Question

我有一个如下所示的数据框：

   LOS   RFG   TMV   SHN   QRE   TES   KLO  
1    0     0     3     0     0     4    28
2    1     0     0     9     0     0     0
3    0     0    39    98     0     0     0
4    2     0     0    10     0     0     0
5    0     0     7     5     0     0     0
6    0     0     0     0     0     2     6
7    0     2     3     9     0     3     0

我想弄清楚当某个列填充大于0的某个列时，哪些列也填充了大于0的值，但是我很难解决这个问题。我试着用

library(dplyr)
df %>% 
  group_by(LOS,RFG,TMV,SHN,QRE,TES,KLO) %>%
  mutate(n = n()) %>%
  group_by(row) %>%
  slice(which.max(n)) %>%
  select(-n)

但它无法正常工作。也许我应该使用聚合？基本上我想返回行中通常具有大于0的值的列的名称。

理想情况下，我想弄清楚如何让R返回类似这样的东西

LOS: SHN
RFG: TMV, SHN, TES 
SHN: LOS, TMV, RFG, TES

etc.

我对R很新，所以我不确定这是否可能，或者是否有更好的方法来获得类似的结果，但我真的很感激任何见解。

提前感谢任何建议！

更新：答案很好 - 但有没有办法按填充列而不是按字母顺序排列返回的列名，特别是从最大值到最小值？

Answer 1

library(data.table)

dat <- fread('LOS   RFG   TMV   SHN   QRE   TES   KLO  
    0     0     3     0     0     4    28
                 1     0     0     9     0     0     0
                 0     0    39    98     0     0     0
                 2     0     0    10     0     0     0
                 0     0     7     5     0     0     0
                 0     0     0     0     0     2     6
                 0     2     3     9     0     3     0')

dat_names <- names(dat)

funky <- function(x) {
  res <- apply(dat[get(x) > 0], 2, function(y) length(y[y > 0]))
  vals <- names(res[res > 0])
  vals[!vals == x]
}

sapply(dat_names, funky)

结果：

# $LOS
# [1] "SHN"
# 
# $RFG
# [1] "TMV" "SHN" "TES"
# 
# $TMV
# [1] "RFG" "SHN" "TES" "KLO"
# 
# $SHN
# [1] "LOS" "RFG" "TMV" "TES"
# 
# $QRE
# character(0)
# 
# $TES
# [1] "RFG" "TMV" "SHN" "KLO"
# 
# $KLO
# [1] "TMV" "TES"

Answer 2

setNames(object = lapply(1:NCOL(df), function(i)
    unique(colnames(df)[-i][which(as.matrix(df[which(df[,i] > 0), -i]) > 0,
                                  arr.ind = TRUE)[,2]])),
    nm = colnames(df))
#$LOS
#[1] "SHN"

#$RFG
#[1] "TMV" "SHN" "TES"

#$TMV
#[1] "RFG" "SHN" "TES" "KLO"

#$SHN
#[1] "LOS" "RFG" "TMV" "TES"

#$QRE
#character(0)

#$TES
#[1] "RFG" "TMV" "SHN" "KLO"

#$KLO
#[1] "TMV" "TES"

Answer 3

首先，我使用相关内容构建一个未命名的列表，但包括零，然后我删除零值并命名列表

res <- lapply(seq_along(df1),function(x){df1 %>% subset(df1[x]!=0) %>% select(-x) %>% colSums}) %>%
   lapply(function(x){names(x[x>0])}) %>% setNames(names(df1))
# $LOS
# [1] "SHN"
# 
# $RFG
# [1] "TMV" "SHN" "TES"
# 
# $TMV
# [1] "RFG" "SHN" "TES" "KLO"
# 
# $SHN
# [1] "LOS" "RFG" "TMV" "TES"
# 
# $QRE
# character(0)
# 
# $TES
# [1] "RFG" "TMV" "SHN" "KLO"
# 
# $KLO
# [1] "TMV" "TES"

Answer 4

df <- data.frame(LOS=c(0,1,0,2,0,0,0),
                 RFG=c(0,0,0,0,0,0,2),
                 TMV=c(3,0,39,0,7,0,3),
                 SHN=c(0,9,98,10,5,0,9),
                 QRE=rep(0,7),
                 TES=c(4,0,0,0,0,2,3),
                 KLO=c(28,0,0,0,0,6,0))

从df删除全部为0的列。

library(dplyr)
library(iterators)
df1 <- df %>% select_if(function(col) mean(col)>0)

使用icount作为迭代器和dplyr谓词将数据框减少到相关的行和列。

 l1 <- lapply(icount(ncol(df1)), function(x) df1 %>% 
                                               filter(df1[,x]>0) %>% 
                                               select_if(function(col) mean(col)>0) %>% 
                                               select(-1) %>% 
                                               colnames())

输出：

[[1]]
[1] "SHN"

[[2]]
[1] "TMV" "SHN" "TES"

[[3]]
[1] "TMV" "SHN" "TES" "KLO"

[[4]]
[1] "RFG" "TMV" "SHN" "TES"

[[5]]
[1] "TMV" "SHN" "TES" "KLO"

[[6]]
[1] "TES" "KLO"

R：如果填充了一列，那么下一个最常见的列也会被填充？

4 个答案: