큰 데이터 프레임 (~ 700 nx 36000 p)이 있고 R에서 randomForest 분석을 수행 할 계획입니다. 전체 프레임 전송의 런타임 부담으로 인해 randomForest (병렬 컴퓨팅 및 512GB RAM조차도), 많은 독립적 인 실행 (Nruns)에서 randomForest에 데이터 프레임 (~ 5 % p)의 다른 무작위 하위 샘플을 보내고 싶습니다. 작은 데이터 프레임의 경우, 전체 데이터 프레임을 randomForest로 보내고 dim (p, Nruns)와 Nrun에서 생성 된 몇 가지 추가 정보를 포함하는 추가 행을 포함하는 중요 결과 행렬을 반환하는 foreach 루프를 만들었습니다. 그러나 각 run에 대해 randomForest에 데이터 프레임의 다른 하위 샘플을 보내도록 스크립트의 foreach() 구성 요소를 생성하는 데 문제가 있습니다. 서브 샘플링은 두 단계로 구성됩니다 : 행을 먼저 샘플링하여 (이 부분이 작동하는) 균형 잡힌 데이터 세트를 생성하고 (결과 클래스에 대해), 열의 서브 세트를 선택하십시오. 원하는 결과는 여전히 dim (p + 3, Nruns)하지만 각 열에는 해당 열이 나타내는 실행에서 임의로 선택한 변수에 대한 결과 만 포함됩니다 (즉, 해당 실행에 대해 선택되지 않은 변수에 누락 값이 있음). 아래 코드를 사용하여 아래 코드를 제출하면 다음과 같은 오류 메시지가 나타납니다. "전화 기능 결합 오류 : " 코드에서와 같이 임의의 열을 선택한 단계를 제외하면 그러나 밸런싱이 수행되는 단계를 유지하면 오류가 발생하지 않으며 출력이 예상대로 (희미한 (p + 3, Nruns) 및 모든 셀에 0이 아닌 값이 있음). 따라서 문제는 섹션 열 샘플링이 수행되는 코드의 1 : Nruns 각각에 대해 열 (및 행)의 새로운 무작위 하위 샘플링을 수행하는 코드에 대한 해결책을 제안 할 수 있는지 알고 싶습니다.R : randomForest() 호출에서 sample() 프로 시저와 함께 foreach()를 사용합니다.
의견을 보내 주셔서 감사합니다.
##########################################################################
# CREATE FAKE DATA
##########################################################################
FAKEinput <-
data.frame(A=sample(25:75,20, replace=T), B=sample(1:2,20,replace=T), C=as.factor(sample(0:1,20,replace=T,prob=c(0.3,0.7))),
D=sample(200:350,20,replace=T), E=sample(2300:2500,20,replace=T), F=sample(92000:105000,20,replace=T),
G=sample(280:475,20,replace=T),H=sample(470:550,20,replace=T),I=sample(2537:2723,20,replace=T),
J=sample(2984:4199,20,replace=T),K=sample(222:301,20,replace=T),L=sample(28:53,20,replace=T),
M=sample(3:9,20,replace=T),N=sample(0:2,20,replace=T),O=sample(0:5,20,replace=T),P=sample(0:2,20,replace=T),
Q=sample(0:2,20,replace=T), R=sample(0:2,20,replace=T), S=sample(0:7,20,replace=T))
##########################################################################
# set FOREST DATASET
##########################################################################
forestData <- FAKEinput
##########################################################################
# set Outcome
##########################################################################
Outcome <- "C"
##########################################################################
# set DV
#########################################################################
forestDV <- forestData$C
str(forestDV) #factor
##########################################################################
#set up number of runs:
##########################################################################
Nruns<-5
##########################################################################
#set up ntree
##########################################################################
ntree=100
###########################################################################
#set up mtry:
###########################################################################
mtry=round(sqrt(ncol(forestData))) #4
###########################################################################
## CREATE DATASET WITH ONLY THE PREDICTORS (I.E., OMIT OUTCOME).
###########################################################################
dropVars <- names(forestData) %in% c(Outcome)
forestPREDICTORS <- forestData[!dropVars]
###########################################################################
#set seed first to replicate the random draw of seeds
###########################################################################
set.seed(3456)
###########################################################################
# GENERATE Nruns RANDOMSEEDS
###########################################################################
randomseed<- sample(1:(length(forestData[,1])),Nruns, replace=TRUE) #16 16 18 8 11
##########################################
#Load necessary packages into R's memory
##########################################
require(iterators)
require(foreach)
require(parallel)
require(doParallel)
require(randomForest)
###########################################
# Get the number of available logical cores
###########################################
cores <- detectCores()
cores
###########################################
# Print info on computer, OS, cores
###########################################
print(paste('Processor: ', Sys.getenv('PROCESSOR_IDENTIFIER')), sep='')
print(paste('OS: ', Sys.getenv('OS')), sep='')
print(paste('Cores: ', cores, sep=''))
##################################################################################################
# Set up new function, called ’ImpOOBerr':
# 1)write in the set random seed part that uses the same ‘i’ from the ‘foreach’ loops
# 2) save the importance and summary measures output from the random forest run
# 3) combine all of the importance scores and OOB error summary results (as columns) into single matrix
# * other options tried to correct error commented out.
###################################################################################################
ImpOOBerr<-function(y,d) {
set.seed(randomseed[i])
out.model<-randomForest(y ~ .,
data=d,
ntree=ntree,
mtry=mtry,
nodesize=0.1*nrow(forestData),
importance=TRUE,
proximity=FALSE)
# create the frame before filling with values?
#out<-data.frame(matrix(nrow=ncol(forestPREDICTORS)+3, ncol=Nruns))
out<-rbind(importance(out.model, type=1, scale=FALSE),
mean(out.model$err.rate[,1]),
rbind(t(t(quantile(out.model$err.rate[,1], probs=c(0.025, 0.975))))))
#rownames(out) <- c(names(forestPREDICTORS),'meanOOB','oobL95CI', 'oobU95CI') # name all the rows
# OR name only newly-added rows since randomForest importance output preserves the variable names
rownames(out)[(nrow(out)-2):nrow(out)]<-c('meanOOB','oobL95CI', 'oobU95CI')
return(out)
}
###########################################################################
# SET UP THE CLUSTER
###########################################################################
#Setup clusters via parallel/DoParallel
cl.spec <- rep("localhost", 10)
cl <- makeCluster(cl.spec, type="SOCK")
registerDoParallel(cl, cores=10)
###########################################################################
# Employ foreach to carry out randomForest in parallel
##########################################################################
system.time(fakeRF <- foreach(i=1:Nruns, .combine='cbind', .packages='randomForest')
%dopar% { #<<change to %do% to see speed difference
######################################################################################################
# FIRST, BALANCE THE DATASET ON OUTCOME CLASS FOR INPUT TO randomForest CLASSIFICATION
######################################################################################################
dat1<-forestData[forestData$C==1,]
dat0<-forestData[forestData$C==0,]
####################################################
# RESET the seed to make sure it is updating and
# giving different samples for each run
####################################################
set.seed(randomseed[i])
####################################################
# OVERSAMPLE FROM SMALLER GROUP TO BALANCE DATASET
####################################################
rands=sample(1:dim(dat0)[1],dim(dat1)[1], replace=TRUE)
balancedCLASS<-rbind(dat0[rands,],dat1)
######################################################################################################
# NOW DO RANDOM SAMPLES OF THE COLUMNS (VARIABLES) TO CREATE NEW DATA SUBSETS TO SEND TO randomForest
# AT EACH RUN
# NOTE: TO TEST SCRIPT WITHOUT COLUMN SAMPLING, COMMENT OUT ALL SCRIPT BETWEEN TWO "#xxxxxxxxx.." ROWS
# AND UNCOMMENT THE NEXT THREE LINES
######################################################################################################
#forestData<-balancedCLASS
#forestDV<-balancedCLASS$C
#forestPREDICTORS <- balancedCLASS[!names(balancedCLASS) %in% c('C')]
##xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
##xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
####################################################
# PULL OUT PREDICTORS (i.e., exclue the outcome)
# before sampling the columns
####################################################
PREDICTORS <- balancedCLASS[!names(balancedCLASS) %in% c('C')]
####################################################
# from the row-balanced set created above,
# draw a 5-column subset for each run
####################################################
randsCOL= sample(1:dim(PREDICTORS)[2], 5, replace=FALSE)
####################################################
# BIND OUTCOME VAR BACK ONTO RANDOM COL SET
####################################################
Set_BALrandsCOL <- cbind(balancedCLASS$C, balancedCLASS[,randsCOL])
####################################################
# FIX OUTCOME NAME (was retained as "balancedCLASS$C")
####################################################
names(Set_BALrandsCOL)[names(Set_BALrandsCOL)=="balancedCLASS$C"] <- "C"
####################################################
# ASSIGN THE OUTCOME OF SAMPLING BACK TO
# forestData, forestDV and forestPREDICTORS for RF runs
####################################################
forestData<-Set_BALrandsCOL
forestDV<-Set_BALrandsCOL$C
forestPREDICTORS <- Set_BALrandsCOL[!names(Set_BALrandsCOL) %in% c('C')]
##xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
##xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
#############################################################################################
# CALL FUNCTION THAT WILL RUN randomForest AND COMBINE THE OUTPUT FROM EACH RUN
#############################################################################################
ImpOOBerr(forestDV, forestPREDICTORS)
})
##########################
# stop the cluster
##########################
stopCluster(cl)
#############################################################################################
# SAVE THE OUTPUT TO FILE
#############################################################################################
save(fakeRF, file="D:/RF/WORKING/fakeRF.rda")
'i = 1'로 수동으로 시도하면 dim (8,1)의 행렬을 얻고 'i = 2'는 dim (7,1)을 얻습니다. 이것이'ImpOOBerr'의 출력에서 알려진 변형이라면'cbind'는 같은 수의 행을 필요로하기 때문에 다른 결합기가 필요합니다. – r2evans
답변 해 주셔서 감사합니다. – KDA
답변 해 주셔서 감사합니다. ImpOOBerr()은 같은 크기의 행렬을 생성해야하며, 무작위로 cols 샘플을 취하는 스크립트 부분 (예 : "#xxxx"행 사이)을 제외하면 수행됩니다. 랜덤 콜 선택에서의 의도는 각 독립 실행에서 동일한 수의 콜을 선택하는 것이 었습니다. 선택된 #col은 출력 행렬의 #rows를 지정하기 때문에 각 행은 동일한 크기의 행렬을 생성해야합니다. 그러나 무작위 샘플링이므로 선택한 특정 콜은 실행 과정에 따라 달라집니다. ImpOOBerr로 결합되는 행렬의 row.names가 각 실행마다 서로 다르기 때문에 오류가 발생합니까? 제안? – KDA