Phpml\Math\Statistic\Covariance::fromDataset()

Complexity

Conditions	16
Paths	9

Size

Total Lines	56
Code Lines	29

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

<?php
    public static function fromDataset(array $data, int $i, int $k, bool $sample = true, ?float $meanX = null, ?float $meanY = null): float
    {
        if (count($data) === 0) {
            throw new InvalidArgumentException('The array has zero elements');
        }

        $n = count($data);
        if ($sample && $n === 1) {
            throw new InvalidArgumentException('The array must have at least 2 elements');
        }

        if ($i < 0 || $k < 0 || $i >= $n || $k >= $n) {
            throw new InvalidArgumentException('Given indices i and k do not match with the dimensionality of data');
        }

        if ($meanX === null || $meanY === null) {
            $x = array_column($data, $i);
            $y = array_column($data, $k);

            $meanX = Mean::arithmetic($x);
            $meanY = Mean::arithmetic($y);
            $sum = 0.0;
            foreach ($x as $index => $xi) {
                $yi = $y[$index];
                $sum += ($xi - $meanX) * ($yi - $meanY);
            }
        } else {
            // In the case, whole dataset given along with dimension indices, i and k,
            // we would like to avoid getting column data with array_column and operate
            // over this extra copy of column data for memory efficiency purposes.
            //
            // Instead we traverse through the whole data and get what we actually need
            // without copying the data. This way, memory use will be reduced
            // with a slight cost of CPU utilization.
            $sum = 0.0;
            foreach ($data as $row) {
                $val = [0, 0];
                foreach ($row as $index => $col) {
                    if ($index == $i) {
                        $val[0] = $col - $meanX;
                    }

                    if ($index == $k) {
                        $val[1] = $col - $meanY;
                    }
                }

                $sum += $val[0] * $val[1];
            }
        }

        if ($sample) {
            --$n;
        }

        return $sum / $n;
    }