diff --git a/README.Rmd b/README.Rmd index 2a72c91..e24eae4 100644 --- a/README.Rmd +++ b/README.Rmd @@ -257,6 +257,8 @@ head(taxon) ### Sugested citation ```{r} + citation("mammalcol") + ``` diff --git a/README.md b/README.md index cdde537..2f5a5a3 100644 --- a/README.md +++ b/README.md @@ -82,8 +82,15 @@ search_mammalcol(splist) #> 4 Northern Pudu 17 ``` -`mammalcol` has the ability to correct minor typos and lower case in the -genus. +#### Search database whith typos + +`mammalcol` has the ability to identify and correct minor typos and +lower case in the genus. Correcting potential typos or variations in +species names through fuzzy matching is a crucial aspect of data +management. This technique ensures precise retrieval by adeptly +identifying and accommodating minor differences in input names, thus +enhancing the reliability of analyses conducted on diverse, +inconsistent, and ensemble datasets. ``` r # vector with species names and intentional typos @@ -199,3 +206,27 @@ head(taxon) #> 5 No #> 6 No ``` + +### Sugested citation + +``` r + +citation("mammalcol") +#> Warning in citation("mammalcol"): could not determine year for 'mammalcol' from +#> package DESCRIPTION file +#> To cite package 'mammalcol' in publications use: +#> +#> Lizcano D (????). _mammalcol: What the Package Does (One Line, Title +#> Case)_. R package version 0.0.0.9000, +#> https://dlizcano.github.io/MammalCol/, +#> . +#> +#> A BibTeX entry for LaTeX users is +#> +#> @Manual{, +#> title = {mammalcol: What the Package Does (One Line, Title Case)}, +#> author = {Diego J. Lizcano}, +#> note = {R package version 0.0.0.9000, https://dlizcano.github.io/MammalCol/}, +#> url = {https://github.com/dlizcano/MamalCol}, +#> } +``` diff --git a/_pkgdown.yml b/_pkgdown.yml index 53d9df2..7bf4e66 100644 --- a/_pkgdown.yml +++ b/_pkgdown.yml @@ -15,12 +15,12 @@ navbar: text: "Articles" menu: - text: "1. Getting started with mammalcol" - href: articles/getting_started.html + href: getting_started.html - text: "2. Selecting and filtering species" - href: articles/selecting_species.html + href: selecting_species.html - text: "3. Using mammalcol to map mammals" - href: articles/Spatialize_florabr.html + href: Spatialize_florabr.html - text: "4. Getting a Presence-Absence Matrix" - href: articles/getting_pam.html + href: getting_pam.html components: home: ~ \ No newline at end of file diff --git a/docs/404.html b/docs/404.html index 1dd3fe0..d19965e 100644 --- a/docs/404.html +++ b/docs/404.html @@ -64,16 +64,16 @@ diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html index 30e3161..dece076 100644 --- a/docs/LICENSE-text.html +++ b/docs/LICENSE-text.html @@ -40,16 +40,16 @@
  • diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 8892c63..92d452c 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -6,6 +6,9 @@ https://dlizcano.github.io/mammalcol/authors.html + + https://dlizcano.github.io/mammalcol/getting_started.html + https://dlizcano.github.io/mammalcol/index.html diff --git a/getting_started.RMD b/getting_started.RMD new file mode 100644 index 0000000..6e9f1fb --- /dev/null +++ b/getting_started.RMD @@ -0,0 +1,208 @@ +--- +output: github_document +--- + + + +```{r, include = FALSE} +knitr::opts_chunk$set( + collapse = TRUE, + comment = "#>", + fig.path = "man/figures/README-", + out.width = "100%" +) + +############# +load(file="C:/CodigoR/Mammal_Col/MammalCol/data/taxon.rda")#, taxon +load(file="C:/CodigoR/Mammal_Col/MammalCol/data/colmap.rda")#, colmap +############ + +search_mammalcol <- function(splist, max_distance = 0.2) { + # Defensive function here, check for user input errors + if (is.factor(splist)) { + splist <- as.character(splist) + } + # Fix species name + splist_st <- standardize_names(splist) + dupes_splist_st <- find_duplicates(splist_st) + + if(length(dupes_splist_st) != 0 ){ + message("The following names are repeated in the 'splist': ", + paste(dupes_splist_st, collapse = ", ")) + } + splist_std <- unique(splist_st) + + # create an output data container + output_matrix <- matrix(nrow = length(splist_std), ncol = 20) # two more + colnames(output_matrix) <- c("name_submitted", + names(taxon), + "Distance") + + # loop code to find the matching string + + for (i in seq_along(splist_std)) { + # Standardise max distance value + if (max_distance < 1 & max_distance > 0) { + max_distance_fixed <- ceiling(nchar(splist_std[i]) * max_distance) + } else { + max_distance_fixed <- max_distance + } + + # fuzzy and exact match + matches <- agrep(splist_std[i], + taxon$scientificName, # base data column + max.distance = max_distance_fixed, + value = TRUE) + + # check non matching result + if (length(matches) == 0) { + row_data <- rep("nill", 18) # 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", 18) # 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",]) +} + + + + +standardize_names <- function(splist) { + fixed1 <- simple_cap(trimws(splist)) # all up + fixed2 <- gsub("cf\\.", "", fixed1) + fixed3 <- gsub("aff\\.", "", fixed2) + fixed4 <- trimws(fixed3) # remove trailing and leading space + fixed5 <- gsub("_", " ", fixed4) # change names separated by _ to space + + # Hybrids + fixed6 <- gsub("(^x )|( x$)|( x )", " ", fixed5) + hybrids <- fixed5 == fixed6 + if (!all(hybrids)) { + sp_hybrids <- splist[!hybrids] + warning(paste("The 'x' sign indicating hybrids have been removed in the", + "following names before search:", + paste(paste0("'", sp_hybrids, "'"), collapse = ", ")), + immediate. = TRUE, call. = FALSE) + } + # Merge multiple spaces + fixed7 <- gsub("(?