DecisionStump::calculateErrorRate() - Code Metrics - Inspection of "One-v-Rest Classification technique applied to lin..." - php-ai/php-ml - Measure and Improve Code Quality continuously with Scrutinizer

Test Failed

Pull Request — master (#54)

unknown

created 2017-03-03 19:11 UTC

DecisionStump::calculateErrorRate() C

↳ Parent: DecisionStump

Complexity

Conditions	8
Paths	36

Size

Total Lines	38
Code Lines	23

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	38
rs	5.3846
c	0
b	0
f	0
cc	8
eloc	23
nc	36
nop	3

<?php

declare(strict_types=1);

namespace Phpml\Classification\Linear;

use Phpml\Helper\Predictable;
use Phpml\Helper\Trainable;
use Phpml\Helper\OneVsRest;
use Phpml\Classification\WeightedClassifier;
use Phpml\Classification\DecisionTree;

class DecisionStump extends WeightedClassifier
{
    use Trainable, Predictable, OneVsRest;

    const AUTO_SELECT = -1;

    /**
     * @var int
     */
    protected $givenColumnIndex;

    /**
     * @var array
     */
    protected $binaryLabels;

    /**
     * Sample weights : If used the optimization on the decision value
     * will take these weights into account. If not given, all samples
     * will be weighed with the same value of 1
     *
     * @var array
     */
    protected $weights = null;

    /**
     * Lowest error rate obtained while training/optimizing the model
     *
     * @var float
     */
    protected $trainingErrorRate;

    /**
     * @var int
     */
    protected $column;

    /**
     * @var mixed
     */
    protected $value;

    /**
     * @var string
     */
    protected $operator;

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

    /**
     * @var int
     */
    protected $featureCount;

    /**
     * @var float
     */
    protected $numSplitCount = 100.0;

    /**
     * Distribution of samples in the leaves
     *
     * @var array
     */
    protected $prob;

    /**
     * A DecisionStump classifier is a one-level deep DecisionTree. It is generally
     * used with ensemble algorithms as in the weak classifier role. <br>
     *
     * If columnIndex is given, then the stump tries to produce a decision node
     * on this column, otherwise in cases given the value of -1, the stump itself
     * decides which column to take for the decision (Default DecisionTree behaviour)
     *
     * @param int $columnIndex
     */
    public function __construct(int $columnIndex = self::AUTO_SELECT)
    {
        $this->givenColumnIndex = $columnIndex;
    }

    /**
     * @param array $samples
     * @param array $targets
     */
    protected function trainBinary(array $samples, array $targets)
    {
        $this->samples = array_merge($this->samples, $samples);
        $this->targets = array_merge($this->targets, $targets);
        $this->binaryLabels = array_keys(array_count_values($this->targets));
        $this->featureCount = count($this->samples[0]);

        // If a column index is given, it should be among the existing columns
        if ($this->givenColumnIndex > count($this->samples[0]) - 1) {
            $this->givenColumnIndex = self::AUTO_SELECT;
        }

        // Check the size of the weights given.
        // If none given, then assign 1 as a weight to each sample
        if ($this->weights) {

            $numWeights = count($this->weights);
            if ($numWeights != count($this->samples)) {
                throw new \Exception("Number of sample weights does not match with number of samples");
            }
        } else {
            $this->weights = array_fill(0, count($this->samples), 1);
        }

        // Determine type of each column as either "continuous" or "nominal"
        $this->columnTypes = DecisionTree::getColumnTypes($this->samples);

        // Try to find the best split in the columns of the dataset
        // by calculating error rate for each split point in each column
        $columns = range(0, count($this->samples[0]) - 1);
        if ($this->givenColumnIndex != self::AUTO_SELECT) {
            $columns = [$this->givenColumnIndex];
        }

        $bestSplit = [
            'value' => 0, 'operator' => '',
            'prob' => [], 'column' => 0,
            'trainingErrorRate' => 1.0];
        foreach ($columns as $col) {
            if ($this->columnTypes[$col] == DecisionTree::CONTINUOS) {
                $split = $this->getBestNumericalSplit($col);
            } else {
                $split = $this->getBestNominalSplit($col);
            }

            if ($split['trainingErrorRate'] < $bestSplit['trainingErrorRate']) {
                $bestSplit = $split;
            }
        }

        // Assign determined best values to the stump
        foreach ($bestSplit as $name => $value) {
            $this->{$name} = $value;
        }
    }

