TokenCountVectorizer::fit() - Code Metrics - Inspection of "php-cs-fixer" - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — develop ( 7f4a0b...601ff8 )

by Arkadiusz

created 2016-06-16 22:34 UTC

TokenCountVectorizer::fit() A

↳ Parent: TokenCountVectorizer

Complexity

Conditions	1
Paths	1

Size

Total Lines	4
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
c	1
b	0
f	1
dl	0
loc	4
rs	10
cc	1
eloc	2
nc	1
nop	1

<?php

declare (strict_types = 1);

namespace Phpml\FeatureExtraction;

use Phpml\Tokenization\Tokenizer;
use Phpml\Transformer;

class TokenCountVectorizer implements Transformer
{
    /**
     * @var Tokenizer
     */
    private $tokenizer;

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

    /**
     * @var array
     */
    private $vocabulary;

    /**
     * @var array
     */
    private $frequencies;

    /**
     * @param Tokenizer $tokenizer
     * @param float     $minDF
     */
    public function __construct(Tokenizer $tokenizer, float $minDF = 0)
    {
        $this->tokenizer = $tokenizer;
        $this->minDF = $minDF;
class Id
{
    public $id;

    public function __construct($id)
    {
        $this->id = $id;
    }

}

class Account
{
    /** @var  Id $id */
    public $id;
}

$account_id = false;

if (starsAreRight()) {
    $account_id = new Id(42);
}

$account = new Account();
if ($account instanceof Id)
{
    $account->id = $account_id;
}
        $this->vocabulary = [];
        $this->frequencies = [];
    }

    /**
     * @param array $samples
     */
    public function fit(array $samples)
    {
        $this->buildVocabulary($samples);
    }

    /**
     * @param array $samples
     */
    public function transform(array &$samples)
    {
        foreach ($samples as &$sample) {
            $this->transformSample($sample);
        }

        $this->checkDocumentFrequency($samples);
    }

    /**
     * @return array
     */
    public function getVocabulary()
    {
        return array_flip($this->vocabulary);
    }

    /**
     * @param array $samples
     */
    private function buildVocabulary(array &$samples)
    {
        foreach ($samples as $index => $sample) {
            $tokens = $this->tokenizer->tokenize($sample);
            foreach ($tokens as $token) {
                $this->addTokenToVocabulary($token);
            }
        }
    }

    /**
     * @param string $sample
     */
    private function transformSample(string &$sample)
    {
        $counts = [];
        $tokens = $this->tokenizer->tokenize($sample);

        foreach ($tokens as $token) {
            $index = $this->getTokenIndex($token);
            if (false !== $index) {
                $this->updateFrequency($token);
                if (!isset($counts[$index])) {
                    $counts[$index] = 0;
                }

                ++$counts[$index];
            }
        }

        foreach ($this->vocabulary as $index) {
            if (!isset($counts[$index])) {
                $counts[$index] = 0;
            }
        }

        $sample = $counts;
    }

    /**
     * @param string $token
     *
     * @return int|bool
     */
    private function getTokenIndex(string $token)
    {
        return isset($this->vocabulary[$token]) ? $this->vocabulary[$token] : false;
    }

    /**
     * @param string $token
     */
    private function addTokenToVocabulary(string $token)
    {
        if (!isset($this->vocabulary[$token])) {
            $this->vocabulary[$token] = count($this->vocabulary);
        }
    }

    /**
     * @param string $token
     */
    private function updateFrequency(string $token)
    {
        if (!isset($this->frequencies[$token])) {
            $this->frequencies[$token] = 0;
        }

        ++$this->frequencies[$token];
    }

    /**
     * @param array $samples
     * 
     * @return array
     */
    private function checkDocumentFrequency(array &$samples)
    {
        if ($this->minDF > 0) {
            $beyondMinimum = $this->getBeyondMinimumIndexes(count($samples));
            foreach ($samples as &$sample) {
                $this->resetBeyondMinimum($sample, $beyondMinimum);
            }
        }
    }

    /**
     * @param array $sample
     * @param array $beyondMinimum
     */
    private function resetBeyondMinimum(array &$sample, array $beyondMinimum)
    {
        foreach ($beyondMinimum as $index) {
            $sample[$index] = 0;
        }
    }

    /**
     * @param int $samplesCount
     *
     * @return array
     */
    private function getBeyondMinimumIndexes(int $samplesCount)
    {
        $indexes = [];
        foreach ($this->frequencies as $token => $frequency) {
            if (($frequency / $samplesCount) < $this->minDF) {
                $indexes[] = $this->getTokenIndex($token);
            }
        }

