可能解决方案包含许多循环。但它解决了我的问题。
以下是R代码:
rm(list=ls())
data <- read.delim(file.choose(),header=F)
# Now using strsplit function to create a regular dataser
temp <- list()
for(i in 1:length(data$V1)){
temp[i] <- strsplit(as.character(data$V1[i]),c(" "))
}
response <- list()
for(i in 1:length(temp)){
response[[i]] <- as.numeric(strsplit(temp[[i]][1],",")[[1]])
}
# Now working for responses
l.response <- 0
for (i in 1:length(response)){
l.response[i] <- length(response[[i]])
}
col.names <- paste(rep("R",22),1:22,sep="")
l.r <- length(temp)
df.response <- data.frame(R1=rep(0,l.r),R2=rep(0,l.r),R3=rep(0,l.r),R4=rep(0,l.r),R5=rep(0,l.r)
,R6=rep(0,l.r),R7=rep(0,l.r),R8=rep(0,l.r),R9=rep(0,l.r),R10=rep(0,l.r)
,R11=rep(0,l.r),R12=rep(0,l.r),R13=rep(0,l.r),R14=rep(0,l.r),R15=rep(0,l.r)
,R16=rep(0,l.r),R17=rep(0,l.r),R18=rep(0,l.r),R19=rep(0,l.r),R20=rep(0,l.r)
,R21=rep(0,l.r),R22=rep(0,l.r))
for(i in 1:length(response)){
df.response[i,(response[[i]]+1)] <- 1
}
feature <- c(0)
value <- c(0)
v.l <- 21519
v.list <- list()
list.name <- paste(rep("V",v.l),1:v.l,sep="")
f.vec <- 0
v.vec <- 0
for(i in 1:length(temp)){
for(j in 2:length(temp[[i]])){
f.vec[j-1] <- as.numeric(strsplit(temp[[i]][j],":")[[1]])[1]
v.vec[j-1] <- as.numeric(strsplit(temp[[i]][j],":")[[1]])[2]
}
v.list[[i]] <- data.frame(f.vec,v.vec)
}
feature.name <- paste(rep("V",30438),1:30438,sep="")
v.l <- 21519
variables <- data.frame(temp = rep(0,v.l))
for(i in 1:length(feature.name)){
variables[,feature.name[i]] <- rep(0,v.l)
}
variables <- variables[,-1]
copy.variables <- variables
for(i in 1:100){
pos <- v.list[[i]][,"f.vec"]
replace <- v.list[[i]][,"v.vec"]
if(length(unique(pos))!=length(pos)){
repeat{
uni <- as.numeric(attr(which(table(pos)>1), "names"))
for(k in 1:length(uni)){
t.pos <- which(pos==uni[k])
pos <- pos[-t.pos[1]]
replace <- replace[-t.pos[1]]
}
if(length(unique(pos))==length(pos)) break
}
}
variables[i,pos]<- replace
}
dim(df.response)
dim(variables)
下面的代码将给出100行100列的最终数据。
final.data <- cbind(variables[1:100,],df.response[1:100,])
欢迎使用其他解决方案@伦格里斯基