    /**
     * While finding best split point for a numerical valued column,
     * DecisionStump looks for equally distanced values between minimum and maximum
     * values in the column. Given <i>$count</i> value determines how many split
     * points to be probed. The more split counts, the better performance but
     * worse processing time (Default value is 10.0)
     *
     * @param float $count
     */
    public function setNumericalSplitCount(float $count)
    {
        $this->numSplitCount = $count;
    }

    /**
     * Determines best split point for the given column
     *
     * @param int $col
     *
     * @return array
     */
    protected function getBestNumericalSplit(int $col)
    {
        $values = array_column($this->samples, $col);
        // Trying all possible points may be accomplished in two general ways:
        // 1- Try all values in the $samples array ($values)
        // 2- Artificially split the range of values into several parts and try them
        // We choose the second one because it is faster in larger datasets
        $minValue = min($values);
        $maxValue = max($values);
        $stepSize = ($maxValue - $minValue) / $this->numSplitCount;

        $split = null;

        foreach (['<=', '>'] as $operator) {
            // Before trying all possible split points, let's first try
            // the average value for the cut point
            $threshold = array_sum($values) / (float) count($values);
            list($errorRate, $prob) = $this->calculateErrorRate($threshold, $operator, $values);
            if ($split == null || $errorRate < $split['trainingErrorRate']) {

                $split = ['value' => $threshold, 'operator' => $operator,
                        'prob' => $prob, 'column' => $col,
                        'trainingErrorRate' => $errorRate];
            }

            // Try other possible points one by one
            for ($step = $minValue; $step <= $maxValue; $step+= $stepSize) {
                $threshold = (float)$step;
                list($errorRate, $prob) = $this->calculateErrorRate($threshold, $operator, $values);
                if ($errorRate < $split['trainingErrorRate']) {

                    $split = ['value' => $threshold, 'operator' => $operator,
                        'prob' => $prob, 'column' => $col,
                        'trainingErrorRate' => $errorRate];
                }
            }// for
        }

        return $split;
    }

    /**
     *
     * @param int $col
     *
     * @return array
     */
    protected function getBestNominalSplit(int $col)
    {
        $values = array_column($this->samples, $col);
        $valueCounts = array_count_values($values);
        $distinctVals= array_keys($valueCounts);

        $split = null;

        foreach (['=', '!='] as $operator) {
            foreach ($distinctVals as $val) {
                list($errorRate, $prob) = $this->calculateErrorRate($val, $operator, $values);

                if ($split == null || $split['trainingErrorRate'] < $errorRate) {

                    $split = ['value' => $val, 'operator' => $operator,
                        'prob' => $prob, 'column' => $col,
                        'trainingErrorRate' => $errorRate];
                }
            }// for
        }

        return $split;
    }


    /**
     *
     * @param type $leftValue
     * @param type $operator
     * @param type $rightValue
     *
     * @return boolean
     */
    protected function evaluate($leftValue, $operator, $rightValue)
    {
        switch ($operator) {
            case '>': return $leftValue > $rightValue;
switch ($expr) {
case "A":
    doSomething(); //right
    break;
case "B":

    doSomethingElse(); //wrong
    break;
            case '>=': return $leftValue >= $rightValue;
switch ($expr) {
case "A":
    doSomething(); //right
    break;
case "B":

    doSomethingElse(); //wrong
    break;
            case '<': return $leftValue < $rightValue;
switch ($expr) {
case "A":
    doSomething(); //right
    break;
case "B":

    doSomethingElse(); //wrong
    break;
            case '<=': return $leftValue <= $rightValue;
switch ($expr) {
case "A":
    doSomething(); //right
    break;
case "B":

    doSomethingElse(); //wrong
    break;
            case '=': return $leftValue === $rightValue;
switch ($expr) {
case "A":
    doSomething(); //right
    break;
case "B":

    doSomethingElse(); //wrong
    break;
            case '!=':
            case '<>': return $leftValue !== $rightValue;
switch ($expr) {
case "A":
    doSomething(); //right
    break;
case "B":

    doSomethingElse(); //wrong
    break;
        }

        return false;
    }

    /**
     * Calculates the ratio of wrong predictions based on the new threshold
     * value given as the parameter
     *
     * @param float $threshold
     * @param string $operator
     * @param array $values
     *
     * @return array
     */
    protected function calculateErrorRate(float $threshold, string $operator, array $values)
    {
        $wrong = 0.0;
        $prob = [];
        $leftLabel = $this->binaryLabels[0];
        $rightLabel= $this->binaryLabels[1];

        foreach ($values as $index => $value) {
            if ($this->evaluate($value, $operator, $threshold)) {
function acceptsInteger($int) { }

