Question

我面临的挑战比我在这里意识到的要大：Merge contents from three dataframes into one column，因此是我的新问题。我有以下三个数据帧。

 df1 <- data.frame(c("A", "B", "C", "D"), 
      c("text1", "texta", "textk", "textx"),
      c("texti", "textI", "texti", "textI"))
 names(df1) <- c('dummy_1', 'dummy_2', 'dummy_3')
 df2 <- data.frame(c("A", "B", "C", "D"), 
      c("text2", "textb", "textl", "texty"), 
      c("textii", "textII", "textii", "textII"))
 names(df2) <- c('dummy_1', 'dummy_2', 'dummy_3')
 df3 <- data.frame(c("A", "B", "C", "D"), 
      c("text3", "textc", "textm", "textz"),
      c("textiii", "textIII", "textiii", "textIII"))
 names(df3) <- c('dummy_1', 'dummy_2', 'dummy_3')

如何将dfs df1，df2和df3中的每一列dummy_2和每一列dummy_3的文本合并到由" \n "分隔的一列中？所以理想的结果就是这个data.frame：

 dummy_1    dummy2_merge                 dummy3_merge
 A          text1 \n text2 \n text3      texti \n textii \n textiii
 B          texta \n textb \n textc      textI \n textII \n textIII
 C          textk \n textl \n textm      texti \n textii \n textiii
 D          textx \n texty \n textz      textI \n textII \n textIII

谢谢您的任何建议。

Answer 1

使用data.table进行合并和替换

library(data.table)

setDT(df1);setDT(df2);setDT(df3)

df1[df2, on = .(dummy_1), `:=` (dummy_2 = paste0(dummy_2, ' \n ', i.dummy_2),
                                dummy_3 = paste0(dummy_3, ' \n ', i.dummy_3))][]
df1[df3, on = .(dummy_1), `:=` (dummy_2 = paste0(dummy_2, ' \n ', i.dummy_2),
                                dummy_3 = paste0(dummy_3, ' \n ', i.dummy_3))][]

产生

   dummy_1                 dummy_2                    dummy_3
1:       A text1 \n text2 \n text3 texti \n textii \n textiii
2:       B texta \n textb \n textc textI \n textII \n textIII
3:       C textk \n textl \n textm texti \n textii \n textiii
4:       D textx \n texty \n textz textI \n textII \n textIII

Answer 2

您可以使用<div class="res-com"> <input class="res-com-pub" type="submit" value="Publish"> <input class="res-com-dec" type="submit" value="Cancel"> </div>和dplyr

tidyr

有输出

library(dplyr)
library(tidyr)

df <- left_join(left_join(df1, df2, by='dummy_1'), df3, by='dummy_1') #combine into one dataframe based on dummy_1
df <- df %>% unite('dummy2_merge', grep('dummy_2', colnames(df), value = T), sep=' \n ') # unite columns that have dummy_2 in their colname
df <- df %>% unite('dummy3_merge', grep('dummy_3', colnames(df), value = T), sep=' \n ') # unite columns that have dummy_3 in their colname

希望这会有所帮助。

Answer 3

通过R为底的想法可以是

d1 <- Reduce(function(...)merge(..., by = 'dummy_1'), list(df1, df2, df3))

sapply(unique(sub('\\..*', '', names(d1))), function(i) 
                                do.call(paste, c(d1[grepl(i, names(d1))], sep = ' \n ')))

#     dummy_1 dummy_2                   dummy_3                     
#[1,] "A"     "text1 \n text2 \n text3" "texti \n textii \n textiii"
#[2,] "B"     "texta \n textb \n textc" "textI \n textII \n textIII"
#[3,] "C"     "textk \n textl \n textm" "texti \n textii \n textiii"
#[4,] "D"     "textx \n texty \n textz" "textI \n textII \n textIII"

Answer 4

这里是使用tidyverse

的选项

library(tidyverse)
mget(paste0("df", 1:3)) %>% 
    reduce(left_join, by = 'dummy_1') %>% 
    split.default(str_remove(names(.), '\\..*$')) %>%
    map_dfc(~  .x %>%
             unite(!!rlang::sym(names(.)[length(.x)]),
                 !!! rlang::syms(names(.)), sep=" \n "))
# A tibble: 4 x 3
#  dummy_1 dummy_2                   dummy_3                     
#  <chr>   <chr>                     <chr>                       
#1 A       "text1 \n text2 \n text3" "texti \n textii \n textiii"
#2 B       "texta \n textb \n textc" "textI \n textII \n textIII"
#3 C       "textk \n textl \n textm" "texti \n textii \n textiii"
#4 D       "textx \n texty \n textz" "textI \n textII \n textIII"

将三个数据帧中的内容合并到R中的一列中（跨多列）

4 个答案: