id_for_municipality and related functions

.gitignore

@@ -3,3 +3,4 @@
 .RData
 .Ruserdata
 inst/doc
+.DS_Store

NAMESPACE

@@ -7,7 +7,9 @@ export(add_days_between)
 export(add_detailed_label)
 export(add_detailed_label_es)
 export(add_id_for_event)
+export(add_id_for_municipality)
 export(add_id_for_president)
+export(add_muni_gb2014_from_id)
 export(add_nameline)
 export(add_nameline_es)
 export(add_presidency_column)
@@ -30,6 +32,7 @@ export(combine_names)
 export(count_events_in_month)
 export(count_ongoing_events)
 export(count_range_by)
+export(department_name_from_id)
 export(displayed_date_string)
 export(estimated_date)
 export(estimated_date_string)
@@ -48,16 +51,22 @@ export(fully_annotate_es)
 export(generate_examples_with_results)
 export(gray_pal)
 export(id_for_event)
+export(id_for_municipality)
+export(id_for_municipality_2)
 export(id_for_president)
 export(muni_counts_by)
 export(muni_list_with_counts_by)
+export(municipality_name_from_id)
+export(municipality_vector_from_id)
 export(n_categorized_by)
 export(n_filter)
 export(n_municipality)
 export(n_responsibility_by)
 export(perp_pal)
+export(province_name_from_id)
 export(quasilogical_as_binary)
 export(red_pal)
+export(rename_anexo_columns)
 export(render_age)
 export(render_age_es)
 export(render_presidency)
@@ -70,6 +79,7 @@ export(set_maximums)
 export(share_of_largest_n)
 export(standard_filter)
 export(str_equivalent)
+export(str_equivalent_list)
 export(string_to_listcase)
 export(sv_pal)
 export(top_values_string)
@@ -90,10 +100,13 @@ importFrom(dplyr,if_any)
 importFrom(dplyr,is.tbl)
 importFrom(dplyr,left_join)
 importFrom(dplyr,mutate)
+importFrom(dplyr,pull)
 importFrom(dplyr,relocate)
+importFrom(dplyr,rename)
 importFrom(dplyr,rename_with)
 importFrom(dplyr,rowwise)
 importFrom(dplyr,select)
+importFrom(dplyr,starts_with)
 importFrom(dplyr,summarize)
 importFrom(dplyr,ungroup)
 importFrom(forcats,fct_collapse)

R/aaa-data.R

@@ -160,6 +160,92 @@
 #'   to "diciembre"
 "month.name.es"
 
+#' Municipal Reference Table for Bolivia
+#'
+#' A reference table containing municipality information for Bolivia,
+#' read from the official anexo of municipalities.
+#'
+#' @format A data frame with columns:
+#' \describe{
+#'   \item{codigo_ine}{Municipal code (INE code)}
+#'   \item{municipio}{Municipality name}
+#'   \item{provincia}{Province name}
+#'   \item{departamento}{Department name}
+#'   \item{superficie}{Area of the municipality in square kilometers}
+#'   \item{poblacion}{Population of the municipality}
+#'   \item{densidad}{Population density (people per square kilometer)}
+#'   \item{municipio_alt}{Alternative municipality name}
+#' }
+#'
+#' @details
+#' This table contains the official list of municipalities in Bolivia
+#' with their corresponding INE (Instituto Nacional de Estadística) codes,
+#' provinces, and departments. The table is used for municipality lookup
+#' and ID assignment functions.
+"anexo_municipios"
+
+#' Municipality ID Lookup Table
+#'
+#' A comprehensive lookup table for municipality IDs and names in Bolivia,
+#' including alternative municipality names and mappings.
+#'
+#' @format A data frame with columns:
+#' \describe{
+#'   \item{id_muni}{Municipal ID (INE code)}
+#'   \item{muni_gb2014}{Municipality name in GB2014 map format}
+#'   \item{muni_anexo}{Standard municipality name from anexo}
+#'   \item{muni_ine}{Municipality name in INE table}
+#'   \item{muni_census}{Municipality name in census table}
+#'   \item{department}{Department name}
+#'   \item{muni_list}{List of alternative municipality names}
+#'   \item{n_unique}{Number of unique names for the municipality}
+#' }
+#'
+#' @details
+#' This table provides comprehensive municipality lookup functionality,
+#' including alternative spellings and name variations. It supports
+#' the id_for_municipality_2() function and other advanced municipality
+#' matching operations.
+"muni_id_lookup_table"
+
+#' Municipality Name Conversion Table for GB2014 Format
+#'
+#' A lookup table for converting between standard municipality names
+#' and GB2014 format municipality names in Bolivia.
+#'
+#' @format A data frame with columns:
+#' \describe{
+#'   \item{id_muni}{Municipal ID (INE code)}
+#'   \item{muni_gb2014}{Municipality name in GB2014 format}
+#'   \item{muni_anexo}{Standard municipality name from anexo}
+#'   \item{recode}{R code string for recoding municipality names}
+#' }
+#'
+#' @details
+#' This table contains only municipalities where the GB2014 format name
+#' differs from the standard anexo name. It includes generated R code
+#' strings that can be used to perform the name conversions automatically.
+"muni_gb2014_conversion"
+
+#' Municipality Lookup Table in GB2014 Format
+#'
+#' A simplified lookup table using GB2014 format municipality names
+#' for municipality ID and department lookup.
+#'
+#' @format A data frame with columns:
+#' \describe{
+#'   \item{id_muni}{Municipal ID (INE code)}
+#'   \item{municipality}{Municipality name in GB2014 format}
+#'   \item{department}{Department name}
+#' }
+#'
+#' @details
+#' This table provides a streamlined lookup mechanism using GB2014
+#' format municipality names. It's derived from muni_id_lookup_table
+#' and can be used when working with data that uses GB2014 naming
+#' conventions.
+"muni_gb2014_lookup"
+
 # This list produced by colnames(deaths_aug24) %>% dput()
 # Needed for dplyr references to variables
 # See: https://www.r-bloggers.com/2019/08/no-visible-binding-for-global-variable/
@@ -228,7 +314,17 @@ utils::globalVariables(
     "date_text",
     "sr_text",
     "lev",
-    "standard_factoring_variables"
+    "standard_factoring_variables",
+    "muni_list",
+    "muni_anexo",
+    "muni_gb2014",
+    "anexo_municipios",
+    "muni_id_lookup_table",
+    "code",
+    "id_muni",
+    "municipio",
+    "provincia",
+    "departamento"
   )
 )
 

R/add-presidency-column.R

@@ -93,6 +93,9 @@ add_presidency_column <- function(dataframe, variable,
 #' render_presidency("Gonzalo Sanchez de Lozada (2nd)", "id_presidency") # "p107"
 #' render_presidency("Gonzalo Sanchez de Lozada (2nd)", "presidency_surnames")
 #' render_presidency("Gonzalo Sanchez de Lozada (2nd)", "presidency_year_es")
+#' render_presidency("p111", "presidency_commonname_es", source_var="id_presidency")
+#' render_presidency("p111", "presidency_initials_num", source_var="id_presidency")
+#' render_presidency("p111", "presidency_commonname", source_var="id_presidency")
 render_presidency <- function(value,
                                   dest_var,
                                   lookup_table = presidency_name_table,

R/data-cleaning.R

@@ -64,14 +64,22 @@ assign_state_perpetrator_levels <- function(dataframe, simplify=FALSE){
   de$state_perpetrator <- str_to_title(de$state_perpetrator)
   de$state_perpetrator <- fct_na_value_to_level(de$state_perpetrator, level = "Unknown")
   if (simplify){
+    sp_levels_in_order <- c("Unknown", "No", "Indirect", "Mutiny", "Yes")
+
     de$state_perpetrator <- fct_collapse(de$state_perpetrator,
                                          Yes = c("Yes", "Likely Yes", "Presumed Yes"),
                                          Indirect = c("Indirect"),
                                          No = c("No", "Likely No"),
                                          Mutiny = c("In Mutiny"),
                                          Unknown  = c("Unknown", "Disputed", "Suspected") ) %>% suppressWarnings()
+
+    if(length(levels(de$state_responsibility)) > length(lev$state_responsibility$levels)) {
+      warning(paste("Unknown state_perpetrator level:",
+                    setdiff(levels(de$state_perpetrator), sp_levels_in_order), "\n"))
+    }
+
     de$state_perpetrator <- fct_relevel(de$state_perpetrator,
-                                        c("Unknown", "No", "Indirect", "Mutiny", "Yes")) # default ordering
+                                        sp_levels_in_order) # default ordering
   }
   return(de)
 }
@@ -136,6 +144,12 @@ assign_state_responsibility_levels <- function(dataframe, simplify=FALSE){
                                             Unknown  = c("Unknown", "Unclear", "Disputed") ) %>%
                                  suppressWarnings()
 
+
+    if(length(levels(de$state_responsibility)) > length(lev$state_responsibility$levels)) {
+      warning(paste("Unknown state_responsibility level:",
+                    setdiff(levels(de$state_responsibility), lev$state_responsibility$levels), "\n"))
+    }
+
     de$state_responsibility <- fct_relevel(de$state_responsibility,
                                            lev$state_responsibility$levels) %>%
       suppressWarnings()