Question

我正在尝试编写一个函数Cv（X，y，model，folds）该函数获取X，y我想要使用的模型（SVM，logistic.linear.perspetron等。）并返回平均训练误差经过k折和验证错误。我可以通过函数cross_val_score获得验证错误，但我不知道如何获得训练错误，我考虑过使用Kfold函数，但不知道如何实现。

我的代码：

    import numpy as np
    import pandas as pd
    import requests
    from sklearn.svm import SVC
    from sklearn.datasets import fetch_mldata
    from sklearn.model_selection import cross_val_score
    from sklearn.model_selection import KFold


##then I wrote a function that load data into DF and return labal_df and Data_df (didn't write it in here because it working)

def cv(X,y,model,folds):

 Cv= cross_val_score(model, X,y, cv=folds,scoring='accuracy')
        Cv=Cv.mean() ##Now I have the validation error for the model I selected after K folds.
But how can I calculate the mean of the train error?

曾想过使用Kfold函数在每个折叠上运行并测试火车错误，但找不到如何执行此操作。

如果有人可以解释，我将不胜感激

任何模型的交叉验证功能-python

0 个答案: