superpc.decorrelate {superpc} | R Documentation |
Fits a linear model to the features as a function of some competing predictors. Replaces the features by the residual from this fit. These "decorrelated" features are then used in the superpc model building process, to explicitly look for predictors that are independent of the competing predictors. Useful for example, when the competing predictors are clinical predictors like stage, grade etc.
superpc.decorrelate(x, competing.predictors)
x |
matrix of features. Different features in different rows, one observation per column |
competing.predictors |
List of one or more competing predictors. Discrete predictors should be factors |
Returns lm (linear model) fit of rows of x on compeiting predictors
~~further notes~~
Eric Bair and Robert Tibshirani
~put references to the literature/web site here ~
set.seed(332) #generate some data x<-matrix(rnorm(1000*20),ncol=20) y<-10+svd(x[1:30,])$v[,1]+ .1*rnorm(20) ytest<-10+svd(x[1:30,])$v[,1]+ .1*rnorm(20) censoring.status<- sample(c(rep(1,17),rep(0,3))) censoring.status.test<- sample(c(rep(1,17),rep(0,3))) competing.predictors=list(pred1=rnorm(20), pred2=as.factor(sample(c(1,2),replace=TRUE,size=20))) featurenames <- paste("feature",as.character(1:1000),sep="") # decorrelate x foo<-superpc.decorrelate(x,competing.predictors) xnew<-t(foo$res) # now use xnew in superpc data<-list(x=xnew,y=y, censoring.status=censoring.status, featurenames=featurenames) a<- superpc.train(data, type="survival") # etc. Remember to decorrelate test data in the same way, before making predictions.