def test_count_vector_featurizer(
sentence: Text,
expected: List[List[int]],
expected_cls: List[List[int]],
create_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
whitespace_tokenizer: WhitespaceTokenizerGraphComponent,
):
ftr = create_featurizer()
train_message = Message(data={TEXT: sentence})
test_message = Message(data={TEXT: sentence})
whitespace_tokenizer.process([train_message])
whitespace_tokenizer.process([test_message])
ftr.train(TrainingData([train_message]))
ftr.process([test_message])
seq_vecs, sen_vecs = test_message.get_sparse_features(TEXT, [])
if seq_vecs:
seq_vecs = seq_vecs.features
if sen_vecs:
sen_vecs = sen_vecs.features
assert isinstance(seq_vecs, scipy.sparse.coo_matrix)
assert isinstance(sen_vecs, scipy.sparse.coo_matrix)
actual_seq_vecs = seq_vecs.toarray()
actual_sen_vecs = sen_vecs.toarray()
assert np.all(actual_seq_vecs[0] == expected)
assert np.all(actual_sen_vecs[-1] == expected_cls)
async def test_train_persist_load_with_composite_entities(
crf_entity_extractor: Callable[[Dict[Text, Any]],
CRFEntityExtractorGraphComponent],
default_model_storage: ModelStorage,
default_execution_context: ExecutionContext,
whitespace_tokenizer: WhitespaceTokenizerGraphComponent,
):
importer = RasaFileImporter(
training_data_paths=["data/test/demo-rasa-composite-entities.yml"])
training_data = importer.get_nlu_data()
whitespace_tokenizer.process_training_data(training_data)
crf_extractor = crf_entity_extractor({})
crf_extractor.train(training_data)
message = Message(data={TEXT: "I am looking for an italian restaurant"})
whitespace_tokenizer.process([message])
message2 = copy.deepcopy(message)
processed_message = crf_extractor.process([message])[0]
loaded_extractor = CRFEntityExtractorGraphComponent.load(
CRFEntityExtractorGraphComponent.get_default_config(),
default_model_storage,
Resource("CRFEntityExtractor"),
default_execution_context,
)
processed_message2 = loaded_extractor.process([message2])[0]
assert processed_message2.fingerprint() == processed_message.fingerprint()
def process_messages(
texts: List[Text],
model_name: Text,
model_weights: Text,
create_language_model_featurizer: Callable[
[Dict[Text, Any]], LanguageModelFeaturizerGraphComponent
],
whitespace_tokenizer: WhitespaceTokenizerGraphComponent,
) -> List[Message]:
""" Creates a featurizer and processes messages """
config = create_pretrained_transformers_config(model_name, model_weights)
lm_featurizer = create_language_model_featurizer(config)
messages = []
for text in texts:
message = Message.build(text=text)
whitespace_tokenizer.process([message])
messages.append(message)
lm_featurizer.process(messages)
return messages
def test_count_vector_featurizer_process_by_attribute(
sentence: Text,
action_name: Text,
action_text: Text,
action_name_features: np.ndarray,
response_features: np.ndarray,
create_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
whitespace_tokenizer: WhitespaceTokenizerGraphComponent,
):
ftr = create_featurizer({"token_pattern": r"(?u)\b\w+\b",})
# add a second example that has some response, so that the vocabulary for
# response exists
train_message = Message(data={TEXT: "hello"})
train_message.set(ACTION_NAME, "greet")
train_message1 = Message(data={TEXT: "hello"})
train_message1.set(ACTION_TEXT, "hi")
data = TrainingData([train_message, train_message1])
whitespace_tokenizer.process_training_data(data)
ftr.train(data)
test_message = Message(data={TEXT: sentence})
test_message.set(ACTION_NAME, action_name)
test_message.set(ACTION_TEXT, action_text)
whitespace_tokenizer.process([test_message])
ftr.process([test_message])
action_name_seq_vecs, action_name_sen_vecs = test_message.get_sparse_features(
ACTION_NAME, []
)
if action_name_seq_vecs:
action_name_seq_vecs = action_name_seq_vecs.features
if action_name_sen_vecs:
action_name_sen_vecs = action_name_sen_vecs.features
assert action_name_seq_vecs.toarray()[0] == action_name_features
assert action_name_sen_vecs is None
def test_count_vector_featurizer_oov_token(
sentence: Text,
expected: List[List[int]],
create_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
whitespace_tokenizer: WhitespaceTokenizerGraphComponent,
):
ftr = create_featurizer({"OOV_token": "__oov__"})
train_message = Message(data={TEXT: sentence})
whitespace_tokenizer.process([train_message])
data = TrainingData([train_message])
ftr.train(data)
ftr.process_training_data(data)
seq_vec, sen_vec = train_message.get_sparse_features(TEXT, [])
if seq_vec:
seq_vec = seq_vec.features
if sen_vec:
sen_vec = sen_vec.features
assert np.all(seq_vec.toarray()[0] == expected)
assert sen_vec is not None
def test_count_vector_featurizer_persist_load(
create_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
load_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
whitespace_tokenizer: WhitespaceTokenizerGraphComponent,
):
# set non default values to config
config = {
"analyzer": "char",
"strip_accents": "ascii",
"stop_words": "stop",
"min_df": 2,
"max_df": 3,
"min_ngram": 2,
"max_ngram": 3,
"max_features": 10,
"lowercase": False,
}
train_ftr = create_featurizer(config)
sentence1 = "ababab 123 13xc лаомтгцу sfjv oö aà"
sentence2 = "abababalidcn 123123 13xcdc лаомтгцу sfjv oö aà"
train_message1 = Message(data={TEXT: sentence1})
train_message2 = Message(data={TEXT: sentence2})
whitespace_tokenizer.process([train_message1])
whitespace_tokenizer.process([train_message2])
data = TrainingData([train_message1, train_message2])
train_ftr.train(data)
train_ftr.process_training_data(data)
# persist featurizer
train_vect_params = {
attribute: vectorizer.get_params()
for attribute, vectorizer in train_ftr.vectorizers.items()
}
# add trained vocabulary to vectorizer params
for attribute, attribute_vect_params in train_vect_params.items():
if hasattr(train_ftr.vectorizers[attribute], "vocabulary_"):
train_vect_params[attribute].update(
{"vocabulary": train_ftr.vectorizers[attribute].vocabulary_}
)
test_ftr = load_featurizer(config)
test_vect_params = {
attribute: vectorizer.get_params()
for attribute, vectorizer in test_ftr.vectorizers.items()
}
assert train_vect_params == test_vect_params
# check if vocaculary was loaded correctly
assert hasattr(test_ftr.vectorizers[TEXT], "vocabulary_")
test_message1 = Message(data={TEXT: sentence1})
whitespace_tokenizer.process([test_message1])
test_ftr.process([test_message1])
test_message2 = Message(data={TEXT: sentence2})
whitespace_tokenizer.process([test_message2])
test_ftr.process([test_message2])
test_seq_vec_1, test_sen_vec_1 = test_message1.get_sparse_features(TEXT, [])
if test_seq_vec_1:
test_seq_vec_1 = test_seq_vec_1.features
if test_sen_vec_1:
test_sen_vec_1 = test_sen_vec_1.features
train_seq_vec_1, train_sen_vec_1 = train_message1.get_sparse_features(TEXT, [])
if train_seq_vec_1:
train_seq_vec_1 = train_seq_vec_1.features
if train_sen_vec_1:
train_sen_vec_1 = train_sen_vec_1.features
test_seq_vec_2, test_sen_vec_2 = test_message2.get_sparse_features(TEXT, [])
if test_seq_vec_2:
test_seq_vec_2 = test_seq_vec_2.features
if test_sen_vec_2:
test_sen_vec_2 = test_sen_vec_2.features
train_seq_vec_2, train_sen_vec_2 = train_message2.get_sparse_features(TEXT, [])
if train_seq_vec_2:
train_seq_vec_2 = train_seq_vec_2.features
if train_sen_vec_2:
train_sen_vec_2 = train_sen_vec_2.features
# check that train features and test features after loading are the same
assert np.all(test_seq_vec_1.toarray() == train_seq_vec_1.toarray())
assert np.all(test_sen_vec_1.toarray() == train_sen_vec_1.toarray())
assert np.all(test_seq_vec_2.toarray() == train_seq_vec_2.toarray())
assert np.all(test_sen_vec_2.toarray() == train_sen_vec_2.toarray())