I have a data set that contains 2 columns columns A is winning teams and column B is losing team I would like to shuffle the values between the 2 columns so when i start training the model the model can't predict the winning ream simply by looking at the winning team column

Before

A B
1 2
2 1
3 4
4 3

After

A B
1 2
2 1
4 3
3 4

CodePudding user response：

Here is a way to shuffle each row randomly

(pd.DataFrame(df.apply(lambda x: np.random.choice(x,df.columns.size,replace = False),axis=1)
              .tolist(),
              columns = df.columns))

Output:

   A  B
0  1  2
1  1  2
2  3  4
3  4  3