Update input with additional sales

dvc.lock

@@ -33,20 +33,20 @@ stages:
     outs:
     - path: input/assessment_data.parquet
       hash: md5
-      md5: b32480d27f75180149afe1b2de908037
-      size: 310404298
+      md5: c5c5b10a62f815a8b47de9101424dea6
+      size: 309845333
     - path: input/char_data.parquet
       hash: md5
-      md5: 537c278255d5721744ad8f180df22526
-      size: 618205566
+      md5: 95b41b06f03b055c8f1ba77bf80c8d30
+      size: 616908148
     - path: input/complex_id_data.parquet
       hash: md5
-      md5: 0492bec3b81f48d814bfedb9d9f893e0
-      size: 703076
+      md5: d0b2c6cb1dbf8ae90de2ccee2e99568d
+      size: 702334
     - path: input/hie_data.parquet
       hash: md5
-      md5: 2e049a011cae0a45d2072406e95b78b7
-      size: 1925258
+      md5: 675edaaee68b015e15a9d753a3531124
+      size: 1924257
     - path: input/land_nbhd_rate_data.parquet
       hash: md5
       md5: e508daf5790982c303d6503fe1cb8e2b
@@ -56,8 +56,8 @@ stages:
       size: 2109
     - path: input/training_data.parquet
       hash: md5
-      md5: 292caca708c332ecb5acc7886ce46e80
-      size: 156692811
+      md5: 787d2c901d1d957b87ecaee83663e8e5
+      size: 163303649
   train:
     cmd: Rscript pipeline/01-train.R
     deps:

params.yaml

@@ -445,4 +445,4 @@ comp:
 # upload
 export:
   triad_code: "1"
-  run_id: "2024-02-06-relaxed-tristan"
+  run_id: "2024-03-17-stupefied-maya"

pipeline/02-assess.R

@@ -350,6 +350,11 @@ sales_data_ratio_study <- sales_data %>%
   # For ratio studies, we don't want to include outliers
   filter(!sv_is_outlier) %>%
   filter(meta_year == params$assessment$data_year) %>%
+  # Kludge to remove some sales that somehow appear to be for a single card
+  # on a multi-card PIN. Will need to go back and hand validate these
+  filter(
+    !meta_sale_document_num %in% c("2335646020", "2312245016")
+  ) %>%
   group_by(meta_pin) %>%
   filter(meta_sale_date == max(meta_sale_date)) %>%
   distinct(

reports/_setup.qmd

@@ -1,6 +1,6 @@
 ---
 params:
-  run_id: "2024-02-06-relaxed-tristan"
+  run_id: "2024-03-17-stupefied-maya"
   year: "2024"
 ---
 

reports/performance/performance.qmd

@@ -20,7 +20,7 @@ knitr:
     out.width: "100%"
 editor: source
 params:
-  run_id: "2024-02-06-relaxed-tristan"
+  run_id: "2024-03-17-stupefied-maya"
   year: "2024"
 ---