用pandas划分数据集实现训练集和测试集

# 导入pandas模块，sklearn中model_select模块
import pandas as pd
from sklearn.model_select import train_test_split
# 读取数据
data = pd.read_csv('.../titanic_dataset/train.csv')
# 将特征划分到 X 中，标签划分到 Y 中
x = data.iloc[:, 2:]
y = data.loc['Survived']
# 使用train_test_split函数划分数据集(训练集占75%，测试集占25%)

# 不洗牌模式下数据划分情况
import numpy as np
from sklearn.model_selection import KFold
x = np.arange(46).reshape(23,2)
kf = KFold(n_splits=5,shuffle=False)
for train_index, test_index in kf.split(x):
  print(train_index,test_index)
[ 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22] [0 1 2 3 4]
[ 0 1 2 3 4 10 11 12 13 14 15 16 17 18 19 20 21 22] [5 6 7 8 9]
[ 0 1 2 3 4 5 6 7 8 9 15 16 17 18 19 20 21 22] [10 11 12 13 14]
[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 19 20 21 22] [15 16 17 18]
[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18] [19 20 21 22]

import numpy as np
from sklearn.model_selection import KFold
x = np.arange(46).reshape(23,2)
kf = KFold(n_splits=5,shuffle=True)
for train_index, test_index in kf.split(x):
  print(train_index,test_index)
[ 0 3 4 5 6 7 8 9 10 11 12 14 15 16 17 19 20 21] [ 1 2 13 18 22]
[ 0 1 2 3 5 6 7 10 11 13 15 16 17 18 19 20 21 22] [ 4 8 9 12 14]
[ 0 1 2 3 4 7 8 9 10 12 13 14 15 16 17 18 19 22] [ 5 6 11 20 21]
[ 1 2 3 4 5 6 8 9 10 11 12 13 14 15 18 19 20 21 22] [ 0 7 16 17]
[ 0 1 2 4 5 6 7 8 9 11 12 13 14 16 17 18 20 21 22] [ 3 10 15 19]