Space::initializeKMPPClusters() - Code Metrics - Inspection of "extract functions from loops and remove unused cod..." - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — develop ( 2f5b09...f186aa )

by Arkadiusz

created 2016-08-02 11:24 UTC

Space::initializeKMPPClusters() B

↳ Parent: Space

Complexity

Conditions	5
Paths	7

Size

Total Lines	29
Code Lines	17

Duplication

Lines	0
Ratio	0 %

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
c	2
b	0
f	0
dl	0
loc	29
rs	8.439
cc	5
eloc	17
nc	7
nop	1

<?php

declare (strict_types = 1);

namespace Phpml\Clustering\KMeans;

use Phpml\Clustering\KMeans;
use SplObjectStorage;
use LogicException;
use InvalidArgumentException;

class Space extends SplObjectStorage
{
    /**
     * @var int
     */
    protected $dimension;

    /**
     * @param $dimension
     */
    public function __construct($dimension)
    {
        if ($dimension < 1) {
            throw new LogicException('a space dimension cannot be null or negative');
        }

        $this->dimension = $dimension;
    }

    /**
     * @return array
     */
    public function toArray()
    {
        $points = [];
        foreach ($this as $point) {
            $points[] = $point->toArray();
        }

        return ['points' => $points];
    }

    /**
     * @param array $coordinates
     *
     * @return Point
     */
    public function newPoint(array $coordinates)
    {
        if (count($coordinates) != $this->dimension) {
            throw new LogicException('('.implode(',', $coordinates).') is not a point of this space');
        }

        return new Point($coordinates);
    }

    /**
     * @param array $coordinates
     * @param null  $data
     */
    public function addPoint(array $coordinates, $data = null)
    {
        $this->attach($this->newPoint($coordinates), $data);
    }

    /**
     * @param object $point
     * @param null   $data
     */
    public function attach($point, $data = null)
    {
        if (!$point instanceof Point) {
            throw new InvalidArgumentException('can only attach points to spaces');
        }

        parent::attach($point, $data);
    }

    /**
     * @return int
     */
    public function getDimension()
    {
        return $this->dimension;
    }

    /**
     * @return array|bool
     */
    public function getBoundaries()
    {
        if (!count($this)) {
            return false;
        }

        $min = $this->newPoint(array_fill(0, $this->dimension, null));
        $max = $this->newPoint(array_fill(0, $this->dimension, null));

        foreach ($this as $point) {
            for ($n = 0; $n < $this->dimension; ++$n) {
                ($min[$n] > $point[$n] || $min[$n] === null) && $min[$n] = $point[$n];
                ($max[$n] < $point[$n] || $max[$n] === null) && $max[$n] = $point[$n];
            }
        }

        return array($min, $max);
    }

    /**
     * @param Point $min
     * @param Point $max
     *
     * @return Point
     */
    public function getRandomPoint(Point $min, Point $max)
    {
        $point = $this->newPoint(array_fill(0, $this->dimension, null));

        for ($n = 0; $n < $this->dimension; ++$n) {
            $point[$n] = rand($min[$n], $max[$n]);
        }

        return $point;
    }

    /**
     * @param int $clustersNumber
     * @param int $initMethod
     *
     * @return array|Cluster[]
     */
    public function cluster(int $clustersNumber, int $initMethod = KMeans::INIT_RANDOM)
    {
        $clusters = $this->initializeClusters($clustersNumber, $initMethod);

        do {

        } while (!$this->iterate($clusters));

        return $clusters;
    }

    /**
     * @param $clustersNumber
     * @param $initMethod
     *
     * @return array|Cluster[]
     */
    protected function initializeClusters(int $clustersNumber, int $initMethod)
    {
        switch ($initMethod) {
            case KMeans::INIT_RANDOM:
                $clusters = $this->initializeRandomClusters($clustersNumber);
                break;

            case KMeans::INIT_KMEANS_PLUS_PLUS:
                $clusters = $this->initializeKMPPClusters($clustersNumber);
                break;
        }
        $clusters[0]->attachAll($this);
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

        case 'bar':
            $x = 2;
            break;
    }

    // $x is potentially undefined here.
    echo $x;
}

        return $clusters;
    }

    /**
     * @param $clusters
     *
     * @return bool
     */
    protected function iterate($clusters)
    {
        $convergence = true;

        $attach = new SplObjectStorage();
        $detach = new SplObjectStorage();

        foreach ($clusters as $cluster) {
            foreach ($cluster as $point) {
                $closest = $point->getClosest($clusters);

                if ($closest !== $cluster) {
                    isset($attach[$closest]) || $attach[$closest] = new SplObjectStorage();
                    isset($detach[$cluster]) || $detach[$cluster] = new SplObjectStorage();

                    $attach[$closest]->attach($point);
                    $detach[$cluster]->attach($point);

