version 0.2.1

.Rbuildignore

@@ -9,3 +9,4 @@
 ^codecov\.yml$
 ^doc$
 ^Meta$
+^cran-comments\.md$

DESCRIPTION

@@ -1,28 +1,35 @@
 Package: mammalcol
-Title: Access to the List of Mammals Species of Colombia
-Version: 0.1.0
+Title: Access to the List of Mammal Species of Colombia
+Version: 0.2.1
 Authors@R: 
+    c(
     person("Diego J.", "Lizcano", , "[email protected]", role = c("aut", "cre"),
-           comment = c(ORCID = "0000-0002-9648-0576"))
-Date: 2024
+           comment = c(ORCID = "0000-0002-9648-0576")),
+    person("Baltazar", "González", , "[email protected]", role = c("ctb"),
+           comment = c(ORCID = "0000-0001-5805-8107")),
+    person("Alejandra", "Bonilla-Sánchez", , "[email protected]", role = c("ctb"),
+           comment = c(ORCID = "0000-0003-0803-5884"))
+           )
+Date: 2024-03-28
 Maintainer: Diego J. Lizcano <[email protected]>
 Description: Allows easy access to the data found in the species list featured
     in the renowned "Ramírez-Chaves, et al. 2021. Checklist of the Mammals
     (Mammalia) of Colombia”. Mammalogy Notes 7(2),253.
-    <https://doi.org/10.47603/mano.v7n2.253>. This publication stands as
+    <doi:10.47603/mano.v7n2.253>. This publication stands as
     one of Colombia's most comprehensive reviews of mammal diversity. The
     dataset incorporates detailed species accounts and has been
     meticulously structured for effortless utilization within the R
     environment.
 License: MIT + file LICENSE
-URL: https://github.com/dlizcano/mamalcol,
+URL: 
+    https://github.com/dlizcano/mammalcol,
     https://dlizcano.github.io/mammalcol/
 BugReports: https://github.com/dlizcano/mammalcol/issues
 Depends: 
     R (>= 2.10)
 Imports:
     ggplot2,
-    magrittr
+    magrittr,
 Suggests:
     dplyr,
     finch,

NEWS.md

@@ -1,7 +1,18 @@
+# mammalcol 0.2.1
+
+* Added new option to function mammalmap() to retrieve the ggplot object and select if want the legend or not, as suggested by Baltazar González.
+* Some typos corrected.
+* Contributors Baltazar González y Alejandra Bonilla-Sánchez added.
+
+
+# mammalcol 0.2.0
+
+* Added sp_by_depto() function
+
 # mammalcol 0.1.0
 
 * Initial CRAN submission.
 * Added vignettes
 * Added search_mammalcol() function
 * Added mammalmap() function
-* Added sp_by_depto() function
+

R/colmap.R

@@ -1,9 +1,12 @@
 #' colmap Dataset
 #'
-#' The colmap dataset Simple feature collection with 33 features and 11 fields. This version 
-#' was obtained from: GDAM using: 
+#' The colmap dataset is a simple feature collection with 33 features and 11 fields. This version 
+#' was obtained from: GDAM using the sf package.
+#' 
 #' colmap <- sf::st_as_sf(gadm(country="COL", level=1, path=tempdir()))
-#' al later apply st_simplify with a tolerance of 1km:
+#' 
+#' and later apply a polygon simplify using st_simplify with a tolerance of 1km:
+#' 
 #' colmap <- st_simplify(colmap, preserveTopology = FALSE, dTolerance = 1000)
 #'
 #' @format Simple feature collection with 33 features and 11 fields:
@@ -23,10 +26,11 @@
 #'   }
 #'
 #'
-#' @details This dataset is designed to provide users with a companion map to
-#' plot the mammal distribution per departamento
+#' @details This dataset is designed to provide users of mammalcol package with a companion map to
+#' plot the mammal distribution per departamento.
 #'
 #' @examples
+#' \dontrun{
 #' # Load the mammalcol package
 #' library(mammalcol)
 #'
@@ -35,6 +39,7 @@
 #'
 #' # Display the first few rows
 #' head(colmap)
+#'}
 #'
 #' @seealso
 #' For more information about the "mammalcol" package and the data sources, visit
@@ -46,5 +51,5 @@
 #' @author
 #' Data compilation: Ramírez-Chaves 2021, Package implementation: Diego J. Lizcano
 #'
-#' @keywords dataset
+#' @keywords internal
 "colmap"

R/distribution.R

@@ -4,7 +4,8 @@
 #' regarding mammal species distribution documented in Colombia, sourced from the "List of the
 #' mammals of Colombia" compiled by Ramírez-Chaves 2021. It encompasses various
 #' details, including locality, source, threat status and appendix CITES of each species. 
-#' The table is a variant of the distribution table from https://doi.org/10.15472/kl1whs
+#' The table is a variant of the distribution table from: <doi:10.15472/kl1whs> 
+#'  
 #'
 #' @format A data frame with 548 rows and 8 columns:
 #'   \describe{
@@ -20,9 +21,9 @@
 #'
 #'
 #' @details This dataset is designed to provide users with comprehensive
-#' information about the mammal species found in Colombia, as documented
-#' by Ramírez-Chaves 2021. It is organized for easy access and utilization within
-#' the R environment.
+#' information about the mammal species found in each departamento of Colombia, 
+#' as documented by Ramírez-Chaves 2021. The data set is organized for easy 
+#' access and utilization within the R environment.
 #'
 #' @seealso
 #' For more information about the "mammalcol" package and the data sources, visit
@@ -34,5 +35,7 @@
 #' @author
 #' Data compilation: Ramírez-Chaves 2021, Package implementation: Diego J. Lizcano
 #'
-#' @keywords dataset
+#' @keywords internal
 "distribution"
+
+

R/mammalmap.R

@@ -1,35 +1,46 @@
 
-#' Plot a map Data for one species of the List of the Mammals of Colombia
+#' Plot a map for one species of the List of the Mammals of Colombia
 #'
 #' This function retrieve the locality data for one species in
-#' the MammalCol pacakage dataset, and returns a map of Departamentos
-#' where the species has been recorded.
+#' the mammalcol pacakage dataset, and returns a map using ggplot2 of the 
+#' departamentos where the species has been recorded.
 #'
 #' The function does not allows fuzzy matching, so the specie name should be correct. 
 #' It is advised to run first the search_mammalcol function.
 #'
-#' @param species A character string containing the name of the species to plot the map.
+#' @param species A character string containing the name of one species present in 
+#' Colombia to plot a map of presence by departamento.
+#' 
+#' @param legend A logical (TRUE or FALSE) to get the legend in the map when is TRUE, 
+#' or not if it is FALSE.
 #' 
 #'
-#' @return A map for the species.
+#' @return A ggplot2 map for the species.
 #'
 #' @examples
-#'
 #' species <- "Tapirus pinchaque" 
-#' mammalmap(species)
+#' mammalmap(species, legend=FALSE)
 #'
 #' @importFrom mammalcol taxon
 #' @importFrom mammalcol colmap
 #' @export
-mammalmap <- function(species){
+mammalmap <- function(species, legend=TRUE){
 
   if (!requireNamespace("ggplot2", quietly = TRUE))
     install.packages("ggplot2")
   if (!requireNamespace("sf", quietly = TRUE))
     install.packages("sf")
 
+  if (missing(species)) {
+    stop("Argument species was not included")
+  }
+
   if (!is.character(species)) {
-    stop(paste0("Argument species must be a character, not ", class(Species)))
+    stop(paste0("Argument species must be a character, not ", class(species)))
+  }
+
+  if (!is.logical(legend)) {
+    stop(paste0("Argument legend must be logical, not ", class(legend)))
   }
 
   # require("ggplot2")
@@ -38,6 +49,9 @@ mammalmap <- function(species){
   #load("data/colmap.rda")
   #load("data/taxon.rda")
 
+  #data(mammalcol::taxon)
+  #data(mammalcol::colmap)
+
   distribution_list <-
     strsplit(taxon$distribution, "\\|") # trimws () removes spaces
 
@@ -53,14 +67,27 @@ mammalmap <- function(species){
   }
 
   # make the map
-  ggplot2::ggplot(colmap) +
-    ggplot2::geom_sf(ggplot2::aes(fill = NAME_1)) +
-    ggplot2::scale_fill_manual(values = deptos$fill) +
-    # ggtitle(taxon$scientificName[25]) + #species name number
-    ggplot2::labs(subtitle = taxon$scientificName[sp_id])+
-    ggplot2::theme(legend.position="right", # locatio legend
-            legend.title = ggplot2::element_blank(),#element_text(size=7),#,
-            legend.text = ggplot2::element_text(size=7,), # text depto size
-            plot.subtitle = ggplot2::element_text(face = "italic") # italica
-    )#,
-}
+  # if legend true 
+  if(legend==TRUE) {
+    mapa <-   ggplot2::ggplot(colmap) +
+      ggplot2::geom_sf(ggplot2::aes(fill = NAME_1)) +
+      ggplot2::scale_fill_manual(values = deptos$fill) +
+      # ggtitle(taxon$scientificName[25]) + #species name number
+      ggplot2::labs(subtitle = taxon$scientificName[sp_id])+
+      ggplot2::theme(legend.position="right", # location legend
+                     legend.title = ggplot2::element_blank(),#element_text(size=7),#,
+                     legend.text = ggplot2::element_text(size=8,), # text depto size
+                     plot.subtitle = ggplot2::element_text(face = "italic") # italica
+      )
+  }else{ # if legend false
+    mapa <-   ggplot2::ggplot(colmap) +
+      ggplot2::geom_sf(ggplot2::aes(fill = NAME_1), show.legend = FALSE) + # removes legend
+      ggplot2::scale_fill_manual(values = deptos$fill) +
+      # ggtitle(taxon$scientificName[25]) + #species name number
+      ggplot2::labs(subtitle = taxon$scientificName[sp_id]) +
+      ggplot2::theme(plot.subtitle = ggplot2::element_text(face = "italic")
+                      )# italica
+  }
+
+return(mapa)
+} # end function

