def feature_scaling(x_train_input, x_test_input):
print("\n*****FUNCTION feature_scaling*****")
global SCALER
x_train = x_train_input.copy(deep=True)
x_test = x_test_input.copy(deep=True)
SCALER = SklearnTransformerWrapper(transformer=MinMaxScaler(),
variables=['Tenure', 'MonthlyCharges'])
# fit,transform x_train
SCALER.fit(x_train)
x_train = SCALER.transform(x_train)
# transform x_test
x_test = SCALER.transform(x_test)
return (x_train, x_test)
def test_error_when_inverse_transform_not_implemented(transformer):
X = fetch_california_housing(as_frame=True).frame
y = X["MedHouseVal"]
X = X.drop(["MedHouseVal"], axis=1)
tr_wrap = SklearnTransformerWrapper(transformer=transformer)
tr_wrap.fit(X, y)
X_tr = tr_wrap.transform(X)
with pytest.raises(NotImplementedError):
tr_wrap.inverse_transform(X_tr)
def test_selectKBest_all_variables():
X, y = load_boston(return_X_y=True)
X = pd.DataFrame(X)
selector = SklearnTransformerWrapper(transformer=SelectKBest(f_regression,
k=5), )
selector.fit(X, y)
X_train_t = selector.transform(X)
pd.testing.assert_frame_equal(X_train_t, X[[2, 5, 9, 10, 12]])
def test_selectFromModel_all_variables():
X, y = load_boston(return_X_y=True)
X = pd.DataFrame(X)
lasso = Lasso(alpha=10, random_state=0)
sfm = SelectFromModel(lasso, prefit=False)
selector = SklearnTransformerWrapper(transformer=sfm)
selector.fit(X, y)
X_train_t = selector.transform(X)
pd.testing.assert_frame_equal(X_train_t, X[[1, 9, 11, 12]])