Merge branch 'release-0.3.12'

.github/workflows/R-CMD-check.yaml

@@ -1,15 +1,10 @@
-# For help debugging build failures open an issue on the RStudio community with the 'github-actions' tag.
-# https://community.rstudio.com/new-topic?category=Package%20development&tags=github-actions
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    branches:
-      - master
-      - develop
-      - release-*
+    branches: [master, develop, release-*]
   pull_request:
-    branches:
-      - master
-      - develop
+    branches: [master, develop]
   schedule:
     # Build main branch daily at 7 AM UTC, 2 AM EST, 3 AM EDT.
     - cron: "0 7 * * *"
@@ -26,65 +21,32 @@ jobs:
       fail-fast: false
       matrix:
         config:
+          - {os: macos-latest,   r: 'release'}
           - {os: windows-latest, r: 'release'}
-          - {os: macOS-latest, r: 'release'}
-          - {os: ubuntu-20.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
-          - {os: ubuntu-20.04, r: 'devel', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
 
     env:
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
-      RSPM: ${{ matrix.config.rspm }}
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
-      - uses: r-lib/actions/setup-r@v1
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
         with:
           r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
 
-      - uses: r-lib/actions/setup-pandoc@v1
-
-      - name: Query dependencies
-        run: |
-          install.packages('remotes')
-          saveRDS(remotes::dev_package_deps(dependencies = TRUE), ".github/depends.Rds", version = 2)
-          writeLines(sprintf("R-%i.%i", getRversion()$major, getRversion()$minor), ".github/R-version")
-        shell: Rscript {0}
-
-      - name: Restore R package cache
-        if: runner.os != 'Windows'
-        uses: actions/cache@v2
+      - uses: r-lib/actions/setup-r-dependencies@v2
         with:
-          path: ${{ env.R_LIBS_USER }}
-          key: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ runner.os }}-${{ hashFiles('.github/R-version') }}-1-
-
-      - name: Install system dependencies
-        if: runner.os == 'Linux'
-        run: |
-          while read -r cmd
-          do
-            eval sudo $cmd
-          done < <(Rscript -e 'writeLines(remotes::system_requirements("ubuntu", "20.04"))')
-
-      - name: Install dependencies
-        run: |
-          remotes::install_deps(dependencies = TRUE)
-          remotes::install_cran("rcmdcheck")
-        shell: Rscript {0}
-
-      - name: Check
-        env:
-          _R_CHECK_CRAN_INCOMING_REMOTE_: false
-        run: |
-          options(crayon.enabled = TRUE)
-          rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), error_on = "warning", check_dir = "check")
-        shell: Rscript {0}
+          extra-packages: any::rcmdcheck
+          needs: check
 
-      - name: Upload check results
-        if: failure()
-        uses: actions/upload-artifact@main
+      - uses: r-lib/actions/check-r-package@v2
         with:
-          name: ${{ runner.os }}-r${{ matrix.config.r }}-results
-          path: check
+          upload-snapshots: true

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"))
@@ -13,7 +13,7 @@ License: MIT + file LICENSE
 Language: en-US
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.2.0
+RoxygenNote: 7.2.3
 Roxygen: list(markdown = TRUE)
 Depends: R (>= 2.10)
 Imports:
@@ -27,6 +27,7 @@ Imports:
 Suggests:
     covr,
     ggplot2,
+    Hmisc,
     knitr,
     RCLabels,
     rmarkdown,

LICENSE

@@ -1,2 +1,2 @@
-YEAR: 2022
+YEAR: 2023
 COPYRIGHT HOLDER: Matthew Kuperus Heun

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)

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.
 

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"

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",

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.