mirror of
https://github.com/Llewellynvdm/php-ml.git
synced 2024-06-15 23:02:21 +00:00
3ba35918a3
* Add sum of squares deviations * Calculate population variance * Add VarianceThreshold - feature selection transformer * Add docs about VarianceThreshold * Add missing code for pipeline usage
28 lines
811 B
PHP
28 lines
811 B
PHP
<?php
|
|
|
|
declare(strict_types=1);
|
|
|
|
namespace Phpml\Math\Statistic;
|
|
|
|
/**
|
|
* In probability theory and statistics, variance is the expectation of the squared deviation of a random variable from its mean.
|
|
* Informally, it measures how far a set of (random) numbers are spread out from their average value
|
|
* https://en.wikipedia.org/wiki/Variance
|
|
*/
|
|
final class Variance
|
|
{
|
|
/**
|
|
* Population variance
|
|
* Use when all possible observations of the system are present.
|
|
* If used with a subset of data (sample variance), it will be a biased variance.
|
|
*
|
|
* ∑⟮xᵢ - μ⟯²
|
|
* σ² = ----------
|
|
* N
|
|
*/
|
|
public static function population(array $population): float
|
|
{
|
|
return StandardDeviation::sumOfSquares($population) / count($population);
|
|
}
|
|
}
|