def test_transform_target_regressor_multi_to_single(): X = friedman[0] y = np.transpose([friedman[1], (friedman[1] ** 2 + 1)]) def func(y): out = np.sqrt(y[:, 0] ** 2 + y[:, 1] ** 2) return out[:, np.newaxis] def inverse_func(y): return y tt = TransformedTargetRegressor(func=func, inverse_func=inverse_func, check_inverse=False) tt.fit(X, y) y_pred_2d_func = tt.predict(X) assert y_pred_2d_func.shape == (100, 1) # force that the function only return a 1D array def func(y): return np.sqrt(y[:, 0] ** 2 + y[:, 1] ** 2) tt = TransformedTargetRegressor(func=func, inverse_func=inverse_func, check_inverse=False) tt.fit(X, y) y_pred_1d_func = tt.predict(X) assert y_pred_1d_func.shape == (100, 1) assert_allclose(y_pred_1d_func, y_pred_2d_func)
def test_transform_target_regressor_multi_to_single(): X = friedman[0] y = np.transpose([friedman[1], (friedman[1]**2 + 1)]) def func(y): out = np.sqrt(y[:, 0]**2 + y[:, 1]**2) return out[:, np.newaxis] def inverse_func(y): return y tt = TransformedTargetRegressor(func=func, inverse_func=inverse_func, check_inverse=False) tt.fit(X, y) y_pred_2d_func = tt.predict(X) assert y_pred_2d_func.shape == (100, 1) # force that the function only return a 1D array def func(y): return np.sqrt(y[:, 0]**2 + y[:, 1]**2) tt = TransformedTargetRegressor(func=func, inverse_func=inverse_func, check_inverse=False) tt.fit(X, y) y_pred_1d_func = tt.predict(X) assert y_pred_1d_func.shape == (100, 1) assert_allclose(y_pred_1d_func, y_pred_2d_func)
def test_transform_target_regressor_ensure_y_array(): # check that the target ``y`` passed to the transformer will always be a # numpy array. Similarly, if ``X`` is passed as a list, we check that the # predictor receive as it is. X, y = friedman tt = TransformedTargetRegressor(transformer=DummyCheckerArrayTransformer(), regressor=DummyCheckerListRegressor(), check_inverse=False) tt.fit(X.tolist(), y.tolist()) tt.predict(X.tolist()) assert_raises(AssertionError, tt.fit, X, y.tolist()) assert_raises(AssertionError, tt.predict, X)
def test_transform_target_regressor_ensure_y_array(): # check that the target ``y`` passed to the transformer will always be a # numpy array. Similarly, if ``X`` is passed as a list, we check that the # predictor receive as it is. X, y = friedman tt = TransformedTargetRegressor(transformer=DummyCheckerArrayTransformer(), regressor=DummyCheckerListRegressor(), check_inverse=False) tt.fit(X.tolist(), y.tolist()) tt.predict(X.tolist()) assert_raises(AssertionError, tt.fit, X, y.tolist()) assert_raises(AssertionError, tt.predict, X)
def test_transform_target_regressor_2d_transformer(X, y): # Check consistency with transformer accepting only 2D array and a 1D/2D y # array. transformer = StandardScaler() regr = TransformedTargetRegressor(regressor=LinearRegression(), transformer=transformer) y_pred = regr.fit(X, y).predict(X) assert y.shape == y_pred.shape # consistency forward transform if y.ndim == 1: # create a 2D array and squeeze results y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze() else: y_tran = regr.transformer_.transform(y) _check_standard_scaled(y, y_tran) assert y.shape == y_pred.shape # consistency inverse transform assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze()) # consistency of the regressor lr = LinearRegression() transformer2 = clone(transformer) if y.ndim == 1: # create a 2D array and squeeze results lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze()) else: lr.fit(X, transformer2.fit_transform(y)) y_lr_pred = lr.predict(X) assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred)) assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_1d_transformer(X, y): # All transformer in scikit-learn expect 2D data. FunctionTransformer with # validate=False lift this constraint without checking that the input is a # 2D vector. We check the consistency of the data shape using a 1D and 2D y # array. transformer = FunctionTransformer(func=lambda x: x + 1, inverse_func=lambda x: x - 1, validate=False) regr = TransformedTargetRegressor(regressor=LinearRegression(), transformer=transformer) y_pred = regr.fit(X, y).predict(X) assert y.shape == y_pred.shape # consistency forward transform y_tran = regr.transformer_.transform(y) _check_shifted_by_one(y, y_tran) assert y.shape == y_pred.shape # consistency inverse transform assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze()) # consistency of the regressor lr = LinearRegression() transformer2 = clone(transformer) lr.fit(X, transformer2.fit_transform(y)) y_lr_pred = lr.predict(X) assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred)) assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_2d_transformer(X, y): # Check consistency with transformer accepting only 2D array and a 1D/2D y # array. transformer = StandardScaler() regr = TransformedTargetRegressor(regressor=LinearRegression(), transformer=transformer) y_pred = regr.fit(X, y).predict(X) assert y.shape == y_pred.shape # consistency forward transform if y.ndim == 1: # create a 2D array and squeeze results y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze() else: y_tran = regr.transformer_.transform(y) _check_standard_scaled(y, y_tran) assert y.shape == y_pred.shape # consistency inverse transform assert_allclose(y, regr.transformer_.inverse_transform( y_tran).squeeze()) # consistency of the regressor lr = LinearRegression() transformer2 = clone(transformer) if y.ndim == 1: # create a 2D array and squeeze results lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze()) else: lr.fit(X, transformer2.fit_transform(y)) y_lr_pred = lr.predict(X) assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred)) assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_1d_transformer(X, y): # All transformer in scikit-learn expect 2D data. FunctionTransformer with # validate=False lift this constraint without checking that the input is a # 2D vector. We check the consistency of the data shape using a 1D and 2D y # array. transformer = FunctionTransformer(func=lambda x: x + 1, inverse_func=lambda x: x - 1, validate=False) regr = TransformedTargetRegressor(regressor=LinearRegression(), transformer=transformer) y_pred = regr.fit(X, y).predict(X) assert y.shape == y_pred.shape # consistency forward transform y_tran = regr.transformer_.transform(y) _check_shifted_by_one(y, y_tran) assert y.shape == y_pred.shape # consistency inverse transform assert_allclose(y, regr.transformer_.inverse_transform( y_tran).squeeze()) # consistency of the regressor lr = LinearRegression() transformer2 = clone(transformer) lr.fit(X, transformer2.fit_transform(y)) y_lr_pred = lr.predict(X) assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred)) assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_functions_multioutput(): X = friedman[0] y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T regr = TransformedTargetRegressor(regressor=LinearRegression(), func=np.log, inverse_func=np.exp) y_pred = regr.fit(X, y).predict(X) # check the transformer output y_tran = regr.transformer_.transform(y) assert_allclose(np.log(y), y_tran) assert_allclose(y, regr.transformer_.inverse_transform(y_tran)) assert y.shape == y_pred.shape assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X))) # check the regressor output lr = LinearRegression().fit(X, regr.func(y)) assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_functions(): X, y = friedman regr = TransformedTargetRegressor(regressor=LinearRegression(), func=np.log, inverse_func=np.exp) y_pred = regr.fit(X, y).predict(X) # check the transformer output y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze() assert_allclose(np.log(y), y_tran) assert_allclose(y, regr.transformer_.inverse_transform( y_tran.reshape(-1, 1)).squeeze()) assert y.shape == y_pred.shape assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X))) # check the regressor output lr = LinearRegression().fit(X, regr.func(y)) assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_functions_multioutput(): X = friedman[0] y = np.vstack((friedman[1], friedman[1]**2 + 1)).T regr = TransformedTargetRegressor(regressor=LinearRegression(), func=np.log, inverse_func=np.exp) y_pred = regr.fit(X, y).predict(X) # check the transformer output y_tran = regr.transformer_.transform(y) assert_allclose(np.log(y), y_tran) assert_allclose(y, regr.transformer_.inverse_transform(y_tran)) assert y.shape == y_pred.shape assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X))) # check the regressor output lr = LinearRegression().fit(X, regr.func(y)) assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_functions(): X, y = friedman regr = TransformedTargetRegressor(regressor=LinearRegression(), func=np.log, inverse_func=np.exp) y_pred = regr.fit(X, y).predict(X) # check the transformer output y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze() assert_allclose(np.log(y), y_tran) assert_allclose( y, regr.transformer_.inverse_transform(y_tran.reshape(-1, 1)).squeeze()) assert y.shape == y_pred.shape assert_allclose(y_pred, regr.inverse_func(regr.regressor_.predict(X))) # check the regressor output lr = LinearRegression().fit(X, regr.func(y)) assert_allclose(regr.regressor_.coef_.ravel(), lr.coef_.ravel())
