def test_get_num_of_features():
session_data = {
"text_features": [
np.array(
[
np.random.rand(5, 14),
np.random.rand(2, 14),
np.random.rand(3, 14),
np.random.rand(1, 14),
np.random.rand(3, 14),
]
),
np.array(
[
scipy.sparse.csr_matrix(np.random.randint(5, size=(5, 10))),
scipy.sparse.csr_matrix(np.random.randint(5, size=(2, 10))),
scipy.sparse.csr_matrix(np.random.randint(5, size=(3, 10))),
scipy.sparse.csr_matrix(np.random.randint(5, size=(1, 10))),
scipy.sparse.csr_matrix(np.random.randint(5, size=(3, 10))),
]
),
]
}
num_features = EmbeddingIntentClassifier._get_num_of_features(
session_data, "text_features"
)
assert num_features == 24
def test_check_labels_features_exist(messages, expected):
attribute = TEXT_ATTRIBUTE
assert (
EmbeddingIntentClassifier._check_labels_features_exist(messages, attribute)
== expected
)
def test_compute_default_label_features():
label_features = [
Message("test a"),
Message("test b"),
Message("test c"),
Message("test d"),
]
output = EmbeddingIntentClassifier._compute_default_label_features(label_features)
output = output[0]
for i, o in enumerate(output):
assert isinstance(o, np.ndarray)
assert o[0][i] == 1
assert o.shape == (1, len(label_features))
def test_text_features_present(session_data, expected):
assert EmbeddingIntentClassifier._text_features_present(
session_data) == expected