gbm_oob_simpleloess.txt

R version 3.1.1 (2014-07-10) -- "Sock it to Me"
Copyright (C) 2014 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64 (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.

> #
> # This is basically the standard demo with a high shrinkage.
> # In GBM 2.1 this causes an obscure error.  This same kind
> # of thing happens on real data with normal shrinkage like 0.1
> #
> 
> require(gbm)
Loading required package: gbm
Loading required package: survival
Loading required package: splines
Loading required package: lattice
Loading required package: parallel
Loaded gbm 2.1
> 
> N <- 1000
> X1 <- runif(N)
> X2 <- 2*runif(N)
> X3 <- ordered(sample(letters[1:4],N,replace=TRUE),levels=letters[4:1])
> X4 <- factor(sample(letters[1:6],N,replace=TRUE))
> X5 <- factor(sample(letters[1:3],N,replace=TRUE))
> X6 <- 3*runif(N) 
> mu <- c(-1,0,1,2)[as.numeric(X3)]
> 
> SNR <- 10 # signal-to-noise ratio
> Y <- X1**1.5 + 2 * (X2**.5) + mu
> sigma <- sqrt(var(Y)/SNR)
> Y <- Y + rnorm(N,0,sigma)
> 
> # introduce some missing values
> X1[sample(1:N,size=500)] <- NA
> X4[sample(1:N,size=300)] <- NA
> 
> data <- data.frame(Y=Y,X1=X1,X2=X2,X3=X3,X4=X4,X5=X5,X6=X6)
> 
> # fit initial model
> gbm1 <-
+ gbm(Y~X1+X2+X3+X4+X5+X6,         # formula
+     data=data,                   # dataset
+     var.monotone=c(0,0,0,0,0,0), # -1: monotone decrease,
+                                  # +1: monotone increase,
+                                  #  0: no monotone restrictions
+     distribution="gaussian",     # see the help for other choices
+     n.trees=1000,                # number of trees
+     shrinkage=10,              # shrinkage or learning rate,
+                                  # 0.001 to 0.1 usually work
+     interaction.depth=3,         # 1: additive model, 2: two-way interactions, etc.
+     bag.fraction = 0.5,          # subsampling fraction, 0.5 is probably best
+     train.fraction = 0.5,        # fraction of data for training,
+                                  # first train.fraction*N used for training
+     n.minobsinnode = 10,         # minimum total weight needed in each node
+     cv.folds = 3,                # do 3-fold cross-validation
+     keep.data=TRUE,              # keep a copy of the dataset with the object
+     verbose=FALSE,               # don't print out progress
+     n.cores=1)                   # use only a single core (detecting #cores is
>                                  # error-prone, so avoided here)
> 
> 
> best.iter <- gbm.perf(gbm1,method="OOB")
Error in simpleLoess(y, x, w, span, degree, parametric, drop.square, normalize,  : 
  NA/NaN/Inf in foreign function call (arg 1)
> traceback()
3: simpleLoess(y, x, w, span, degree, parametric, drop.square, normalize, 
       control$statistics, control$surface, control$cell, iterations, 
       control$trace.hat)
2: loess(object$oobag.improve ~ x, enp.target = min(max(4, length(x)/10), 
       50))
1: gbm.perf(gbm1, method = "OOB")
> sessionInfo()
R version 3.1.1 (2014-07-10)
Platform: x86_64-w64-mingw32/x64 (64-bit)

locale:
[1] LC_COLLATE=English_United States.1252 
[2] LC_CTYPE=English_United States.1252   
[3] LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                          
[5] LC_TIME=English_United States.1252    

attached base packages:
[1] parallel  splines   stats     graphics  grDevices utils     datasets 
[8] methods   base     

other attached packages:
[1] gbm_2.1         lattice_0.20-29 survival_2.37-7

loaded via a namespace (and not attached):
[1] grid_3.1.1
>