Allow normalizers to skip NaN values (#333)

* Add is_finite checks to skip NAN values * Tests and fix issue with samples that are all non-finite
RubixML · Dec 26, 2024 · 646b1a2 · 646b1a2
1 parent 37730cb
commit 646b1a2
Show file tree

Hide file tree

Showing 4 changed files with 33 additions and 3 deletions.
diff --git a/src/Transformers/MaxAbsoluteScaler.php b/src/Transformers/MaxAbsoluteScaler.php
@@ -100,7 +100,7 @@ public function update(Dataset $dataset) : void
         foreach ($this->maxabs as $column => $oldMax) {
             $values = $dataset->feature($column);
 
-            $max = max(array_map('abs', $values));
+            $max = max(array_map('abs', array_filter($values, 'is_finite') ?: [0]));
 
             $max = max($oldMax, $max);
 

diff --git a/src/Transformers/MinMaxNormalizer.php b/src/Transformers/MinMaxNormalizer.php
@@ -138,10 +138,10 @@ public function fit(Dataset $dataset) : void
                 $values = $dataset->feature($column);
 
                 /** @var int|float $min */
-                $min = min($values);
+                $min = min(array_filter($values, 'is_finite') ?: [0]);
 
                 /** @var int|float $max */
-                $max = max($values);
+                $max = max(array_filter($values, 'is_finite') ?: [0]);
 
                 $scale = ($this->max - $this->min) / (($max - $min) ?: EPSILON);
 
@@ -199,6 +199,10 @@ public function transform(array &$samples) : void
             foreach ($this->scales as $column => $scale) {
                 $value = &$sample[$column];
 
+                if (!is_finite($value)) {
+                    continue;
+                }
+
                 $min = $this->minimums[$column];
 
                 $value *= $scale;
@@ -224,6 +228,10 @@ public function reverseTransform(array &$samples) : void
             foreach ($this->scales as $column => $scale) {
                 $value = &$sample[$column];
 
+                if (!is_finite($value)) {
+                    continue;
+                }
+
                 $min = $this->minimums[$column];
 
                 $value -= $this->min - $min * $scale;

diff --git a/tests/Transformers/MaxAbsoluteScalerTest.php b/tests/Transformers/MaxAbsoluteScalerTest.php
@@ -109,4 +109,15 @@ public function reverseTransformUnfitted() : void
 
         $this->transformer->reverseTransform($samples);
     }
+
+    /**
+     * @test
+     */
+    public function skipsNonFinite(): void
+    {
+        $samples = Unlabeled::build([[0.0, 3000.0, NAN, -6.0], [1.0, 30.0, NAN, 0.001]]);
+        $this->transformer->fit($samples);
+        $this->assertNan($samples[0][2]);
+        $this->assertNan($samples[1][2]);
+    }
 }
diff --git a/tests/Transformers/MinMaxNormalizerTest.php b/tests/Transformers/MinMaxNormalizerTest.php
@@ -102,4 +102,15 @@ public function transformUnfitted() : void
 
         $this->transformer->transform($samples);
     }
+
+    /**
+     * @test
+     */
+    public function skipsNonFinite(): void
+    {
+        $samples = Unlabeled::build([[0.0, 3000.0, NAN, -6.0], [1.0, 30.0, NAN, 0.001]]);
+        $this->transformer->fit($samples);
+        $this->assertNan($samples[0][2]);
+        $this->assertNan($samples[1][2]);
+    }
 }