整条的数据集划分

import random
def randSplit(dataSet,rate):
    l = list(dataSet.index)
    random.shuffle(l)
    dataSet.index = l
    n = dataSet.shape[0]
    m = int(n*rate)
    train = dataSet.loc[range(m),:]
    test = dataSet.loc[range(m,n),:]
    dataSet.index = range(dataSet.shape[0])
    test.index = range(test.shape[0])
    return train, test

特征值和目标值分离的数据集划分

#划分数据集和测试集 ，划分数据集随机划分数据
from sklearn.model_selection import train_test_split
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=0.25)