The Practical Importance of Feature Selection(变量筛选重要性)
python机器学习-乳腺癌细胞挖掘(博主亲自录制视频)
https://study.163.com/course/introduction.htm?courseId=1005269003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share
原文链接
https://www.kdnuggets.com/2017/06/practical-importance-feature-selection.html
Feature selection is useful on a variety of fronts: it is the best weapon against the Curse of Dimensionality; it can reduce overall training times; and it is a powerful defense against overfitting, increasing generalizability.
特征选择在各个方面都很有用:它是反对过度拟合的最佳武器; 它可以减少整体培训时间; 它是对过度拟合,增加普遍性的有力防御。
By Matthew Mayo, KDnuggets.
If you wanted to classify animals, for example, based on a plethora of relevant collected data, you would quickly find that all sorts of potential data attributes, or features, were relatively unhelpful for classification. For example, given that most living creatures have precisely 1 heart, this particular feature would not be beneficial, from a learning perspective. On the other hand, an attribute denoting whether or not a given animal is hoofed would likely be a powerful predictor.
如果您想对动物进行分类,例如,基于过多的相关收集数据,您会很快发现各种潜在的数据属性或特征对于分类而言相对无益。例如,鉴于大多数生物只有1颗心脏,从学习的角度来看,这一特殊功能并不是有益的。另一方面,表示给定动物是否有蹄的属性可能是强有力的预测因子。
Further, using all of these irrelevant attributes, mixed in with the powerful predictors, may actually have a negative effect on the resulting model. This is to say nothing of the increased training times that may come along with the inclusion of useless attributes, or the overfitting which may occur on the training data.
此外,使用所有这些无关属性,与强大的预测变量混合,实际上可能对结果模型产生负面影响。这也就是说,可能伴随着包含无用属性或训练数据可能出现的过度拟合而增加的训练时间。
Feature selection is the process of narrowing down a subset of features, or attributes, to be used in the predictive modeling process. Feature selection is useful on a variety of fronts: it is the best weapon against the Curse of Dimensionality; it can reduce overall training times; and it is a powerful defense against overfitting, increasing model generalizability.
特征选择是缩小要在预测建模过程中使用的特征或属性子集的过程。特征选择在各个方面都很有用:它是反对维度诅咒的最佳武器; 它可以减少整体培训时间; 它是对过度拟合的强大防御,增加了模型的普遍性。
Something I read recently -- written so eloquently and concisely by data scientist Rubens Zimbres -- alludes to the importance of feature selection from a practical standpoint:
After some experiences, using stacked neural nets, parallel neural nets, asymmetric configs, simple neural nets, multiple layers, dropouts, activation functions etc there is one conclusion: There's NOTHING like a good Feature Selection.
Having had some previous professional contacts with Rubens Zimbres in the past, I reached out to him for some elaboration. He provided the following:
Feature selection should be one of the main concerns for a Data Scientist. Accuracy and generalization power can be leveraged by a correct feature selection, based in correlation, skewness, t-test, ANOVA, entropy and information gain.
Many times a correct feature selection allows you to develop simpler and faster Machine Learning models. Consider the picture below (Support Vector Machine classification of the IRIS dataset): on the left side a wrong variable selection is presented. The linear kernel cannot handle the classification task properly, neither the radial basis function kernel. On the right side, petal width and petal length were selected as features and even the linear kernel is quite accurate. A correct variable selection, a good algorithm choice and hyperparameter tuning are the keys to success. Picture below made with Python.
特征选择应该是数据科学家的主要关注点之一。基于相关性,偏度,t检验,ANOVA,熵和信息增益,通过正确的特征选择可以利用准确性和泛化能力。
很多时候,正确的功能选择可以让您开发更简单,更快速的机器学习模型。考虑下面的图片(IRIS数据集的支持向量机分类):在左侧显示错误的变量选择。线性内核无法正确处理分类任务,也不能处理径向基函数内核。在右侧,选择花瓣宽度和花瓣长度作为特征,甚至线性内核也非常准确。正确的变量选择,良好的算法选择和超参数调整是成功的关键。下面用Python制作的图片。
In a time when ample processing power can tempt us to think that feature selection may not be as relevant as it once was, it's important to remember that this only accounts for one of the numerous benefits of informed feature selection -- decreased training times. As Zimbres notes above, with a simple concrete example, feature selection can quite literally mean the difference between valid, generalizable models and a big waste of time.
