CODEWITHSUNDEEP
rfunctional-programmingdplyrpurrr
SteveS
SteveS

Reputation: 4040

Map and bind different dataframes given a list of different dataframes

Given a function foo that outputs a list of 3 dataframes:

structure(list(isSameUser = structure(1:2, .Label = c("0", "1"
), class = "factor"), n = c(212L, 72L), cum_n = c(212L, 284L), 
    user_id = c(1, 1)), .Names = c("isSameUser", "n", "cum_n", 
"user_id"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-2L))

structure(list(isSameUser = structure(1:2, .Label = c("0", "1"
), class = "factor"), n = c(54L, 18L), cum_n = c(54L, 72L), user_id = c(1, 
1)), .Names = c("isSameUser", "n", "cum_n", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -2L))

structure(list(error_abs_perc = 0.0694444444444444, user_id = 1), .Names = c("error_abs_perc", 
"user_id"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-1L))

I have 1000 users ----> meaning I have 1000*3 dataframes, 1000 of the first, 1000 of the second and 1000 of the third. Please advise how can I map_dfr it and get 3 binded dataframes.

I am trying to do this using imap_dfr and map_dfr.

Tried this: Use Dplyr::Bind_Rows and Purrr to Selectively Bind Different Dataframes In a List of Dataframes

But it doesn't solve my issue.

Per @markus request:

list(structure(list(train_stats = structure(list(isSameUser = structure(1:2, .Label = c("0", 
"1"), class = "factor"), n = c(212L, 72L), cum_n = c(212L, 284L
), user_id = c(1L, 1L)), .Names = c("isSameUser", "n", "cum_n", 
"user_id"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-2L)), test_stats = structure(list(isSameUser = structure(1:2, .Label = c("0", 
"1"), class = "factor"), n = c(54L, 18L), cum_n = c(54L, 72L), 
    user_id = c(1L, 1L)), .Names = c("isSameUser", "n", "cum_n", 
"user_id"), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-2L)), test_set_error = structure(list(error_abs_perc = 0.0694444444444444, 
    user_id = 1L), .Names = c("error_abs_perc", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -1L))), .Names = c("train_stats", 
"test_stats", "test_set_error")), structure(list(train_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(238L, 46L), cum_n = c(238L, 284L), user_id = c(2L, 
    2L)), .Names = c("isSameUser", "n", "cum_n", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -2L)), test_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(60L, 12L), cum_n = c(60L, 72L), user_id = c(2L, 2L)), .Names = c("isSameUser", 
"n", "cum_n", "user_id"), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -2L)), test_set_error = structure(list(error_abs_perc = 0.0555555555555556, 
    user_id = 2L), .Names = c("error_abs_perc", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -1L))), .Names = c("train_stats", 
"test_stats", "test_set_error")), structure(list(train_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(232L, 52L), cum_n = c(232L, 284L), user_id = c(3L, 
    3L)), .Names = c("isSameUser", "n", "cum_n", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -2L)), test_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(58L, 14L), cum_n = c(58L, 72L), user_id = c(3L, 3L)), .Names = c("isSameUser", 
"n", "cum_n", "user_id"), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -2L)), test_set_error = structure(list(error_abs_perc = 0.0138888888888889, 
    user_id = 3L), .Names = c("error_abs_perc", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -1L))), .Names = c("train_stats", 
"test_stats", "test_set_error")), structure(list(train_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(224L, 60L), cum_n = c(224L, 284L), user_id = c(4L, 
    4L)), .Names = c("isSameUser", "n", "cum_n", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -2L)), test_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(56L, 16L), cum_n = c(56L, 72L), user_id = c(4L, 4L)), .Names = c("isSameUser", 
"n", "cum_n", "user_id"), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -2L)), test_set_error = structure(list(error_abs_perc = 0.0694444444444444, 
    user_id = 4L), .Names = c("error_abs_perc", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -1L))), .Names = c("train_stats", 
"test_stats", "test_set_error")), structure(list(train_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(232L, 52L), cum_n = c(232L, 284L), user_id = c(5L, 
    5L)), .Names = c("isSameUser", "n", "cum_n", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -2L)), test_stats = structure(list(
    isSameUser = structure(1:2, .Label = c("0", "1"), class = "factor"), 
    n = c(58L, 14L), cum_n = c(58L, 72L), user_id = c(5L, 5L)), .Names = c("isSameUser", 
"n", "cum_n", "user_id"), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -2L)), test_set_error = structure(list(error_abs_perc = 0.0138888888888889, 
    user_id = 5L), .Names = c("error_abs_perc", "user_id"), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -1L))), .Names = c("train_stats", 
"test_stats", "test_set_error")))

Upvotes: 1

Views: 81

Answers (1)

markus
markus

Reputation: 26343

We can transpose your list and then use map and bind_rows

library(purrr)
map(transpose(lst), bind_rows)
#$train_stats
# A tibble: 10 x 4
#   isSameUser     n cum_n user_id
#   <fct>      <int> <int>   <int>
# 1 0            212   212       1
# 2 1             72   284       1
# 3 0            238   238       2
# 4 1             46   284       2
# 5 0            232   232       3
# 6 1             52   284       3
# 7 0            224   224       4
# 8 1             60   284       4
# 9 0            232   232       5
#10 1             52   284       5

#$test_stats
# A tibble: 10 x 4
#   isSameUser     n cum_n user_id
#   <fct>      <int> <int>   <int>
# 1 0             54    54       1
# 2 1             18    72       1
# 3 0             60    60       2
# 4 1             12    72       2
# 5 0             58    58       3
# 6 1             14    72       3
# 7 0             56    56       4
# 8 1             16    72       4
# 9 0             58    58       5
#10 1             14    72       5

#$test_set_error
# A tibble: 5 x 2
#  error_abs_perc user_id
#           <dbl>   <int>
#1         0.0694       1
#2         0.0556       2
#3         0.0139       3
#4         0.0694       4
#5         0.0139       5

Upvotes: 1

Related Questions