php-ai / php-ml

src/Phpml/Classification/Ensemble/RandomForest.php

Spacing +4 added lines, -4 removed lines

@@ -1,5 +1,5 @@ 
 <?php
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\Ensemble;
 
@@ -70,11 +70,11 @@ 
     protected function initSingleClassifier($classifier, $index)
     {
         if (is_float($this->featureSubsetRatio)) {
-            $featureCount = (int)($this->featureSubsetRatio * $this->featureCount);
+            $featureCount = (int) ($this->featureSubsetRatio * $this->featureCount);
         } elseif ($this->featureCount == 'sqrt') {
-            $featureCount = (int)sqrt($this->featureCount) + 1;
+            $featureCount = (int) sqrt($this->featureCount) + 1;
         } else {
-            $featureCount = (int)log($this->featureCount, 2) + 1;
+            $featureCount = (int) log($this->featureCount, 2) + 1;
         }
 
         if ($featureCount >= $this->featureCount) {

src/Phpml/Classification/DecisionTree.php

Doc Comments +1 added lines, -3 removed lines

@@ -166,7 +166,7 @@ 
 
     /**
      * @param array $records
-     * @return DecisionTreeLeaf[]
+     * @return null|DecisionTreeLeaf
      */
     protected function getBestSplit($records)
     {
@@ -354,7 +354,6 @@ 
      * each column in the given dataset. The importance values are
      * normalized and their total makes 1.<br/>
      *
-     * @param array $labels
      * @return array
      */
     public function getFeatureImportances()
@@ -394,7 +393,6 @@ 
      *
      * @param int $column
      * @param DecisionTreeLeaf
-     * @param array $collected
      *
      * @return array
      */

Spacing +9 added lines, -9 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification;
 
@@ -114,7 +114,7 @@ 
     {
         $types = [];
         $featureCount = count($samples[0]);
-        for ($i=0; $i < $featureCount; $i++) {
+        for ($i = 0; $i < $featureCount; $i++) {
             $values = array_column($samples, $i);
             $isCategorical = self::isCategoricalColumn($values);
             $types[] = $isCategorical ? self::NOMINAL : self::CONTINUOS;
@@ -138,7 +138,7 @@ 
         // otherwise group the records so that we can classify the leaf
         // in case maximum depth is reached
         $leftRecords = [];
-        $rightRecords= [];
+        $rightRecords = [];
         $remainingTargets = [];
         $prevRecord = null;
         $allSame = true;
@@ -156,12 +156,12 @@ 
             if ($split->evaluate($record)) {
                 $leftRecords[] = $recordNo;
             } else {
-                $rightRecords[]= $recordNo;
+                $rightRecords[] = $recordNo;
             }
 
             // Group remaining targets
             $target = $this->targets[$recordNo];
-            if (! array_key_exists($target, $remainingTargets)) {
+            if (!array_key_exists($target, $remainingTargets)) {
                 $remainingTargets[$target] = 1;
             } else {
                 $remainingTargets[$target]++;
@@ -177,7 +177,7 @@ 
                 $split->leftLeaf = $this->getSplitLeaf($leftRecords, $depth + 1);
             }
             if ($rightRecords) {
-                $split->rightLeaf= $this->getSplitLeaf($rightRecords, $depth + 1);
+                $split->rightLeaf = $this->getSplitLeaf($rightRecords, $depth + 1);
             }
         }
         return $split;
@@ -247,7 +247,7 @@ 
     protected function getSelectedFeatures()
     {
         $allFeatures = range(0, $this->featureCount - 1);
-        if ($this->numUsableFeatures == 0 && ! $this->selectedFeatures) {
+        if ($this->numUsableFeatures == 0 && !$this->selectedFeatures) {
             return $allFeatures;
         }
 
@@ -283,7 +283,7 @@ 
             $countMatrix[$label][$rowIndex]++;
         }
         $giniParts = [0, 0];
-        for ($i=0; $i<=1; $i++) {
+        for ($i = 0; $i <= 1; $i++) {
             $part = 0;
             $sum = array_sum(array_column($countMatrix, $i));
             if ($sum > 0) {
@@ -305,7 +305,7 @@ 
         // 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; $i++) {
+        for ($i = 0; $i < $this->featureCount; $i++) {
             $values = array_column($samples, $i);
             if ($this->columnTypes[$i] == self::CONTINUOS) {
                 $median = Mean::median($values);

src/Phpml/Classification/Ensemble/Bagging.php

Spacing +3 added lines, -3 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\Ensemble;
 
@@ -140,7 +140,7 @@ 
         $targets = [];
         srand($index);
         $bootstrapSize = $this->subsetRatio * $this->numSamples;
-        for ($i=0; $i < $bootstrapSize; $i++) {
+        for ($i = 0; $i < $bootstrapSize; $i++) {
             $rand = rand(0, $this->numSamples - 1);
             $samples[] = $this->samples[$rand];
             $targets[] = $this->targets[$rand];
@@ -154,7 +154,7 @@ 
     protected function initClassifiers()
     {
         $classifiers = [];
-        for ($i=0; $i<$this->numClassifier; $i++) {
+        for ($i = 0; $i < $this->numClassifier; $i++) {
             $ref = new \ReflectionClass($this->classifier);
             if ($this->classifierOptions) {
                 $obj = $ref->newInstanceArgs($this->classifierOptions);

src/Phpml/Classification/Linear/Adaline.php

Doc Comments +1 added lines, -1 removed lines

@@ -52,7 +52,7 @@
      * If normalizeInputs is set to true, then every input given to the algorithm will be standardized
      * by use of standard deviation and mean calculation
      *
-     * @param int $learningRate
+     * @param double $learningRate
      * @param int $maxIterations
      */
     public function __construct(float $learningRate = 0.001, int $maxIterations = 1000,

Spacing +5 added lines, -5 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\Linear;
 
@@ -15,12 +15,12 @@ 
     /**
      * Batch training is the default Adaline training algorithm
      */
-    const BATCH_TRAINING    = 1;
+    const BATCH_TRAINING = 1;
 
     /**
      * Online training: Stochastic gradient descent learning
      */
-    const ONLINE_TRAINING    = 2;
+    const ONLINE_TRAINING = 2;
 
     /**
      * The function whose result will be used to calculate the network error
@@ -52,7 +52,7 @@ 
     public function __construct(float $learningRate = 0.001, int $maxIterations = 1000,
         bool $normalizeInputs = true, int $trainingType = self::BATCH_TRAINING)
     {
-        if (! in_array($trainingType, [self::BATCH_TRAINING, self::ONLINE_TRAINING])) {
+        if (!in_array($trainingType, [self::BATCH_TRAINING, self::ONLINE_TRAINING])) {
             throw new \Exception("Adaline can only be trained with batch and online/stochastic gradient descent algorithm");
         }
 
@@ -104,7 +104,7 @@ 
     protected function updateWeights(array $updates)
     {
         // Updates all weights at once
-        for ($i=0; $i <= $this->featureCount; $i++) {
+        for ($i = 0; $i <= $this->featureCount; $i++) {
             if ($i == 0) {
                 $this->weights[0] += $this->learningRate * array_sum($updates);
             } else {

Unused Use Statements -2 removed lines

@@ -4,8 +4,6 @@
 
 namespace Phpml\Classification\Linear;
 
-use Phpml\Classification\Classifier;
-
 class Adaline extends Perceptron
 {
 

src/Phpml/Preprocessing/Normalizer.php

Spacing +3 added lines, -3 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Preprocessing;
 
@@ -12,7 +12,7 @@ 
 {
     const NORM_L1 = 1;
     const NORM_L2 = 2;
-    const NORM_STD= 3;
+    const NORM_STD = 3;
 
     /**
      * @var int
@@ -117,7 +117,7 @@ 
         foreach ($sample as $feature) {
             $norm2 += $feature * $feature;
         }
-        $norm2 = sqrt((float)$norm2);
+        $norm2 = sqrt((float) $norm2);
 
         if (0 == $norm2) {
             $sample = array_fill(0, count($sample), 1);

src/Phpml/Classification/DecisionTree/DecisionTreeLeaf.php

Spacing +14 added lines, -14 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\DecisionTree;
 
