DecisionTree::preprocess() - Code Metrics - Inspection of "DecisionTree and Fuzzy C Means classifiers (#35)" - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 95fc13...87396e )

by Arkadiusz

created 2017-01-31 19:27 UTC

DecisionTree::preprocess() B

↳ Parent: DecisionTree

Complexity

Conditions	5
Paths	3

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	3
nop	1

<?php

declare(strict_types=1);

namespace Phpml\Classification;

use Phpml\Helper\Predictable;
use Phpml\Helper\Trainable;
use Phpml\Math\Statistic\Mean;
use Phpml\Classification\DecisionTree\DecisionTreeLeaf;

class DecisionTree implements Classifier
{
    use Trainable, Predictable;

    const CONTINUOS = 1;
    const NOMINAL = 2;

    /**
     * @var array
     */
    private $samples = array();

    /**
     * @var array
     */
    private $columnTypes;
    /**
     * @var array
     */
    private $labels = array();
    /**
     * @var int
     */
    private $featureCount = 0;
    /**
     * @var DecisionTreeLeaf
     */
    private $tree = null;

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

    /**
     * @var int
     */
    public $actualDepth = 0;

    /**
     * @param int $maxDepth
     */
    public function __construct($maxDepth = 10)
    {
        $this->maxDepth = $maxDepth;
    }
    /**
     * @param array $samples
     * @param array $targets
     */
    public function train(array $samples, array $targets)
    {
        $this->featureCount = count($samples[0]);
        $this->columnTypes = $this->getColumnTypes($samples);
        $this->samples = $samples;
        $this->targets = $targets;
        $this->labels = array_keys(array_count_values($targets));
        $this->tree = $this->getSplitLeaf(range(0, count($samples) - 1));
    }

    protected function getColumnTypes(array $samples)
    {
        $types = [];
        for ($i=0; $i<$this->featureCount; $i++) {
            $values = array_column($samples, $i);
            $isCategorical = $this->isCategoricalColumn($values);
            $types[] = $isCategorical ? self::NOMINAL : self::CONTINUOS;
        }
        return $types;
    }

    /**
     * @param null|array $records
     * @return DecisionTreeLeaf
     */
    protected function getSplitLeaf($records, $depth = 0)
    {
        $split = $this->getBestSplit($records);

        $split->level = $depth;
        if ($this->actualDepth < $depth) {
            $this->actualDepth = $depth;
        }
        $leftRecords = [];
        $rightRecords= [];
        $remainingTargets = [];
        $prevRecord = null;
        $allSame = true;
        foreach ($records as $recordNo) {
$collection = json_decode($data, true);
if ( ! is_array($collection)) {
    throw new \RuntimeException('$collection must be an array.');
}

foreach ($collection as $item) { /** ... */ }
            $record = $this->samples[$recordNo];
            if ($prevRecord && $prevRecord != $record) {
                $allSame = false;
            }
            $prevRecord = $record;
            if ($split->evaluate($record)) {
                $leftRecords[] = $recordNo;
            } else {
                $rightRecords[]= $recordNo;
            }
            $target = $this->targets[$recordNo];
            if (! in_array($target, $remainingTargets)) {
                $remainingTargets[] = $target;
            }
        }

        if (count($remainingTargets) == 1 || $allSame || $depth >= $this->maxDepth) {
            $split->isTerminal = 1;
$answer = 42;

$correct = false;

$correct = (bool) $answer;
            $classes = array_count_values($remainingTargets);
            arsort($classes);
            $split->classValue = key($classes);
        } else {
            if ($leftRecords) {

                $split->leftLeaf = $this->getSplitLeaf($leftRecords, $depth + 1);
            }
            if ($rightRecords) {

                $split->rightLeaf= $this->getSplitLeaf($rightRecords, $depth + 1);
            }
        }
        return $split;
    }

    /**
     * @param array $records
     * @return DecisionTreeLeaf[]
     */
    protected function getBestSplit($records)
    {
        $targets = array_intersect_key($this->targets, array_flip($records));
        $samples = array_intersect_key($this->samples, array_flip($records));
        $samples = array_combine($records, $this->preprocess($samples));
        $bestGiniVal = 1;
        $bestSplit = null;
        for ($i=0; $i<$this->featureCount; $i++) {
            $colValues = [];
            $baseValue = null;
            foreach ($samples as $index => $row) {
                $colValues[$index] = $row[$i];
                if ($baseValue === null) {
                    $baseValue = $row[$i];
                }
            }
            $gini = $this->getGiniIndex($baseValue, $colValues, $targets);
            if ($bestSplit == null || $bestGiniVal > $gini) {
                $split = new DecisionTreeLeaf();
                $split->value = $baseValue;
                $split->giniIndex = $gini;
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;
}
                $split->columnIndex = $i;
                $split->records = $records;
                $bestSplit = $split;
                $bestGiniVal = $gini;
            }
        }
        return $bestSplit;
    }

