From be23c401ad3bc1b16d1cbd642e12721c46c4c117 Mon Sep 17 00:00:00 2001 From: maurolepore Date: Wed, 20 Jun 2018 18:55:26 -0400 Subject: [PATCH] Improve interface of functions input_to_output --- ...nput_to_output.R => inout_dfs_to_output.R} | 30 +-- R/{files_to_df.R => inout_files_to_df.R} | 38 ++- ...lff_to_output.R => inout_xlff_to_output.R} | 58 ++--- _pkgdown.yml | 19 +- docs/articles/read_df_write.html | 9 +- docs/index.html | 238 ++++++++---------- docs/reference/dfs_to_csv.html | 205 +++++++++++++++ docs/reference/dfs_to_df.html | 222 ++++++++++++++++ docs/reference/files_to_df.html | 226 ++++++++++------- docs/reference/index.html | 32 +-- docs/reference/xlff_to_output.html | 32 +-- docs/reference/xlsheets_to_dfs.html | 211 ++++++++++++++++ docs/sitemap.xml | 6 +- man/dfs_to_csv.Rd | 6 +- man/dfs_to_df.Rd | 12 +- man/files_to_df.Rd | 20 +- man/xlff_to_output.Rd | 32 +-- man/xlsheets_to_dfs.Rd | 2 +- tests/testthat/test-files_to_df.R | 16 -- ...to_output.R => test-inout_dfs_to_output.R} | 31 +-- tests/testthat/test-inout_files_to_df.R | 26 ++ ...o_output.R => test-inout_xlff_to_output.R} | 10 +- tmp.R | 8 +- vignettes/read_df_write.Rmd | 4 +- 24 files changed, 1065 insertions(+), 428 deletions(-) rename R/{input_to_output.R => inout_dfs_to_output.R} (81%) rename R/{files_to_df.R => inout_files_to_df.R} (61%) rename R/{xlff_to_output.R => inout_xlff_to_output.R} (81%) create mode 100644 docs/reference/dfs_to_csv.html create mode 100644 docs/reference/dfs_to_df.html create mode 100644 docs/reference/xlsheets_to_dfs.html delete mode 100644 tests/testthat/test-files_to_df.R rename tests/testthat/{test-input_to_output.R => test-inout_dfs_to_output.R} (57%) create mode 100644 tests/testthat/test-inout_files_to_df.R rename tests/testthat/{test-xlff_to_output.R => test-inout_xlff_to_output.R} (95%) diff --git a/R/input_to_output.R b/R/inout_dfs_to_output.R similarity index 81% rename from R/input_to_output.R rename to R/inout_dfs_to_output.R index 1f7f26c1..501edbec 100644 --- a/R/input_to_output.R +++ b/R/inout_dfs_to_output.R @@ -1,28 +1,3 @@ -#' Read one excel workbook and map each spreadsheet to a dataframe in a list. -#' -#' A useful complement of this function is [dfs_to_csv()]. -#' -#' @param path A path to an excel file. -#' -#' @source Adapted from an article by Jenny Bryan (https://goo.gl/ah8qkX). -#' @return A list of dataframes. -#' -#' @seealso [dfs_to_csv()]. -#' @family functions to handle multiple spreadsheets of an excel workbook. -#' -#' @export -#' @examples -#' xlsheets_to_dfs(tool_example("multiple_sheets.xlsx")) -xlsheets_to_dfs <- function(path) { - # Piping to avoid useless intermediate variables - path %>% - readxl::excel_sheets() %>% - rlang::set_names() %>% - purrr::map(readxl::read_excel, path = path) -} - - - #' Save each dataframe in a list to a different .csv file. #' #' A useful complement of this function is [xlsheets_to_dfs()]. @@ -53,10 +28,7 @@ dfs_to_csv <- function(dfs, dir, prefix = NULL) { } validate_dir(dir = dir, dir_name = "`dir`") - purrr::walk2( - dfs, names(dfs), - dfs_to_csv_, prefix = prefix, dir = dir - ) + purrr::walk2(dfs, names(dfs), dfs_to_csv_, prefix = prefix, dir = dir) } validate_dir <- function(dir, dir_name) { diff --git a/R/files_to_df.R b/R/inout_files_to_df.R similarity index 61% rename from R/files_to_df.R rename to R/inout_files_to_df.R index 74a42ed8..b7469ba5 100644 --- a/R/files_to_df.R +++ b/R/inout_files_to_df.R @@ -1,14 +1,14 @@ -#' Read flat .csv or flat excel files from a directory into dataframes. +#' Read all .csv or flat excel files from a directory into dataframes. #' #' Read all .csv (`csv_*()`), or excel files (`xl_*()`) from a directory into a #' single dataframe (`*_df()`) or a list of dataframes (`*_dfs()`) -- where each #' element of the list is named as the source file. Excel files are treated as #' if they were flat -- meaning that these `xl_*()` functions can read only a #' single sheet (specified via the argument `sheet` passed to -#' [readr::read_excel()] via `...`). For reading multiple all sheets in a single +#' [readxl::read_excel()] via `...`). For reading multiple all sheets in a single #' file see [xlsheets_to_dfs()]. #' -#' @param input_dir String giving the directory containing the excel workbooks +#' @param dir String giving the directory containing the excel workbooks #' to read from. #' @param ... Arguments passed to [readr::read_csv()] (`csv_*()`) or #' [readxl::read_excel()] (`xl_*()`). @@ -26,21 +26,21 @@ #' #' xl_to_df(tool_example("multiple_workbooks")) #' -#' # Pass an argument to `reaxl::read_excel()` via `...` +#' # Pass an argument to `read_excel()` via `...` #' xl_to_dfs(tool_example("multiple_workbooks"), sheet = 2) #' #' csv_to_dfs(tool_example("multiple_csv")) #' #' csv_to_df(tool_example("multiple_csv")) #' -#' # Pass an argument to `readr::read_csv()` via `...` +#' # Pass an argument to `read_csv()` via `...` #' csv_to_dfs(tool_example("multiple_csv"), n_max = 2) #' @name files_to_df NULL files_to_df <- function(.map, .read, ext) { - function(input_dir, ...) { - files <- fs::dir_ls(input_dir, regexp = ext) + function(dir, ...) { + files <- fs::dir_ls(dir, regexp = ext) dfs <- .map(files, .read, ...) rlang::set_names(dfs, fs::path_file(names(dfs))) } @@ -59,3 +59,27 @@ xl_to_df <- files_to_df(purrr::map_df, readxl::read_excel, "xls|xlsx") #' @name files_to_df xl_to_dfs <- files_to_df(purrr::map, readxl::read_excel, "xls|xlsx") + + +#' Read one excel workbook and map each spreadsheet to a dataframe in a list. +#' +#' A useful complement of this function is [dfs_to_csv()]. +#' +#' @param path A path to an excel file. +#' +#' @source Adapted from an article by Jenny Bryan (https://goo.gl/ah8qkX). +#' @return A list of dataframes. +#' +#' @seealso [dfs_to_csv()]. +#' @family functions to handle multiple spreadsheets of an excel workbook. +#' +#' @export +#' @examples +#' xlsheets_to_dfs(tool_example("multiple_sheets.xlsx")) +xlsheets_to_dfs <- function(path) { + # Piping to avoid useless intermediate variables + path %>% + readxl::excel_sheets() %>% + rlang::set_names() %>% + purrr::map(readxl::read_excel, path = path) +} diff --git a/R/xlff_to_output.R b/R/inout_xlff_to_output.R similarity index 81% rename from R/xlff_to_output.R rename to R/inout_xlff_to_output.R index 83620b76..eb2c2b02 100644 --- a/R/xlff_to_output.R +++ b/R/inout_xlff_to_output.R @@ -22,9 +22,9 @@ #' * Drops fake stems. #' * Output a common data structure of your choice. #' -#' @param input_dir String giving the directory containing the excel workbooks +#' @param dir_in String giving the directory containing the excel workbooks #' to read from. -#' @param output_dir String giving the directory where to write .csv files to. +#' @param dir_out String giving the directory where to write .csv files to. #' @param first_census Use `TRUE` if this is your first census. Use `FALSE` #' (default) if this is not your first census but a recensus. #' @@ -45,45 +45,45 @@ #' #' # NOT A FIRST CENSUS #' # Path to the folder I want to read excel files from -#' input_dir <- dirname(tool_example("two_files/new_stem_1.xlsx")) -#' input_dir +#' dir_in <- dirname(tool_example("two_files/new_stem_1.xlsx")) +#' dir_in #' #' # Files I want to read -#' dir(input_dir, pattern = "xlsx") +#' dir(dir_in, pattern = "xlsx") #' #' # Path to the folder I want to write .csv files to -#' output_dir <- tempdir() +#' dir_out <- tempdir() #' #' # Output a csv file -#' xlff_to_csv(input_dir, output_dir) +#' xlff_to_csv(dir_in, dir_out) #' #' # Confirm -#' path_file(dir_ls(output_dir, regexp = "new_stem.*csv$")) +#' path_file(dir_ls(dir_out, regexp = "new_stem.*csv$")) #' #' # Also possible to output excel and a list of dataframe. See next section. #' #' # FIRST CENSUS -#' input_dir <- dirname(tool_example("first_census/census.xlsx")) +#' dir_in <- dirname(tool_example("first_census/census.xlsx")) #' # As a reminder you'll get a warning of missing sheets #' # Output list of dataframes (one per input workbook -- here only one) -#' dfs <- xlff_to_dfs(input_dir, first_census = TRUE) +#' dfs <- xlff_to_dfs(dir_in, first_census = TRUE) #' str(dfs, give.attr = FALSE) #' #' # Output excel -#' xlff_to_xl(input_dir, output_dir, first_census = TRUE) +#' xlff_to_xl(dir_in, dir_out, first_census = TRUE) #' # Read back -#' filename <- path(output_dir, "census.xlsx") +#' filename <- path(dir_out, "census.xlsx") #' out <- read_excel(filename) #' str(out, give.attr = FALSE) #' @name xlff_to_output NULL xlff_to_file <- function(ext, fun_write) { - function(input_dir, output_dir = "./", first_census = FALSE) { - check_output_dir(output_dir = output_dir, print_as = "`output_dir`") - dfs <- xlff_to_dfs(input_dir = input_dir, first_census = first_census) + function(dir_in, dir_out = "./", first_census = FALSE) { + check_dir_out(dir_out = dir_out, print_as = "`dir_out`") + dfs <- xlff_to_dfs(dir_in = dir_in, first_census = first_census) files <- fs::path_ext_remove(names(dfs)) - paths <- fs::path(output_dir, fs::path_ext_set(files, ext)) + paths <- fs::path(dir_out, fs::path_ext_set(files, ext)) purrr::walk2(dfs, paths, fun_write) } } @@ -98,10 +98,10 @@ xlff_to_xl <- xlff_to_file("xlsx", writexl::write_xlsx) #' @export #' @rdname xlff_to_output -xlff_to_dfs <- function(input_dir, first_census = FALSE) { - check_input_dir(input_dir = input_dir, print_as = "`input_dir`") +xlff_to_dfs <- function(dir_in, first_census = FALSE) { + check_dir_in(dir_in = dir_in, print_as = "`dir_in`") out <- purrr::map( - xl_workbooks_to_chr(input_dir), + xl_workbooks_to_chr(dir_in), xlff_to_dfs_, first_census = first_census ) purrr::set_names(out, basename(names(out))) @@ -222,20 +222,20 @@ join_and_date <- function(.x) { dplyr::left_join(date, by = "submission_id") } -check_input_dir <- function(input_dir, print_as) { - stopifnot(is.character(input_dir)) - validate_dir(input_dir, "`input_dir`") - msg <- "`input_dir` must contain at least one excel file." - file_names <- xl_workbooks_to_chr(input_dir) +check_dir_in <- function(dir_in, print_as) { + stopifnot(is.character(dir_in)) + validate_dir(dir_in, "`dir_in`") + msg <- "`dir_in` must contain at least one excel file." + file_names <- xl_workbooks_to_chr(dir_in) if (length(file_names) == 0) { abort(msg) } invisible() } -check_output_dir <- function(output_dir, print_as) { - stopifnot(is.character(output_dir)) - validate_dir(output_dir, "`output_dir`") +check_dir_out <- function(dir_out, print_as) { + stopifnot(is.character(dir_out)) + validate_dir(dir_out, "`dir_out`") invisible() } @@ -252,6 +252,6 @@ validate_dir <- function(dir, dir_name) { } } -xl_workbooks_to_chr <- function(input_dir) { - fs::dir_ls(input_dir, regexp = "\\.xls") +xl_workbooks_to_chr <- function(dir_in) { + fs::dir_ls(dir_in, regexp = "\\.xls") } diff --git a/_pkgdown.yml b/_pkgdown.yml index 34d75e2e..d922b22f 100644 --- a/_pkgdown.yml +++ b/_pkgdown.yml @@ -42,24 +42,23 @@ reference: - type_fgeo - title: Input to output - desc: General (not specificto ForestGEO) + desc: General (not specific to ForestGEO) contents: - - files_to_df - csv_to_df - csv_to_dfs + + - dfs_to_csv + - dfs_to_df + - xl_to_df - xl_to_dfs - - xlff_to_output + - xlsheets_to_dfs + - xlff_to_csv - xlff_to_dfs - xlff_to_xl - - xlsheets_to_dfs - - dfs_to_csv - - ls_join_df - - - title: Pick/drop rows with matching conditions desc: Specific to ForestGEO contents: @@ -80,7 +79,7 @@ reference: - recode_subquad - title: Edit dataframe columns or vectors - desc: General (not specificto ForestGEO) + desc: General (not specific to ForestGEO) contents: - conv_unit_at - conv_unit @@ -104,7 +103,7 @@ reference: - fgeo_habitat - title: For developers - desc: General (not specificto ForestGEO) + desc: General (not specific to ForestGEO) contents: - hide_data_of_class - show_data_of_class diff --git a/docs/articles/read_df_write.html b/docs/articles/read_df_write.html index 4f47c524..c0031a66 100644 --- a/docs/articles/read_df_write.html +++ b/docs/articles/read_df_write.html @@ -108,12 +108,9 @@

2018-06-20

library(writexl)

If you have multiple files in a directory, you may want to combine them all into a single dataframe and export it as a .csv or excel file. Here is how you can do this and a a little more.

Suppose you have these files in a directory:

-
path <- system.file("extdata", "files/01.csv", package = "fgeo.tool")
-files <- path_dir(path)
-files
-#> C:/Users/LeporeM/Documents/R/R-3.5.0/library/fgeo.tool/extdata/files
-dir(files)
-#> [1] "01.csv"  "01.xls"  "02.csv"  "02.xlsx"
+
files <- tool_example("files")
+dir(files)
+#> [1] "01.csv"  "01.xls"  "02.csv"  "02.xlsx"

Let’s read all the .csv files into a single dataframe.

combined <- csv_to_df(files)
 #> Parsed with column specification:
diff --git a/docs/index.html b/docs/index.html
index 11bd2120..632491fa 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -1,57 +1,25 @@
-
 
-
-  
-  
+
+
+
+
 
 
-
 Functions for General Purposes • fgeo.tool
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
-
-
-  
-
-  
+
+
     

-      

-      
+
+

+
 
       
-      
-
-
-

+      

   

-    

-      

-            
-      
-      
-      
-
-    

+    
 
     
     
 
 

-
 Functions for general purposes

-
lifecycle Travis build status Coverage status 

+

+ Functions for general purposes

+
 
The goal of fgeo.tool is to provide functions for general purposes. Many of its functions are used in multiple other fgeo packages so fgeo.tool acts as a central repository of code. In particular, the packages. For general porpose functions with no expternal dependency see fgeo.base.

 

-
Installation

-
# install.packages("remotes")
-remotes::install_github("forestgeo/fgeo.tool")

+

+Installation

+
# install.packages("remotes")
+remotes::install_github("forestgeo/fgeo.tool")

 
For details on how to install packages from GitHub, see this article.

 

 

-
Example

+

+Example

 
Setup.

 
 
Manipulate data.

 
# Mutate a data set
 
 # Determine the status of each tree based on the status of its stems
-df <- add_status_tree(df)
+df <- add_status_tree(df)
 #> Warning: No observation has .status = D, A
 #>   * Detected values: alive, dead
 
 # Filter a data set
 
 # Filter from the head or tail of a variable
-pick_top(df, Tag)
+pick_top(df, Tag)
 #> # A tibble: 4 x 4
 #>   CensusID   Tag Status status_tree
 #>      <dbl> <dbl> <chr>  <chr>      
@@ -187,7 +149,7 @@ 
Example

 #> 2        1     1 dead   A          
 #> 3        2     1 alive  A          
 #> 4        2     1 alive  A
-pick_top(df, Tag, -1)
+pick_top(df, Tag, -1)
 #> # A tibble: 4 x 4
 #>   CensusID   Tag Status status_tree
 #>      <dbl> <dbl> <chr>  <chr>      
@@ -196,7 +158,7 @@ 
Example

 #> 3        2     3 dead   A          
 #> 4        2     3 dead   A
 # Remove trees found dead in two or more censuses
-drop_twice_dead(df)
+drop_twice_dead(df)
 #> # A tibble: 12 x 4
 #>    CensusID   Tag Status status_tree
 #>       <dbl> <dbl> <chr>  <chr>      
@@ -216,19 +178,19 @@ 
Example

 
 
You can combine fgeo.tool with dplyr.

-
edited <- add_status_tree(pick_top(df, CensusID, -1))
+
 
 

-
Acknowledgements

+

+Acknowledgements

 
Thanks to all partners of ForestGEO, for sharing their ideas and code.

 

 

   

 
   
 
   
 
diff --git a/docs/reference/dfs_to_csv.html b/docs/reference/dfs_to_csv.html
new file mode 100644
index 00000000..d5732a10
--- /dev/null
+++ b/docs/reference/dfs_to_csv.html
@@ -0,0 +1,205 @@
+
+
+
+  
+  
+
+
+
+Save each dataframe in a list to a different .csv file. — dfs_to_csv • fgeo.tool
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  
+
+  
+    

+      

+      
+
+      
+      

+
+

+  

+    

+    
Save each dataframe in a list to a different .csv file.

+    Source: R/inout_dfs_to_output.R
+    
+    

+
+    

+    
+    
A useful complement of this function is xlsheets_to_dfs().

+    
+    

+
+    
dfs_to_csv(dfs, dir, prefix = NULL)

+    
+    
Arguments

+    
+    
+    
+      
+      
+    
+    
+      
+      
+    
+    
+      
+      
+    
+    
dfs
A list of dataframes.
dir
Character; the directory where the files will be saved.
prefix
Character; a prefix to add to the file names.

+    
+    
Source

+
+    
Adapted from an article by Jenny Bryan (https://goo.gl/ah8qkX).

+    
+    
See also

+
+    
xlsheets_to_dfs

+
Other functions to handle multiple spreadsheets of an excel workbook.: xlsheets_to_dfs

+    
+
+    
Examples

+    
dfs <- xlsheets_to_dfs(tool_example("multiple_sheets.xlsx"))
+
+# Saving the output to a temporary file
+output <- tempdir()
+dfs_to_csv(dfs, output, prefix = "myfile-")
+
+# Look inside the output directory to confirm it worked
+dir(output, pattern = "myfile")
#> [1] "myfile-Sheet1.csv" "myfile-Sheet2.csv"

+  

+  
+

+
+      
+   

+
+  
+
+  
+
+
diff --git a/docs/reference/dfs_to_df.html b/docs/reference/dfs_to_df.html
new file mode 100644
index 00000000..a0402bfe
--- /dev/null
+++ b/docs/reference/dfs_to_df.html
@@ -0,0 +1,222 @@
+
+
+
+  
+  
+
+
+
+Reduce a list of dataframes into a single dataframe via dplyr::full_join() — dfs_to_df • fgeo.tool
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  
+
+  
+    

+      

+      
+
+      
+      

+
+

+  

+    

+    
Reduce a list of dataframes into a single dataframe via dplyr::full_join()

+    Source: R/inout_dfs_to_output.R
+    
+    

+
+    

+    
+    
This function wraps purrr::reduce() and dplyr::full_join() to reduce
+all or some dataframes in a list into a single dataframe.

+    
+    

+
+    
dfs_to_df(dfs, df_names = NULL, by = NULL)

+    
+    
Arguments

+    
+    
+    
+      
+      
+    
+    
+      
+      
+    
+    
+      
+      
+    
+    
dfs
A list of dataframes.
df_names
Names of the list elements to join. NULL defaults to use
+all list elements.
by
A character vector of variables to join by. If NULL, the default,
+*_join() will do a natural join, using all variables with common names
+across the two tables. To join by different variables on x and y use a
+named vector. For example, by = c("a" = "b") will match x.a to y.b. Passed
+to dplyr::full_join()

+    
+    
Value

+
+    
A dataframe.

+    
+    
See also

+
+    
purrr::reduce() and dplyr::full_join().

+    
+
+    
Examples

+    
dfs <- list(
+  a = data.frame(x = 1),
+  b = data.frame(x = 2, y = 2),
+  c = data.frame(x = 1, z = 3)
+)
+
+dfs_to_df(dfs, df_names = c("a", "c"))
#>   x z
+#> 1 1 3

+dfs_to_df(dfs, df_names = c("b", "c"))
#>   x  y  z
+#> 1 2  2 NA
+#> 2 1 NA  3

+dfs_to_df(list(data.frame(1)))
#>   X1
+#> 1  1
# Use argument `by` if dataframes have no matching variable,
+dfs_to_df(
+  list(data.frame(x = 1), data.frame(z = 2)),
+  by = c("x" = "z")
+)
#>   x
+#> 1 1
+#> 2 2

+  

+  
+

+
+      
+   

+
+  
+
+  
+
+
diff --git a/docs/reference/files_to_df.html b/docs/reference/files_to_df.html
index 57b59b96..877d35ea 100644
--- a/docs/reference/files_to_df.html
+++ b/docs/reference/files_to_df.html
@@ -6,7 +6,7 @@
 
 
 
-Read all files from a directory into dataframes. — files_to_df • fgeo.tool
+Read all .csv or flat excel files from a directory into dataframes. — files_to_df • fgeo.tool
 
 
 
@@ -30,11 +30,15 @@
 
 
 
-
+
 
-
+
 
 
 
@@ -123,34 +127,43 @@
 

   

     

-    
Read all files from a directory into dataframes.

-    Source: R/files_to_df.R
+    
Read all .csv or flat excel files from a directory into dataframes.

+    Source: R/inout_files_to_df.R
     
     

 
     

     
-    
Read all .csv, .xls, or .xlsx files from a directory into a single dataframe
-or a list of dataframes -- where each element of the list is named as the
-source file.

+    
Read all .csv (csv_*()), or excel files (xl_*()) from a directory into a
+single dataframe (*_df()) or a list of dataframes (*_dfs()) -- where each
+element of the list is named as the source file. Excel files are treated as
+if they were flat -- meaning that these xl_*() functions can read only a
+single sheet (specified via the argument sheet passed to
+readxl::read_excel() via ...). For reading multiple all sheets in a single
+file see xlsheets_to_dfs().

     
     

 
-    
csv_to_df(input_dir)
+    
csv_to_df(dir, ...)
 
-csv_to_dfs(input_dir)
+csv_to_dfs(dir, ...)
 
-xl_to_df(input_dir)
+xl_to_df(dir, ...)
 
-xl_to_dfs(input_dir)

+xl_to_dfs(dir, ...)

     
     
Arguments

     
-      
+      
+    
+    
+      
+      

     
     
input_dirdir
       
String giving the directory containing the excel workbooks
 to read from.
...
Arguments passed to readr::read_csv() (csv_*()) or
+readxl::read_excel() (xl_*()).

     

     

     
@@ -164,93 +177,118 @@ 
See also

+
+    
readr::read_csv(), readxl::read_excel().

+    
 
     
Examples

-    
path <- system.file("extdata", "files/01.csv", package = "fgeo.tool")
-input_dir <- fs::path_dir(path)
-input_dir
#> C:/Users/LeporeM/Dropbox/git_repos/fgeo.tool/inst/extdata/files
dir(input_dir)
#> [1] "01.csv"  "01.xls"  "02.csv"  "02.xlsx"

-# Read all .csv files
-csv_to_df(input_dir)
#> Parsed with column specification:
+    
xl_to_dfs(tool_example("multiple_workbooks"))
#> $workbook1.xlsx
+#> # A tibble: 3 x 2
+#>   numbers letters
+#>     <dbl> <chr>  
+#> 1       1 a      
+#> 2       2 b      
+#> 3       3 c      
+#> 
+#> $workbook2.xlsx
+#> # A tibble: 3 x 2
+#>   numbers letters
+#>     <dbl> <chr>  
+#> 1       1 a      
+#> 2       2 b      
+#> 3       3 c      
+#> 

+xl_to_df(tool_example("multiple_workbooks"))
#> # A tibble: 6 x 2
+#>   numbers letters
+#>     <dbl> <chr>  
+#> 1       1 a      
+#> 2       2 b      
+#> 3       3 c      
+#> 4       1 a      
+#> 5       2 b      
+#> 6       3 c      

+# Pass an argument to `read_excel()` via `...`
+xl_to_dfs(tool_example("multiple_workbooks"), sheet = 2)
#> $workbook1.xlsx
+#> # A tibble: 3 x 2
+#>   colors LETTERS
+#>   <chr>  <chr>  
+#> 1 red    A      
+#> 2 yellow B      
+#> 3 blue   C      
+#> 
+#> $workbook2.xlsx
+#> # A tibble: 3 x 2
+#>   colors LETTERS
+#>   <chr>  <chr>  
+#> 1 red    A      
+#> 2 yellow B      
+#> 3 blue   C      
+#> 

+csv_to_dfs(tool_example("multiple_csv"))
#> Parsed with column specification:
 #> cols(
-#>   x = col_integer(),
-#>   y = col_character()
+#>   numbers = col_integer(),
+#>   letters = col_character()
 #> )
#> Parsed with column specification:
 #> cols(
-#>   x = col_integer(),
-#>   y = col_character()
-#> )
#> # A tibble: 10 x 2
-#>        x y    
-#>    <int> <chr>
-#>  1     1 a    
-#>  2     2 b    
-#>  3     3 c    
-#>  4     4 d    
-#>  5     5 e    
-#>  6     1 k    
-#>  7     2 l    
-#>  8     3 m    
-#>  9     4 n    
-#> 10     5 o    
csv_to_dfs(input_dir)
#> Parsed with column specification:
+#>   numbers = col_integer(),
+#>   letters = col_character()
+#> )
#> $csv1.csv
+#> # A tibble: 3 x 2
+#>   numbers letters
+#>     <int> <chr>  
+#> 1       1 a      
+#> 2       2 b      
+#> 3       3 c      
+#> 
+#> $csv2.csv
+#> # A tibble: 3 x 2
+#>   numbers letters
+#>     <int> <chr>  
+#> 1       4 a      
+#> 2       5 b      
+#> 3       6 c      
+#> 

+csv_to_df(tool_example("multiple_csv"))
#> Parsed with column specification:
 #> cols(
-#>   x = col_integer(),
-#>   y = col_character()
+#>   numbers = col_integer(),
+#>   letters = col_character()
 #> )
#> Parsed with column specification:
 #> cols(
-#>   x = col_integer(),
-#>   y = col_character()
-#> )
#> $`01.csv`
-#> # A tibble: 5 x 2
-#>       x y    
-#>   <int> <chr>
-#> 1     1 a    
-#> 2     2 b    
-#> 3     3 c    
-#> 4     4 d    
-#> 5     5 e    
-#> 
-#> $`02.csv`
-#> # A tibble: 5 x 2
-#>       x y    
-#>   <int> <chr>
-#> 1     1 k    
-#> 2     2 l    
-#> 3     3 m    
-#> 4     4 n    
-#> 5     5 o    
-#> 

-# Read all .xls or .xlsx files
-xl_to_dfs(input_dir)
#> $`01.xls`
-#> # A tibble: 5 x 2
-#>       x y    
-#>   <dbl> <chr>
-#> 1     1 a    
-#> 2     2 b    
-#> 3     3 c    
-#> 4     4 d    
-#> 5     5 e    
+#>   numbers = col_integer(),
+#>   letters = col_character()
+#> )
#> # A tibble: 6 x 2
+#>   numbers letters
+#>     <int> <chr>  
+#> 1       1 a      
+#> 2       2 b      
+#> 3       3 c      
+#> 4       4 a      
+#> 5       5 b      
+#> 6       6 c      

+# Pass an argument to `read_csv()` via `...`
+csv_to_dfs(tool_example("multiple_csv"), n_max = 2)
#> Parsed with column specification:
+#> cols(
+#>   numbers = col_integer(),
+#>   letters = col_character()
+#> )
#> Parsed with column specification:
+#> cols(
+#>   numbers = col_integer(),
+#>   letters = col_character()
+#> )
#> $csv1.csv
+#> # A tibble: 2 x 2
+#>   numbers letters
+#>     <int> <chr>  
+#> 1       1 a      
+#> 2       2 b      
 #> 
-#> $`02.xlsx`
-#> # A tibble: 5 x 2
-#>       x y    
-#>   <dbl> <chr>
-#> 1     1 k    
-#> 2     2 l    
-#> 3     3 m    
-#> 4     4 n    
-#> 5     5 o    
-#> 
xl_to_df(input_dir)
#> # A tibble: 10 x 2
-#>        x y    
-#>    <dbl> <chr>
-#>  1     1 a    
-#>  2     2 b    
-#>  3     3 c    
-#>  4     4 d    
-#>  5     5 e    
-#>  6     1 k    
-#>  7     2 l    
-#>  8     3 m    
-#>  9     4 n    
-#> 10     5 o    

+#> $csv2.csv
+#> # A tibble: 2 x 2
+#>   numbers letters
+#>     <int> <chr>  
+#> 1       4 a      
+#> 2       5 b      
+#> 

   

   
+  
+

+
+      
+   

+
+  
+
+  
+
+
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 97e76bd4..1dfab1a0 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -18,6 +18,9 @@
   
     https://forestgeo.github.io/fgeo.tool//reference/dfs_to_csv.html
   
+  
+    https://forestgeo.github.io/fgeo.tool//reference/dfs_to_df.html
+  
   
     https://forestgeo.github.io/fgeo.tool//reference/drop_twice_dead.html
   
@@ -42,9 +45,6 @@
   
     https://forestgeo.github.io/fgeo.tool//reference/lookup.html
   
-  
-    https://forestgeo.github.io/fgeo.tool//reference/ls_join_df.html
-  
   
     https://forestgeo.github.io/fgeo.tool//reference/nms.html
   
diff --git a/man/dfs_to_csv.Rd b/man/dfs_to_csv.Rd
index cded0da9..39666acd 100644
--- a/man/dfs_to_csv.Rd
+++ b/man/dfs_to_csv.Rd
@@ -1,5 +1,5 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/input_to_output.R
+% Please edit documentation in R/inout_dfs_to_output.R
 \name{dfs_to_csv}
 \alias{dfs_to_csv}
 \title{Save each dataframe in a list to a different .csv file.}
@@ -7,10 +7,10 @@
 Adapted from an article by Jenny Bryan (https://goo.gl/ah8qkX).
 }
 \usage{
-dfs_to_csv(df_list, dir, prefix = NULL)
+dfs_to_csv(dfs, dir, prefix = NULL)
 }
 \arguments{
-\item{df_list}{A list of dataframes.}
+\item{dfs}{A list of dataframes.}
 
 \item{dir}{Character; the directory where the files will be saved.}
 
diff --git a/man/dfs_to_df.Rd b/man/dfs_to_df.Rd
index 586bbd4e..e6bec093 100644
--- a/man/dfs_to_df.Rd
+++ b/man/dfs_to_df.Rd
@@ -1,5 +1,5 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/input_to_output.R
+% Please edit documentation in R/inout_dfs_to_output.R
 \name{dfs_to_df}
 \alias{dfs_to_df}
 \title{Reduce a list of dataframes into a single dataframe via dplyr::full_join()}
@@ -7,6 +7,8 @@
 dfs_to_df(dfs, df_names = NULL, by = NULL)
 }
 \arguments{
+\item{dfs}{A list of dataframes.}
+
 \item{df_names}{Names of the list elements to join. \code{NULL} defaults to use
 all list elements.}
 
@@ -15,8 +17,6 @@ all list elements.}
 across the two tables. To join by different variables on x and y use a
 named vector. For example, by = c("a" = "b") will match x.a to y.b. Passed
 to \code{\link[dplyr:full_join]{dplyr::full_join()}}}
-
-\item{df_list}{A list of dataframes.}
 }
 \value{
 A dataframe.
@@ -26,15 +26,15 @@ This function wraps \code{\link[purrr:reduce]{purrr::reduce()}} and \code{\link[
 all or some dataframes in a list into a single dataframe.
 }
 \examples{
-df_list <- list(
+dfs <- list(
   a = data.frame(x = 1),
   b = data.frame(x = 2, y = 2),
   c = data.frame(x = 1, z = 3)
 )
 
-dfs_to_df(df_list, df_names = c("a", "c"))
+dfs_to_df(dfs, df_names = c("a", "c"))
 
-dfs_to_df(df_list, df_names = c("b", "c"))
+dfs_to_df(dfs, df_names = c("b", "c"))
 
 dfs_to_df(list(data.frame(1)))
 # Use argument `by` if dataframes have no matching variable,
diff --git a/man/files_to_df.Rd b/man/files_to_df.Rd
index 5c10cf69..fe92f70b 100644
--- a/man/files_to_df.Rd
+++ b/man/files_to_df.Rd
@@ -1,23 +1,23 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/files_to_df.R
+% Please edit documentation in R/inout_files_to_df.R
 \name{files_to_df}
 \alias{files_to_df}
 \alias{csv_to_df}
 \alias{csv_to_dfs}
 \alias{xl_to_df}
 \alias{xl_to_dfs}
-\title{Read flat .csv or flat excel files from a directory into dataframes.}
+\title{Read all .csv or flat excel files from a directory into dataframes.}
 \usage{
-csv_to_df(input_dir, ...)
+csv_to_df(dir, ...)
 
-csv_to_dfs(input_dir, ...)
+csv_to_dfs(dir, ...)
 
-xl_to_df(input_dir, ...)
+xl_to_df(dir, ...)
 
-xl_to_dfs(input_dir, ...)
+xl_to_dfs(dir, ...)
 }
 \arguments{
-\item{input_dir}{String giving the directory containing the excel workbooks
+\item{dir}{String giving the directory containing the excel workbooks
 to read from.}
 
 \item{...}{Arguments passed to \code{\link[readr:read_csv]{readr::read_csv()}} (\code{csv_*()}) or
@@ -33,7 +33,7 @@ single dataframe (\code{*_df()}) or a list of dataframes (\code{*_dfs()}) -- whe
 element of the list is named as the source file. Excel files are treated as
 if they were flat -- meaning that these \code{xl_*()} functions can read only a
 single sheet (specified via the argument \code{sheet} passed to
-\code{\link[readr:read_excel]{readr::read_excel()}} via \code{...}). For reading multiple all sheets in a single
+\code{\link[readxl:read_excel]{readxl::read_excel()}} via \code{...}). For reading multiple all sheets in a single
 file see \code{\link[=xlsheets_to_dfs]{xlsheets_to_dfs()}}.
 }
 \section{Acknowledgment}{
@@ -46,14 +46,14 @@ xl_to_dfs(tool_example("multiple_workbooks"))
 
 xl_to_df(tool_example("multiple_workbooks"))
 
-# Pass an argument to `reaxl::read_excel()` via `...`
+# Pass an argument to `read_excel()` via `...`
 xl_to_dfs(tool_example("multiple_workbooks"), sheet = 2)
 
 csv_to_dfs(tool_example("multiple_csv"))
 
 csv_to_df(tool_example("multiple_csv"))
 
-# Pass an argument to `readr::read_csv()` via `...`
+# Pass an argument to `read_csv()` via `...`
 csv_to_dfs(tool_example("multiple_csv"), n_max = 2)
 }
 \seealso{
diff --git a/man/xlff_to_output.Rd b/man/xlff_to_output.Rd
index f5e1e19a..94628b18 100644
--- a/man/xlff_to_output.Rd
+++ b/man/xlff_to_output.Rd
@@ -1,5 +1,5 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/xlff_to_output.R
+% Please edit documentation in R/inout_xlff_to_output.R
 \name{xlff_to_output}
 \alias{xlff_to_output}
 \alias{xlff_to_csv}
@@ -7,17 +7,17 @@
 \alias{xlff_to_dfs}
 \title{Read and wrangle excel-FastField and output dataframes or .csv/.xlsx files.}
 \usage{
-xlff_to_csv(input_dir, output_dir = "./", first_census = FALSE)
+xlff_to_csv(dir_in, dir_out = "./", first_census = FALSE)
 
-xlff_to_xl(input_dir, output_dir = "./", first_census = FALSE)
+xlff_to_xl(dir_in, dir_out = "./", first_census = FALSE)
 
-xlff_to_dfs(input_dir, first_census = FALSE)
+xlff_to_dfs(dir_in, first_census = FALSE)
 }
 \arguments{
-\item{input_dir}{String giving the directory containing the excel workbooks
+\item{dir_in}{String giving the directory containing the excel workbooks
 to read from.}
 
-\item{output_dir}{String giving the directory where to write .csv files to.}
+\item{dir_out}{String giving the directory where to write .csv files to.}
 
 \item{first_census}{Use \code{TRUE} if this is your first census. Use \code{FALSE}
 (default) if this is not your first census but a recensus.}
@@ -70,34 +70,34 @@ library(readxl)
 
 # NOT A FIRST CENSUS
 # Path to the folder I want to read excel files from
-input_dir <- dirname(tool_example("two_files/new_stem_1.xlsx"))
-input_dir
+dir_in <- dirname(tool_example("two_files/new_stem_1.xlsx"))
+dir_in
 
 # Files I want to read
-dir(input_dir, pattern = "xlsx")
+dir(dir_in, pattern = "xlsx")
 
 # Path to the folder I want to write .csv files to
-output_dir <- tempdir()
+dir_out <- tempdir()
 
 # Output a csv file
-xlff_to_csv(input_dir, output_dir)
+xlff_to_csv(dir_in, dir_out)
 
 # Confirm
-path_file(dir_ls(output_dir, regexp = "new_stem.*csv$"))
+path_file(dir_ls(dir_out, regexp = "new_stem.*csv$"))
 
 # Also possible to output excel and a list of dataframe. See next section.
 
 # FIRST CENSUS
-input_dir <- dirname(tool_example("first_census/census.xlsx"))
+dir_in <- dirname(tool_example("first_census/census.xlsx"))
 # As a reminder you'll get a warning of missing sheets
 # Output list of dataframes (one per input workbook -- here only one)
-dfs <- xlff_to_dfs(input_dir, first_census = TRUE)
+dfs <- xlff_to_dfs(dir_in, first_census = TRUE)
 str(dfs, give.attr = FALSE)
 
 # Output excel
-xlff_to_xl(input_dir, output_dir, first_census = TRUE)
+xlff_to_xl(dir_in, dir_out, first_census = TRUE)
 # Read back
-filename <- path(output_dir, "census.xlsx")
+filename <- path(dir_out, "census.xlsx")
 out <- read_excel(filename)
 str(out, give.attr = FALSE)
 }
diff --git a/man/xlsheets_to_dfs.Rd b/man/xlsheets_to_dfs.Rd
index 1d590774..6b544879 100644
--- a/man/xlsheets_to_dfs.Rd
+++ b/man/xlsheets_to_dfs.Rd
@@ -1,5 +1,5 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/input_to_output.R
+% Please edit documentation in R/inout_files_to_df.R
 \name{xlsheets_to_dfs}
 \alias{xlsheets_to_dfs}
 \title{Read one excel workbook and map each spreadsheet to a dataframe in a list.}
diff --git a/tests/testthat/test-files_to_df.R b/tests/testthat/test-files_to_df.R
deleted file mode 100644
index b9adb6d3..00000000
--- a/tests/testthat/test-files_to_df.R
+++ /dev/null
@@ -1,16 +0,0 @@
-context("files_to_df")
-
-library(fs)
-
-test_that("outputs expected object", {
-  path <- system.file("extdata", "files/01.csv", package = "fgeo.tool")
-  input_dir <- path_dir(path)
-  input_dir
-  dir(input_dir)
-
-  expect_is(csv_to_df(input_dir), "data.frame")
-  expect_is(csv_to_dfs(input_dir), "list")
-
-  expect_is(xl_to_df(input_dir), "data.frame")
-  expect_is(xl_to_dfs(input_dir), "list")
-})
diff --git a/tests/testthat/test-input_to_output.R b/tests/testthat/test-inout_dfs_to_output.R
similarity index 57%
rename from tests/testthat/test-input_to_output.R
rename to tests/testthat/test-inout_dfs_to_output.R
index 30b1aa96..a9c21bbb 100644
--- a/tests/testthat/test-input_to_output.R
+++ b/tests/testthat/test-inout_dfs_to_output.R
@@ -1,31 +1,18 @@
-input <- system.file("extdata", "example.xlsx", package = "fgeo.tool")
-
-
-
-context("xlsheets_to_dfs")
-
-x <- xlsheets_to_dfs(input)
-
-test_that("input is a list of data frames", {
-  expect_type(x, "list")
-  expect_true(each_list_item_is_df(x))
-})
-
-
+input <- tool_example("example.xlsx")
 
 context("dfs_to_csv")
 
-df_list <- xlsheets_to_dfs(input)
+dfs <- xlsheets_to_dfs(input)
 output <- tempdir()
 test_that("errs with wrong input", {
   expect_error(dfs_to_csv(1, output))
   expect_error(dfs_to_csv(list(1), output))
-  expect_error(dfs_to_csv(df_list, 1))
-  expect_error(dfs_to_csv(df_list, output, prefix = 1))
+  expect_error(dfs_to_csv(dfs, 1))
+  expect_error(dfs_to_csv(dfs, output, prefix = 1))
 })
 
 test_that("works as expected", {
-  dfs_to_csv(df_list, output, prefix = "myfile-")
+  dfs_to_csv(dfs, output, prefix = "myfile-")
   files <- dir(output)
   expect_true(length(files[grepl("^myfile.*csv$", files)]) > 0)
 })
@@ -34,7 +21,7 @@ test_that("works as expected", {
 
 context("dfs_to_df")
 
-df_list <- list(
+dfs <- list(
   a = data.frame(x = 1),
   b = data.frame(x = 2, y = 2),
   c = data.frame(x = 1, z = 3)
@@ -43,13 +30,13 @@ df_list <- list(
 test_that("errs with wrong input", {
   expect_error(dfs_to_df(1))
   expect_error(dfs_to_df(data.frame(1)))
-  expect_error(dfs_to_df(df_list, 1))
+  expect_error(dfs_to_df(dfs, 1))
 })
 
 test_that("works as expected", {
-  x <- dfs_to_df(df_list, df_names = c("a", "c"))
+  x <- dfs_to_df(dfs, df_names = c("a", "c"))
   expect_equal(names(x), c("x", "z"))
-  x <- dfs_to_df(df_list, df_names = c("b", "c"))
+  x <- dfs_to_df(dfs, df_names = c("b", "c"))
   expect_equal(names(x), c("x", "y", "z"))
   expect_silent(dfs_to_df(list(data.frame(1))))
   expect_silent(
diff --git a/tests/testthat/test-inout_files_to_df.R b/tests/testthat/test-inout_files_to_df.R
new file mode 100644
index 00000000..b34b8fa1
--- /dev/null
+++ b/tests/testthat/test-inout_files_to_df.R
@@ -0,0 +1,26 @@
+input <- tool_example("example.xlsx")
+
+context("xlsheets_to_dfs")
+
+x <- xlsheets_to_dfs(input)
+
+test_that("input is a list of data frames", {
+  expect_type(x, "list")
+  expect_true(each_list_item_is_df(x))
+})
+
+
+
+context("files_to_df")
+
+library(fs)
+
+test_that("outputs expected object", {
+  dir <- tool_example("files")
+
+  expect_is(csv_to_df(dir), "data.frame")
+  expect_is(csv_to_dfs(dir), "list")
+
+  expect_is(xl_to_df(dir), "data.frame")
+  expect_is(xl_to_dfs(dir), "list")
+})
diff --git a/tests/testthat/test-xlff_to_output.R b/tests/testthat/test-inout_xlff_to_output.R
similarity index 95%
rename from tests/testthat/test-xlff_to_output.R
rename to tests/testthat/test-inout_xlff_to_output.R
index 2bcb2301..dd599133 100644
--- a/tests/testthat/test-xlff_to_output.R
+++ b/tests/testthat/test-inout_xlff_to_output.R
@@ -58,7 +58,7 @@ test_that("works as expected", {
 
 context("xlff_to_csv")
 
-test_that("errs if input_dir does not exist", {
+test_that("errs if `dir` does not exist", {
   expect_error(
     xlff_to_csv("invalid_dir"),
     "must match a valid directory"
@@ -166,9 +166,9 @@ test_that("outputs column codes with commas replaced by semicolon (#13)", {
 })
 
 test_that("allows first_census", {
-  input_dir <- dirname(tool_example("first_census/census.xlsx"))
+  `dir` <- dirname(tool_example("first_census/census.xlsx"))
   output_dir <- tempdir()
-  out <- xlff_to_dfs(input_dir, first_census = TRUE)[[1]]
+  out <- xlff_to_dfs(`dir`, first_census = TRUE)[[1]]
 
   nms <- c(
     "submission_id", "quadrat", "tag", "stem_tag", "species", 
@@ -180,9 +180,9 @@ test_that("allows first_census", {
 })
 
 test_that("passes with input missing key sheets (#33)", {
-  input_dir <- dirname(tool_example("missing_key/recensus.xlsx"))
+  `dir` <- dirname(tool_example("missing_key/recensus.xlsx"))
   expect_warning(
-    xlff_to_dfs(input_dir),
+    xlff_to_dfs(`dir`),
     "Adding missing sheets: original_stems, new_secondary_stems, recruits, root"
   )
 })
diff --git a/tmp.R b/tmp.R
index 8fd01e08..7e770092 100644
--- a/tmp.R
+++ b/tmp.R
@@ -2,6 +2,7 @@
 
 # xxx cont here
 # * Replace bci data by luquillo data in map (top1quad by vft_1quad, ...)
+# * Remove internal data functions_priority
 
 # Families ----------------------------------------------------------------
 
@@ -62,18 +63,11 @@ type_vft
 # dependencies. GENERAL -- NOT SPECIFIC TO FGEO -----------------------------
 
 # Read or write
-# TODO: Rename all of these functions to the format input_to_output().
-# Find common suffix?
-# replace _lst by s? e.g. csv_to_df_lst() by csv_to_dfs()
-# replace _ls by _lst? 
 files_to_df
 csv_to_df
 csv_to_dfs
 xl_to_df
 xl_to_dfs
-
-# TODO: consider renaming xl_ to sheets when appropriate
-# TODO: rename to end with output, something like df_to_csv() or dfs_to_csvs()
 dfs_to_csv
 dfs_to_df
 xlsheets_to_dfs
diff --git a/vignettes/read_df_write.Rmd b/vignettes/read_df_write.Rmd
index 66f9c0f4..7e089e47 100644
--- a/vignettes/read_df_write.Rmd
+++ b/vignettes/read_df_write.Rmd
@@ -30,9 +30,7 @@ If you have multiple files in a directory, you may want to combine them all into
 Suppose you have these files in a directory:
 
 ```{r}
-path <- system.file("extdata", "files/01.csv", package = "fgeo.tool")
-files <- path_dir(path)
-files
+files <- tool_example("files")
 dir(files)
 ```