『Sklearn』数据划分方法

原理介绍

K折交叉验证：

KFold，GroupKFold，StratifiedKFold，

留一法：

LeaveOneGroupOut，LeavePGroupsOut，LeaveOneOut，LeavePOut，

随机划分法：

ShuffleSplit，GroupShuffleSplit，StratifiedShuffleSplit，

代码实现

流程：

实例化分类器 -> 迭代器迭代组[.split()]

KFold(n_splits=2)

#KFoldimport numpy as np
from sklearn.model_selection import KFold
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
kf=KFold(n_splits=2)    # 定义分成几个组
# kf.get_n_splits(X)    # 查询分成几个组
print(kf)
for train_index,test_index in kf.split(X):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)

GroupKFold(n_splits=2)

# GroupKFold，不是很懂这个划分方法
import numpy as np
from sklearn.model_selection import GroupKFold
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
groups=np.array([1,2,3,4,5,6])
group_kfold=GroupKFold(n_splits=2)
group_kfold.get_n_splits(X,y,groups)
print(group_kfold)
for train_index,test_index in group_kfold.split(X,y,groups):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)

#GroupKFold(n_splits=2)
#Train Index: [0 2 4] ,Test Index: [1 3 5]
#Train Index: [1 3 5] ,Test Index: [0 2 4]

StratifiedKFold(n_splits=3)

# stratifiedKFold：保证训练集中每一类的比例是相同的（尽量）
import numpy as np
from sklearn.model_selection import StratifiedKFold
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,1,1,2,2,2])
skf=StratifiedKFold(n_splits=3)
skf.get_n_splits(X,y)
print(skf)
for train_index,test_index in skf.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)

#StratifiedKFold(n_splits=3, random_state=None, shuffle=False)
#Train Index: [1 2 4 5] ,Test Index: [0 3]
#Train Index: [0 2 3 5] ,Test Index: [1 4]

LeaveOneOut()

# leaveOneOut：测试集就留下一个
import numpy as np
from sklearn.model_selection import LeaveOneOut
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
loo=LeaveOneOut()
loo.get_n_splits(X)
print(loo)
for train_index,test_index in loo.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)
#LeaveOneOut()
#Train Index: [1 2 3 4 5] ,Test Index: [0]
#Train Index: [0 2 3 4 5] ,Test Index: [1]
#Train Index: [0 1 3 4 5] ,Test Index: [2]
#Train Index: [0 1 2 4 5] ,Test Index: [3]
#Train Index: [0 1 2 3 5] ,Test Index: [4]
#Train Index: [0 1 2 3 4] ,Test Index: [5]

LeavePOut(p=3)

LeavePOut：测试集留下P个
import numpy as np
from sklearn.model_selection import LeavePOut
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
lpo=LeavePOut(p=3)
lpo.get_n_splits(X)
print(lpo)
for train_index,test_index in lpo.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)

#LeavePOut(p=3)
#Train Index: [3 4 5] ,Test Index: [0 1 2]
#Train Index: [2 4 5] ,Test Index: [0 1 3]
#Train Index: [2 3 5] ,Test Index: [0 1 4]
#Train Index: [2 3 4] ,Test Index: [0 1 5]
#Train Index: [1 4 5] ,Test Index: [0 2 3]
#Train Index: [1 3 5] ,Test Index: [0 2 4]
#Train Index: [1 3 4] ,Test Index: [0 2 5]
#Train Index: [1 2 5] ,Test Index: [0 3 4]
#Train Index: [1 2 4] ,Test Index: [0 3 5]
#Train Index: [1 2 3] ,Test Index: [0 4 5]
#Train Index: [0 4 5] ,Test Index: [1 2 3]
#Train Index: [0 3 5] ,Test Index: [1 2 4]
#Train Index: [0 3 4] ,Test Index: [1 2 5]
#Train Index: [0 2 5] ,Test Index: [1 3 4]
#Train Index: [0 2 4] ,Test Index: [1 3 5]
#Train Index: [0 2 3] ,Test Index: [1 4 5]
#Train Index: [0 1 5] ,Test Index: [2 3 4]
#Train Index: [0 1 4] ,Test Index: [2 3 5]
#Train Index: [0 1 3] ,Test Index: [2 4 5]
#Train Index: [0 1 2] ,Test Index: [3 4 5]

ShuffleSplit(n_splits=3,test_size=.25,random_state=0)

#ShuffleSplit 把数据集打乱顺序，然后划分测试集和训练集，训练集额和测试集的比例随机选定，训练集和测试集的比例的和可以小于1
 
import numpy as np
from sklearn.model_selection import ShuffleSplit
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,3,4,5,6])
rs=ShuffleSplit(n_splits=3,test_size=.25,random_state=0)
rs.get_n_splits(X)
print(rs)
for train_index,test_index in rs.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)
print("==============================")
rs=ShuffleSplit(n_splits=3,train_size=.5,test_size=.25,random_state=0)
rs.get_n_splits(X)
print(rs)
for train_index,test_index in rs.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)

