データの前処理と特徴エンジニアリングに PHP を使用する方法

$csvFile = 'data.csv'; $data = []; if (($handle = fopen($csvFile, 'r')) !== false) { while (($row = fgetcsv($handle)) !== false) { $data[] = $row; } fclose($handle); } // 打印数据 print_r($data);

foreach ($data as &$row) { for ($i = 0; $i < count($row); $i++) { if ($row[$i] === null || $row[$i] === '') { // 填充缺失值为0 $row[$i] = 0; } } }

foreach ($data as &$row) { for ($i = 0; $i < count($row); $i++) { if ($row[$i] < $lowerThreshold || $row[$i] > $upperThreshold) { // 替换异常值为平均值 $row[$i] = $meanValue; } } }

$newData = []; $uniqueKeys = []; foreach ($data as $row) { $key = implode('-', $row); if (!in_array($key, $uniqueKeys)) { $newData[] = $row; $uniqueKeys[] = $key; } } // 更新数据 $data = $newData;

$categories = ['cat', 'dog', 'rabbit']; $encodedData = []; foreach ($data as $row) { $encodedRow = []; foreach ($row as $value) { if (in_array($value, $categories)) { // 使用数字编码离散特征值 $encodedRow[] = array_search($value, $categories); } else { // 原样保留其他特征值 $encodedRow[] = $value; } } $encodedData[] = $encodedRow; }

$normalizedData = []; foreach ($data as $row) { $mean = array_sum($row) / count($row); // 计算平均值 $stdDev = sqrt(array_sum(array_map(function ($value) use ($mean) { return pow($value - $mean, 2); }, $row)) / count($row)); // 计算标准差 $normalizedRow = array_map(function ($value) use ($mean, $stdDev) { // 标准化特征值 return ($value - $mean) / $stdDev; }, $row); $normalizedData[] = $normalizedRow; }

require 'vendor/autoload.php'; use PhpmlClusteringKMeans; $clusterer = new KMeans(3); // 设定聚类数为3 $clusterer->train($normalizedData); $clusterLabels = $clusterer->predict($normalizedData); // 打印聚类结果 print_r($clusterLabels);