.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, heatingkwh-dev, heatingkwh-prod]
+    branches: [ sap-dev, sap-prod, heat-dev, heat-prod, carbon-dev, carbon-prod]
 
 jobs:
   deploy:

.github/workflows/MLPipelinePostMerge.yml

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

.github/workflows/MLPipelinePullRequest.yml

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

MODEL_REGISTRY.md

@@ -16,57 +16,17 @@
         "active": true
     },
     "heat": {
-        "version": "v0.6.0",
+        "version": "v0.5.0",
         "stage": {
-            "dev": "v0.6.0"
+            "dev": "v0.5.0"
         },
         "registered": true,
         "active": true
     },
     "carbon": {
-        "version": "v0.6.0",
+        "version": "v0.5.0",
         "stage": {
-            "dev": "v0.6.0"
+            "dev": "v0.5.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "hotwater": {
-        "version": "v1.0.0",
-        "stage": {
-            "dev": "v1.0.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "heating": {
-        "version": "v1.0.0",
-        "stage": {
-            "dev": "v1.0.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "lighting": {
-        "version": "v1.0.0",
-        "stage": {
-            "dev": "v1.0.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "hotwaterkwh": {
-        "version": "v1.0.0",
-        "stage": {
-            "dev": "v1.0.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "heatingkwh": {
-        "version": "v1.0.0",
-        "stage": {
-            "dev": "v1.0.0"
         },
         "registered": true,
         "active": true

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

@@ -5,18 +5,6 @@ During the feature processor step, we can apply additional business logic and fe
 """
 Business Logic dict + functions
 """
-import pandas as pd
-import numpy as np
-import boto3
-import msgpack
-
-s3 = boto3.resource('s3')
-
-# Get the MessagePack data from S3
-obj = s3.Object("retrofit-data-dev", "cleaned_epc_data/cleaned.bson")
-cleaned = obj.get()['Body'].read()
-
-cleaned = msgpack.unpackb(cleaned, raw=False)
 
 
 def remove_starting_columns(df):
@@ -56,111 +44,6 @@ def keep_non_zero_rdsap(df):
     df = df[df["rdsap_change"] != 0]
     return df
 
-def remove_heatingkwh_bottom_percentile(df, percentile=0.0001):
-    df = df[df["heating_kwh"] > df["heating_kwh"].quantile(percentile)]
-    return df
-
-def add_features_from_code(df):
-
-    FEATURES = {
-        "heating_kwh": [
-            "lodgement-year", "lodgement-month", "current-energy-efficiency", "energy-consumption-current",
-            "heating-cost-current", "heating-cost-potential", "total-floor-area", "number-heated-rooms",
-            "mainheat-description", "mainheat-energy-eff", "main-fuel", "secondheat-description", "property-type",
-            "built-form", "mainheatcont-description", "hotwater-description", "hot-water-energy-eff",
-            "walls-energy-eff",
-            "roof-energy-eff", "windows-description", "windows-energy-eff", "floor-description", "flat-top-storey",
-            "flat-storey-count", "unheated-corridor-length", "solar-water-heating-flag", "mechanical-ventilation",
-            "low-energy-lighting", "environment-impact-current", "energy-tariff",
-            "county", "construction-age-band", "co2-emissions-current",
-        ],
-        "hot_water_kwh": [
-            "lodgement-year", "lodgement-month",
-            "current-energy-efficiency",
-            "energy-consumption-current",
-            "hot-water-cost-current",
-            "total-floor-area", "number-heated-rooms",
-            "hotwater-description", "hot-water-energy-eff", "main-fuel", "property-type", "built-form",
-            "co2-emissions-current",
-        ]
-    }
-    CATEGORICAL_COLUMNS = [
-        "lodgement-year", "lodgement-month", "main-fuel", "mainheat-description", "number-heated-rooms",
-        "number-habitable-rooms", "mainheat-energy-eff", "mainheatcont-description", "property-type", "built-form",
-        "construction-age-band", "secondheat-description", "hotwater-description", "hot-water-energy-eff",
-        "walls-description", "walls-energy-eff", "roof-description", "roof-energy-eff", "floor-description",
-        "county",
-        "windows-description", "windows-energy-eff", "flat-top-storey",
-        "flat-storey-count", "unheated-corridor-length", "solar-water-heating-flag", "mechanical-ventilation",
-        "low-energy-lighting", "environment-impact-current", "energy-tariff", "current-energy-rating"
-    ]
-
-    NUMERICAL_COLUMNS = list({
-            x for x in FEATURES["heating_kwh"] + FEATURES["hot_water_kwh"]
-            if x not in CATEGORICAL_COLUMNS
-        })
-    
-
-    """Performs feature engineering on the dataset."""
-    df["lodgement-date"] = pd.to_datetime(df["lodgement-date"])
-    df["lodgement-year"] = df["lodgement-date"].dt.year
-    df["lodgement-month"] = df["lodgement-date"].dt.month
-
-    # For walls, roof, floor description where we have average thermal transmittance, to avoid too many categories
-    # we group them
-    ranges = {
-        "lessthan 0.1": (0, 0.1),
-        "0.1 - 0.3": (0.1, 0.3),
-        "0.3 - 0.5": (0.3, 0.5),
-        "morethan 0.5": (0.5, 2.5),
-    }
-
-    # Generate the lookup table
-    thermal_transmittance_lookup_table = []
-    for i in range(1, 251):
-        value = i / 100
-        for label, (low, high) in ranges.items():
-            if low < value <= high:
-                thermal_transmittance_lookup_table.append({"from": value, "to": label})
-                break
-
-    # Convert to DataFrame for display
-    thermal_transmittance_lookup_table = pd.DataFrame(thermal_transmittance_lookup_table)
-    thermal_transmittance_lookup_table["from"] = thermal_transmittance_lookup_table["from"].astype(str)
-
-    # Apply the lookup table to the data
-    for feature in ["walls-description", "roof-description", "floor-description"]:
-        cleaned_df = pd.DataFrame(cleaned[feature])[["original_description", "thermal_transmittance"]]
-        # Round to 2 decimal places and convert to string
-        cleaned_df["thermal_transmittance"] = cleaned_df["thermal_transmittance"].round(2).astype(str)
-
-        df = df.merge(
-            cleaned_df,
-            how="left",
-            left_on=feature,
-            right_on="original_description",
-        )
-        # We now have the thermal transmittance in the data, which we can use to group with the lookup table
-        df = df.merge(
-            thermal_transmittance_lookup_table,
-            how="left",
-            left_on="thermal_transmittance",
-            right_on="from",
-        )
-        # Where "to" is populated, replace feature with to
-        df[feature] = np.where(
-            ~pd.isnull(df["to"]),
-            df["to"],
-            df[feature]
-        )
-        df = df.drop(columns=["original_description", "thermal_transmittance", "from", "to"])
-
-    # Convert data types
-    df[NUMERICAL_COLUMNS] = df[NUMERICAL_COLUMNS].apply(pd.to_numeric)
-    df[CATEGORICAL_COLUMNS] = df[CATEGORICAL_COLUMNS].astype(str)
-
-    return df
-
 
 # def keep_ending_columns(df):
 #     ending_column_index = [ col_name.endswith("_ENDING") for col_name in list(df.columns)]
@@ -170,36 +53,7 @@ def add_features_from_code(df):
 #     df = df[keep_columns]
 #     return df
 
-def enforce_minimum_habitable_room_size(df):
-    # Need minimum of 6.5m per habitable room
-    df = df[
-        df["total-floor-area"] / df["number-habitable-rooms"].astype(float) > 6.5
-    ].reset_index(drop=True)
-    return df
-
-def round_to_100s(df):
-    df['heating_kwh'] = (df['heating_kwh']/100).round()*100
-    return df 
-
-def remove_high_ratio_of_area_to_rooms(df):
-    df['area-to-heated-rooms'] = df['total-floor-area'] / df['number-heated-rooms'].astype(float)
-
-    # Remove na rows
-    df = df[(df['area-to-heated-rooms'].notna())].reset_index(drop=True)
-
-    # change any infinite values to 0
-    df['area-to-heated-rooms'] = df['area-to-heated-rooms'].replace([np.inf], 0)
-
-    # Remove top 0.05% of area-to-heated-rooms
-    df = df[df['area-to-heated-rooms'] < df['area-to-heated-rooms'].quantile(0.9995)].reset_index(drop=True)
-    return df
-
 business_logic = {
-    "add_features_from_code": add_features_from_code,
-    "remove_heatingkwh_bottom_percentile": remove_heatingkwh_bottom_percentile,
-    "round_to_100s": round_to_100s,
-    "enforce_minimum_habitable_room_size": enforce_minimum_habitable_room_size,
-    "remove_high_ratio_of_area_to_rooms": remove_high_ratio_of_area_to_rooms
     # "keep_non_zero_rdsap": keep_non_zero_rdsap,
     # "keep_flats": keep_flats,
     # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,

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

@@ -21,10 +21,7 @@ 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
-    # data_filepath: s3://retrofit-data-dev/energy_consumption/2024-07-08/energy_consumption_dataset.parquet
-    data_filepath: s3://retrofit-data-dev/energy_consumption/2024-07-25/energy_consumption_dataset.parquet
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
@@ -34,81 +31,14 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: heating_kwh
+      target: sap_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: ["hot_water_kwh"]
+      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", 
+        'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', 'number_heated_rooms_ending',
-      #   "heating_cost_ending", "hot_water_cost_ending",
+        'number_habitable_rooms', 'number_heated_rooms']
-      #   # "days_to_starting", "days_to_ending",
+      retain_features: null
-      #   'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', 'number_heated_rooms_ending',
-      #   'number_habitable_rooms', 'number_heated_rooms']
-      retain_features: ['uprn', 'heating-cost-current',
- 'co2-emissions-current',
- 'hot-water-cost-current',
- 'total-floor-area',
- 'secondheat-description',
- 'environment-impact-current',
- 'floor-description',
- 'mainheat-energy-eff',
- 'current-energy-efficiency',
- 'mainheat-env-eff',
- 'walls-energy-eff',
- 'roof-energy-eff',
- 'property-type',
- 'mainheat-description',
- 'hot-water-env-eff',
- 'mechanical-ventilation',
- 'floor-level',
- 'built-form',
- 'walls-description',
- 'mainheatcont-description',
- 'roof-description',
- 'energy-consumption-current',
- 'construction-age-band',
- 'hotwater-description',
- 'lodgement-datetime',
- 'main-fuel',
- 'hot-water-energy-eff',
- 'co2-emiss-curr-per-floor-area',
- 'windows-energy-eff',
- 'current-energy-rating',
- 'lodgement-year',
- 'extension-count',
- 'number-open-fireplaces',
- 'number-heated-rooms',
- 'lodgement-date',
-#  'number-habitable-rooms',
- 'windows-description',
- 'local-authority',
- 'photo-supply',
- 'heat-loss-corridor',
- 'posttown',
-#  'address',
- 'flat-top-storey',
- 'unheated-corridor-length',
- 'fixed-lighting-outlets-count',
- 'inspection-date',
- 'tenure',
- 'county',
- 'constituency-label',
- 'multi-glaze-proportion',
- 'solar-water-heating-flag',
-#  'address2',
- 'energy-tariff',
- 'floor-height',
- 'constituency',
- 'uprn-source',
- 'transaction-type',
- 'floor-energy-eff',
- 'postcode',
- 'lodgement-month',
- 'lighting-cost-current',
- 'glazed-area',
-#  'address1',
- 'floor-env-eff',
- 'main-heating-controls']
       # 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',

