Development Release 3.0.0

.Rbuildignore

@@ -12,3 +12,5 @@ ChangeLog
 
 ^cran-comments\.md$
 ^CRAN-SUBMISSION$
+^README\.Rmd$
+^data-raw$

.gitignore

@@ -1,3 +1,5 @@
+.DS_Store
+
 # History files
 .Rhistory
 .Rapp.history
@@ -8,6 +10,7 @@
 # RStudio files
 .Rproj.user/
 .Rproj
+.lazytest
 
 # produced vignettes
 vignettes/*.html
@@ -21,4 +24,4 @@ vignettes/*.pdf
 src/RcppExports.o
 src/aux_funs.o
 src/sample_me.o
-src/wru.so
+src/wru.so

ChangeLog

@@ -16,3 +16,4 @@ Date        Version  Comment
 2022-06-17  1.0.0    Updates to BISG, inclusion of fBISG and other package improvements
 2022-10-04  1.0.1    Bug fixes for census url and census year
 2023-06-12  2.0.0    Updated defaults to 2020 data, specifiy as next major version 2.0.
+2024-02-15  3.0.0    Adding back age and sex functionality. Other improvements. 

DESCRIPTION

@@ -1,47 +1,58 @@
 Package: wru
-Version: 2.0.0
-Date: 2023-07-12
-Title: Who are You? Bayesian Prediction of Racial Category Using Surname, First Name, Middle Name, and
-    Geolocation
+Title: Who are You? Bayesian Prediction of Racial Category Using Surname,
+    First Name, Middle Name, and Geolocation
+Version: 3.0.0
+Date: 2024-02-14
 Authors@R: c(
-  person("Kabir", "Khanna", email = "[email protected]", role = c("aut")),
-  person("Brandon", "Bertelsen", email = "[email protected]", role = c("aut","cre")),
-  person("Santiago", "Olivella", email = "[email protected]", role = c("aut")),
-  person("Evan", "Rosenman", email = "[email protected]", role = c("aut")),
-  person("Kosuke", "Imai", email = "[email protected]", role = c("aut"))
+    person("Kabir", "Khanna", , "[email protected]", role = "aut"),
+    person("Brandon", "Bertelsen", , "[email protected]", role = c("aut", "cre")),
+    person("Santiago", "Olivella", , "[email protected]", role = "aut"),
+    person("Evan", "Rosenman", , "[email protected]", role = "aut"),
+    person("Alex", "Rossell Hayes", , "[email protected]", role = "aut"),
+    person("Kosuke", "Imai", , "[email protected]", role = "aut")
   )
-Description: Predicts individual race/ethnicity using surname, first name, middle name, geolocation,
-    and other attributes, such as gender and age. The method utilizes Bayes'
-    Rule (with optional measurement error correction) to compute the posterior probability of each racial category for any given
-    individual. The package implements methods described in Imai and Khanna (2016)
-    "Improving Ecological Inference by Predicting Individual Ethnicity from Voter
-    Registration Records" Political Analysis <DOI:10.1093/pan/mpw001> and Imai, Olivella, and Rosenman (2022) 
-    "Addressing census data problems in race imputation via fully Bayesian Improved Surname Geocoding and name supplements" 
-    <DOI:10.1126/sciadv.adc9824>.  The package also incorporates the data described in Rosenman, Olivella, and Imai (2023) 
-    "Race and ethnicity data for first, middle, and surnames" <DOI:10.1038/s41597-023-02202-2>.
+Description: Predicts individual race/ethnicity using surname, first name,
+    middle name, geolocation, and other attributes, such as gender and
+    age. The method utilizes Bayes' Rule (with optional measurement error
+    correction) to compute the posterior probability of each racial
+    category for any given individual. The package implements methods
+    described in Imai and Khanna (2016) "Improving Ecological Inference by
+    Predicting Individual Ethnicity from Voter Registration Records"
+    Political Analysis <DOI:10.1093/pan/mpw001> and Imai, Olivella, and
+    Rosenman (2022) "Addressing census data problems in race imputation
+    via fully Bayesian Improved Surname Geocoding and name supplements"
+    <DOI:10.1126/sciadv.adc9824>.  The package also incorporates the data
+    described in Rosenman, Olivella, and Imai (2023) "Race and ethnicity
+    data for first, middle, and surnames"
+    <DOI:10.1038/s41597-023-02202-2>.
+License: GPL (>= 3)
 URL: https://github.com/kosukeimai/wru
 BugReports: https://github.com/kosukeimai/wru/issues
 Depends:
     R (>= 4.1.0),
     utils
 Imports:
+    cli,
     dplyr,
+    tidyr,
     furrr,
     future,
+    piggyback (>= 0.1.4),
+    PL94171,
     purrr,
     Rcpp,
-    piggyback (>= 0.1.4), 
-    PL94171
+    rlang
 Suggests:
+    covr,
     testthat (>= 3.0.0),
-    covr
+    tidycensus
 LinkingTo:
     Rcpp,
     RcppArmadillo
-LazyLoad: yes
+Config/testthat/edition: 3
+Encoding: UTF-8
 LazyData: yes
 LazyDataCompression: xz
-License: GPL (>= 3)
+LazyLoad: yes
+Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.2.3
-Encoding: UTF-8
-Config/testthat/edition: 3

