ElasticNetCMA(CMA)
ElasticNetCMA()所属R语言包：CMA
Classfication and variable selection by the ElasticNet
分类及变量选择的ElasticNet
译者：生物统计家园网 机器人LoveR
描述----------Description----------
Zou and Hastie (2004) proposed a combined L1/L2 penalty for regularization and variable selection. The Elastic Net penalty encourages a grouping effect, where strongly correlated predictors tend to be in or out of the model together. The computation is done with the function glmpath from the package of the same name.<br> The method can be used for variable selection alone, s. GeneSelection.<br>
邹和哈斯蒂（2004）提出了正规化和变量选择合并的L1/L2罚款。弹性净罚款鼓励分组的效果，其中密切相关的预测往往模型在了一起。计算功能glmpath来自同名的软件包。参考变量选择该方法可以单独使用的。 GeneSelection参考。
用法----------Usage----------
ElasticNetCMA(X, y, f, learnind, norm.fraction = 0.1, alpha=0.5, models=FALSE, ...)
参数----------Arguments----------
参数：X
Gene expression data. Can be one of the following:
基因表达数据。可以是下列之一：
A matrix. Rows correspond to observations, columns to variables.
Amatrix。行对应的观察，列变量。
A data.frame, when f is not missing (s. below).
一个data.frame时f不缺少（S.下面）。
An object of class ExpressionSet. note: by default, the predictors are scaled to have unit variance and zero mean. Can be changed by passing standardize = FALSE via the ... argument.
对象类ExpressionSet。注：默认情况下，预测缩小到单位方差和零均值。传递standardize = FALSE通过...参数是可以改变的。
参数：y
Class labels. Can be one of the following:
类的标签。可以是下列之一：
A numeric vector.
一个numeric向量。
A factor.
Afactor。
A character if X is an ExpressionSet that specifies the phenotype variable.
一个如果character X是一个ExpressionSet指定的表型变量。
missing, if X is a data.frame and a proper formula f is provided.
missing，X是data.frame和适当的公式f提供。
WARNING: The class labels will be re-coded to range from 0 to K-1, where K is the total number of different classes in the learning set.
警告：类标签将被重新编码范围从0K-1，K是在学习集不同类别的总数。
参数：f
A two-sided formula, if X is a data.frame. The left part correspond to class labels, the right to variables.
一个双面的公式，如果X是data.frame。左边部分对应类的标签，对变量的权利。
参数：learnind
An index vector specifying the observations that belong to the learning set. May be missing; in that case, the learning set consists of all observations and predictions are made on the learning set.
索引向量指定属于学习集的意见。可能missing;在这种情况下，学习组学习集的所有意见和预测。
参数：norm.fraction
L1 Shrinkage intensity, expressed as the fraction of the coefficient L1 norm compared to the maximum possible L1 norm (corresponds to fraction = 1). Lower values correspond to higher shrinkage. Note that the default (0.1) need not produce good results, i.e. tuning of this parameter is recommended.
L1收缩强度系数L1范数的比例相比，最大可能的L1范数（对应fraction = 1）表示。较低的值对应较高的收缩。请注意，默认情况下（0.1）不需要产生了良好的效果，即此参数的调整建议。
参数：alpha
The elasticnet mixing parameter, with 0<alpha<= 1. The penalty is defined as (1-alpha)/2||beta||_2^2+alpha||beta||_1. alpha=1 is the lasso penalty; Currently 'alpha<0.01' not reliable, unless you supply your own lambda sequence
elasticnet混合参数，0 <α<= 1。罚款被定义为（1-α）/ 2 | |测试| | _2的^ 2 +α| |测试| | _1。 alpha=1是的套索处罚;目前“阿尔法<0.01”不可靠的，除非你提供你自己的lambda序列
参数：models
a logical value indicating whether the model object shall be returned
一个逻辑值，该值指示是否应归还模型对象
参数：...
Further arguments passed to the function glmpath from the package of the same name.
进一步传递给函数的参数glmpath同名的软件包。
值----------Value----------
An object of class clvarseloutput.
对象类clvarseloutput。
注意----------Note----------
For a strongly related method, s. LassoCMA.<br>
一个强烈的相关方法。 LassoCMA参考。
作者（S）----------Author(s)----------
Martin Slawski <a href="mailto:ms@cs.uni-sb.de">ms@cs.uni-sb.de</a>
Anne-Laure Boulesteix <a href="mailto:boulesteix@ibe.med.uni-muenchen.de">boulesteix@ibe.med.uni-muenchen.de</a>
Christoph Bernau <a href="mailto:bernau@ibe.med.uni-muenchen.de">bernau@ibe.med.uni-muenchen.de</a>
参考文献----------References----------
Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society B, 67(2),301-320
L1-regularization path algorithm for generalized linear models.<br>
参见----------See Also----------
compBoostCMA, dldaCMA, fdaCMA, flexdaCMA, gbmCMA, knnCMA, ldaCMA, LassoCMA, nnetCMA, pknnCMA, plrCMA, pls_ldaCMA, pls_lrCMA, pls_rfCMA, pnnCMA, qdaCMA, rfCMA,
compBoostCMA，dldaCMA，fdaCMA，flexdaCMA，gbmCMA，knnCMA，ldaCMA，LassoCMA，nnetCMA，pknnCMA，plrCMA，pls_ldaCMA，pls_lrCMA，pls_rfCMA，pnnCMA，qdaCMA，rfCMA ，
举例----------Examples----------
### load Golub AML/ALL data[＃负载戈卢布反洗钱/所有数据]
data(golub)
### extract class labels[＃提取类标签]
golubY <- golub[,1]
### extract gene expression[＃提取的基因表达]
golubX <- as.matrix(golub[,-1])
### select learningset[＃选择learningset]
ratio <- 2/3
set.seed(111)
learnind <- sample(length(golubY), size=floor(ratio*length(golubY)))
### run ElasticNet - penalized logistic regression (no tuning)[＃运行处罚ElasticNet - 罗吉斯回归（无调整）]
result <- ElasticNetCMA(X=golubX, y=golubY, learnind=learnind, norm.fraction = 0.2, alpha=0.5)
show(result)
ftable(result)
plot(result)
转载请注明:出自 生物统计家园网(http://www.biostatistic.net)。
注：
注1：为了方便大家学习，本文档为生物统计家园网机器人LoveR翻译而成，仅供个人R语言学习参考使用，生物统计家园保留版权。
注2：由于是机器人自动翻译，难免有不准确之处，使用时仔细对照中、英文内容进行反复理解，可以帮助R语言的学习。
注3：如遇到不准确之处，请在本贴的后面进行回帖，我们会逐渐进行修订。
|
发表于 2012-2-25 15:19:23
