R语言purrr包详细介绍
KJY
2020-05-17
参考：
https://jiaxiangli.netlify.app/2018/02/27/purrr/ https://cloud.tencent.com/developer/article/1771939
urrr包除了占据tidyverse风格核心函数式编程的map_* 功能，还提供非常强大的list操作功能
R写循环有三个境界：
手动for循环 apply循环 purrr泛函式编程
泛函式定义: 函数的函数成为泛函式，map(x,f)中，map是函数，f也是函数，f是map的参数，那么map就是泛函数。 在数学上，函数的函数称为泛函，在编程中表示函数作用在函数上，或者说函数包含其它函数作为参数，这就是泛函式。 循环迭代，本质上就是将一个函数依次应用（映射）到序列的每一个元素上。 表示出来就是泛函式：map_*(x, f)
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.1.1 ✓ dplyr 1.0.5
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()载入R包tidyverse后，自动加载了8个R包，即ggplot2，tibble，tidyr，readr，purrr，dplyr，stringr，以及forcats(将在下文介绍其中最重要的几个包)。结果还显示，R包dplyr中的filter()函数与lag()函数分别“掩盖”(mask)了同名的R基础函数。如果你想调用R基础函数filter()或lag()，则须使用它们的全称stats::filter()或stats::lag()，从R的基础包stats调用这两个函数。
我们可以通过下面两种方式看一个包内所有的function
ls("package:purrr")## [1] "%@%" "%>%" "%||%"
