删除R中数据帧中重复单元格(不是整行/列)的所有实例

data.frame(
  genes_1 = c("a","b","c","d","e"),
  genes_2 = c("f","g","c","e","j"),
  genes_3 = c("a","b","m","n","o"),
  stringsAsFactors = FALSE
) -> xdf

dups <- names(which(table(unlist(xdf, use.names = FALSE)) > 1))

xdf[] <- lapply(xdf, function(x) { x[x %in% dups] <- "" ; x })

xdf

unlist() 递归地将所有列展开为单个字符向量。

table() 计算每个元素的所有出现次数。

which() TRUE

names() 获取角色选择向量元素。

""

library(microbenchmark)
library(data.table)

microbenchmark(
  base = {
    ydf <- xdf
    dups <- names(which(table(unlist(ydf, use.names = FALSE)) > 1))
    ydf[] <- lapply(ydf, function(x) { x[x %in% dups] <- "" ; x })
  },
  base.2 = {
    ydf <- xdf
    tmp <- unlist(ydf)
    ydf[arrayInd(which(duplicated(tmp) | duplicated(tmp, fromLast = TRUE)), dim(ydf))] <- ""
  },
  tidyverse = {
    ydf <- xdf
    ydf %>%
      gather(genes, value) %>%
      add_count(value) %>%
      mutate(value = ifelse(n > 1, "", value)) %>%
      select(-n) %>%
      group_by(genes) %>%
      mutate(ID = 1:n()) %>%
      spread(genes, value) %>%
      select(-ID) -> ydf
  },
  data.table = {
    ydt <- data.table(xdf)
    ydt[,lapply(.SD, function(x) { x[x %in% dups] <- "" ; x })]
  }
) %>%
  { print(.) ; . } %>% 
  autoplot()

另一种基本解决方案:

tmp <- unlist(df)
df[arrayInd(which(duplicated(tmp) | duplicated(tmp,fromLast=TRUE)), dim(df))] <- NA

#  genes_1 genes_2 genes_3
#1    <NA>       f    <NA>
#2    <NA>       g    <NA>
#3    <NA>    <NA>       m
#4       d    <NA>       n
#5    <NA>       j       o

unlist 只需为中的所有值创建一个长向量 df
arrayInd 然后为子集创建一个两列的行/列索引 测向 duplicated 价值观。

tidyverse 解决方案。 df2 是最终输出。

library(tidyverse)

df2 <- df %>%
  gather(genes, value) %>%
  add_count(value) %>%
  mutate(value = ifelse(n > 1, "", value)) %>%
  select(-n) %>%
  group_by(genes) %>%
  mutate(ID = 1:n()) %>%
  spread(genes, value) %>%
  select(-ID)