This commit is contained in:
Arkadiusz Kondas 2016-05-01 00:56:43 +02:00
parent 26be771668
commit 01a2499754
3 changed files with 25 additions and 25 deletions

View File

@ -1,16 +1,15 @@
<?php
declare(strict_types = 1);
declare (strict_types = 1);
namespace Phpml\Clustering;
interface Clusterer
{
/**
* @param array $samples
*
* @return array
*/
public function cluster(array $samples);
}

View File

@ -1,5 +1,6 @@
<?php
declare(strict_types = 1);
declare (strict_types = 1);
namespace Phpml\Clustering;
@ -24,8 +25,8 @@ class DBSCAN implements Clusterer
private $distanceMetric;
/**
* @param float $epsilon
* @param int $minSamples
* @param float $epsilon
* @param int $minSamples
* @param Distance $distanceMetric
*/
public function __construct($epsilon = 0.5, $minSamples = 3, Distance $distanceMetric = null)
@ -49,14 +50,14 @@ class DBSCAN implements Clusterer
$clusters = [];
$visited = [];
foreach($samples as $index => $sample) {
if(isset($visited[$index])) {
foreach ($samples as $index => $sample) {
if (isset($visited[$index])) {
continue;
}
$visited[$index] = true;
$regionSamples = $this->getSamplesInRegion($sample, $samples);
if(count($regionSamples) >= $this->minSamples) {
if (count($regionSamples) >= $this->minSamples) {
$clusters[] = $this->expandCluster($regionSamples, $visited);
}
}
@ -70,11 +71,12 @@ class DBSCAN implements Clusterer
*
* @return array
*/
private function getSamplesInRegion($localSample, $samples) {
private function getSamplesInRegion($localSample, $samples)
{
$region = [];
foreach($samples as $index => $sample) {
if($this->distanceMetric->distance($localSample, $sample) < $this->epsilon) {
foreach ($samples as $index => $sample) {
if ($this->distanceMetric->distance($localSample, $sample) < $this->epsilon) {
$region[$index] = $sample;
}
}
@ -88,14 +90,15 @@ class DBSCAN implements Clusterer
*
* @return array
*/
private function expandCluster($samples, &$visited) {
private function expandCluster($samples, &$visited)
{
$cluster = [];
foreach($samples as $index => $sample) {
if(!isset($visited[$index])) {
foreach ($samples as $index => $sample) {
if (!isset($visited[$index])) {
$visited[$index] = true;
$regionSamples = $this->getSamplesInRegion($sample, $samples);
if(count($regionSamples) > $this->minSamples) {
if (count($regionSamples) > $this->minSamples) {
$cluster = array_merge($regionSamples, $cluster);
}
}
@ -105,5 +108,4 @@ class DBSCAN implements Clusterer
return $cluster;
}
}

View File

@ -1,5 +1,6 @@
<?php
declare(strict_types = 1);
declare (strict_types = 1);
namespace tests\Clustering;
@ -7,14 +8,13 @@ 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]];
$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]]
[[8, 7], [7, 8], [8, 9]],
];
$dbscan = new DBSCAN($epsilon = 2, $minSamples = 3);
@ -24,16 +24,15 @@ class DBSCANTest extends \PHPUnit_Framework_TestCase
public function testDBSCANSamplesInCircleClustering()
{
$samples = [[1, 1],[6, 6],[1, -1],[5, 6],[-1, -1],[7, 8],[-1, 1],[7, 7]];
$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]]
[[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));
}
}