def test_five_components():
'''
Assert that components computed are identical to the original version for n dimensions.
'''
np.random.seed(42)
n_components = 5
online_lda = LDA(
n_components=n_components,
number_of_documents=60,
maximum_size_vocabulary=100,
alpha_beta=100,
alpha_theta=0.5,
)
components_list = []
for document in DOC_SET:
components_list.append(online_lda.fit_transform_one(document))
for index, component in enumerate(components_list):
assert np.array_equal(
a1=list(component.values()),
a2=REFERENCE_FIVE_COMPONENTS[index],
)
def test_five_components():
"""
Assert that components computed are identical to the original version for n dimensions.
"""
n_components = 5
lda = LDA(n_components=n_components,
number_of_documents=60,
maximum_size_vocabulary=100,
alpha_beta=100,
alpha_theta=0.5,
seed=42)
components_list = []
for document in DOC_SET:
tokens = {token: 1 for token in document.split(' ')}
components_list.append(lda.fit_transform_one(tokens))
for index, component in enumerate(components_list):
assert np.array_equal(
a1=list(component.values()),
a2=REFERENCE_FIVE_COMPONENTS[index],
)
def test_prunning_vocabulary():
'''
Vocabulary prunning is available to improve accuracy and limit memory usage.
You can perform vocabulary prunning with parameters vocab_prune_interval (int) and
maximum_size_vocabulary (int).
'''
np.random.seed(42)
online_lda = LDA(n_components=2,
number_of_documents=60,
vocab_prune_interval=2,
maximum_size_vocabulary=3)
components_list = []
for document in DOC_SET:
components_list.append(online_lda.fit_transform_one(x=document))
for index, component in enumerate(components_list):
assert np.array_equal(a1=list(component.values()),
a2=REFERENCE_COMPONENTS_WITH_PRUNNING[index])
def test_prunning_vocabulary():
"""
Vocabulary prunning is available to improve accuracy and limit memory usage.
You can perform vocabulary prunning with parameters vocab_prune_interval (int) and
maximum_size_vocabulary (int).
"""
lda = LDA(n_components=2,
number_of_documents=60,
vocab_prune_interval=2,
maximum_size_vocabulary=3,
seed=42)
components_list = []
for document in DOC_SET:
tokens = {token: 1 for token in document.split(' ')}
components_list.append(lda.fit_transform_one(tokens))
for index, component in enumerate(components_list):
assert np.array_equal(a1=list(component.values()),
a2=REFERENCE_COMPONENTS_WITH_PRUNNING[index])