$x = '123'; // string "123"

// Instead of
acceptsInteger($x);

// we recommend to use
acceptsInteger((integer) $x);
                $predicted = $leftLabel;
            } else {
                $predicted = $rightLabel;
            }

            $target = $this->targets[$index];
            if (strval($predicted) != strval($this->targets[$index])) {
                $wrong += $this->weights[$index];
            }

            if (! isset($prob[$predicted][$target])) {
                $prob[$predicted][$target] = 0;
            }
            $prob[$predicted][$target]++;
        }

        // Calculate probabilities: Proportion of labels in each leaf
        $dist = array_combine($this->binaryLabels, array_fill(0, 2, 0.0));
        foreach ($prob as $leaf => $counts) {
            $leafTotal = (float)array_sum($prob[$leaf]);
            foreach ($counts as $label => $count) {
                if (strval($leaf) == strval($label)) {
                    $dist[$leaf] = $count / $leafTotal;
                }
            }
        }

        return [$wrong / (float) array_sum($this->weights), $dist];
    }

    /**
     * Returns the probability of the sample of belonging to the given label
     *
     * Probability of a sample is calculated as the proportion of the label
     * within the labels of the training samples in the decision node
     *
     * @param array $sample
     * @param mixed $label
     *
     * @return float
     */
    protected function predictProbability(array $sample, $label)
    {
        $predicted = $this->predictSampleBinary($sample);
        if (strval($predicted) == strval($label)) {
            return $this->prob[$label];
        }

        return 0.0;
    }

    /**
     * @param array $sample
     *
     * @return mixed
     */
    protected function predictSampleBinary(array $sample)
    {
        if ($this->evaluate($sample[$this->column], $this->operator, $this->value)) {
function acceptsInteger($int) { }

$x = '123'; // string "123"

// Instead of
acceptsInteger($x);

// we recommend to use
acceptsInteger((integer) $x);
            return $this->binaryLabels[0];
        }

        return $this->binaryLabels[1];
    }

    /**
     * @return string
     */
    public function __toString()
    {
        return "IF $this->column $this->operator $this->value " .
            "THEN " . $this->binaryLabels[0] . " ".
            "ELSE " . $this->binaryLabels[1];
    }
}


