MODEL_REGISTRY.md

@@ -24,9 +24,9 @@
         "active": true
     },
     "carbon": {
-        "version": "v0.6.0",
+        "version": "v0.5.0",
         "stage": {
-            "dev": "v0.6.0"
+            "dev": "v0.5.0"
         },
         "registered": true,
         "active": true

deployment/Dockerfile.prediction.lambda

@@ -13,11 +13,7 @@ RUN yum install -y gcc python3-devel gcc-c++
 
 # Install python packages
 COPY modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt ./requirements.txt
-
-RUN pip install uv
-
-RUN uv pip install -r requirements.txt --system
-# RUN pip install --no-cache-dir -r ./requirements.txt
+RUN pip install --no-cache-dir -r ./requirements.txt
 
 # Copy the project code
 COPY modules/ml-pipeline/src/pipeline ./pipeline

modules/ml-pipeline/src/Prediction.Dockerfile

@@ -5,11 +5,8 @@ RUN apt-get update && apt-get install -y libgomp1 gcc python3-dev
 
 COPY pipeline/requirements/predictions/requirements.txt requirements.txt
 
-RUN pip install uv
-
-RUN uv pip install -r requirements.txt --system
-
-# RUN pip install -r requirements.txt
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
 
 # Assuming in the CI/CD step, there will be a dvc pull step to get data and model, so will just need to run a single script
 COPY pipeline/ /home/pipeline/

modules/ml-pipeline/src/README.md

@@ -1,3 +1,3 @@
-# The generic reproducible ML-pipeline!
+# The generic reproducible ML-pipeline
 
 Pipeline required to build a model to produce an output, that gets hashed via DVC

modules/ml-pipeline/src/pipeline/.gitignore

@@ -1,4 +1,3 @@
 
 # Ignore dynaconf secret files
 .secrets.*
-example.py

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

@@ -18,44 +18,30 @@ def remove_starting_columns(df):
     return df
 
 
-def keep_negative_heat_change(df):
-    df = df[df["heat_demand_change"] < 0]
+def remove_floor_height_ending(df):
+    # df.describe(percentiles=[0.005,0.99])['FLOOR_HEIGHT_ENDING']
+    # shows bottom 0.5 percentile is 1.665
+    # So keep anything above this
+    df = df[df["floor_height_ending"] > 1.665].reset_index(drop=True)
+    print("we in here")
     return df
 
 
-def keep_non_negative_carbon_ending(df):
-    df = df[df["carbon_ending"] > 0]
+def remove_minimum_habitable_room_size(df):
+    # Need minimum of 6.5m per habitable room
+    df = df[
+        df["total_floor_area_ending"] / df["number_habitable_rooms"] > 6.5
+    ].reset_index(drop=True)
     return df
 
 
-def keep_negative_carbon_change(df):
-    df = df[df["carbon_change"] < 0]
+def keep_flats(df):
+    df = df[df["property_type"] == "Flat"]
     return df
 
 
-# TODO: Move to ETL pipeline
-def remove_unreasonable_habitable_rooms(df):
-    """
-    Assumption is that proportion of floor area to habitable rooms should be at least 6.5m2
-    """
-    minimum_room_size_index = (
-        df["total_floor_area_ending"] / df["number_habitable_rooms"] >= 6.5
-    )
-    df = df[minimum_room_size_index]
-    return df
-
-
-def remove_top_1_percent_heat_demand(df):
-    # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
-    threshold_value = 860
-    df = df[df["heat_demand_starting"] < threshold_value]
-    return df
-
-
-def remove_top_1_percent_carbon(df):
-    # threshold_value = df.describe(percentiles=[0.99])['CARBON_STARTING']['99%']
-    threshold_value = 18
-    df = df[df["carbon_starting"] < threshold_value]
+def keep_non_zero_rdsap(df):
+    df = df[df["rdsap_change"] != 0]
     return df
 
 
@@ -68,12 +54,10 @@ def remove_top_1_percent_carbon(df):
 #     return df
 
 business_logic = {
-    "remove_unreasonable_habitable_rooms": remove_unreasonable_habitable_rooms,
-    "keep_negative_heat_change": keep_negative_heat_change,
-    "keep_negative_carbon_change": keep_negative_carbon_change,
-    "remove_top_1_percent_heat_demand": remove_top_1_percent_heat_demand,
-    "remove_top_1_percent_carbon": remove_top_1_percent_carbon,
-    "keep_non_negative_carbon_ending": keep_non_negative_carbon_ending,
+    # "keep_non_zero_rdsap": keep_non_zero_rdsap,
+    # "keep_flats": keep_flats,
+    # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,
+    # "remove_floor_height_ending": remove_floor_height_ending
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

