r 将多列数据合并为一列

Question

我知道有很多关于这个主题的问题，所以如果这是一个重复的问题，我深表歉意。我正在尝试将数据集中的多列折叠成一列：

假设这是我正在使用的数据集的结构，

df <- data.frame(
      cbind(
      variable_1 = c('Var1', NA, NA,'Var1'),
      variable_2 = c('Var2', 'No', NA, NA),
      variable_3 = c(NA, NA, 'Var3', NA),
      variable_4 = c(NA, 'Var4', NA, NA),
      variable_5 = c(NA, 'No', 'Var5', NA),
      variable_6 = c(NA, NA, 'Var6', NA)

    ))

 variable_1  variable_2  variable_3  variable_4  variable_5  variable_6 
 Var1        Var2        NA          NA          NA          NA
 NA          No          NA          Var4        No          NA
 NA          NA          Var3        NA          Var5        Var6
 Var1        NA          NA          NA          NA          NA

我期待的是像这样的一栏 variable_7

 variable_1  variable_2  variable_3  variable_4  variable_5  variable_6  variable_7
 Var1        Var2        NA          NA          NA          NA          Var1, Var2
 NA          No          NA          Var4        No          NA          Var4
 NA          NA          Var3        NA          Var5        Var6        Var3, Var5, Var6
 Var1        NA          NA          NA          NA          NA          Var1

非常感谢任何帮助完成此任务的人。

Answer 1

df$variable_7 <- apply(df, 1, function(x) paste(x[!is.na(x) & x != "No"], collapse = ", "));
df;
#  variable_1 variable_2 variable_3 variable_4 variable_5 variable_6
#1       Var1       Var2       <NA>       <NA>       <NA>       <NA>
#2       <NA>         No       <NA>       Var4         No       <NA>
#3       <NA>       <NA>       Var3       <NA>       Var5       Var6
#4       Var1       <NA>       <NA>       <NA>       <NA>       <NA>
#        variable_7
#1       Var1, Var2
#2             Var4
#3 Var3, Var5, Var6
#4             Var1

说明：使用 apply 和 paste(..., collapse = ", ") 连接所有行条目（NAs 和 "No"s 除外）并存储在新列 variable_7 中.

示例数据

df <- data.frame(
      cbind(
      variable_1 = c('Var1', NA, NA,'Var1'),
      variable_2 = c('Var2', 'No', NA, NA),
      variable_3 = c(NA, NA, 'Var3', NA),
      variable_4 = c(NA, 'Var4', NA, NA),
      variable_5 = c(NA, 'No', 'Var5', NA),
      variable_6 = c(NA, NA, 'Var6', NA)

    ))

Answer 2

我收集到，如果有 n 行，那么 objective 是创建一个 n 向量，其中包含每行中包含字符 Var 的那些值的逗号分隔字符串。（如果您打算使用其他一些标准来分隔所需值和不需要的值，则相应地更改 grep。）

apply(df, 1, function(x) toString(grep("Var", x, value = TRUE)))
## [1] "Var1, Var2"       "Var4"             "Var3, Var5, Var6" "Var1"

Answer 3

使用 data.table 'reshap' 方法而不是 loop/apply

library(data.table)
setDT(df)

df[, id := .I][
    melt(df, id.vars = "id")[grepl("Var", value), .(variable_7 = paste0(value, collapse = ",")), by = .(id)]
    , on = "id"
    , nomatch = 0
    ][order(id)]


#    variable_1 variable_2 variable_3 variable_4 variable_5 variable_6 id     variable_7
# 1:       Var1       Var2         NA         NA         NA         NA  1      Var1,Var2
# 2:         NA         No         NA       Var4         No         NA  2           Var4
# 3:         NA         NA       Var3         NA       Var5       Var6  3 Var3,Var5,Var6
# 4:       Var1         NA         NA         NA         NA         NA  4           Var1

Answer 4

使用 dplyr 的解决方案。 df4 是最终输出。请看我是如何创建数据框的 df。 cbind 不是必需的，最好添加 stringsAsFactors = FALSE 以防止创建因子列。

library(dplyr)
library(tidyr)

df2 <- df %>% mutate(ID = 1:n()) 

df3 <- df2 %>%
  gather(Variable, Value, -ID, na.rm = TRUE) %>%
  filter(!Value %in% "No") %>%
  group_by(ID) %>%
  summarise(variable_7 = toString(Value))

df4 <- df2 %>% 
  left_join(df3, by = "ID") %>%
  select(-ID) 

df4
#   variable_1 variable_2 variable_3 variable_4 variable_5 variable_6       variable_7
# 1       Var1       Var2       <NA>       <NA>       <NA>       <NA>       Var1, Var2
# 2       <NA>         No       <NA>       Var4         No       <NA>             Var4
# 3       <NA>       <NA>       Var3       <NA>       Var5       Var6 Var3, Var5, Var6
# 4       Var1       <NA>       <NA>       <NA>       <NA>       <NA>             Var1

数据

df <- data.frame(
    variable_1 = c('Var1', NA, NA,'Var1'),
    variable_2 = c('Var2', 'No', NA, NA),
    variable_3 = c(NA, NA, 'Var3', NA),
    variable_4 = c(NA, 'Var4', NA, NA),
    variable_5 = c(NA, 'No', 'Var5', NA),
    variable_6 = c(NA, NA, 'Var6', NA),
    stringsAsFactors = FALSE
  )

r 将多列数据合并为一列

r collapsing data from multiple columns into one

aggregate

r

collapse

dplyr

示例数据