Merge pull request #119 from Hestia-Homes/carbon-dev-model

Carbon dev model

MODEL_REGISTRY.md

@@ -18,7 +18,7 @@
     "heat": {
         "version": "v0.5.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.11.0"
         },
         "registered": true,
         "active": true

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

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

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

@@ -18,30 +18,44 @@ def remove_starting_columns(df):
     return df
 
 
-def remove_floor_height_ending(df):
+def keep_negative_heat_change(df):
-    # df.describe(percentiles=[0.005,0.99])['FLOOR_HEIGHT_ENDING']
+    df = df[df["heat_demand_change"] < 0]
-    # 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 remove_minimum_habitable_room_size(df):
+def keep_non_negative_carbon_ending(df):
-    # Need minimum of 6.5m per habitable room
+    df = df[df["carbon_ending"] > 0]
-    df = df[
-        df["total_floor_area_ending"] / df["number_habitable_rooms"] > 6.5
-    ].reset_index(drop=True)
     return df
 
 
-def keep_flats(df):
+def keep_negative_carbon_change(df):
-    df = df[df["property_type"] == "Flat"]
+    df = df[df["carbon_change"] < 0]
     return df
 
 
-def keep_non_zero_rdsap(df):
+# TODO: Move to ETL pipeline
-    df = df[df["rdsap_change"] != 0]
+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]
     return df
 
 
@@ -54,10 +68,12 @@ def keep_non_zero_rdsap(df):
 #     return df
 
 business_logic = {
-    # "keep_non_zero_rdsap": keep_non_zero_rdsap,
+    "remove_unreasonable_habitable_rooms": remove_unreasonable_habitable_rooms,
-    # "keep_flats": keep_flats,
+    "keep_negative_heat_change": keep_negative_heat_change,
-    # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,
+    "keep_negative_carbon_change": keep_negative_carbon_change,
-    # "remove_floor_height_ending": remove_floor_height_ending
+    "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,
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

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

@@ -1,23 +1,24 @@
 """
 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, minimum_value: int = 0
+    data: pd.DataFrame,
+    predictions: pd.Series,
 ) -> 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 = (
+    replace_index = predictions_df["predictions"] > predictions_df["carbon_starting"]
-        predictions_df["sap_starting"] + minimum_value > predictions_df["predictions"]
+    predictions_df.loc[replace_index, "predictions"] = predictions_df.loc[
-    )
+        replace_index, "carbon_starting"
-    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

@@ -31,13 +31,14 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
+      target: carbon_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", "sap_ending"]
       drop_columns: [
-        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending",
+        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_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: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       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
-        - carbon_ending
+        - sap_ending
         - days_to_starting
         - days_to_ending
         - number_habitable_rooms_starting
@@ -37,7 +37,7 @@ 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: carbon_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
@@ -49,8 +49,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: e2efac20634b919381adfb962a42d40a.dir
-      size: 45056059
+      size: 36961727
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -61,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: e2efac20634b919381adfb962a42d40a.dir
-      size: 45056059
+      size: 36961727
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -94,18 +94,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
+      md5: d2568a3244df4d3444b6190599f74b96.dir
-      size: 3349989
+      size: 3661106
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
+      md5: 756100e033e0bd4445a437e43f4c53af.dir
-      size: 773523079
+      size: 730442848
       nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
+      md5: 3bcb3b9728521cd341eb71af109ca778
-      size: 224
+      size: 227
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,13 +115,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
+      md5: 756100e033e0bd4445a437e43f4c53af.dir
-      size: 773523079
+      size: 730442848
       nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: e2efac20634b919381adfb962a42d40a.dir
-      size: 45056059
+      size: 36961727
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,8 +133,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      md5: 09f3584d6fbd447dd2714eb2774139d5.dir
-      size: 463197
+      size: 499683
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -145,13 +145,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
+      md5: 09f3584d6fbd447dd2714eb2774139d5.dir
-      size: 463197
+      size: 499683
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
+      md5: e2efac20634b919381adfb962a42d40a.dir
-      size: 45056059
+      size: 36961727
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,8 +161,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3e08df02fd5c5d094bcf936e1338d596
+      md5: abf8720d06f073f47501aa1172527e9e
-      size: 223
+      size: 225
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
@@ -176,15 +176,14 @@ 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