Question

我是R（和编码新手），我正在寻找一种方法将下面的表A显示重新配置到表B中。

表A：

type   x1  x2  x3  
A      4   6   9  
A      7   4   1  
A      9   6   2   
B      1   3   8  
B      2   7   9

我正在寻找可转换为以下内容的代码

表B：

type   x1  x2  x3  x1'  x2'  x3'  x1'' x2'' x3''  
A      4    6   9   7    4   1    9     6   2  
B      1    3   8   2    7   9

真正的表A超过150000行和36列。拥有2100种独特的“类型”值。

感谢您的帮助。

-Shawn

Answer 1

对我来说，这个解决方案似乎很简单

# split the data frame by type and use unlist, which will provide names
ld <- lapply(split(d[-1], d[["type"]]), unlist)

# gather all the unique names in the list
ldNames <- Reduce(unique, lapply(ld, names))

# use the names to index each list element, which makes them
# all of equal length and suitable for row binding.  
do.call(rbind, lapply(ld, function(x) x[ldNames]))
#   x11 x12 x13 x21 x22 x23 x31 x32 x33
# A   4   7   9   6   4   6   9   1   2
# B   1   2  NA   3   7  NA   8   9  NA

如果上述输出的顺序不满意，您可以重新排列：

# save the output from above
d2 <- do.call(rbind, lapply(ld, function(x) x[ldNames]))
# reorder the names
ldNames_sorted <- c(matrix(ldNames, ncol = (ncol(d) - 1), byrow = TRUE))

# apply the new order.
d2 <- d2[, ldNames_sorted]
#  x11 x21 x31 x12 x22 x32 x13 x23 x33
#A   4   6   9   7   4   1   9   6   2
#B   1   3   8   2   7   9  NA  NA  NA

要为类型添加列而不是使用行名，一种方法是：

data.frame(type = row.names(d2), d2)

Answer 2

派对有点晚了，但使用dcast包的data.table功能也可以轻松完成，因为您可以使用多个value.var：< / p>

library(data.table)

dcast(setDT(d), type ~ rowid(type), value.var = c('x1','x2','x3'), sep = '')

给出：

   type x11 x12 x13 x21 x22 x23 x31 x32 x33
1:    A   4   7   9   6   4   6   9   1   2
2:    B   1   2  NA   3   7  NA   8   9  NA

您也可以在基地R中执行以下操作：

d$num <- ave(d$x1, d$type, FUN = seq_along)
reshape(d, idvar = 'type', direction = 'wide', timevar = 'num', sep = '')

Answer 3

试一试，解决方案不是那么简洁，只是给你一个提示。我认为很多事情都可以改进。

但最后我们必须在这里介绍NAs :(

zz <- "type   x1  x2  x3  
A      4   6   9  
A      7   4   1  
A      9   6   2   
B      1   3   8  
B      2   7   9"

dA <- read.table(text=zz, header=T)


tmp<-(sapply(unique(dA$type), FUN=function(x) as.vector(t(dA[dA$type == x, -1]))))

t(sapply(tmp, '[', seq(max(sapply(tmp, length)))))
      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
[1,]    4    6    9    7    4    1    9    6    2
[2,]    1    3    8    2    7    9   NA   NA   NA

Answer 4

a <- data.frame(type=c("A", "A","A", "B", "B"), x1 = c(4,7,9,1,2),x2=c(6,4,6,3,7),
               x3 = c(9,1,2,8,9))

library(dplyr)
tmp <-
a %>% 
  group_by(type) %>%
  summarise(no_rows = length(type))

for(i in unique(a$type)){
  n <- max(tmp$no_rows) - nrow(a[a$type == i,])
  nn <- nrow(a)
  if(n > 0){
    for(ii in 1:n){
      a[nn+ii,] <- c(i,NA,NA,NA)
    }    
  }

}

a <- a[order(a$type),]
a$timevar <- seq(1:max(tmp$no_rows) )

b<-reshape(a,timevar="timevar",idvar="type",direction="wide",drop = F)
b

  type x1.1 x2.1 x3.1 x1.2 x2.2 x3.2 x1.3 x2.3 x3.3
1    A    4    6    9    7    4    1    9    6    2
4    B    1    3    8    2    7    9 <NA> <NA> <NA>

Answer 5

@ Hack-R答案的变化：

A$num <- with(A, ave(as.character(type), type, FUN=seq_along) )
tmp <- cbind(A[c(1,5)], stack(A[2:4]))
tmp$time <- paste(tmp$ind, tmp$num, sep=".")

reshape(tmp[c("type","time","values")], idvar="type", timevar="time", direction="wide")

#  type values.x1.1 values.x1.2 values.x1.3 values.x2.1 values.x2.2 values.x2.3 values.x3.1 values.x3.2 values.x3.3
#1    A           4           7           9           6           4           6           9           1           2
#4    B           1           2          NA           3           7          NA           8           9          NA

有趣的dplyr版本：

library(dplyr)
library(tidyr)

A %>%
  gather(var, value, -type) %>%
  group_by(type,var) %>%
  mutate(time=seq_along(var)) %>% 
  ungroup() %>%
  unite(grpvar, c(time,var) ) %>%
  spread(grpvar, value )

#Source: local data frame [2 x 10]
#
#   type  1_x1  1_x2  1_x3  2_x1  2_x2  2_x3  3_x1  3_x2  3_x3
#  (chr) (int) (int) (int) (int) (int) (int) (int) (int) (int)
#1     A     4     6     9     7     4     1     9     6     2
#2     B     1     3     8     2     7     9    NA    NA    NA

如何将表格数据重塑为每组一行

5 个答案: