166 lines (151 with data), 7.0 kB
R Under development (unstable) (2014-06-29 r66051) -- "Unsuffered Consequences"
Copyright (C) 2014 The R Foundation for Statistical Computing
Platform: x86_64-unknown-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.
>
> set.seed(290875)
> library("party")
Loading required package: grid
Loading required package: zoo
Attaching package: 'zoo'
The following objects are masked from 'package:base':
as.Date, as.Date.numeric
Loading required package: sandwich
Loading required package: strucchange
Loading required package: modeltools
Loading required package: stats4
> if (!require("TH.data"))
+ stop("cannot load package TH.data")
Loading required package: TH.data
> if (!require("coin"))
+ stop("cannot load package coin")
Loading required package: coin
Loading required package: survival
Loading required package: splines
>
> data("GlaucomaM", package = "TH.data")
> rf <- cforest(Class ~ ., data = GlaucomaM, control = cforest_unbiased(ntree = 30))
> stopifnot(mean(GlaucomaM$Class != predict(rf)) <
+ mean(GlaucomaM$Class != predict(rf, OOB = TRUE)))
>
> data("GBSG2", package = "TH.data")
> rfS <- cforest(Surv(time, cens) ~ ., data = GBSG2, control = cforest_unbiased(ntree = 30))
> treeresponse(rfS, newdata = GBSG2[1:2,])
$`1`
Call: survfit(formula = y ~ 1, weights = weights)
records n.max n.start events median 0.95LCL 0.95UCL
143 394 394 237 1528 1306 1675
$`2`
Call: survfit(formula = y ~ 1, weights = weights)
records n.max n.start events median 0.95LCL 0.95UCL
145 380 380 160 2015 1807 2018
>
> ### give it a try, at least
> varimp(rf, pre1.0_0 = TRUE)
ag at as an ai
0.0000000000 0.0004629630 0.0027777778 0.0013888889 0.0032407407
eag eat eas ean eai
0.0000000000 0.0000000000 0.0000000000 0.0027777778 -0.0004629630
abrg abrt abrs abrn abri
0.0000000000 0.0023148148 0.0013888889 0.0018518519 0.0046296296
hic mhcg mhct mhcs mhcn
0.0069444444 0.0000000000 0.0009259259 0.0000000000 0.0009259259
mhci phcg phct phcs phcn
0.0078703704 0.0097222222 0.0000000000 0.0000000000 -0.0004629630
phci hvc vbsg vbst vbss
0.0171296296 0.0018518519 0.0013888889 -0.0004629630 0.0018518519
vbsn vbsi vasg vast vass
0.0000000000 0.0000000000 -0.0023148148 0.0000000000 0.0000000000
vasn vasi vbrg vbrt vbrs
0.0000000000 0.0018518519 0.0000000000 0.0013888889 -0.0004629630
vbrn vbri varg vart vars
0.0032407407 0.0004629630 0.0351851852 0.0000000000 0.0254629630
varn vari mdg mdt mds
0.0138888889 0.0425925926 0.0000000000 0.0000000000 -0.0023148148
mdn mdi tmg tmt tms
0.0032407407 0.0004629630 0.0222222222 0.0009259259 0.0069444444
tmn tmi mr rnf mdic
-0.0027777778 0.0273148148 0.0000000000 0.0055555556 0.0074074074
emd mv
0.0000000000 -0.0013888889
>
> P <- proximity(rf)
> stopifnot(max(abs(P - t(P))) == 0)
>
> P[1:10,1:10]
2 43 25 65 70 16 6
2 1.00000000 0.15384615 0.7500000 0.0000000 0.07142857 0.13333333 0.7142857
43 0.15384615 1.00000000 0.1818182 0.0000000 0.11111111 0.45454545 0.1111111
25 0.75000000 0.18181818 1.0000000 0.1818182 0.11111111 0.14285714 0.8000000
65 0.00000000 0.00000000 0.1818182 1.0000000 0.00000000 0.00000000 0.1666667
70 0.07142857 0.11111111 0.1111111 0.0000000 1.00000000 0.00000000 0.1428571
16 0.13333333 0.45454545 0.1428571 0.0000000 0.00000000 1.00000000 0.0000000
6 0.71428571 0.11111111 0.8000000 0.1666667 0.14285714 0.00000000 1.0000000
5 0.58823529 0.09090909 0.7692308 0.5000000 0.09090909 0.08333333 0.5000000
12 0.44444444 0.00000000 0.5714286 0.5833333 0.07692308 0.06666667 0.3333333
63 0.46153846 0.10000000 0.5000000 0.2222222 0.00000000 0.18181818 0.5000000
5 12 63
2 0.58823529 0.44444444 0.4615385
43 0.09090909 0.00000000 0.1000000
25 0.76923077 0.57142857 0.5000000
65 0.50000000 0.58333333 0.2222222
70 0.09090909 0.07692308 0.0000000
16 0.08333333 0.06666667 0.1818182
6 0.50000000 0.33333333 0.5000000
5 1.00000000 0.76923077 0.5454545
12 0.76923077 1.00000000 0.5714286
63 0.54545455 0.57142857 1.0000000
>
> ### variable importances
> a <- cforest(Species ~ ., data = iris,
+ control = cforest_unbiased(mtry = 2, ntree = 10))
> varimp(a, pre1.0_0 = TRUE)
Sepal.Length Sepal.Width Petal.Length Petal.Width
0.036363636 0.007272727 0.312727273 0.276363636
> varimp(a, conditional = TRUE)
Sepal.Length Sepal.Width Petal.Length Petal.Width
0.003636364 -0.003636364 0.167272727 0.194545455
>
> airq <- subset(airquality, complete.cases(airquality))
> a <- cforest(Ozone ~ ., data = airq,
+ control = cforest_unbiased(mtry = 2, ntree = 10))
> varimp(a, pre1.0_0 = TRUE)
Solar.R Wind Temp Month Day
139.397699 501.974401 500.220403 28.532700 3.806919
> varimp(a, conditional = TRUE)
Solar.R Wind Temp Month Day
93.220640 334.737163 212.686904 14.329278 2.061793
>
> data("mammoexp", package = "TH.data")
> a <- cforest(ME ~ ., data = mammoexp, control = cforest_classical(ntree = 10))
> varimp(a, pre1.0_0 = TRUE)
SYMPT PB HIST BSE DECT
0.027998627 0.021174836 0.018630793 0.002646901 0.005578231
> varimp(a, conditional = TRUE)
SYMPT PB HIST BSE DECT
0.021408831 0.012420497 0.013407572 0.001282682 0.002857143
>
> stopifnot(all.equal(unique(sapply(a@weights, sum)), nrow(mammoexp)))
>
> ### check user-defined weights
> nobs <- nrow(GlaucomaM)
> i <- rep(0.0, nobs)
> i[1:floor(.632 * nobs)] <- 1
> folds <- replicate(100, sample(i))
> rf2 <- cforest(Class ~ ., data = GlaucomaM, control = cforest_unbiased(ntree = 100), weights = folds)
> table(predict(rf), predict(rf2))
glaucoma normal
glaucoma 89 4
normal 2 101
>
> proc.time()
user system elapsed
3.132 0.052 3.185
Datasets
Models
