def test_check_preprocessing_options_1(self):
"""
Unit test 1 for check_preprocessing_options
"""
y = pd.DataFrame(data=[0, 1], columns=['y'])
train = pd.DataFrame({
'num1': [0, 1],
'num2': [0, 2],
'other': ['A', 'B']
})
enc = ColumnTransformer(transformers=[
('power', skp.QuantileTransformer(n_quantiles=2), ['num1', 'num2'])
],
remainder='drop')
enc.fit(train, y)
with self.assertRaises(ValueError):
check_preprocessing_options(enc)
enc = ColumnTransformer(transformers=[
('power', skp.QuantileTransformer(n_quantiles=2), ['num1', 'num2'])
],
remainder='passthrough')
enc.fit(train, y)
check_preprocessing_options(enc)
def test_check_preprocessing_options_1(self):
"""
Unit test check_preprocessing_options 1
"""
df = pd.DataFrame(range(0, 5), columns=['id'])
df['y'] = df['id'].apply(lambda x: 1 if x < 2 else 0)
df['x1'] = np.random.randint(1, 123, df.shape[0])
df = df.set_index('id')
df['x2'] = ["S", "M", "S", "D", "M"]
df['x3'] = np.random.randint(1, 123, df.shape[0])
df['x4'] = ["S", "M", "S", "D", "M"]
features_dict = {
"x1": "age",
"x2": "weight",
"x3": 'test',
'x4': "test2"
}
columns_dict = {0: "x1", 1: "x2", 2: "x3", 3: "x4"}
encoder = ColumnTransformer(transformers=[
('onehot_ce_1', ce.OneHotEncoder(), ['x2']),
('onehot_ce_2', ce.OneHotEncoder(), ['x4'])
],
remainder='drop')
encoder_fitted = encoder.fit(df[["x1", "x2", "x3", 'x4']])
encoder_2 = ColumnTransformer(transformers=[
('onehot_ce_1', ce.OneHotEncoder(), ['x2']),
('onehot_ce_2', ce.OneHotEncoder(), ['x4'])
],
remainder='passthrough')
encoder_fitted_2 = encoder_2.fit(df[["x1", "x2", "x3", 'x4']])
expected_dict = {
'features_to_drop': ['x1', 'x3'],
'features_dict_op': {
'x2': 'weight',
'x4': 'test2'
},
'columns_dict_op': {
0: 'x2',
1: 'x4'
}
}
expected_dict_2 = None
drop_option_1 = check_preprocessing_options(columns_dict,
features_dict,
encoder_fitted,
[encoder_fitted])
drop_option_2 = check_preprocessing_options(columns_dict,
features_dict,
encoder_fitted_2,
[encoder_fitted_2])
assert drop_option_1 == expected_dict
assert drop_option_2 == expected_dict_2
def __init__(
self,
features_dict,
model,
columns_dict,
explainer,
features_types,
label_dict=None,
preprocessing=None,
postprocessing=None,
mask_params={
"features_to_hide": None,
"threshold": None,
"positive": None,
"max_contrib": None
}):
params_dict = [
features_dict, features_types, label_dict, columns_dict,
postprocessing
]
for params in params_dict:
if params is not None and isinstance(params, dict) == False:
raise ValueError("""
{0} must be a dict.
""".format(str(params)))
self.model = model
self._case, self._classes = self.check_model()
self.explainer = self.check_explainer(explainer)
check_preprocessing_options(preprocessing)
self.preprocessing = preprocessing
self.check_preprocessing()
self.features_dict = features_dict
self.features_types = features_types
self.label_dict = label_dict
self.check_label_dict()
self.columns_dict = columns_dict
self.mask_params = mask_params
self.check_mask_params()
self.postprocessing = postprocessing
check_consistency_model_features(self.features_dict, self.model,
self.columns_dict,
self.features_types, self.mask_params,
self.preprocessing,
self.postprocessing)
check_consistency_model_label(self.columns_dict, self.label_dict)