UfsCov_ff {SFtools} | R Documentation |
UfsCov for unsupervised features selection
Description
Applies the UfsCov algorithm based on the space filling concept, by using a sequatial forward search (for memory efficient storage of large data on disk and fast access).
Usage
UfsCov_ff(data, blocks=2)
Arguments
data |
Data of class: |
blocks |
Number of splits to facilitate the computation of the distance matrix (by default: blocks=2). |
Value
A list of two elements:
-
CovD
a vector containing the coverage measure of each step of the SFS. -
IdR
a vector containing the added variables during the selection procedure.
Note
This function is still under developement.
Author(s)
Mohamed Laib Mohamed.Laib@unil.ch
References
M. Laib and M. Kanevski (2017). Unsupervised Feature Selection Based on Space Filling Concept, arXiv:1706.08894.
Examples
## Not run:
#### Infinity dataset ####
N <- 1000
dat<-Infinity(N)
Results<- UfsCov_ff(dat)
cou<-colnames(dat)
nom<-cou[Results[[2]]]
par(mfrow=c(1,1), mar=c(5,5,2,2))
names(Results[[1]])<-cou[Results[[2]]]
plot(Results[[1]] ,pch=16,cex=1,col="blue", axes = FALSE,
xlab = "Added Features", ylab = "Coverage measure")
lines(Results[[1]] ,cex=2,col="blue")
grid(lwd=1.5,col="gray" )
box()
axis(2)
axis(1,1:length(nom),nom)
which.min(Results[[1]])
#### Butterfly dataset ####
require(IDmining)
N <- 1000
raw_dat <- Butterfly(N)
dat<-raw_dat[,-9]
Results<- UfsCov_ff(dat)
## End(Not run)
[Package SFtools version 0.1.0 Index]