DecisionTree::predictSample() - Code Metrics - Inspection of "Ensemble Classifiers : Bagging and RandomForest" - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#36)

unknown

created 2017-02-04 14:57 UTC

DecisionTree::predictSample() B

↳ Parent: DecisionTree

Complexity

Conditions	5
Paths	6

Size

Total Lines	16
Code Lines	11

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	16
rs	8.8571
c	0
b	0
f	0
cc	5
eloc	11
nc	6
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 = [];

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

    /**
     * @var array
     */
    private $labels = [];

    /**
     * @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)
    {
        $this->samples = array_merge($this->samples, $samples);
        $this->targets = array_merge($this->targets, $targets);

        $this->featureCount = count($this->samples[0]);
        $this->columnTypes = $this->getColumnTypes($this->samples);
        $this->labels = array_keys(array_count_values($this->targets));
        $this->tree = $this->getSplitLeaf(range(0, count($this->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++) {
            $colValues = [];
            foreach ($samples as $index => $row) {
                $colValues[$index] = $row[$i];
            }
            $counts = array_count_values($colValues);
            arsort($counts);
            $baseValue = key($counts);
            $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
        $columns = [];
        for ($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 ? $node->classValue : $this->labels[0];
    }
}


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 = [];
23
24			/**
25			* @var array
26			*/
27			private $columnTypes;
28
29			/**
30			* @var array
31			*/
32			private $labels = [];
33
34			/**
35			* @var int
36			*/
37			private $featureCount = 0;
38
39			/**
40			* @var DecisionTreeLeaf
41			*/
42			private $tree = null;
43
44			/**
45			* @var int
46			*/
47			private $maxDepth;
48
49			/**
50			* @var int
51			*/
52			public $actualDepth = 0;
53
54			/**
55			* @param int $maxDepth
56			*/
57			public function __construct($maxDepth = 10)
58			{
59			$this->maxDepth = $maxDepth;
60			}
61			/**
62			* @param array $samples
63			* @param array $targets
64			*/
65			public function train(array $samples, array $targets)
66			{
67			$this->samples = array_merge($this->samples, $samples);
68			$this->targets = array_merge($this->targets, $targets);
69
70			$this->featureCount = count($this->samples[0]);
71			$this->columnTypes = $this->getColumnTypes($this->samples);
72			$this->labels = array_keys(array_count_values($this->targets));
73			$this->tree = $this->getSplitLeaf(range(0, count($this->samples) - 1));
74			}
75
76			protected function getColumnTypes(array $samples)
77			{
78			$types = [];
79			for ($i=0; $i<$this->featureCount; $i++) {
80			$values = array_column($samples, $i);
81			$isCategorical = $this->isCategoricalColumn($values);
82			$types[] = $isCategorical ? self::NOMINAL : self::CONTINUOS;
83			}
84			return $types;
85			}
86
87			/**
88			* @param null\|array $records
89			* @return DecisionTreeLeaf
90			*/
91			protected function getSplitLeaf($records, $depth = 0)
92			{
93			$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 91 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...
94			$split->level = $depth;
95			if ($this->actualDepth < $depth) {
96			$this->actualDepth = $depth;
97			}
98			$leftRecords = [];
99			$rightRecords= [];
100			$remainingTargets = [];
101			$prevRecord = null;
102			$allSame = true;
103			foreach ($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...
104			$record = $this->samples[$recordNo];
105			if ($prevRecord && $prevRecord != $record) {
106			$allSame = false;
107			}
108			$prevRecord = $record;
109			if ($split->evaluate($record)) {
110			$leftRecords[] = $recordNo;
111			} else {
112			$rightRecords[]= $recordNo;
113			}
114			$target = $this->targets[$recordNo];
115			if (! in_array($target, $remainingTargets)) {
116			$remainingTargets[] = $target;
117			}
118			}
119
120			if (count($remainingTargets) == 1 \|\| $allSame \|\| $depth >= $this->maxDepth) {
121			$split->isTerminal = 1;
			0 ignored issues – show Documentation Bug introduced 2017-01-29 10:19 UTC by Report Bug Copy Issue Report The property `$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...
122			$classes = array_count_values($remainingTargets);
123			arsort($classes);
124			$split->classValue = key($classes);
125			} else {
126			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...
