| import pandas as pd |
| from sklearn.linear_model import LinearRegression |
| from sklearn.metrics import mean_squared_error |
|
|
| df = pd.read_csv("normalized_train_dataset_with_train_number.csv") |
|
|
|
|
| X = df[["departure_station", "arrival_station", "departure_time", "arrival_time", "day_of_week", "train_type", "distance_km"]] |
| y = df["train_number"] |
|
|
| model = LinearRegression() |
| model.fit(X, y) |
|
|
| weights = model.coef_ |
| bias = model.intercept_ |
|
|
| feature_names = X.columns |
| print("Learned Weights:") |
| for feature, weight in zip(feature_names, weights): |
| print(f"{feature}: {weight:.4f}") |
|
|
| print(f"\nLearned Bias (Intercept): {bias:.4f}") |
|
|
| y_pred = model.predict(X) |
| mse = mean_squared_error(y, y_pred) |
| print(f"\nMean Squared Error on Training Data: {mse:.4f}") |
