def test_gap_encoder(hashing, init, analyzer, add_words, n_samples=70):
X_txt = fetch_20newsgroups(subset='train')['data']
X = X_txt[:n_samples]
n_components = 10
# Test output shape
encoder = GapEncoder(
n_components=n_components, hashing=hashing, init=init,
analyzer=analyzer, add_words=add_words,
random_state=42, rescale_W=True)
encoder.fit(X)
y = encoder.transform(X)
assert y.shape == (n_samples, n_components), str(y.shape)
assert len(set(y[0])) == n_components
# Test L1-norm of topics W.
l1_norm_W = np.abs(encoder.W_).sum(axis=1)
np.testing.assert_array_almost_equal(
l1_norm_W, np.ones(n_components))
# Test same seed return the same output
encoder = GapEncoder(
n_components=n_components, hashing=hashing, init=init,
analyzer=analyzer, add_words=add_words,
random_state=42)
encoder.fit(X)
y2 = encoder.transform(X)
np.testing.assert_array_equal(y, y2)
return
def test_analyzer(init1, analyzer1, analyzer2):
"""" Test if the output is different when the analyzer is 'word' or 'char'.
If it is, no error ir raised.
"""
add_words = False
n_samples = 70
X_txt = fetch_20newsgroups(subset='train')['data'][:n_samples]
X = np.array([X_txt, X_txt]).T
n_components = 10
# Test first analyzer output:
encoder = GapEncoder(n_components=n_components,
init='k-means++',
analyzer=analyzer1,
add_words=add_words,
random_state=42,
rescale_W=True)
encoder.fit(X)
y = encoder.transform(X)
# Test the other analyzer output:
encoder = GapEncoder(n_components=n_components,
init='k-means++',
analyzer=analyzer2,
add_words=add_words,
random_state=42)
encoder.fit(X)
y2 = encoder.transform(X)
# Test inequality btw analyzer word and char ouput:
np.testing.assert_raises(AssertionError, np.testing.assert_array_equal, y,
y2)
def test_overflow_error():
np.seterr(over='raise', divide='raise')
r = np.random.RandomState(0)
X = r.randint(1e5, 1e6, size=(8000, 1)).astype(str)
enc = GapEncoder(n_components=2, batch_size=1, min_iter=1, max_iter=1,
random_state=0)
enc.fit(X)
return
def test_get_feature_names(n_samples=70):
X_txt = fetch_20newsgroups(subset='train')['data']
X = X_txt[:n_samples]
enc = GapEncoder()
enc.fit(X)
topic_labels = enc.get_feature_names()
# Check number of labels
assert len(topic_labels) == enc.n_components
return
def test_score(n_samples=70):
X_txt = fetch_20newsgroups(subset='train')['data'][:n_samples]
X1 = np.array(X_txt)[:, None]
X2 = np.hstack([X1, X1])
enc = GapEncoder(random_state=42)
enc.fit(X1)
score_X1 = enc.score(X1)
enc.fit(X2)
score_X2 = enc.score(X2)
# Check that two identical columns give the same score
assert score_X1 * 2 == score_X2
return
def test_get_feature_names_out(n_samples=70):
X_txt = fetch_20newsgroups(subset='train')['data'][:n_samples]
X = np.array([X_txt, X_txt]).T
enc = GapEncoder(random_state=42)
enc.fit(X)
for topic_labels in [enc.get_feature_names(), enc.get_feature_names_out()]:
# Check number of labels
assert len(topic_labels) == enc.n_components * X.shape[1]
# Test different parameters for col_names
topic_labels_2 = enc.get_feature_names_out(col_names='auto')
assert topic_labels_2[0] == 'col0: ' + topic_labels[0]
topic_labels_3 = enc.get_feature_names_out(col_names=['abc', 'def'])
assert topic_labels_3[0] == 'abc: ' + topic_labels[0]
return