127			$split->leftLeaf = $this->getSplitLeaf($leftRecords, $depth + 1);
128			}
129			if ($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...
130			$split->rightLeaf= $this->getSplitLeaf($rightRecords, $depth + 1);
131			}
132			}
133			return $split;
134			}
135
136			/**
137			* @param array $records
138			* @return DecisionTreeLeaf[]
139			*/
140			protected function getBestSplit($records)
141			{
142			$targets = array_intersect_key($this->targets, array_flip($records));
143			$samples = array_intersect_key($this->samples, array_flip($records));
144			$samples = array_combine($records, $this->preprocess($samples));
145			$bestGiniVal = 1;
146			$bestSplit = null;
147			for ($i=0; $i<$this->featureCount; $i++) {
148			$colValues = [];
149			foreach ($samples as $index => $row) {
150			$colValues[$index] = $row[$i];
151			}
152			$counts = array_count_values($colValues);
153			arsort($counts);
154			$baseValue = key($counts);
155			$gini = $this->getGiniIndex($baseValue, $colValues, $targets);
156			if ($bestSplit == null \|\| $bestGiniVal > $gini) {
157			$split = new DecisionTreeLeaf();
158			$split->value = $baseValue;
159			$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...
160			$split->columnIndex = $i;
161			$split->records = $records;
162			$bestSplit = $split;
163			$bestGiniVal = $gini;
164			}
165			}
166			return $bestSplit;
167			}
168
169			/**
170			* @param string $baseValue
171			* @param array $colValues
172			* @param array $targets
173			*/
174			public function getGiniIndex($baseValue, $colValues, $targets)
175			{
176			$countMatrix = [];
177			foreach ($this->labels as $label) {
178			$countMatrix[$label] = [0, 0];
179			}
180			foreach ($colValues as $index => $value) {
181			$label = $targets[$index];
182			$rowIndex = $value == $baseValue ? 0 : 1;
183			$countMatrix[$label][$rowIndex]++;
184			}
185			$giniParts = [0, 0];
186			for ($i=0; $i<=1; $i++) {
187			$part = 0;
188			$sum = array_sum(array_column($countMatrix, $i));
189			if ($sum > 0) {
190			foreach ($this->labels as $label) {
191			$part += pow($countMatrix[$label][$i] / floatval($sum), 2);
192			}
193			}
194			$giniParts[$i] = (1 - $part) * $sum;
195			}
196			return array_sum($giniParts) / count($colValues);
197			}
198
199			/**
200			* @param array $samples
201			* @return array
202			*/
203			protected function preprocess(array $samples)
204			{
205			// Detect and convert continuous data column values into
206			// discrete values by using the median as a threshold value
207			$columns = [];
208			for ($i=0; $i<$this->featureCount; $i++) {
209			$values = array_column($samples, $i);
210			if ($this->columnTypes[$i] == self::CONTINUOS) {
211			$median = Mean::median($values);
212			foreach ($values as &$value) {
213			if ($value <= $median) {
214			$value = "<= $median";
215			} else {
216			$value = "> $median";
217			}
218			}
219			}
220			$columns[] = $values;
221			}
222			// Below method is a strange yet very simple & efficient method
223			// to get the transpose of a 2D array
224			return array_map(null, ...$columns);
225			}
226
227			/**
228			* @param array $columnValues
229			* @return bool
230			*/
231			protected function isCategoricalColumn(array $columnValues)
232			{
233			$count = count($columnValues);
234			// There are two main indicators that may show whether a
235			// column is composed of discrete set of values:
236			// 1- Column may contain string values
237			// 2- Number of unique values in the column is only a small fraction of
238			// all values in that column (Lower than or equal to %20 of all values)
239			$numericValues = array_filter($columnValues, 'is_numeric');
240			if (count($numericValues) != $count) {
241			return true;
242			}
243			$distinctValues = array_count_values($columnValues);
244			if (count($distinctValues) <= $count / 5) {
245			return true;
246			}
247			return false;
248			}
249
250			/**
251			* @return string
252			*/
253			public function getHtml()
254			{
255			return $this->tree->__toString();
256			}
257
258			/**
259			* @param array $sample
260			* @return mixed
261			*/
262			protected function predictSample(array $sample)
263			{
264			$node = $this->tree;
265			do {
266			if ($node->isTerminal) {
267			break;
268			}
269			if ($node->evaluate($sample)) {
270			$node = $node->leftLeaf;
271			} else {
272			$node = $node->rightLeaf;
273			}
274			} while ($node);
275
276			return $node ? $node->classValue : $this->labels[0];
277			}
278			}
279

php-ai / php-ml

Pull Request — master (#36)

DecisionTree::predictSample() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like