Add removeColumns function to ArrayDataset (#249)

* Add removeColumns function to ArrayDataset

* Add removeColumns to docs

* Fix cs

docs/machine-learning/datasets/array-dataset.md

@@ -8,6 +8,8 @@ Helper class that holds data as PHP `array` type. Implements the `Dataset` inter
 * $labels - (array) of labels
 
 ```
+use Phpml\Dataset\ArrayDataset;
+
 $dataset = new ArrayDataset([[1, 1], [2, 1], [3, 2], [4, 1]], ['a', 'a', 'b', 'b']);
 ```
 
@@ -19,3 +21,21 @@ To get samples or labels you can use getters:
 $dataset->getSamples();
 $dataset->getTargets();
 ```
+
+### Remove columns
+
+You can remove columns by index numbers, for example:
+
+```
+use Phpml\Dataset\ArrayDataset;
+
+$dataset = new ArrayDataset(
+    [[1,2,3,4], [2,3,4,5], [3,4,5,6], [4,5,6,7]],
+    ['a', 'a', 'b', 'b']
+);
+
+$dataset->removeColumns([0,2]);
+
+// now from each sample column 0 and 2 are removed
+// [[2,4], [3,5], [4,6], [5,7]]
+```

src/Dataset/ArrayDataset.php

@@ -40,4 +40,23 @@ class ArrayDataset implements Dataset
     {
         return $this->targets;
     }
+
+    /**
+     * @param int[] $columns
+     */
+    public function removeColumns(array $columns): void
+    {
+        foreach ($this->samples as &$sample) {
+            $this->removeColumnsFromSample($sample, $columns);
+        }
+    }
+
+    private function removeColumnsFromSample(array &$sample, array $columns): void
+    {
+        foreach ($columns as $index) {
+            unset($sample[$index]);
+        }
+
+        $sample = array_values($sample);
+    }
 }

tests/Dataset/ArrayDatasetTest.php

@@ -26,4 +26,15 @@ class ArrayDatasetTest extends TestCase
         $this->assertEquals($samples, $dataset->getSamples());
         $this->assertEquals($labels, $dataset->getTargets());
     }
+
+    public function testRemoveColumns(): void
+    {
+        $dataset = new ArrayDataset(
+            [[1, 2, 3, 4], [2, 3, 4, 5], [3, 4, 5, 6], [4, 5, 6, 7]],
+            ['a', 'a', 'b', 'b']
+        );
+        $dataset->removeColumns([0, 2]);
+
+        $this->assertEquals([[2, 4], [3, 5], [4, 6], [5, 7]], $dataset->getSamples());
+    }
 }