Flatten recursive list

Question

There are quite a few questions apparently on this topic, but I can\'t see any general solution proposed: I have a deeply recursive list and want to flatten it into a single lis

Answer 1

Your data:

d <- list(
  list(
    list(
      iris[sample(1:150,3),],
      iris[sample(1:150,3),]
    ),
    list(
      list(
        iris[sample(1:150,3),],
        list(
          iris[sample(1:150,3),],
          iris[sample(1:150,3),]
        )
      )
    )
  )
)

First, a crude, but effective function:

f <- function(x) {

  if (is.null(x)) return
  n <- length(x)

  if (length(n) == 0) return

  for (i in 1:n) {

    if (is.data.frame(x[[i]])) {
      res <<- append(res, list(x[[i]]))
    } else {
      if (is.list(x[[i]])) {
        f(x[[i]])
      }
    }

  }

}

The crude but effective accompanying global variable:

res <- list()

f(d)

The results:

res
## [[1]]
##    Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 37          5.5         3.5          1.3         0.2  setosa
## 16          5.7         4.4          1.5         0.4  setosa
## 8           5.0         3.4          1.5         0.2  setosa
## 
## [[2]]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 10           4.9         3.1          1.5         0.1     setosa
## 141          6.7         3.1          5.6         2.4  virginica
## 86           6.0         3.4          4.5         1.6 versicolor
## 
## [[3]]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
## 134          6.3         2.8          5.1         1.5 virginica
## 40           5.1         3.4          1.5         0.2    setosa
## 3            4.7         3.2          1.3         0.2    setosa
## 
## [[4]]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 33           5.2         4.1          1.5         0.1     setosa
## 132          7.9         3.8          6.4         2.0  virginica
## 76           6.6         3.0          4.4         1.4 versicolor
## 
## [[5]]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
## 10           4.9         3.1          1.5         0.1    setosa
## 16           5.7         4.4          1.5         0.4    setosa
## 135          6.1         2.6          5.6         1.4 virginica

Less crude (no global variable) solution:

f2 <- function(x) {

  res <- list()

  if (is.null(x)) return
  n <- length(x)

  if (length(n) == 0) return

  for (i in 1:n) {
    if (is.data.frame(x[[i]])) {
      res <- append(res, list(x[[i]]))
    } else {
      if (is.list(x[[i]])) res <- append(res, f2(x[[i]]))
    }
  }

  return(res)

}

f2(d)
## same output

Answer 2

This is a general flatten function using only base R:

flatten <- function(x) {
  if (!inherits(x, "list")) return(list(x))
  else return(unlist(c(lapply(x, flatten)), recursive = FALSE))
}

Result:

flatten(d)
#[[1]]
#    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#44           5.0         3.5          1.6         0.6     setosa
#138          6.4         3.1          5.5         1.8  virginica
#87           6.7         3.1          4.7         1.5 versicolor
#
#[[2]]
#   Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#19          5.7         3.8          1.7         0.3     setosa
#1           5.1         3.5          1.4         0.2     setosa
#71          5.9         3.2          4.8         1.8 versicolor
#
#[[3]]
#    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#31           4.8         3.1          1.6         0.2     setosa
#98           6.2         2.9          4.3         1.3 versicolor
#134          6.3         2.8          5.1         1.5  virginica
#
#[[4]]
#    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#140          6.9         3.1          5.4         2.1  virginica
#119          7.7         2.6          6.9         2.3  virginica
#57           6.3         3.3          4.7         1.6 versicolor
#
#[[5]]
#    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#73           6.3         2.5          4.9         1.5 versicolor
#54           5.5         2.3          4.0         1.3 versicolor
#146          6.7         3.0          5.2         2.3  virginica

Similarly:

x <- list(list("A"), list(list("A"), list("A")))
flatten(x)
#[[1]]
#[1] "A"
#
#[[2]]
#[1] "A"
#
#[[3]]
#[1] "A"

x <- list(list(1), list(list(2), list(3)))
flatten(x)
#[[1]]
#[1] 1
#
#[[2]]
#[1] 2
#
#[[3]]
#[1] 3

It seems a bit round-about to add more lists when the goal is to remove them, but the list/unlist route is the only reliable way to concatenate lists with different numbers of elements.

Answer 3

rrapply in the rrapply package is a generalization of rapply that can flatten the nested list into a list of leaves. dfaslist=FALSE will cause data frames to be regarded as leaves rather than being recursed into.

library(rrapply)

rrapply(d, f = identity, dfaslist = FALSE, how = "flatten")

Answer 4

rlang::squash is pretty magical:

set.seed(47)

d = list(list(list(iris[sample(1:150,3),],
                   iris[sample(1:150,3),]),
              list(list(iris[sample(1:150,3),],
                        list(iris[sample(1:150,3),],
                             iris[sample(1:150,3),])
              ))
))

rlang::squash(d)
#> [[1]]
#>     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#> 147          6.3         2.5          5.0         1.9  virginica
#> 56           5.7         2.8          4.5         1.3 versicolor
#> 113          6.8         3.0          5.5         2.1  virginica
#> 
#> [[2]]
#>     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#> 124          6.3         2.7          4.9         1.8  virginica
#> 86           6.0         3.4          4.5         1.6 versicolor
#> 103          7.1         3.0          5.9         2.1  virginica
#> 
#> [[3]]
#>    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#> 59          6.6         2.9          4.6         1.3 versicolor
#> 70          5.6         2.5          3.9         1.1 versicolor
#> 81          5.5         2.4          3.8         1.1 versicolor
#> 
#> [[4]]
#>     Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
#> 139          6.0         3.0          4.8         1.8 virginica
#> 21           5.4         3.4          1.7         0.2    setosa
#> 104          6.3         2.9          5.6         1.8 virginica
#> 
#> [[5]]
#>    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
#> 25          4.8         3.4          1.9         0.2     setosa
#> 90          5.5         2.5          4.0         1.3 versicolor
#> 75          6.4         2.9          4.3         1.3 versicolor