ValueError：形状（3,4）和（3，）不对齐：4（dim 1）！= 3（dim 0）

Question

我想预测一家餐厅的销售情况，并习惯于以下代码：

my_model = str('sales + competition + population + income')

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

my_model_fit = smf.OLS(y_train, X_train)

df['predict_sales'] = results.fittedvalues

print('\nProportion of Test Set Variance Accounted for: ',\
     round(np.power(df['sales'].corr(df['predict_sales']), 2), 3))

sites_data = {'sales': [0,0,0],
             'competition': [2, 3, 5],
             'population': [50000, 200000, 220000],
             'income': [25000, 220000, 190000]}

sites = pd.DataFrame(sites_data)

sites['sales_pred'] = results.predict(sites)
print('\nNew sites with predicted sales', sites, '\n')

但是在最后一个代码之后，我收到了一个错误：

ValueError: shapes (3,4) and (3,) not aligned: 4 (dim 1) != 3 (dim 0)

有人可以帮忙吗？我现在真的很绝望。