def test_transform_unseen(self, X, y, handle_unseen, expected):
enc = WeightOfEvidenceEncoder(cols=['cat'], handle_unseen=handle_unseen)
X = pd.DataFrame(X, columns=['cat'])
enc.fit(X, pd.Series(y))
X.iloc[0, 0] = 'foo'
result = enc.transform(X)
assert_array_almost_equal(result, pd.DataFrame(expected), decimal=3)
def woe_encoding(cls, X, Y=None, encoder=None):
cols = ['some_id', 'other_id']
if encoder is None:
encoder = WeightOfEvidenceEncoder(cols=cols, min_samples=5)
encoder.fit(X, Y)
encoded = encoder.transform(X).rename(
columns={c: 'woe_enc_{}'.format(c)
for c in cols})
return pd.concat([X[cols], encoded], axis=1), encoder
def test_transform_error(self, X, y, expected):
enc = WeightOfEvidenceEncoder(cols=['cat'], handle_unseen='error')
X = pd.DataFrame(X, columns=['cat'])
enc.fit(X, pd.Series(y))
X.iloc[0, 0] = 'foo'
assert_raises(ValueError, enc.transform, X)