I have 5 data frames:
a <- data.frame(ID = c("1", "2", "3", "4", "5"), peak = c("peak1", "peak2", "peak3", "peak4", "peak10"))
b <- data.frame(ID = c("1", "2", "3", "4"), peak = c("peak1","peak3", "peak20", "peak21"))
c <- data.frame(ID = c("1", "2", "3"), peak = c("peak1", "peak5", "peak3"))
d <- data.frame(ID = c("1", "2", "3", "4", "5", "6"),peak = c("peak1", "peak3", "peak7", "peak8", "peak11", "peak12"))
e <- data.frame(ID = c("1", "2", "3"), peak = c("peak1", "peak3", "peak9"))
I would like to remove the common peaks across the data frames, with a desired outputs:
a <- data.frame(ID = c("1", "2", "3", "4", "5"), peak = c("peak2", "peak4", "peak10"))
b <- data.frame(ID = c("1", "2", "3", "4"), peak = c("peak20", "peak21"))
c <- data.frame(ID = c("1", "2", "3"), peak = c("peak5", ))
d <- data.frame(ID = c("1", "2", "3", "4", "5", "6"),peak = c( "peak7", "peak8", "peak11", "peak12"))
e <- data.frame(ID = c("1", "2", "3"), peak = c( "peak9"))
I know how to compare two data frames a[!(a$peak %in% b$peak),] but I'm struggling with 5.
Use the following approach :
#Put the data in a list
list_df <- dplyr::lst(a, b, c, d, e)
#Get the common peak value
common_peak <- Reduce(intersect, lapply(list_df, `[[`, 'peak'))
common_peak
#[1] "peak1" "peak3"
#Remove the common peak value from all the dataframes
result <- lapply(list_df, function(x) subset(x, !peak %in% common_peak))
result
#$a
# ID peak
#2 2 peak2
#4 4 peak4
#5 5 peak10
#$b
# ID peak
#3 3 peak20
#4 4 peak21
#$c
# ID peak
#2 2 peak5
#$d
# ID peak
#3 3 peak7
#4 4 peak8
#5 5 peak11
#6 6 peak12
#$e
# ID peak
#3 3 peak9
#Update all the individual dataframes
list2env(result, .GlobalEnv)