Brute force hhyperparameters

src/training/decision_tree/main.py

@@ -38,33 +38,58 @@ def create_split(x, y, game_ids):
 
 if __name__ == "__main__":
 
-    model_path = "C:/Users/Laurent/Desktop/chess-engine/src/training/decision_tree/cache/model.joblib"
+    model_path = "./src/training/decision_tree/cache/model.joblib"
 
     if os.path.exists(model_path):
         model = Model.load(model_path)
 
     else:
-        x, y, game_ids = preprocessor.run("C:/Users/Laurent/Desktop/chess-engine/dataset/v1/output.csv")
+        x, y, game_ids = preprocessor.run("./dataset/output.csv")
 
         split = create_split(x, y, game_ids)
+        
+        trained_model = []
+        
+        is_hyperparameter_tuning = True
+        for depth in range(1, 10):
+            for leafs in range(1, int(depth * 5)):
+                print(f"Training model with depth={depth} and leafs={leafs}")
 
-        depth = 35
-        leafs = int(depth * 3.5)
+                model = Model(
+                    tree=RandomForestRegressor(
+                        n_estimators=25,
+                        max_depth=depth,
+                        max_features=0.35,
+                        min_samples_leaf=leafs,
+                        random_state=42
+                    ),
+                    feature_names=preprocessor.get_feature_names(),
+                    train_test_split=split
+                )
 
-        model = Model(
-            tree=RandomForestRegressor(
-                n_estimators=25,
-                max_depth=depth,
-                max_features=0.35,
-                min_samples_leaf=leafs,
-                random_state=42
-            ),
-            feature_names=preprocessor.get_feature_names(),
-            train_test_split=split
-        )
-
-        model.train()
-        model.evaluate()
+                model.train()
+                [train_mae, train_mse, test_mae, test_mse] = model.evaluate()
+                
+                # Verify it's not overfitting
+                if test_mae > 1.5 * train_mae:
+                    print("Model is overfitting, skipping saving...")
+                else:
+                    trained_model.append({
+                        "depth": depth,
+                        "leafs": leafs,
+                        "train_mae": train_mae,
+                        "train_mse": train_mse,
+                        "test_mae": test_mae,
+                        "test_mse": test_mse
+                    })
+                    
+        best_model = min(trained_model, key=lambda x: x["test_mae"])
+        
+        print("Best model so far:")
+        print("MAE:", best_model["test_mae"])
+        print("MSE:", best_model["test_mse"])
+                    
+                    
         #model.save_model(model_path)
 
     visualizer = Visualizer(model=model)

src/training/decision_tree/model.py

@@ -64,6 +64,8 @@ class Model:
         print("Test:")
         print("MAE:", test_mae)
         print("MSE:", test_mse)
+        
+        return [train_mae, train_mse, test_mae, test_mse]
 
 
     def save_model(self, path):