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

@@ -21,76 +21,26 @@ stages:
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
-        - hot_water_kwh
+        - 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
         default.feature_processor.feature_processor_config.retain_features:
-        - uprn
-        - heating-cost-current
-        - co2-emissions-current
-        - hot-water-cost-current
-        - total-floor-area
-        - secondheat-description
-        - environment-impact-current
-        - floor-description
-        - mainheat-energy-eff
-        - current-energy-efficiency
-        - mainheat-env-eff
-        - walls-energy-eff
-        - roof-energy-eff
-        - property-type
-        - mainheat-description
-        - hot-water-env-eff
-        - mechanical-ventilation
-        - floor-level
-        - built-form
-        - walls-description
-        - mainheatcont-description
-        - roof-description
-        - energy-consumption-current
-        - construction-age-band
-        - hotwater-description
-        - lodgement-datetime
-        - main-fuel
-        - hot-water-energy-eff
-        - co2-emiss-curr-per-floor-area
-        - windows-energy-eff
-        - current-energy-rating
-        - lodgement-year
-        - extension-count
-        - number-open-fireplaces
-        - number-heated-rooms
-        - lodgement-date
-        - windows-description
-        - local-authority
-        - photo-supply
-        - heat-loss-corridor
-        - posttown
-        - flat-top-storey
-        - unheated-corridor-length
-        - fixed-lighting-outlets-count
-        - inspection-date
-        - tenure
-        - county
-        - constituency-label
-        - multi-glaze-proportion
-        - solar-water-heating-flag
-        - energy-tariff
-        - floor-height
-        - constituency
-        - uprn-source
-        - transaction-type
-        - floor-energy-eff
-        - postcode
-        - lodgement-month
-        - lighting-cost-current
-        - glazed-area
-        - floor-env-eff
-        - main-heating-controls
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
-        default.feature_processor.feature_processor_config.target: heating_kwh
+        default.feature_processor.feature_processor_config.target: sap_ending
         default.feature_processor.feature_processor_type: dataframe
-        default.prepare_data.data_filepath: 
+        default.prepare_data.data_filepath:
-          s3://retrofit-data-dev/energy_consumption/2024-07-25/energy_consumption_dataset.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
@@ -99,8 +49,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 8585e7f26fa0008dcc0074996a51a78d.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 18062621
+      size: 45056059
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -111,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 8585e7f26fa0008dcc0074996a51a78d.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 18062621
+      size: 45056059
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -144,18 +94,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 0f536790b342ee84fe51f5bf66ca4e3c.dir
+      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
-      size: 1545512
+      size: 3349989
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 0ce09cc5e2d12876d9315cb18f8b70a9.dir
+      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 320950858
+      size: 773523079
       nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 5c38cf3ad988c55fb9685d76c7da78b3
+      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
-      size: 216
+      size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -165,13 +115,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 0ce09cc5e2d12876d9315cb18f8b70a9.dir
+      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 320950858
+      size: 773523079
       nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: 8585e7f26fa0008dcc0074996a51a78d.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 18062621
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -183,8 +133,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 9f32b5e943df8cd9336077b8daf2975c.dir
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 163552
+      size: 463197
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -195,13 +145,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 9f32b5e943df8cd9336077b8daf2975c.dir
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 163552
+      size: 463197
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 8585e7f26fa0008dcc0074996a51a78d.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 18062621
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -211,7 +161,7 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 752659c808d2bf0f176a0bf1ad7088a1
+      md5: 3e08df02fd5c5d094bcf936e1338d596
       size: 223
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
@@ -226,14 +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
+      md5: fa4d6d7bbd7818613800da5f8f37ea96
-      size: 0
+      size: 363
     - path: metrics/scenario_table.md
       hash: md5
-      md5: d41d8cd98f00b204e9800998ecf8427e
+      md5: d6baf100a1623cc2467c2f8221d314c9
-      size: 0
+      size: 2133