        return $indexes;
    }
}


1			<?php
2
3			declare (strict_types = 1);
4
5			namespace Phpml\FeatureExtraction;
6
7			use Phpml\Tokenization\Tokenizer;
8			use Phpml\Transformer;
9
10			class TokenCountVectorizer implements Transformer
11			{
12			/**
13			* @var Tokenizer
14			*/
15			private $tokenizer;
16
17			/**
18			* @var float
19			*/
20			private $minDF;
21
22			/**
23			* @var array
24			*/
25			private $vocabulary;
26
27			/**
28			* @var array
29			*/
30			private $frequencies;
31
32			/**
33			* @param Tokenizer $tokenizer
34			* @param float $minDF
35			*/
36			public function __construct(Tokenizer $tokenizer, float $minDF = 0)
37			{
38			$this->tokenizer = $tokenizer;
39			$this->minDF = $minDF;
			0 ignored issues – show Documentation Bug introduced 2016-05-03 21:31 UTC by Report Bug Copy Issue Report It seems like `$minDF` can also be of type `integer`. However, the property `$minDF` is declared as type `double`. Maybe add an additional type check? Our type inference engine has found a suspicous assignment of a value to a property. This check raises an issue when a value that can be of a mixed type is assigned to a property that is type hinted more strictly. For example, imagine you have a variable `$accountId` that can either hold an Id object or false (if there is no account id yet). Your code now assigns that value to the `id` property of an instance of the `Account` class. This class holds a proper account, so the id value must no longer be false. Either this assignment is in error or a type check should be added for that assignment. class Id { public $id; public function __construct($id) { $this->id = $id; } } class Account { /** @var Id $id */ public $id; } $account_id = false; if (starsAreRight()) { $account_id = new Id(42); } $account = new Account(); if ($account instanceof Id) { $account->id = $account_id; } Loading history...
40			$this->vocabulary = [];
41			$this->frequencies = [];
42			}
43
44			/**
45			* @param array $samples
46			*/
47			public function fit(array $samples)
48			{
49			$this->buildVocabulary($samples);
50			}
51
52			/**
53			* @param array $samples
54			*/
55			public function transform(array &$samples)
56			{
57			foreach ($samples as &$sample) {
58			$this->transformSample($sample);
59			}
60
61			$this->checkDocumentFrequency($samples);
62			}
63
64			/**
65			* @return array
66			*/
67			public function getVocabulary()
68			{
69			return array_flip($this->vocabulary);
70			}
71
72			/**
73			* @param array $samples
74			*/
75			private function buildVocabulary(array &$samples)
76			{
77			foreach ($samples as $index => $sample) {
78			$tokens = $this->tokenizer->tokenize($sample);
79			foreach ($tokens as $token) {
80			$this->addTokenToVocabulary($token);
81			}
82			}
83			}
84
85			/**
86			* @param string $sample
87			*/
88			private function transformSample(string &$sample)
89			{
90			$counts = [];
91			$tokens = $this->tokenizer->tokenize($sample);
92
93			foreach ($tokens as $token) {
94			$index = $this->getTokenIndex($token);
95			if (false !== $index) {
96			$this->updateFrequency($token);
97			if (!isset($counts[$index])) {
98			$counts[$index] = 0;
99			}
100
101			++$counts[$index];
102			}
103			}
104
105			foreach ($this->vocabulary as $index) {
106			if (!isset($counts[$index])) {
107			$counts[$index] = 0;
108			}
109			}
110
111			$sample = $counts;
112			}
113
114			/**
115			* @param string $token
116			*
117			* @return int\|bool
118			*/
119			private function getTokenIndex(string $token)
120			{
121			return isset($this->vocabulary[$token]) ? $this->vocabulary[$token] : false;
122			}
123
124			/**
125			* @param string $token
126			*/
127			private function addTokenToVocabulary(string $token)
128			{
129			if (!isset($this->vocabulary[$token])) {
130			$this->vocabulary[$token] = count($this->vocabulary);
131			}
132			}
133
134			/**
135			* @param string $token
136			*/
137			private function updateFrequency(string $token)
138			{
139			if (!isset($this->frequencies[$token])) {
140			$this->frequencies[$token] = 0;
141			}
142
143			++$this->frequencies[$token];
144			}
145
146			/**
147			* @param array $samples
148			*
149			* @return array
150			*/
151			private function checkDocumentFrequency(array &$samples)
152			{
153			if ($this->minDF > 0) {
154			$beyondMinimum = $this->getBeyondMinimumIndexes(count($samples));
155			foreach ($samples as &$sample) {
156			$this->resetBeyondMinimum($sample, $beyondMinimum);
157			}
158			}
159			}
160
161			/**
162			* @param array $sample
163			* @param array $beyondMinimum
164			*/
165			private function resetBeyondMinimum(array &$sample, array $beyondMinimum)
166			{
167			foreach ($beyondMinimum as $index) {
168			$sample[$index] = 0;
169			}
170			}
171
172			/**
173			* @param int $samplesCount
174			*
175			* @return array
176			*/
177			private function getBeyondMinimumIndexes(int $samplesCount)
178			{
179			$indexes = [];
180			foreach ($this->frequencies as $token => $frequency) {
181			if (($frequency / $samplesCount) < $this->minDF) {
182			$indexes[] = $this->getTokenIndex($token);
183			}
184			}
185
186			return $indexes;
187			}
188			}
189

php-ai / php-ml

Push — develop ( 7f4a0b...601ff8 )

TokenCountVectorizer::fit() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like