Merge pull request #124 from Hestia-Homes/lighting-dev-model

test lighting model

.github/workflows/Deploy.yml

@@ -2,7 +2,7 @@ name: Sap Change Model Deploy
 
 on:
   push:
-    branches: [ sap-dev, sap-prod, heat-dev, heat-prod, carbon-dev, carbon-prod]
+    branches: [ sap-dev, sap-prod, heat-dev, heat-prod, carbon-dev, carbon-prod, lighting-dev, lighting-prod ]
 
 jobs:
   deploy:

.github/workflows/MLPipelinePostMerge.yml

@@ -13,6 +13,7 @@ on:
       - "sap-dev"
       - "heat-dev"
       - "carbon-dev"
+      - "lighting-dev"
 
 permissions: write-all
 

.github/workflows/MLPipelinePullRequest.yml

@@ -5,7 +5,7 @@ on:
   #   branches:
   #     - "model-**"
   pull_request:
-    branches: ["sap-dev", "heat-dev", "carbon-dev"]
+    branches: ["sap-dev", "heat-dev", "carbon-dev", "lighting-dev"]
   label:
     types: ["created", "edited"]
 

modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py

@@ -30,6 +30,6 @@ def clip_predictions_to_minimum_value(
 
 
 post_prediction_logic = {
-    "clip_predictions_to_minimum_value": clip_predictions_to_minimum_value,
+    # "clip_predictions_to_minimum_value": clip_predictions_to_minimum_value,
     # "round_predictions": round_predictions
 }

modules/ml-pipeline/src/pipeline/configs/scenarios.yaml

@@ -8,6 +8,6 @@ default:
       # - s3://retrofit-data-dev/scenario_data/27-03-2024-11-38-15/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/26-05-2024-08-47-45/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/26-05-2024-10-44-53/recommendations_scoring_data.parquet
-      - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
+      # - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
     comparison_output_filepath: ./metrics/scenario_table.md
     metrics_output_filepath: ./metrics/scenario_metrics.md

modules/ml-pipeline/src/pipeline/configs/settings.yaml

@@ -21,7 +21,8 @@ default:
     # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet
     # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-25-08-36-36/dataset_rooms.parquet
     # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-26-10-31-39/dataset_rooms.parquet
-    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-07-03-23-11-39/dataset_rooms.parquet
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
@@ -31,11 +32,13 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
+      target: lighting_cost_ending
       identifier_columns: ["uprn"]
       # drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending"]
       drop_columns: [
-        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending",
+        "sap_ending", "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", 
+        "heating_cost_ending", "hot_water_cost_ending",
+        # "days_to_starting", "days_to_ending",
         'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', 'number_heated_rooms_ending',
         'number_habitable_rooms', 'number_heated_rooms']
       retain_features: null

modules/ml-pipeline/src/pipeline/dvc.lock

@@ -21,13 +21,14 @@ stages:
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
+        - sap_ending
         - heat_demand_change
         - carbon_change
         - rdsap_change
         - heat_demand_ending
         - carbon_ending
-        - days_to_starting
+        - heating_cost_ending
-        - days_to_ending
+        - hot_water_cost_ending
         - number_habitable_rooms_starting
         - number_habitable_rooms_ending
         - number_heated_rooms_starting
@@ -37,10 +38,10 @@ stages:
         default.feature_processor.feature_processor_config.retain_features:
         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
+        default.feature_processor.feature_processor_config.target: lighting_cost_ending
         default.feature_processor.feature_processor_type: dataframe
         default.prepare_data.data_filepath: 
-          s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
+          s3://retrofit-data-dev/sap_change_model/2024-07-03-23-11-39/dataset_rooms.parquet
         default.prepare_data.input_dataclient_type: aws-s3
         default.prepare_data.output_dataclient_type: local
         default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet
@@ -49,8 +50,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: 0f11a02cf75c0421757c0b26184cec33.dir
-      size: 45056059
+      size: 48971227
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -61,8 +62,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: 0f11a02cf75c0421757c0b26184cec33.dir
-      size: 45056059
+      size: 48971227
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -94,18 +95,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
+      md5: 36c41f88681ab90668c17ce63fd9c318.dir
-      size: 3349989
+      size: 3444201
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
+      md5: bb9c3f1538e02e20e918ec36a0b7546f.dir
-      size: 773523079
+      size: 754271944
-      nfiles: 36
+      nfiles: 37
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
+      md5: 16ae1efa8ac48d8ed978bb3fa67be64a
-      size: 224
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,13 +116,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
+      md5: bb9c3f1538e02e20e918ec36a0b7546f.dir
-      size: 773523079
+      size: 754271944
-      nfiles: 36
+      nfiles: 37
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: 0f11a02cf75c0421757c0b26184cec33.dir
-      size: 45056059
+      size: 48971227
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,8 +134,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      md5: 50909a5b19c2551410e921dc9a92bef7.dir
-      size: 463197
+      size: 480359
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -145,13 +146,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      md5: 50909a5b19c2551410e921dc9a92bef7.dir
-      size: 463197
+      size: 480359
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: 0f11a02cf75c0421757c0b26184cec33.dir
-      size: 45056059
+      size: 48971227
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,8 +162,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3e08df02fd5c5d094bcf936e1338d596
+      md5: d74767b34a1042c9ab0e3d6535791be6
-      size: 223
+      size: 224
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
@@ -176,15 +177,14 @@ stages:
           input_dataclient_type: aws-s3
           output_dataclient_type: local
           scenario_data_filepaths:
-          - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
           comparison_output_filepath: ./metrics/scenario_table.md
           metrics_output_filepath: ./metrics/scenario_metrics.md
     outs:
     - path: metrics/scenario_metrics.md
       hash: md5
-      md5: fa4d6d7bbd7818613800da5f8f37ea96
+      md5: d41d8cd98f00b204e9800998ecf8427e
-      size: 363
+      size: 0
     - path: metrics/scenario_table.md
       hash: md5
-      md5: d6baf100a1623cc2467c2f8221d314c9
+      md5: d41d8cd98f00b204e9800998ecf8427e
-      size: 2133
+      size: 0