我有多个数据框。这些数据帧中的别名具有特定的前缀。我想以这些数据帧的前缀存储方式创建一个列表。
在此示例中，我有两个数据帧。每个都有两个不同的前缀。
dput（head（FEB_gems））输出：
structure(list(GAME1_Class = structure(c(2L, 1L, 5L, 4L, 3L), .Label = c("fighter",
"paladin", "rouge", "sorcerer", "wizard"), class = "factor"),
GAME1_Race = structure(c(3L, 1L, 4L, 3L, 2L), .Label = c("elf",
"gnome", "human", "orc"), class = "factor"), GAME1_Alignment = structure(c(4L,
2L, 1L, 5L, 3L), .Label = c("CE", "CG", "LG", "NE", "NN"), class = "factor"),
GAME1_Level = c(6, 7, 6, 7, 7), GAME1_Alive = structure(c(1L,
1L, 1L, 1L, 1L), .Label = "y", class = "factor"), GAME2_Class = structure(c(3L,
5L, 2L, 4L, 1L), .Label = c("bard", "cleric", "fighter",
"monk", "wizard"), class = "factor"), GAME2_Race = structure(c(2L,
3L, 2L, 4L, 1L), .Label = c("dwarf", "elf", "half-elf", "human"
), class = "factor"), GAME2_Alignment = structure(c(4L, 2L,
1L, 5L, 3L), .Label = c("CE", "CG", "LG", "NE", "NN"), class = "factor"),
GAME2_Level = c(5, 5, 5, 5, 5), GAME2_Alive = structure(c(1L,
2L, 2L, 2L, 2L), .Label = c("n", "y"), class = "factor")), row.names = c(NA,
5L), class = "data.frame")
dput（head（MAR_gems））输出：
structure(list(GAME3_Class = structure(c(2L, 1L, 5L, 4L, 3L), .Label = c("barbarian",
"cleric", "monk", "ranger", "warlock"), class = "factor"), GAME3_Race = structure(c(2L,
3L, 2L, 4L, 1L), .Label = c("dwarf", "elf", "half-elf", "human"
), class = "factor"), GAME3_Alignment = structure(c(2L, 2L, 1L,
3L, 2L), .Label = c("CE", "LG", "LN"), class = "factor"), GAME3_Level = c(1,
1, 1, 1, 1), GAME3_Alive = structure(c(2L, 2L, 2L, 1L, 2L), .Label = c("n",
"y"), class = "factor"), GAME4_Class = structure(c(2L, 1L, 5L,
4L, 3L), .Label = c("fighter", "paladin", "rouge", "sorcerer",
"wizard"), class = "factor"), GAME4_Race = structure(c(2L, 3L,
2L, 4L, 1L), .Label = c("dwarf", "elf", "half-elf", "human"), class = "factor"),
GAME4_Alignment = structure(c(1L, 2L, 1L, 4L, 3L), .Label = c("CE",
"CG", "LG", "LN"), class = "factor"), GAME4_Level = c(5,
5, 5, 5, 5), GAME4_Alive = structure(c(1L, 2L, 2L, 2L, 2L
), .Label = c("n", "y"), class = "factor")), row.names = c(NA,
5L), class = "data.frame")
为此进行了尝试，包括：
分隔游戏信息
CharecterInfo <- function(df){
names(df) -> rons
gsub(x=names(df), pattern = '_.*', replacement = '') -> subn
subn[! duplicated(subn)] -> dupn
return(dupn)
}
CharecterInfo(FEB_games) -> FCharInfo
CharecterInfo(MAR_games) -> MCharInfo
然后尝试通过特定前缀将数据帧分开。
for (i in FCharInfo) {
assign(i, FCharInfo[, grep(paste0(i, '\\.'), colnames(FCharInfo), ignore.case = T)])
}
这不起作用，因为我的尺寸不正确，但是只会生成许多数据框，而不是列出列表。
我也尝试了R中的Map函数，但没有成功。
我的理想输出是：
1）包含“ GAME1 _”，“ GAME_2”，“ GAME_3”和“ GAME_4”数据作为单独数据帧的列表。
2）最好在函数中，因为我的真实数据比此处显示的数据大得多。
尝试说明理想的列表（我知道缩进/灰色框仅用于代码，但是我不知道如何在stackoverflow上说明列表）
GameInfo
Game1_
GAME1_Class
GAME1_Race
GAME1_Alignment
GAME1_Level
GAME1_Alive
Game2_
GAME2_Class
GAME2_Race
GAME2_Alignment
GAME2_Level
GAME2_Alive
Game3_
GAME3_Class
GAME3_Race
GAME3_Alignment
GAME3_Level
GAME3_Alive
Game4_
GAME4_Class
GAME4_Race
GAME4_Alignment
GAME4_Level
GAME4_Alive
我的前缀有点复杂，其中可能包括：
GAME_1.Class
GAME_10.Class
GAME_100.Class
我尝试过（基于Julian_hn的回答）
Gems <- list(FEB_gems = FEB_games, MAR_gems = MAR_games)
Gems.split <- lapply(Gems, function(df)
{
Games <- unique(str_extract(names(df),"[:alnum:]+..."))
