def test_one_hot_encoder_drop_manual():
cats_to_drop = ['def', 12, 3, 56]
enc = OneHotEncoder(drop=cats_to_drop)
X = [['abc', 12, 2, 55], ['def', 12, 1, 55], ['def', 12, 3, 56]]
trans = enc.fit_transform(X).toarray()
exp = [[1, 0, 1, 1], [0, 1, 0, 1], [0, 0, 0, 0]]
assert_array_equal(trans, exp)
dropped_cats = [
cat[feature] for cat, feature in zip(enc.categories_, enc.drop_idx_)
]
assert_array_equal(dropped_cats, cats_to_drop)
assert_array_equal(np.array(X, dtype=object), enc.inverse_transform(trans))
def test_one_hot_encoder_inverse(sparse_, drop):
X = [['abc', 2, 55], ['def', 1, 55], ['abc', 3, 55]]
enc = OneHotEncoder(sparse=sparse_, drop=drop)
X_tr = enc.fit_transform(X)
exp = np.array(X, dtype=object)
assert_array_equal(enc.inverse_transform(X_tr), exp)
X = [[2, 55], [1, 55], [3, 55]]
enc = OneHotEncoder(sparse=sparse_, categories='auto', drop=drop)
X_tr = enc.fit_transform(X)
exp = np.array(X)
assert_array_equal(enc.inverse_transform(X_tr), exp)
if drop is None:
# with unknown categories
# drop is incompatible with handle_unknown=ignore
X = [['abc', 2, 55], ['def', 1, 55], ['abc', 3, 55]]
enc = OneHotEncoder(sparse=sparse_,
handle_unknown='ignore',
categories=[['abc', 'def'], [1, 2], [54, 55, 56]])
X_tr = enc.fit_transform(X)
exp = np.array(X, dtype=object)
exp[2, 1] = None
assert_array_equal(enc.inverse_transform(X_tr), exp)
# with an otherwise numerical output, still object if unknown
X = [[2, 55], [1, 55], [3, 55]]
enc = OneHotEncoder(sparse=sparse_,
categories=[[1, 2], [54, 56]],
handle_unknown='ignore')
X_tr = enc.fit_transform(X)
exp = np.array(X, dtype=object)
exp[2, 0] = None
exp[:, 1] = None
assert_array_equal(enc.inverse_transform(X_tr), exp)
# incorrect shape raises
X_tr = np.array([[0, 1, 1], [1, 0, 1]])
msg = re.escape('Shape of the passed X data is not correct')
with pytest.raises(ValueError, match=msg):
enc.inverse_transform(X_tr)
