1.對數據集打亂是個很重要的課題,在sklearn裏面提供了置亂的函數,我這裏提供一個簡單的例子:
import numpy as np
from sklearn.utils import shuffle
data = np.array([['王大'], ['王二'], ['王三'], ['王四'],['王五'],['王六'],['王七'],['王八'],['王九'],['王十']])
label = np.array([1, 2, 3, 4,5,6,7,8,9,10])
data,label = shuffle(data,label)
print('data = \n' ,data,'\nlabel = ',label)
輸出結果:
data =
[['王六']
['王五']
['王四']
['王二']
['王八']
['王三']
['王七']
['王十']
['王大']
['王九']]
label = [ 6 5 4 2 8 3 7 10 1 9]