model.py 文件源码

def MultinomialNBPredictModel(localTrainLabel, config):
    train = pd.read_csv('../feature/trainQlist.csv', header = 0, sep = ",")
    test = pd.read_csv('../feature/testQlist.csv', header = 0, sep = ",")
    print "Train tf-idf vector Model..."    
    encode = TfidfVectorizer(decode_error = 'ignore', norm = "l2", binary = False, sublinear_tf = True, min_df = 50)
    localTrainFeature = encode.fit_transform(train['qlist'].values)
    localTestFeature = encode.transform(train['qlist'].values)

    print localTrainFeature.shape, localTestFeature.shape

    print 'train...'
    model = MultinomialNB(alpha=1.0, fit_prior=True, class_prior=None)
    model.fit(X = localTrainFeature, y = localTrainLabel)
    print 'predict...'
    if config['prob'] == False:
        return model.predict(localTestFeature), test['uid'].values
    else:
        return model.predict_log_proba(localTestFeature), test['uid'].values

#-- xgboost local corss validation model frame