Merge branch '2025-assessment-year' into 7-revisit-condo-strata-imput…

…ation
ccao-data · Jan 16, 2025 · 155fffc · 155fffc
2 parents 9efaac3 + 30f3b60
commit 155fffc
Show file tree

Hide file tree

Showing 12 changed files with 403 additions and 205 deletions.
diff --git a/dvc.lock b/dvc.lock
diff --git a/params.yaml b/params.yaml
@@ -168,28 +168,32 @@ model:
       - "prox_num_pin_in_half_mile"
       - "prox_num_bus_stop_in_half_mile"
       - "prox_num_foreclosure_per_1000_pin_past_5_years"
-      - "prox_num_school_in_half_mile"
       - "prox_airport_dnl_total"
       - "prox_nearest_bike_trail_dist_ft"
       - "prox_nearest_cemetery_dist_ft"
       - "prox_nearest_cta_route_dist_ft"
       - "prox_nearest_cta_stop_dist_ft"
       - "prox_nearest_hospital_dist_ft"
       - "prox_lake_michigan_dist_ft"
-      - "prox_nearest_major_road_dist_ft"
       - "prox_nearest_metra_route_dist_ft"
       - "prox_nearest_metra_stop_dist_ft"
       - "prox_nearest_park_dist_ft"
       - "prox_nearest_railroad_dist_ft"
-      - "prox_nearest_secondary_road_dist_ft"
       - "prox_nearest_university_dist_ft"
       - "prox_nearest_vacant_land_dist_ft"
       - "prox_nearest_water_dist_ft"
       - "prox_nearest_golf_course_dist_ft"
+      - "prox_nearest_road_highway_dist_ft"
+      - "prox_nearest_road_arterial_dist_ft"
+      - "prox_nearest_road_collector_dist_ft"
+      - "prox_nearest_road_highway_daily_traffic"
+      - "prox_nearest_road_arterial_daily_traffic"
+      - "prox_nearest_road_collector_daily_traffic"
+      - "prox_nearest_new_construction_dist_ft"
+      - "prox_nearest_stadium_dist_ft"
       - "acs5_percent_age_children"
       - "acs5_percent_age_senior"
       - "acs5_median_age_total"
-      - "acs5_percent_mobility_moved_from_other_state"
       - "acs5_percent_household_family_married"
       - "acs5_percent_household_nonfamily_alone"
       - "acs5_percent_education_high_school"
@@ -203,11 +207,8 @@ model:
       - "acs5_median_household_total_occupied_year_built"
       - "acs5_median_household_renter_occupied_gross_rent"
       - "acs5_percent_household_owner_occupied"
-      - "acs5_percent_household_total_occupied_w_sel_cond"
-      - "acs5_percent_mobility_moved_in_county"
       - "other_tax_bill_rate"
       - "ccao_is_active_exe_homeowner"
-      - "ccao_is_corner_lot"
       - "ccao_n_years_exe_homeowner"
       - "time_sale_year"
       - "time_sale_day"
@@ -217,6 +218,12 @@ model:
       - "time_sale_day_of_month"
       - "time_sale_day_of_week"
       - "time_sale_post_covid"
+      - "shp_parcel_centroid_dist_ft_sd"
+      - "shp_parcel_edge_len_ft_sd"
+      - "shp_parcel_interior_angle_sd"
+      - "shp_parcel_mrr_area_ratio"
+      - "shp_parcel_mrr_side_ratio"
+      - "shp_parcel_num_vertices"
       - "meta_strata_1"
       - "meta_strata_2"
 
@@ -390,4 +397,4 @@ ratio_study:
 # upload
 export:
   triad_code: "1"
-  run_id: "2024-03-11-pensive-manasi"
+  run_id: "2025-01-11-practical-tristan"
diff --git a/pipeline/05-finalize.R b/pipeline/05-finalize.R
@@ -16,6 +16,8 @@ purrr::walk(list.files("R/", "\\.R$", full.names = TRUE), source)
 set.seed(NULL)
 
