KMeans associative clustering (#262)

* KMeans associative clustering added

* fix travis error

* KMeans will return provided keys as point label if they are provided

* fix travis

* fix travis

Author: IcaVestica

docs/machine-learning/clustering/k-means.md

@@ -19,10 +19,12 @@ To divide the samples into clusters simply use `cluster` method. It's return the
 
 ```
 $samples = [[1, 1], [8, 7], [1, 2], [7, 8], [2, 1], [8, 9]];
+Or if you need to keep your indentifiers along with yours samples you can use array keys as labels.
+$samples = [ 'Label1' => [1, 1], 'Label2' => [8, 7], 'Label3' => [1, 2]];
 
 $kmeans = new KMeans(2);
 $kmeans->cluster($samples);
-// return [0=>[[1, 1], ...], 1=>[[8, 7], ...]] 
+// return [0=>[[1, 1], ...], 1=>[[8, 7], ...]] or [0=>['Label1' => [1, 1], 'Label3' => [1, 2], ...], 1=>['Label2' => [8, 7], ...]]
 ```
 
 ### Initialization methods

src/Clustering/KMeans.php

@@ -35,9 +35,9 @@ public function __construct(int $clustersNumber, int $initialization = self::INI
 
     public function cluster(array $samples): array
     {
-        $space = new Space(count($samples[0]));
-        foreach ($samples as $sample) {
-            $space->addPoint($sample);
+        $space = new Space(count(reset($samples)));
+        foreach ($samples as $key => $sample) {
+            $space->addPoint($sample, $key);
         }
 
         $clusters = [];

src/Clustering/KMeans/Cluster.php

@@ -32,7 +32,11 @@ public function getPoints(): array
     {
         $points = [];
         foreach ($this->points as $point) {
-            $points[] = $point->toArray();
+            if (!empty($point->label)) {
+                $points[$point->label] = $point->toArray();
+            } else {
+                $points[] = $point->toArray();
+            }
         }
 
         return $points;

src/Clustering/KMeans/Point.php

@@ -18,10 +18,16 @@ class Point implements ArrayAccess
      */
     protected $coordinates = [];
 
-    public function __construct(array $coordinates)
+    /**
+     * @var mixed
+     */
+    protected $label;
+
+    public function __construct(array $coordinates, $label = null)
     {
         $this->dimension = count($coordinates);
         $this->coordinates = $coordinates;
+        $this->label = $label;
     }
 
     public function toArray(): array

src/Clustering/KMeans/Space.php

@@ -35,21 +35,21 @@ public function toArray(): array
         return ['points' => $points];
     }
 
-    public function newPoint(array $coordinates): Point
+    public function newPoint(array $coordinates, $label = null): Point
     {
         if (count($coordinates) != $this->dimension) {
             throw new LogicException('('.implode(',', $coordinates).') is not a point of this space');
         }
 
-        return new Point($coordinates);
+        return new Point($coordinates, $label);
     }
 
     /**
      * @param null $data
      */
-    public function addPoint(array $coordinates, $data = null): void
+    public function addPoint(array $coordinates, $label = null, $data = null): void
     {
-        $this->attach($this->newPoint($coordinates), $data);
+        $this->attach($this->newPoint($coordinates, $label), $data);
     }
 
     /**

tests/Clustering/KMeansTest.php

@@ -28,6 +28,32 @@ public function testKMeansSamplesClustering(): void
         $this->assertCount(0, $samples);
     }
 
+    public function testKMeansSamplesLabeledClustering(): void
+    {
+        $samples = [
+            '555' => [1, 1],
+            '666' => [8, 7],
+            'ABC' => [1, 2],
+            'DEF' => [7, 8],
+            668 => [2, 1],
+            [8, 9],
+        ];
+
+        $kmeans = new KMeans(2);
+        $clusters = $kmeans->cluster($samples);
+
+        $this->assertCount(2, $clusters);
+
+        foreach ($samples as $index => $sample) {
+            if (in_array($sample, $clusters[0], true) || in_array($sample, $clusters[1], true)) {
+                $this->assertArrayHasKey($index, $clusters[0] + $clusters[1]);
+                unset($samples[$index]);
+            }
+        }
+
+        $this->assertCount(0, $samples);
+    }
+
     public function testKMeansInitializationMethods(): void
     {
         $samples = [