version 0.3.12

cran · Jan 24, 2023 · bb095f8 · bb095f8
1 parent 5eb9931
commit bb095f8
Show file tree

Hide file tree

Showing 24 changed files with 1,039 additions and 591 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: matsindf
 Type: Package
 Title: Matrices in Data Frames
-Version: 0.3.11
-Date: 2022-05-18
+Version: 0.3.12
+Date: 2023-01-24
 Authors@R: c(person("Matthew", "Heun", role = c("aut", "cre"),
                      comment = c(ORCID = "0000-0002-7438-214X"),
                      email = "matthew.heun@me.com"))
@@ -13,16 +13,17 @@ License: MIT + file LICENSE
 Language: en-US
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.2.0
+RoxygenNote: 7.2.3
 Depends: R (>= 2.10)
 Imports: dplyr, magrittr, matsbyname, purrr, rlang, tibble, tidyr
-Suggests: covr, ggplot2, knitr, RCLabels, rmarkdown, spelling, testthat
+Suggests: covr, ggplot2, Hmisc, knitr, RCLabels, rmarkdown, spelling,
+        testthat
 Config/testthat/edition: 3
 VignetteBuilder: knitr
 URL: https://github.com/MatthewHeun/matsindf
 BugReports: https://github.com/MatthewHeun/matsindf/issues
 NeedsCompilation: no
-Packaged: 2022-05-19 12:59:12 UTC; mkh2
+Packaged: 2023-01-25 00:38:27 UTC; mkh2
 Author: Matthew Heun [aut, cre] (<https://orcid.org/0000-0002-7438-214X>)
 Repository: CRAN
-Date/Publication: 2022-05-19 13:20:02 UTC
+Date/Publication: 2023-01-25 00:50:02 UTC
diff --git a/LICENSE b/LICENSE
@@ -1,2 +1,2 @@
-YEAR: 2022
+YEAR: 2023
 COPYRIGHT HOLDER: Matthew Kuperus Heun
diff --git a/MD5 b/MD5
@@ -1,41 +1,43 @@
-e1f8b8a7e300af9d5174cfeb9ca4b08b *DESCRIPTION
-48e44876707d63eece2c5fab64cacc15 *LICENSE
-f5f590c72b11ab746d662a42727417b3 *NAMESPACE
-0081dd30bf93b0d6a542f52957eab2d9 *NEWS.md
+a707ca2714d1f79c4ae0a1d3e502453c *DESCRIPTION
+58a3c955cbbf973ec3fa1898f9e9f182 *LICENSE
+28b9fb61cd668f96027d296d08b07abe *NAMESPACE
+5705756632dc569e404b70a0fda53ff1 *NEWS.md
 07e9619c519a4555d0a4a52136b3a8af *R/collapse.R
-f74acdac92135210d2e51daef4ced235 *R/data.R
-ae790120a1a44da5ecf8edc103431e71 *R/expand.R
-a8e3195897bacb52262d27c79c2a09b8 *R/matsindf_apply.R
-0874367810191d5713392bc88b013e8a *R/utilities.R
+ec2122278b8840558f1d32429d82a142 *R/data.R
+a22f6793a7b7c34108398b3f49594f87 *R/expand.R
+65eebad2f68a8a2f1e8369bddc33b4e1 *R/matsindf_apply.R
+eca78db419b8201f5a376de0a4efaaa2 *R/utilities.R
 e3702e4a4f1c2f263d84afd1e53f185c *R/utils-.data.R
 15355d49503b97b502d614bc1629aefa *R/utils-pipe.R
 f60225411bc1570c427e39238dc2c8c2 *R/utils-qqassign.R
 726ddac0a53e1e024268749c46bfac6b *README.md
-c890661466bd8fa92bb33d2c36151a0b *build/vignette.rds
+ea124a494ad7922985532ad3b308e4d5 *build/partial.rdb
+279b6b78f5c7609ee3fa088380de4a00 *build/vignette.rds
 8e890f45eea6929749a53f5c49db8d80 *data/UKEnergy2000.rda
-06c79f69992005e37714c0c77a442982 *inst/CITATION
+bd8e0c6b229111b7c532d7c207ad6701 *inst/CITATION
 bc4d88a62b30136b4db89d349c3ac396 *inst/WORDLIST
 e68b3aaaf76912751f8dff77ac754326 *inst/doc/iris_pca.R
 7cd37ad63ba95504eccda7762e1ba3aa *inst/doc/iris_pca.Rmd
-b3e634067ec4d2304ad503382402149d *inst/doc/iris_pca.html
+9468b310de57408a302178eb31772e68 *inst/doc/iris_pca.html
 49c938acbb5aa316f8b3d78573af8734 *inst/doc/matsindf.R
 afd9f781834457ab22880f3419c62ae4 *inst/doc/matsindf.Rmd
-77582428f47974e460131ce9f51e4226 *inst/doc/matsindf.html
-8ed0d1531ae5d19e5d96b7c473399420 *inst/doc/midf_apply_primer.R
-ac0b476766474c602d64844285480e37 *inst/doc/midf_apply_primer.Rmd
-67751efc546bde2ef8ee4ae82d84ff8c *inst/doc/midf_apply_primer.html
-e7bd260e3ef68ee779c92ac4ea8b867d *man/UKEnergy2000.Rd
+69176531f72e3dcacc9b52b8ac00555a *inst/doc/matsindf.html
+485fa2e100721d78d02763d5db32d154 *inst/doc/midf_apply_primer.R
+b2e3da673708123eebe738cd4a5fa379 *inst/doc/midf_apply_primer.Rmd
+25a99c7a3649dfa4bd6a012b2f0b0f87 *inst/doc/midf_apply_primer.html
+24627d4f6f4d8d302fa5b0d163cb023c *man/UKEnergy2000.Rd
 9efef69d4592fa064023ef08607fcf94 *man/add_UKEnergy2000_matnames.Rd
 2b3b543bfe8cbc20a65a4b37c6c342c4 *man/add_UKEnergy2000_row_col_meta.Rd
 89b69e680d097b46e2b587de60577eaa *man/collapse_to_matrices.Rd
 32ec27f8d295593fe3d4d72927cf5962 *man/data.Rd
 5824b74cd7d0bd21716c8d2a8aa1193f *man/df_to_msg.Rd
 466f54c2ff4cae8f69997e68ea65dc77 *man/everything_except.Rd
-d48d44a6dc7782e4780ff0eca6d77be6 *man/expand_to_tidy.Rd
+9b02c4132344dd24627411f33e52c0a6 *man/expand_to_tidy.Rd
 b2dd8fc6eb10f8e500a78b6c2069c9ec *man/group_by_everything_except.Rd
 96892d1c7cb1a49f69f3084ef5aa4d40 *man/index_column.Rd
 983d0d1a850b6a90cfba14d0e0c5c31d *man/mat_to_rowcolval.Rd
-2102151a6f5c240da89a880907d3e54b *man/matsindf_apply.Rd
+10fbcac0fcce590c2b95453a75690c33 *man/matrix_cols.Rd
+ea163df2c8746cd6071a8cf4433bd9ba *man/matsindf_apply.Rd
 c5e90a4c39cb6d36ab5f597d3ff8c1b4 *man/matsindf_apply_types.Rd
 6eef5d2f49de0f38fd4bee2a0eadb799 *man/pipe.Rd
 c1f1088e8dc4f7b59661dd74d293beef *man/quasi-quote-assign.Rd
@@ -47,9 +49,9 @@ a9eecca1fd9f4078e4ed9a64830cdf17 *tests/testthat/UKEnergy2000_with_UVY.rds
 fa505a94f1c22afbe56b6fbde33a5d5b *tests/testthat/UKEnergy2000_with_metadata.rds
 e2f5768a703d1cf79cd64400d7850839 *tests/testthat/test-collapse.R
 f1fb327f810b6f5f52729cd2f08101f4 *tests/testthat/test-expand.R
-c79de4cea3122ec5b090a586ccc3fb5f *tests/testthat/test-matsindf_apply.R
-ad710b2e110594a89c34b31974c7b40a *tests/testthat/test-utilities.R
+932f2af864394496841d80f0c773795d *tests/testthat/test-matsindf_apply.R
+0b0568ed52cb53937aad770f28dfed9b *tests/testthat/test-utilities.R
 41d243a4d4106763cb78f7924490c205 *vignettes/References.bib
 7cd37ad63ba95504eccda7762e1ba3aa *vignettes/iris_pca.Rmd
 afd9f781834457ab22880f3419c62ae4 *vignettes/matsindf.Rmd
-ac0b476766474c602d64844285480e37 *vignettes/midf_apply_primer.Rmd
+b2e3da673708123eebe738cd4a5fa379 *vignettes/midf_apply_primer.Rmd
diff --git a/NAMESPACE b/NAMESPACE
@@ -10,6 +10,7 @@ export(expand_to_tidy)
 export(group_by_everything_except)
 export(index_column)
 export(mat_to_rowcolval)
+export(matrix_cols)
 export(matsindf_apply)
 export(matsindf_apply_types)
 export(rowcolval_to_mat)