## [4] "accumulate" "accumulate_right" "accumulate2"
## [7] "array_branch" "array_tree" "as_function"
## [10] "as_mapper" "as_vector" "assign_in"
## [13] "at_depth" "attr_getter" "auto_browse"
## [16] "chuck" "compact" "compose"
## [19] "cross" "cross_d" "cross_df"
## [22] "cross_n" "cross2" "cross3"
## [25] "detect" "detect_index" "discard"
## [28] "done" "every" "exec"
## [31] "flatten" "flatten_chr" "flatten_dbl"
## [34] "flatten_df" "flatten_dfc" "flatten_dfr"
## [37] "flatten_int" "flatten_lgl" "flatten_raw"
## [40] "has_element" "head_while" "imap"
## [43] "imap_chr" "imap_dbl" "imap_dfc"
## [46] "imap_dfr" "imap_int" "imap_lgl"
## [49] "imap_raw" "imodify" "insistently"
## [52] "invoke" "invoke_map" "invoke_map_chr"
## [55] "invoke_map_dbl" "invoke_map_df" "invoke_map_dfc"
## [58] "invoke_map_dfr" "invoke_map_int" "invoke_map_lgl"
## [61] "invoke_map_raw" "is_atomic" "is_bare_atomic"
## [64] "is_bare_character" "is_bare_double" "is_bare_integer"
## [67] "is_bare_list" "is_bare_logical" "is_bare_numeric"
## [70] "is_bare_vector" "is_character" "is_double"
## [73] "is_empty" "is_formula" "is_function"
## [76] "is_integer" "is_list" "is_logical"
## [79] "is_null" "is_numeric" "is_rate"
## [82] "is_scalar_atomic" "is_scalar_character" "is_scalar_double"
## [85] "is_scalar_integer" "is_scalar_list" "is_scalar_logical"
## [88] "is_scalar_numeric" "is_scalar_vector" "is_vector"
## [91] "iwalk" "keep" "lift"
## [94] "lift_dl" "lift_dv" "lift_ld"
## [97] "lift_lv" "lift_vd" "lift_vl"
## [100] "list_along" "list_merge" "list_modify"
## [103] "lmap" "lmap_at" "lmap_if"
## [106] "map" "map_at" "map_call"
## [109] "map_chr" "map_dbl" "map_depth"
## [112] "map_df" "map_dfc" "map_dfr"
## [115] "map_if" "map_int" "map_lgl"
## [118] "map_raw" "map2" "map2_chr"
## [121] "map2_dbl" "map2_df" "map2_dfc"
## [124] "map2_dfr" "map2_int" "map2_lgl"
## [127] "map2_raw" "modify" "modify_at"
## [130] "modify_depth" "modify_if" "modify_in"
## [133] "modify2" "negate" "none"
## [136] "partial" "pluck" "pluck<-"
## [139] "pmap" "pmap_chr" "pmap_dbl"
## [142] "pmap_df" "pmap_dfc" "pmap_dfr"
## [145] "pmap_int" "pmap_lgl" "pmap_raw"
## [148] "possibly" "prepend" "pwalk"
## [151] "quietly" "rate_backoff" "rate_delay"
## [154] "rate_reset" "rate_sleep" "rbernoulli"
## [157] "rdunif" "reduce" "reduce_right"
## [160] "reduce2" "reduce2_right" "rep_along"
## [163] "rerun" "safely" "set_names"
## [166] "simplify" "simplify_all" "slowly"
## [169] "some" "splice" "tail_while"
## [172] "transpose" "update_list" "vec_depth"
## [175] "walk" "walk2" "when"
## [178] "zap"lsf.str("package:purrr") # List Objects and their Structure## %@% : function (x, name)
## %>% : function (lhs, rhs)
## %||% : function (x, y)
## accumulate : function (.x, .f, ..., .init, .dir = c("forward", "backward"))
## accumulate_right : function (.x, .f, ..., .init)
## accumulate2 : function (.x, .y, .f, ..., .init)
## array_branch : function (array, margin = NULL)
## array_tree : function (array, margin = NULL)
## as_function : function (...)
## as_mapper : function (.f, ...)
## as_vector : function (.x, .type = NULL)
## assign_in : function (x, where, value)
## at_depth : function (.x, .depth, .f, ...)
## attr_getter : function (attr)
## auto_browse : function (.f)
## chuck : function (.x, ...)
## compact : function (.x, .p = identity)
## compose : function (..., .dir = c("backward", "forward"))
## cross : function (.l, .filter = NULL)
## cross_d : function (...)
## cross_df : function (.l, .filter = NULL)
## cross_n : function (...)
## cross2 : function (.x, .y, .filter = NULL)
## cross3 : function (.x, .y, .z, .filter = NULL)
## detect : function (.x, .f, ..., .dir = c("forward", "backward"), .right = NULL,
## .default = NULL)
## detect_index : function (.x, .f, ..., .dir = c("forward", "backward"), .right = NULL)
## discard : function (.x, .p, ...)
## done : function (x)
## every : function (.x, .p, ...)
## exec : function (.fn, ..., .env = caller_env())
## flatten : function (.x)
## flatten_chr : function (.x)
## flatten_dbl : function (.x)
## flatten_df : function (.x, .id = NULL)
## flatten_dfc : function (.x)
## flatten_dfr : function (.x, .id = NULL)
## flatten_int : function (.x)
## flatten_lgl : function (.x)
## flatten_raw : function (.x)
## has_element : function (.x, .y)
## head_while : function (.x, .p, ...)
## imap : function (.x, .f, ...)
## imap_chr : function (.x, .f, ...)
## imap_dbl : function (.x, .f, ...)
## imap_dfc : function (.x, .f, ...)
## imap_dfr : function (.x, .f, ..., .id = NULL)
## imap_int : function (.x, .f, ...)
## imap_lgl : function (.x, .f, ...)
## imap_raw : function (.x, .f, ...)
## imodify : function (.x, .f, ...)
## insistently : function (f, rate = rate_backoff(), quiet = TRUE)
## invoke : function (.f, .x = NULL, ..., .env = NULL)
## invoke_map : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_chr : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_dbl : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_df : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_dfc : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_dfr : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_int : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_lgl : function (.f, .x = list(NULL), ..., .env = NULL)