NAMESPACE

@@ -1,14 +1,18 @@
 # Generated by roxygen2: do not edit by hand
 
+export(as_fips_code)
+export(as_state_abbreviation)
 export(format_legacy_data)
 export(get_census_data)
 export(predict_race)
 import(PL94171)
 importFrom(Rcpp,evalCpp)
 importFrom(dplyr,coalesce)
+importFrom(dplyr,pull)
 importFrom(furrr,future_map_dfr)
 importFrom(piggyback,pb_download)
 importFrom(purrr,map_dfr)
+importFrom(rlang,"%||%")
 importFrom(stats,rmultinom)
 importFrom(utils,setTxtProgressBar)
 importFrom(utils,txtProgressBar)

R/RcppExports.R

@@ -5,21 +5,16 @@
 #'
 #' @param last_name Integer vector of last name identifiers for each record (zero indexed; as all that follow). Must match columns numbers in M_rs.  
 #' @param first_name See last_name
-#' @param middle_name See last_name
+#' @param mid_name See last_name
 #' @param geo Integer vector of geographic units for each record. Must match column number in N_rg
 #' @param N_rg Integer matrix of race | geography counts in census (geograpgies in columns).
-#' @param M_rs Integer matrix of race | surname counts in dictionary (surnames in columns).
-#' @param M_rf Same as `M_rs`, but for first names (can be empty matrix for surname only models).
-#' @param M_rm Same as `M_rs`, but for middle names (can be empty matrix for surname, or surname and first name only models).
-#' @param alpha Numeric matrix of race | geography prior probabilities.
 #' @param pi_s Numeric matrix of race | surname prior probabilities.
 #' @param pi_f Same as `pi_s`, but for first names.
 #' @param pi_m Same as `pi_s`, but for middle names.
 #' @param pi_nr Matrix of marginal probability distribution over missing names; non-keyword names default to this distribution.
 #' @param which_names Integer; 0=surname only. 1=surname + first name. 2= surname, first, and middle names.
 #' @param samples Integer number of samples to take after (in total)
 #' @param burnin Integer number of samples to discard as burn-in of Markov chain
-#' @param me_race Boolean; should measurement error in race | geography be corrected?
 #' @param race_init Integer vector of initial race assignments
 #' @param verbose Boolean; should informative messages be printed?
 #'

R/census_data_preflight.R

@@ -1,31 +1,15 @@
 #' Preflight census data
 #' 
-#' @param census.data See documentation in \code{race_predict}.
-#' @param census.geo See documentation in \code{race_predict}.
-#' @param year See documentation in \code{race_predict}.
+#' @inheritParams predict_race
 #' @keywords internal
 
 census_data_preflight <- function(census.data, census.geo, year) {
-
-  if (year != "2020"){
-    vars_ <- c(
-      pop_white = 'P005003', pop_black = 'P005004',
-      pop_aian = 'P005005', pop_asian = 'P005006',
-      pop_nhpi = 'P005007', pop_other = 'P005008', 
-      pop_two = 'P005009', pop_hisp = 'P005010'
-    )
-  } else {
-    vars_ <- c(
-      pop_white = 'P2_005N', pop_black = 'P2_006N',
-      pop_aian = 'P2_007N', pop_asian = 'P2_008N', 
-      pop_nhpi = 'P2_009N', pop_other = 'P2_010N', 
-      pop_two = 'P2_011N', pop_hisp = 'P2_002N'
-    )
-  }
+  vars_ <- unlist(census_geo_api_names(year = year))
+  legacy_vars <- unlist(census_geo_api_names_legacy(year = year))
 
   test <- lapply(census.data, function(x) {
     nms_to_test <- names(x[[census.geo]])
-    all(vars_ %in% nms_to_test)
+    all(vars_ %in% nms_to_test) || all(legacy_vars %in% nms_to_test)
   }) 
   missings <- names(test)[!unlist(test)]