Question

是否有一种快速而聪明的方式，就像DF这样说道

vec <- data.frame(Names = c("var1","var2","var3","var4","var5","var6","var7",
                            "var8","var9","var10","var11","var12","var13",
                            "var14") ,
                  phase1= runif(14),
                  phase1.away= runif(14),
                  phase1_in= runif(14),
                  phase1_out= runif(14),
                  phase1.1= runif(14),
                  phase1.away.1= runif(14),
                  phase1_in.1= runif(14),
                  phase1_out.1= runif(14),
                  phase1.2= runif(14),
                  phase1.away.2= runif(14),
                  phase1_in.2= runif(14),
                  phase1_out.2= runif(14))

给出一个新的DF：

- 根据phase1.x进行排序，给出与值相对应的变量名称，phase1_in和phase1_out值，但不包括phase1.away。

我正在做的只是

vec.o<-vec[with(vec, order(-phase1)),]
d1<-vec.o[c("Names","phase1","phase1_in","phase1_out")]

vec.o<-vec[with(vec, order(-phase1.1)),]
d2<-vec.o[c("Names","phase1.1","phase1_in.1","phase1_out.1")]

cbind(d1,d2)

这非常无聊，我也确信反R-ish。任何聪明的想法？我正在永久处理大型数据帧，R似乎是有点累赘。有没有人会为这些目的推荐的好文献？（加载许多变量，为它们创建名称，使用这些变量进行操作等等），

Answer 1

编辑：针对案例阶段进行了更正.x进入了10及更高版本。

我认为你有比phase1.1，phase1.2更多的东西，所以使用正则表达式的一般解决方案将是这样的：

# Make an id vector for the phase1.x, and give Names id -1
# gives a warning as character is transformed to NA
id <- as.numeric(gsub(".*\\.(\\d+$)","\\1",names(vec)))
id[1] <- -1
id[is.na(id)] <- 0 # first occurence, no .x


veclist <- lapply(unique(id)[-1],function(i){
    #select all variables necessary, exclude the away
    out <- vec[id %in% c(i,-1) & !grepl("away",names(vec))]
    # find the phase1.x for ordering
    ovec <- grepl("phase1(\\.\\d+)?$",names(out))
    # order and produce
    out[order(out[,ovec]),]
})

do.call(cbind,veclist)

它基于对前面带有点的最后一个数字的识别，并将其删除。如果没有以点开头的最后一个数字，则它是Names变量（我用-1表示）或第一个阶段（我用0表示）。

现在你有一个id向量，可以轻松选择属于一起的变量，因此你可以循环id的唯一值，除了第一个（为-1）。再次使用正则表达式，您可以获得构建新数据帧所需的任何变量。最后的do.call再次组合了所有这些数据帧。

顺便说一句，订购子数据帧比先订购原始数据帧然后选择变量要快得多。这是你在nullglob解决方案中获得的收益。

Answer 2

这不是特别聪明，但速度快了两倍（根据我的简单基准）：

o1 <- order(-vec$phase1)   
o2 <- order(-vec$phase1.1)
cbind(vec[o1,c("Names","phase1","phase1_in","phase1_out")],
         vec[o2,c("Names","phase1.1","phase1_in.1","phase1_out.1")])

基准点在这里：

> n <- 2e5
> vec<-data.frame(Names = as.character(runif(n)) ,
+                  phase1= runif(n),
+                  phase1.away= runif(n),
+                  phase1_in= runif(n),
+                  phase1_out= runif(n),
+                  phase1.1= runif(n),
+                  phase1.away.1= runif(n),
+                  phase1_in.1= runif(n),
+                  phase1_out.1= runif(n),
+                  phase1.2= runif(n),
+                  phase1.away.2= runif(n),
+                  phase1_in.2= runif(n),
+                  phase1_out.2= runif(n))
>
>
> test1 <- function(){
+   vec.o<-vec[with(vec, order(-phase1)),]
+   d1<-vec.o[c("Names","phase1","phase1_in","phase1_out")]
+   vec.o<-vec[with(vec, order(-phase1.1)),]
+   d2<-vec.o[c("Names","phase1.1","phase1_in.1","phase1_out.1")]
+   d3 <- cbind(d1,d2)
+ }
> system.time(test1())
   user  system elapsed
  1.764   0.048   1.811
>
>
> test2 <- function(){
+   o1 <- order(-vec$phase1)
+   o2 <- order(-vec$phase1.1)
+   d4 <- cbind(vec[o1,c("Names","phase1","phase1_in","phase1_out")],
+               vec[o2,c("Names","phase1.1","phase1_in.1","phase1_out.1")])
+ }
> system.time(test2())
   user  system elapsed
  0.736   0.056   0.791

子集大数据帧

2 个答案: