blocks|key|1805127|text|R中的caret包具有丰富的功能，可以很容易地在您提到的算法之间进行切换。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1805128|他们的网站上也有很多文档：|1805129|1805130|http://topepo.github.io/caret/featureselection.html，以概括介绍caret|unordered-list-item|1805131|http://topepo.github.io/caret/rfe.html中的特征选择，以便为遗传算法实现递归特征elimination|1805132|http://topepo.github.io/caret/GA.html。|1805133|1805134|希望这能有所帮助|1805135|entityMap|0|LINK|mutability|MUTABLE|url|http://topepo.github.io/caret/featureselection.html|1|http://topepo.github.io/caret/rfe.html|2|http://topepo.github.io/caret/GA.html^0|3|5|0|0|0|0|1F|0|0|0|12|1|0|0|11|2|0|0|0^^$0|@$1|2|3|4|5|6|7|14|8|@$9|15|A|16|B|C]]|D|@]|E|$]]|$1|F|3|G|5|6|7|17|8|@]|D|@]|E|$]]|$1|H|3|-4|5|6|7|18|8|@]|D|@]|E|$]]|$1|I|3|J|5|K|7|19|8|@]|D|@$9|1A|A|1B|1|1C]]|E|$]]|$1|L|3|M|5|K|7|1D|8|@]|D|@$9|1E|A|1F|1|1G]]|E|$]]|$1|N|3|O|5|K|7|1H|8|@]|D|@$9|1I|A|1J|1|1K]]|E|$]]|$1|P|3|-4|5|6|7|1L|8|@]|D|@]|E|$]]|$1|Q|3|R|5|6|7|1M|8|@]|D|@]|E|$]]|$1|S|3|-4|5|6|7|1N|8|@]|D|@]|E|$]]]|T|$U|$5|V|W|X|E|$Y|Z]]|10|$5|V|W|X|E|$Y|11]]|12|$5|V|W|X|E|$Y|13]]]]

The <code>caret</code> package in R has extensive functionality for doing this, and it would be very easy to switch amongst the algorithms you mentioned.

There is also a lot of documentation on their site:

<ul>
<li><a href="http://topepo.github.io/caret/featureselection.html" rel="nofollow">http://topepo.github.io/caret/featureselection.html</a> for a general overview of feature selection in caret</li>
<li><a href="http://topepo.github.io/caret/rfe.html" rel="nofollow">http://topepo.github.io/caret/rfe.html</a> to implement recursive feature elimination</li>
<li><a href="http://topepo.github.io/caret/GA.html" rel="nofollow">http://topepo.github.io/caret/GA.html</a> for genetic algorithms. </li>
</ul>

Hope this helps

blocks|key|1620940|text|下面是一些用于正向特征选择的代码|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1620941|selectFeature+<-+function(train,+test,+cls.train,+cls.test,+features)+{
++##+identify+a+feature+to+be+selected
++current.best.accuracy+<-+-Inf+#nagtive+infinity
++selected.i+<-+NULL
++for(i+in+1:ncol(train))+{
++++current.f+<-+colnames(train)[i]
++++if(!current.f+%25in%25+features)+{
++++++model+<-+knn(train=train[,c(features,+current.f)],++++++test=test[,c(features,+current.f)],+cl=cls.train,+k=3)
++++++test.acc+<-+sum(model+==+cls.test)+/+length(cls.test)

++++++if(test.acc+>+current.best.accuracy)+{
++++++++current.best.accuracy+<-+test.acc
++++++++selected.i+<-+colnames(train)[i]
++++++}
++++}
++}
++return(selected.i)
}


##
library(caret)
set.seed(1)
inTrain+<-+createDataPartition(Sonar$Class,+p+=+.6)[[1]]
allFeatures+<-+colnames(Sonar)[-61]
train+<-+Sonar[+inTrain,-61]
test++<-+Sonar[-inTrain,-61]
cls.train+<-+Sonar$Class[inTrain]
cls.test+<-+Sonar$Class[-inTrain]

#+use+correlation+to+determine+the+first+feature
cls.train.numeric+<-+rep(c(0,+1),+c(sum(cls.train+==+"R"),+++sum(cls.train+==+"M")))
features+<-+c()
current.best.cor+<-+0
for(i+in+1:ncol(train[,-61]))+{
++if(current.best.cor+<+abs(cor(train[,i],+cls.train.numeric)))+{
++++current.best.cor+<-+abs(cor(train[,i],+cls.train.numeric))
++++features+<-+colnames(train)[i]
++}
}
print(features)

#+select+the+2+to+10+best+features+using+knn+as+a+wrapper+classifier
for+(j+in+2:10)+{
++selected.i+<-+selectFeature(train,+test,+cls.train,+cls.test,+features)
++print(selected.i)

++#+add+the+best+feature+from+current+run
++features+<-+c(features,+selected.i)
}|code-block|syntax|javascript|1620942|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Here is some code for forward feature selection

<pre><code>selectFeature &lt;- function(train, test, cls.train, cls.test, features) {
 ## identify a feature to be selected
 current.best.accuracy &lt;- -Inf #nagtive infinity
 selected.i &lt;- NULL
 for(i in 1:ncol(train)) {
 current.f &lt;- colnames(train)[i]
 if(!current.f %in% features) {
 model &lt;- knn(train=train[,c(features, current.f)], test=test[,c(features, current.f)], cl=cls.train, k=3)
 test.acc &lt;- sum(model == cls.test) / length(cls.test)

 if(test.acc &gt; current.best.accuracy) {
 current.best.accuracy &lt;- test.acc
 selected.i &lt;- colnames(train)[i]
 }
 }
 }
 return(selected.i)
}


##
library(caret)
set.seed(1)
inTrain &lt;- createDataPartition(Sonar$Class, p = .6)[[1]]
allFeatures &lt;- colnames(Sonar)[-61]
train &lt;- Sonar[ inTrain,-61]
test &lt;- Sonar[-inTrain,-61]
cls.train &lt;- Sonar$Class[inTrain]
cls.test &lt;- Sonar$Class[-inTrain]

# use correlation to determine the first feature
cls.train.numeric &lt;- rep(c(0, 1), c(sum(cls.train == "R"), sum(cls.train == "M")))
features &lt;- c()
current.best.cor &lt;- 0
for(i in 1:ncol(train[,-61])) {
 if(current.best.cor &lt; abs(cor(train[,i], cls.train.numeric))) {
 current.best.cor &lt;- abs(cor(train[,i], cls.train.numeric))
 features &lt;- colnames(train)[i]
 }
}
print(features)

# select the 2 to 10 best features using knn as a wrapper classifier
for (j in 2:10) {
 selected.i &lt;- selectFeature(train, test, cls.train, cls.test, features)
 print(selected.i)

 # add the best feature from current run
 features &lt;- c(features, selected.i)
}
</code></pre>

blocks|key|1609993|text|我现在正在测试包装器，所以我会在R中给你几个Pacckage名称。什么是wrapper？|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1609994|📷|atomic|1609995|​|1609996|现在使用的方法是:+MASS+Package：在逐步算法中选择一个模型|style|BOLD|1609997|stepAIC(model,+direction+=+"both",+trace+=+FALSE)+stepAIC(model,+direction+=+"backward",+trace+=+FALSE)+stepAIC(model,+direction+=+"forward",+trace+=+FALSE)|CODE|1609998|点菜套餐：Backwards+Feature+Selection|1609999|control+<-+rfeControl(functions+=+lmFuncs,+method+=+"repeatedcv",+number+=+5,+verbose+=+TRUE)
rfe_results+<-+rfe(x,+y,+sizes+=+c(1:10),+rfeControl+=+control)|code-block|syntax|javascript|1610000|或使用遗传算法的监督特征选择|1610001|gafs_results+<-+gafs(x,+y,+gafsControl+=+control)|1610002|或模拟退火特征选择|1610003|safs_results+<-++safs(x,+y,+iters+=+10,+safsControl+=+control)|1610004|希望我能给你一个很好的概述。有更多的方法...|1610005|entityMap|0|LINK|mutability|MUTABLE|url|https://www.analyticsvidhya.com/blog/2016/12/introduction-to-feature-selection-methods-with-an-example-or-how-to-select-the-right-variables/|1|IMAGE|IMMUTABLE|imageUrl|https://ask.qcloudimg.com/http-save/yehe-900000/bb006b2883036d8515fde6ac48d4bdde.png|imageAlt^0|10|7|0|0|0|1|1|0|0|N|5|0|0|4C|0|5|R|0|0|8|6|0|0|0|9|0|0|0|N|0^^$0|@$1|2|3|4|5|6|7|1K|8|@]|9|@$A|1L|B|1M|1|1N]]|C|$]]|$1|D|3|E|5|F|7|1O|8|@]|9|@$A|1P|B|1Q|1|1R]]|C|$]]|$1|G|3|H|5|6|7|1S|8|@]|9|@]|C|$]]|$1|I|3|J|5|6|7|1T|8|@$A|1U|B|1V|K|L]]|9|@]|C|$]]|$1|M|3|N|5|6|7|1W|8|@$A|1X|B|1Y|K|O]]|9|@]|C|$]]|$1|P|3|Q|5|6|7|1Z|8|@$A|20|B|21|K|L]]|9|@]|C|$]]|$1|R|3|S|5|T|7|22|8|@]|9|@]|C|$U|V]]|$1|W|3|X|5|6|7|23|8|@$A|24|B|25|K|L]]|9|@]|C|$]]|$1|Y|3|Z|5|T|7|26|8|@]|9|@]|C|$U|V]]|$1|10|3|11|5|6|7|27|8|@$A|28|B|29|K|L]]|9|@]|C|$]]|$1|12|3|13|5|T|7|2A|8|@]|9|@]|C|$U|V]]|$1|14|3|15|5|6|7|2B|8|@$A|2C|B|2D|K|L]]|9|@]|C|$]]|$1|16|3|-4|5|6|7|2E|8|@]|9|@]|C|$]]]|17|$18|$5|19|1A|1B|C|$1C|1D]]|1E|$5|1F|1A|1G|C|$1H|1I|1J|-4]]]]

I'm testing wrappers at the moment so I'll give you a few Pacckage names in R. What is a <a href="https://www.analyticsvidhya.com/blog/2016/12/introduction-to-feature-selection-methods-with-an-example-or-how-to-select-the-right-variables/" rel="nofollow noreferrer">wrapper</a>? <a href="https://i.stack.imgur.com/cTR95.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/cTR95.png" alt="enter image description here"></a>

Now to the Methods:
MASS Package: Choose a model by AIC in a Stepwise Algorithm

<code>stepAIC(model, direction = "both", trace = FALSE)
stepAIC(model, direction = "backward", trace = FALSE)
stepAIC(model, direction = "forward", trace = FALSE)</code>

Carte Package: Backwards Feature Selection 

<pre><code>control &lt;- rfeControl(functions = lmFuncs, method = "repeatedcv", number = 5, verbose = TRUE)
rfe_results &lt;- rfe(x, y, sizes = c(1:10), rfeControl = control)
</code></pre>

or Supervised feature selection using genetic algorithms

<pre><code>gafs_results &lt;- gafs(x, y, gafsControl = control)
</code></pre>

or Simulated annealing feature selection

<pre><code>safs_results &lt;- safs(x, y, iters = 10, safsControl = control)
</code></pre>

hope i could give you a good overview. There are a lot more Methods out there...

I have several algorithms: rpart, kNN, logistic regression, randomForest, Naive Bayes, and SVM. I'd like to use forward/backward and genetic algorithm selection for finding the best subset of features to use for the particular algorithms.

How can I implement wrapper type forward/backward and genetic selection of features in R?

How to use wrapper feature selection algorithms in R?

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

我有几种算法: rpart，kNN，logistic回归，randomForest，朴素贝叶斯和支持向量机。我想使用前向/后向和遗传算法选择来找到用于特定算法的最佳特征子集。我如何在R中实现包装器类型的向前/向后和特征的遗传选择？

问如何在R中使用包装器特征选择算法？
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问如何在R中使用包装器特征选择算法？EN