TokenCountVectorizer::checkDocumentFrequency() - Code Metrics - Inspection of "feature extractions tools - TokenCountVectorizez" - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — develop ( 00178c...c05ce8 )

by Arkadiusz

created 2016-05-03 21:28 UTC

TokenCountVectorizer::checkDocumentFrequency() A

↳ Parent: TokenCountVectorizer

Complexity

Conditions	3
Paths	2

Size

Total Lines	11
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Metric	Value
dl	0
loc	11
rs	9.4285
cc	3
eloc	6
nc	2
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 $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 $samples): array
    {
        foreach ($samples as $index => $sample) {
            $samples[$index] = $this->transformSample($sample);
        }

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

        return $samples;
    }

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

    /**
     * @param string $sample
     *
     * @return array
     */
    private function transformSample(string $sample)
    {
        $counts = [];
        $tokens = $this->tokenizer->tokenize($sample);
        foreach ($tokens as $token) {
            $index = $this->getTokenIndex($token);
            $this->updateFrequency($token);
            if (!isset($counts[$index])) {
                $counts[$index] = 0;
            }

            ++$counts[$index];
        }

        return $counts;
    }

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

        return $this->vocabulary[$token];
    }

    /**
     * @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] = $this->unsetBeyondMinimum($sample, $beyondMinimum);
            }
        }

        return $samples;
    }

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

        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 $frequencies;
30
31			/**
32			* @param Tokenizer $tokenizer
33			* @param float $minDF
34			*/
35			public function __construct(Tokenizer $tokenizer, float $minDF = 0)
36			{
37			$this->tokenizer = $tokenizer;
38			$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...
39			$this->vocabulary = [];
40			$this->frequencies = [];
41			}
42
43			/**
44			* @param array $samples
45			*
46			* @return array
47			*/
48			public function transform(array $samples): array
49			{
50			foreach ($samples as $index => $sample) {
51			$samples[$index] = $this->transformSample($sample);
52			}
53
54			$samples = $this->checkDocumentFrequency($samples);
55
56			return $samples;
57			}
58
59			/**
60			* @return array
61			*/
62			public function getVocabulary()
63			{
64			return array_flip($this->vocabulary);
65			}
66
67			/**
68			* @param string $sample
69			*
70			* @return array
71			*/
72			private function transformSample(string $sample)
73			{
74			$counts = [];
75			$tokens = $this->tokenizer->tokenize($sample);
76			foreach ($tokens as $token) {
77			$index = $this->getTokenIndex($token);
78			$this->updateFrequency($token);
79			if (!isset($counts[$index])) {
80			$counts[$index] = 0;
81			}
82
83			++$counts[$index];
84			}
85
86			return $counts;
87			}
88
89			/**
90			* @param string $token
91			*
92			* @return mixed
93			*/
94			private function getTokenIndex(string $token)
95			{
96			if (!isset($this->vocabulary[$token])) {
97			$this->vocabulary[$token] = count($this->vocabulary);
98			}
99
100			return $this->vocabulary[$token];
101			}
102
103			/**
104			* @param string $token
105			*/
106			private function updateFrequency(string $token)
107			{
108			if (!isset($this->frequencies[$token])) {
109			$this->frequencies[$token] = 0;
110			}
111
112			++$this->frequencies[$token];
113			}
114
115			/**
116			* @param array $samples
117			*
118			* @return array
119			*/
120			private function checkDocumentFrequency(array $samples)
121			{
122			if ($this->minDF > 0) {
123			$beyondMinimum = $this->getBeyondMinimumIndexes(count($samples));
124			foreach ($samples as $index => $sample) {
125			$samples[$index] = $this->unsetBeyondMinimum($sample, $beyondMinimum);
126			}
127			}
128
129			return $samples;
130			}
131
132			/**
133			* @param array $sample
134			* @param array $beyondMinimum
135			*
136			* @return array
137			*/
138			private function unsetBeyondMinimum(array $sample, array $beyondMinimum)
139			{
140			foreach ($beyondMinimum as $index) {
141			unset($sample[$index]);
142			}
143
144			return $sample;
145			}
146
147			/**
148			* @param int $samplesCount
149			*
150			* @return array
151			*/
152			private function getBeyondMinimumIndexes(int $samplesCount)
153			{
154			$indexes = [];
155			foreach ($this->frequencies as $token => $frequency) {
156			if (($frequency / $samplesCount) < $this->minDF) {
157			$indexes[] = $this->getTokenIndex($token);
158			}
159			}
160
161			return $indexes;
162			}
163			}
164

php-ai / php-ml

Push — develop ( 00178c...c05ce8 )

TokenCountVectorizer::checkDocumentFrequency() A

Complexity

Size

Duplication

Duplication Side-by-Side

Filter issues like