1		<?php
2
3		declare(strict_types=1);
4
5		namespace Phpml\Classification\Linear;
6
7		use Phpml\Helper\Predictable;
8		use Phpml\Helper\Trainable;
9		use Phpml\Helper\OneVsRest;
10		use Phpml\Classification\WeightedClassifier;
11		use Phpml\Classification\DecisionTree;
12
13		class DecisionStump extends WeightedClassifier
14		{
15		use Trainable, Predictable, OneVsRest;
16
17		const AUTO_SELECT = -1;
18
19		/**
20		* @var int
21		*/
22		protected $givenColumnIndex;
23
24		/**
25		* @var array
26		*/
27		protected $binaryLabels;
28
29		/**
30		* Sample weights : If used the optimization on the decision value
31		* will take these weights into account. If not given, all samples
32		* will be weighed with the same value of 1
33		*
34		* @var array
35		*/
36		protected $weights = null;
37
38		/**
39		* Lowest error rate obtained while training/optimizing the model
40		*
41		* @var float
42		*/
43		protected $trainingErrorRate;
44
45		/**
46		* @var int
47		*/
48		protected $column;
49
50		/**
51		* @var mixed
52		*/
53		protected $value;
54
55		/**
56		* @var string
57		*/
58		protected $operator;
59
60		/**
61		* @var array
62		*/
63		protected $columnTypes;
64
65		/**
66		* @var int
67		*/
68		protected $featureCount;
69
70		/**
71		* @var float
72		*/
73		protected $numSplitCount = 100.0;
74
75		/**
76		* Distribution of samples in the leaves
77		*
78		* @var array
79		*/
80		protected $prob;
81
82		/**
83		* A DecisionStump classifier is a one-level deep DecisionTree. It is generally
84		* used with ensemble algorithms as in the weak classifier role. <br>
85		*
86		* If columnIndex is given, then the stump tries to produce a decision node
87		* on this column, otherwise in cases given the value of -1, the stump itself
88		* decides which column to take for the decision (Default DecisionTree behaviour)
89		*
90		* @param int $columnIndex
91		*/
92		public function __construct(int $columnIndex = self::AUTO_SELECT)
93		{
94		$this->givenColumnIndex = $columnIndex;
95		}
96
97		/**
98		* @param array $samples
99		* @param array $targets
100		*/
101		protected function trainBinary(array $samples, array $targets)
102		{
103		$this->samples = array_merge($this->samples, $samples);
104		$this->targets = array_merge($this->targets, $targets);
105		$this->binaryLabels = array_keys(array_count_values($this->targets));
106		$this->featureCount = count($this->samples[0]);
107
108		// If a column index is given, it should be among the existing columns
109		if ($this->givenColumnIndex > count($this->samples[0]) - 1) {
110		$this->givenColumnIndex = self::AUTO_SELECT;
111		}
112
113		// Check the size of the weights given.
114		// If none given, then assign 1 as a weight to each sample
115		if ($this->weights) {
		0 ignored issues – show Bug Best Practice introduced 2017-02-19 10:47 UTC by Report Bug Copy Issue Report The expression `$this->weights` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($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...
116		$numWeights = count($this->weights);
117		if ($numWeights != count($this->samples)) {
118		throw new \Exception("Number of sample weights does not match with number of samples");
119		}
120		} else {
121		$this->weights = array_fill(0, count($this->samples), 1);
122		}
123
124		// Determine type of each column as either "continuous" or "nominal"
125		$this->columnTypes = DecisionTree::getColumnTypes($this->samples);
126
127		// Try to find the best split in the columns of the dataset
128		// by calculating error rate for each split point in each column
129		$columns = range(0, count($this->samples[0]) - 1);
130		if ($this->givenColumnIndex != self::AUTO_SELECT) {
131		$columns = [$this->givenColumnIndex];
132		}
133
134		$bestSplit = [
135		'value' => 0, 'operator' => '',
136		'prob' => [], 'column' => 0,
137		'trainingErrorRate' => 1.0];
138		foreach ($columns as $col) {
139		if ($this->columnTypes[$col] == DecisionTree::CONTINUOS) {
140		$split = $this->getBestNumericalSplit($col);
141		} else {
142		$split = $this->getBestNominalSplit($col);
143		}
144
145		if ($split['trainingErrorRate'] < $bestSplit['trainingErrorRate']) {
146		$bestSplit = $split;
147		}
148		}
149
150		// Assign determined best values to the stump
151		foreach ($bestSplit as $name => $value) {
152		$this->{$name} = $value;
153		}
154		}
155
156		/**
157		* While finding best split point for a numerical valued column,
158		* DecisionStump looks for equally distanced values between minimum and maximum
159		* values in the column. Given <i>$count</i> value determines how many split
160		* points to be probed. The more split counts, the better performance but
161		* worse processing time (Default value is 10.0)
162		*
163		* @param float $count
164		*/
165		public function setNumericalSplitCount(float $count)
166		{
167		$this->numSplitCount = $count;
168		}
169
170		/**
171		* Determines best split point for the given column
172		*
173		* @param int $col
174		*
175		* @return array
176		*/
177		protected function getBestNumericalSplit(int $col)
178		{
179		$values = array_column($this->samples, $col);
180		// Trying all possible points may be accomplished in two general ways:
181		// 1- Try all values in the $samples array ($values)
182		// 2- Artificially split the range of values into several parts and try them
183		// We choose the second one because it is faster in larger datasets
184		$minValue = min($values);
185		$maxValue = max($values);
186		$stepSize = ($maxValue - $minValue) / $this->numSplitCount;
187
188		$split = null;
189
190		foreach (['<=', '>'] as $operator) {
191		// Before trying all possible split points, let's first try
192		// the average value for the cut point