<=[\\s])\\s*|^\\s+|\\s+$", "", fixed6, perl = TRUE) + return(fixed7) +} + + + +simple_cap <- function(x) { + # Split each string into words, remove unnecessary white spaces, and convert to lowercase + words <- sapply(strsplit(x, "\\s+"), function(words) paste(tolower(words), collapse = " ")) + + # Capitalize the first letter of each word + capitalized <- sapply(strsplit(words, ""), function(word) { + if (length(word) > 0) { + word[1] <- toupper(word[1]) + } + paste(word, collapse = "") + }) + + return(capitalized) +} + + + +find_duplicates <- function(vector) { + # Count the frequency of each word + word_counts <- table(vector) + # Find words with a frequency greater than 1 + duplicated_words <- names(word_counts[word_counts > 1]) + return(duplicated_words) +} + + +################ +mammalmap <- function(species){ + + if (!requireNamespace("ggplot2", quietly = TRUE)) + install.packages("ggplot2") + if (!requireNamespace("sf", quietly = TRUE)) + install.packages("sf") + + # require("ggplot2") + # require("sf") + + #load("data/colmap.rda") + #load("data/taxon.rda") + + distribution_list <- + strsplit(taxon$distribution, "\\|") # trimws () removes spaces + + deptos <- as.data.frame( cbind(Depto=unique(colmap$NAME_1), fill="white")) + sp_id <- which(taxon$scientificName==species) + unos <- trimws(distribution_list[[ sp_id ]]) # species number + + # nested loop to get deptos + for (i in 1:length(deptos[,1])){ + for (j in 1:length(unos)){ + if(deptos$Depto[i]==unos[j]){deptos$fill[i] <- "blue"} + } + } + + # make the map + ggplot2::ggplot(colmap) + + ggplot2::geom_sf(ggplot2::aes(fill = NAME_1)) + + ggplot2::scale_fill_manual(values = deptos$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 + )#, +} + + + +``` + + + +# mammalcol + +[![R-CMD-check](https://github.com/dlizcano/mammalcol/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/dlizcano/mammalcol/actions/workflows/R-CMD-check.yaml) +[![Codecov test coverage](https://codecov.io/gh/dlizcano/mammalcol/branch/main/graph/badge.svg)](https://app.codecov.io/gh/dlizcano/mammalcol?branch=main) +[![CRAN status](https://www.r-pkg.org/badges/version/mammalcol)](https://CRAN.R-project.org/package=mammalcol) + + +The goal of mammalcol is to allow easy access to the List of Mammal Species of Colombia. + +## Installation + +You can install the development version of mammalcol from [GitHub](https://github.com/mammalcol) with: + +``` r +# install.packages("devtools") +devtools::install_github("dlizcano/mammalcol") +``` diff --git a/getting_started.md b/getting_started.md new file mode 100644 index 0000000..101a44e --- /dev/null +++ b/getting_started.md @@ -0,0 +1,26 @@ + + + +# mammalcol + + + +[![R-CMD-check](https://github.com/dlizcano/mammalcol/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/dlizcano/mammalcol/actions/workflows/R-CMD-check.yaml) +[![Codecov test +coverage](https://codecov.io/gh/dlizcano/mammalcol/branch/main/graph/badge.svg)](https://app.codecov.io/gh/dlizcano/mammalcol?branch=main) +[![CRAN +status](https://www.r-pkg.org/badges/version/mammalcol)](https://CRAN.R-project.org/package=mammalcol) + + +The goal of mammalcol is to allow easy access to the List of Mammal +Species of Colombia. + +## Installation + +You can install the development version of mammalcol from +[GitHub](https://github.com/mammalcol) with: + +``` r +# install.packages("devtools") +devtools::install_github("dlizcano/mammalcol") +``` diff --git a/inst/CITATION b/inst/CITATION index 6620f6d..66584dc 100644 --- a/inst/CITATION +++ b/inst/CITATION @@ -1,14 +1,14 @@ -citHeader("To cite avesperu in publications use:") +citHeader("To cite mammalcol package in publications use:") bibentry( bibtype = "Manual", title = "mammalcol: Access to the List of Mammal Species of Colombia", author = "Diego J. Lizcano", - note = "R package version 0.0.2", - year = "2024", + year = 2024, + note = "R package version 0.1.0", textVersion = paste( "Lizcano, DJ. (2024). mammalcol: Access to the List of Mammal Species of Colombia. R package version 0.0.2" ), - footer = "To cite the mammalcol dataset, please use: \nPlenge, M. A. Version [06/03/2024] List of the mammals of Colombia / Lista de los mamíferos de Colombia. SCMas: https://doi.org/10.15472/kl1whs" + footer = "To cite the mammalcol dataset, please use: Mammals of Colombia / Mamíferos de Colombia. SCMas: https://doi.org/10.15472/kl1whs" )