## invoke_map_raw : function (.f, .x = list(NULL), ..., .env = NULL)
## is_atomic : function (x, n = NULL)
## is_bare_atomic : function (x, n = NULL)
## is_bare_character : function (x, n = NULL)
## is_bare_double : function (x, n = NULL)
## is_bare_integer : function (x, n = NULL)
## is_bare_list : function (x, n = NULL)
## is_bare_logical : function (x, n = NULL)
## is_bare_numeric : function (x, n = NULL)
## is_bare_vector : function (x, n = NULL)
## is_character : function (x, n = NULL)
## is_double : function (x, n = NULL, finite = NULL)
## is_empty : function (x)
## is_formula : function (x, scoped = NULL, lhs = NULL)
## is_function : function (x)
## is_integer : function (x, n = NULL)
## is_list : function (x, n = NULL)
## is_logical : function (x, n = NULL)
## is_null : function (x)
## is_numeric : function (x)
## is_rate : function (x)
## is_scalar_atomic : function (x)
## is_scalar_character : function (x)
## is_scalar_double : function (x)
## is_scalar_integer : function (x)
## is_scalar_list : function (x)
## is_scalar_logical : function (x)
## is_scalar_numeric : function (x)
## is_scalar_vector : function (x)
## is_vector : function (x, n = NULL)
## iwalk : function (.x, .f, ...)
## keep : function (.x, .p, ...)
## lift : function (..f, ..., .unnamed = FALSE)
## lift_dl : function (..f, ..., .unnamed = FALSE)
## lift_dv : function (..f, ..., .unnamed = FALSE)
## lift_ld : function (..f, ...)
## lift_lv : function (..f, ...)
## lift_vd : function (..f, ..., .type)
## lift_vl : function (..f, ..., .type)
## list_along : function (x)
## list_merge : function (.x, ...)
## list_modify : function (.x, ...)
## lmap : function (.x, .f, ...)
## lmap_at : function (.x, .at, .f, ...)
## lmap_if : function (.x, .p, .f, ..., .else = NULL)
## map : function (.x, .f, ...)
## map_at : function (.x, .at, .f, ...)
## map_call : function (.x, .f, ...)
## map_chr : function (.x, .f, ...)
## map_dbl : function (.x, .f, ...)
## map_depth : function (.x, .depth, .f, ..., .ragged = FALSE)
## map_df : function (.x, .f, ..., .id = NULL)
## map_dfc : function (.x, .f, ...)
## map_dfr : function (.x, .f, ..., .id = NULL)
## map_if : function (.x, .p, .f, ..., .else = NULL)
## map_int : function (.x, .f, ...)
## map_lgl : function (.x, .f, ...)
## map_raw : function (.x, .f, ...)
## map2 : function (.x, .y, .f, ...)
## map2_chr : function (.x, .y, .f, ...)
## map2_dbl : function (.x, .y, .f, ...)
## map2_df : function (.x, .y, .f, ..., .id = NULL)
## map2_dfc : function (.x, .y, .f, ...)
## map2_dfr : function (.x, .y, .f, ..., .id = NULL)
## map2_int : function (.x, .y, .f, ...)
## map2_lgl : function (.x, .y, .f, ...)
## map2_raw : function (.x, .y, .f, ...)
## modify : function (.x, .f, ...)
## modify_at : function (.x, .at, .f, ...)
## modify_depth : function (.x, .depth, .f, ..., .ragged = .depth < 0)
## modify_if : function (.x, .p, .f, ..., .else = NULL)
## modify_in : function (.x, .where, .f, ...)
## modify2 : function (.x, .y, .f, ...)
## negate : function (.p)
## none : function (.x, .p, ...)
## partial : function (.f, ..., .env = NULL, .lazy = NULL, .first = NULL)
## pluck : function (.x, ..., .default = NULL)
## pluck<- : function (.x, ..., value)
## pmap : function (.l, .f, ...)
## pmap_chr : function (.l, .f, ...)
## pmap_dbl : function (.l, .f, ...)
## pmap_df : function (.l, .f, ..., .id = NULL)
## pmap_dfc : function (.l, .f, ...)
## pmap_dfr : function (.l, .f, ..., .id = NULL)
## pmap_int : function (.l, .f, ...)
## pmap_lgl : function (.l, .f, ...)
## pmap_raw : function (.l, .f, ...)
## possibly : function (.f, otherwise, quiet = TRUE)
## prepend : function (x, values, before = NULL)
## pwalk : function (.l, .f, ...)
## quietly : function (.f)
## rate_backoff : function (pause_base = 1, pause_cap = 60, pause_min = 1, max_times = 3,
## jitter = TRUE)
## rate_delay : function (pause = 1, max_times = Inf)
## rate_reset : function (rate)
## rate_sleep : function (rate, quiet = TRUE)
## rbernoulli : function (n, p = 0.5)
## rdunif : function (n, b, a = 1)
## reduce : function (.x, .f, ..., .init, .dir = c("forward", "backward"))
## reduce_right : function (.x, .f, ..., .init)
## reduce2 : function (.x, .y, .f, ..., .init)
## reduce2_right : function (.x, .y, .f, ..., .init)
## rep_along : function (along, x)
## rerun : function (.n, ...)
## safely : function (.f, otherwise = NULL, quiet = TRUE)
## set_names : function (x, nm = x, ...)
## simplify : function (.x, .type = NULL)
## simplify_all : function (.x, .type = NULL)
## slowly : function (f, rate = rate_delay(), quiet = TRUE)
## some : function (.x, .p, ...)
## splice : function (...)
## tail_while : function (.x, .p, ...)
## transpose : function (.l, .names = NULL)
## update_list : function (.x, ...)
## vec_depth : function (x)
## walk : function (.x, .f, ...)
## walk2 : function (.x, .y, .f, ...)
## when : function (., ...)
## zap : function ()包含的内容太多，所以选择一些重要的function进行介绍
map表示映射，可以在一个或多个列表/向量的每个位置上应用相同函数进行计算。map函数的映射对象只有一个。
map(.x, .f, …) .x: 列表或向量； .f: 映射函数； …: 映射函数的其他参数
# 单个向量map,指定函数参数
1:4 %>%
map(rnorm,mean=1,sd=2)## [[1]]
## [1] -0.5741208
##
## [[2]]
## [1] 0.1116946 1.0608781
##
## [[3]]
## [1] 4.518926 2.606170 2.559288
##
## [[4]]
## [1] -0.3756527 0.5174267 1.1310676 -2.4495747map2函数是map函数的变形，映射对象有两个，需要注意两个列表/向量的长度必须相同。
map2(.x,.y, .f, …) .x: 列表或向量； .y: 列表或向量,与.x等长； .f: 映射函数； …: 映射函数的其他参数
# 两个向量map，使用公式函数
map2(1:3,2:4,~sum(.x,.y))## [[1]]
## [1] 3
##
## [[2]]
## [1] 5
##
## [[3]]
## [1] 7pmap函数是map函数的变形，映射对象为多个，需要注意多个列表/向量的长度必须相同。
pmap(.l, .f, …) .l: 列表向量/列表； .f: 映射函数； …: 映射函数的其他参数
# 多个向量map，使用公式函数
pmap(list(1:3,2:4,3:5),~sum(..1,..2,..3))## [[1]]
## [1] 6
##
## [[2]]
## [1] 9
##
## [[3]]
## [1] 12调用不同的函数 还有一种更复杂的情况：不但传给函数的参数不同，甚至函数本身也是不同的。
f = c("runif", "rnorm", "rpois")
param = list(
list(min = -1, max = 1),
list(sd = 5),
list(lambda = 10)
)为了处理这种情况，我们使用invoke_map()函数：
invoke_map(f, param, n = 5)## [[1]]
## [1] 0.3487803 0.8372930 -0.3171254 0.7508114 0.8994670
##
## [[2]]
## [1] -6.888394 2.939924 7.346825 8.321915 -6.096242
##
## [[3]]
## [1] 15 10 5 10 8第1个参数是一个函数列表或包含函数名称的字符串向量。第2个参数是列表的一个列表，给出了要传给各个函数的不同参数。随后的参数要传给每个函数。
reduce reduce函数表示规约，计算向量中相邻的两个元素，结果再与第三个元素计算，…，最后计算出一个值。
reduce(1:5,paste)## [1] "1 2 3 4 5"reduce函数可以有很多的妙用，比如将一系列data.frame，进行left_join
reduce2函数可以同时对两个向量进行规约计算，注意第二个向量长度需要比第一个向量小1。
# 多个向量reduce
reduce2(1:4,c(1,1,1),function(x,y,z) x+y-z)## [1] 7计算逻辑为第一次：1+2-1=2，第二次2+3-1=4，第三次4+4-1=7。
函数 accumulate() 与 reduce() 作用方式相同，不同之处是：reduce() 只保留最终的结果，而 accumulate() 会保留所有中间结果。例如，
accumulate(1:100, sum) ## [1] 1 3 6 10 15 21 28 36 45 55 66 78 91 105 120
## [16] 136 153 171 190 210 231 253 276 300 325 351 378 406 435 465
## [31] 496 528 561 595 630 666 703 741 780 820 861 903 946 990 1035
## [46] 1081 1128 1176 1225 1275 1326 1378 1431 1485 1540 1596 1653 1711 1770 1830
## [61] 1891 1953 2016 2080 2145 2211 2278 2346 2415 2485 2556 2628 2701 2775 2850
## [76] 2926 3003 3081 3160 3240 3321 3403 3486 3570 3655 3741 3828 3916 4005 4095
## [91] 4186 4278 4371 4465 4560 4656 4753 4851 4950 5050pluck()：同 [[ 提取列表中的元素 keep(): 保留满足条件的元素 dicard(): 删除满足条件的元素 compact(): 删除列表中的空元素 append()：在列表末尾增加元素 flatten(): 摊平列表（只摊平一层）
library(tidyverse)
set.seed(42722)
## Names of the example data frames we'll create
## are df_1 ... df5
df_names <- paste0("df_", 1:5) %>%
set_names()
df_names## df_1 df_2 df_3 df_4 df_5
## "df_1" "df_2" "df_3" "df_4" "df_5"## We'll make the new dfs by sampling from mtcars
base_df <- as_tibble(mtcars, rownames = "model") %>%
select(model, cyl, hp)
base_df## # A tibble: 32 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Mazda RX4 6 110
## 2 Mazda RX4 Wag 6 110
## 3 Datsun 710 4 93
## 4 Hornet 4 Drive 6 110
## 5 Hornet Sportabout 8 175
## 6 Valiant 6 105
## 7 Duster 360 8 245
## 8 Merc 240D 4 62
## 9 Merc 230 4 95
## 10 Merc 280 6 123
## # … with 22 more rows## Create 5 new data frame objects in our environment.
## Each is a sample of ten rows of three columns from mtcars
df_names %>%
walk(~ assign(x = .x, # each element of df_names in turn
value = sample_n(base_df, 10),
envir = .GlobalEnv))
## Now we have, e.g.
df_1## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Chrysler Imperial 8 230
## 2 Mazda RX4 Wag 6 110
## 3 Merc 450SE 8 180
## 4 Porsche 914-2 4 91
## 5 Toyota Corona 4 97
## 6 Ford Pantera L 8 264
## 7 Toyota Corolla 4 65
## 8 Merc 280C 6 123
## 9 Duster 360 8 245
## 10 Merc 230 4 95df_2## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Toyota Corolla 4 65
## 2 Pontiac Firebird 8 175
## 3 Merc 280 6 123
## 4 Merc 450SE 8 180
## 5 Toyota Corona 4 97
## 6 Lincoln Continental 8 215
## 7 Ferrari Dino 6 175
## 8 Merc 450SLC 8 180
## 9 Dodge Challenger 8 150
## 10 Lotus Europa 4 113df_names## df_1 df_2 df_3 df_4 df_5
## "df_1" "df_2" "df_3" "df_4" "df_5"df_list <- map(df_names, get)
df_list## $df_1
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Chrysler Imperial 8 230
## 2 Mazda RX4 Wag 6 110
## 3 Merc 450SE 8 180
## 4 Porsche 914-2 4 91
## 5 Toyota Corona 4 97
## 6 Ford Pantera L 8 264
## 7 Toyota Corolla 4 65
## 8 Merc 280C 6 123
## 9 Duster 360 8 245
## 10 Merc 230 4 95
##
## $df_2
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Toyota Corolla 4 65
## 2 Pontiac Firebird 8 175
## 3 Merc 280 6 123
## 4 Merc 450SE 8 180
## 5 Toyota Corona 4 97
## 6 Lincoln Continental 8 215
## 7 Ferrari Dino 6 175
## 8 Merc 450SLC 8 180
## 9 Dodge Challenger 8 150
## 10 Lotus Europa 4 113
##
## $df_3
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Fiat 128 4 66
## 2 Hornet 4 Drive 6 110
## 3 Fiat X1-9 4 66
## 4 Hornet Sportabout 8 175
## 5 Maserati Bora 8 335
## 6 Merc 230 4 95
## 7 Valiant 6 105
## 8 Mazda RX4 Wag 6 110
## 9 Toyota Corona 4 97
## 10 Cadillac Fleetwood 8 205
##
## $df_4
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Fiat X1-9 4 66
## 2 AMC Javelin 8 150
## 3 Chrysler Imperial 8 230
## 4 Valiant 6 105
## 5 Hornet Sportabout 8 175
## 6 Merc 240D 4 62
## 7 Merc 280 6 123
## 8 Mazda RX4 Wag 6 110
## 9 Lotus Europa 4 113
## 10 Hornet 4 Drive 6 110
##
## $df_5
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Chrysler Imperial 8 230
## 2 Porsche 914-2 4 91
## 3 Camaro Z28 8 245
## 4 Merc 450SL 8 180
## 5 Toyota Corona 4 97
## 6 Hornet 4 Drive 6 110
## 7 Cadillac Fleetwood 8 205
## 8 Merc 280C 6 123
## 9 Toyota Corolla 4 65
## 10 Pontiac Firebird 8 175split_list <- df_list %>%
map(~ mutate(.,
over_under = if_else(.$cyl > 5, "over", "under"))) %>%
map(~ split(., as.factor(.$over_under)))
split_list## $df_1
## $df_1$over
## # A tibble: 6 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Mazda RX4 Wag 6 110 over
## 3 Merc 450SE 8 180 over
## 4 Ford Pantera L 8 264 over
## 5 Merc 280C 6 123 over
## 6 Duster 360 8 245 over
##
## $df_1$under
## # A tibble: 4 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Porsche 914-2 4 91 under
## 2 Toyota Corona 4 97 under
## 3 Toyota Corolla 4 65 under
## 4 Merc 230 4 95 under
##
##
## $df_2
## $df_2$over
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Pontiac Firebird 8 175 over
## 2 Merc 280 6 123 over
## 3 Merc 450SE 8 180 over
## 4 Lincoln Continental 8 215 over
## 5 Ferrari Dino 6 175 over
## 6 Merc 450SLC 8 180 over
## 7 Dodge Challenger 8 150 over
##
## $df_2$under
## # A tibble: 3 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Toyota Corolla 4 65 under
## 2 Toyota Corona 4 97 under
## 3 Lotus Europa 4 113 under
##
##
## $df_3
## $df_3$over
## # A tibble: 6 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Hornet 4 Drive 6 110 over
## 2 Hornet Sportabout 8 175 over
## 3 Maserati Bora 8 335 over
## 4 Valiant 6 105 over
## 5 Mazda RX4 Wag 6 110 over
## 6 Cadillac Fleetwood 8 205 over
##
## $df_3$under
## # A tibble: 4 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Fiat 128 4 66 under
## 2 Fiat X1-9 4 66 under
## 3 Merc 230 4 95 under
## 4 Toyota Corona 4 97 under
##
##
## $df_4
## $df_4$over
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 AMC Javelin 8 150 over
## 2 Chrysler Imperial 8 230 over
## 3 Valiant 6 105 over
## 4 Hornet Sportabout 8 175 over
## 5 Merc 280 6 123 over
## 6 Mazda RX4 Wag 6 110 over
## 7 Hornet 4 Drive 6 110 over
##
## $df_4$under
## # A tibble: 3 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Fiat X1-9 4 66 under
## 2 Merc 240D 4 62 under
## 3 Lotus Europa 4 113 under
##
##
## $df_5
## $df_5$over
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Camaro Z28 8 245 over
## 3 Merc 450SL 8 180 over
## 4 Hornet 4 Drive 6 110 over
## 5 Cadillac Fleetwood 8 205 over
## 6 Merc 280C 6 123 over
## 7 Pontiac Firebird 8 175 over
##
## $df_5$under
## # A tibble: 3 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Porsche 914-2 4 91 under
## 2 Toyota Corona 4 97 under
## 3 Toyota Corolla 4 65 underdf_list %>%
map(~ mutate(.,
over_under = if_else(.$cyl > 5, "over", "under")))## $df_1
## # A tibble: 10 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Mazda RX4 Wag 6 110 over
## 3 Merc 450SE 8 180 over
## 4 Porsche 914-2 4 91 under
## 5 Toyota Corona 4 97 under
## 6 Ford Pantera L 8 264 over
## 7 Toyota Corolla 4 65 under
## 8 Merc 280C 6 123 over
## 9 Duster 360 8 245 over
## 10 Merc 230 4 95 under
##
## $df_2
## # A tibble: 10 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Toyota Corolla 4 65 under
## 2 Pontiac Firebird 8 175 over
## 3 Merc 280 6 123 over
## 4 Merc 450SE 8 180 over
## 5 Toyota Corona 4 97 under
## 6 Lincoln Continental 8 215 over
## 7 Ferrari Dino 6 175 over
## 8 Merc 450SLC 8 180 over
## 9 Dodge Challenger 8 150 over
## 10 Lotus Europa 4 113 under
##
## $df_3
## # A tibble: 10 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Fiat 128 4 66 under
## 2 Hornet 4 Drive 6 110 over
## 3 Fiat X1-9 4 66 under
## 4 Hornet Sportabout 8 175 over
## 5 Maserati Bora 8 335 over
## 6 Merc 230 4 95 under
## 7 Valiant 6 105 over
## 8 Mazda RX4 Wag 6 110 over
## 9 Toyota Corona 4 97 under
## 10 Cadillac Fleetwood 8 205 over
##
## $df_4
## # A tibble: 10 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Fiat X1-9 4 66 under
## 2 AMC Javelin 8 150 over
## 3 Chrysler Imperial 8 230 over
## 4 Valiant 6 105 over
## 5 Hornet Sportabout 8 175 over
## 6 Merc 240D 4 62 under
## 7 Merc 280 6 123 over
## 8 Mazda RX4 Wag 6 110 over
## 9 Lotus Europa 4 113 under
## 10 Hornet 4 Drive 6 110 over
##
## $df_5
## # A tibble: 10 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Porsche 914-2 4 91 under
## 3 Camaro Z28 8 245 over
## 4 Merc 450SL 8 180 over
## 5 Toyota Corona 4 97 under
## 6 Hornet 4 Drive 6 110 over
## 7 Cadillac Fleetwood 8 205 over
## 8 Merc 280C 6 123 over
## 9 Toyota Corolla 4 65 under
## 10 Pontiac Firebird 8 175 overThe . inside the mutate() and split() functions are pronouns standing for “the thing we’re referring to/computing on right now”. In this case, that’s “the current data frame as we iterate through df_list”. Now we have a nested list. Each of df_1 to df_5 is split into an over or under table. The whole thing looks like this:
split_list %>%
map("over") %>% # subset to "over" dfs only
set_names(nm = ~ paste0(.x, "_over")) %>% # name each element, add the _over suffix
walk2(.x = names(.), # # write out each df with its name
.y = .,
.f = ~ assign(x = .x,
value = as_tibble(.y),
envir = .GlobalEnv))
split_list## $df_1
## $df_1$over
## # A tibble: 6 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Mazda RX4 Wag 6 110 over
## 3 Merc 450SE 8 180 over
## 4 Ford Pantera L 8 264 over
## 5 Merc 280C 6 123 over
## 6 Duster 360 8 245 over
##
## $df_1$under
## # A tibble: 4 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Porsche 914-2 4 91 under
## 2 Toyota Corona 4 97 under
## 3 Toyota Corolla 4 65 under
## 4 Merc 230 4 95 under
##
##
## $df_2
## $df_2$over
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Pontiac Firebird 8 175 over
## 2 Merc 280 6 123 over
## 3 Merc 450SE 8 180 over
## 4 Lincoln Continental 8 215 over
## 5 Ferrari Dino 6 175 over
## 6 Merc 450SLC 8 180 over
## 7 Dodge Challenger 8 150 over
##
## $df_2$under
## # A tibble: 3 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Toyota Corolla 4 65 under
## 2 Toyota Corona 4 97 under
## 3 Lotus Europa 4 113 under
##
##
## $df_3
## $df_3$over
## # A tibble: 6 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Hornet 4 Drive 6 110 over
## 2 Hornet Sportabout 8 175 over
## 3 Maserati Bora 8 335 over
## 4 Valiant 6 105 over
## 5 Mazda RX4 Wag 6 110 over
## 6 Cadillac Fleetwood 8 205 over
##
## $df_3$under
## # A tibble: 4 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Fiat 128 4 66 under
## 2 Fiat X1-9 4 66 under
## 3 Merc 230 4 95 under
## 4 Toyota Corona 4 97 under
##
##
## $df_4
## $df_4$over
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 AMC Javelin 8 150 over
## 2 Chrysler Imperial 8 230 over
## 3 Valiant 6 105 over
## 4 Hornet Sportabout 8 175 over
## 5 Merc 280 6 123 over
## 6 Mazda RX4 Wag 6 110 over
## 7 Hornet 4 Drive 6 110 over
##
## $df_4$under
## # A tibble: 3 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Fiat X1-9 4 66 under
## 2 Merc 240D 4 62 under
## 3 Lotus Europa 4 113 under
##
##
## $df_5
## $df_5$over
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Camaro Z28 8 245 over
## 3 Merc 450SL 8 180 over
## 4 Hornet 4 Drive 6 110 over
## 5 Cadillac Fleetwood 8 205 over
## 6 Merc 280C 6 123 over
## 7 Pontiac Firebird 8 175 over
##
## $df_5$under
## # A tibble: 3 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Porsche 914-2 4 91 under
## 2 Toyota Corona 4 97 under
## 3 Toyota Corolla 4 65 underlapply(split_list, `[[`, "over")## $df_1
## # A tibble: 6 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Mazda RX4 Wag 6 110 over
## 3 Merc 450SE 8 180 over
## 4 Ford Pantera L 8 264 over
## 5 Merc 280C 6 123 over
## 6 Duster 360 8 245 over
##
## $df_2
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Pontiac Firebird 8 175 over
## 2 Merc 280 6 123 over
## 3 Merc 450SE 8 180 over
## 4 Lincoln Continental 8 215 over
## 5 Ferrari Dino 6 175 over
## 6 Merc 450SLC 8 180 over
## 7 Dodge Challenger 8 150 over
##
## $df_3
## # A tibble: 6 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Hornet 4 Drive 6 110 over
## 2 Hornet Sportabout 8 175 over
## 3 Maserati Bora 8 335 over
## 4 Valiant 6 105 over
## 5 Mazda RX4 Wag 6 110 over
## 6 Cadillac Fleetwood 8 205 over
##
## $df_4
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 AMC Javelin 8 150 over
## 2 Chrysler Imperial 8 230 over
## 3 Valiant 6 105 over
## 4 Hornet Sportabout 8 175 over
## 5 Merc 280 6 123 over
## 6 Mazda RX4 Wag 6 110 over
## 7 Hornet 4 Drive 6 110 over
##
## $df_5
## # A tibble: 7 x 4
## model cyl hp over_under
## <chr> <dbl> <dbl> <chr>
## 1 Chrysler Imperial 8 230 over
## 2 Camaro Z28 8 245 over
## 3 Merc 450SL 8 180 over
## 4 Hornet 4 Drive 6 110 over
## 5 Cadillac Fleetwood 8 205 over
## 6 Merc 280C 6 123 over
## 7 Pontiac Firebird 8 175 overdf_list## $df_1
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Chrysler Imperial 8 230
## 2 Mazda RX4 Wag 6 110
## 3 Merc 450SE 8 180
## 4 Porsche 914-2 4 91
## 5 Toyota Corona 4 97
## 6 Ford Pantera L 8 264
## 7 Toyota Corolla 4 65
## 8 Merc 280C 6 123
## 9 Duster 360 8 245
## 10 Merc 230 4 95
##
## $df_2
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Toyota Corolla 4 65
## 2 Pontiac Firebird 8 175
## 3 Merc 280 6 123
## 4 Merc 450SE 8 180
## 5 Toyota Corona 4 97
## 6 Lincoln Continental 8 215
## 7 Ferrari Dino 6 175
## 8 Merc 450SLC 8 180
## 9 Dodge Challenger 8 150
## 10 Lotus Europa 4 113
##
## $df_3
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Fiat 128 4 66
## 2 Hornet 4 Drive 6 110
## 3 Fiat X1-9 4 66
## 4 Hornet Sportabout 8 175
## 5 Maserati Bora 8 335
## 6 Merc 230 4 95
## 7 Valiant 6 105
## 8 Mazda RX4 Wag 6 110
## 9 Toyota Corona 4 97
## 10 Cadillac Fleetwood 8 205
##
## $df_4
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Fiat X1-9 4 66
## 2 AMC Javelin 8 150
## 3 Chrysler Imperial 8 230
## 4 Valiant 6 105
## 5 Hornet Sportabout 8 175
## 6 Merc 240D 4 62
## 7 Merc 280 6 123
## 8 Mazda RX4 Wag 6 110
## 9 Lotus Europa 4 113
## 10 Hornet 4 Drive 6 110
##
## $df_5
## # A tibble: 10 x 3
## model cyl hp
## <chr> <dbl> <dbl>
## 1 Chrysler Imperial 8 230
## 2 Porsche 914-2 4 91
## 3 Camaro Z28 8 245
## 4 Merc 450SL 8 180
## 5 Toyota Corona 4 97
## 6 Hornet 4 Drive 6 110
## 7 Cadillac Fleetwood 8 205
## 8 Merc 280C 6 123
## 9 Toyota Corolla 4 65
## 10 Pontiac Firebird 8 175df_all <- bind_rows(df_list, .id = "id")
df_all## # A tibble: 50 x 4
## id model cyl hp
## <chr> <chr> <dbl> <dbl>
## 1 df_1 Chrysler Imperial 8 230
## 2 df_1 Mazda RX4 Wag 6 110
## 3 df_1 Merc 450SE 8 180
## 4 df_1 Porsche 914-2 4 91
## 5 df_1 Toyota Corona 4 97
## 6 df_1 Ford Pantera L 8 264
## 7 df_1 Toyota Corolla 4 65
## 8 df_1 Merc 280C 6 123
## 9 df_1 Duster 360 8 245
## 10 df_1 Merc 230 4 95
## # … with 40 more rows最后一次修改于 2022-05-17