def test_one_hot_encoder_feature_names():
enc = OneHotEncoder()
X = [['Male', 1, 'girl', 2, 3], ['Female', 41, 'girl', 1, 10],
['Male', 51, 'boy', 12, 3], ['Male', 91, 'girl', 21, 30]]
enc.fit(X)
feature_names = enc.get_feature_names()
assert isinstance(feature_names, np.ndarray)
assert_array_equal([
'x0_Female', 'x0_Male', 'x1_1', 'x1_41', 'x1_51', 'x1_91', 'x2_boy',
'x2_girl', 'x3_1', 'x3_2', 'x3_12', 'x3_21', 'x4_3', 'x4_10', 'x4_30'
], feature_names)
feature_names2 = enc.get_feature_names(
['one', 'two', 'three', 'four', 'five'])
assert_array_equal([
'one_Female', 'one_Male', 'two_1', 'two_41', 'two_51', 'two_91',
'three_boy', 'three_girl', 'four_1', 'four_2', 'four_12', 'four_21',
'five_3', 'five_10', 'five_30'
], feature_names2)
with pytest.raises(ValueError, match="input_features should have length"):
enc.get_feature_names(['one', 'two'])
def test_one_hot_encoder_feature_names_unicode():
enc = OneHotEncoder()
X = np.array([['c❤t1', 'dat2']], dtype=object).T
enc.fit(X)
feature_names = enc.get_feature_names()
assert_array_equal(['x0_c❤t1', 'x0_dat2'], feature_names)
feature_names = enc.get_feature_names(input_features=['n👍me'])
assert_array_equal(['n👍me_c❤t1', 'n👍me_dat2'], feature_names)
def test_one_hot_encoder_feature_names_drop(drop, expected_names):
X = [['c', 2, 'a'], ['b', 2, 'b']]
ohe = OneHotEncoder(drop=drop)
ohe.fit(X)
feature_names = ohe.get_feature_names()
assert isinstance(feature_names, np.ndarray)
assert_array_equal(expected_names, feature_names)
def test_one_hot_encoder_diff_n_features():
X = np.array([[0, 2, 1], [1, 0, 3], [1, 0, 2]])
X2 = np.array([[1, 0]])
enc = OneHotEncoder()
enc.fit(X)
err_msg = ("The number of features in X is different to the number of "
"features of the fitted data.")
with pytest.raises(ValueError, match=err_msg):
enc.transform(X2)
def test_one_hot_encoder_categories(X, cat_exp, cat_dtype):
# order of categories should not depend on order of samples
for Xi in [X, X[::-1]]:
enc = OneHotEncoder(categories='auto')
enc.fit(Xi)
# assert enc.categories == 'auto'
assert isinstance(enc.categories_, list)
for res, exp in zip(enc.categories_, cat_exp):
assert res.tolist() == exp
assert np.issubdtype(res.dtype, cat_dtype)
def test_one_hot_encoder_dtype(input_dtype, output_dtype):
X = np.asarray([[0, 1]], dtype=input_dtype).T
X_expected = np.asarray([[1, 0], [0, 1]], dtype=output_dtype)
oh = OneHotEncoder(categories='auto', dtype=output_dtype)
assert_array_equal(oh.fit_transform(X).toarray(), X_expected)
assert_array_equal(oh.fit(X).transform(X).toarray(), X_expected)
oh = OneHotEncoder(categories='auto', dtype=output_dtype, sparse=False)
assert_array_equal(oh.fit_transform(X), X_expected)
assert_array_equal(oh.fit(X).transform(X), X_expected)
def test_one_hot_encoder_dtype_pandas(output_dtype):
pd = pytest.importorskip('pandas')
X_df = pd.DataFrame({'A': ['a', 'b'], 'B': [1, 2]})
X_expected = np.array([[1, 0, 1, 0], [0, 1, 0, 1]], dtype=output_dtype)
oh = OneHotEncoder(dtype=output_dtype)
assert_array_equal(oh.fit_transform(X_df).toarray(), X_expected)
assert_array_equal(oh.fit(X_df).transform(X_df).toarray(), X_expected)
oh = OneHotEncoder(dtype=output_dtype, sparse=False)
assert_array_equal(oh.fit_transform(X_df), X_expected)
assert_array_equal(oh.fit(X_df).transform(X_df), X_expected)
def test_one_hot_encoder_handle_unknown_strings():
X = np.array(['11111111', '22', '333', '4444']).reshape((-1, 1))
X2 = np.array(['55555', '22']).reshape((-1, 1))
# Non Regression test for the issue #12470
# Test the ignore option, when categories are numpy string dtype
# particularly when the known category strings are larger
# than the unknown category strings
oh = OneHotEncoder(handle_unknown='ignore')
oh.fit(X)
X2_passed = X2.copy()
assert_array_equal(
oh.transform(X2_passed).toarray(),
np.array([[0., 0., 0., 0.], [0., 1., 0., 0.]]))
# ensure transformed data was not modified in place
assert_array_equal(X2, X2_passed)
def test_categories(density, drop):
ohe_base = OneHotEncoder(sparse=density)
ohe_test = OneHotEncoder(sparse=density, drop=drop)
X = [['c', 1, 'a'], ['a', 2, 'b']]
ohe_base.fit(X)
ohe_test.fit(X)
assert_array_equal(ohe_base.categories_, ohe_test.categories_)
if drop == 'first':
assert_array_equal(ohe_test.drop_idx_, 0)
else:
for drop_cat, drop_idx, cat_list in zip(drop, ohe_test.drop_idx_,
ohe_test.categories_):
assert cat_list[drop_idx] == drop_cat
assert isinstance(ohe_test.drop_idx_, np.ndarray)
assert ohe_test.drop_idx_.dtype == np.int_
def test_encoder_dtypes_pandas():
# check dtype (similar to test_categorical_encoder_dtypes for dataframes)
pd = pytest.importorskip('pandas')
enc = OneHotEncoder(categories='auto')
exp = np.array([[1., 0., 1., 0., 1., 0.], [0., 1., 0., 1., 0., 1.]],
dtype='float64')
X = pd.DataFrame({'A': [1, 2], 'B': [3, 4], 'C': [5, 6]}, dtype='int64')
enc.fit(X)
assert all([enc.categories_[i].dtype == 'int64' for i in range(2)])
assert_array_equal(enc.transform(X).toarray(), exp)
X = pd.DataFrame({'A': [1, 2], 'B': ['a', 'b'], 'C': [3., 4.]})
X_type = [X['A'].dtype, X['B'].dtype, X['C'].dtype]
enc.fit(X)
assert all([enc.categories_[i].dtype == X_type[i] for i in range(3)])
assert_array_equal(enc.transform(X).toarray(), exp)
def test_one_hot_encoder_specified_categories(X, X2, cats, cat_dtype):
enc = OneHotEncoder(categories=cats)
exp = np.array([[1., 0., 0.], [0., 1., 0.]])
assert_array_equal(enc.fit_transform(X).toarray(), exp)
assert list(enc.categories[0]) == list(cats[0])
assert enc.categories_[0].tolist() == list(cats[0])
# manually specified categories should have same dtype as
# the data when coerced from lists
assert enc.categories_[0].dtype == cat_dtype
# when specifying categories manually, unknown categories should already
# raise when fitting
enc = OneHotEncoder(categories=cats)
with pytest.raises(ValueError, match="Found unknown categories"):
enc.fit(X2)
enc = OneHotEncoder(categories=cats, handle_unknown='ignore')
exp = np.array([[1., 0., 0.], [0., 0., 0.]])
assert_array_equal(enc.fit(X2).transform(X2).toarray(), exp)
def test_one_hot_encoder_handle_unknown():
X = np.array([[0, 2, 1], [1, 0, 3], [1, 0, 2]])
X2 = np.array([[4, 1, 1]])
# Test that one hot encoder raises error for unknown features
# present during transform.
oh = OneHotEncoder(handle_unknown='error')
oh.fit(X)
with pytest.raises(ValueError, match='Found unknown categories'):
oh.transform(X2)
# Test the ignore option, ignores unknown features (giving all 0's)
oh = OneHotEncoder(handle_unknown='ignore')
oh.fit(X)
X2_passed = X2.copy()
assert_array_equal(
oh.transform(X2_passed).toarray(),
np.array([[0., 0., 0., 0., 1., 0., 0.]]))
