Fix tax bill agency name matching

Give priority to certain names on bills in the detail output and add names for TY2022
ccao-data · Jan 18, 2024 · 5317ba4 · 5317ba4
1 parent e9dd0b7
commit 5317ba4
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 6 deletions.
diff --git a/data-raw/sample_tax_bills/agency_name_match.csv b/data-raw/sample_tax_bills/agency_name_match.csv
diff --git a/data-raw/sample_tax_bills/sample_tax_bills_detail.R b/data-raw/sample_tax_bills/sample_tax_bills_detail.R
@@ -59,7 +59,10 @@ extract_tax_bill <- function(file) {
       agency_name != "",
       !str_detect(
         agency_name,
-        "TAXES|Assess|Property|EAV|Local Tax|Total Tax|Do not|Equalizer|cookcountyclerk.com"
+        paste0(
+          "TAXES|Assess|Property|EAV|Local Tax|",
+          "Total Tax|Do not|Equalizer|cookcountyclerk.com"
+        )
       )
     )
   # Create a list with metadata for output
@@ -109,7 +112,8 @@ bills_df <- bills_df %>%
   group_by(pin, year, agency_num) %>%
   mutate(across(final_tax:prev_tax, sum)) %>%
   select(-cook) %>%
-  filter(!is.na(agency_num), row_number() == 1) %>%
+  filter(!is.na(agency_num), name_priority == 1) %>%
+  select(-name_priority) %>%
   ungroup()
 
 # Round numeric values to nearest hundredth

diff --git a/data-raw/sample_tax_bills/sample_tax_bills_detail.csv b/data-raw/sample_tax_bills/sample_tax_bills_detail.csv
diff --git a/data/sample_tax_bills_detail.rda b/data/sample_tax_bills_detail.rda