def test_lda_transform_mismatch():
# test `n_features` mismatch in partial_fit and transform
rng = np.random.RandomState(0)
X = rng.randint(4, size=(20, 10))
X_2 = rng.randint(4, size=(10, 8))
n_components = rng.randint(3, 6)
lda = LatentDirichletAllocation(n_components=n_components,
random_state=rng)
lda.partial_fit(X)
with pytest.raises(ValueError, match=r"^The provided data has"):
lda.partial_fit(X_2)
def test_lda_partial_fit_dim_mismatch():
# test `n_features` mismatch in `partial_fit`
rng = np.random.RandomState(0)
n_components = rng.randint(3, 6)
n_col = rng.randint(6, 10)
X_1 = np.random.randint(4, size=(10, n_col))
X_2 = np.random.randint(4, size=(10, n_col + 1))
lda = LatentDirichletAllocation(n_components=n_components,
learning_offset=5., total_samples=20,
random_state=rng)
lda.partial_fit(X_1)
with pytest.raises(ValueError, match=r"^The provided data has"):
lda.partial_fit(X_2)
def test_lda_partial_fit_multi_jobs():
# Test LDA online training with multi CPU
rng = np.random.RandomState(0)
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components, n_jobs=2,
learning_offset=5., total_samples=30,
random_state=rng)
for i in range(2):
lda.partial_fit(X)
correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
for c in lda.components_:
top_idx = set(c.argsort()[-3:][::-1])
assert tuple(sorted(top_idx)) in correct_idx_grps
def test_lda_partial_fit():
# Test LDA online learning (`partial_fit` method)
# (same as test_lda_batch)
rng = np.random.RandomState(0)
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components,
learning_offset=10., total_samples=100,
random_state=rng)
for i in range(3):
lda.partial_fit(X)
correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
for c in lda.components_:
top_idx = set(c.argsort()[-3:][::-1])
assert tuple(sorted(top_idx)) in correct_idx_grps