3
我想實現tomek鏈接處理不平衡數據。 此代碼用於二元分類問題，其中1類是多數類，0類是少數類。 X輸入，Y輸出 我寫了下面的代碼，但我正在尋找一種加速計算的方法。快速計算R中的Tomek鏈接
我該如何改進我的代碼？
#########################
#remove overlapping observation using tomek links
#given observations i and j belonging to different classes
#(i,j) is a Tomek link if there is NO example z, such that d(i, z) < d(i, j) or d(j , z) < d(i, j)
#find tomek links and remove only the observations of the tomek links belonging to majority class (0 class).
#########################
tomekLink<-function(X,Y,distType="euclidean"){
i.1<-which(Y==1)
i.0<-which(Y==0)
X.1<-X[i.1,]
X.0<-X[i.0,]
i.tomekLink=NULL
j.tomekLink=NULL
#i and j belong to different classes
timeTomek<-system.time({
for(i in i.1){
for(j in i.0){
d<-dst(X,i,j,distType)
obsleft<-setdiff(1:nrow(X),c(i,j))
for(z in obsleft){
if (dst(X,i,z,distType)<d | dst(X,j,z,distType)<d){
break() #(i,j) is not a Tomek link, get next pair (i,j)
}
#if z is the last obs and d(i, z) > d(i, j) and d(j , z) > d(i, j),then (i,j) is a Tomek link
if(z==obsleft[length(obsleft)]){
if (dst(X,i,z,distType)>d & dst(X,j,z,distType)>d){
#(i,j) is a Tomek link
#cat("\n tomeklink obs",i,"and",j)
i.tomekLink=c(i.tomekLink,i)
j.tomekLink=c(j.tomekLink,j)
#since we want to eliminate only majority class observations
#remove j from i.0 to speed up the loop
i.0<-setdiff(i.0,j)
}
}
}
}
}
})
print(paste("Time to find tomek links:",round(timeTomek[3],digit=2)))
#id2keep<-setdiff(1:nrow(X),c(i.tomekLink,j.tomekLink))
id2keep<-setdiff(1:nrow(X),j.tomekLink)
cat("numb of obs removed usign tomeklink",nrow(X)-length(id2keep),"\n",
(nrow(X)-length(id2keep))/nrow(X)*100,"% of training ;",
(length(j.tomekLink))/length(which(Y==0))*100,"% of 0 class")
X<-X[id2keep,]
Y<-Y[id2keep]
cat("\n prop of 1 afer TomekLink:",(length(which(Y==1))/length(Y))*100,"% \n")
return(list(X=X,Y=Y))
}
#distance measure used in tomekLink function
dst<-function(X,i,j,distType="euclidean"){
d<-dist(rbind(X[i,],X[j,]), method= distType)
return(d)
}