所以对我来说,解决方案不是编辑现有的 randomForest 函数。相反,我自己编写了逐块引导程序,使用split2
Soren H. Welling 给出的用于创建块的函数。一旦我按块引导了数据,我就寻找一个包(rpart
)只执行一个回归树并自己聚合它(采用方法)。
我的实际数据的结果是在 RMSPE 方面比正常随机森林性能略有但持续改进的版本。
对于下面的代码,性能似乎是一个抛硬币的问题。
以 Soren 的代码为例,它看起来有点像这样:
library(randomForest)
library(doParallel) #parallel package and mclapply is better for linux
library(rpart)
#parallel backend ftw
nCPU = detectCores()
cl = makeCluster(nCPU)
registerDoParallel(cl)
#simulated time series(y) with time roll and lag=1
timepoints=1000;var=6;noise.factor=.2
#past to present orientation
y = sin((1:timepoints)*pi/30) * 1000 +
sin((1:timepoints)*pi/40) * 1000 + 1:timepoints
y = y+rnorm(timepoints,sd=sd(y))*noise.factor
plot(y,type="l")
#convert to absolute change, with lag=1
dy = c(0,y[-1]-y[-length(y)]) # c(0,t2-t1,t3-t2,...)
#compute lag
dy = dy + rnorm(timepoints)*sd(dy)*noise.factor #add noise
dy = c(0,y[-1]-y[-length(y)]) #convert to absolute change, with lag=1
dX = sapply(1:40,function(i){
getTheseLags = (1:timepoints) - i
getTheseLags[getTheseLags<1] = NA #remove before start timePoints
dx.lag.i = dy[getTheseLags]
})
dX[is.na(dX)]=-100 #quick fix of when lag exceed timeseries
pairs(data.frame(dy,dX[,1:5]),cex=.2)#data structure
#make train- and test-set
train=1:600
dy.train = dy[ train]
dy.test = dy[-train]
dX.train = dX[ train,]
dX.test = dX[-train,]
#classic rf
rf = randomForest(dX.train,dy.train,ntree=500)
print(rf)
#like function split for a vector without mixing
split2 = function(aVector,splits=31) {
lVector = length(aVector)
mod = lVector %% splits
lBlocks = rep(floor(lVector/splits),splits)
if(mod!=0) lBlocks[1:mod] = lBlocks[1:mod] + 1
lapply(1:splits,function(i) {
Stop = sum(lBlocks[1:i])
Start = Stop - lBlocks[i] + 1
aVector[Start:Stop]
})
}
#create a list of block-wise bootstrapped samples
aBlock <- list()
numTrees <- 500
splits <- 40
for (ttt in 1:numTrees){
aBlock[[ttt]] <- unlist(
sample(
split2(1:nrow(dX.train),splits=splits),
splits,
replace=T
)
)
}
#put data into a dataframe so rpart understands it
df1 <- data.frame(dy.train, dX.train)
#perform regression trees for Blocks
rfBlocks = foreach(aBlock = aBlock,
.packages=("rpart")) %dopar% {
dBlock = df1[aBlock,]
rf = predict( rpart( dy.train ~., data = dBlock, method ="anova" ), newdata=data.frame(dX.test) )
}
#predict test, make results table
#use rowMeans to aggregate the block-wise predictions
results = data.frame(predBlock = rowMeans(do.call(cbind.data.frame, rfBlocks)),
true=dy.test,
predBootstrap = predict(rf,newdata=dX.test)
)
plot(results[,1:2],xlab="OOB-CV predicted change",
ylab="trueChange",
main="black bootstrap and blue block train")
points(results[,3:2],xlab="OOB-CV predicted change",
ylab="trueChange",
col="blue")
#prediction results
print(cor(results)^2)
stopCluster(cl)#close cluster