    /**
     * @param string $baseValue
     * @param array $colValues
     * @param array $targets
     */
    public function getGiniIndex($baseValue, $colValues, $targets)
    {
        $countMatrix = [];
        foreach ($this->labels as $label) {
            $countMatrix[$label] = [0, 0];
        }
        foreach ($colValues as $index => $value) {
            $label = $targets[$index];
            $rowIndex = $value == $baseValue ? 0 : 1;
            $countMatrix[$label][$rowIndex]++;
        }
        $giniParts = [0, 0];
        for ($i=0; $i<=1; $i++) {
            $part = 0;
            $sum = array_sum(array_column($countMatrix, $i));
            if ($sum > 0) {
                foreach ($this->labels as $label) {
                    $part += pow($countMatrix[$label][$i] / floatval($sum), 2);
                }
            }
            $giniParts[$i] = (1 - $part) * $sum;
        }
        return array_sum($giniParts) / count($colValues);
    }

    /**
     * @param array $samples
     * @return array
     */
    protected function preprocess(array $samples)
    {
        // Detect and convert continuous data column values into
        // discrete values by using the median as a threshold value
        $columns = array();
        for ($i=0; $i<$this->featureCount; $i++) {
            $values = array_column($samples, $i);
            if ($this->columnTypes[$i] == self::CONTINUOS) {
                $median = Mean::median($values);
                foreach ($values as &$value) {
                    if ($value <= $median) {
                        $value = "<= $median";
                    } else {
                        $value = "> $median";
                    }
                }
            }
            $columns[] = $values;
        }
        // Below method is a strange yet very simple & efficient method
        // to get the transpose of a 2D array
        return array_map(null, ...$columns);
    }

    /**
     * @param array $columnValues
     * @return bool
     */
    protected function isCategoricalColumn(array $columnValues)
    {
        $count = count($columnValues);
        // There are two main indicators that *may* show whether a
        // column is composed of discrete set of values:
        // 1- Column may contain string values
        // 2- Number of unique values in the column is only a small fraction of
        //	  all values in that column (Lower than or equal to %20 of all values)
        $numericValues = array_filter($columnValues, 'is_numeric');
        if (count($numericValues) != $count) {
            return true;
        }
        $distinctValues = array_count_values($columnValues);
        if (count($distinctValues) <= $count / 5) {
            return true;
        }
        return false;
    }

    /**
     * @return string
     */
    public function getHtml()
    {
        return $this->tree->__toString();
    }

    /**
     * @param array $sample
     * @return mixed
     */
    protected function predictSample(array $sample)
    {
        $node = $this->tree;
        do {
            if ($node->isTerminal) {
                break;
            }
            if ($node->evaluate($sample)) {
                $node = $node->leftLeaf;
            } else {
                $node = $node->rightLeaf;
            }
        } while ($node);
        return $node->classValue;
    }
}


