找回密码
 注册
查看: 410|回复: 0

R语言 fabia包 spfabia()函数中文帮助文档(中英文对照)

[复制链接]
发表于 2012-2-25 17:31:57 | 显示全部楼层 |阅读模式
spfabia(fabia)
spfabia()所属R语言包:fabia

                                        Factor Analysis for Bicluster Acquisition: SPARSE FABIA
                                         因子分析Bicluster收购:稀疏斯柯达法比亚

                                         译者:生物统计家园网 机器人LoveR

描述----------Description----------

spfabia: C implementation of  spfabia.
spfabia:C的spfabia实施。


用法----------Usage----------



spfabia(X,p=5,alpha=0.1,cyc=500,spl=0,spz=0.5,non_negative=0,random=1.0,write_file=1,norm=1,scale=0.0,lap=1.0,nL=0,lL=0,bL=0,samples=0,initL=0,iter=1,quant=0.001,lowerB=0.0,upperB=1000.0)




参数----------Arguments----------

参数:X
the file name of the sparse matrix in sparse format.
稀疏矩阵稀疏格式的文件名。


参数:p
number of hidden factors = number of biclusters; default = 5.
隐性因素数=的biclusters;默认值= 5。


参数:alpha
sparseness loadings (0 - 1.0); default = 0.1.
稀疏负荷(0  -  1.0);默认值= 0.1。


参数:cyc
number of iterations; default = 500.
迭代次数,默认为500。


参数:spl
sparseness prior loadings (0 - 2.0); default = 0 (Laplace).
稀疏的前负荷(0  -  2.0);默认值= 0(拉普拉斯)。


参数:spz
sparseness factors (0.5 - 2.0); default = 0.5 (Laplace).
稀疏的因素(0.5  -  2.0);默认值= 0.5(拉普拉斯)。


参数:non_negative
Non-negative factors and loadings if non_negative > 0; default = 0.
如果非消极因素和负荷non_negative> 0;默认= 0。


参数:random
>0: random initialization of loadings in [0,random], <0: random initialization of loadings in [-random,random]; default = 1.0.
> 0:0负荷的随机初始化,随机] <0:随机载荷初始化[随机,随机];默认值= 1.0。


参数:write_file
>0: results are written to files (L in sparse format), default = 1.
> 0:结果被写入到文件(sparse格式L)的,默认为1。


参数:norm
data normalization:  >0 (var=1), 0 (no); default = 1.
数据标准化:0(VAR = 1),0(无);默认值= 1。


参数:scale
loading vectors are scaled in each iteration to the given variance. 0.0 indicates non scaling; default = 0.0.
加载矢量缩放在每次迭代中给定的差异。 0.0表示不结垢;默认值= 0.0。


参数:lap
minimal value of the variational parameter; default = 1.0.  
极小值变分参数的默认值= 1.0;


参数:nL
maximal number of biclusters at which a row element can participate; default = 0 (no limit).  
数量最大的biclusters行元素可以参加;默认值= 0(没有限制)。


参数:lL
maximal number of row elements per bicluster; default = 0 (no limit).  
最大数量每bicluster行元素;默认= 0(没有限制)。


参数:bL
cycle at which the nL or lL maximum starts; default = 0 (start at the beginning).  
周期NL或LL最大开始;默认= 0(从头开始)。


参数:samples
vector of samples which should be included into the analysis; default = 0 (all samples)  
应纳入分析的样本向量;默认值= 0(所有样本)


参数:initL
vector of indices of the selected samples which are used to initialize L; default = 0 (random initialization).  
这是用来初始化大号选定样本指数的向量;默认= 0(随机初始化)。


参数:iter
number of iterations; default = 1.  
迭代次数,默认为1。


参数:quant
qunatile of largest L values to remove in each iteration; default = 0.001.  
qunatile最大的L值在每次迭代中删除;默认值= 0.001。


参数:lowerB
lower bound for filtering the inputs columns, the minimal column sum; default = 0.0.  
过滤输入列,最小的列的总和降低的约束;默认值= 0.0。


参数:upperB
upper bound for filtering the inputs columns, the maximal column sum; default = 1000.0.  
上部过滤的输入列,最大列的总和约束,默认值= 1000.0。


Details

详情----------Details----------

Version of fabia for a sparse data matrix. The data matrix is directly scanned by the C-code and must be in sparse matrix format.
稀疏数据矩阵FABIA版本。由C代码和数据矩阵直接扫描必须在稀疏矩阵格式。

Sparse matrix format: *first line: numer of columns (the samples). *second line: number of rows (the features). *following lines: for each sample (column) three lines with
稀疏矩阵格式:*第一行:高等学校计算列(样品) *第二行的行数(功能)。 *以下行:每个样品(列)三线

I) number of nonzero row elements
我)数非零行元素

II) indices of the nonzero row elements
二)非零行元素的指数

III) values of the nonzero row elements
三)非零行元素的值

Biclusters are found by sparse factor analysis where both the factors and the loadings are sparse.
biclusters发现稀疏的因子分析的因素和负荷稀疏。

Essentially the model is the sum of outer products of vectors:
模型本质上是向量外产品的总和:

where the number of summands  p is the number of biclusters. The matrix factorization is
加数p是的biclusters数量。矩阵分解

Here &lambda;_i are from R^n, z_i from R^l, L from R^{n \times p}, Z from R^{p \times l}, and X, U from R^{n \times l}.
这里&lambda;_iR^n,z_iR^l,LR^{n \times p},ZR^{p \times l} X,UR^{n \times l}。

If the nonzero components of the sparse vectors are grouped together then the outer product results in a matrix with a nonzero block and zeros elsewhere.
如果稀疏向量的非零组件被组合在一起,然后在同一个非零块矩阵和零别处外产品的结果。

The model selection is performed by a variational approach according to Girolami 2001 and Palmer et al. 2006.
模型的选择是由变分法,根据2001年Girolami和帕尔默等。 2006年。

We included a prior on the parameters and minimize a lower bound on the posterior of the parameters given the data. The update of the loadings includes an additive term which pushes the loadings toward zero (Gaussian prior leads to an multiplicative factor).
我们包括之前的参数,并最大限度地减少后提供的数据参数约束的下限。负荷的更新包括添加剂术语推趋于零(高斯之前导致乘法因子)的负荷。

The code is implemented in C.
在C代码实现


值----------Value----------


参数:
object of the class Factorization. Containing L (loadings  L), Z (factors  Z), Psi (noise variance &sigma;), lapla (variational parameter), avini (the information which the factor z_{ij} contains about x_j averaged over j) xavini (the information which the factor z_{j} contains about x_j) ini (for each j the information which the factor z_{ij} contains about x_j).  
对象类Factorization。含有L(负荷L)Z(因素Z)Psi(噪声方差&sigma;)lapla(变参数),avini(因素z_{ij}约x_j多j)xavini(信息的因素z_{j}平均包含的信息包含有关x_j)ini(每个j的因素z_{ij}约x_j包含的信息)。


作者(S)----------Author(s)----------


Sepp Hochreiter



参考文献----------References----------

&lsquo;FABIA: Factor Analysis for Bicluster Acquisition&rsquo;, Bioinformatics 26(12):1520-1527, 2010. http://bioinformatics.oxfordjournals.org/cgi/content/abstract/btq227
&lsquo;A Variational Method for Learning Sparse and Overcomplete Representations&rsquo;, Neural Computation 13(11): 2517-2532, 2001.
&lsquo;Variational EM algorithms for non-Gaussian latent variable models&rsquo;, Advances in Neural Information Processing Systems 18, pp. 1059-1066, 2006.

参见----------See Also----------

fabia, fabias, fabiap, spfabia, readSamplesSpfabia, readSpfabiaResult, fabi, fabiasp, mfsc, nmfdiv, nmfeu, nmfsc, plot, extractPlot, extractBic, plotBicluster, Factorization, projFuncPos, projFunc, estimateMode, makeFabiaData, makeFabiaDataBlocks, makeFabiaDataPos, makeFabiaDataBlocksPos, matrixImagePlot, summary, show, showSelected, fabiaDemo, fabiaVersion
fabia,fabias,fabiap,spfabia,readSamplesSpfabia,readSpfabiaResult,fabi,fabiasp,mfsc,nmfdiv,nmfeu,nmfsc,plot,extractPlot,extractBic,plotBicluster,Factorization ,projFuncPos,projFunc,estimateMode,makeFabiaData,makeFabiaDataBlocks,makeFabiaDataPos,makeFabiaDataBlocksPos,matrixImagePlot summary,show,showSelected,fabiaDemo,fabiaVersion


举例----------Examples----------



#---------------[---------------]
# TEST[试验]
#---------------[---------------]

samples <- 20
features <- 200
sparseness <- 0.9
write(samples, file = "sparseFarmsTest.txt",ncolumns = features,append = FALSE, sep = " ")
write(features, file = "sparseFarmsTest.txt",ncolumns = features,append = TRUE, sep = " ")
for (i in 1:samples)
{
  ind <- which(runif(features)>sparseness)-1
  num <- length(ind)
  val <- abs(rnorm(num))
  write(num, file = "sparseFarmsTest.txt",ncolumns = features,append = TRUE, sep = " ")
  write(ind, file = "sparseFarmsTest.txt",ncolumns = features,append = TRUE, sep = " ")
  write(val, file = "sparseFarmsTest.txt",ncolumns = features,append = TRUE, sep = " ")
}

res <- spfabia("sparseFarmsTest",p=3,alpha=0.03,cyc=50,non_negative=1,write_file=0,norm=0)

unlink("sparseFarmsTest.txt")

plot(res,dim=c(1,2))
plot(res,dim=c(1,3))
plot(res,dim=c(2,3))




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。
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 注册

本版积分规则

手机版|小黑屋|生物统计家园 网站价格

GMT+8, 2025-2-9 08:01 , Processed in 0.025695 second(s), 16 queries .

Powered by Discuz! X3.5

© 2001-2024 Discuz! Team.

快速回复 返回顶部 返回列表