def train_intent_classifier(intents):
"""
Train intent classifier model
:param intents:
:return:
"""
X = []
y = []
for intent in intents:
training_data = intent.trainingData
for example in training_data:
if example.get("text").strip() == "":
continue
X.append(example.get("text"))
y.append(str(intent.id))
intent_classifier = EmbeddingIntentClassifier()
intent_classifier.train(X,y)
def train_intent_classifier(intents):
"""
Train intent classifier model
:param intents:
:return:
"""
X = []
y = []
for intent in intents:
training_data = intent.trainingData
for example in training_data:
if example.get("text").strip() == "":
continue
X.append(example.get("text"))
y.append(str(intent.intentId))
intent_classifier = EmbeddingIntentClassifier()
intent_classifier.train(X,y)
intent_classifier.persist(model_dir=app.config["MODELS_DIR"])
def update_model(app, message, **extra):
"""
Signal hook to be called after training is completed.
Reloads ml models and synonyms.
:param app:
:param message:
:param extra:
:return:
"""
global sentence_classifier
sentence_classifier = EmbeddingIntentClassifier.load(app.config["MODELS_DIR"])
synonyms = get_synonyms()
global entity_extraction
entity_extraction = EntityExtractor(synonyms)
app.logger.info("Intent Model updated")
def update_model(app, message, **extra):
"""
Signal hook to be called after training is completed.
Reloads ml models and synonyms.
:param app:
:param message:
:param extra:
:return:
"""
global sentence_classifier
sentence_classifier = EmbeddingIntentClassifier.load(
app.config["MODELS_DIR"])
synonyms = get_synonyms()
global entity_extraction
entity_extraction = EntityExtractor(synonyms)
app.logger.info("Intent Model updated")
def train_intent_classifier(intents):
"""
Train intent classifier model
:param intents:
:return:
"""
X = []
y = []
for intent in intents:
training_data = intent.trainingData
for example in training_data:
if example.get("text").strip() == "":
continue
X.append(example.get("text"))
y.append(str(intent.intentId.encode('utf8')))
intent_classifier = EmbeddingIntentClassifier(use_word_vectors=app.config['USE_WORD_VECTORS'])
intent_classifier.train(X, y)
intent_classifier.persist(model_dir=app.config["MODELS_DIR"])
