medium model with scenario and upgraded autogluon

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
@@ -45,12 +85,21 @@ stages:
         default.prepare_data.output_dataclient_type: local
         default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet
         default.prepare_data.output_train_filepath: ./data/prepared_data/train.parquet
+<<<<<<< HEAD
         default.prepare_data.train_proportion: 0.9
     outs:
     - path: data/prepared_data/
       hash: md5
       md5: efa416abea618ae6220a0c3d597603cf.dir
       size: 44750997
+=======
+        default.prepare_data.train_proportion: 0.98
+    outs:
+    - path: data/prepared_data/
+      hash: md5
+      md5: 544427230544c2cc526334e246db4845.dir
+      size: 26132493
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -61,8 +110,13 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
+<<<<<<< HEAD
       md5: efa416abea618ae6220a0c3d597603cf.dir
       size: 44750997
+=======
+      md5: 544427230544c2cc526334e246db4845.dir
+      size: 26132493
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -94,6 +148,7 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
+<<<<<<< HEAD
       md5: de46250d454c4d713ab580b10ff3fd31.dir
       size: 3349318
       nfiles: 1
@@ -106,6 +161,20 @@ stages:
       hash: md5
       md5: 8a952a5e884c268e6059357a627b9251
       size: 224
+=======
+      md5: 8f9e2059782dd55d3ecdad54b4551f6a.dir
+      size: 3630849
+      nfiles: 1
+    - path: data/model/
+      hash: md5
+      md5: e031eb3c3fdb63917aabfea745b56ac6.dir
+      size: 618445494
+      nfiles: 31
+    - path: metrics/fit_metrics.json
+      hash: md5
+      md5: e68009f5b66230b3ee4cd2ffc9a2d697
+      size: 222
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,6 +184,7 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
+<<<<<<< HEAD
       md5: 18bd7a93ece75a65d3a950b7dfdab4fb.dir
       size: 735951861
       nfiles: 35
@@ -122,6 +192,15 @@ stages:
       hash: md5
       md5: efa416abea618ae6220a0c3d597603cf.dir
       size: 44750997
+=======
+      md5: e031eb3c3fdb63917aabfea745b56ac6.dir
+      size: 618445494
+      nfiles: 31
+    - path: data/prepared_data
+      hash: md5
+      md5: 544427230544c2cc526334e246db4845.dir
+      size: 26132493
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,8 +212,13 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
+<<<<<<< HEAD
       md5: 07ef721a0dc94a52e3ba7a70ac45b8ff.dir
       size: 463563
+=======
+      md5: 1c14c9ac9711f5d33a60890e3ca72454.dir
+      size: 90361
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -145,6 +229,7 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
+<<<<<<< HEAD
       md5: 07ef721a0dc94a52e3ba7a70ac45b8ff.dir
       size: 463563
       nfiles: 1
@@ -152,6 +237,15 @@ stages:
       hash: md5
       md5: efa416abea618ae6220a0c3d597603cf.dir
       size: 44750997
+=======
+      md5: 1c14c9ac9711f5d33a60890e3ca72454.dir
+      size: 90361
+      nfiles: 1
+    - path: data/prepared_data
+      hash: md5
+      md5: 544427230544c2cc526334e246db4845.dir
+      size: 26132493
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,25 +255,55 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
+<<<<<<< HEAD
       md5: 9f863f47799d42c101eba3b03a179455
       size: 224
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
+=======
+      md5: 98e59ea9569522a8665c4e6c1bea7473
+      size: 222
+  startup_cleanup:
+    cmd: python 0_startup_cleanup.py
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
+    deps:
+    - path: 5_generate_scenarios.py
+      hash: md5
+      md5: 30f80ffeb6ee50c5f7b82943a4dc7702
+      size: 4014
+    params:
+<<<<<<< HEAD
+=======
+      configs/settings.yaml:
+        default.startup_cleanup.artefacts: ./data
+        default.startup_cleanup.metrics: ./metrics
+  generate_scenerio_metrics:
+    cmd: python 5_generate_scenarios.py
     deps:
     - path: 5_generate_scenarios.py
       hash: md5
       md5: 30f80ffeb6ee50c5f7b82943a4dc7702
       size: 4014
     params:
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
       configs/scenarios.yaml:
         default.scenarios:
           input_dataclient_type: aws-s3
           output_dataclient_type: local
           scenario_data_filepaths:
+<<<<<<< HEAD
           - s3://retrofit-data-dev/scenario_data/24-03-2024-20-23-25/recommendations_scoring_data.parquet
+=======
+          - s3://retrofit-data-dev/scenario_data/recommendations_scoring_data.parquet
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23
           output_filepath: ./metrics/scenario_table.md
     outs:
     - path: metrics/scenario_table.md
       hash: md5
+<<<<<<< HEAD
       md5: 54856c66fca8b2ebd1fa4dea2d25734a
       size: 2133
+=======
+      md5: 3ee1966a06c1e5b9c37797597be94797
+      size: 1648
+>>>>>>> d5f40a8eb294924e0525904d6ee1864999d77c23