| varImpStruct-class {MLInterfaces} | R Documentation |
collects data on variable importance
Objects can be created by calls of the form new("varImpStruct", ...).
These are matrices of importance measures with separate
slots identifying algorithm generating the measures and
variable names.
.Data:"matrix" actual importance
measures method:"character" tag varnames:"character" conformant
vector of names of variables
Class "matrix", from data part.
Class "structure", by class "matrix".
Class "array", by class "matrix".
Class "vector", by class "matrix", with explicit coerce.
Class "vector", by class "matrix", with explicit coerce.
signature(x = "varImpStruct"): make a bar plot,
you can supply arguments plat
and toktype which will use lookUp(...,plat,toktype)
from the annotate package to translate probe names to, e.g.,
gene symbols.signature(object = "varImpStruct"): simple abbreviated
display signature(object = "classifOutput", fixNames="logical"): extractor
of variable importance structure; fixNames parameter is to remove leading X used
to make variable names syntactic by randomForest (ca 1/2008). You can set fixNames to false
if using hu6800 platform, because all featureNames are syntactic as given.signature(object = "classifOutput", fixNames="logical"): extractor
of variable importance data, with annotation; fixNames parameter is to remove leading X used
to make variable names syntactic by randomForest (ca 1/2008). You can set fixNames to false
if using hu6800 platform, because all featureNames are syntactic as given.library(golubEsets) data(Golub_Merge) library(hu6800.db) smallG <- Golub_Merge[1001:1060,] set.seed(1234) opar=par(no.readonly=TRUE) par(las=2, mar=c(10,11,5,5)) rf2 <- MLearn(ALL.AML~., smallG, randomForestI, 1:40, importance=TRUE, sampsize=table(smallG$ALL.AML[1:40]), mtry=sqrt(ncol(exprs(smallG)))) plot( getVarImp( rf2, FALSE ), n=10, plat="hu6800", toktype="SYMBOL") par(opar) report( getVarImp( rf2, FALSE ), n=10, plat="hu6800", toktype="SYMBOL")