def check_preprocessing(self):
"""
Check that all transformation of the preprocessing are supported.
"""
return check_preprocessing(self.preprocessing)
def test_check_preprocessing_1(self):
"""
Test check preprocessing on multiple preprocessing
"""
train = pd.DataFrame({'Onehot1': ['A', 'B', 'A', 'B'], 'Onehot2': ['C', 'D', 'C', 'D'],
'Binary1': ['E', 'F', 'E', 'F'], 'Binary2': ['G', 'H', 'G', 'H'],
'Ordinal1': ['I', 'J', 'I', 'J'], 'Ordinal2': ['K', 'L', 'K', 'L'],
'BaseN1': ['M', 'N', 'M', 'N'], 'BaseN2': ['O', 'P', 'O', 'P'],
'Target1': ['Q', 'R', 'Q', 'R'], 'Target2': ['S', 'T', 'S', 'T'],
'other': ['other', np.nan, 'other', 'other']})
y = pd.DataFrame(data=[0, 1, 0, 0], columns=['y'])
enc_onehot = ce.OneHotEncoder(cols=['Onehot1', 'Onehot2']).fit(train)
train_onehot = enc_onehot.transform(train)
enc_binary = ce.BinaryEncoder(cols=['Binary1', 'Binary2']).fit(train_onehot)
train_binary = enc_binary.transform(train_onehot)
enc_ordinal = ce.OrdinalEncoder(cols=['Ordinal1', 'Ordinal2']).fit(train_binary)
train_ordinal = enc_ordinal.transform(train_binary)
enc_basen = ce.BaseNEncoder(cols=['BaseN1', 'BaseN2']).fit(train_ordinal)
train_basen = enc_basen.transform(train_ordinal)
enc_target = ce.TargetEncoder(cols=['Target1', 'Target2']).fit(train_basen, y)
input_dict1 = dict()
input_dict1['col'] = 'Onehot2'
input_dict1['mapping'] = pd.Series(data=['C', 'D', np.nan], index=['C', 'D', 'missing'])
input_dict1['data_type'] = 'object'
input_dict2 = dict()
input_dict2['col'] = 'Binary2'
input_dict2['mapping'] = pd.Series(data=['G', 'H', np.nan], index=['G', 'H', 'missing'])
input_dict2['data_type'] = 'object'
input_dict = dict()
input_dict['col'] = 'state'
input_dict['mapping'] = pd.Series(data=['US', 'FR-1', 'FR-2'], index=['US', 'FR', 'FR'])
input_dict['data_type'] = 'object'
input_dict3 = dict()
input_dict3['col'] = 'Ordinal2'
input_dict3['mapping'] = pd.Series(data=['K', 'L', np.nan], index=['K', 'L', 'missing'])
input_dict3['data_type'] = 'object'
list_dict = [input_dict2, input_dict3]
y = pd.DataFrame(data=[0, 1], columns=['y'])
train = pd.DataFrame({'city': ['chicago', 'paris'],
'state': ['US', 'FR'],
'other': ['A', 'B']})
enc = ColumnTransformer(
transformers=[
('onehot', skp.OneHotEncoder(), ['city', 'state'])
],
remainder='drop')
enc.fit(train, y)
wrong_prepro = skp.OneHotEncoder().fit(train, y)
check_preprocessing([enc_onehot, enc_binary, enc_ordinal, enc_basen, enc_target, input_dict1,
list_dict])
for preprocessing in [enc_onehot, enc_binary, enc_ordinal, enc_basen, enc_target]:
check_preprocessing(preprocessing)
check_preprocessing(input_dict2)
check_preprocessing(enc)
check_preprocessing(None)
with self.assertRaises(Exception):
check_preprocessing(wrong_prepro)