 
+
+
 #- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
 # 2. Save Metadata -------------------------------------------------------------
 #- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

diff --git a/renv.lock b/renv.lock
@@ -1,6 +1,6 @@
 {
   "R": {
-    "Version": "4.4.1",
+    "Version": "4.4.2",
     "Repositories": [
       {
         "Name": "CRAN",
@@ -279,11 +279,11 @@
       "Version": "1.3.0",
       "Source": "GitHub",
       "RemoteType": "github",
+      "RemoteHost": "api.github.com",
       "RemoteUsername": "ccao-data",
       "RemoteRepo": "ccao",
       "RemoteRef": "master",
-      "RemoteSha": "6445f79e6b4207a174c22d7a139511cf8e2516b6",
-      "RemoteHost": "api.github.com",
+      "RemoteSha": "8b6f53e14c1732fcec5f6982fbc4bfb32f45f194",
       "Requirements": [
         "R",
         "assessr",
@@ -292,11 +292,11 @@
         "rlang",
         "tidyr"
       ],
-      "Hash": "d452fba08dff15c8379f18aa03af084e"
+      "Hash": "1663306aa228ded9892f07d65ec20db3"
     },
     "class": {
       "Package": "class",
-      "Version": "7.3-22",
+      "Version": "7.3-23",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
@@ -305,7 +305,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "f91f6b29f38b8c280f2b9477787d4bb2"
+      "Hash": "d0cb9cc838c3b43560bd958fc4317fdc"
     },
     "cli": {
       "Package": "cli",
@@ -1044,15 +1044,15 @@
     },
     "nnet": {
       "Package": "nnet",
-      "Version": "7.3-19",
+      "Version": "7.3-20",
       "Source": "Repository",
       "Repository": "CRAN",
       "Requirements": [
         "R",
         "stats",
         "utils"
       ],
-      "Hash": "2c797b46eea7fb58ede195bc0b1f1138"
+      "Hash": "c955edf99ff24a32e96bd0a22645af60"
     },
     "numDeriv": {
       "Package": "numDeriv",

diff --git a/renv/profiles/reporting/renv.lock b/renv/profiles/reporting/renv.lock
@@ -1,6 +1,6 @@
 {
   "R": {
-    "Version": "4.4.1",
+    "Version": "4.4.2",
     "Repositories": [
       {
         "Name": "CRAN",
@@ -39,20 +39,20 @@
     },
     "KernSmooth": {
       "Package": "KernSmooth",
-      "Version": "2.23-24",
+      "Version": "2.23-26",
       "Source": "Repository",
-      "Repository": "CRAN",
+      "Repository": "RSPM",
       "Requirements": [
         "R",
         "stats"
       ],
-      "Hash": "9f33a1ee37bbe8919eb2ec4b9f2473a5"
+      "Hash": "2fb39782c07b5ad422b0448ae83f64c4"
     },
     "MASS": {
       "Package": "MASS",
-      "Version": "7.3-61",
+      "Version": "7.3-64",
       "Source": "Repository",
-      "Repository": "CRAN",
+      "Repository": "RSPM",
       "Requirements": [
         "R",
         "grDevices",
@@ -61,7 +61,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "0cafd6f0500e5deba33be22c46bf6055"
+      "Hash": "49d2d8090b74c1179df1aff16201caf8"
     },
     "Matrix": {
       "Package": "Matrix",
@@ -257,7 +257,7 @@
     },
     "class": {
       "Package": "class",
-      "Version": "7.3-22",
+      "Version": "7.3-23",
       "Source": "Repository",
       "Repository": "RSPM",
       "Requirements": [
@@ -266,7 +266,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "f91f6b29f38b8c280f2b9477787d4bb2"
+      "Hash": "d0cb9cc838c3b43560bd958fc4317fdc"
     },
     "classInt": {
       "Package": "classInt",
@@ -1649,9 +1649,9 @@
     },
     "survival": {
       "Package": "survival",
-      "Version": "3.7-0",
+      "Version": "3.8-3",
       "Source": "Repository",
-      "Repository": "CRAN",
+      "Repository": "RSPM",
       "Requirements": [
         "Matrix",
         "R",
@@ -1661,7 +1661,7 @@
         "stats",
         "utils"
       ],
-      "Hash": "5aaa9cbaf4aba20f8e06fdea1850a398"
+      "Hash": "fe42836742a4f065b3f3f5de81fccab9"
     },
     "svglite": {
       "Package": "svglite",

