php-ai / php-ml

src/Phpml/Classification/NaiveBayes.php

Indentation +116 added lines, -116 removed lines

@@ -12,112 +12,112 @@ 
 class NaiveBayes implements Classifier
 {
     use Trainable, Predictable;
-	const CONTINUOS	= 1;
-	const NOMINAL	= 2;
-	const SMALL_VALUE = 1e-32;
-	private $std = array();
-	private $mean= array();
-	private $discreteProb = array();
-	private $dataType = array();
-	private $p = array();
-	private $sampleCount = 0;
-	private $featureCount = 0;
-	private $labels = array();
-	public function train(array $samples, array $targets)
+    const CONTINUOS	= 1;
+    const NOMINAL	= 2;
+    const SMALL_VALUE = 1e-32;
+    private $std = array();
+    private $mean= array();
+    private $discreteProb = array();
+    private $dataType = array();
+    private $p = array();
+    private $sampleCount = 0;
+    private $featureCount = 0;
+    private $labels = array();
+    public function train(array $samples, array $targets)
     {
         $this->samples = $samples;
         $this->targets = $targets;
-		$this->sampleCount = count($samples);
-		$this->featureCount = count($samples[0]);
-		// Get distinct targets
-		$this->labels = $targets;
-		array_unique($this->labels);
-		foreach($this->labels as $label)
-		{
-			$samples = $this->getSamplesByLabel($label);
-			$this->p[$label] = count($samples) / $this->sampleCount;
-			$this->calculateStatistics($label, $samples);
-		}
+        $this->sampleCount = count($samples);
+        $this->featureCount = count($samples[0]);
+        // Get distinct targets
+        $this->labels = $targets;
+        array_unique($this->labels);
+        foreach($this->labels as $label)
+        {
+            $samples = $this->getSamplesByLabel($label);
+            $this->p[$label] = count($samples) / $this->sampleCount;
+            $this->calculateStatistics($label, $samples);
+        }
     }
 
-	/**
-	 * Calculates vital statistics for each label & feature. Stores these
-	 * values in private array in order to avoid repeated calculation
-	 * @param string $label
-	 * @param array $samples
-	 */
-	private function calculateStatistics($label, $samples)
-	{
-		$this->std[$label] = array_fill(0, $this->featureCount, 0);
-		$this->mean[$label]= array_fill(0, $this->featureCount, 0);
-		$this->dataType[$label] = array_fill(0, $this->featureCount, self::CONTINUOS);
-		$this->discreteProb[$label] = array_fill(0, $this->featureCount, self::CONTINUOS);
-		for($i=0; $i<$this->featureCount; $i++)
-		{
-			// Get the values of nth column in the samples array
-			// Mean::arithmetic is called twice, can be optimized
-			$values = array_column($samples, $i);
-			$numValues = count($values);
-			$freq = array_count_values($values);
-			// if values are of only a few types or the column contain categorical/string
-			// values, then it should be treated as nominal/categorical/discrete column
-			if (count($freq) <= $numValues / 2)
-			{
-				$this->dataType[$label][$i] = self::NOMINAL;
-				$this->discreteProb[$label][$i] = $freq;
-				$db = &$this->discreteProb[$label][$i];
-				$db = array_map(function($el) use ($numValues) {
-					return $el / $numValues;
-				}, $db);
-			}
-			else
-			{
-				$this->mean[$label][$i] = Mean::arithmetic($values);
-				$this->std[$label][$i] = StandardDeviation::population($values, false);
-			}
-		}
-	}
+    /**
+     * Calculates vital statistics for each label & feature. Stores these
+     * values in private array in order to avoid repeated calculation
+     * @param string $label
+     * @param array $samples
+     */
+    private function calculateStatistics($label, $samples)
+    {
+        $this->std[$label] = array_fill(0, $this->featureCount, 0);
+        $this->mean[$label]= array_fill(0, $this->featureCount, 0);
+        $this->dataType[$label] = array_fill(0, $this->featureCount, self::CONTINUOS);
+        $this->discreteProb[$label] = array_fill(0, $this->featureCount, self::CONTINUOS);
+        for($i=0; $i<$this->featureCount; $i++)
+        {
+            // Get the values of nth column in the samples array
+            // Mean::arithmetic is called twice, can be optimized
+            $values = array_column($samples, $i);
+            $numValues = count($values);
+            $freq = array_count_values($values);
+            // if values are of only a few types or the column contain categorical/string
+            // values, then it should be treated as nominal/categorical/discrete column
+            if (count($freq) <= $numValues / 2)
+            {
+                $this->dataType[$label][$i] = self::NOMINAL;
+                $this->discreteProb[$label][$i] = $freq;
+                $db = &$this->discreteProb[$label][$i];
+                $db = array_map(function($el) use ($numValues) {
+                    return $el / $numValues;
+                }, $db);
+            }
+            else
+            {
+                $this->mean[$label][$i] = Mean::arithmetic($values);
+                $this->std[$label][$i] = StandardDeviation::population($values, false);
+            }
+        }
+    }
 
