entityRecognition.py 文件源码

def train(filePath):
    try:
        if not filePath.lower().endswith('json'):
            return {'success':False,'message':'Training file should be in json format'}
        with open(filePath) as file:
            ent_data = json.load(file)
        dataset = [jsonToCrf(q, nlp) for q in ent_data['entity_examples']]
        X_train = [sent2features(s) for s in dataset]
        y_train = [sent2labels(s) for s in dataset]
        crf = sklearn_crfsuite.CRF(
        algorithm='lbfgs', 
        c1=0.1, 
        c2=0.1, 
        max_iterations=100, 
        all_possible_transitions=True
        )
        crf.fit(X_train, y_train)
        if(not os.path.exists("crfModel")):
            os.mkdir("crfModel")
        if(os.path.isfile("crfModel/classifier.pkl")):
            os.remove("crfModel/classifier.pkl")
        joblib.dump(crf,"crfModel/classifier.pkl")
        return {'success':True,'message':'Model Trained Successfully'}
    except Exception as ex:
        return {'success':False,'message':'Error while Training the model - '+str(ex)}