TokenCountVectorizer::transformSample() - Code Metrics - Inspection of "change token count vectorizer to return full token..." - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — develop ( 23eff0...2f5171 )

by Arkadiusz

created 2016-06-14 08:31 UTC

TokenCountVectorizer::transformSample() B

↳ Parent: TokenCountVectorizer

Complexity

Conditions	5
Paths	9

Size

Total Lines	23
Code Lines	13

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	23
rs	8.5906
c	0
b	0
f	0
cc	5
eloc	13
nc	9
nop	1

<?php

declare (strict_types = 1);

namespace Phpml\FeatureExtraction;

use Phpml\Tokenization\Tokenizer;

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

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

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

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

    /**
     * @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
     *
     * @return array
     */
    public function transform(array $samples): array
    {
        $this->buildVocabulary($samples);

        foreach ($samples as $index => $sample) {
            $samples[$index] = $this->transformSample($index);
        }

        $samples = $this->checkDocumentFrequency($samples);

        return $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);
            }
            $this->tokens[$index] = $tokens;
        }
    }

    /**
     * @param int $index
     *
     * @return array
     */
    private function transformSample(int $index)
    {
        $counts = [];
        $tokens = $this->tokens[$index];

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

            ++$counts[$index];
        }

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

        return $counts;
    }

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

    /**
     * @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 $index => $sample) {
                $samples[$index] = $this->resetBeyondMinimum($sample, $beyondMinimum);
            }
        }

        return $samples;
    }

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

        return $sample;
    }

    /**
     * @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
9			class TokenCountVectorizer implements Vectorizer
10			{
11			/**
12			* @var Tokenizer
13			*/
14			private $tokenizer;
15
16			/**
17			* @var float
18			*/
19			private $minDF;
20
21			/**
22			* @var array
23			*/
24			private $vocabulary;
25
26			/**
27			* @var array
28			*/
29			private $tokens;
30
31			/**
32			* @var array
33			*/
34			private $frequencies;
35
36			/**
37			* @param Tokenizer $tokenizer
38			* @param float $minDF
39			*/
40			public function __construct(Tokenizer $tokenizer, float $minDF = 0)
41			{
42			$this->tokenizer = $tokenizer;
43			$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...
44			$this->vocabulary = [];
45			$this->frequencies = [];
46			}
47
48			/**
49			* @param array $samples
50			*
51			* @return array
52			*/
53			public function transform(array $samples): array
54			{
55			$this->buildVocabulary($samples);
56
57			foreach ($samples as $index => $sample) {
58			$samples[$index] = $this->transformSample($index);
59			}
60
61			$samples = $this->checkDocumentFrequency($samples);
62
63			return $samples;
64			}
65
66			/**
67			* @return array
68			*/
69			public function getVocabulary()
70			{
71			return array_flip($this->vocabulary);
72			}
73
74			/**
75			* @param array $samples
76			*/
77			private function buildVocabulary(array &$samples)
78			{
79			foreach ($samples as $index => $sample) {
80			$tokens = $this->tokenizer->tokenize($sample);
81			foreach ($tokens as $token) {
82			$this->addTokenToVocabulary($token);
83			}
84			$this->tokens[$index] = $tokens;
85			}
86			}
87
88			/**
89			* @param int $index
90			*
91			* @return array
92			*/
93			private function transformSample(int $index)
94			{
95			$counts = [];
96			$tokens = $this->tokens[$index];
97
98			foreach ($tokens as $token) {
99			$index = $this->getTokenIndex($token);
100			$this->updateFrequency($token);
101			if (!isset($counts[$index])) {
102			$counts[$index] = 0;
103			}
104
105			++$counts[$index];
106			}
107
108			foreach ($this->vocabulary as $index) {
109			if (!isset($counts[$index])) {
110			$counts[$index] = 0;
111			}
112			}
113
114			return $counts;
115			}
116
117			/**
118			* @param string $token
119			*
120			* @return int
121			*/
122			private function getTokenIndex(string $token): int
123			{
124			return $this->vocabulary[$token];
125			}
126
127			/**
128			* @param string $token
129			*/
130			private function addTokenToVocabulary(string $token)
131			{
132			if (!isset($this->vocabulary[$token])) {
133			$this->vocabulary[$token] = count($this->vocabulary);
134			}
135			}
136
137			/**
138			* @param string $token
139			*/
140			private function updateFrequency(string $token)
141			{
142			if (!isset($this->frequencies[$token])) {
143			$this->frequencies[$token] = 0;
144			}
145
146			++$this->frequencies[$token];
147			}
148
149			/**
150			* @param array $samples
151			*
152			* @return array
153			*/
154			private function checkDocumentFrequency(array $samples)
155			{
156			if ($this->minDF > 0) {
157			$beyondMinimum = $this->getBeyondMinimumIndexes(count($samples));
158			foreach ($samples as $index => $sample) {
159			$samples[$index] = $this->resetBeyondMinimum($sample, $beyondMinimum);
160			}
161			}
162
163			return $samples;
164			}
165
166			/**
167			* @param array $sample
168			* @param array $beyondMinimum
169			*
170			* @return array
171			*/
172			private function resetBeyondMinimum(array $sample, array $beyondMinimum)
173			{
174			foreach ($beyondMinimum as $index) {
175			$sample[$index] = 0;
176			}
177
178			return $sample;
179			}
180
181			/**
182			* @param int $samplesCount
183			*
184			* @return array
185			*/
186			private function getBeyondMinimumIndexes(int $samplesCount)
187			{
188			$indexes = [];
189			foreach ($this->frequencies as $token => $frequency) {
190			if (($frequency / $samplesCount) < $this->minDF) {
191			$indexes[] = $this->getTokenIndex($token);
192			}
193			}
194
195			return $indexes;
196			}
197			}
198

php-ai / php-ml

Push — develop ( 23eff0...2f5171 )

TokenCountVectorizer::transformSample() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like