#ShuffleSplit(n_splits=3, random_state=0, test_size=0.25, train_size=None)
#Train Index: [1 3 0 4] ,Test Index: [5 2]
#Train Index: [4 0 2 5] ,Test Index: [1 3]
#Train Index: [1 2 4 0] ,Test Index: [3 5]
#==============================
#ShuffleSplit(n_splits=3, random_state=0, test_size=0.25, train_size=0.5)
#Train Index: [1 3 0] ,Test Index: [5 2]
#Train Index: [4 0 2] ,Test Index: [1 3]
#Train Index: [1 2 4] ,Test Index: [3 5]

StratifiedShuffleSplit(n_splits=3,test_size=.5,random_state=0)

# StratifiedShuffleSplitShuffleSplit 把数据集打乱顺序，然后划分测试集和训练集，
# 训练集额和测试集的比例随机选定，训练集和测试集的比例的和可以小于1,但是还要保证训练集中各类所占的比例是一样的

import numpy as np
from sklearn.model_selection import StratifiedShuffleSplit
X=np.array([[1,2],[3,4],[5,6],[7,8],[9,10],[11,12]])
y=np.array([1,2,1,2,1,2])
sss=StratifiedShuffleSplit(n_splits=3,test_size=.5,random_state=0)
sss.get_n_splits(X,y)
print(sss)
for train_index,test_index in sss.split(X,y):
    print("Train Index:",train_index,",Test Index:",test_index)
    X_train,X_test=X[train_index],X[test_index]
    y_train,y_test=y[train_index],y[test_index]
    #print(X_train,X_test,y_train,y_test)

#StratifiedShuffleSplit(n_splits=3, random_state=0, test_size=0.5,train_size=None)
#Train Index: [5 4 1] ,Test Index: [3 2 0]
#Train Index: [5 2 3] ,Test Index: [0 4 1]
#Train Index: [5 0 4] ,Test Index: [3 1 2]

时间： 2024-12-29 05:12:24

『Sklearn』数据划分方法的相关文章

『Sklearn』自带数据集API

自带数据集类型如下: # 自带小型数据集# sklearn.datasets.load_<name># 在线下载数据集# sklearn.datasets.fetch_<name># 计算机生成数据集# sklearn.datasets.make_<name># svmlight/libsvm格式数据集# sklearn.datasets.load_svmlight_file(path)# mldata.org在线下载网站数据集# sklearn.datasets.fe

『Sklearn』机器学习概述

机器学习概述 SKLearn相关模块老师扯得闲篇

『Sklearn』机器学习绪论

机器学习目标: 1.一定的自主能力 2.进化能力方法: 1.归纳统计:经验结论 2.演绎推理:逻辑结论流程: 原始数据 -> 特征提取 -> 学习机器 -> 规律知识主要内容: 1.特征提取 2.学习机器应用:

『Sklearn』学习器设计

机器学习问题是一个搜索优化问题思路实例--人工智能西洋棋学习器

JS 中通过对象关联实现『继承』

JS 中继承其实是种委托,而不是传统面向对象中的复制父类到子类,只是通过原型链将要做的事委托给父类. 下面介绍通过对象关联来实现『继承』的方法: Foo = { // 需要提供一个 init 方法来初始化参数,而不能通过构造函数来初始化参数了 init: function(who) { this.me = who; }, identify: function() { return "I am " + this.me; } }; Bar = Object.create(Foo); //

『行式报表』通过方法对数据进行过滤

(关于Scriptcase产品,请查看 http://www.phpscriptcase.com 查看相关功能) Scriptcase提供了方便的方式直接创建行式报表,可以一键生成简单.直接的报表.Scriptcase会根据数据机构,自动判断其数据类型,并且生成相应格式的字段(如整形.字符型.图片型等等). 使用Scriptcase创建行式报表虽然方便,但是实际的工作中我们一定会遇到这样的问题: 当前用户只允许查看自己的记录: 组管理员(或者部门管理员)允许查看本组(部门)的数据,对自己的数据可

『TensorFlow』读书笔记_降噪自编码器

『TensorFlow』降噪自编码器设计之前学习过的代码,又敲了一遍,新的收获也还是有的,因为这次注释写的比较详尽,所以再次记录一下,具体的相关知识查阅之前写的文章即可(见上面链接). # Author : Hellcat # Time : 2017/12/6 import numpy as np import sklearn.preprocessing as prep import tensorflow as tf from tensorflow.examples.tutorials.mni

『TensorFlow』函数查询列表_神经网络相关

神经网络(Neural Network) 激活函数(Activation Functions) 操作描述 tf.nn.relu(features, name=None) 整流函数:max(features, 0) tf.nn.relu6(features, name=None) 以6为阈值的整流函数:min(max(features, 0), 6) tf.nn.elu(features, name=None) elu函数,exp(features) - 1 if < 0,否则featuresE

『AngularJS』$location 服务

参考: ng.$location Developer Guide: Angular Services: Using $location 简介 $location服务解析在浏览器地址栏中的URL(基于window.location)并且让URL在你的应用中可用.改变在地址栏中的URL会作用到$location服务,同样的,改变$location服务也会改变浏览器的地址栏.(可以使用$location进行重定向等操作) $location服务: 暴露浏览器地址栏中的URL,让你可以: 监察URL.