Remove duplicates in vars_dict and add pre-commit check to guard ag…

…ainst dupes (#36)

* Remove duplicates in `vars_dict` and add pre-commit check to guard against future dupes

* Update vars_dict data documentation

* Rename validate-vars-dict -> check-vars-dict

* Add Rscript shebang to check-vars-dict.R hook

.pre-commit-config.yaml

@@ -34,6 +34,11 @@ repos:
         entry: Cannot commit .Rhistory, .RData, .Rds or .rds.
         language: fail
         files: '\.(Rhistory|RData|Rds|rds)$'
+    -   id: check-vars-dict
+        name: Validate vars_dict
+        entry: Rscript scripts/check-vars-dict.R
+        files: data/vars_dict.rda
+        language: r
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.7.4
     hooks:

R/data.R

@@ -153,7 +153,7 @@
 #' to their human-readable value (ROOF_CNST = 1
 #' becomes ROOF_CNST = Shingle/Asphalt).
 #'
-#' @format A data frame with 509 rows and 11 variables:
+#' @format A data frame with 518 rows and 11 variables:
 #' \describe{
 #'   \item{var_name_hie}{Column name of variable when stored in the legacy
 #'   ADDCHARS SQL table}

data-raw/vars_dict.csv

@@ -488,7 +488,7 @@ qu_mlt_cd,card,card,meta_card_num,card_num,Card Number,meta,character,,,
 ,,parking_space_flag_reason,parking_space_flag_reason,,Reason Parcel Is Considered Parking/Garage Space or Storage Unit,meta,character,,,
 ,,is_common_area,is_common_area,is_common_area,Building Common Area,meta,logical,,,
 ,,char_building_units,char_building_units,building_units,Total Condominium Building Livable Parcels,char,numeric,,,
-,,char_building_sf       ,char_building_sf       ,building_sf       ,Total Condominium Building Square Footage,char,numeric,,,
+,,char_building_sf,char_building_sf,building_sf,Total Condominium Building Square Footage,char,numeric,,,
 ,,char_unit_sf,char_unit_sf,unit_sf,Condominium Unit Square Footage,char,numeric,,,
 ,,char_bedrooms,char_bedrooms,bedrooms,Condominium Unit Bedrooms,char,numeric,,,
 ,,char_half_baths,char_half_baths,half_baths,Condominium Unit Half Baths,char,numeric,,,
@@ -509,11 +509,6 @@ qu_mlt_cd,card,card,meta_card_num,card_num,Card Number,meta,character,,,
 ,,ccao_is_active_exe_homeowner,ccao_is_active_exe_homeowner,is_active_exe_homeowner,Active Homeowner Exemption,ccao,logical,,,
 ,,ccao_n_years_exe_homeowner,ccao_n_years_exe_homeowner,n_years_exe_homeowner,Number of Years Active Homeowner Exemption,ccao,numeric,,,
 ,,sale_count_past_n_years,meta_sale_count_past_n_years,sale_count_past_n_years,Number of sales within previous N years of sale/lien date,meta,numeric,,,
-,,char_building_sf,char_building_sf,building_sf,Building Square Footage,char,numeric,,,
-,,char_unit_sf,char_unit_sf,unit_sf,Unit Square Footage,char,numeric,,,
-,,char_bedrooms,char_bedrooms,bedrooms,Bedrooms,char,numeric,,,
-,,char_half_baths,char_half_baths,half_baths,Half Baths,char,numeric,,,
-,,char_full_baths,char_full_baths,full_baths,Full Baths,char,numeric,,,
 ,,strata_1,meta_strata_1,strata_1,Condominium Building Strata 1,meta,character,,,
 ,,strata_2,meta_strata_2,strata_2,Condominium Building Strata 2,meta,character,,,
 ,,shp_parcel_centroid_dist_ft_sd,shp_parcel_centroid_dist_ft_sd,parcel_centroid_dist_ft_sd,Standard Deviation Distance From Parcel Centroid to Vertices (Feet),shp,numeric,,,

scripts/check-vars-dict.R

@@ -0,0 +1,17 @@
+#!/usr/bin/env Rscript
+# Script to check that the `vars_dict` data object is well-formed
+load("data/vars_dict.rda")
+
+# Check for duplicate model parameters
+non_na_model_vars <- subset(
+  vars_dict,
+  !is.na(var_name_model)
+)[c("var_name_model", "var_code", "var_value")]
+dupes <- non_na_model_vars[which(duplicated(non_na_model_vars)), ]
+
+if (nrow(dupes) > 0) {
+  stop(
+    "Duplicate var_name_model entries in vars_dict: ",
+    paste(dupes$var_name_model, collapse = ", ")
+  )
+}