def test_train_load_predict_loop(
default_model_storage: ModelStorage,
default_execution_context: ExecutionContext,
mitie_model: MitieModel,
mitie_tokenizer: MitieTokenizer,
):
resource = Resource("mitie_classifier")
component = MitieIntentClassifier.create(
MitieIntentClassifier.get_default_config(),
default_model_storage,
resource,
default_execution_context,
)
training_data = rasa.shared.nlu.training_data.loading.load_data(
"data/examples/rasa/demo-rasa.yml")
# Tokenize message as classifier needs that
mitie_tokenizer.process_training_data(training_data)
component.train(training_data, mitie_model)
component = MitieIntentClassifier.load(
MitieIntentClassifier.get_default_config(),
default_model_storage,
resource,
default_execution_context,
)
test_message = Message({TEXT: "hi"})
mitie_tokenizer.process([test_message])
component.process([test_message], mitie_model)
assert test_message.data[INTENT][INTENT_NAME_KEY] == "greet"
assert test_message.data[INTENT][PREDICTED_CONFIDENCE_KEY] > 0
def test_mitie_featurizer_train(
create: Callable[[Dict[Text, Any]], MitieFeaturizer],
mitie_model: MitieModel,
mitie_tokenizer: MitieTokenizer,
):
featurizer = create({"alias": "mitie_featurizer"})
sentence = "Hey how are you today"
message = Message(data={TEXT: sentence})
message.set(RESPONSE, sentence)
message.set(INTENT, "intent")
mitie_tokenizer.process_training_data(TrainingData([message]))
featurizer.process_training_data(TrainingData([message]), mitie_model)
expected = np.array([
0.00000000e00, -5.12735510e00, 4.39929873e-01, -5.60760403e00,
-8.26445103e00
])
expected_cls = np.array(
[0.0, -4.4551446, 0.26073121, -1.46632245, -1.84205751])
seq_vec, sen_vec = message.get_dense_features(TEXT, [])
if seq_vec:
seq_vec = seq_vec.features
if sen_vec:
sen_vec = sen_vec.features
assert len(message.get(TOKENS_NAMES[TEXT])) == len(seq_vec)
assert np.allclose(seq_vec[0][:5], expected, atol=1e-5)
assert np.allclose(sen_vec[-1][:5], expected_cls, atol=1e-5)
seq_vec, sen_vec = message.get_dense_features(RESPONSE, [])
if seq_vec:
seq_vec = seq_vec.features
if sen_vec:
sen_vec = sen_vec.features
assert len(message.get(TOKENS_NAMES[RESPONSE])) == len(seq_vec)
assert np.allclose(seq_vec[0][:5], expected, atol=1e-5)
assert np.allclose(sen_vec[-1][:5], expected_cls, atol=1e-5)
seq_vec, sen_vec = message.get_dense_features(INTENT, [])
if seq_vec:
seq_vec = seq_vec.features
if sen_vec:
sen_vec = sen_vec.features
assert seq_vec is None
assert sen_vec is None
