| import pandas as pd | |
| import pickle | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.linear_model import LinearRegression | |
| # Load dataset | |
| df = pd.read_csv("data.csv") | |
| # Ensure required columns exist | |
| REQUIRED_COLUMNS = {"sqft_living", "price"} | |
| if not REQUIRED_COLUMNS.issubset(df.columns): | |
| raise ValueError(f"Dataset is missing required columns: {REQUIRED_COLUMNS - set(df.columns)}") | |
| # Features & Target | |
| X = df[["sqft_living"]] # Input: Square footage | |
| y = df["price"] # Output: House price | |
| # Split data into training and test sets | |
| X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) | |
| # Train model | |
| model = LinearRegression() | |
| model.fit(X_train, y_train) | |
| # Save model to 'model.pkl' using built-in pickle | |
| with open("model.pkl", "wb") as file: | |
| pickle.dump(model, file) | |
| print("✅ Model training complete. Saved as 'model.pkl'.") | |