193		$threshold = array_sum($values) / (float) count($values);
194		list($errorRate, $prob) = $this->calculateErrorRate($threshold, $operator, $values);
195	View Code Duplication	if ($split == null \|\| $errorRate < $split['trainingErrorRate']) {
		0 ignored issues – show Duplication introduced 2017-02-25 14:37 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
196		$split = ['value' => $threshold, 'operator' => $operator,
197		'prob' => $prob, 'column' => $col,
198		'trainingErrorRate' => $errorRate];
199		}
200
201		// Try other possible points one by one
202		for ($step = $minValue; $step <= $maxValue; $step+= $stepSize) {
203		$threshold = (float)$step;
204		list($errorRate, $prob) = $this->calculateErrorRate($threshold, $operator, $values);
205	View Code Duplication	if ($errorRate < $split['trainingErrorRate']) {
		0 ignored issues – show Duplication introduced 2017-02-25 14:37 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
206		$split = ['value' => $threshold, 'operator' => $operator,
207		'prob' => $prob, 'column' => $col,
208		'trainingErrorRate' => $errorRate];
209		}
210		}// for
211		}
212
213		return $split;
214		}
215
216		/**
217		*
218		* @param int $col
219		*
220		* @return array
221		*/
222		protected function getBestNominalSplit(int $col)
223		{
224		$values = array_column($this->samples, $col);
225		$valueCounts = array_count_values($values);
226		$distinctVals= array_keys($valueCounts);
227
228		$split = null;
229
230		foreach (['=', '!='] as $operator) {
231		foreach ($distinctVals as $val) {
232		list($errorRate, $prob) = $this->calculateErrorRate($val, $operator, $values);
233
234	View Code Duplication	if ($split == null \|\| $split['trainingErrorRate'] < $errorRate) {
		0 ignored issues – show Duplication introduced 2017-02-25 14:37 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
235		$split = ['value' => $val, 'operator' => $operator,
236		'prob' => $prob, 'column' => $col,
237		'trainingErrorRate' => $errorRate];
238		}
239		}// for
240		}
241
242		return $split;
243		}
244
245
246		/**
247		*
248		* @param type $leftValue
249		* @param type $operator
250		* @param type $rightValue
251		*
252		* @return boolean
253		*/
254		protected function evaluate($leftValue, $operator, $rightValue)
255		{
256		switch ($operator) {
257		case '>': return $leftValue > $rightValue;
		0 ignored issues – show Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report The case body in a switch statement must start on the line following the statement. According to the PSR-2, the body of a case statement must start on the line immediately following the case statement. switch ($expr) { case "A": doSomething(); //right break; case "B": doSomethingElse(); //wrong break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history... Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report Terminating statement must be on a line by itself As per the PSR-2 coding standard, the `break` (or other terminating) statement must be on a line of its own. switch ($expr) { case "A": doSomething(); break; //wrong case "B": doSomething(); break; //right case "C:": doSomething(); return true; //right } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
258		case '>=': return $leftValue >= $rightValue;
		0 ignored issues – show Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report The case body in a switch statement must start on the line following the statement. According to the PSR-2, the body of a case statement must start on the line immediately following the case statement. switch ($expr) { case "A": doSomething(); //right break; case "B": doSomethingElse(); //wrong break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history... Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report Terminating statement must be on a line by itself As per the PSR-2 coding standard, the `break` (or other terminating) statement must be on a line of its own. switch ($expr) { case "A": doSomething(); break; //wrong case "B": doSomething(); break; //right case "C:": doSomething(); return true; //right } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
259		case '<': return $leftValue < $rightValue;
		0 ignored issues – show Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report The case body in a switch statement must start on the line following the statement. According to the PSR-2, the body of a case statement must start on the line immediately following the case statement. switch ($expr) { case "A": doSomething(); //right break; case "B": doSomethingElse(); //wrong break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history... Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report Terminating statement must be on a line by itself As per the PSR-2 coding standard, the `break` (or other terminating) statement must be on a line of its own. switch ($expr) { case "A": doSomething(); break; //wrong case "B": doSomething(); break; //right case "C:": doSomething(); return true; //right } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
260		case '<=': return $leftValue <= $rightValue;
		0 ignored issues – show Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report The case body in a switch statement must start on the line following the statement. According to the PSR-2, the body of a case statement must start on the line immediately following the case statement. switch ($expr) { case "A": doSomething(); //right break; case "B": doSomethingElse(); //wrong break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history... Coding Style introduced 2017-02-27 13:38 UTC by Report Bug Copy Issue Report Terminating statement must be on a line by itself As per the PSR-2 coding standard, the `break` (or other terminating) statement must be on a line of its own. switch ($expr) { case "A": doSomething(); break; //wrong case "B": doSomething(); break; //right case "C:": doSomething(); return true; //right } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
