def test_partial_fit(n_samples=70):
X_txt = fetch_20newsgroups(subset='train')['data']
X = X_txt[:n_samples]
# Gap encoder with fit on one batch
enc = GapEncoder(random_state=42, batch_size=n_samples, max_iter=1)
X_enc = enc.fit_transform(X)
# Gap encoder with partial fit
enc = GapEncoder(random_state=42)
enc.partial_fit(X)
X_enc_partial = enc.transform(X)
# Check if the encoded vectors are the same
np.testing.assert_almost_equal(X_enc, X_enc_partial)
return
def test_missing_values(missing):
observations = [['alice', 'bob'], ['bob', 'alice'], ['bob', np.nan],
['alice', 'charlie'], [np.nan, 'alice']]
observations = np.array(observations, dtype=object)
enc = GapEncoder(handle_missing=missing, n_components=3)
if missing == 'error':
with pytest.raises(ValueError,
match=r'Input data contains missing values.'):
enc.fit_transform(observations)
elif missing == 'zero_impute':
enc.fit_transform(observations)
enc.partial_fit(observations)
else:
with pytest.raises(ValueError,
match=r"handle_missing should be either "
r"'error' or 'zero_impute', got 'aaa'"):
enc.fit_transform(observations)