Prunning the Maximal tree

Description

this function is set to prune back the maximal tree by using the BIC or the AIC criterion.

Usage

best.tree.BIC.AIC(xtree, xdata, Y.name, X.names,
                  family = "binomial", verbose = TRUE)

Arguments

Value

a list of four elements:

Author(s)

Cyprien Mbogning and Wilson Toussile

References

Mbogning, C., Perdry, H., Toussile, W., Broet, P.: A novel tree-based procedure for deciphering the genomic spectrum of clinical disease entities. Journal of Clinical Bioinformatics 4:6, (2014)

Akaike, H.: A new look at the statistical model identification. IEEE Trans. Automat. Control AC-19, 716-723 (1974)

Schwarz, G.: Estimating the dimension of a model. The Annals of Statistics 6, 461-464 (1978)

See Also

best.tree.CV, pltr.glm

Examples

data(burn)

args.rpart <- list(minbucket = 10, maxdepth = 4, cp = 0, maxcompete = 0, 
                    maxsurrogate = 0)
 family <- "binomial"
 X.names = "Z2"
 Y.name = "D2"
 G.names = c('Z1','Z3','Z4','Z5','Z6','Z7','Z8','Z9','Z10','Z11')
 
pltr.burn <- pltr.glm(burn, Y.name, X.names, G.names, args.rpart = args.rpart,
                   family = family, iterMax = 4, iterMin = 3, verbose = FALSE)

## Prunned back the maximal tree using either the BIC or the AIC criterion

pltr.burn_prun <- best.tree.BIC.AIC(xtree = pltr.burn$tree, burn, Y.name, 
                                    X.names, family = family)

## plot the BIC selected tree

plot(pltr.burn_prun$tree$BIC, main = 'BIC selected tree')
text(pltr.burn_prun$tree$BIC, xpd = TRUE, cex = .6, col = 'blue')

## Not run: 
##load the data set

data(data_pltr)

## Set the parameters

args.rpart <- list(minbucket = 40, maxdepth = 10, cp = 0)
family <- "binomial"
Y.name <- "Y"
X.names <- "G1"
G.names <- paste("G", 2:15, sep="")

## build a maximal tree

fit_pltr <- pltr.glm(data_pltr, Y.name, X.names, G.names, args.rpart = args.rpart, 
                     family = family,iterMax = 5, iterMin = 3)
                     
##prunned back the maximal tree by BIC or AIC criterion

tree_select <- best.tree.BIC.AIC(xtree = fit_pltr$tree,data_pltr,Y.name, 
                                 X.names, family = family)
                            
plot(tree_select$tree$BIC, main = 'BIC TREE')
text(tree_select$tree$BIC, minlength = 0L, xpd = TRUE, cex = .6)


## End(Not run)

Results

R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(GPLTR)
Loading required package: rpart
Loading required package: parallel
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/GPLTR/best.tree.BIC.AIC.Rd_%03d_medium.png", width=480, height=480)
> ### Name: best.tree.BIC.AIC
> ### Title: Prunning the Maximal tree
> ### Aliases: best.tree.BIC.AIC
> ### Keywords: documentation tree
> 
> ### ** Examples
> 
> data(burn)
> 
> args.rpart <- list(minbucket = 10, maxdepth = 4, cp = 0, maxcompete = 0, 
+                     maxsurrogate = 0)
>  family <- "binomial"
>  X.names = "Z2"
>  Y.name = "D2"
>  G.names = c('Z1','Z3','Z4','Z5','Z6','Z7','Z8','Z9','Z10','Z11')
>  
> pltr.burn <- pltr.glm(burn, Y.name, X.names, G.names, args.rpart = args.rpart,
+                    family = family, iterMax = 4, iterMin = 3, verbose = FALSE)
> 
> ## Prunned back the maximal tree using either the BIC or the AIC criterion
> 
> pltr.burn_prun <- best.tree.BIC.AIC(xtree = pltr.burn$tree, burn, Y.name, 
+                                     X.names, family = family)
Number of leaves in the max tree =  10 
Best sub-tree 
 2 3 

 Number of sub-trees =  2 
Best sub-tree 
 2 6 7 

 Number of sub-trees =  3 
Best sub-tree 
 6 7 4 5 

 Number of sub-trees =  4 
Best sub-tree 
 7 4 5 12 13 

 Number of sub-trees =  5 
Best sub-tree 
 7 4 5 13 24 25 

 Number of sub-trees =  6 
Best sub-tree 
 4 5 13 24 25 14 15 

 Number of sub-trees =  7 
Best sub-tree 
 4 13 24 25 14 15 10 11 

 Number of sub-trees =  8 
Best sub-tree 
 4 13 24 25 14 15 10 22 23 

 Number of sub-trees =  9 
> 
> ## plot the BIC selected tree
> 
> plot(pltr.burn_prun$tree$BIC, main = 'BIC selected tree')
> text(pltr.burn_prun$tree$BIC, xpd = TRUE, cex = .6, col = 'blue')
> 
> ## Not run: 
> ##D ##load the data set
> ##D 
> ##D data(data_pltr)
> ##D 
> ##D ## Set the parameters
> ##D 
> ##D args.rpart <- list(minbucket = 40, maxdepth = 10, cp = 0)
> ##D family <- "binomial"
> ##D Y.name <- "Y"
> ##D X.names <- "G1"
> ##D G.names <- paste("G", 2:15, sep="")
> ##D 
> ##D ## build a maximal tree
> ##D 
> ##D fit_pltr <- pltr.glm(data_pltr, Y.name, X.names, G.names, args.rpart = args.rpart, 
> ##D                      family = family,iterMax = 5, iterMin = 3)
> ##D                      
> ##D ##prunned back the maximal tree by BIC or AIC criterion
> ##D 
> ##D tree_select <- best.tree.BIC.AIC(xtree = fit_pltr$tree,data_pltr,Y.name, 
> ##D                                  X.names, family = family)
> ##D                             
> ##D plot(tree_select$tree$BIC, main = 'BIC TREE')
> ##D text(tree_select$tree$BIC, minlength = 0L, xpd = TRUE, cex = .6)
> ##D 
> ## End(Not run)
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>