-	/**
-	 * Calculates the probability P(label|sample_n) assuming
-	 * the feature is a continuous value
-	 * @param array $sample
-	 * @param int $feature
-	 * @param string $label
-	 */
-	private function sampleProbability($sample, $feature, $label)
-	{
-		$value = $sample[$feature];
-		if ($this->dataType[$label][$feature] == self::NOMINAL)
-		{
-			if (! isset($this->discreteProb[$label][$feature][$value]) ||
-				$this->discreteProb[$label][$feature][$value] == 0)
-				return self::SMALL_VALUE;
-			return $this->discreteProb[$label][$feature][$value];
-		}
-		$std = $this->std[$label][$feature] ;
-		$mean= $this->mean[$label][$feature];
-		$std2 = $std * $std;
-		if ($std2 == 0)
-			$std2 = self::SMALL_VALUE;
-		// Calculate the probability density by use of normal/Gaussian distribution
-		// Ref: https://en.wikipedia.org/wiki/Normal_distribution
-		return (1 / sqrt(2 * $std2 * pi())) * exp( - pow($value - $mean, 2) / (2 * $std2));
-	}
+    /**
+     * Calculates the probability P(label|sample_n) assuming
+     * the feature is a continuous value
+     * @param array $sample
+     * @param int $feature
+     * @param string $label
+     */
+    private function sampleProbability($sample, $feature, $label)
+    {
+        $value = $sample[$feature];
+        if ($this->dataType[$label][$feature] == self::NOMINAL)
+        {
+            if (! isset($this->discreteProb[$label][$feature][$value]) ||
+                $this->discreteProb[$label][$feature][$value] == 0)
+                return self::SMALL_VALUE;
+            return $this->discreteProb[$label][$feature][$value];
+        }
+        $std = $this->std[$label][$feature] ;
+        $mean= $this->mean[$label][$feature];
+        $std2 = $std * $std;
+        if ($std2 == 0)
+            $std2 = self::SMALL_VALUE;
+        // Calculate the probability density by use of normal/Gaussian distribution
+        // Ref: https://en.wikipedia.org/wiki/Normal_distribution
+        return (1 / sqrt(2 * $std2 * pi())) * exp( - pow($value - $mean, 2) / (2 * $std2));
+    }
 
-	/**
-	 * Return samples belonging to specific label
-	 * @param string $label
-	 * @return array
-	 */
-	private function getSamplesByLabel($label)
-	{
-		$samples = array();
-		for($i=0; $i<$this->sampleCount; $i++)
-			if ($this->targets[$i] == $label)
-				$samples[] = $this->samples[$i];
-		return $samples;
-	}
+    /**
+     * Return samples belonging to specific label
+     * @param string $label
+     * @return array
+     */
+    private function getSamplesByLabel($label)
+    {
+        $samples = array();
+        for($i=0; $i<$this->sampleCount; $i++)
+            if ($this->targets[$i] == $label)
+                $samples[] = $this->samples[$i];
+        return $samples;
+    }
 
     /**
      * @param array $sample
@@ -125,23 +125,23 @@ 
      */
     protected function predictSample(array $sample)
     {
-		// Use NaiveBayes assumption for each label using:
-		//	P(label|features) = P(label) * P(feature0|label) * P(feature1|label) .... P(featureN|label)
-		// Then compare probability for each class to determine which is most likely
-		$predictions = array();
-		foreach($this->labels as $label)
-		{
-			$p = $this->p[$label];
-			for($i=0; $i<$this->featureCount; $i++)
-			{
-				$Plf = $this->sampleProbability($sample, $i, $label);
-				// Correct the value for small and zero values
-				if (is_nan($Plf) || $Plf < self::SMALL_VALUE)
-					$Plf = self::SMALL_VALUE;
-				$p *= $Plf;
-			}
-			$predictions[$label] = $p;
-		}
+        // Use NaiveBayes assumption for each label using:
+        //	P(label|features) = P(label) * P(feature0|label) * P(feature1|label) .... P(featureN|label)
+        // Then compare probability for each class to determine which is most likely
+        $predictions = array();
+        foreach($this->labels as $label)
+        {
+            $p = $this->p[$label];
+            for($i=0; $i<$this->featureCount; $i++)
+            {
+                $Plf = $this->sampleProbability($sample, $i, $label);
+                // Correct the value for small and zero values
+                if (is_nan($Plf) || $Plf < self::SMALL_VALUE)
+                    $Plf = self::SMALL_VALUE;
+                $p *= $Plf;
+            }
+            $predictions[$label] = $p;
+        }
         arsort($predictions, SORT_NUMERIC);
         reset($predictions);
         return key($predictions);