def test_lda_negative_input():
# test pass dense matrix with sparse negative input.
X = np.full((5, 10), -1.)
lda = LatentDirichletAllocation()
regex = r"^Negative values in data passed"
with pytest.raises(ValueError, match=regex):
lda.fit(X)
def test_lda_score_perplexity():
# Test the relationship between LDA score and perplexity
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components, max_iter=10,
random_state=0)
lda.fit(X)
perplexity_1 = lda.perplexity(X, sub_sampling=False)
score = lda.score(X)
perplexity_2 = np.exp(-1. * (score / np.sum(X.data)))
assert_almost_equal(perplexity_1, perplexity_2)
def test_perplexity_input_format():
# Test LDA perplexity for sparse and dense input
# score should be the same for both dense and sparse input
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components, max_iter=1,
learning_method='batch',
total_samples=100, random_state=0)
lda.fit(X)
perp_1 = lda.perplexity(X)
perp_2 = lda.perplexity(X.toarray())
assert_almost_equal(perp_1, perp_2)
def test_lda_dense_input():
# Test LDA with dense input.
rng = np.random.RandomState(0)
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components,
learning_method='batch', random_state=rng)
lda.fit(X.toarray())
correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
for component in lda.components_:
# Find top 3 words in each LDA component
top_idx = set(component.argsort()[-3:][::-1])
assert tuple(sorted(top_idx)) in correct_idx_grps
def test_lda_multi_jobs(method):
n_components, X = _build_sparse_mtx()
# Test LDA batch training with multi CPU
rng = np.random.RandomState(0)
lda = LatentDirichletAllocation(n_components=n_components, n_jobs=2,
learning_method=method,
evaluate_every=1, random_state=rng)
lda.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_fit_online():
# Test LDA online learning (`fit` method with 'online' learning)
rng = np.random.RandomState(0)
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components,
learning_offset=10., evaluate_every=1,
learning_method='online', random_state=rng)
lda.fit(X)
correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
for component in lda.components_:
# Find top 3 words in each LDA component
top_idx = set(component.argsort()[-3:][::-1])
assert tuple(sorted(top_idx)) in correct_idx_grps
def test_lda_fit_perplexity():
# Test that the perplexity computed during fit is consistent with what is
# returned by the perplexity method
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components, max_iter=1,
learning_method='batch', random_state=0,
evaluate_every=1)
lda.fit(X)
# Perplexity computed at end of fit method
perplexity1 = lda.bound_
# Result of perplexity method on the train set
perplexity2 = lda.perplexity(X)
assert_almost_equal(perplexity1, perplexity2)
def test_lda_preplexity_mismatch():
# test dimension mismatch in `perplexity` method
rng = np.random.RandomState(0)
n_components = rng.randint(3, 6)
n_samples = rng.randint(6, 10)
X = np.random.randint(4, size=(n_samples, 10))
lda = LatentDirichletAllocation(n_components=n_components,
learning_offset=5., total_samples=20,
random_state=rng)
lda.fit(X)
# invalid samples
invalid_n_samples = rng.randint(4, size=(n_samples + 1, n_components))
with pytest.raises(ValueError, match=r'Number of samples'):
lda._perplexity_precomp_distr(X, invalid_n_samples)
# invalid topic number
invalid_n_components = rng.randint(4, size=(n_samples, n_components + 1))
with pytest.raises(ValueError, match=r'Number of topics'):
lda._perplexity_precomp_distr(X, invalid_n_components)
def check_verbosity(verbose, evaluate_every, expected_lines,
expected_perplexities):
n_components, X = _build_sparse_mtx()
lda = LatentDirichletAllocation(n_components=n_components, max_iter=3,
learning_method='batch',
verbose=verbose,
evaluate_every=evaluate_every,
random_state=0)
out = StringIO()
old_out, sys.stdout = sys.stdout, out
try:
lda.fit(X)
finally:
sys.stdout = old_out
n_lines = out.getvalue().count('\n')
n_perplexity = out.getvalue().count('perplexity')
assert expected_lines == n_lines
assert expected_perplexities == n_perplexity
def test_lda_perplexity(method):
# Test LDA perplexity for batch training
# perplexity should be lower after each iteration
n_components, X = _build_sparse_mtx()
lda_1 = LatentDirichletAllocation(n_components=n_components,
max_iter=1, learning_method=method,
total_samples=100, random_state=0)
lda_2 = LatentDirichletAllocation(n_components=n_components,
max_iter=10, learning_method=method,
total_samples=100, random_state=0)
lda_1.fit(X)
perp_1 = lda_1.perplexity(X, sub_sampling=False)
lda_2.fit(X)
perp_2 = lda_2.perplexity(X, sub_sampling=False)
assert perp_1 >= perp_2
perp_1_subsampling = lda_1.perplexity(X, sub_sampling=True)
perp_2_subsampling = lda_2.perplexity(X, sub_sampling=True)
assert perp_1_subsampling >= perp_2_subsampling