diff options
Diffstat (limited to 'power_predictor.py')
| -rw-r--r-- | power_predictor.py | 38 |
1 files changed, 36 insertions, 2 deletions
diff --git a/power_predictor.py b/power_predictor.py index 49e49fe..ca38498 100644 --- a/power_predictor.py +++ b/power_predictor.py @@ -14,6 +14,7 @@ import matplotlib.pyplot as plt def load_data(csv_path): # Read the CSV file df = pd.read_csv(csv_path) + df = df.sample(frac=1).reset_index(drop=True) # Extract target (power usage) y = df['package_power_j'].values @@ -82,8 +83,18 @@ class PowerEstimator(nn.Module): def __init__(self, input_size): super(PowerEstimator, self).__init__() self.model = nn.Sequential( + # nn.Linear(input_size, 128), + # nn.ReLU(), + # nn.Dropout(0.3), + # nn.Linear(128, 64), + # nn.ReLU(), + # nn.Dropout(0.2), + # nn.Linear(64, 32), + # nn.ReLU(), + # nn.Linear(32, 1) nn.Linear(input_size, 64), nn.ReLU(), + # // leaky relu nn.Dropout(0.2), nn.Linear(64, 32), nn.ReLU(), @@ -94,10 +105,12 @@ class PowerEstimator(nn.Module): return self.model(x) # Step 5: Train the model -def train_model(X, y, batch_size=32, epochs=100, lr=0.001): +def train_model(X, y, batch_size=32, epochs=100, lr=0.001, early_stopping_patience=10): # Split data into training and validation sets X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42) + + # Scale the features scaler = StandardScaler() X_train_scaled = scaler.fit_transform(X_train) @@ -123,6 +136,9 @@ def train_model(X, y, batch_size=32, epochs=100, lr=0.001): # Training loop train_losses = [] val_losses = [] + best_val_loss = float('inf') + epochs_without_improvement = 0 + best_model_state = None for epoch in range(epochs): # Training @@ -150,10 +166,27 @@ def train_model(X, y, batch_size=32, epochs=100, lr=0.001): val_loss /= len(val_loader.dataset) val_losses.append(val_loss) + + # Early stopping check + if val_loss < best_val_loss: + best_val_loss = val_loss + best_model_state = model.state_dict().copy() + epochs_without_improvement = 0 + else: + epochs_without_improvement += 1 # Print progress if (epoch + 1) % 10 == 0: print(f"Epoch {epoch+1}/{epochs}, Train Loss: {train_loss:.6f}, Val Loss: {val_loss:.6f}") + + # Check early stopping + if epochs_without_improvement >= early_stopping_patience: + print(f"\nEarly stopping triggered after {epoch+1} epochs") + break + + # Load best model + if best_model_state is not None: + model.load_state_dict(best_model_state) # Plot training history plt.figure(figsize=(10, 5)) @@ -233,11 +266,12 @@ def main(): print("Loading data...") X, y = load_data(csv_path) - X, y = remove_outliers(X, y) # Impute missing values print("\nImputing missing values...") X_imputed = impute_missing_values(X) + + X_imputed, y = remove_outliers(X_imputed, y) # Analyze feature importance print("\nAnalyzing feature importance...") |