| 1 |
efrain |
1 |
<?php
|
|
|
2 |
|
|
|
3 |
declare(strict_types=1);
|
|
|
4 |
|
|
|
5 |
namespace Phpml\FeatureSelection\ScoringFunction;
|
|
|
6 |
|
|
|
7 |
use Phpml\FeatureSelection\ScoringFunction;
|
|
|
8 |
use Phpml\Math\Matrix;
|
|
|
9 |
use Phpml\Math\Statistic\Mean;
|
|
|
10 |
|
|
|
11 |
/**
|
|
|
12 |
* Quick linear model for testing the effect of a single regressor,
|
|
|
13 |
* sequentially for many regressors.
|
|
|
14 |
*
|
|
|
15 |
* This is done in 2 steps:
|
|
|
16 |
*
|
|
|
17 |
* 1. The cross correlation between each regressor and the target is computed,
|
|
|
18 |
* that is, ((X[:, i] - mean(X[:, i])) * (y - mean_y)) / (std(X[:, i]) *std(y)).
|
|
|
19 |
* 2. It is converted to an F score.
|
|
|
20 |
*
|
|
|
21 |
* Ported from scikit-learn f_regression function (http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.f_regression.html#sklearn.feature_selection.f_regression)
|
|
|
22 |
*/
|
|
|
23 |
final class UnivariateLinearRegression implements ScoringFunction
|
|
|
24 |
{
|
|
|
25 |
/**
|
|
|
26 |
* @var bool
|
|
|
27 |
*/
|
|
|
28 |
private $center;
|
|
|
29 |
|
|
|
30 |
/**
|
|
|
31 |
* @param bool $center - if true samples and targets will be centered
|
|
|
32 |
*/
|
|
|
33 |
public function __construct(bool $center = true)
|
|
|
34 |
{
|
|
|
35 |
$this->center = $center;
|
|
|
36 |
}
|
|
|
37 |
|
|
|
38 |
public function score(array $samples, array $targets): array
|
|
|
39 |
{
|
|
|
40 |
if ($this->center) {
|
|
|
41 |
$this->centerTargets($targets);
|
|
|
42 |
$this->centerSamples($samples);
|
|
|
43 |
}
|
|
|
44 |
|
|
|
45 |
$correlations = [];
|
|
|
46 |
foreach (array_keys($samples[0]) as $index) {
|
|
|
47 |
$featureColumn = array_column($samples, $index);
|
|
|
48 |
$correlations[$index] =
|
|
|
49 |
Matrix::dot($targets, $featureColumn)[0] / (new Matrix($featureColumn, false))->transpose()->frobeniusNorm()
|
|
|
50 |
/ (new Matrix($targets, false))->frobeniusNorm();
|
|
|
51 |
}
|
|
|
52 |
|
|
|
53 |
$degreesOfFreedom = count($targets) - ($this->center ? 2 : 1);
|
|
|
54 |
|
|
|
55 |
return array_map(function (float $correlation) use ($degreesOfFreedom): float {
|
|
|
56 |
return $correlation ** 2 / (1 - $correlation ** 2) * $degreesOfFreedom;
|
|
|
57 |
}, $correlations);
|
|
|
58 |
}
|
|
|
59 |
|
|
|
60 |
private function centerTargets(array &$targets): void
|
|
|
61 |
{
|
|
|
62 |
$mean = Mean::arithmetic($targets);
|
|
|
63 |
array_walk($targets, function (&$target) use ($mean): void {
|
|
|
64 |
$target -= $mean;
|
|
|
65 |
});
|
|
|
66 |
}
|
|
|
67 |
|
|
|
68 |
private function centerSamples(array &$samples): void
|
|
|
69 |
{
|
|
|
70 |
$means = [];
|
|
|
71 |
foreach ($samples[0] as $index => $feature) {
|
|
|
72 |
$means[$index] = Mean::arithmetic(array_column($samples, $index));
|
|
|
73 |
}
|
|
|
74 |
|
|
|
75 |
foreach ($samples as &$sample) {
|
|
|
76 |
foreach ($sample as $index => &$feature) {
|
|
|
77 |
$feature -= $means[$index];
|
|
|
78 |
}
|
|
|
79 |
}
|
|
|
80 |
}
|
|
|
81 |
}
|