def test_mitie():
from rasa_nlu.featurizers.mitie_featurizer import MITIEFeaturizer
filename = os.environ.get('MITIE_FILE')
if (filename and os.path.isfile(filename)):
ftr = MITIEFeaturizer(os.environ.get('MITIE_FILE'))
sentence = "Hey how are you today"
vecs = ftr.create_bow_vecs([sentence])
assert np.allclose(vecs[0][:5], np.array([0., -4.4551446, 0.26073121, -1.46632245, -1.84205751]), atol=1e-5)
class MITIESklearnInterpreter(Interpreter):
def __init__(self, intent_classifier_file=None, entity_extractor_file=None, feature_extractor_file=None, **kwargs):
if entity_extractor_file:
self.extractor = named_entity_extractor(entity_extractor_file) # ,metadata["feature_extractor"])
with open(intent_classifier_file, 'rb') as f:
self.classifier = cloudpickle.load(f)
self.featurizer = MITIEFeaturizer(feature_extractor_file)
self.tokenizer = MITIETokenizer()
def get_entities(self, tokens):
d = {}
entities = self.extractor.extract_entities(tokens)
for e in entities:
_range = e[0]
d[e[1]] = " ".join(tokens[i] for i in _range)
return d
def get_intent(self, text):
"""Returns the most likely intent and its probability for the input text.
:param text: text to classify
:return: tuple of most likely intent name and its probability"""
if self.classifier:
X = self.featurizer.create_bow_vecs([text])
intent_ids, probabilities = self.classifier.predict(X)
intents = self.classifier.transform_labels_num2str(intent_ids)
intent, score = intents[0], probabilities[0]
else:
intent, score = "None", 0.0
return intent, score
def parse(self, text):
tokens = self.tokenizer.tokenize(text)
intent, probability = self.get_intent(tokens)
entities = self.get_entities(tokens)
return {'text': text, 'intent': intent, 'entities': entities, 'confidence': probability}