Test dispersion features

dvc.lock

@@ -5,8 +5,8 @@ stages:
     deps:
     - path: pipeline/00-ingest.R
       hash: md5
-      md5: c453195da12dd0197e0bdd16f4ef3937
-      size: 23004
+      md5: 21bea1f0eda90f9b77c215e562c7af69
+      size: 23612
     params:
       params.yaml:
         assessment:
@@ -38,28 +38,28 @@ stages:
     outs:
     - path: input/assessment_data.parquet
       hash: md5
-      md5: e4b429a0121c6898b972fa20b42544fd
-      size: 425747228
+      md5: af14e5cc79bd08d679ffaa969df292c7
+      size: 427188490
     - path: input/char_data.parquet
       hash: md5
-      md5: 827c97f9d3bbd3426e8f6fd9136313f8
-      size: 847441146
+      md5: 320e9762d7244496215b0c76fd391fe4
+      size: 851611635
     - path: input/complex_id_data.parquet
       hash: md5
-      md5: 0e2a42a935106a9b6f50d8250012d98c
-      size: 703255
+      md5: c453537444b319bdd023117a4e2ec3a4
+      size: 703686
     - path: input/hie_data.parquet
       hash: md5
-      md5: ca86d0e5f29fd252455dc67e2dd40ac1
-      size: 1927927
+      md5: ca545885f4033cf366f25820f27b6a13
+      size: 1926795
     - path: input/land_nbhd_rate_data.parquet
       hash: md5
-      md5: f3ec9627322bd271bf2957b7388aaa34
-      size: 3873
+      md5: 6c1baaf2acbcba9869025bb336f4ad25
+      size: 4413
     - path: input/training_data.parquet
       hash: md5
-      md5: 76d91858f84f57ad2dce9fd292fe1ae2
-      size: 208138341
+      md5: d662d199383f18567643185cbc0f64db
+      size: 209497727
   train:
     cmd: Rscript pipeline/01-train.R
     deps:

dvc.yaml

@@ -5,17 +5,17 @@ stages:
       Ingest training and assessment data from Athena + generate townhome
       complex identifiers
     deps:
-      - pipeline/00-ingest.R
+    - pipeline/00-ingest.R
     params:
-      - assessment
-      - input
+    - assessment
+    - input
     outs:
-      - input/assessment_data.parquet
-      - input/char_data.parquet
-      - input/complex_id_data.parquet
-      - input/hie_data.parquet
-      - input/land_nbhd_rate_data.parquet
-      - input/training_data.parquet
+    - input/assessment_data.parquet
+    - input/char_data.parquet
+    - input/complex_id_data.parquet
+    - input/hie_data.parquet
+    - input/land_nbhd_rate_data.parquet
+    - input/training_data.parquet
 
     frozen: true
   train:
@@ -24,34 +24,34 @@ stages:
       Train a LightGBM model with cross-validation. Generate model objects,
       data recipes, and predictions on the test set (most recent 10% of sales)
     deps:
-      - pipeline/01-train.R
-      - input/training_data.parquet
+    - pipeline/01-train.R
+    - input/training_data.parquet
     params:
-      - cv
-      - model.engine
-      - model.hyperparameter
-      - model.objective
-      - model.parameter
-      - model.predictor
-      - model.seed
-      - model.verbose
-      - ratio_study
-      - toggle.cv_enable
+    - cv
+    - model.engine
+    - model.hyperparameter
+    - model.objective
+    - model.parameter
+    - model.predictor
+    - model.seed
+    - model.verbose
+    - ratio_study
+    - toggle.cv_enable
     outs:
-      - output/intermediate/timing/model_timing_train.parquet:
-          cache: false
-      - output/parameter_final/model_parameter_final.parquet:
-          cache: false
-      - output/parameter_range/model_parameter_range.parquet:
-          cache: false
-      - output/parameter_search/model_parameter_search.parquet:
-          cache: false
-      - output/test_card/model_test_card.parquet:
-          cache: false
-      - output/workflow/fit/model_workflow_fit.zip:
-          cache: false
-      - output/workflow/recipe/model_workflow_recipe.rds:
-          cache: false
+    - output/intermediate/timing/model_timing_train.parquet:
+        cache: false
+    - output/parameter_final/model_parameter_final.parquet:
+        cache: false
+    - output/parameter_range/model_parameter_range.parquet:
+        cache: false
+    - output/parameter_search/model_parameter_search.parquet:
+        cache: false
+    - output/test_card/model_test_card.parquet:
+        cache: false
+    - output/workflow/fit/model_workflow_fit.zip:
+        cache: false
+    - output/workflow/recipe/model_workflow_recipe.rds:
+        cache: false
 
   assess:
     cmd: Rscript pipeline/02-assess.R
@@ -60,25 +60,25 @@ stages:
       County. Also generate flags, calculate land values, and make any
       post-modeling changes
     deps:
-      - pipeline/02-assess.R
-      - input/training_data.parquet
-      - input/assessment_data.parquet
-      - input/complex_id_data.parquet
-      - input/land_nbhd_rate_data.parquet
-      - output/workflow/fit/model_workflow_fit.zip
-      - output/workflow/recipe/model_workflow_recipe.rds
+    - pipeline/02-assess.R
+    - input/training_data.parquet
+    - input/assessment_data.parquet
+    - input/complex_id_data.parquet
+    - input/land_nbhd_rate_data.parquet
+    - output/workflow/fit/model_workflow_fit.zip
+    - output/workflow/recipe/model_workflow_recipe.rds
     params:
-      - assessment
-      - pv
-      - ratio_study
-      - model.predictor.all
+    - assessment
+    - pv
+    - ratio_study
+    - model.predictor.all
     outs:
-      - output/assessment_card/model_assessment_card.parquet:
-          cache: false
-      - output/assessment_pin/model_assessment_pin.parquet:
-          cache: false
-      - output/intermediate/timing/model_timing_assess.parquet:
-          cache: false
+    - output/assessment_card/model_assessment_card.parquet:
+        cache: false
+    - output/assessment_pin/model_assessment_pin.parquet:
+        cache: false
+    - output/intermediate/timing/model_timing_assess.parquet:
+        cache: false
 
   evaluate:
     cmd: Rscript pipeline/03-evaluate.R
@@ -88,78 +88,78 @@ stages:
         2. An assessor-specific ratio study comparing estimated assessments to
            the previous year's sales
     deps:
-      - pipeline/03-evaluate.R
-      - output/test_card/model_test_card.parquet
-      - output/assessment_pin/model_assessment_pin.parquet
+    - pipeline/03-evaluate.R
+    - output/test_card/model_test_card.parquet
+    - output/assessment_pin/model_assessment_pin.parquet
     params:
-      - assessment
-      - ratio_study
+    - assessment
+    - ratio_study
     outs:
-      - output/performance/model_performance_test.parquet:
-          cache: false
-      - output/performance_quantile/model_performance_quantile_test.parquet:
-          cache: false
-      - output/performance/model_performance_assessment.parquet:
-          cache: false
-      - output/performance_quantile/model_performance_quantile_assessment.parquet:
-          cache: false
-      - output/intermediate/timing/model_timing_evaluate.parquet:
-          cache: false
+    - output/performance/model_performance_test.parquet:
+        cache: false
+    - output/performance_quantile/model_performance_quantile_test.parquet:
+        cache: false
+    - output/performance/model_performance_assessment.parquet:
+        cache: false
+    - output/performance_quantile/model_performance_quantile_assessment.parquet:
+        cache: false
+    - output/intermediate/timing/model_timing_evaluate.parquet:
+        cache: false
 
   interpret:
     cmd: Rscript pipeline/04-interpret.R
     desc: >
       Generate SHAP values for each card and feature as well as feature
       importance metrics for each feature
     deps:
-      - pipeline/04-interpret.R
-      - input/assessment_data.parquet
-      - input/training_data.parquet
-      - output/assessment_card/model_assessment_card.parquet
-      - output/workflow/fit/model_workflow_fit.zip
-      - output/workflow/recipe/model_workflow_recipe.rds
+    - pipeline/04-interpret.R
+    - input/assessment_data.parquet
+    - input/training_data.parquet
+    - output/assessment_card/model_assessment_card.parquet
+    - output/workflow/fit/model_workflow_fit.zip
+    - output/workflow/recipe/model_workflow_recipe.rds
     params:
-      - toggle.shap_enable
-      - toggle.comp_enable
-      - model.predictor.all
+    - toggle.shap_enable
+    - toggle.comp_enable
+    - model.predictor.all
     outs:
-      - output/shap/model_shap.parquet:
-          cache: false
-      - output/feature_importance/model_feature_importance.parquet:
-          cache: false
-      - output/intermediate/timing/model_timing_interpret.parquet:
-          cache: false
-      - output/comp/model_comp.parquet:
-          cache: false
+    - output/shap/model_shap.parquet:
+        cache: false
+    - output/feature_importance/model_feature_importance.parquet:
+        cache: false
+    - output/intermediate/timing/model_timing_interpret.parquet:
+        cache: false
+    - output/comp/model_comp.parquet:
+        cache: false
 
