spliting a data.frame to a list of smaller data.frames containing a pair

user_16762740 0
Viewed 69

I wonder how to split my data below such that I get a list of smaller dataf.rames each of which containing a unique pair of type in it?

My desired_output is shown below.

Note that this is just a toy data, so type can be any other variable. Also, note that if a particular type has just one row (like type == 4), I want to exclude that with a warning that says:

type 4 has just one row thus is excluded.

m=
"
  obs   type
    1   1
    2   1
    3   a
    4   a
    5   3
    6   3
    7   4
"
data <- read.table(text = m, h=T)


desired_output <-list(
  
  data.frame(obs=1:4,   type=c(1,1,"a","a")),
  
  data.frame(obs=c(1,2,5,6),   type=c(1,1,3,3)),
  
  data.frame(obs=3:6,   type=c("a","a",3,3))
)

# warning: type 4 has just one row thus is excluded.
dplyr tidyverse dataframe r function
2 Answers

Here is base R function -

return_list_data <- function(data, type) {
  unique_counts <- table(data[[type]])
  single_count <- names(unique_counts[unique_counts == 1])
  if(length(single_count)) {
    warning(sprintf('%s %s has just one row thus is excluded.', type, toString(single_count)))
  }
  multiple_count <- names(unique_counts[unique_counts > 1])
  
  combn(multiple_count, 2, function(x) {
    data[data[[type]] %in% x, ]
  }, simplify = FALSE)  
}

This returns -

return_list_data(data, 'type')

#[[1]]
#  obs type
#1   1    1
#2   2    1
#5   5    3
#6   6    3

#[[2]]
#  obs type
#1   1    1
#2   2    1
#3   3    a
#4   4    a

#[[3]]
#  obs type
#3   3    a
#4   4    a
#5   5    3
#6   6    3

#Warning message:
#In return_list_data(data, "type") :
#  type 4 has just one row thus is excluded.

No warning is generated if there is no type with single row i.e return_list_data(data[-7, ], 'type').

user_39629140

You may try using dplyr,

df1 <- read.table(text = m, h=T)
fun <- function(df1){
  df2 <- df1 %>%
    group_by(type) %>%
    filter(n() > 1) 
  
  df3 <- combn(unique(df2$type), 2) %>% as.data.frame
  
  df4 <- lapply(df3, function(x){
    df2 %>%
      filter(type %in% x)
  })
  war <- df1 %>%
    group_by(type) %>%
    filter(n()<= 1) %>%
    pull(type)%>%
    unique
  if (length(war)>0){
  warning(paste("type", war, "has just one row thus is excluded"))}
  return(df4)
}
fun(df1)

result:

$V1
# A tibble: 4 x 2
# Groups:   type [2]
    obs type 
  <int> <chr>
1     1 1    
2     2 1    
3     3 a    
4     4 a    

$V2
# A tibble: 4 x 2
# Groups:   type [2]
    obs type 
  <int> <chr>
1     1 1    
2     2 1    
3     5 3    
4     6 3    

$V3
# A tibble: 4 x 2
# Groups:   type [2]
    obs type 
  <int> <chr>
1     3 a    
2     4 a    
3     5 3    
4     6 3 
Warnings: In fun(df1) : type 4 has just one row thus is excluded
user_167291750
Related