diff --git a/reports/_setup.qmd → reports/_setup.R b/reports/_setup.qmd → reports/_setup.R
@@ -1,10 +1,3 @@
----
-params:
-  run_id: "2024-02-08-dreamy-sam"
-  year: "2024"
----
-
-```{r}
 # This setup script is run at the top of each Quarto report subsection to load
 # libraries, data, and other objects needed for the report. It only loads
 # objects if they don't already exist in the environment, so it can be run
@@ -127,12 +120,14 @@ if (!exists("model_performance_test_linear")) {
     arrow::read_parquet(paths$output$performance_test_linear$local)
 }
 if (!exists("model_performance_quantile_test")) {
+  # nolint start: object_length_linter
   model_performance_quantile_test <-
     arrow::read_parquet(paths$output$performance_quantile_test$local)
 }
 if (!exists("model_performance_quantile_test_linear")) {
   model_performance_quantile_test_linear <-
     arrow::read_parquet(paths$output$performance_quantile_test_linear$local)
+  # nolint end
 }
 if (!exists("model_performance_assessment")) {
   model_performance_assessment <-
@@ -147,7 +142,7 @@ if (!exists("feat_imp_df")) {
 }
 
 # Load SHAP data if it exists (only exists for important runs)
-if (file.exists(paths$output$shap$local) & metadata$shap_enable) {
+if (file.exists(paths$output$shap$local) && metadata$shap_enable) {
   shap_df <- read_parquet(paths$output$shap$local)
   shap_exists <- nrow(shap_df) > 0
 } else {
@@ -167,9 +162,7 @@ plot_colors <- list(
 shorten_number <- function(x) {
   scales::dollar(x, accuracy = 1, scale = 1 / 1000, suffix = "K")
 }
-```
 
-```{r}
 # Chunk to populate the metadata / dataset summaries in the text of each module
 # Anything prefixed with m_ is a variable that will be used directly in the text
 m_test_min_date <- min(test_card$meta_sale_date)
@@ -181,14 +174,18 @@ m_test_n_sales_triad <- test_card %>%
   filter(meta_triad_code == run_triad_code) %>%
   nrow() %>%
   scales::comma()
-m_test_n_sales_prop <-
-  (nrow(filter(test_card, meta_triad_code == run_triad_code)) /
-    nrow(test_card)) %>%
+m_test_n_sales_prop <- (
+  nrow(filter(test_card, meta_triad_code == run_triad_code)) /
+    nrow(test_card)
+) %>%
   scales::percent(accuracy = 0.01)
 m_test_med_sp <- test_card$meta_sale_price %>%
   median() %>%
   scales::dollar()
-m_test_split_prop <- scales::percent(1 - metadata$cv_split_prop, accuracy = 0.01)
+m_test_split_prop <- scales::percent(
+  1 - metadata$cv_split_prop,
+  accuracy = 0.01
+)
 
 m_train_min_date <- min(training_data$meta_sale_date)
 m_train_max_date <- max(training_data$meta_sale_date)
@@ -199,9 +196,10 @@ m_train_n_sales_triad <- training_data %>%
   filter(meta_triad_code == run_triad_code) %>%
   nrow() %>%
   scales::comma()
-m_train_n_sales_prop <-
-  (nrow(filter(training_data, meta_triad_code == run_triad_code)) /
-    nrow(training_data)) %>%
+m_train_n_sales_prop <- (
+  nrow(filter(training_data, meta_triad_code == run_triad_code)) /
+    nrow(training_data)
+) %>%
   scales::percent(accuracy = 0.01)
 m_train_med_sp <- training_data$meta_sale_price %>%
   median() %>%
@@ -228,4 +226,3 @@ m_assess_stage_near <- paste(
   metadata$ratio_study_near_year,
   metadata$ratio_study_near_stage
 )
-```