def test_transform_feature_names_iris(transformer, expected, iris_train):
X, y, _, _ = iris_train
transformer.fit(X, y)
# Test in_names being provided
res = transform_feature_names(transformer,
['<NAME0>', '<NAME1>', '<NAME2>', '<NAME3>'])
assert res == expected
# Test in_names being None
expected_default_names = [
re.sub('<NAME([0-9]+)>', r'x\1', name) for name in expected
]
assert transform_feature_names(transformer, None) == expected_default_names
def _col_tfm_names(transformer, in_names=None):
if in_names is None:
from eli5.sklearn.utils import get_feature_names
# generate default feature names
in_names = get_feature_names(transformer,
num_features=transformer._n_features)
# return a list of strings derived from in_names
feature_names = []
for name, trans, column, _ in transformer._iter(fitted=True):
if hasattr(transformer, '_df_columns'):
if ((not isinstance(column, slice))
and all(isinstance(col, str) for col in column)):
names = column
else:
names = transformer._df_columns[column]
else:
indices = np.arange(transformer._n_features)
names = ['x%d' % i for i in indices[column]]
# erm, want to be able to override with in_names maybe???
if trans == 'drop' or (hasattr(column, '__len__') and not len(column)):
continue
if trans == 'passthrough':
feature_names.extend(names)
continue
feature_names.extend([
name + "__" + f
for f in transform_feature_names(trans, in_names=names)
])
return feature_names