261		case '=': return $leftValue === $rightValue;
		0 ignored issues – show Coding Style introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report The case body in a switch statement must start on the line following the statement. According to the PSR-2, the body of a case statement must start on the line immediately following the case statement. switch ($expr) { case "A": doSomething(); //right break; case "B": doSomethingElse(); //wrong break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history... Coding Style introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report Terminating statement must be on a line by itself As per the PSR-2 coding standard, the `break` (or other terminating) statement must be on a line of its own. switch ($expr) { case "A": doSomething(); break; //wrong case "B": doSomething(); break; //right case "C:": doSomething(); return true; //right } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
262		case '!=':
263		case '<>': return $leftValue !== $rightValue;
		0 ignored issues – show Coding Style introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report The case body in a switch statement must start on the line following the statement. According to the PSR-2, the body of a case statement must start on the line immediately following the case statement. switch ($expr) { case "A": doSomething(); //right break; case "B": doSomethingElse(); //wrong break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history... Coding Style introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report Terminating statement must be on a line by itself As per the PSR-2 coding standard, the `break` (or other terminating) statement must be on a line of its own. switch ($expr) { case "A": doSomething(); break; //wrong case "B": doSomething(); break; //right case "C:": doSomething(); return true; //right } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
264		}
265
266		return false;
267		}
268
269		/**
270		* Calculates the ratio of wrong predictions based on the new threshold
271		* value given as the parameter
272		*
273		* @param float $threshold
274		* @param string $operator
275		* @param array $values
276		*
277		* @return array
278		*/
279		protected function calculateErrorRate(float $threshold, string $operator, array $values)
280		{
281		$wrong = 0.0;
282		$prob = [];
283		$leftLabel = $this->binaryLabels[0];
284		$rightLabel= $this->binaryLabels[1];
285
286		foreach ($values as $index => $value) {
287		if ($this->evaluate($value, $operator, $threshold)) {
		0 ignored issues – show Documentation introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report `$operator` is of type `string`, but the function expects a `object<Phpml\Classification\Linear\type>`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history... Documentation introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report `$threshold` is of type `double`, but the function expects a `object<Phpml\Classification\Linear\type>`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history...
288		$predicted = $leftLabel;
289		} else {
290		$predicted = $rightLabel;
291		}
292
293		$target = $this->targets[$index];
294		if (strval($predicted) != strval($this->targets[$index])) {
295		$wrong += $this->weights[$index];
296		}
297
298		if (! isset($prob[$predicted][$target])) {
299		$prob[$predicted][$target] = 0;
300		}
301		$prob[$predicted][$target]++;
302		}
303
304		// Calculate probabilities: Proportion of labels in each leaf
305		$dist = array_combine($this->binaryLabels, array_fill(0, 2, 0.0));
306		foreach ($prob as $leaf => $counts) {
307		$leafTotal = (float)array_sum($prob[$leaf]);
308		foreach ($counts as $label => $count) {
309		if (strval($leaf) == strval($label)) {
310		$dist[$leaf] = $count / $leafTotal;
311		}
312		}
313		}
314
315		return [$wrong / (float) array_sum($this->weights), $dist];
316		}
317
318		/**
319		* Returns the probability of the sample of belonging to the given label
320		*
321		* Probability of a sample is calculated as the proportion of the label
322		* within the labels of the training samples in the decision node
323		*
324		* @param array $sample
325		* @param mixed $label
326		*
327		* @return float
328		*/
329		protected function predictProbability(array $sample, $label)
330		{
331		$predicted = $this->predictSampleBinary($sample);
332		if (strval($predicted) == strval($label)) {
333		return $this->prob[$label];
334		}
335
336		return 0.0;
337		}
338
339		/**
340		* @param array $sample
341		*
342		* @return mixed
343		*/
344		protected function predictSampleBinary(array $sample)
345		{
346		if ($this->evaluate($sample[$this->column], $this->operator, $this->value)) {
		0 ignored issues – show Documentation introduced 2017-03-03 19:08 UTC by Report Bug Copy Issue Report `$this->operator` is of type `string`, but the function expects a `object<Phpml\Classification\Linear\type>`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history...
347		return $this->binaryLabels[0];
348		}
349
350		return $this->binaryLabels[1];
351		}
352
353		/**
354		* @return string
355		*/
356		public function __toString()
357		{
358		return "IF $this->column $this->operator $this->value " .
359		"THEN " . $this->binaryLabels[0] . " ".
360		"ELSE " . $this->binaryLabels[1];
361		}
362		}
363

php-ai / php-ml

Pull Request — master (#54)

DecisionStump::calculateErrorRate() C

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like