreach ($metrics as $metric) {
                    $diff = $normalized[$i][$metric] - $normalized[$j][$metric];
                    $distance += $diff * $diff;
                }
                $this->distanceMatrix[$i][$j] = sqrt($distance);
                $this->distanceMatrix[$j][$i] = $this->distanceMatrix[$i][$j];
            }
        }
        // 执行MDS
        $this->coordinates = ClassicMDS::compute($this->distanceMatrix, 2);
    }
    public function getCustomerPosition(int $customerId): array {
        $idx = array_search($customerId, array_column($this->customers, 'id'));
        return $this->coordinates[$idx] ?? [];
    }
    public function findNearestCustomers(int $customerId, int $k = 5): array {
        $pos = $this->getCustomerPosition($customerId);
        $distances = [];
        foreach ($this->coordinates as $idx => $coord) {
            if ($this->customers[$idx]['id'] !== $customerId) {
                $dist = sqrt(($pos[0] - $coord[0])**2 + ($pos[1] - $coord[1])**2);
                $distances[$idx] = $dist;
            }
        }
        asort($distances);
        return array_slice(array_keys($distances), 0, $k);
    }
    private function normalize(array $metrics): array {
        $min = [];
        $max = [];
        foreach ($metrics as $metric) {
            $values = array_column($this->customers, $metric);
            $min[$metric] = min($values);
            $max[$metric] = max($values);
        }
        $normalized = $this->customers;
        foreach ($normalized as &$customer) {
            foreach ($metrics as $metric) {
                $range = $max[$metric] - $min[$metric];
                $customer[$metric] = $range > 0 ? ($customer[$metric] - $min[$metric]) / $range : 0;
            }
        }
        return $normalized;
    }
}