Merge pull request #109 from Hestia-Homes/heat-dev-model

Heat dev model

MODEL_REGISTRY.md

@@ -16,15 +16,15 @@
         "active": true
     },
     "heat": {
-        "version": "v0.3.0",
+        "version": "v0.4.0",
         "stage": {
-            "dev": "v0.3.0"
+            "dev": "v0.5.0"
         },
         "registered": true,
         "active": true
     },
     "carbon": {
-        "version": "v0.3.0",
+        "version": "v0.4.0",
         "stage": {
             "dev": "v0.3.0"
         },

deployment/Dockerfile.prediction.lambda

@@ -9,7 +9,7 @@ ARG RUNTIME_ENVIRONMENT
 ENV RUNTIME_ENVIRONMENT=${RUNTIME_ENVIRONMENT}
 
 # Install necessary build tools - required to test locally
-RUN yum install -y gcc python3-devel
+RUN yum install -y gcc python3-devel gcc-c++
 
 # Install python packages
 COPY modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt ./requirements.txt

modules/ml-pipeline/src/pipeline/4_generate_metrics.py

@@ -4,9 +4,7 @@ After the model is built, we can evaluate its performance
 """
 
 import os
-import yaml
 import pandas as pd
-from pathlib import Path
 from core.interface.InterfaceModels import MLModel
 from core.interface.InterfaceMetrics import MLMetrics
 from core.interface.InterfaceDataClient import DataClient

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

@@ -18,30 +18,39 @@ def remove_starting_columns(df):
     return df
 
 
-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")
+def keep_negative_heat_change(df):
+    df = df[df["heat_demand_change"] < 0]
     return df
 
 
-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)
+def keep_negative_carbon_change(df):
+    df = df[df["carbon_change"] < 0]
     return df
 
 
-def keep_flats(df):
-    df = df[df["property_type"] == "Flat"]
+# 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 keep_non_zero_rdsap(df):
-    df = df[df["rdsap_change"] != 0]
+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 +63,11 @@ def keep_non_zero_rdsap(df):
 #     return df
 
 business_logic = {
-    # "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_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,
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

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

@@ -1,6 +1,7 @@
 """
 After predictions, we may want to apply some post processing to the predictions
 """
+
 import pandas as pd
 
 
@@ -13,10 +14,11 @@ def clip_predictions_to_minimum_value(
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
     replace_index = (
-        predictions_df["sap_starting"] + minimum_value > predictions_df["predictions"]
+        predictions_df["predictions"]
+        > predictions_df["heat_demand_starting"] - minimum_value
     )
     predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "sap_starting"] + minimum_value
+        predictions_df.loc[replace_index, "heat_demand_starting"] - minimum_value
     )
 
     predictions_new = predictions_df["predictions"]

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

@@ -18,13 +18,9 @@ default:
   prepare_data:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_with_differencing.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/floor_area_clean_test.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_without_differencing.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_test.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
-    data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
-    train_proportion: 1
+    # data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet
+    train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
 
@@ -33,9 +29,12 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
+      target: heat_demand_ending
       identifier_columns: ["uprn"]
-      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending"]
+      drop_columns: [
+        "heat_demand_change", "carbon_change", "rdsap_change", "sap_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']
       # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
 

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

@@ -1,36 +1,56 @@
 schema: '2.0'
 stages:
+  startup_cleanup:
+    cmd: python 0_startup_cleanup.py
+    deps:
+    - path: 0_startup_cleanup.py
+      hash: md5
+      md5: b1b12f6b6393fbf8b83d23684df0a3d4
+      size: 1220
+    params:
+      configs/settings.yaml:
+        default.startup_cleanup.artefacts: ./data
+        default.startup_cleanup.metrics: ./metrics
   prepare_data:
     cmd: python 1_prepare_data.py
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: 1793a35e71751d3c84f9affc67ecb9a8
-      size: 4296
+      md5: 11a3b8bfdfe199ab7ecc39ccc5652649
+      size: 4298
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
         - heat_demand_change
         - carbon_change
         - rdsap_change
-        - heat_demand_ending
+        - sap_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:
         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: heat_demand_ending
         default.feature_processor.feature_processor_type: dataframe
-        default.prepare_data.data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
+        default.prepare_data.data_filepath: 
+          s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/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
         default.prepare_data.output_train_filepath: ./data/prepared_data/train.parquet
-        default.prepare_data.train_proportion: 1
+        default.prepare_data.train_proportion: 0.9
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: 4cec69f112537658f14eb3cb678f91e3.dir
+      size: 36889932
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: 4cec69f112537658f14eb3cb678f91e3.dir
+      size: 36889932
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -73,18 +93,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: ede187e9d0bffdef054f573f3c2bd222.dir
-      size: 3578590
+      md5: 7dda2f1dd257a6c5beaaa0b74eab6d5d.dir
+      size: 2901760
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: b2ad0b538dc4aef0de3d431fc9c40c4f.dir
-      size: 814720415
-      nfiles: 31
+      md5: 741f8aed57383e860c535feb8b0adb71.dir
+      size: 752079341
+      nfiles: 32
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: c45b84f12971a0156e4f3d85d3e725f5
-      size: 218
+      md5: 8eaa72b08074f735a9e54de871edc6e6
+      size: 221
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -94,13 +114,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: b2ad0b538dc4aef0de3d431fc9c40c4f.dir
-      size: 814720415
-      nfiles: 31
+      md5: 741f8aed57383e860c535feb8b0adb71.dir
+      size: 752079341
+      nfiles: 32
     - path: data/prepared_data
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: 4cec69f112537658f14eb3cb678f91e3.dir
+      size: 36889932
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -112,25 +132,25 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5e60ca251af51de6fef3d0c659f8bb27.dir
-      size: 627416
+      md5: d842fe5350a3330c4c17e7e21c6359b2.dir
+      size: 380489
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: 4fedb86d89d528f0a6597934ba3890a0
-      size: 3484
+      md5: d61bb524f706917f6a3eb72b1ab8bc61
+      size: 3447
     - path: data/predictions
       hash: md5
-      md5: 5e60ca251af51de6fef3d0c659f8bb27.dir
-      size: 627416
+      md5: d842fe5350a3330c4c17e7e21c6359b2.dir
+      size: 380489
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 84fa631bd02686b052d6a7144eafd38e.dir
-      size: 43859225
+      md5: 4cec69f112537658f14eb3cb678f91e3.dir
+      size: 36889932
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -140,16 +160,5 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 033efa4d4044b6b6fc92dd37194727fa
-      size: 225
-  startup_cleanup:
-    cmd: python 0_startup_cleanup.py
-    deps:
-    - path: 0_startup_cleanup.py
-      hash: md5
-      md5: b1b12f6b6393fbf8b83d23684df0a3d4
-      size: 1220
-    params:
-      configs/settings.yaml:
-        default.startup_cleanup.artefacts: ./data
-        default.startup_cleanup.metrics: ./metrics
+      md5: 2632fa5d0a38763c177bf0466a670c8b
+      size: 220

modules/ml-pipeline/src/pipeline/eda.py

@@ -1,6 +1,7 @@
 """
 Doing some eda on dataset
 """
+
 # Look at response variable
 
 from matplotlib import pyplot as plt
@@ -38,7 +39,6 @@ train_df[[target, "SAP_STARTING"]].plot(y=target, x="SAP_STARTING", style="o")
 train_df[[target, "HEAT_DEMAND_STARTING"]].plot(
     x=target, y="HEAT_DEMAND_STARTING", style="o"
 )
-
 # Both make sense: i.e. the higher the sap, the lower we predict and the higher the heat demand, the higher we predict
 
 # Load the autogluon model and check feature importance
@@ -176,6 +176,8 @@ plot_permutation_importance(exp, fig_kw={"figwidth": 7, "figheight": 6})
 #
 #
 
+from core.MLMetrics import metrics_factory
+
 from core.MLModels import model_factory
 from core.DataClient import dataclient_factory
 import pandas as pd
@@ -216,6 +218,12 @@ mix_df["residual"] = abs(mix_df[predictions_column_name] - mix_df[target])
 mix_df = mix_df.sort_values("residual", ascending=False)
 
 cosine_similarity_df = mix_df[mix_df.columns.difference(["predictions", "residual"])]
+metrics = metrics_factory("Regression")
+metrics.generate_metrics(mix_df["predictions"], mix_df["HEAT_DEMAND_ENDING"])
+
+cosine_similarity_df = mix_df[
+    mix_df.columns.difference(["predictions", "residual", "SAP_ENDING"])
+]
 from sklearn.metrics.pairwise import cosine_similarity
 
 row_index = 0

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

@@ -1,7 +1,7 @@
 joblib==1.3.2
 boto3==1.28.17
-pandas==1.5.3
-autogluon==0.8.2
-dynaconf==3.2.0
+pandas==2.1.4
+autogluon==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==1.5.3
-autogluon==0.8.2
-dynaconf==3.2.0
+pandas==2.1.4
+autogluon==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

@@ -1,9 +1,10 @@
 joblib==1.3.2
 boto3==1.28.17
-pandas==1.5.3
-autogluon==0.8.2
-dynaconf==3.2.0
-alibi==0.9.4
+pandas==2.1.4
+autogluon==1.0.0
+ray==2.6.3
+dynaconf==3.2.1
+alibi==0.9.5
 shap==0.42.1
 pyarrow==13.0.0
 pre-commit==3.3.3

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

@@ -1,4 +1,4 @@
 boto3==1.28.41
-pandas==1.5.3
-autogluon==0.8.2
-dynaconf==3.2.0
+pandas==2.1.4
+autogluon==1.0.0
+dynaconf==3.2.1