diff --git a/NEWS.md b/NEWS.md
@@ -4,7 +4,26 @@ output: html_document
 ---
 
 
-# matsindf 0.3.11 (2022-05-18)
+# matsindf 0.3.12 (2023-01-24)
+
+* Fixed a differential error message challenge for tests.
+* Move tests associated with `verify_cols_missing()`
+  from the `Recca` package to `matsindf`.
+  Those tests didn't belong in `Recca`.
+* Updated to the latest version of the github actions
+  continuous integration workflow.
+* Better docs for `expand_to_tidy()`.
+* New function `matrix_cols()` tells which columns contain matrices, 
+  either in the `any()` sense or in the `all()` sense.
+* Improved `matsindf_apply()` primer vignette
+  discusses how to handle heterogeneous arguments
+  types to `FUN`.
+* New tests to verify `matsindf_apply()` when using string arguments to `FUN`.
+    * Now at 209 tests, all passing.
+    * Test coverage remains at 100 %.
+
+
+# matsindf 0.3.11 (2022-05-18) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6564300.svg)](https://doi.org/10.5281/zenodo.6564300)
 
 * Fixed a very subtle bug in `matsindf_apply()` where the list returned from `Map()`
   had names on each individual item.
@@ -15,9 +34,12 @@ output: html_document
   The solution was to remove the names from each individual item
   after calling `Map()` and
   before calling `purrr::transpose()`.
+* No new tests.
+    * Still at 195 tests, all passing.
+    * Test coverage remains at 100 %.
 
 
-# matsindf 0.3.10 (2020-12-17) [![DOI](https://zenodo.org/badge/112986384.svg)](https://zenodo.org/badge/latestdoi/112986384)
+# matsindf 0.3.10 (2021-12-17) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5789218.svg)](https://doi.org/10.5281/zenodo.5789218)
 
 * New vignette from Alexander Davis shows how to use `matsindf` 
   for principal components analysis (PCA).
@@ -33,7 +55,7 @@ output: html_document
     * Test coverage remains at 100 %.
 
 
-# matsindf 0.3.9 (2020-10-02) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5546359.svg)](https://doi.org/10.5281/zenodo.5546359)
+# matsindf 0.3.9 (2021-10-02) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5546359.svg)](https://doi.org/10.5281/zenodo.5546359)
 
 * New function `df_to_msg()` can assist with error messages.
   `df_to_msg()` was moved from the `SEAPSUTWorkflow` package, 
@@ -43,7 +65,7 @@ output: html_document
     * Test coverage remains at 100 %.
 
 
-# matsindf 0.3.8 (2020-09-02) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5475444.svg)](https://doi.org/10.5281/zenodo.5475444)
+# matsindf 0.3.8 (2021-09-02) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5475444.svg)](https://doi.org/10.5281/zenodo.5475444)
 
 * `matsindf.Rmd` vignette now uses the `keep` argument on `matsbyname::hatize_byname()`.
 * Fixed a bug in the `matsindf.Rmd` vignette.
@@ -54,7 +76,7 @@ output: html_document
     * Test coverage remains at 100 %.
 
 
-# matsindf 0.3.7 (2020-04-11)
+# matsindf 0.3.7 (2021-04-11)
 
 * Not released to CRAN, because there are no changes in the code itself.
 * Move away from Travis to GitHub Actions for continuous integration testing.
@@ -71,7 +93,7 @@ output: html_document
 
 # matsindf 0.3.6 (2020-08-24)
 
-* To comply with a deprecating change in `dplyr`, 
+* To comply with a breaking change in `dplyr`, 
   all calls to `dplyr::group_by()` now use `.add` argument
   instead of `add` argument.
 

diff --git a/R/data.R b/R/data.R
@@ -3,14 +3,12 @@
 #' A dataset containing approximations to
 #' some of the energy flows in the UK in the year 2000.
 #' These data first appeared as the example in
-#' Figures 3 and 4 of
-#' M.K. Heun, A. Owen, and P.E. Brockway.
+#' Figures 3, 7, and 11 of
+#' M.K. Heun, A. Owen, and P.E. Brockway. 2018.
 #' A physical supply-use table framework for energy analysis on the energy conversion chain.
-#' Sustainability Research Institute Paper 111,
-#' University of Leeds, School of Earth and Environment,
-#' Sustainability Research Institute,
-#' Leeds, England,
-#' 13 November 2017.
+#' Applied Energy,
+#' Vol. 226,
+#' pp. 1134-1162.
 #'
 #' @format A data frame with 36 rows and 7 variables:
 #' \describe{
@@ -22,5 +20,5 @@
 #'   \item{Product}{the energy product involved in this flow}
 #'   \item{E.ktoe}{magnitude of the energy flow in ktoe}
 #' }
-#' @source \url{http://www.see.leeds.ac.uk/fileadmin/Documents/research/sri/workingpapers/sri-wp111.pdf}
+#' @source \doi{10.1016/j.apenergy.2018.05.109}
 "UKEnergy2000"
diff --git a/R/expand.R b/R/expand.R
@@ -1,38 +1,37 @@
-#' Expand a "tidy" data frame with matsindf-style matrices to a "tidy" data frame with each matrix entry as an observation
+#' Expand a `matsindf` data frame
 #'
-#' A data frame with \pkg{matsindf}-style matrices contains matrices with names \code{matnames}
-#' in the column specified by \code{matvals}).
-#' An IO-style matrix has named rows and columns.
-#' In addition, \pkg{matsindf}-style matrices have "types" for row and column information, such as "Commodities", "Industries",
-#' "Products", or "Machines".
+#' Any tidy data frame of matrices (in which each row represents one matrix observation)
+#' can also be represented as a tidy data frame
+#' with each non-zero matrix entry as an observation on its own row.
+#' This function (and `collapse_to_matrices()`) convert between the two representations.
 #'
-#' Names for output columns are specified in the \code{rownames}, \code{colnames},
-#' \code{rowtypes}, and \code{coltypes}, arguments.
-#' The entries of the \pkg{matsindf}-style matrices are stored in an output column named \code{values}.
+#' Names for output columns are specified in the `rownames`, `colnames`,
+#' `rowtypes`, and `coltypes`, arguments.
+#' The entries of the \pkg{matsindf}-style matrices are stored in an output column named `values.`
 #'
-#' @param      .DF the data frame containing \pkg{matsindf}-style matrices.
-#'                 (\code{.DF} may also be a named list of matrices, in which case
+#' @param      .DF The data frame containing \pkg{matsindf}-style matrices.
+#'                 (`.DF` may also be a named list of matrices, in which case
 #'                 names of the matrices are taken from the names of items in the list and
 #'                 list items are expected to be matrices.)
-#' @param matnames name of the column in \code{.DF} containing matrix names (a string).
-#'                 Default is "\code{matnames}".
-#' @param  matvals name of the column in \code{.DF} containing IO-style matrices or constants (a string),
+#' @param matnames The name of the column in `.DF` containing matrix names (a string).
+#'                 Default is "matnames".
+#' @param  matvals The name of the column in `.DF` containing IO-style matrices or constants (a string),
 #'                 This will also be the name of the column containing matrix entries in the output data frame.
-#'                 Default is "\code{matvals}".
-#' @param rownames name for the output column of row names (a string).
-#'                 Default is "\code{rownames}".
-#' @param colnames name for the output column of column names (a string).
-#'                 Default is "\code{colnames}".
-#' @param rowtypes optional name for the output column of row types (a string).
-#'                 Default is "\code{rowtypes}".
-#' @param coltypes optional name for the output column of column types (a string)
-#'                 Default is "\code{coltypes}".
-#' @param     drop if specified, the value to be dropped from output,
-#'                 For example, \code{drop = 0} will cause \code{0} entries in the matrices to be deleted from output.
-#'                 If \code{NA}, no values are dropped from output.
-#'                 Default is \code{NA}.
+#'                 Default is "matvals".
+#' @param rownames The name for the output column of row names (a string).
+#'                 Default is "rownames".
+#' @param colnames The name for the output column of column names (a string).
+#'                 Default is "colnames".
+#' @param rowtypes An optional name for the output column of row types (a string).
+#'                 Default is "rowtypes".
+#' @param coltypes The optional name for the output column of column types (a string)
+#'                 Default is "coltypes".
+#' @param     drop If specified, the value to be dropped from output,
+#'                 For example, `drop = 0` will cause `0` entries in the matrices to be deleted from output.
+#'                 If `NA`, no values are dropped from output.
+#'                 Default is `NA`.
 #'
-#' @return a tidy data frame containing expanded \pkg{matsindf}-style matrices
+#' @return A tidy data frame containing expanded \pkg{matsindf}-style matrices
 #'
 #' @export
 #'
@@ -55,7 +54,7 @@
 #'                                  ptype, ptype, ptype, ptype, NA, NA),
 #'                   coltypes  = c(itype, itype, itype, itype, itype, ptype, ptype,
 #'                                 itype, itype, itype, itype, NA, NA),
-#'                   vals  = c(    11  ,  22,    11 ,   22 ,   23 ,   11 ,   22 ,
+#'                   vals      = c(11  ,  22,    11 ,   22 ,   23 ,   11 ,   22 ,
 #'                                 11 ,   12 ,   11 ,   22,   0.2, 0.3)) %>%
 #'   group_by(Country, Year, matrix)
 #' mats <- collapse_to_matrices(tidy, matnames = "matrix", rownames = "row", colnames = "col",

diff --git a/R/matsindf_apply.R b/R/matsindf_apply.R
@@ -54,7 +54,7 @@
 #' @param FUN the function to be applied to `.dat`.
 #' @param ... named arguments to be passed by name to `FUN`.
 #'
-#' @return a named list or a data frame. (See details.)
+#' @return A named list or a data frame. (See details.)
 #'
 #' @export
 #'
@@ -87,7 +87,7 @@
 #' # All arguments are supplied by named arguments in ..., but mix them up.
 #' # Note that the named arguments override the items in .dat
 #' matsindf_apply(list(a = 1, b = 2, z = 10), FUN = example_fun, a = "z", b = "b")
-#' # Warning is issued when an output item has same name as an input item.
+#' # A warning is issued when an output item has same name as an input item.
 #' matsindf_apply(list(a = 1, b = 2, c = 10), FUN = example_fun, a = "c", b = "b")
 matsindf_apply <- function(.dat = NULL, FUN, ...){
   if (!is.null(.dat)) {
@@ -97,7 +97,6 @@ matsindf_apply <- function(.dat = NULL, FUN, ...){
       stop(".dat must be a data frame or a list in matsindf_apply, was ", class(.dat))
     }
   }
-  # .dat is NULL (the default)
   types <- matsindf_apply_types(...)
 
   # Note that is.list(.dat) covers the cases where .dat is either a list or a data frame.
@@ -129,8 +128,13 @@ matsindf_apply <- function(.dat = NULL, FUN, ...){
     out_list <- Map(f = FUN, ...) %>%
       unname() %>%
       purrr::transpose()
-    numrows <- length(out_list[[1]])
+    # Work around a possible error condition here.
     numcols <- length(out_list)
+    if (numcols == 0) {
+      numrows <- 0
+    } else {
+      numrows <- length(out_list[[1]])
+    }
     # Create a data frame filled with NA values.
     out_df <- data.frame(matrix(NA, nrow = numrows, ncol = numcols)) %>%
       magrittr::set_names(names(out_list))
@@ -162,7 +166,9 @@ matsindf_apply <- function(.dat = NULL, FUN, ...){
     # extract a column from .dat.
     # So, eliminate all NULLs from the ... strings.
     use_dots_not_null <- use_dots[which(!as.logical(lapply(use_dots, is.null)))]
-    arg_cols <- lapply(use_dots_not_null, FUN = function(colname){return(.dat[[colname]])})
+    arg_cols <- lapply(use_dots_not_null, FUN = function(colname){
+      .dat[[colname]]
+    })
     # If one of the ... strings is not a name of a column in .dat,
     # it is, practically speaking, a missing argument, and we should treat it as such.
     # If an arg is not present in .dat, it will be NULL in arg_cols.