FuzzyCMeans::__construct() - Code Metrics - Inspection of "Implement OneHotEncoder (#384)" - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Branch — master (4590d5)

by Arkadiusz

created 2019-05-15 06:06 UTC

FuzzyCMeans::__construct() A

↳ Parent: FuzzyCMeans

Complexity

Conditions	2
Paths	2

Size

Total Lines	10
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	6
dl	0
loc	10
rs	10
c	0
b	0
f	0
cc	2
nc	2
nop	4

<?php

declare(strict_types=1);

namespace Phpml\Clustering;

use Phpml\Clustering\KMeans\Cluster;
use Phpml\Clustering\KMeans\Point;
use Phpml\Clustering\KMeans\Space;
use Phpml\Exception\InvalidArgumentException;
use Phpml\Math\Distance\Euclidean;

class FuzzyCMeans implements Clusterer
{
    /**
     * @var int
     */
    private $clustersNumber;

    /**
     * @var Cluster[]
     */
    private $clusters = [];

    /**
     * @var Space
     */
    private $space;

    /**
     * @var float[][]
     */
    private $membership = [];

    /**
     * @var float
     */
    private $fuzziness;

    /**
     * @var float
     */
    private $epsilon;

    /**
     * @var int
     */
    private $maxIterations;

    /**
     * @var int
     */
    private $sampleCount;

    /**
     * @var array
     */
    private $samples = [];

    /**
     * @throws InvalidArgumentException
     */
    public function __construct(int $clustersNumber, float $fuzziness = 2.0, float $epsilon = 1e-2, int $maxIterations = 100)
    {
        if ($clustersNumber <= 0) {
            throw new InvalidArgumentException('Invalid clusters number');
        }

        $this->clustersNumber = $clustersNumber;
        $this->fuzziness = $fuzziness;
        $this->epsilon = $epsilon;
        $this->maxIterations = $maxIterations;
    }

    public function getMembershipMatrix(): array
    {
        return $this->membership;
    }

    public function cluster(array $samples): array
    {
        // Initialize variables, clusters and membership matrix
        $this->sampleCount = count($samples);
        $this->samples = &$samples;
        $this->space = new Space(count($samples[0]));
        $this->initClusters();

        // Our goal is minimizing the objective value while
        // executing the clustering steps at a maximum number of iterations
        $lastObjective = 0.0;
        $iterations = 0;
        do {
            // Update the membership matrix and cluster centers, respectively
            $this->updateMembershipMatrix();
            $this->updateClusters();

            // Calculate the new value of the objective function
            $objectiveVal = $this->getObjective();
            $difference = abs($lastObjective - $objectiveVal);
            $lastObjective = $objectiveVal;
        } while ($difference > $this->epsilon && $iterations++ <= $this->maxIterations);

        // Attach (hard cluster) each data point to the nearest cluster
        for ($k = 0; $k < $this->sampleCount; ++$k) {
            $column = array_column($this->membership, $k);
            arsort($column);
            reset($column);
            $cluster = $this->clusters[key($column)];
            $cluster->attach(new Point($this->samples[$k]));
        }

        // Return grouped samples
        $grouped = [];
        foreach ($this->clusters as $cluster) {
            $grouped[] = $cluster->getPoints();
        }

        return $grouped;
    }

    protected function initClusters(): void
    {
        // Membership array is a matrix of cluster number by sample counts
        // We initilize the membership array with random values
        $dim = $this->space->getDimension();
        $this->generateRandomMembership($dim, $this->sampleCount);
        $this->updateClusters();
    }

    protected function generateRandomMembership(int $rows, int $cols): void
    {
        $this->membership = [];
        for ($i = 0; $i < $rows; ++$i) {
            $row = [];
            $total = 0.0;
            for ($k = 0; $k < $cols; ++$k) {
                $val = random_int(1, 5) / 10.0;
                $row[] = $val;
                $total += $val;
            }

            $this->membership[] = array_map(function ($val) use ($total) {
                return $val / $total;
            }, $row);
        }
    }

    protected function updateClusters(): void
    {
        $dim = $this->space->getDimension();
        if (count($this->clusters) === 0) {
            for ($i = 0; $i < $this->clustersNumber; ++$i) {
                $this->clusters[] = new Cluster($this->space, array_fill(0, $dim, 0.0));
            }
        }

        for ($i = 0; $i < $this->clustersNumber; ++$i) {
            $cluster = $this->clusters[$i];
            $center = $cluster->getCoordinates();
            for ($k = 0; $k < $dim; ++$k) {
                $a = $this->getMembershipRowTotal($i, $k, true);
                $b = $this->getMembershipRowTotal($i, $k, false);
                $center[$k] = $a / $b;
            }

            $cluster->setCoordinates($center);
        }
    }

    protected function getMembershipRowTotal(int $row, int $col, bool $multiply): float
    {
        $sum = 0.0;
        for ($k = 0; $k < $this->sampleCount; ++$k) {
            $val = $this->membership[$row][$k] ** $this->fuzziness;
            if ($multiply) {
                $val *= $this->samples[$k][$col];
            }

            $sum += $val;
        }

        return $sum;
    }

    protected function updateMembershipMatrix(): void
    {
        for ($i = 0; $i < $this->clustersNumber; ++$i) {
            for ($k = 0; $k < $this->sampleCount; ++$k) {
                $distCalc = $this->getDistanceCalc($i, $k);
                $this->membership[$i][$k] = 1.0 / $distCalc;
            }
        }
    }

    protected function getDistanceCalc(int $row, int $col): float
    {
        $sum = 0.0;
        $distance = new Euclidean();
        $dist1 = $distance->distance(
            $this->clusters[$row]->getCoordinates(),
            $this->samples[$col]
        );

        for ($j = 0; $j < $this->clustersNumber; ++$j) {
            $dist2 = $distance->distance(
                $this->clusters[$j]->getCoordinates(),
                $this->samples[$col]
            );

            $val = (($dist1 / $dist2) ** 2.0) / ($this->fuzziness - 1);
            $sum += $val;
        }

        return $sum;
    }

    /**
     * The objective is to minimize the distance between all data points
     * and all cluster centers. This method returns the summation of all
     * these distances
     */
    protected function getObjective(): float
    {
        $sum = 0.0;
        $distance = new Euclidean();
        for ($i = 0; $i < $this->clustersNumber; ++$i) {
            $clust = $this->clusters[$i]->getCoordinates();
            for ($k = 0; $k < $this->sampleCount; ++$k) {
                $point = $this->samples[$k];
                $sum += $distance->distance($clust, $point);
            }
        }

