一些tidyverse函数返回数据帧，但也有一些返回tibble。我找不到任何关于哪些函数返回哪种数据类型的资源，也看不到任何真正可预测的模式
library(tidyverse)
# Returns dataframe
df1 <- iris %>% mutate(newcol = mean(Sepal.Length))
df2 <- iris %>% filter(Sepal.Length > 5)
df3 <- iris %>% select(Sepal.Length, Species)
class(df1); class(df2); class(df3)
[1] "data.frame"
[1] "data.frame"
[1] "data.frame"
# Returns tibble
df4 <- iris %>% add_count(Species)
df5 <- iris %>% pivot_longer(cols = -Species)
df6 <- iris %>% group_by(Species) %>% mutate(newcol = mean(Sepal.Length))
class(df4); class(df5); class(df6)
[1] "tbl_df" "tbl" "data.frame"
[1] "tbl_df" "tbl" "data.frame"
[1] "grouped_df" "tbl_df" "tbl" "data.frame"
有没有办法告诉函数的返回值类型是什么？或者可能有一个资源，哪些函数返回tidyverse中的哪种数据类型？许多R代码在tibble和数据帧上运行相同，但有一些重要的区别，例如提取列的默认行为，其中drop = FALSE是tibble的默认行为。我知道我总是可以手动更改类型，但当处理大量遗留代码时，了解会非常有用
我用伪参数调用了这些tidyverse函数中的每一个，以找到生成的类。
lst(
"dplyr::filter"=dplyr::filter(iris, T) %>% class(),
"dplyr::filter_all"=dplyr::filter_all(mtcars, all_vars(. > 1)) %>% class(),
"dplyr::group_by"=dplyr::group_by(iris, Species) %>% class(),
"dplyr::group_by_all"=dplyr::group_by_all(iris, function(...) TRUE) %>% class(),
"dplyr::group_keys"=dplyr::group_keys(iris) %>% class(),
"dplyr::group_modify"=dplyr::group_modify(iris, function(x, ...) identity(x)) %>% class(),
"dplyr::mutate"=dplyr::mutate(iris) %>% class(),
"dplyr::mutate_all"=dplyr::mutate_all(iris, identity) %>% class(),
"dplyr::rowwise"=dplyr::rowwise(iris) %>% class(),
"dplyr::select"=dplyr::select(iris) %>% class(),
"dplyr::select_all"=dplyr::select_all(iris) %>% class(),
"dplyr::slice"=dplyr::slice(iris) %>% class(),
"dplyr::summarise"=dplyr::summarise(iris) %>% class(),
"dplyr::summarise_all"=dplyr::summarise_all(iris, ~.) %>% class(),
"modelr::add_predictions"=modelr::add_predictions(mtcars, lm(cyl~hp, data = mtcars)) %>% class(),
"modelr::add_residuals"=modelr::add_residuals(mtcars, lm(cyl~hp, data = mtcars)) %>% class(),
"modelr::bootstrap"=modelr::bootstrap(mtcars, 1) %>% class(),
"modelr::crossv_mc"=modelr::crossv_mc(iris, 1) %>% class(),
"modelr::data_grid"=modelr::data_grid(mtcars, vs, am) %>% class(),
"modelr::model_matrix"=modelr::model_matrix(mtcars, am ~ disp) %>% class(),
"modelr::permute"=modelr::permute(iris, 1) %>% class(),
"tibble::add_column"=tibble::add_column(iris) %>% class(),
"tibble::add_row"=tibble::add_row(iris) %>% class(),
"tidyr::complete"=tidyr::complete(iris) %>% class(),
"tidyr::drop_na"=tidyr::drop_na(iris) %>% class(),
"tidyr::expand"=tidyr::expand(iris) %>% class(),
"tidyr::extract"=tidyr::extract(data.frame(x = c(NA, "a-b", "a-d", "b-c", "d-e")), x, "A") %>% class(),
"tidyr::fill"=tidyr::fill(iris) %>% class(),
"tidyr::gather"=tidyr::gather(iris) %>% class(),
"tidyr::nest"=tidyr::nest(iris) %>% class(),
"tidyr::replace_na"=tidyr::replace_na(iris) %>% class(),
"tidyr::separate"=tidyr::separate(data.frame(x = c(NA, "a.b", "a.d", "b.c")), x, c("A", "B")) %>% class(),
"tidyr::separate_rows"=tidyr::separate_rows(iris) %>% class(),
"tidyr::spread"=tidyr::spread(data.frame(x = c("a", "b"), y = c(3, 4), z = c(5, 6)), x, y) %>% class(),
"tidyr::uncount"=tidyr::uncount(data.frame(x = c("a", "b"), n = c(1, 2)), n) %>% class(),
"tidyr::unite"=tidyr::unite(iris, "z", 1:2) %>% class(),
"tidyr::unnest"=tidyr::unnest(iris) %>% class()
) %>%
enframe() %>%
mutate(value = map_chr(value, max)) %>%
data.frame()
#> name value
#> 1 dplyr::filter data.frame
#> 2 dplyr::filter_all data.frame
#> 3 dplyr::group_by tbl_df
#> 4 dplyr::group_by_all tbl_df
#> 5 dplyr::group_keys data.frame
#> 6 dplyr::group_modify data.frame
#> 7 dplyr::mutate data.frame
#> 8 dplyr::mutate_all data.frame
#> 9 dplyr::rowwise tbl_df
#> 10 dplyr::select data.frame
#> 11 dplyr::select_all data.frame
#> 12 dplyr::slice data.frame
#> 13 dplyr::summarise data.frame
#> 14 dplyr::summarise_all data.frame
#> 15 modelr::add_predictions data.frame
#> 16 modelr::add_residuals data.frame
#> 17 modelr::bootstrap tbl_df
#> 18 modelr::crossv_mc tbl_df
#> 19 modelr::data_grid tbl_df
#> 20 modelr::model_matrix tbl_df
#> 21 modelr::permute tbl_df
#> 22 tibble::add_column data.frame
#> 23 tibble::add_row data.frame
#> 24 tidyr::complete data.frame
#> 25 tidyr::drop_na data.frame
#> 26 tidyr::expand tbl_df
#> 27 tidyr::extract data.frame
#> 28 tidyr::fill data.frame
#> 29 tidyr::gather data.frame
#> 30 tidyr::nest tbl_df
#> 31 tidyr::replace_na data.frame
#> 32 tidyr::separate data.frame
#> 33 tidyr::separate_rows tbl_df
#> 34 tidyr::spread data.frame
#> 35 tidyr::uncount data.frame
#> 36 tidyr::unite data.frame
#> 37 tidyr::unnest tbl_df
通过查找第一个自变量为".data"、".tbl"或"data"的tidyverse函数来识别候选函数。
df <-
collidr::CRANdf %>%
filter(package_names %in% tidyverse::tidyverse_packages()) %>%
mutate(f = map2(function_names, package_names, possibly(getFromNamespace, otherwise = NA))) %>%
filter(map_lgl(f, is_function), !map_lgl(f, rlang::is_primitive)) %>%
mutate(first_arg = map(f, ~rlang::fn_fmls(.) %>% names() %>% first())) %>%
filter(first_arg %in% c(".data", ".tbl", "data")) %>%
select(package_names, function_names, first_arg)
df
#> package_names function_names first_arg
#> 1 cli tree data
#> 2 dbplyr arrange.tbl_lazy .data
#> 3 dbplyr do.tbl_sql .data
#> 4 dbplyr window_order .data
#> 5 dplyr arrange .data
#> 6 dplyr arrange_all .tbl
#> 7 dplyr distinct .data
#> 8 dplyr distinct_all .tbl
#> 9 dplyr do .data
#> 10 dplyr filter .data
#> 11 dplyr filter_all .tbl
#> 12 dplyr group_by .data
#> 13 dplyr group_by_all .tbl
#> 14 dplyr group_keys .tbl
#> 15 dplyr group_map .data
#> 16 dplyr group_rows .data
#> 17 dplyr group_trim .tbl
#> 18 dplyr mutate .data
#> 19 dplyr mutate_all .tbl
#> 20 dplyr pull .data
#> 21 dplyr rowwise data
#> 22 dplyr select .data
#> 23 dplyr select_all .tbl
#> 24 dplyr slice .data
#> 25 dplyr summarise .data
#> 26 dplyr summarise_all .tbl
#> 27 ggplot2 ggplot data
#> 28 modelr add_predictions data
#> 29 modelr add_residuals data
#> 30 modelr bootstrap data
#> 31 modelr crossv_mc data
#> 32 modelr data_grid data
#> 33 modelr fit_with data
#> 34 modelr model_matrix data
#> 35 modelr permute data
#> 36 modelr resample data
#> 37 modelr resample_bootstrap data
#> 38 modelr resample_partition data
#> 39 modelr resample_permutation data
#> 40 rlang as_data_mask data
#> 41 tibble add_column .data
#> 42 tibble add_row .data
#> 43 tidyr complete data
#> 44 tidyr drop_na data
#> 45 tidyr expand data
#> 46 tidyr extract data
#> 47 tidyr fill data
#> 48 tidyr gather data
#> 49 tidyr nest .data
#> 50 tidyr replace_na data
#> 51 tidyr separate data
#> 52 tidyr separate_rows data
#> 53 tidyr spread data
#> 54 tidyr uncount data
#> 55 tidyr unite data
#> 56 tidyr unnest data