RandomForest::setFeatureSubsetRatio() - Code Metrics - Inspection of "Ensemble Classifiers : Bagging and RandomForest" - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#36)

unknown

created 2017-02-02 12:50 UTC

RandomForest::setFeatureSubsetRatio() A

↳ Parent: RandomForest

Complexity

Conditions	3
Paths	2

Size

Total Lines	8
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	8
rs	9.4285
c	0
b	0
f	0
cc	3
eloc	5
nc	2
nop	1

<?php
declare(strict_types=1);

namespace Phpml\Classification\Ensemble;

use Phpml\Classification\Ensemble\Bagging;
use Phpml\Classification\DecisionTree;
use Phpml\Classification\NaiveBayes;

class RandomForest extends Bagging
{
    /**
     * @var array
     */
    protected $classifierColumns;

    /**
     * @var float
     */
    protected $featureSubsetRatio = 0.7;

    public function setFeatureSubsetRatio(float $ratio)
    {
        if ($ratio < 0.1 || $ratio > 0.9) {
            throw new Exception("Feature subset ratio should be between 0.1 and 0.9");
        }
        $this->featureSubsetRatio = $ratio;
        return $this;
    }

    /**
     * @param int $index
     */
    protected function getRandomSubset($index)
    {
        list($subset, $targets) = parent::getRandomSubset($index);

        $features = [];
        $featureCount = (int)ceil($this->featureSubsetRatio * $this->featureCount);
        while (count($features) < $featureCount) {
            $rand = rand(0, $this->featureCount - 1);
            if (! in_array($rand, $features)) {
                $features[] = $rand;
            }
        }
        sort($features);
        $this->classifierColumns[$index] = $features;

        $columns = [];
        foreach ($features as $colIndex) {
            $columns[] = array_column($subset, $colIndex);
        }
        $subset= array_map(null, ...$columns);

        return [$subset, $targets];
    }

    /**
     * @param array $sample
     * @return mixed
     */
    protected function predictSample(array $sample)
    {
        $predictions = [];
        for ($i=0; $i<count($this->classifiers); $i++) {
for ($i=0; $i<count($array); $i++) { // calls count() on each iteration
}

// Better
for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once
}
            $samplePiece = [];
            foreach ($this->classifierColumns[$i] as $colIndex) {
                $samplePiece[] = $sample[$colIndex];
            }
            /* @var $classifier Classifier */
            $predictions[] = $this->classifiers[$i]->predict($samplePiece);
        }

        $counts = array_count_values($predictions);
        arsort($counts);
        reset($counts);
        return key($counts);
    }
}


1			<?php
2			declare(strict_types=1);
3
4			namespace Phpml\Classification\Ensemble;
5
6			use Phpml\Classification\Ensemble\Bagging;
7			use Phpml\Classification\DecisionTree;
8			use Phpml\Classification\NaiveBayes;
9
10			class RandomForest extends Bagging
11			{
12			/**
13			* @var array
14			*/
15			protected $classifierColumns;
16
17			/**
18			* @var float
19			*/
20			protected $featureSubsetRatio = 0.7;
21
22			public function setFeatureSubsetRatio(float $ratio)
23			{
24			if ($ratio < 0.1 \|\| $ratio > 0.9) {
25			throw new Exception("Feature subset ratio should be between 0.1 and 0.9");
26			}
27			$this->featureSubsetRatio = $ratio;
28			return $this;
29			}
30
31			/**
32			* @param int $index
33			*/
34			protected function getRandomSubset($index)
35			{
36			list($subset, $targets) = parent::getRandomSubset($index);
37
38			$features = [];
39			$featureCount = (int)ceil($this->featureSubsetRatio * $this->featureCount);
40			while (count($features) < $featureCount) {
41			$rand = rand(0, $this->featureCount - 1);
42			if (! in_array($rand, $features)) {
43			$features[] = $rand;
44			}
45			}
46			sort($features);
47			$this->classifierColumns[$index] = $features;
48
49			$columns = [];
50			foreach ($features as $colIndex) {
51			$columns[] = array_column($subset, $colIndex);
52			}
53			$subset= array_map(null, ...$columns);
54
55			return [$subset, $targets];
56			}
57
58			/**
59			* @param array $sample
60			* @return mixed
61			*/
62			protected function predictSample(array $sample)
63			{
64			$predictions = [];
65			for ($i=0; $i<count($this->classifiers); $i++) {
			0 ignored issues – show Performance Best Practice introduced 2017-02-02 12:46 UTC by Report Bug Copy Issue Report It seems like you are calling the size function `count()` as part of the test condition. You might want to compute the size beforehand, and not on each iteration. If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: for ($i=0; $i<count($array); $i++) { // calls count() on each iteration } // Better for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once } Loading history...
66			$samplePiece = [];
67			foreach ($this->classifierColumns[$i] as $colIndex) {
68			$samplePiece[] = $sample[$colIndex];
69			}
70			/* @var $classifier Classifier */
71			$predictions[] = $this->classifiers[$i]->predict($samplePiece);
72			}
73
74			$counts = array_count_values($predictions);
75			arsort($counts);
76			reset($counts);
77			return key($counts);
78			}
79			}
80

php-ai / php-ml

Pull Request — master (#36)

RandomForest::setFeatureSubsetRatio() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like