1			<?php
2
3			declare(strict_types=1);
4
5			namespace Phpml\Classification;
6
7			use Phpml\Helper\Predictable;
8			use Phpml\Helper\Trainable;
9			use Phpml\Math\Statistic\Mean;
10			use Phpml\Classification\DecisionTree\DecisionTreeLeaf;
11
12			class DecisionTree implements Classifier
13			{
14			use Trainable, Predictable;
15
16			const CONTINUOS = 1;
17			const NOMINAL = 2;
18
19			/**
20			* @var array
21			*/
22			private $samples = array();
23
24			/**
25			* @var array
26			*/
27			private $columnTypes;
28			/**
29			* @var array
30			*/
31			private $labels = array();
32			/**
33			* @var int
34			*/
35			private $featureCount = 0;
36			/**
37			* @var DecisionTreeLeaf
38			*/
39			private $tree = null;
40
41			/**
42			* @var int
43			*/
44			private $maxDepth;
45
46			/**
47			* @var int
48			*/
49			public $actualDepth = 0;
50
51			/**
52			* @param int $maxDepth
53			*/
54			public function __construct($maxDepth = 10)
55			{
56			$this->maxDepth = $maxDepth;
57			}
58			/**
59			* @param array $samples
60			* @param array $targets
61			*/
62			public function train(array $samples, array $targets)
63			{
64			$this->featureCount = count($samples[0]);
65			$this->columnTypes = $this->getColumnTypes($samples);
66			$this->samples = $samples;
67			$this->targets = $targets;
68			$this->labels = array_keys(array_count_values($targets));
69			$this->tree = $this->getSplitLeaf(range(0, count($samples) - 1));
70			}
71
72			protected function getColumnTypes(array $samples)
73			{
74			$types = [];
75			for ($i=0; $i<$this->featureCount; $i++) {
76			$values = array_column($samples, $i);
77			$isCategorical = $this->isCategoricalColumn($values);
78			$types[] = $isCategorical ? self::NOMINAL : self::CONTINUOS;
79			}
80			return $types;
81			}
82
83			/**
84			* @param null\|array $records
85			* @return DecisionTreeLeaf
86			*/
87			protected function getSplitLeaf($records, $depth = 0)
88			{
89			$split = $this->getBestSplit($records);
			0 ignored issues – show Bug introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report It seems like `$records` defined by parameter `$records` on line 87 can also be of type `null`; however, `Phpml\Classification\DecisionTree::getBestSplit()` does only seem to accept `array`, maybe add an additional type check? This check looks at variables that have been passed in as parameters and are passed out again to other methods. If the outgoing method call has stricter type requirements than the method itself, an issue is raised. An additional type check may prevent trouble. Loading history...
90			$split->level = $depth;
91			if ($this->actualDepth < $depth) {
92			$this->actualDepth = $depth;
93			}
94			$leftRecords = [];
95			$rightRecords= [];
96			$remainingTargets = [];
97			$prevRecord = null;
98			$allSame = true;
99			foreach ($records as $recordNo) {
			0 ignored issues – show Bug introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report The expression `$records` of type `null\|array` is not guaranteed to be traversable. How about adding an additional type check? There are different options of fixing this problem. If you want to be on the safe side, you can add an additional type-check: $collection = json_decode($data, true); if ( ! is_array($collection)) { throw new \RuntimeException('$collection must be an array.'); } foreach ($collection as $item) { /** ... / } If you are sure that the expression is traversable, you might want to add a doc comment cast* to improve IDE auto-completion and static analysis: /** @var array $collection / $collection = json_decode($data, true); foreach ($collection as $item) { /* .. / } Mark the issue as a false-positive*: Just hover the remove button, in the top-right corner of this issue for more options. Loading history...
100			$record = $this->samples[$recordNo];
101			if ($prevRecord && $prevRecord != $record) {
102			$allSame = false;
103			}
104			$prevRecord = $record;
105			if ($split->evaluate($record)) {
106			$leftRecords[] = $recordNo;
107			} else {
108			$rightRecords[]= $recordNo;
109			}
110			$target = $this->targets[$recordNo];
111			if (! in_array($target, $remainingTargets)) {
112			$remainingTargets[] = $target;
113			}
114			}
115
116			if (count($remainingTargets) == 1 \|\| $allSame \|\| $depth >= $this->maxDepth) {
117			$split->isTerminal = 1;
			0 ignored issues – show Documentation Bug introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report The property `$isTerminal` was declared of type `boolean`, but `1` is of type `integer`. Maybe add a type cast? This check looks for assignments to scalar types that may be of the wrong type. To ensure the code behaves as expected, it may be a good idea to add an explicit type cast. $answer = 42; $correct = false; $correct = (bool) $answer; Loading history...
118			$classes = array_count_values($remainingTargets);
119			arsort($classes);
120			$split->classValue = key($classes);
121			} else {
122			if ($leftRecords) {
			0 ignored issues – show Bug Best Practice introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report The expression `$leftRecords` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
123			$split->leftLeaf = $this->getSplitLeaf($leftRecords, $depth + 1);
124			}
125			if ($rightRecords) {
			0 ignored issues – show Bug Best Practice introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report The expression `$rightRecords` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
126			$split->rightLeaf= $this->getSplitLeaf($rightRecords, $depth + 1);
127			}
128			}
129			return $split;
130			}
131
132			/**
133			* @param array $records
134			* @return DecisionTreeLeaf[]
135			*/
136			protected function getBestSplit($records)
137			{
138			$targets = array_intersect_key($this->targets, array_flip($records));
139			$samples = array_intersect_key($this->samples, array_flip($records));
140			$samples = array_combine($records, $this->preprocess($samples));
141			$bestGiniVal = 1;
142			$bestSplit = null;
143			for ($i=0; $i<$this->featureCount; $i++) {
144			$colValues = [];
145			$baseValue = null;
146			foreach ($samples as $index => $row) {
147			$colValues[$index] = $row[$i];
148			if ($baseValue === null) {
149			$baseValue = $row[$i];
150			}
151			}
152			$gini = $this->getGiniIndex($baseValue, $colValues, $targets);
153			if ($bestSplit == null \|\| $bestGiniVal > $gini) {
154			$split = new DecisionTreeLeaf();
155			$split->value = $baseValue;
156			$split->giniIndex = $gini;
			0 ignored issues – show Documentation Bug introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report It seems like `$gini` can also be of type `integer`. However, the property `$giniIndex` is declared as type `double`. Maybe add an additional type check? Our type inference engine has found a suspicous assignment of a value to a property. This check raises an issue when a value that can be of a mixed type is assigned to a property that is type hinted more strictly. For example, imagine you have a variable `$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...
157			$split->columnIndex = $i;
158			$split->records = $records;
159			$bestSplit = $split;
160			$bestGiniVal = $gini;
161			}
162			}
163			return $bestSplit;
164			}
165
166			/**
167			* @param string $baseValue
168			* @param array $colValues
169			* @param array $targets
170			*/
171			public function getGiniIndex($baseValue, $colValues, $targets)
172			{
173			$countMatrix = [];
174			foreach ($this->labels as $label) {
175			$countMatrix[$label] = [0, 0];
176			}
177			foreach ($colValues as $index => $value) {
178			$label = $targets[$index];
179			$rowIndex = $value == $baseValue ? 0 : 1;
180			$countMatrix[$label][$rowIndex]++;
181			}
182			$giniParts = [0, 0];
183			for ($i=0; $i<=1; $i++) {
184			$part = 0;
185			$sum = array_sum(array_column($countMatrix, $i));
186			if ($sum > 0) {
187			foreach ($this->labels as $label) {
188			$part += pow($countMatrix[$label][$i] / floatval($sum), 2);
189			}
190			}
191			$giniParts[$i] = (1 - $part) * $sum;
192			}
193			return array_sum($giniParts) / count($colValues);
194			}
195
196			/**
197			* @param array $samples
198			* @return array
199			*/
200			protected function preprocess(array $samples)
201			{
202			// Detect and convert continuous data column values into
203			// discrete values by using the median as a threshold value
204			$columns = array();
205			for ($i=0; $i<$this->featureCount; $i++) {
206			$values = array_column($samples, $i);
207			if ($this->columnTypes[$i] == self::CONTINUOS) {
208			$median = Mean::median($values);
209			foreach ($values as &$value) {
210			if ($value <= $median) {
211			$value = "<= $median";
212			} else {
213			$value = "> $median";
214			}
215			}
216			}
217			$columns[] = $values;
218			}
219			// Below method is a strange yet very simple & efficient method
220			// to get the transpose of a 2D array
221			return array_map(null, ...$columns);
222			}
223
224			/**
225			* @param array $columnValues
226			* @return bool
227			*/
228			protected function isCategoricalColumn(array $columnValues)
229			{
230			$count = count($columnValues);
231			// There are two main indicators that may show whether a
232			// column is composed of discrete set of values:
233			// 1- Column may contain string values
234			// 2- Number of unique values in the column is only a small fraction of
235			// all values in that column (Lower than or equal to %20 of all values)
236			$numericValues = array_filter($columnValues, 'is_numeric');
237			if (count($numericValues) != $count) {
238			return true;
239			}
240			$distinctValues = array_count_values($columnValues);
241			if (count($distinctValues) <= $count / 5) {
242			return true;
243			}
244			return false;
245			}
246
247			/**
248			* @return string
249			*/
250			public function getHtml()
251			{
252			return $this->tree->__toString();
253			}
254
255			/**
256			* @param array $sample
257			* @return mixed
258			*/
259			protected function predictSample(array $sample)
260			{
261			$node = $this->tree;
262			do {
263			if ($node->isTerminal) {
264			break;
265			}
266			if ($node->evaluate($sample)) {
267			$node = $node->leftLeaf;
268			} else {
269			$node = $node->rightLeaf;
270			}
271			} while ($node);
272			return $node->classValue;
273			}
274			}
275

php-ai / php-ml

Push — master ( 95fc13...87396e )

DecisionTree::preprocess() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like