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

@@ -1,24 +1,23 @@
 """
 After predictions, we may want to apply some post processing to the predictions
 """
-
 import pandas as pd
 
 
 def clip_predictions_to_minimum_value(
-    data: pd.DataFrame,
-    predictions: pd.Series,
+    data: pd.DataFrame, predictions: pd.Series, minimum_value: int = 0
 ) -> pd.Series:
 
     series_name = predictions.name
     predictions.name = "predictions"
-    predictions = predictions.astype(data["carbon_starting"].dtype)
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
-    replace_index = predictions_df["predictions"] > predictions_df["carbon_starting"]
-    predictions_df.loc[replace_index, "predictions"] = predictions_df.loc[
-        replace_index, "carbon_starting"
-    ]
+    replace_index = (
+        predictions_df["sap_starting"] + minimum_value > predictions_df["predictions"]
+    )
+    predictions_df.loc[replace_index, "predictions"] = (
+        predictions_df.loc[replace_index, "sap_starting"] + minimum_value
+    )
 
     predictions_new = predictions_df["predictions"]
     predictions_new.name = series_name

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

@@ -18,8 +18,10 @@ default:
   prepare_data:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
-    # 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/2024-10-03-22-57-23/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
@@ -29,14 +31,13 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: carbon_ending
+      target: sap_ending
       identifier_columns: ["uprn"]
-      # drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_ending"]
+      # 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", "sap_ending", "days_to_starting", "days_to_ending",
+        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_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', 'lighting_cost_starting', 'lighting_cost_ending', 'heating_cost_starting', 'heating_cost_ending', 'hot_water_cost_starting', 'hot_water_cost_ending',]
-      # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
+        'number_habitable_rooms', 'number_heated_rooms']
       retain_features: null
       # retain_features: ['uprn', 'sap_starting', 'hot_water_energy_eff_ending',
       #  'mainheat_energy_eff_ending', 'constituency', 'roof_energy_eff_ending',

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

@@ -25,7 +25,7 @@ stages:
         - carbon_change
         - rdsap_change
         - heat_demand_ending
-        - sap_ending
+        - carbon_ending
         - days_to_starting
         - days_to_ending
         - number_habitable_rooms_starting
@@ -34,19 +34,13 @@ stages:
         - number_heated_rooms_ending
         - number_habitable_rooms
         - number_heated_rooms
-        - lighting_cost_starting
-        - lighting_cost_ending
-        - heating_cost_starting
-        - heating_cost_ending
-        - hot_water_cost_starting
-        - hot_water_cost_ending
         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: carbon_ending
+        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/2024-10-03-22-57-23/dataset_rooms.parquet
+        default.prepare_data.data_filepath:
+          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
@@ -55,8 +49,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: f96aaa1181655a1bef313542f037b346.dir
-      size: 40772097
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      size: 45056059
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -67,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: f96aaa1181655a1bef313542f037b346.dir
-      size: 40772097
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      size: 45056059
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -100,18 +94,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 821aace9a1dfb8b2adb507f4d7e6b36b.dir
-      size: 3995384
+      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
+      size: 3349989
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: fde129c8b8610bdaecc3d28f4cfc6608.dir
-      size: 751284807
+      md5: 13c3100e1486c27a83a8a47491077842.dir
+      size: 773523079
       nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 471606cbb7d4f3e62fb94b493d3ec858
-      size: 227
+      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
+      size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -121,13 +115,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: fde129c8b8610bdaecc3d28f4cfc6608.dir
-      size: 751284807
+      md5: 13c3100e1486c27a83a8a47491077842.dir
+      size: 773523079
       nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: f96aaa1181655a1bef313542f037b346.dir
-      size: 40772097
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -139,8 +133,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 985d380681ab1f7645015a67b695b633.dir
-      size: 557231
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      size: 463197
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -151,13 +145,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 985d380681ab1f7645015a67b695b633.dir
-      size: 557231
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      size: 463197
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: f96aaa1181655a1bef313542f037b346.dir
-      size: 40772097
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -167,8 +161,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 9cc5f3a42681b321c26c414589ba561e
-      size: 226
+      md5: 3e08df02fd5c5d094bcf936e1338d596
+      size: 223
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
@@ -182,14 +176,15 @@ 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: d41d8cd98f00b204e9800998ecf8427e
-      size: 0
+      md5: fa4d6d7bbd7818613800da5f8f37ea96
+      size: 363
     - path: metrics/scenario_table.md
       hash: md5
-      md5: d41d8cd98f00b204e9800998ecf8427e
-      size: 0
+      md5: d6baf100a1623cc2467c2f8221d314c9
+      size: 2133