def test_convert_featurizer_process(monkeypatch: MonkeyPatch):
tokenizer = WhitespaceTokenizer()
monkeypatch.setattr(ConveRTFeaturizer, "_get_validated_model_url",
lambda x: RESTRICTED_ACCESS_URL)
component_config = {
"name": "ConveRTFeaturizer",
"model_url": RESTRICTED_ACCESS_URL
}
featurizer = ConveRTFeaturizer(component_config)
sentence = "Hey how are you today ?"
message = Message.build(text=sentence)
td = TrainingData([message])
tokenizer.train(td)
tokens = featurizer.tokenize(message, attribute=TEXT)
featurizer.process(message, tf_hub_module=featurizer.module)
expected = np.array(
[2.2636216, -0.26475656, -1.1358104, -0.49751878, -1.3946456])
expected_cls = np.array(
[1.0251294, -0.04053932, -0.7018805, -0.82054937, -0.75054353])
seq_vecs, sent_vecs = message.get_dense_features(TEXT, [])
seq_vecs = seq_vecs.features
sent_vecs = sent_vecs.features
assert len(tokens) == len(seq_vecs)
assert np.allclose(seq_vecs[0][:5], expected, atol=1e-5)
assert np.allclose(sent_vecs[-1][:5], expected_cls, atol=1e-5)
def test_convert_featurizer_tokens_to_text(sentence: Text, expected_text: Text,
monkeypatch: MonkeyPatch):
tokenizer = WhitespaceTokenizer()
monkeypatch.setattr(ConveRTFeaturizer, "_get_validated_model_url",
lambda x: RESTRICTED_ACCESS_URL)
component_config = {
"name": "ConveRTFeaturizer",
"model_url": RESTRICTED_ACCESS_URL
}
featurizer = ConveRTFeaturizer(component_config)
message = Message.build(text=sentence)
td = TrainingData([message])
tokenizer.train(td)
tokens = featurizer.tokenize(message, attribute=TEXT)
actual_text = ConveRTFeaturizer._tokens_to_text([tokens])[0]
assert expected_text == actual_text
def test_convert_featurizer_number_of_sub_tokens(
text: Text, expected_number_of_sub_tokens: List[int],
monkeypatch: MonkeyPatch):
tokenizer = WhitespaceTokenizer()
monkeypatch.setattr(ConveRTFeaturizer, "_get_validated_model_url",
lambda x: RESTRICTED_ACCESS_URL)
component_config = {
"name": "ConveRTFeaturizer",
"model_url": RESTRICTED_ACCESS_URL
}
featurizer = ConveRTFeaturizer(component_config)
message = Message.build(text=text)
td = TrainingData([message])
tokenizer.train(td)
tokens = featurizer.tokenize(message, attribute=TEXT)
assert [t.get(NUMBER_OF_SUB_TOKENS)
for t in tokens] == expected_number_of_sub_tokens
def test_convert_featurizer_token_edge_cases(
text: Text,
expected_tokens: List[Text],
expected_indices: List[Tuple[int]],
monkeypatch: MonkeyPatch,
):
tokenizer = WhitespaceTokenizer()
monkeypatch.setattr(ConveRTFeaturizer, "_get_validated_model_url",
lambda x: RESTRICTED_ACCESS_URL)
component_config = {
"name": "ConveRTFeaturizer",
"model_url": RESTRICTED_ACCESS_URL
}
featurizer = ConveRTFeaturizer(component_config)
message = Message.build(text=text)
td = TrainingData([message])
tokenizer.train(td)
tokens = featurizer.tokenize(message, attribute=TEXT)
assert [t.text for t in tokens] == expected_tokens
assert [t.start for t in tokens] == [i[0] for i in expected_indices]
assert [t.end for t in tokens] == [i[1] for i in expected_indices]