                    $convergence = false;
                }
            }
        }

        foreach ($attach as $cluster) {
            $cluster->attachAll($attach[$cluster]);
        }

        foreach ($detach as $cluster) {
            $cluster->detachAll($detach[$cluster]);
        }

        foreach ($clusters as $cluster) {
            $cluster->updateCentroid();
        }

        return $convergence;
    }

    /**
     * @param int $clustersNumber
     *
     * @return array
     */
    private function initializeRandomClusters(int $clustersNumber)
    {
        $clusters = [];
        list($min, $max) = $this->getBoundaries();

        for ($n = 0; $n < $clustersNumber; ++$n) {
            $clusters[] = new Cluster($this, $this->getRandomPoint($min, $max)->getCoordinates());
        }

        return $clusters;
    }

    /**
     * @param int $clustersNumber
     *
     * @return array
     */
    protected function initializeKMPPClusters(int $clustersNumber)
    {
        $clusters = [];
        $this->rewind();

        $clusters[] = new Cluster($this, $this->current()->getCoordinates());

        $distances = new SplObjectStorage();

        for ($i = 1; $i < $clustersNumber; ++$i) {
            $sum = 0;
            foreach ($this as $point) {
                $distance = $point->getDistanceWith($point->getClosest($clusters));
                $sum += $distances[$point] = $distance;
            }

            $sum = rand(0, (int) $sum);
            foreach ($this as $point) {
                if (($sum -= $distances[$point]) > 0) {
                    continue;
                }

                $clusters[] = new Cluster($this, $point->getCoordinates());
                break;
            }
        }

