def test_non_fitted_error(df_vartypes):
with pytest.raises(NotFittedError):
transformer = YeoJohnsonTransformer()
transformer.transform(df_vartypes)
def test_transform_raises_error_if_na_in_df(df_vartypes, df_na):
# test case 3: when dataset contains na, transform method
with pytest.raises(ValueError):
transformer = YeoJohnsonTransformer()
transformer.fit(df_vartypes)
transformer.transform(df_na[["Name", "City", "Age", "Marks", "dob"]])
verbose=1,
patience=10,
min_lr=0.01)
early_stop = EarlyStopping(monitor='val_loss',
mode='min',
min_delta=0,
verbose=1,
patience=20)
pump_pipeline = Pipeline(
steps=[("feature_to_keeper",
pp.FeatureKeeper(variables_to_keep=config.VARIABLES_TO_KEEP)),
("missing_imputer",
pp.MissingImputer(numerical_variables=config.NUMERICAL_VARIABLES)),
("yeoJohnson",
YeoJohnsonTransformer(variables=config.YEO_JHONSON_VARIABLES)),
("discretization",
EqualWidthDiscretiser(bins=5, variables=config.NUMERICAL_VARIABLES)
),
("categorical_grouper",
pp.CategoricalGrouping(config_dict=config.VARIABLES_TO_GROUP)),
("rareCategories_grouper",
pp.RareCategoriesGrouping(threshold=config.VARIABLES_THRESHOLD)),
("one_hot_encoder",
OneHotEncoder(variables=config.REAL_CATEGORICAL_VARIABLES,
drop_last=False)), ("scaler", MinMaxScaler()),
("model",
KerasClassifier(build_fn=create_model,
epochs=1,
validation_split=0.2,
batch_size=256,
def test_fit_raises_error_if_na_in_df(df_na):
# test case 2: when dataset contains na, fit method
with pytest.raises(ValueError):
transformer = YeoJohnsonTransformer()
transformer.fit(df_na)
from tests.estimator_checks.estimator_checks import check_feature_engine_estimator
from feature_engine.transformation import (
BoxCoxTransformer,
LogCpTransformer,
ArcsinTransformer,
LogTransformer,
PowerTransformer,
ReciprocalTransformer,
YeoJohnsonTransformer,
)
_estimators = [
BoxCoxTransformer(),
LogTransformer(),
LogCpTransformer(),
ArcsinTransformer(),
PowerTransformer(),
ReciprocalTransformer(),
YeoJohnsonTransformer(),
]
@pytest.mark.parametrize("estimator", _estimators)
def test_check_estimator_from_sklearn(estimator):
return check_estimator(estimator)
@pytest.mark.parametrize("estimator", _estimators[4:])
def test_check_estimator_from_feature_engine(estimator):
return check_feature_engine_estimator(estimator)