From 22963114c309fe084040a7902bd02646a941923b Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Sun, 1 May 2016 00:47:44 +0200
Subject: [PATCH] dbscan clustering algorithm

---
 src/Phpml/Clustering/Clusterer.php    |  16 ++++
 src/Phpml/Clustering/DBSCAN.php       | 103 ++++++++++++++++++++++++++
 tests/Phpml/Clustering/DBSCANTest.php |  39 ++++++++++
 3 files changed, 158 insertions(+)
 create mode 100644 src/Phpml/Clustering/Clusterer.php
 create mode 100644 src/Phpml/Clustering/DBSCAN.php
 create mode 100644 tests/Phpml/Clustering/DBSCANTest.php

diff --git a/src/Phpml/Clustering/Clusterer.php b/src/Phpml/Clustering/Clusterer.php
new file mode 100644
index 0000000..760c996
--- /dev/null
+++ b/src/Phpml/Clustering/Clusterer.php
@@ -0,0 +1,16 @@
+<?php
+declare(strict_types = 1);
+
+namespace Phpml\Clustering;
+
+interface Clusterer
+{
+
+    /**
+     * @param array $samples
+     *
+     * @return array
+     */
+    public function cluster(array $samples);
+
+}
diff --git a/src/Phpml/Clustering/DBSCAN.php b/src/Phpml/Clustering/DBSCAN.php
new file mode 100644
index 0000000..2972f98
--- /dev/null
+++ b/src/Phpml/Clustering/DBSCAN.php
@@ -0,0 +1,103 @@
+<?php
+declare(strict_types = 1);
+
+namespace Phpml\Clustering;
+
+use Phpml\Math\Distance;
+
+class DBSCAN implements Clusterer
+{
+    /**
+     * @var float
+     */
+    private $epsilon;
+
+    /**
+     * @var int
+     */
+    private $minSamples;
+
+    /**
+     * @var Distance
+     */
+    private $distanceMetric;
+
+    /**
+     * @param float $epsilon
+     * @param int $minSamples
+     */
+    public function __construct($epsilon = 0.5, $minSamples = 3)
+    {
+        $this->epsilon = $epsilon;
+        $this->minSamples = $minSamples;
+        $this->distanceMetric = new Distance\Euclidean();
+    }
+
+    /**
+     * @param array $samples
+     *
+     * @return array
+     */
+    public function cluster(array $samples)
+    {
+        $clusters = [];
+        $visited = [];
+
+        foreach($samples as $index => $sample) {
+            if(isset($visited[$index])) {
+                continue;
+            }
+            $visited[$index] = true;
+
+            $regionSamples = $this->getSamplesInRegion($sample, $samples);
+            if(count($regionSamples) >= $this->minSamples) {
+                $clusters[] = $this->expandCluster($regionSamples, $visited);
+            }
+        }
+
+        return $clusters;
+    }
+
+    /**
+     * @param array $localSample
+     * @param array $samples
+     *
+     * @return array
+     */
+    private function getSamplesInRegion($localSample, $samples) {
+        $region = [];
+
+        foreach($samples as $index => $sample) {
+            if($this->distanceMetric->distance($localSample, $sample) < $this->epsilon) {
+                $region[$index] = $sample;
+            }
+        }
+
+        return $region;
+    }
+
+    /**
+     * @param array $samples
+     * @param array $visited
+     *
+     * @return array
+     */
+    private function expandCluster($samples, &$visited) {
+        $cluster = [];
+
+        foreach($samples as $index => $sample) {
+            if(!isset($visited[$index])) {
+                $visited[$index] = true;
+                $regionSamples = $this->getSamplesInRegion($sample, $samples);
+                if(count($regionSamples) > $this->minSamples) {
+                    $cluster = array_merge($regionSamples, $cluster);
+                }
+            }
+
+            $cluster[] = $sample;
+        }
+
+        return $cluster;
+    }
+
+}
diff --git a/tests/Phpml/Clustering/DBSCANTest.php b/tests/Phpml/Clustering/DBSCANTest.php
new file mode 100644
index 0000000..748b87a
--- /dev/null
+++ b/tests/Phpml/Clustering/DBSCANTest.php
@@ -0,0 +1,39 @@
+<?php
+declare(strict_types = 1);
+
+namespace tests\Clustering;
+
+use Phpml\Clustering\DBSCAN;
+
+class DBSCANTest extends \PHPUnit_Framework_TestCase
+{
+
+    public function testDBSCANSamplesClustering()
+    {
+        $samples = [[1, 1],[8, 7],[1, 2],[7, 8],[2, 1],[8, 9]];
+
+        $clustered = [
+            [[1, 1], [1, 2], [2, 1]],
+            [[8, 7], [7, 8], [8, 9]]
+        ];
+
+        $dbscan = new DBSCAN($epsilon = 2, $minSamples = 3);
+
+        $this->assertEquals($clustered, $dbscan->cluster($samples));
+    }
+
+    public function testDBSCANSamplesInCircleClustering()
+    {
+        $samples = [[1, 1],[6, 6],[1, -1],[5, 6],[-1, -1],[7, 8],[-1, 1],[7, 7]];
+
+        $clustered = [
+            [[1, 1],[1, -1],[-1, -1],[-1, 1]],
+            [[6, 6],[5, 6],[7, 8],[7, 7]]
+        ];
+
+        $dbscan = new DBSCAN($epsilon = 3, $minSamples = 4);
+
+        $this->assertEquals($clustered, $dbscan->cluster($samples));
+    }
+
+}