        return $sum;
    }
}


1			<?php
2
3			declare(strict_types=1);
4
5			namespace Phpml\Clustering;
6
7			use Phpml\Clustering\KMeans\Cluster;
8			use Phpml\Clustering\KMeans\Point;
9			use Phpml\Clustering\KMeans\Space;
10			use Phpml\Exception\InvalidArgumentException;
11			use Phpml\Math\Distance\Euclidean;
12
13			class FuzzyCMeans implements Clusterer
14			{
15			/**
16			* @var int
17			*/
18			private $clustersNumber;
19
20			/**
21			* @var Cluster[]
22			*/
23			private $clusters = [];
24
25			/**
26			* @var Space
27			*/
28			private $space;
29
30			/**
31			* @var float[][]
32			*/
33			private $membership = [];
34
35			/**
36			* @var float
37			*/
38			private $fuzziness;
39
40			/**
41			* @var float
42			*/
43			private $epsilon;
44
45			/**
46			* @var int
47			*/
48			private $maxIterations;
49
50			/**
51			* @var int
52			*/
53			private $sampleCount;
54
55			/**
56			* @var array
57			*/
58			private $samples = [];
59
60			/**
61			* @throws InvalidArgumentException
62			*/
63			public function __construct(int $clustersNumber, float $fuzziness = 2.0, float $epsilon = 1e-2, int $maxIterations = 100)
64			{
65			if ($clustersNumber <= 0) {
66			throw new InvalidArgumentException('Invalid clusters number');
67			}
68
69			$this->clustersNumber = $clustersNumber;
70			$this->fuzziness = $fuzziness;
71			$this->epsilon = $epsilon;
72			$this->maxIterations = $maxIterations;
73			}
74
75			public function getMembershipMatrix(): array
76			{
77			return $this->membership;
78			}
79
80			public function cluster(array $samples): array
81			{
82			// Initialize variables, clusters and membership matrix
83			$this->sampleCount = count($samples);
84			$this->samples = &$samples;
85			$this->space = new Space(count($samples[0]));
86			$this->initClusters();
87
88			// Our goal is minimizing the objective value while
89			// executing the clustering steps at a maximum number of iterations
90			$lastObjective = 0.0;
91			$iterations = 0;
92			do {
93			// Update the membership matrix and cluster centers, respectively
94			$this->updateMembershipMatrix();
95			$this->updateClusters();
96
97			// Calculate the new value of the objective function
98			$objectiveVal = $this->getObjective();
99			$difference = abs($lastObjective - $objectiveVal);
100			$lastObjective = $objectiveVal;
101			} while ($difference > $this->epsilon && $iterations++ <= $this->maxIterations);
102
103			// Attach (hard cluster) each data point to the nearest cluster
104			for ($k = 0; $k < $this->sampleCount; ++$k) {
105			$column = array_column($this->membership, $k);
106			arsort($column);
107			reset($column);
108			$cluster = $this->clusters[key($column)];
109			$cluster->attach(new Point($this->samples[$k]));
110			}
111
112			// Return grouped samples
113			$grouped = [];
114			foreach ($this->clusters as $cluster) {
115			$grouped[] = $cluster->getPoints();
116			}
117
118			return $grouped;
119			}
120
121			protected function initClusters(): void
122			{
123			// Membership array is a matrix of cluster number by sample counts
124			// We initilize the membership array with random values
125			$dim = $this->space->getDimension();
126			$this->generateRandomMembership($dim, $this->sampleCount);
127			$this->updateClusters();
128			}
129
130			protected function generateRandomMembership(int $rows, int $cols): void
131			{
132			$this->membership = [];
133			for ($i = 0; $i < $rows; ++$i) {
134			$row = [];
135			$total = 0.0;
136			for ($k = 0; $k < $cols; ++$k) {
137			$val = random_int(1, 5) / 10.0;
138			$row[] = $val;
139			$total += $val;
140			}
141
142			$this->membership[] = array_map(function ($val) use ($total) {
143			return $val / $total;
144			}, $row);
145			}
146			}
147
148			protected function updateClusters(): void
149			{
150			$dim = $this->space->getDimension();
151			if (count($this->clusters) === 0) {
152			for ($i = 0; $i < $this->clustersNumber; ++$i) {
153			$this->clusters[] = new Cluster($this->space, array_fill(0, $dim, 0.0));
154			}
155			}
156
157			for ($i = 0; $i < $this->clustersNumber; ++$i) {
158			$cluster = $this->clusters[$i];
159			$center = $cluster->getCoordinates();
160			for ($k = 0; $k < $dim; ++$k) {
161			$a = $this->getMembershipRowTotal($i, $k, true);
162			$b = $this->getMembershipRowTotal($i, $k, false);
163			$center[$k] = $a / $b;
164			}
165
166			$cluster->setCoordinates($center);
167			}
168			}
169
170			protected function getMembershipRowTotal(int $row, int $col, bool $multiply): float
171			{
172			$sum = 0.0;
173			for ($k = 0; $k < $this->sampleCount; ++$k) {
174			$val = $this->membership[$row][$k] ** $this->fuzziness;
175			if ($multiply) {
176			$val *= $this->samples[$k][$col];
177			}
178
179			$sum += $val;
180			}
181
182			return $sum;
183			}
184
185			protected function updateMembershipMatrix(): void
186			{
187			for ($i = 0; $i < $this->clustersNumber; ++$i) {
188			for ($k = 0; $k < $this->sampleCount; ++$k) {
189			$distCalc = $this->getDistanceCalc($i, $k);
190			$this->membership[$i][$k] = 1.0 / $distCalc;
191			}
192			}
193			}
194
195			protected function getDistanceCalc(int $row, int $col): float
196			{
197			$sum = 0.0;
198			$distance = new Euclidean();
199			$dist1 = $distance->distance(
200			$this->clusters[$row]->getCoordinates(),
201			$this->samples[$col]
202			);
203
204			for ($j = 0; $j < $this->clustersNumber; ++$j) {
205			$dist2 = $distance->distance(
206			$this->clusters[$j]->getCoordinates(),
207			$this->samples[$col]
208			);
209
210			$val = (($dist1 / $dist2) ** 2.0) / ($this->fuzziness - 1);
211			$sum += $val;
212			}
213
214			return $sum;
215			}
216
217			/**
218			* The objective is to minimize the distance between all data points
219			* and all cluster centers. This method returns the summation of all
220			* these distances
221			*/
222			protected function getObjective(): float
223			{
224			$sum = 0.0;
225			$distance = new Euclidean();
226			for ($i = 0; $i < $this->clustersNumber; ++$i) {
227			$clust = $this->clusters[$i]->getCoordinates();
228			for ($k = 0; $k < $this->sampleCount; ++$k) {
229			$point = $this->samples[$k];
230			$sum += $distance->distance($clust, $point);
231			}
232			}
233
234			return $sum;
235			}
236			}
237

php-ai / php-ml

Branch — master (4590d5)

FuzzyCMeans::__construct() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like