def test_statistics_two_components():
'''
Assert that online lda extracts waited statistics on current document.
'''
n_components = 2
np.random.seed(42)
lda = LDA(n_components, number_of_documents=60)
statistics_list = []
for doc in DOC_SET:
word_list = lda.tokenizer(lda.preprocess(lda._get_text(doc)))
lda._update_indexes(word_list=word_list)
word_indexes = [lda.word_to_index[word] for word in word_list]
statistics, _ = lda._compute_statistics_components(
words_indexes_list=word_indexes, )
statistics_list.append(statistics)
lda._update_weights(statistics=statistics)
for index, statistics in enumerate(statistics_list):
for component in range(n_components):
assert np.array_equal(
a1=statistics[component],
a2=REFERENCE_STATISTICS_TWO_COMPONENTS[index][component],
)
def test_extraction_words_ids():
'''
Assert that inputs words are splitted.
Assert that indexes are updated and extractable.
'''
np.random.seed(42)
lda = LDA(2, number_of_documents=5)
word_indexes_list = []
for doc in DOC_SET:
words = lda.tokenizer(lda.preprocess(lda._get_text(doc)))
lda._update_indexes(word_list=words)
word_indexes_list.append([lda.word_to_index[word] for word in words])
assert word_indexes_list == [
[1, 2],
[1, 3, 4],
[1, 2, 5],
[1, 3],
[1, 2, 6],
]
def test_extraction_words_ids():
"""
Assert that inputs words are splitted.
Assert that indexes are updated and extractable.
"""
lda = LDA(2, number_of_documents=5, seed=42)
word_indexes_list = []
for doc in DOC_SET:
words = doc.split(' ')
lda._update_indexes(word_list=words)
word_indexes_list.append([lda.word_to_index[word] for word in words])
assert word_indexes_list == [
[1, 2],
[1, 3, 4],
[1, 2, 5],
[1, 3],
[1, 2, 6],
]
def test_statistics_two_components():
"""
Assert that online lda extracts waited statistics on current document.
"""
n_components = 2
lda = LDA(n_components, number_of_documents=60, seed=42)
statistics_list = []
for doc in DOC_SET:
word_list = doc.split(' ')
lda._update_indexes(word_list=word_list)
word_indexes = [lda.word_to_index[word] for word in word_list]
statistics, _ = lda._compute_statistics_components(
words_indexes_list=word_indexes, )
statistics_list.append(statistics)
lda._update_weights(statistics=statistics)
for index, statistics in enumerate(statistics_list):
for component in range(n_components):
assert np.array_equal(
a1=statistics[component],
a2=REFERENCE_STATISTICS_TWO_COMPONENTS[index][component],
)
def test_statistics_five_components():
'''
Assert that online lda extracts waited statistics on current document.
'''
np.random.seed(42)
n_components = 5
lda = LDA(
n_components=n_components,
number_of_documents=60,
maximum_size_vocabulary=100,
alpha_beta=100,
alpha_theta=0.5,
)
statistics_list = []
for doc in DOC_SET:
word_list = lda.process_text(doc)
lda._update_indexes(word_list=word_list)
word_indexes = [lda.word_to_index[word] for word in word_list]
statistics, _ = lda._compute_statistics_components(
words_indexes_list=word_indexes, )
statistics_list.append(statistics)
lda._update_weights(statistics=statistics)
for index, statistics in enumerate(statistics_list):
for component in range(n_components):
assert np.array_equal(
a1=statistics[component],
a2=REFERENCE_STATISTICS_FIVE_COMPONENTS[index][component],
)