From cbec77d2478ca5b6c0452cac28829a58f516e775 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Wed, 27 Apr 2016 23:28:01 +0200
Subject: [PATCH] pearson correlation function

---
 src/Phpml/Math/Statistic/Correlation.php      | 45 +++++++++++++++++++
 .../Math/Statistic/StandardDeviation.php      | 15 +++----
 .../Phpml/Math/Statistic/CorrelationTest.php  | 33 ++++++++++++++
 .../Math/Statistic/StandardDeviationTest.php  |  1 -
 4 files changed, 85 insertions(+), 9 deletions(-)
 create mode 100644 src/Phpml/Math/Statistic/Correlation.php
 create mode 100644 tests/Phpml/Math/Statistic/CorrelationTest.php

diff --git a/src/Phpml/Math/Statistic/Correlation.php b/src/Phpml/Math/Statistic/Correlation.php
new file mode 100644
index 0000000..a6047a8
--- /dev/null
+++ b/src/Phpml/Math/Statistic/Correlation.php
@@ -0,0 +1,45 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace Phpml\Math\Statistic;
+
+use Phpml\Exception\InvalidArgumentException;
+
+class Correlation
+{
+    /**
+     * @param array|int[]|float[] $x
+     * @param array|int[]|float[] $y
+     *
+     * @return float
+     *
+     * @throws InvalidArgumentException
+     */
+    public static function pearson(array $x, array $y)
+    {
+        if (count($x) !== count($y)) {
+            throw InvalidArgumentException::arraySizeNotMatch();
+        }
+
+        $count = count($x);
+        $meanX = array_sum($x) / $count;
+        $meanY = array_sum($y) / $count;
+
+        $axb = 0;
+        $a2 = 0;
+        $b2 = 0;
+
+        for ($i = 0;$i < $count;++$i) {
+            $a = $x[$i] - $meanX;
+            $b = $y[$i] - $meanY;
+            $axb = $axb + ($a * $b);
+            $a2 = $a2 + pow($a, 2);
+            $b2 = $b2 + pow($b, 2);
+        }
+
+        $corr = $axb / sqrt($a2 * $b2);
+
+        return $corr;
+    }
+}
diff --git a/src/Phpml/Math/Statistic/StandardDeviation.php b/src/Phpml/Math/Statistic/StandardDeviation.php
index 3c57a4a..a05faa4 100644
--- a/src/Phpml/Math/Statistic/StandardDeviation.php
+++ b/src/Phpml/Math/Statistic/StandardDeviation.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Math\Statistic;
 
@@ -7,10 +8,9 @@ use Phpml\Exception\InvalidArgumentException;
 
 class StandardDeviation
 {
-
     /**
      * @param array|float[] $a
-     * @param bool $sample
+     * @param bool          $sample
      *
      * @return float
      *
@@ -18,16 +18,16 @@ class StandardDeviation
      */
     public static function population(array $a, $sample = true)
     {
-        if(empty($a)) {
+        if (empty($a)) {
             throw InvalidArgumentException::arrayCantBeEmpty();
         }
-        
+
         $n = count($a);
 
         if ($sample && $n === 1) {
             throw InvalidArgumentException::arraySizeToSmall(2);
         }
-        
+
         $mean = array_sum($a) / $n;
         $carry = 0.0;
         foreach ($a as $val) {
@@ -35,11 +35,10 @@ class StandardDeviation
             $carry += $d * $d;
         };
 
-        if($sample) {
+        if ($sample) {
             --$n;
         }
 
         return sqrt($carry / $n);
     }
-
 }
diff --git a/tests/Phpml/Math/Statistic/CorrelationTest.php b/tests/Phpml/Math/Statistic/CorrelationTest.php
new file mode 100644
index 0000000..492d38c
--- /dev/null
+++ b/tests/Phpml/Math/Statistic/CorrelationTest.php
@@ -0,0 +1,33 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace test\Phpml\Math\StandardDeviation;
+
+use Phpml\Math\Statistic\Correlation;
+
+class CorrelationTest extends \PHPUnit_Framework_TestCase
+{
+    public function testPearsonCorrelation()
+    {
+        //http://www.stat.wmich.edu/s216/book/node126.html
+        $delta = 0.001;
+        $x = [9300,  10565,  15000,  15000,  17764,  57000,  65940,  73676,  77006,  93739, 146088, 153260];
+        $y = [7100, 15500, 4400, 4400, 5900, 4600, 8800, 2000, 2750, 2550,  960, 1025];
+        $this->assertEquals(-0.641, Correlation::pearson($x, $y), '', $delta);
+
+        //http://www.statisticshowto.com/how-to-compute-pearsons-correlation-coefficients/
+        $delta = 0.001;
+        $x = [43, 21, 25, 42, 57, 59];
+        $y = [99, 65, 79, 75, 87, 82];
+        $this->assertEquals(0.549, Correlation::pearson($x, $y), '', $delta);
+    }
+
+    /**
+     * @expectedException \Phpml\Exception\InvalidArgumentException
+     */
+    public function testThrowExceptionOnInvalidArgumentsForPearsonCorrelation()
+    {
+        Correlation::pearson([1, 2, 4], [3, 5]);
+    }
+}
diff --git a/tests/Phpml/Math/Statistic/StandardDeviationTest.php b/tests/Phpml/Math/Statistic/StandardDeviationTest.php
index ff69f7c..299c979 100644
--- a/tests/Phpml/Math/Statistic/StandardDeviationTest.php
+++ b/tests/Phpml/Math/Statistic/StandardDeviationTest.php
@@ -39,5 +39,4 @@ class StandardDeviationTest extends \PHPUnit_Framework_TestCase
     {
         StandardDeviation::population([1]);
     }
-
 }