R：根据 NA 位置合并来自相同 data.frame 的列

Question

我有这样一个数据框：

df <- data.frame(theme1=c("hello",NA,NA,NA), theme2=c(NA,"world",NA,NA), theme3=c(NA,NA,"good_morning",NA), theme4=c(NA,NA,NA,"good_evening"))

theme1 theme2 theme3 theme4 1 hello NA NA NA 2 NA world NA NA 3 NA NA good_morning NA 4 NA NA NA good_evening

现在我想获得保留行顺序的一列：

**Theme_merged** hello world good_morning good_evening

尝试次数：

merge_themes <- data.frame(cbind(mycol = na.omit(unlist(data2_tst[18:23]))), stringsAsFactors = F)

上面的代码有效，但不保留行顺序，所以当我想将向量放回原始数据帧时，它不再匹配。

真实数据：

dput(head(data2_tst[18:23], n = 50))
structure(list(Theme1 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, "%Bedrukken%", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, "%Bedrukken%", NA, NA, NA, NA, NA, NA, NA, NA), Theme2 = c(NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "%Nieuwste|Nieuwe|201[6:7]%", 
"%Nieuwste|Nieuwe|201[6:7]%", "%Nieuwste|Nieuwe|201[6:7]%", NA, 
NA, NA, NA, NA, "%Nieuwste|Nieuwe|201[6:7]%", "%Nieuwste|Nieuwe|201[6:7]%", 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "%Nieuwste|Nieuwe|201[6:7]%", 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "%Nieuwste|Nieuwe|201[6:7]%", 
"%Nieuwste|Nieuwe|201[6:7]%"), Theme3 = c("%Nodig%", NA, "%Nodig%", 
"%Nodig%", "%Nodig%", NA, NA, "%Nodig%", NA, "%Nodig%", NA, NA, 
NA, NA, "%Nodig%", "%Nodig%", "%Nodig%", NA, NA, NA, NA, NA, 
NA, "%Nodig%", "%Nodig%", NA, NA, "%Nodig%", NA, "%Nodig%", "%Nodig%", 
"%Nodig%", NA, "%Nodig%", "%Nodig%", "%Nodig%", NA, NA, NA, "%Nodig%", 
"%Nodig%", NA, "%Nodig%", NA, "%Nodig%", "%Nodig%", NA, "%Nodig%", 
NA, NA), Theme4 = c(NA, "%Kopen%", NA, NA, NA, "%Kopen%", "%Kopen%", 
NA, "%Kopen%", NA, NA, NA, NA, NA, NA, NA, NA, "%Kopen%", "%Kopen%", 
NA, NA, "%Kopen%", "%Kopen%", NA, NA, "%Kopen%", "%Kopen%", NA, 
"%Kopen%", NA, NA, NA, NA, NA, NA, NA, "%Kopen%", "%Kopen%", 
"%Kopen%", NA, NA, NA, NA, "%Kopen%", NA, NA, "%Kopen%", NA, 
NA, NA), Theme5 = c(NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_), Theme6 = c(NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_, NA_character_, NA_character_, 
NA_character_, NA_character_, NA_character_)), .Names = c("Theme1", 
"Theme2", "Theme3", "Theme4", "Theme5", "Theme6"), row.names = 3:52, class = "data.frame")

Answer 1

这是一个 tidyverse 解决方案（使用 dplyr 和 tidyr 或仅使用 tidyverse）

library(tidyverse)

> df <- df %>% 
    gather("theme", "theme_merged", 1:4) %>%
    filter(!is.na(theme_merged)) %>% 
    select(theme_merged)

> df
  theme_merged
1        hello
2        world
3 good_morning
4 good_evening

Answer 2

在 SQL 中，这将是 COALESCE 函数：

apply(df, 1, function(r) c(na.omit(r), NA)[1])
# [1] "hello"        "world"        "good_morning" "good_evening"

df <- data.frame(
    theme1=c("hello",NA,NA,NA), 
    theme2=c(NA,"world",NA,NA), 
    theme3=c(NA,NA,"good_morning",NA), 
    theme4=c(NA,NA,NA,"good_evening"),
    stringsAsFactors = FALSE
)

在您的示例数据 na.omit(unlist(df2, use.names = FALSE)) 上可以正常工作，但如果有一行只有 NA 值，它将失败：

df2 <- data.frame(
    theme1=c("hello",NA,NA,NA,NA), 
    theme2=c(NA,"world",NA,NA,NA), 
    theme3=c(NA,NA,"good_morning",NA,NA), 
    theme4=c(NA,NA,NA,"good_evening",NA),
    theme5=c(NA_character_,NA_character_,NA_character_,
             NA_character_,NA_character_),
    stringsAsFactors = FALSE
)

df2$X <- na.omit(unlist(df2, use.names = FALSE))
# Error in `$<-.data.frame`(`*tmp*`, "X", value = c("hello", "world", "good_morning",  : 
#   replacement has 4 rows, data has 5

df2$X <- apply(df2, 1, function(r) c(na.omit(r), NA)[1])
#   theme1 theme2       theme3       theme4 theme5            X
# 1  hello   <NA>         <NA>         <NA>   <NA>        hello
# 2   <NA>  world         <NA>         <NA>   <NA>        world
# 3   <NA>   <NA> good_morning         <NA>   <NA> good_morning
# 4   <NA>   <NA>         <NA> good_evening   <NA> good_evening
# 5   <NA>   <NA>         <NA>         <NA>   <NA>         <NA>

另一个选项可以是 df2$X <- df2[cbind(1:nrow(df2), max.col(!is.na(df2)))]

Answer 3

dplyr 0.5.0版本引入了合并功能：

This version of dplyr gains a number of vector functions inspired by SQL. Two functions make it a little easier to eliminate or generate missing values:

Given a set of vectors, coalesce() finds the first non-missing value in each position.

要将此应用于示例数据框，您可以使用：

df <- mutate_all(df, .funs = as.character)
df$merged <- with(df, coalesce(theme1, theme2, theme3, theme4))

我发现有必要将因子转换为字符以避免 'invalid factor levels' 错误。

您的真实数据无需转换：

df$merged <- with(df, coalesce(Theme1, Theme2, Theme3, Theme4, Theme5, Theme6)

Answer 4

这应该适用于您的数据：

new_df = c(as.matrix(df))

此行首先将 df 转换为矩阵，并将所有列与 c() 绑定到一个向量中。

new_df <- new_df[!is.na(new_df)]

现在我们只保留非NA条目。如果您愿意，可以将其转换回数据框：

new_df <- data.frame(new_df);names(new_df) <- "Themes"

R：根据 NA 位置合并来自相同 data.frame 的列

R: merge columns from same data.frame based on NA positions

merge

r

cbind