在充足的处理能力可以诱使我们认为特征选择可能不像以前那样具有相关性的时代,重要的是要记住,这仅仅是知情特征选择的众多好处之一 - 减少了训练时间。 正如Zimbres上面所说,通过一个简单的具体例子,特征选择可以完全意味着有效的,可推广的模型之间的差异和浪费大量时间。
https://study.163.com/provider/400000000398149/index.htm?share=2&shareId=400000000398149( 欢迎关注博主主页,学习python视频资源,还有大量免费python经典文章)
The Practical Importance of Feature Selection(变量筛选重要性)的更多相关文章
- Feature Selection Can Reduce Overfitting And RF Show Feature Importance
一.特征选择可以减少过拟合代码实例 该实例来自机器学习实战第四章 #coding=utf-8 ''' We use KNN to show that feature selection maybe r ...
- 【转】[特征选择] An Introduction to Feature Selection 翻译
中文原文链接:http://www.cnblogs.com/AHappyCat/p/5318042.html 英文原文链接: An Introduction to Feature Selection ...
- 数据准备<5>:变量筛选-实战篇
在上一篇文章<数据准备<4>:变量筛选-理论篇>中,我们介绍了变量筛选的三种方法:基于经验的方法.基于统计的方法和基于机器学习的方法,本文将介绍后两种方法在Python(skl ...
- the steps that may be taken to solve a feature selection problem:特征选择的步骤
參考:JMLR的paper<an introduction to variable and feature selection> we summarize the steps that m ...
- [Feature] Feature selection
Ref: 1.13. Feature selection Ref: 1.13. 特征选择(Feature selection) 大纲列表 3.1 Filter 3.1.1 方差选择法 3.1.2 相关 ...
- [Feature] Feature selection - Embedded topic
基于惩罚项的特征选择法 一.直接对特征筛选 Ref: 1.13.4. 使用SelectFromModel选择特征(Feature selection using SelectFromModel) 通过 ...
- Feature Engineering and Feature Selection
首先,弄清楚三个相似但是不同的任务: feature extraction and feature engineering: 将原始数据转换为特征,以适合建模. feature transformat ...
- 机器学习-特征工程-Feature generation 和 Feature selection
概述:上节咱们说了特征工程是机器学习的一个核心内容.然后咱们已经学习了特征工程中的基础内容,分别是missing value handling和categorical data encoding的一些 ...
- 单因素特征选择--Univariate Feature Selection
An example showing univariate feature selection. Noisy (non informative) features are added to the i ...
随机推荐
- 【转】C语言宏定义的几个坑和特殊用法
总结一下C语言中宏的一些特殊用法和几个容易踩的坑.由于本文主要参考GCC文档,某些细节(如宏参数中的空格是否处理之类)在别的编译器可能有细微差别,请参考相应文档. 宏基础 宏仅仅是在C预处理阶段的一种 ...
- sqlserver 排序
sqlserver中有几种排序的方式 1.order by asc||desc [默认值升序(asc).降序:desc] 列:select * from tb order by id 2.ROW_N ...
- h5中history实例
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...
- LeetCode - 86、分隔链表
给定一个链表和一个特定值 x,对链表进行分隔,使得所有小于 x 的节点都在大于或等于 x 的节点之前. 你应当保留两个分区中每个节点的初始相对位置. 示例: 输入: head = 1->4-&g ...
- 深度学习环境搭建(CUDA9.0 + cudnn-9.0-linux-x64-v7 + tensorflow_gpu-1.8.0 + keras)
关于计算机的硬件配置说明 推荐配置 如果您是高校学生或者高级研究人员,并且实验室或者个人资金充沛,建议您采用如下配置: 主板:X299型号或Z270型号 CPU: i7-6950X或i7-7700K ...
- P2680 运输计划[二分+LCA+树上差分]
题目描述 公元20442044 年,人类进入了宇宙纪元. L 国有 nn 个星球,还有 n-1n−1 条双向航道,每条航道建立在两个星球之间,这 n-1n−1 条航道连通了 LL 国的所有星球. 小 ...
- 0029redis单机版环境搭建
linux环境下安装单机版redis,主要分为如下几步: 1. 安装gcc 2.下载安装包 3.解压安装包 4.进入解压目录并执行make和make install命令 5.查看默认安装目录 6.更改 ...
- Spring源码窥探之:FactoryBean
1. 定义Fish实体类 /** * @author 70KG * @Title: Fish * @Description: * @date 2018/7/22下午5:00 * @From www.n ...
- 如何修改host
因不可抗拒的原因,有些网站会被q,但只是比较恶心的域名DNS污染,并不需要tiizi,修改hosts文件即可. 以 www.youneed.win 为例: 首先,进入目录:C:\Windows\Sys ...
- 了解区块链&比特币
https://www.bilibili.com/video/av45247943 假如有ABCD四个比特币交易者,其中A交易给B者10个比特币(BTC),而这条信息要广播给其他所有的交易者知道. 假 ...