小编DeV*_*r12的帖子

该代码之前可以运行，没有显示任何错误。这是一个情感分析机器学习项目。该代码基于字数统计的逻辑回归模型：

c = CountVectorizer(stop_words = 'english')

def text_fit(X, y, model,clf_model,coef_show=1):
    
    X_c = model.fit_transform(X)
    print('# features: {}'.format(X_c.shape[1]))
    X_train, X_test, y_train, y_test = train_test_split(X_c, y, random_state=0)
    print('# train records: {}'.format(X_train.shape[0]))
    print('# test records: {}'.format(X_test.shape[0]))
    clf = clf_model.fit(X_train, y_train)
    acc = clf.score(X_test, y_test)
    print ('Model Accuracy: {}'.format(acc))
    
    if coef_show == 1: 
        w = model.get_feature_names()
        coef = clf.coef_.tolist()[0]
        coeff_df = pd.DataFrame({'Word' : w, 'Coefficient' : coef})
        coeff_df = coeff_df.sort_values(['Coefficient', 'Word'], ascending=[0, 1])
        print('')
        print('-Top 20 positive-')
        print(coeff_df.head(20).to_string(index=False))
        print('')
        print('-Top 20 negative-')        
        print(coeff_df.tail(20).to_string(index=False))
    
text_fit(X, y, …