@@ -34,7 +34,7 @@ 
     /**
      * @var DecisionTreeLeaf
      */
-    public $rightLeaf= null;
+    public $rightLeaf = null;
 
     /**
      * @var array
@@ -79,7 +79,7 @@ 
 
         if ($this->isContinuous) {
             $op = $this->operator;
-            $value= $this->numericValue;
+            $value = $this->numericValue;
             $recordField = strval($recordField);
             eval("\$result = $recordField $op $value;");
             return $result;
@@ -100,16 +100,16 @@ 
             return 0.0;
         }
 
-        $nodeSampleCount = (float)count($this->records);
+        $nodeSampleCount = (float) count($this->records);
         $iT = $this->giniIndex;
 
         if ($this->leftLeaf) {
-            $pL = count($this->leftLeaf->records)/$nodeSampleCount;
+            $pL = count($this->leftLeaf->records) / $nodeSampleCount;
             $iT -= $pL * $this->leftLeaf->giniIndex;
         }
 
         if ($this->rightLeaf) {
-            $pR = count($this->rightLeaf->records)/$nodeSampleCount;
+            $pR = count($this->rightLeaf->records) / $nodeSampleCount;
             $iT -= $pR * $this->rightLeaf->giniIndex;
         }
 
@@ -133,25 +133,25 @@ 
             } else {
                 $col = "col_$this->columnIndex";
             }
-            if (! preg_match("/^[<>=]{1,2}/", $value)) {
+            if (!preg_match("/^[<>=]{1,2}/", $value)) {
                 $value = "=$value";
             }
-            $value = "<b>$col $value</b><br>Gini: ". number_format($this->giniIndex, 2);
+            $value = "<b>$col $value</b><br>Gini: ".number_format($this->giniIndex, 2);
         }
         $str = "<table ><tr><td colspan=3 align=center style='border:1px solid;'>
 				$value</td></tr>";
         if ($this->leftLeaf || $this->rightLeaf) {
-            $str .='<tr>';
+            $str .= '<tr>';
             if ($this->leftLeaf) {
-                $str .="<td valign=top><b>| Yes</b><br>" . $this->leftLeaf->getHTML($columnNames) . "</td>";
+                $str .= "<td valign=top><b>| Yes</b><br>".$this->leftLeaf->getHTML($columnNames)."</td>";
             } else {
-                $str .='<td></td>';
+                $str .= '<td></td>';
             }
-            $str .='<td>&nbsp;</td>';
+            $str .= '<td>&nbsp;</td>';
             if ($this->rightLeaf) {
-                $str .="<td valign=top align=right><b>No |</b><br>" . $this->rightLeaf->getHTML($columnNames) . "</td>";
+                $str .= "<td valign=top align=right><b>No |</b><br>".$this->rightLeaf->getHTML($columnNames)."</td>";
             } else {
-                $str .='<td></td>';
+                $str .= '<td></td>';
             }
             $str .= '</tr>';
         }

src/Phpml/Classification/Linear/Perceptron.php

Doc Comments +1 added lines, -1 removed lines

@@ -75,7 +75,7 @@
      *
      * Learning rate should be a float value between 0.0(exclusive) and 1.0(inclusive) <br>
      * Maximum number of iterations can be an integer value greater than 0
-     * @param int $learningRate
+     * @param double $learningRate
      * @param int $maxIterations
      */
     public function __construct(float $learningRate = 0.001, int $maxIterations = 1000,

Indentation +2 added lines, -2 removed lines

@@ -21,7 +21,7 @@ 
      */
     protected static $errorFunction = 'outputClass';
 
-   /**
+    /**
      * @var array
      */
     protected $samples = [];
@@ -111,7 +111,7 @@ 
         $this->threshold = $threshold;
     }
 
-   /**
+    /**
      * @param array $samples
      * @param array $targets
      */

Spacing +4 added lines, -4 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\Linear;
 
