Download src/linear_regression.py from Eric-Yyvuw/ml-from-scratch: direct link, hf CLI and curl.
- Browser
- Download file 3.05 kB
-
https://huggingface.co/Eric-Yyvuw/ml-from-scratch/resolve/main/src/linear_regression.py
- Command line
-
hf download hf://Eric-Yyvuw/ml-from-scratch/src/linear_regression.py
-
curl -L -o linear_regression.py https://huggingface.co/Eric-Yyvuw/ml-from-scratch/resolve/main/src/linear_regression.py
3.05 kB
| """ | |
| Linear Regression with Gradient Descent — CS401 | |
| From scratch, no ML libraries. | |
| """ | |
| import random | |
| # ---- Training Data ---- | |
| # Living area (m²) → Price (€k) | |
| X = [50, 60, 70, 80, 90, 100, 110, 120, 130, 140] | |
| Y = [150, 180, 210, 240, 270, 300, 330, 360, 390, 420] | |
| n = len(X) | |
| # ---- Hypothesis ---- | |
| def predict(x, theta0, theta1): | |
| """h(x) = theta0 + theta1 * x""" | |
| return theta0 + theta1 * x | |
| # ---- Loss Function (MSE) ---- | |
| def compute_loss(theta0, theta1): | |
| """J(theta0, theta1) = (1/n) * sum((h(x_i) - y_i)^2)""" | |
| total = 0 | |
| for i in range(n): | |
| y_pred = predict(X[i], theta0, theta1) | |
| total += (y_pred - Y[i]) ** 2 | |
| return total / n | |
| # ---- Evaluation Metrics ---- | |
| def mae(theta0, theta1): | |
| """Mean Absolute Error = (1/n) * sum(|h(x_i) - y_i|)""" | |
| total = 0 | |
| for i in range(n): | |
| total += abs(predict(X[i], theta0, theta1) - Y[i]) | |
| return total / n | |
| def rmse(theta0, theta1): | |
| """Root Mean Squared Error = sqrt((1/n) * sum((h(x_i) - y_i)^2))""" | |
| return compute_loss(theta0, theta1) ** 0.5 | |
| # ---- Gradient Descent ---- | |
| def gradient_descent(lr=0.00001, iterations=1000): | |
| theta0 = 0 # bias | |
| theta1 = 0 # weight | |
| for iteration in range(iterations): | |
| # Compute gradients | |
| grad0 = 0 # dJ/dtheta0 | |
| grad1 = 0 # dJ/dtheta1 | |
| for i in range(n): | |
| y_pred = predict(X[i], theta0, theta1) | |
| error = y_pred - Y[i] | |
| grad0 += error # derivative w.r.t. theta0 | |
| grad1 += error * X[i] # derivative w.r.t. theta1 | |
| grad0 /= n | |
| grad1 /= n | |
| # Update parameters | |
| theta0 -= lr * grad0 | |
| theta1 -= lr * grad1 | |
| # Print progress every 200 iterations | |
| if iteration % 200 == 0: | |
| loss = compute_loss(theta0, theta1) | |
| print(f"Iter {iteration:4d} | Loss: {loss:>10.2f} | theta0: {theta0:.4f} | theta1: {theta1:.6f}") | |
| return theta0, theta1 | |
| # ---- Main ---- | |
| if __name__ == "__main__": | |
| print("=" * 60) | |
| print("Linear Regression — Gradient Descent") | |
| print("=" * 60) | |
| print(f"Training data: {n} examples") | |
| print(f"X (area m²): {X}") | |
| print(f"Y (price €k): {Y}") | |
| print() | |
| theta0, theta1 = gradient_descent(lr=0.00001, iterations=2000) | |
| print() | |
| print("=" * 60) | |
| print(f"Result: h(x) = {theta0:.2f} + {theta1:.4f} * x") | |
| print(f"Final loss (MSE): {compute_loss(theta0, theta1):.2f}") | |
| print(f"MAE: {mae(theta0, theta1):.4f}") | |
| print(f"RMSE: {rmse(theta0, theta1):.4f}") | |
| print("=" * 60) | |
| # Predictions | |
| print() | |
| print("Predictions:") | |
| print(f"{'Area (m²)':>10} | {'Actual (€k)':>12} | {'Predicted (€k)':>14}") | |
| print("-" * 42) | |
| for x_val, y_val in zip(X, Y): | |
| y_pred = predict(x_val, theta0, theta1) | |
| print(f"{x_val:>10} | {y_val:>12} | {y_pred:>14.2f}") | |
| # Predict new value | |
| print() | |
| new_area = 150 | |
| predicted_price = predict(new_area, theta0, theta1) | |
| print(f"New prediction: {new_area} m² → {predicted_price:.2f} €k") | |