Merge pull request #302 from PSLmodels/pr-move-cd-project-to-subfolder

PR move cd project to subfolder

tmd/areas/targets/prepare/.gitignore → tmd/areas/targets/prepare/prepare_cds/.gitignore

@@ -1,4 +1,4 @@
-# prepare
+# prepare_cds
 
 # ignore quarto at the root level
 /.quarto/

tmd/areas/targets/prepare/R/constants.R → tmd/areas/targets/prepare/prepare_cds/R/constants.R

@@ -8,3 +8,8 @@ CDINTERMEDIATE <- fs::path(CDDIR, "intermediate")
 CDFINAL <- fs::path(CDDIR, "final")
 
 CDDOCEXTRACT <- "cd_documentation_extracted_from_21incddocguide.docx.xlsx"
+
+TMDHOME <- fs::path(here::here(), "..", "..", "..", "..", "..")
+# normalizePath(TMDHOME)
+TMDDATA <- fs::path(TMDHOME, "tmd", "storage", "output")
+# normalizePath(TMDDATA)

tmd/areas/targets/prepare/prepare_cds/README.md

@@ -0,0 +1,6 @@
+# areas / targets / prepare
+
+Contains code and data used to generate sub-national area targets files.
+
+Evolving preparation documentation is available at [this
+website](https://tmd-areas-prepare-targets.netlify.app).

tmd/areas/targets/prepare/_quarto.yml → tmd/areas/targets/prepare/prepare_cds/_quarto.yml

@@ -28,7 +28,7 @@ execute:
   freeze: false  # auto: during global project renders, re-render only when source changes
 
 book:
-  title: "Develop targets for subnational areas"
+  title: "Develop targets for Congressional districts"
   subtitle: "Create csv target files for use by area targeting routines"
   # author: "Don Boyd"
   date: today

tmd/areas/targets/prepare/cd_compare_us_totals_tmd_vs_irs_published.qmd → tmd/areas/targets/prepare/prepare_cds/cd_compare_us_totals_tmd_vs_irs_published.qmd

@@ -26,8 +26,7 @@ source(here::here("R", "functions.R"))
 vmap <- read_csv(fs::path(CDINTERMEDIATE, "cd_variable_mapping.csv"))
 cdirs <- read_csv(fs::path(CDINTERMEDIATE, "cdbasefile_sessions.csv"))
 
-TMDDIR <- here::here("..", "..", "..", "storage", "output")
-fpath <-  fs::path(TMDDIR, "cached_allvars.csv")
+fpath <-  fs::path(TMDDATA, "cached_allvars.csv")
 tmd2021 <- vroom(fpath)
 ns(tmd2021)
 

tmd/areas/targets/prepare/cd_construct_soi_variable_documentation.qmd → tmd/areas/targets/prepare/prepare_cds/cd_construct_soi_variable_documentation.qmd

@@ -13,6 +13,7 @@ editor_options:
 
 source(here::here("R", "libraries.R"))
 source(here::here("R", "constants.R"))
+source(here::here("R", "functions.R"))
 
 ```
 

tmd/areas/targets/prepare/cd_download_and_clean_census_population_data.qmd → tmd/areas/targets/prepare/prepare_cds/cd_download_and_clean_census_population_data.qmd

@@ -13,6 +13,7 @@ editor_options:
 
 source(here::here("R", "libraries.R"))
 source(here::here("R", "constants.R"))
+source(here::here("R", "functions.R"))
 
 # 334283385.27000004 national pop
 

tmd/areas/targets/prepare/cd_download_soi_data.qmd → tmd/areas/targets/prepare/prepare_cds/cd_download_soi_data.qmd

@@ -25,6 +25,7 @@ To re-download data and save to the "../cds/raw_data" folder, set option `eval:
 
 source(here::here("R", "libraries.R"))
 source(here::here("R", "constants.R"))
+source(here::here("R", "functions.R"))
 
 ```
 

tmd/areas/targets/prepare/cd_enhance_basefile_with_special_targets.qmd → tmd/areas/targets/prepare/prepare_cds/cd_enhance_basefile_with_special_targets.qmd

@@ -79,8 +79,7 @@ Get the unenhanced target data and the tmd2021 cached data.
 
 stack <- read_csv(fs::path(CDINTERMEDIATE, "cdbasefile_sessions.csv"))
 
-TMDDIR <- here::here("..", "..", "..", "storage", "output")
-fpath <-  fs::path(TMDDIR, "cached_allvars.csv")
+fpath <-  fs::path(TMDDATA, "cached_allvars.csv")
 tmd2021 <- vroom(fpath)
 ns(tmd2021)
 

tmd/areas/targets/prepare/cdrecipes/phase6_add_socsec.json → tmd/areas/targets/prepare/prepare_cds/cdrecipes/phase6_add_socsec.json

@@ -6,7 +6,7 @@
 	// "cdlist": "all",  // all, or a list such as ["AK00", "DE00"],
 	"cdlist": ["NY21"],   // all, or a list such as ["AK00", "DE00"],
 	// "cdlist": ["AK00", "DE00"],   // all, or a list such as ["AK00", "DE00"],
-	// "cdlist": ["AK00", "DE00", "ID01", "ID02", "ME02", "MT00", "ND00", "PA08", "SD00", "WY00"],
+  // "cdlist": ["AK00", "DE00", "ID01", "ID02", "ME02", "MT00", "ND00", "PA08", "SD00", "WY00"],
 
 	// target parameters
 	"notzero": true, // true or false
@@ -27,19 +27,19 @@
     {
       "varname": "c00100",
       "scope": 1,
-      "count": 1,
+      "count": 2,
       "fstatus": 1
     },      
     {
       "varname": "c00100",
       "scope": 1,
-      "count": 1,
+      "count": 2,
       "fstatus": 2
     },      
     {
       "varname": "c00100",
       "scope": 1,
-      "count": 1,
+      "count": 2,
       "fstatus": 4
     },          
     {

tmd/areas/targets/prepare/create_cdtargets.R → tmd/areas/targets/prepare/prepare_cds/create_cdtargets.R

@@ -1,6 +1,6 @@
 
 # run from terminal with:
-#   Rscript create_cdtargets.R phase5.json
+#   Rscript create_cdtargets.R phase6_add_socsec.json (or phase5.json)
 
 # Rscript test.r > output.log 2>&1
 
@@ -125,22 +125,18 @@ if("agi_exclude" %in% names(target_rules)){
 # target_stubs
 
 # create a dataframe to match against the stack data for targets
-vmap
+# vmap
 vmap2 <- vmap |> 
-  mutate(fstatus=case_when(basevname=="MARS1" ~ 1,
-                           basevname=="MARS2" ~ 2,
-                           basevname=="MARS4" ~ 4,
-                           .default = 0))
+  mutate(fstatus=ifelse(str_starts(basevname, "MARS"),
+                        str_sub(basevname, -1),
+                        0),
+         fstatus=as.integer(fstatus))
 
 targets_matchframe <- target_stubs |>
   mutate(sort=row_number() + 1) |> 
   rows_insert(tibble(varname="XTOT", scope=0, count=0, fstatus=0, agistub=0, sort=1),
               by="varname") |> 
   left_join(vmap2, by = join_by(varname, fstatus),  relationship = "many-to-many") |>
-  mutate(basevname = case_when(fstatus == 1 ~ "MARS1",
-                               fstatus == 2 ~ "MARS2",
-                               fstatus == 4 ~ "MARS4",
-                               .default = basevname)) |> 
   relocate(sort) |> 
   arrange(sort)
 
@@ -150,7 +146,10 @@ targets_matchframe <- target_stubs |>
 ##.. filtering Congressional districts ----
 cdlist <- unlist(cdrecipe$cdlist)
 cdlist
-if(cdlist != "all"){
+if(
+  (length(cdlist) > 1) ||
+  ((length(cdlist) ==1) && (cdlist != "all"))
+   ){
   cd_filter <- expr(statecd %in% cdlist)
 } else if(length(cdlist) == 1 & cdlist == "all") {
   cd_filter <- TRUE
@@ -185,7 +184,17 @@ mapped <- targets_matchframe |>
             relationship = "many-to-many") |> 
   arrange(statecd, sort)
 
+tmp <- stack |>
+  filter(!!cd_filter,
+         !!zero_filter,
+         !!negative_filter,
+         session %in% cdrecipe$session)
+count(tmp, basevname, vname)
+
+tmp |> 
+  filter(basevname=="v00100")
 
+count(stack, count)
 
 # checks
 # mapped |> filter(target == 0)

tmd/areas/targets/prepare/index.qmd → tmd/areas/targets/prepare/prepare_cds/index.qmd

@@ -6,12 +6,8 @@ editor_options:
 
 # Introduction {.unnumbered}
 
-This R project constructs subnational area targets for:
+This R project constructs subnational area targets for Congressional districts.
 
--   States (to come)
-
--   Congressional districts (in progress)
-
-In addition, it creates a local web page that a user can upload to a web service if desired. An in-progress version can be viewed on the web [here](https://tmd-areas-prepare-targets.netlify.app/). During development, it may not be identical to what your clone creates.
+In addition, it creates a local web page that a user can upload to a web service if desired. An in-progress version can be viewed on the web [here](https://tmd-areas-prepare-cd-targets.netlify.app/). During development, it may not be identical to what your clone creates.
 
 This R project is part of the larger tax-microdata-benchmarking project, and is in the subfolder "tmd/areas/targets/prepare/".

tmd/areas/targets/prepare/usage.qmd → tmd/areas/targets/prepare/prepare_cds/usage.qmd

@@ -43,7 +43,7 @@ At present the code prepares target files with targets we believe are useful and
 
 ## To create area weights using the target files in tax-microdata-benchmarking
 
--   copy desired target .csv files from ".../targets/prepare/cds/final/" folder to the ".../targets/" folder
+-   copy desired target .csv files from ".../targets/prepare/prepare_cds/cdtargets/" folder to the ".../targets/" folder
 -   follow tax-microdata-benchmarking instructions to run `make_all.py` or \`create_area_weights.py'
 
 ## Additional notes