R 查找具有相同列值的所有序列

R 查找具有相同列值的所有序列,r,R,我有以下数据框: ╔══════╦═════════╗ ║ Code ║ Airline ║ ╠══════╬═════════╣ ║ 1 ║ AF ║ ║ 1 ║ KL ║ ║ 8 ║ AR ║ ║ 8 ║ AZ ║ ║ 8 ║ DL ║ ╚══════╩═════════╝ dat <- structure(list(Code = c(1L, 1L, 8L, 8L, 8L), Airline = stru

我有以下数据框:

╔══════╦═════════╗
║ Code ║ Airline ║
╠══════╬═════════╣
║    1 ║ AF      ║
║    1 ║ KL      ║
║    8 ║ AR      ║
║    8 ║ AZ      ║
║    8 ║ DL      ║
╚══════╩═════════╝

dat <- structure(list(Code = c(1L, 1L, 8L, 8L, 8L), Airline = structure(c(1L, 
5L, 2L, 3L, 4L), .Label = c("AF  ", "AR  ", "AZ  ", "DL", "KL  "
), class = "factor")), .Names = c("Code", "Airline"), class = "data.frame", row.names = c(NA, 
-5L))
伪代码是任何命令式语言都可以使用的

for each code
  lookup all rows in the table where the value = code

既然R不是那么以列表为导向,那么实现预期输出的最佳方式是什么

拆分
有帮助。这是一个完全可复制的编辑,不需要任何额外的软件包。使用OPs data.frame-在OP添加可复制数据集后对其进行更改

# strip white space in Airline names:
dat$Airline <- gsub(" ","",dat$Airline)
li <- split(dat,factor(dat$Code))
do.call("rbind",lapply(li,function(x) 
data.frame(Airline = x[1,2],
         SharedWith = paste(x$Airline[-1]
                            ,collapse=",")
))
)
#去除航空公司名称中的空白:

dat$Airline您可以在
dplyr

library(dplyr)
df %>% group_by(code) %>% mutate(SharedWith = paste(sort(Airline), collapse = ', ')) %>% ungroup() %>% select(Airline, SharedWith)

可能会有一条更有效的路线,但应该是:

# example data
d <- data.frame(code = c(1,1,8,8,8),
     airline = c("AF","KL","AR","AZ","DL"),
     stringsAsFactors = FALSE)

# merge d to itself on the code column.  This isn't necessarily efficient
d2 <- merge(d, d, by = "code")

# prune d2 to remove occasions where
# airline.x and airline.y (from the merge) are equal
d2 <- d2[d2[["airline.x"]] != d2[["airline.y"]], ]
# construct the combinations for each airline using a split, apply, combine
# then, use stack to get a nice structure for merging
d2 <- stack(
      lapply(split(d2, d2[["airline.x"]]),
        function(ii) paste0(ii$airline.y, collapse = ",")))

# merge d and d2.  "ind" is a column produced by stack
merge(d, d2, by.x = "airline", by.y = "ind")
#  airline code values
#1      AF    1     KL
#2      AR    8  AZ,DL
#3      AZ    8  AR,DL
#4      DL    8  AR,AZ
#5      KL    1     AF
#示例数据

d使用
数据的多个选项。表
包:

1)使用
strsplit
粘贴
&按行操作:

library(data.table)
setDT(dat)[, Airline := trimws(Airline)  # this step is needed to remove the leading and trailing whitespaces
           ][, sharedwith := paste(Airline, collapse = ','), Code
            ][, sharedwith := paste(unlist(strsplit(sharedwith,','))[!unlist(strsplit(sharedwith,',')) %in% Airline], 
                                    collapse = ','), 1:nrow(dat)]
其中:

> dat
   Code Airline sharedwith
1:    1      AF         KL
2:    1      KL         AF
3:    8      AR      AZ,DL
4:    8      AZ      AR,DL
5:    8      DL      AR,AZ
   Code air shared
1:    1  AF     KL
2:    1  KL     AF
3:    8  AR  AZ,DL
4:    8  AZ  AR,DL
5:    8  DL  AR,AZ
   Code Airline SharedWith
  (int)   (chr)      (chr)
1     1      AF         KL
2     1      KL         AF
3     8      AR     AZ, DL
4     8      AZ     AR, DL
5     8      DL     AR, AZ
2)使用
strsplit
粘贴
mapply
而不是
by=1:nrow(dat)

这会给你同样的结果

3)或使用带有
粘贴的
CJ
功能(灵感来自@zx8754的
扩展.grid
解决方案):

其中:

> dat
   Code Airline sharedwith
1:    1      AF         KL
2:    1      KL         AF
3:    8      AR      AZ,DL
4:    8      AZ      AR,DL
5:    8      DL      AR,AZ
   Code air shared
1:    1  AF     KL
2:    1  KL     AF
3:    8  AR  AZ,DL
4:    8  AZ  AR,DL
5:    8  DL  AR,AZ
   Code Airline SharedWith
  (int)   (chr)      (chr)
1     1      AF         KL
2     1      KL         AF
3     8      AR     AZ, DL
4     8      AZ     AR, DL
5     8      DL     AR, AZ

使用
dplyr
tidyr
获得所需解决方案的解决方案(灵感来自@jaimedash):


一种
igraph
方法

library(igraph)

g <- graph_from_data_frame(dat)

# Find neighbours for select nodes
ne <- setNames(ego(g,2, nodes=as.character(dat$Airline), mindist=2), dat$Airline)
ne
#$`AF  `
#+ 1/7 vertex, named:
#[1] KL  

#$`KL  `
#+ 1/7 vertex, named:
#[1] AF  
---
---

# Get final format
data.frame(Airline=names(ne), 
           Shared=sapply(ne, function(x)
                                      paste(V(g)$name[x], collapse=",")))
#   Airline Shared
# 1      AF     KL
# 2      KL     AF
# 3      AR  AZ,DL
# 4      AZ  AR,DL
# 5      DL  AR,AZ
库(igraph)

g使用expand.grid和aggregate:

do.call(rbind,
        lapply(split(dat, dat$Code), function(i){
          x <- expand.grid(i$Airline, i$Airline)
          x <- x[ x$Var1 != x$Var2, ]
          x <- aggregate(x$Var2, list(x$Var1), paste, collapse = ",")
          colnames(x) <- c("Airline", "SharedWith")
          cbind(Code = i$Code, x)
        }))

# output
#     Code Airline SharedWith
# 1.1    1      AF         KL
# 1.2    1      KL         AF
# 8.1    8      AR      AZ,DL
# 8.2    8      AZ      AR,DL
# 8.3    8      DL      AR,AZ
do.call(rbind,
lapply(拆分(dat,dat$代码),函数(i){

我想你需要的只是一张
表格

dat <- structure(list(Code = c(1L, 1L, 8L, 8L, 8L),Airline = structure(c(1L, 5L, 2L, 3L, 4L),.Label = c("AF", "AR", "AZ", "DL", "KL"),class = "factor")),.Names = c("Code", "Airline"),class = "data.frame", row.names = c(NA, -5L))

tbl <- crossprod(table(dat))
diag(tbl) <- 0

#        Airline
# Airline AF AR AZ DL KL
#      AF  0  0  0  0  1
#      AR  0  0  1  1  0
#      AZ  0  1  0  1  0
#      DL  0  1  1  0  0
#      KL  1  0  0  0  0

dd <- data.frame(Airline = colnames(tbl),
                 shared = apply(tbl, 1, function(x)
                   paste(names(x)[x > 0], collapse = ', ')))

merge(dat, dd)
#   Airline Code shared
# 1      AF    1     KL
# 2      AR    8 AZ, DL
# 3      AZ    8 AR, DL
# 4      DL    8 AR, AZ
# 5      KL    1     AF

dat将以下内容作为注释,作为答案发布,只是因为这样可以更方便地设置格式

for each code
  lookup all rows in the table where the value = code
嗯……对不起,我不明白这个psedudocode与您想要的输出有什么关系

+--------------------+
| Airline SharedWith |
+--------------------+
| AF      "KL"       |
| KL      "AF"       |
| AR      "AZ","DL"  |
+--------------------+
此伪代码的结果应该是:

+---------------------+
+ Code  +  Airlines   +
+---------------------+
+  1    +  AF, KL     +
+  2    +  AR, AZ, DL +
+---------------------+
就是

codes <- unique(dat$Code)
data.frame(Code=codes, Airlines = sapply(codes, function(x) paste(subset(dat, Code %in% x)$Airline, collapse=",")))

codes您可以使用
tidyr
nest
快速完成此操作(尽管除非您首先将航空公司作为要素转换为字符,否则速度会慢一些)和
合并

 library(tidyr)
 dat$Airline <- as.character(dat$Airline)
 new_dat <- merge(dat, dat %>% nest(-Code, .key= SharedWith), by="Code")
与其他解决方案相比,此解决方案的一个优点是:
SharedWith
成为
data.frame的列表列,而不是一个字符

> str(new_dat$SharedWith)
List of 5
 $ :'data.frame':   2 obs. of  1 variable:
  ..$ Airline: chr [1:2] "AF" "KL"
 $ :'data.frame':   2 obs. of  1 variable:
  ..$ Airline: chr [1:2] "AF" "KL"
 $ :'data.frame':   3 obs. of  1 variable:
  ..$ Airline: chr [1:3] "AR" "AZ" "DL"
 $ :'data.frame':   3 obs. of  1 variable:
  ..$ Airline: chr [1:3] "AR" "AZ" "DL"
 $ :'data.frame':   3 obs. of  1 variable:
  ..$ Airline: chr [1:3] "AR" "AZ" "DL"
因此,您可以很容易地(albiet不漂亮地)索引出共享值的向量,如:

> new_dat$SharedWith[[1]]$Airline
[1] "AF" "KL"

与其使用
strsplit
或类似的

,不如以一种可以提供给R的形式提供样本输入。这样对想要帮助你的人来说更容易。使用
dput
将数据输出到一种可以轻松导入的形式,而不是面向列表的形式。哈哈,这只是R中的主要数据结构。我也会这样做。我们可以同意这一点。事实上…数据框是一个列表:)我设法从dplyr中通过group_by获得了类似的结果。但是我陷入了查找每列的所有排列的困境。请尝试:
df%>%group_by(code)%%>%mutate(SharedWith=paste(sort(Airline),collapse=','))
这也将航空公司保留在同一列中。太好了!这要好得多!但我需要排除同一家航空公司,因为现在它也与自己共享。@AndreiVaranovich a
dplyr
免费解决方案与base R,这应该会给出您上面指定的输出…但是–我不知道您在t中真正想做什么他结束了。但我有一种预感,这种方法有点不成熟。@AndreiVaranovich这能解决重复问题吗?这种解决方案的优点是你不需要另一个软件包。也就是说,我喜欢@Dellactiatus Maximus,因为
data.table
确实很酷,而且可能是计算时间最快的解决方案。“但这应该飞起来”——很好的双关语。所有的人都欢呼
。非常好地使用它
> str(new_dat$SharedWith)
List of 5
 $ :'data.frame':   2 obs. of  1 variable:
  ..$ Airline: chr [1:2] "AF" "KL"
 $ :'data.frame':   2 obs. of  1 variable:
  ..$ Airline: chr [1:2] "AF" "KL"
 $ :'data.frame':   3 obs. of  1 variable:
  ..$ Airline: chr [1:3] "AR" "AZ" "DL"
 $ :'data.frame':   3 obs. of  1 variable:
  ..$ Airline: chr [1:3] "AR" "AZ" "DL"
 $ :'data.frame':   3 obs. of  1 variable:
  ..$ Airline: chr [1:3] "AR" "AZ" "DL"
> new_dat$SharedWith[[1]]$Airline
[1] "AF" "KL"