Fixed Regression datasets

app/Services/DatasetReader/LinearOrderDataSetReader.php

@@ -29,11 +29,6 @@ class LinearOrderDataSetReader implements IDataSetReader
                 $newLine[] = (float) $value;
             }
 
-            // if the dataset is for regression, we add a fake label of 0
-            if (count($newLine) === 2) {
-                $newLine[] = 0.0;
-            }
-
             $this->lines[] = $newLine;
         }
     }

app/Services/DatasetReader/RandomOrderDataSetReader.php

@@ -29,11 +29,6 @@ class RandomOrderDataSetReader implements IDataSetReader
                 $newLine[] = (float) $value;
             }
 
-            // if the dataset is for regression, we add a fake label of 0
-            if (count($newLine) === 2) {
-                $newLine[] = 0.0;
-            }
-
             $this->lines[] = $newLine;
         }
     }

resources/js/components/PerceptronDecisionGraph.vue

@@ -35,6 +35,30 @@ const farRightDataPointX = computed(() => {
     return maxX;
 });
 
+function getPerceptronOutput(weightsNetwork: number[][], inputs: number[]): number[] {
+    for (const layer of weightsNetwork) {
+        const nextInputs: number[] = [];
+
+        for (const neuron of layer) {
+            const bias = neuron[0];
+            const weights = neuron.slice(1);
+
+            let sum = bias;
+
+            for (let i = 0; i < weights.length; i++) {
+                sum += weights[i] * inputs[i];
+            }
+
+            const activated = props.activationFunction(sum);
+
+            nextInputs.push(activated);
+        }
+
+        inputs = nextInputs;
+    }
+    return inputs;
+}
+
 function getPerceptronDecisionBoundaryDataset(
     networkWeights: number[][][],
     activationFunction: (x: number) => number = (x) => x,
@@ -48,12 +72,17 @@ function getPerceptronDecisionBoundaryDataset(
     if (
         networkWeights.length == 1 &&
         networkWeights[0].length == 1 &&
-        networkWeights[0][0].length == 3
+        networkWeights[0][0].length <= 3
     ) {
         // Unique, 3 weights perceptron
         const perceptronWeights = networkWeights[0][0]; // We take the unique perceptron
 
         function perceptronLine(x: number): number {
+            if (perceptronWeights.length < 3) {
+                // If we have less than 3 weights, we assume missing weights are zero
+                perceptronWeights.push(getPerceptronOutput(networkWeights, [x])[0]);
+            }
+
             // w0 + w1*x + w2*y = 0 => y = -(w1/w2)*x - w0/w2
             const w2 = perceptronWeights[2] == 0 ? 1e-6 : perceptronWeights[2]; // Avoid division by zero
             return -(perceptronWeights[1] / w2) * x - perceptronWeights[0] / w2;