sklearn代码9 7-KNN-salay

import numpy as np

import pandas as pd

from sklearn.neighbors import KNeighborsClassifier

from sklearn.model_selection import train_test_split

# cv int 6 数据分成6份
from sklearn.model_selection import  cross_val_score,GridSearchCV

# KFold、StratifiedKFold 将数据分成多少分
from sklearn.model_selection import KFold,StratifiedKFold

data = np.random.randint(0,10,size = (8,2)) # 从0，10中随机取数 目标值分八组，每组两个

target = np.array([0,0,1,0,1,1,1,0])
display(data,target)

array([[4, 1],
       [5, 4],
       [2, 5],
       [6, 8],
       [7, 2],
       [4, 2],
       [7, 0],
       [6, 4]])



array([0, 0, 1, 0, 1, 1, 1, 0])

train_test_split(data,target)  #对数据进行划分

[array([[6, 4],
        [7, 0],
        [7, 2],
        [6, 8],
        [4, 2],
        [2, 5]]), array([[4, 1],
        [5, 4]]), array([0, 1, 1, 0, 1, 1]), array([0, 0])]

kFold = KFold(n_splits = 4)

# train，test是索引，只要有索引就可以获取数据
for train,test in kFold.split(data,target):  # 生成器
    print(target[train],target[test])

[1 0 1 1 1 0] [0 0]
[0 0 1 1 1 0] [1 0]
[0 0 1 0 1 0] [1 1]
[0 0 1 0 1 1] [