List <- lapply(Games,function(name){return(df[,grep(name,names(df))])})
names(List) <- Games
return(List)
})
但是这不能区分1、100或1000。我可以在'。'之后分隔前缀。符号？
答案 0 :(得分：3)
如果您的FEB_gem和MAR_gem data.frames被构造为列表，则此方法对我有用。
library(stringr)
Gems <- list(FEB_gems=FEB_gems,MAR_gems=MAR_gems)
Gems.Split <- lapply(Gems,function(df)
{
#old solution, requires GAME as name
#Games <- unique(str_extract(names(df),"GAME[0-9]+"))
#old solution 2: splits at "_"
#Games <- unique(str_sub(str_extract(names(df),"[:alnum:]+_"),end=-2))
#new solution: splits at "."
Games <- unique(str_extract(names(df),"\\S+\\."))
List <- lapply(Games,function(name){return(df[,grep(name,names(df),fixed=T)])})
names(List) <- Games
return(List)
})
答案 1 :(得分：2)
这是使用 tidyverse 的一种方式：
fseq <- . %>%
rowid_to_column() %>%
gather(,,-rowid) %>%
separate(key,c("game","col")) %>%
spread(col,value) %>%
select(-rowid)
map_dfr(list(FEB_gems, MAR_gems), fseq) %>%
{split(.[-1],.$game)}
# $GAME1
# Alignment Alive Class Level Race
# 1 NE y paladin 6 human
# 3 CG y fighter 7 elf
# 5 CE y wizard 6 orc
# 7 NN y sorcerer 7 human
# 9 LG y rouge 7 gnome
#
# $GAME2
# Alignment Alive Class Level Race
# 2 NE n fighter 5 elf
# 4 CG y wizard 5 half-elf
# 6 CE y cleric 5 elf
# 8 NN y monk 5 human
# 10 LG y bard 5 dwarf
#
# $GAME3
# Alignment Alive Class Level Race
# 11 LG y cleric 1 elf
# 13 LG y barbarian 1 half-elf
# 15 CE y warlock 1 elf
# 17 LN n ranger 1 human
# 19 LG y monk 1 dwarf
#
# $GAME4
# Alignment Alive Class Level Race
# 12 CE n paladin 5 elf
# 14 CG y fighter 5 half-elf
# 16 CE y wizard 5 elf
# 18 LN y sorcerer 5 human
# 20 LG y rouge 5 dwarf
#
# Warning messages:
# 1: attributes are not identical across measure variables;
# they will be dropped
# 2: attributes are not identical across measure variables;
# they will be dropped
答案 2 :(得分：1)
另一种可能（嵌套）的tidyverse解决方案：
library(tidyverse)
t_tib <- function(df) {
as_tibble(cbind(nms = names(df), t(df)))
}
GameInfo <- t_tib(FEB_gems) %>%
bind_rows(t_tib(MAR_gems)) %>%
gather(rowid, val, -nms) %>%
separate(nms, into = c("Game", "var")) %>%
spread(var, val) %>%
select(-rowid) %>%
select(1, 4, 6, 2, 5, 3) %>%
nest(-Game)
（根据Moody_Mudskipper的建议删除了bind_cols。）