R/search_mammalcol.R

@@ -0,0 +1,98 @@
+
+#' Retrieve Data from the List of the Mammals of Colombia
+#'
+#' This function takes a list of Mammal species names, searches for their data in
+#' the MammalCol pacakage dataset, and returns a data frame containing the relevant
+#' information for each species.
+#'
+#' The function allows fuzzy matching for species names with a maximum
+#' distance threshold to handle potential typos or variations in species names.
+#'
+#' @param splist A character vector containing the names of the species to search for.
+#' @param max_distance The maximum allowed distance for fuzzy matching of species names.
+#'   Defaults to 0.2.
+#'
+#' @return A data frame containing the retrieved information for each species.
+#'
+#' @examples
+#'
+#' splist <- c("Tapirus bairdii", "Tapirus pinchaque", "Tapirus terrestris",
+#'             "Tapirus terrestris", "tapir terrestre", "Pudu mephistophiles")
+#'
+#' search_mammalcol(splist)
+#'
+#' @importFrom mammalcol taxon
+#' 
+#' @export
+search_mammalcol <- function(splist, max_distance = 0.2) {
+  # Defensive function here, check for user input errors
+  if (is.factor(splist)) {
+    splist <- as.character(splist)
+  }
+  # Fix species name
+  splist_st <- standardize_names(splist)
+  dupes_splist_st <- find_duplicates(splist_st)
+
+  if(length(dupes_splist_st) != 0 ){
+    message("The following names are repeated in the 'splist': ",
+            paste(dupes_splist_st, collapse = ", "))
+  }
+  splist_std <- unique(splist_st)
+
+  # create an output data container
+  output_matrix <- matrix(nrow = length(splist_std), ncol = 21) # two more
+  colnames(output_matrix) <- c("name_submitted",
+                               names(taxon), 
+                               "Distance")
+
+  # loop code to find the matching string
+
+  for (i in seq_along(splist_std)) {
+    # Standardise max distance value
+    if (max_distance < 1 & max_distance > 0) {
+      max_distance_fixed <- ceiling(nchar(splist_std[i]) * max_distance)
+    } else {
+      max_distance_fixed <- max_distance
+    }
+
+    # fuzzy and exact match
+    matches <- agrep(splist_std[i],
+                     taxon$scientificName, # base data column
+                     max.distance = max_distance_fixed,
+                     value = TRUE)
+
+    # check non matching result
+    if (length(matches) == 0) {
+      row_data <- rep("nill", 19) # number of columns
+    }
+    else if (length(matches) != 0){ # match result
+      dis_value <- as.numeric(utils::adist(splist_std[i], matches))
+      matches1 <- matches[dis_value <= max_distance_fixed]
+      dis_val_1 <- dis_value[dis_value <= max_distance_fixed]
+
+      if (length(matches1) == 0){
+        row_data <- rep("nill", 19) # number of columns
+      }
+      else if (length(matches1) != 0){
+        row_data <- as.matrix(taxon[taxon$scientificName %in% matches1,])
+      }
+    }
+
+    # distance value
+    if(is.null(nrow(row_data))){
+      dis_value_1 <- "nill"
+    } else{
+      dis_value_1 <- utils::adist(splist_std[i], row_data[,2])
+    }
+
+    output_matrix[i, ] <-
+      c(splist_std[i], row_data, dis_value_1)
+  }
+
+  # Output
+  output <- as.data.frame(output_matrix)
+  # rownames(output) <- NULL
+  output <- output[,-2]# delete the id column
+  return(output[output$scientificName != "nill",])
+}
+

R/sp_by_depto.R

@@ -8,8 +8,9 @@
 #'   occur only in all provided (no more, no less) \code{states} and \code{all} matches 
 #'   mammal species that occur at least in all \code{states} passed. See examples.
 #' @param taxa optional character vector to match against the departamentos. Use the order name
-#' @export
+#' 
 #' @return a data frame
+#' 
 #' @examples
 #' \dontrun{
 #' occ.any <- sp_by_depto(c("Arauca", "Norte de Santander"), type = "any")
@@ -23,10 +24,12 @@
 #' head(occ.taxa)
 #' }
 #' 
+#' @export 
 sp_by_depto <- function(states, type = c("any", "only", "all"), taxa = NULL) {
   if (length(states) == 0) stop("Please provide at least one Colombian Departamento")
   type <- match.arg(type)
   states <- sort(states)
+
   # states <- paste("BR-", states, sep = "")
   if (length(states) == 0) stop("Please provide at least one Colombian Departamento")
   # res <- lapply(occurrences, match, states)