        return $clusters;
    }
}


1			<?php
2
3			declare (strict_types = 1);
4
5			namespace Phpml\Clustering\KMeans;
6
7			use Phpml\Clustering\KMeans;
8			use SplObjectStorage;
9			use LogicException;
10			use InvalidArgumentException;
11
12			class Space extends SplObjectStorage
13			{
14			/**
15			* @var int
16			*/
17			protected $dimension;
18
19			/**
20			* @param $dimension
21			*/
22			public function __construct($dimension)
23			{
24			if ($dimension < 1) {
25			throw new LogicException('a space dimension cannot be null or negative');
26			}
27
28			$this->dimension = $dimension;
29			}
30
31			/**
32			* @return array
33			*/
34			public function toArray()
35			{
36			$points = [];
37			foreach ($this as $point) {
38			$points[] = $point->toArray();
39			}
40
41			return ['points' => $points];
42			}
43
44			/**
45			* @param array $coordinates
46			*
47			* @return Point
48			*/
49			public function newPoint(array $coordinates)
50			{
51			if (count($coordinates) != $this->dimension) {
52			throw new LogicException('('.implode(',', $coordinates).') is not a point of this space');
53			}
54
55			return new Point($coordinates);
56			}
57
58			/**
59			* @param array $coordinates
60			* @param null $data
61			*/
62			public function addPoint(array $coordinates, $data = null)
63			{
64			$this->attach($this->newPoint($coordinates), $data);
65			}
66
67			/**
68			* @param object $point
69			* @param null $data
70			*/
71			public function attach($point, $data = null)
72			{
73			if (!$point instanceof Point) {
74			throw new InvalidArgumentException('can only attach points to spaces');
75			}
76
77			parent::attach($point, $data);
78			}
79
80			/**
81			* @return int
82			*/
83			public function getDimension()
84			{
85			return $this->dimension;
86			}
87
88			/**
89			* @return array\|bool
90			*/
91			public function getBoundaries()
92			{
93			if (!count($this)) {
94			return false;
95			}
96
97			$min = $this->newPoint(array_fill(0, $this->dimension, null));
98			$max = $this->newPoint(array_fill(0, $this->dimension, null));
99
100			foreach ($this as $point) {
101			for ($n = 0; $n < $this->dimension; ++$n) {
102			($min[$n] > $point[$n] \|\| $min[$n] === null) && $min[$n] = $point[$n];
103			($max[$n] < $point[$n] \|\| $max[$n] === null) && $max[$n] = $point[$n];
104			}
105			}
106
107			return array($min, $max);
108			}
109
110			/**
111			* @param Point $min
112			* @param Point $max
113			*
114			* @return Point
115			*/
116			public function getRandomPoint(Point $min, Point $max)
117			{
118			$point = $this->newPoint(array_fill(0, $this->dimension, null));
119
120			for ($n = 0; $n < $this->dimension; ++$n) {
121			$point[$n] = rand($min[$n], $max[$n]);
122			}
123
124			return $point;
125			}
126
127			/**
128			* @param int $clustersNumber
129			* @param int $initMethod
130			*
131			* @return array\|Cluster[]
132			*/
133			public function cluster(int $clustersNumber, int $initMethod = KMeans::INIT_RANDOM)
134			{
135			$clusters = $this->initializeClusters($clustersNumber, $initMethod);
136
137			do {
			0 ignored issues – show Unused Code introduced 2016-05-02 12:05 UTC by Report Bug Copy Issue Report This `do` loop is empty and can be removed. This check looks for `do` loops that have no statements or where all statements have been commented out. This may be the result of changes for debugging or the code may simply be obsolete. Consider removing the loop. Loading history...
138			} while (!$this->iterate($clusters));
139
140			return $clusters;
141			}
142
143			/**
144			* @param $clustersNumber
145			* @param $initMethod
146			*
147			* @return array\|Cluster[]
148			*/
149			protected function initializeClusters(int $clustersNumber, int $initMethod)
150			{
151			switch ($initMethod) {
152			case KMeans::INIT_RANDOM:
153			$clusters = $this->initializeRandomClusters($clustersNumber);
154			break;
155
156			case KMeans::INIT_KMEANS_PLUS_PLUS:
157			$clusters = $this->initializeKMPPClusters($clustersNumber);
158			break;
159			}
160			$clusters[0]->attachAll($this);
			0 ignored issues – show Bug introduced 2016-05-01 21:46 UTC by Report Bug Copy Issue Report The variable `$clusters` does not seem to be defined for all execution paths leading up to this point. If you define a variable conditionally, it can happen that it is not defined for all execution paths. Let’s take a look at an example: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } // $x is potentially undefined here. echo $x; } In the above example, the variable `$x` is defined if you pass “foo” or “bar” as argument for `$a`. However, since the `switch` statement has no default case statement, if you pass any other value, the variable `$x` would be undefined. Available Fixes Check for existence of the variable explicitly: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } if (isset($x)) { // Make sure it's always set. echo $x; } } Define a default value for the variable: function myFunction($a) { $x = ''; // Set a default which gets overridden for certain paths. switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } echo $x; } Add a value for the missing path: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; // We add support for the missing case. default: $x = ''; break; } echo $x; } Loading history...
161
162			return $clusters;
163			}
164
165			/**
166			* @param $clusters
167			*
168			* @return bool
169			*/
170			protected function iterate($clusters)
171			{
172			$convergence = true;
173
174			$attach = new SplObjectStorage();
175			$detach = new SplObjectStorage();
176
177			foreach ($clusters as $cluster) {
178			foreach ($cluster as $point) {
179			$closest = $point->getClosest($clusters);
180
181			if ($closest !== $cluster) {
182			isset($attach[$closest]) \|\| $attach[$closest] = new SplObjectStorage();
183			isset($detach[$cluster]) \|\| $detach[$cluster] = new SplObjectStorage();
184
185			$attach[$closest]->attach($point);
186			$detach[$cluster]->attach($point);
187
188			$convergence = false;
189			}
190			}
191			}
192
193			foreach ($attach as $cluster) {
194			$cluster->attachAll($attach[$cluster]);
195			}
196
197			foreach ($detach as $cluster) {
198			$cluster->detachAll($detach[$cluster]);
199			}
200
201			foreach ($clusters as $cluster) {
202			$cluster->updateCentroid();
203			}
204
205			return $convergence;
206			}
207
208			/**
209			* @param int $clustersNumber
210			*
211			* @return array
212			*/
213			private function initializeRandomClusters(int $clustersNumber)
214			{
215			$clusters = [];
216			list($min, $max) = $this->getBoundaries();
217
218			for ($n = 0; $n < $clustersNumber; ++$n) {
219			$clusters[] = new Cluster($this, $this->getRandomPoint($min, $max)->getCoordinates());
220			}
221
222			return $clusters;
223			}
224
225			/**
226			* @param int $clustersNumber
227			*
228			* @return array
229			*/
230			protected function initializeKMPPClusters(int $clustersNumber)
231			{
232			$clusters = [];
233			$this->rewind();
234
235			$clusters[] = new Cluster($this, $this->current()->getCoordinates());
236
237			$distances = new SplObjectStorage();
238
239			for ($i = 1; $i < $clustersNumber; ++$i) {
240			$sum = 0;
241			foreach ($this as $point) {
242			$distance = $point->getDistanceWith($point->getClosest($clusters));
243			$sum += $distances[$point] = $distance;
244			}
245
246			$sum = rand(0, (int) $sum);
247			foreach ($this as $point) {
248			if (($sum -= $distances[$point]) > 0) {
249			continue;
250			}
251
252			$clusters[] = new Cluster($this, $point->getCoordinates());
253			break;
254			}
255			}
256
257			return $clusters;
258			}
259			}
260

php-ai / php-ml

Push — develop ( 2f5b09...f186aa )

Space::initializeKMPPClusters() B

Complexity

Size

Duplication

Importance

Available Fixes

Duplication Side-by-Side

Filter issues like