()
| 11 | |
| 12 | |
| 13 | def regression(): |
| 14 | # Generate a random regression problem |
| 15 | X, y = make_regression( |
| 16 | n_samples=500, |
| 17 | n_features=5, |
| 18 | n_informative=5, |
| 19 | n_targets=1, |
| 20 | noise=0.05, |
| 21 | random_state=1111, |
| 22 | bias=0.5, |
| 23 | ) |
| 24 | X_train, X_test, y_train, y_test = train_test_split( |
| 25 | X, y, test_size=0.25, random_state=1111 |
| 26 | ) |
| 27 | |
| 28 | model = knn.KNNRegressor(k=5, distance_func=distance.euclidean) |
| 29 | model.fit(X_train, y_train) |
| 30 | predictions = model.predict(X_test) |
| 31 | print("regression mse", mean_squared_error(y_test, predictions)) |
| 32 | |
| 33 | |
| 34 | def classification(): |
no test coverage detected