Merge pull request #140 from Hestia-Homes/heatingkwh-dev-model

remove the rounding the 100 kwh

.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, heatingkwh-dev, heatingkwh-prod]
 
 jobs:
   deploy:

.github/workflows/MLPipelinePostMerge.yml

@@ -13,6 +13,7 @@ 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"]
+    branches: ["sap-dev", "heat-dev", "carbon-dev", "heatingkwh-dev"]
   label:
     types: ["created", "edited"]
 

MODEL_REGISTRY.md

@@ -16,17 +16,57 @@
         "active": true
     },
     "heat": {
-        "version": "v0.5.0",
+        "version": "v0.6.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.6.0"
         },
         "registered": true,
         "active": true
     },
     "carbon": {
-        "version": "v0.5.0",
+        "version": "v0.6.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.6.0"
+        },
+        "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": "v1.1.0",
+        "stage": {
+            "dev": "v1.1.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "heatingkwh": {
+        "version": "v1.2.0",
+        "stage": {
+            "dev": "v1.2.0"
         },
         "registered": true,
         "active": true

modules/ml-pipeline/README.MD

@@ -17,14 +17,15 @@ Within `src` folder, the structure is as follows:
 
 # How to develop using this pipeline:
 
-Run `make init`, which will:
-- Download pyenv (Python version management)
-- Download Python 3.X.X as defined in the `make` file - current 3.10.12
-- Create a virtual environment with this version of python
+First, download miniconda to use conda to manage Python Environments
+Rund `conda init`, to initialise your terminal
+
+Change to this directory and run `make init`, which will:
+- Create a conda virtual environment with this version of python - current 3.10.12
 - Install packages in the training and version control directories in the pipeline folder (dev version if applicable)
 - Install pre-commit to enable pre-commit hooks
 
-To use the environment, run `source .dev_env_pipeline/bin/activate`.
+To use the environment, run `conda activate dev_env_pipeline`
 
 To enable the virtual envrionemnt created in vscode:
 - Open settings

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

@@ -5,6 +5,18 @@ 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):
@@ -44,6 +56,111 @@ 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)]
@@ -53,7 +170,41 @@ def keep_non_zero_rdsap(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
+
+def add_estimate_annual_kwh(df):
+    df['estimate_annual_kwh'] = df['energy-consumption-current'] * df['total-floor-area']
+    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,
+    "add_estimate_annual_kwh": add_estimate_annual_kwh,
     # "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

@@ -21,7 +21,10 @@ 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
@@ -31,37 +34,11 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
+      target: heating_kwh
       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",
-        'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', 'number_heated_rooms_ending',
-        'number_habitable_rooms', 'number_heated_rooms']
+      drop_columns: ["hot_water_kwh", 'lodgement-datetime', 'lodgement-date', 'number-habitable-rooms', 'local-authority', 'posttown', 'address', 'inspection-date',
+      "county", "constituency-label", 'address2', 'uprn-source', 'postcode', 'address1',]
       retain_features: null
-      # 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']
 
   generate_predictions:
     input_dataclient_type: local

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

@@ -21,26 +21,27 @@ stages:
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
-        - 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
+        - hot_water_kwh
+        - lodgement-datetime
+        - lodgement-date
+        - number-habitable-rooms
+        - local-authority
+        - posttown
+        - address
+        - inspection-date
+        - county
+        - constituency-label
+        - address2
+        - uprn-source
+        - postcode
+        - address1
         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: heating_kwh
         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
+        default.prepare_data.data_filepath: 
+          s3://retrofit-data-dev/energy_consumption/2024-07-25/energy_consumption_dataset.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
-      size: 45056059
+      md5: f506f1f059945c0f014c3f505a63726c.dir
+      size: 30388447
       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
-      size: 45056059
+      md5: f506f1f059945c0f014c3f505a63726c.dir
+      size: 30388447
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -94,18 +95,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
-      size: 3349989
+      md5: 9a2abeada227b8bb4c13d6c745bef581.dir
+      size: 1547064
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 773523079
+      md5: 43b72f9284e92842cbc82bc7cc0950e2.dir
+      size: 506201607
       nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
-      size: 224
+      md5: 4a496483bffad3efe671f29110729e48
+      size: 221
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,13 +116,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 773523079
+      md5: 43b72f9284e92842cbc82bc7cc0950e2.dir
+      size: 506201607
       nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: f506f1f059945c0f014c3f505a63726c.dir
+      size: 30388447
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,8 +134,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463197
+      md5: 88832d623c3e437eaec221307ac33aae.dir
+      size: 163584
       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
-      size: 463197
+      md5: 88832d623c3e437eaec221307ac33aae.dir
+      size: 163584
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: f506f1f059945c0f014c3f505a63726c.dir
+      size: 30388447
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,8 +162,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3e08df02fd5c5d094bcf936e1338d596
-      size: 223
+      md5: f2783bdec0f0974b6d799609c6189467
+      size: 222
   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
-      size: 363
+      md5: d41d8cd98f00b204e9800998ecf8427e
+      size: 0
     - path: metrics/scenario_table.md
       hash: md5
-      md5: d6baf100a1623cc2467c2f8221d314c9
-      size: 2133
+      md5: d41d8cd98f00b204e9800998ecf8427e
+      size: 0