def test_transform_target_regressor_2d_transformer_multioutput(): # Check consistency with transformer accepting only 2D array and a 2D y # array. X = friedman[0] y = np.vstack((friedman[1], friedman[1]**2 + 1)).T transformer = StandardScaler() regr = TransformedTargetRegressor(regressor=LinearRegression(), transformer=transformer) y_pred = regr.fit(X, y).predict(X) assert y.shape == y_pred.shape # consistency forward transform y_tran = regr.transformer_.transform(y) _check_standard_scaled(y, y_tran) assert y.shape == y_pred.shape # consistency inverse transform assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze()) # consistency of the regressor lr = LinearRegression() transformer2 = clone(transformer) lr.fit(X, transformer2.fit_transform(y)) y_lr_pred = lr.predict(X) assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred)) assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_2d_transformer_multioutput(): # Check consistency with transformer accepting only 2D array and a 2D y # array. X = friedman[0] y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T transformer = StandardScaler() regr = TransformedTargetRegressor(regressor=LinearRegression(), transformer=transformer) y_pred = regr.fit(X, y).predict(X) assert y.shape == y_pred.shape # consistency forward transform y_tran = regr.transformer_.transform(y) _check_standard_scaled(y, y_tran) assert y.shape == y_pred.shape # consistency inverse transform assert_allclose(y, regr.transformer_.inverse_transform( y_tran).squeeze()) # consistency of the regressor lr = LinearRegression() transformer2 = clone(transformer) lr.fit(X, transformer2.fit_transform(y)) y_lr_pred = lr.predict(X) assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred)) assert_allclose(regr.regressor_.coef_, lr.coef_)
ax0.scatter(y_test, y_pred) ax0.plot([0, 2000], [0, 2000], '--k') ax0.set_ylabel('Target predicted') ax0.set_xlabel('True Target') ax0.set_title('Ridge regression \n without target transformation') ax0.text( 100, 1750, r'$R^2$=%.2f, MAE=%.2f' % (r2_score(y_test, y_pred), median_absolute_error(y_test, y_pred))) ax0.set_xlim([0, 2000]) ax0.set_ylim([0, 2000]) regr_trans = TransformedTargetRegressor(regressor=RidgeCV(), func=np.log1p, inverse_func=np.expm1) regr_trans.fit(X_train, y_train) y_pred = regr_trans.predict(X_test) ax1.scatter(y_test, y_pred) ax1.plot([0, 2000], [0, 2000], '--k') ax1.set_ylabel('Target predicted') ax1.set_xlabel('True Target') ax1.set_title('Ridge regression \n with target transformation') ax1.text( 100, 1750, r'$R^2$=%.2f, MAE=%.2f' % (r2_score(y_test, y_pred), median_absolute_error(y_test, y_pred))) ax1.set_xlim([0, 2000]) ax1.set_ylim([0, 2000]) f.suptitle("Synthetic data", y=0.035) f.tight_layout(rect=[0.05, 0.05, 0.95, 0.95])
y_pred = regr.predict(X_test) ax0.scatter(y_test, y_pred) ax0.plot([0, 2000], [0, 2000], '--k') ax0.set_ylabel('Target predicted') ax0.set_xlabel('True Target') ax0.set_title('Ridge regression \n without target transformation') ax0.text(100, 1750, r'$R^2$=%.2f, MAE=%.2f' % ( r2_score(y_test, y_pred), median_absolute_error(y_test, y_pred))) ax0.set_xlim([0, 2000]) ax0.set_ylim([0, 2000]) regr_trans = TransformedTargetRegressor(regressor=RidgeCV(), func=np.log1p, inverse_func=np.expm1) regr_trans.fit(X_train, y_train) y_pred = regr_trans.predict(X_test) ax1.scatter(y_test, y_pred) ax1.plot([0, 2000], [0, 2000], '--k') ax1.set_ylabel('Target predicted') ax1.set_xlabel('True Target') ax1.set_title('Ridge regression \n with target transformation') ax1.text(100, 1750, r'$R^2$=%.2f, MAE=%.2f' % ( r2_score(y_test, y_pred), median_absolute_error(y_test, y_pred))) ax1.set_xlim([0, 2000]) ax1.set_ylim([0, 2000]) f.suptitle("Synthetic data", y=0.035) f.tight_layout(rect=[0.05, 0.05, 0.95, 0.95])