   finalize:
     cmd: Rscript pipeline/05-finalize.R
     desc: >
       Save run timings and run metadata to disk and render a performance report
       using Quarto.
     deps:
-      - pipeline/05-finalize.R
-      - output/intermediate/timing/model_timing_train.parquet
-      - output/intermediate/timing/model_timing_assess.parquet
-      - output/intermediate/timing/model_timing_evaluate.parquet
-      - output/intermediate/timing/model_timing_interpret.parquet
+    - pipeline/05-finalize.R
+    - output/intermediate/timing/model_timing_train.parquet
+    - output/intermediate/timing/model_timing_assess.parquet
+    - output/intermediate/timing/model_timing_evaluate.parquet
+    - output/intermediate/timing/model_timing_interpret.parquet
     params:
-      - run_note
-      - toggle
-      - input
-      - cv
-      - model
-      - pv
-      - ratio_study
+    - run_note
+    - toggle
+    - input
+    - cv
+    - model
+    - pv
+    - ratio_study
     outs:
-      - output/intermediate/timing/model_timing_finalize.parquet:
-          cache: false
-      - output/timing/model_timing.parquet:
-          cache: false
-      - output/metadata/model_metadata.parquet:
-          cache: false
-      - reports/performance/performance.html:
-          cache: false
+    - output/intermediate/timing/model_timing_finalize.parquet:
+        cache: false
+    - output/timing/model_timing.parquet:
+        cache: false
+    - output/metadata/model_metadata.parquet:
+        cache: false
+    - reports/performance/performance.html:
+        cache: false
 
   upload:
     cmd: Rscript pipeline/06-upload.R
@@ -169,25 +169,25 @@ stages:
       outputs prior to upload and attach a unique run ID. This step requires
       access to the CCAO Data AWS account, and so is assumed to be internal-only
     deps:
-      - pipeline/06-upload.R
-      - output/parameter_final/model_parameter_final.parquet
-      - output/parameter_range/model_parameter_range.parquet
-      - output/parameter_search/model_parameter_search.parquet
-      - output/workflow/fit/model_workflow_fit.zip
-      - output/workflow/recipe/model_workflow_recipe.rds
-      - output/test_card/model_test_card.parquet
-      - output/assessment_card/model_assessment_card.parquet
-      - output/assessment_pin/model_assessment_pin.parquet
-      - output/performance/model_performance_test.parquet
-      - output/performance_quantile/model_performance_quantile_test.parquet
-      - output/performance/model_performance_assessment.parquet
-      - output/performance_quantile/model_performance_quantile_assessment.parquet
-      - output/shap/model_shap.parquet
-      - output/comp/model_comp.parquet
-      - output/feature_importance/model_feature_importance.parquet
-      - output/metadata/model_metadata.parquet
-      - output/timing/model_timing.parquet
-      - reports/performance/performance.html
+    - pipeline/06-upload.R
+    - output/parameter_final/model_parameter_final.parquet
+    - output/parameter_range/model_parameter_range.parquet
+    - output/parameter_search/model_parameter_search.parquet
+    - output/workflow/fit/model_workflow_fit.zip
+    - output/workflow/recipe/model_workflow_recipe.rds
+    - output/test_card/model_test_card.parquet
+    - output/assessment_card/model_assessment_card.parquet
+    - output/assessment_pin/model_assessment_pin.parquet
+    - output/performance/model_performance_test.parquet
+    - output/performance_quantile/model_performance_quantile_test.parquet
+    - output/performance/model_performance_assessment.parquet
+    - output/performance_quantile/model_performance_quantile_assessment.parquet
+    - output/shap/model_shap.parquet
+    - output/comp/model_comp.parquet
+    - output/feature_importance/model_feature_importance.parquet
+    - output/metadata/model_metadata.parquet
+    - output/timing/model_timing.parquet
+    - reports/performance/performance.html
 
   export:
     cmd: Rscript pipeline/07-export.R
@@ -196,11 +196,11 @@ stages:
       run. NOT automatically run since it is typically only run once. Manually
       run once a model is selected
     deps:
-      - pipeline/07-export.R
+    - pipeline/07-export.R
     params:
-      - assessment.year
-      - input.min_sale_year
-      - input.max_sale_year
-      - ratio_study
-      - export
+    - assessment.year
+    - input.min_sale_year
+    - input.max_sale_year
+    - ratio_study
+    - export
     frozen: true