From f43d0774798c0f0042e36e4f4a36d70720a905ac Mon Sep 17 00:00:00 2001
From: Michael Duong <michaelduong22@gmail.com>
Date: Mon, 22 Apr 2024 19:10:40 +0100
Subject: [PATCH] use previous model with new downstream processes

---
 modules/ml-pipeline/src/pipeline/dvc.lock | 94 ++++++++++++++++-------
 1 file changed, 67 insertions(+), 27 deletions(-)

diff --git a/modules/ml-pipeline/src/pipeline/dvc.lock b/modules/ml-pipeline/src/pipeline/dvc.lock
index ca4bfdd..104dc83 100644
--- a/modules/ml-pipeline/src/pipeline/dvc.lock
+++ b/modules/ml-pipeline/src/pipeline/dvc.lock
@@ -35,6 +35,46 @@ stages:
         - number_habitable_rooms
         - number_heated_rooms
         default.feature_processor.feature_processor_config.retain_features:
+        - uprn
+        - sap_starting
+        - hot_water_energy_eff_ending
+        - mainheat_energy_eff_ending
+        - constituency
+        - roof_energy_eff_ending
+        - walls_energy_eff_ending
+        - secondheat_description_ending
+        - property_type
+        - mainheatc_energy_eff_ending
+        - built_form
+        - walls_insulation_thickness_ending
+        - potential_energy_efficiency
+        - transaction_type_ending
+        - floor_thermal_transmittance_ending
+        - low_energy_lighting_ending
+        - heat_demand_starting
+        - photo_supply_ending
+        - carbon_starting
+        - walls_thermal_transmittance_ending
+        - roof_insulation_thickness_ending
+        - total_floor_area_ending
+        - number_open_fireplaces_ending
+        - windows_energy_eff_ending
+        - floor_height_ending
+        - extension_count_ending
+        - has_air_source_heat_pump_ending
+        - charging_system_ending
+        - construction_age_band
+        - glazed_type_ending
+        - roof_thermal_transmittance_ending
+        - floor_insulation_thickness_ending
+        - has_mains_gas_ending
+        - estimated_perimeter_starting
+        - energy_consumption_potential
+        - environment_impact_potential
+        - heater_type_ending
+        - multi_glaze_proportion_ending
+        - lighting_energy_eff_ending
+        - fixed_lighting_outlets_count
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
         default.feature_processor.feature_processor_config.target: sap_ending
@@ -49,8 +89,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: a1ff276b1cbd2db0b8e2982cfd524b40.dir
-      size: 44713582
+      md5: efa416abea618ae6220a0c3d597603cf.dir
+      size: 44750997
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -61,8 +101,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: a1ff276b1cbd2db0b8e2982cfd524b40.dir
-      size: 44713582
+      md5: efa416abea618ae6220a0c3d597603cf.dir
+      size: 44750997
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -94,18 +134,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 750cd7426e2909ed36bc05601b5e04c4.dir
-      size: 3349190
+      md5: de46250d454c4d713ab580b10ff3fd31.dir
+      size: 3349318
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: aa5eb60be553f2a01e63783cf8f1fad1.dir
-      size: 765461992
-      nfiles: 36
+      md5: 18bd7a93ece75a65d3a950b7dfdab4fb.dir
+      size: 735951861
+      nfiles: 35
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: ca5190b3292210c57a58668fdb48296c
-      size: 226
+      md5: 8a952a5e884c268e6059357a627b9251
+      size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,13 +155,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: aa5eb60be553f2a01e63783cf8f1fad1.dir
-      size: 765461992
-      nfiles: 36
+      md5: 18bd7a93ece75a65d3a950b7dfdab4fb.dir
+      size: 735951861
+      nfiles: 35
     - path: data/prepared_data
       hash: md5
-      md5: a1ff276b1cbd2db0b8e2982cfd524b40.dir
-      size: 44713582
+      md5: efa416abea618ae6220a0c3d597603cf.dir
+      size: 44750997
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,8 +173,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 934c94e5b1a2c70db3dc865ee056f460.dir
-      size: 463619
+      md5: 07ef721a0dc94a52e3ba7a70ac45b8ff.dir
+      size: 463563
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -145,13 +185,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 934c94e5b1a2c70db3dc865ee056f460.dir
-      size: 463619
+      md5: 07ef721a0dc94a52e3ba7a70ac45b8ff.dir
+      size: 463563
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: a1ff276b1cbd2db0b8e2982cfd524b40.dir
-      size: 44713582
+      md5: efa416abea618ae6220a0c3d597603cf.dir
+      size: 44750997
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,15 +201,15 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: aa2a511ac759225549636ba05d6b667c
+      md5: 9f863f47799d42c101eba3b03a179455
       size: 224
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
     - path: 5_generate_scenarios.py
       hash: md5
-      md5: 40506749fefd926d47c60ff5b16db307
-      size: 5337
+      md5: a18f6c6ae2082f038df47386cf3e418e
+      size: 4896
     params:
       configs/scenarios.yaml:
         default.scenarios:
@@ -182,9 +222,9 @@ stages:
     outs:
     - path: metrics/scenario_metrics.md
       hash: md5
-      md5: 4085a6ea3d044ad2fe7ac63b0a685fed
+      md5: 64e7db945ff655ae03c20c9845f19106
       size: 363
     - path: metrics/scenario_table.md
       hash: md5
-      md5: a2b3da77921b5dcc10f7068646e0eae3
+      md5: d4f8afe07b774374aeaa48f1b7b8a5fc
       size: 2133