@@ -169,7 +169,7 @@ 
                 // Update bias
                 $this->weights[0] += $update * $this->learningRate; // Bias
                 // Update other weights
-                for ($i=1; $i <= $this->featureCount; $i++) {
+                for ($i = 1; $i <= $this->featureCount; $i++) {
                     $this->weights[$i] += $update * $sample[$i - 1] * $this->learningRate;
                 }
             }
@@ -202,7 +202,7 @@ 
     {
         // Check for early stop: No change larger than 1e-5
         $diff = array_map(
-            function ($w1, $w2) {
+            function($w1, $w2) {
                 return abs($w1 - $w2) > 1e-5 ? 1 : 0;
             },
             $oldWeights, $this->weights);
@@ -259,6 +259,6 @@ 
 
         $predictedClass = $this->outputClass($sample);
 
-        return $this->labels[ $predictedClass ];
+        return $this->labels[$predictedClass];
     }
 }

src/Phpml/Classification/Linear/DecisionStump.php

Doc Comments +1 added lines, -1 removed lines

@@ -226,7 +226,7 @@
     /**
      *
      * @param type $leftValue
-     * @param type $operator
+     * @param string $operator
      * @param type $rightValue
      *
      * @return boolean

Spacing +10 added lines, -10 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\Linear;
 
@@ -199,8 +199,8 @@ 
             }
 
             // Try other possible points one by one
-            for ($step = $minValue; $step <= $maxValue; $step+= $stepSize) {
-                $threshold = (float)$step;
+            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,
@@ -223,7 +223,7 @@ 
     {
         $values = array_column($this->samples, $col);
         $valueCounts = array_count_values($values);
-        $distinctVals= array_keys($valueCounts);
+        $distinctVals = array_keys($valueCounts);
 
         $split = null;
 
@@ -281,7 +281,7 @@ 
         $wrong = 0.0;
         $prob = [];
         $leftLabel = $this->binaryLabels[0];
-        $rightLabel= $this->binaryLabels[1];
+        $rightLabel = $this->binaryLabels[1];
 
         foreach ($values as $index => $value) {
             if ($this->evaluate($value, $operator, $threshold)) {
@@ -295,7 +295,7 @@ 
                 $wrong += $this->weights[$index];
             }
 
-            if (! isset($prob[$predicted][$target])) {
+            if (!isset($prob[$predicted][$target])) {
                 $prob[$predicted][$target] = 0;
             }
             $prob[$predicted][$target]++;
@@ -304,7 +304,7 @@ 
         // 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]);
+            $leafTotal = (float) array_sum($prob[$leaf]);
             foreach ($counts as $label => $count) {
                 if (strval($leaf) == strval($label)) {
                     $dist[$leaf] = $count / $leafTotal;
@@ -355,8 +355,8 @@ 
      */
     public function __toString()
     {
-        return "IF $this->column $this->operator $this->value " .
-            "THEN " . $this->binaryLabels[0] . " ".
-            "ELSE " . $this->binaryLabels[1];
+        return "IF $this->column $this->operator $this->value ".
+            "THEN ".$this->binaryLabels[0]." ".
+            "ELSE ".$this->binaryLabels[1];
     }
 }

src/Phpml/Classification/Ensemble/AdaBoost.php

Spacing +6 added lines, -6 removed lines

@@ -1,6 +1,6 @@ 
 <?php
 
-declare(strict_types=1);
+declare(strict_types = 1);
 
 namespace Phpml\Classification\Ensemble;
 
@@ -173,15 +173,15 @@ 
     {
         $weights = $this->weights;
         $std = StandardDeviation::population($weights);
-        $mean= Mean::arithmetic($weights);
+        $mean = Mean::arithmetic($weights);
         $min = min($weights);
-        $minZ= (int)round(($min - $mean) / $std);
+        $minZ = (int) round(($min - $mean) / $std);
 
         $samples = [];
         $targets = [];
         foreach ($weights as $index => $weight) {
-            $z = (int)round(($weight - $mean) / $std) - $minZ + 1;
-            for ($i=0; $i < $z; $i++) {
+            $z = (int) round(($weight - $mean) / $std) - $minZ + 1;
+            for ($i = 0; $i < $z; $i++) {
                 if (rand(0, 1) == 0) {
                     continue;
                 }
@@ -260,6 +260,6 @@ 
             $sum += $h * $alpha;
         }
 
-        return $this->labels[ $sum > 0 ? 1 : -1];
+        return $this->labels[$sum > 0 ? 1 : -1];
     }
 }