Merge pull request #117 from Hestia-Homes/sap-dev

Sap dev

.dockerignore

@@ -0,0 +1,9 @@
+modules/ml-pipeline/src/pipeline/data/predictions
+modules/ml-pipeline/src/pipeline/data/fit_predictions
+modules/ml-pipeline/src/pipeline/data/prepared_data
+modules/ml-pipeline/src/pipeline/data/model/allmodels
+modules/ml-pipeline/src/pipeline/metrics
+modules/ml-pipeline/src/pipeline/__pycache__
+modules/ml-pipeline/src/pipeline/.dvc
+modules/ml-pipeline/src/pipeline/analysis
+modules/ml-pipeline/src/pipeline/metrics

.github/workflows/Deploy.yml

@@ -19,8 +19,8 @@ jobs:
 
       - name: Install Serverless and plugins
         run: |
-          npm install -g serverless
+          npm install -g serverless@^3.38.0
-          npm install -g serverless-domain-manager
+          npm install -g serverless-domain-manager@^7.3.8
 
       - name: Install DVC
         run: |

MODEL_REGISTRY.md

@@ -8,25 +8,25 @@
         "active": true
     },
     "sap": {
-        "version": "v0.10.1",
+        "version": "v0.14.0",
         "stage": {
-            "dev": "v0.10.1"
+            "dev": "v0.14.0"
         },
         "registered": true,
         "active": true
     },
     "heat": {
-        "version": "v0.4.0",
+        "version": "v0.5.0",
         "stage": {
-            "dev": "v0.4.0"
+            "dev": "v0.5.0"
         },
         "registered": true,
         "active": true
     },
     "carbon": {
-        "version": "v0.4.0",
+        "version": "v0.5.0",
         "stage": {
-            "dev": "v0.4.0"
+            "dev": "v0.5.0"
         },
         "registered": true,
         "active": true

deployment/.dockerignore

@@ -1,4 +1,9 @@
-modules/ml-pipeline/src/pipeline/data/predictions*
+modules/ml-pipeline/src/pipeline/data/predictions
-modules/ml-pipeline/src/pipeline/data/prepared_data*
+modules/ml-pipeline/src/pipeline/data/fit_predictions
-modules/ml-pipeline/src/pipeline/data/model/allmodels*
+modules/ml-pipeline/src/pipeline/data/prepared_data
-modules/ml-pipeline/src/pipeline/metrics*
+modules/ml-pipeline/src/pipeline/data/model/allmodels
+modules/ml-pipeline/src/pipeline/metrics
+modules/ml-pipeline/src/__pycache__
+modules/ml-pipeline/src/.dvc
+modules/ml-pipeline/src/analysis
+modules/ml-pipeline/src/metrics

modules/ml-pipeline/src/.dockerignore

@@ -1,4 +1,8 @@
-pipeline/data/predictions*
+pipeline/data/predictions
-pipeline/data/prepared_data/train.parquet*
+pipeline/data/fit_predictions
-pipeline/data/model/allmodels*
+pipeline/data/prepared_data/train.parquet
-pipeline/metrics*
+pipeline/data/fit_predictions
+pipeline/data/model/allmodels
+pipeline/metrics
+pipeline/.dvc
+pipeline/analysis

modules/ml-pipeline/src/Prediction.Dockerfile

@@ -1,7 +1,7 @@
 # Dockerfile that can be used to test loading a model to generate a prediction (part of CI/CD flow)
 FROM python:3.10.12-slim
 
-RUN apt-get update && apt-get install -y libgomp1
+RUN apt-get update && apt-get install -y libgomp1 gcc python3-dev
 
 COPY pipeline/requirements/predictions/requirements.txt requirements.txt
 

modules/ml-pipeline/src/pipeline/5_generate_scenarios.py

@@ -78,6 +78,18 @@ def generate_scenario_predictions(
 
     scenario_data = pd.DataFrame()
 
+    # If we have no scenario data, we can save empty dataframes
+    if scenario_data_filepaths is None:
+        logger.info("No scenario data filepaths provided")
+        output_dataclient.save_data(
+            obj=scenario_data, location=comparison_output_filepath, save_config=None
+        )
+
+        output_dataclient.save_data(
+            obj=scenario_data, location=metrics_output_filepath, save_config=None
+        )
+        return
+
     # Can have multiple scenario data files
     for scenario_data_filepath in scenario_data_filepaths:
         scenario_data = pd.concat(

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

@@ -5,6 +5,9 @@ default:
     scenario_data_filepaths:
       # - s3://retrofit-data-dev/scenario_data/22-03-2024-19-20-09/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/24-03-2024-20-23-25/recommendations_scoring_data.parquet
-      - s3://retrofit-data-dev/scenario_data/27-03-2024-11-38-15/recommendations_scoring_data.parquet
+      # - 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
     comparison_output_filepath: ./metrics/scenario_table.md
     metrics_output_filepath: ./metrics/scenario_metrics.md

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

@@ -18,7 +18,10 @@ default:
   prepare_data:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
-    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/2024-03-22-18-56-53/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
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet

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

@@ -35,52 +35,12 @@ 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
         default.feature_processor.feature_processor_type: dataframe
         default.prepare_data.data_filepath:
-          s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet
+          s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/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
@@ -89,8 +49,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: efa416abea618ae6220a0c3d597603cf.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 44750997
+      size: 45056059
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -101,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: efa416abea618ae6220a0c3d597603cf.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 44750997
+      size: 45056059
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -134,17 +94,17 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: de46250d454c4d713ab580b10ff3fd31.dir
+      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
-      size: 3349318
+      size: 3349989
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 18bd7a93ece75a65d3a950b7dfdab4fb.dir
+      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 735951861
+      size: 773523079
-      nfiles: 35
+      nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 8a952a5e884c268e6059357a627b9251
+      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
       size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
@@ -155,13 +115,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 18bd7a93ece75a65d3a950b7dfdab4fb.dir
+      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 735951861
+      size: 773523079
-      nfiles: 35
+      nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: efa416abea618ae6220a0c3d597603cf.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 44750997
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -173,8 +133,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 07ef721a0dc94a52e3ba7a70ac45b8ff.dir
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463563
+      size: 463197
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -185,13 +145,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 07ef721a0dc94a52e3ba7a70ac45b8ff.dir
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463563
+      size: 463197
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: efa416abea618ae6220a0c3d597603cf.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 44750997
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -201,30 +161,30 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 9f863f47799d42c101eba3b03a179455
+      md5: 3e08df02fd5c5d094bcf936e1338d596
-      size: 224
+      size: 223
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
     - path: 5_generate_scenarios.py
       hash: md5
-      md5: a18f6c6ae2082f038df47386cf3e418e
+      md5: 40506749fefd926d47c60ff5b16db307
-      size: 4896
+      size: 5337
     params:
       configs/scenarios.yaml:
         default.scenarios:
           input_dataclient_type: aws-s3
           output_dataclient_type: local
           scenario_data_filepaths:
-          - s3://retrofit-data-dev/scenario_data/27-03-2024-11-38-15/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
     outs:
     - path: metrics/scenario_metrics.md
       hash: md5
-      md5: 64e7db945ff655ae03c20c9845f19106
+      md5: fa4d6d7bbd7818613800da5f8f37ea96
       size: 363
     - path: metrics/scenario_table.md
       hash: md5
-      md5: d4f8afe07b774374aeaa48f1b7b8a5fc
+      md5: d6baf100a1623cc2467c2f8221d314c9
       size: 2133

modules/ml-pipeline/src/pipeline/requirements/predictions/requirements-dev.txt

@@ -1,7 +1,7 @@
 joblib==1.3.2
 boto3==1.28.17
 pandas==2.1.4
-autogluon==1.0.0
+autogluon.tabular[all]==1.0.0
 dynaconf==3.2.1
 pyarrow==13.0.0
 pre-commit==3.3.3

modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt

@@ -1,7 +1,7 @@
 joblib==1.3.2
 boto3==1.28.17
 pandas==2.1.4
-autogluon==1.0.0
+autogluon.tabular[all]==1.0.0
 dynaconf==3.2.1
 pyarrow==13.0.0
 PyYAML==6.0.1

modules/ml-pipeline/src/pipeline/requirements/training/requirements-dev.txt

@@ -1,7 +1,7 @@
 joblib==1.3.2
 boto3==1.28.17
 pandas==2.1.4
-autogluon==1.0.0
+autogluon.tabular[all]==1.0.0
 ray==2.6.3
 dynaconf==3.2.1
 alibi==0.9.5

modules/ml-pipeline/src/pipeline/requirements/training/requirements.txt

@@ -1,4 +1,4 @@
 boto3==1.28.41
 pandas==2.1.4
-autogluon==1.0.0
+autogluon.tabular[all]==1.0.0
 dynaconf==3.2.1

modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt

@@ -1,4 +1,4 @@
-dvc==3.36.0
+dvc==3.51.0
-dvc-s3==3.0.1
+dvc-s3==3.2.0
-gto==1.6.1
+gto==1.7.1
 pyOpenSSL==23.3.0