def test_lda_default_prior_params():
# default prior parameter should be `1 / topics`
# and verbose params should not affect result
n_components, X = _build_sparse_mtx()
prior = 1. / n_components
lda_1 = LatentDirichletAllocation(n_components=n_components,
doc_topic_prior=prior,
topic_word_prior=prior, random_state=0)
lda_2 = LatentDirichletAllocation(n_components=n_components,
random_state=0)
topic_distr_1 = lda_1.fit_transform(X)
topic_distr_2 = lda_2.fit_transform(X)
assert_almost_equal(topic_distr_1, topic_distr_2)
def test_lda_score(method):
# Test LDA score for batch training
# score should be higher 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_transform(X)
score_1 = lda_1.score(X)
lda_2.fit_transform(X)
score_2 = lda_2.score(X)
assert score_2 >= score_1
def test_lda_fit_transform(method):
# Test LDA fit_transform & transform
# fit_transform and transform result should be the same
rng = np.random.RandomState(0)
X = rng.randint(10, size=(50, 20))
lda = LatentDirichletAllocation(n_components=5, learning_method=method,
random_state=rng)
X_fit = lda.fit_transform(X)
X_trans = lda.transform(X)
assert_array_almost_equal(X_fit, X_trans, 4)
def test_lda_transform():
# Test LDA transform.
# Transform result cannot be negative and should be normalized
rng = np.random.RandomState(0)
X = rng.randint(5, size=(20, 10))
n_components = 3
lda = LatentDirichletAllocation(n_components=n_components,
random_state=rng)
X_trans = lda.fit_transform(X)
assert (X_trans > 0.0).any()
assert_array_almost_equal(np.sum(X_trans, axis=1),
np.ones(X_trans.shape[0]))