# ensure transformed data was not modified in place
assert_allclose(X2, X2_passed)
# Raise error if handle_unknown is neither ignore or error.
oh = OneHotEncoder(handle_unknown='42')
with pytest.raises(ValueError, match='handle_unknown should be either'):
oh.fit(X)
def test_encoder_dtypes():
# check that dtypes are preserved when determining categories
enc = OneHotEncoder(categories='auto')
exp = np.array([[1., 0., 1., 0.], [0., 1., 0., 1.]], dtype='float64')
for X in [
np.array([[1, 2], [3, 4]], dtype='int64'),
np.array([[1, 2], [3, 4]], dtype='float64'),
np.array([['a', 'b'], ['c', 'd']]), # string dtype
np.array([[1, 'a'], [3, 'b']], dtype='object')
]:
enc.fit(X)
assert all([enc.categories_[i].dtype == X.dtype for i in range(2)])
assert_array_equal(enc.transform(X).toarray(), exp)
X = [[1, 2], [3, 4]]
enc.fit(X)
assert all([
np.issubdtype(enc.categories_[i].dtype, np.integer) for i in range(2)
])
assert_array_equal(enc.transform(X).toarray(), exp)
X = [[1, 'a'], [3, 'b']]
enc.fit(X)
assert all([enc.categories_[i].dtype == 'object' for i in range(2)])
assert_array_equal(enc.transform(X).toarray(), exp)
def test_one_hot_encoder_raise_missing(X, as_data_frame, handle_unknown):
if as_data_frame:
pd = pytest.importorskip('pandas')
X = pd.DataFrame(X)
ohe = OneHotEncoder(categories='auto', handle_unknown=handle_unknown)
with pytest.raises(ValueError, match="Input contains NaN"):
ohe.fit(X)
with pytest.raises(ValueError, match="Input contains NaN"):
ohe.fit_transform(X)
if as_data_frame:
X_partial = X.iloc[:1, :]
else:
X_partial = X[:1, :]
ohe.fit(X_partial)
with pytest.raises(ValueError, match="Input contains NaN"):
ohe.transform(X)
def test_one_hot_encoder_unsorted_categories():
X = np.array([['a', 'b']], dtype=object).T
enc = OneHotEncoder(categories=[['b', 'a', 'c']])
exp = np.array([[0., 1., 0.], [1., 0., 0.]])
assert_array_equal(enc.fit(X).transform(X).toarray(), exp)
assert_array_equal(enc.fit_transform(X).toarray(), exp)
assert enc.categories_[0].tolist() == ['b', 'a', 'c']
assert np.issubdtype(enc.categories_[0].dtype, np.object_)
# unsorted passed categories still raise for numerical values
X = np.array([[1, 2]]).T
enc = OneHotEncoder(categories=[[2, 1, 3]])
msg = 'Unsorted categories are not supported'
with pytest.raises(ValueError, match=msg):
enc.fit_transform(X)
rt = RandomTreesEmbedding(max_depth=3,
n_estimators=n_estimator,
random_state=0)
rt_lm = LogisticRegression(max_iter=1000)
pipeline = make_pipeline(rt, rt_lm)
pipeline.fit(X_train, y_train)
y_pred_rt = pipeline.predict_proba(X_test)[:, 1]
fpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)
# Supervised transformation based on random forests
rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
rf_enc = OneHotEncoder()
rf_lm = LogisticRegression(max_iter=1000)
rf.fit(X_train, y_train)
rf_enc.fit(rf.apply(X_train))
rf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)
y_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]
fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
# Supervised transformation based on gradient boosted trees
grd = GradientBoostingClassifier(n_estimators=n_estimator)
grd_enc = OneHotEncoder()
grd_lm = LogisticRegression(max_iter=1000)
grd.fit(X_train, y_train)
grd_enc.fit(grd.apply(X_train)[:, :, 0])
grd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)
y_pred_grd_lm = grd_lm.predict_proba(
grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]
def test_invalid_drop_length(drop):
enc = OneHotEncoder(drop=drop)
err_msg = "`drop` should have length equal to the number"
with pytest.raises(ValueError, match=err_msg):
enc.fit([['abc', 2, 55], ['def', 1, 55], ['def', 3, 59]])
def test_one_hot_encoder_invalid_params(X_fit, params, err_msg):
enc = OneHotEncoder(**params)
with pytest.raises(ValueError, match=err_msg):
enc.fit(X_fit)
