Merge pull request #92 from Hestia-Homes/carbon-dev-model

Carbon dev model

MODEL_REGISTRY.md

@@ -8,17 +8,25 @@
         "active": true
     },
     "sap": {
-        "version": "v0.1.0",
+        "version": "v0.2.6",
         "stage": {
-            "dev": "v0.1.0"
+            "dev": "v0.2.6"
         },
         "registered": true,
         "active": true
     },
     "heat": {
-        "version": "v0.0.1",
+        "version": "v0.2.0",
         "stage": {
-            "dev": "v0.0.1"
+            "dev": "v0.2.0"
+        },
+        "registered": true,
+        "active": true
+    },
+    "carbon": {
+        "version": "v0.2.0",
+        "stage": {
+            "dev": "v0.2.0"
         },
         "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/configs/build_model.yaml

@@ -13,7 +13,7 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 4000
+      time_limit: 600
       presets: medium_quality
       excluded_model_types: ['KNN', 'RF']
       infer_limit: 0.05

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

@@ -9,15 +9,56 @@ Business Logic dict + functions
 
 def remove_starting_columns(df):
     keep_column_index = [
-        False if col_name.endswith("_STARTING") else True
+        False if col_name.endswith("_starting") else True
         for col_name in list(df.columns)
     ]
     keep_columns = df.columns[keep_column_index].to_list()
-    keep_columns.append("SAP_STARTING")
+    keep_columns.append("sap_starting")
     df = df[keep_columns]
     return df
 
 
+def keep_negative_heat_change(df):
+    df = df[df["heat_demand_change"] < 0]
+    return df
+
+
+def keep_non_negative_carbon_ending(df):
+    df = df[df["carbon_ending"] > 0]
+    return df
+
+
+def keep_negative_carbon_change(df):
+    df = df[df["carbon_change"] < 0]
+    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]
+    return df
+
+
 # def keep_ending_columns(df):
 #     ending_column_index = [ col_name.endswith("_ENDING") for col_name in list(df.columns)]
 #     keep_columns = df.columns[ending_column_index].to_list()
@@ -27,6 +68,12 @@ def remove_starting_columns(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
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

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

@@ -5,17 +5,18 @@ import pandas as pd
 
 
 def clip_predictions_to_minimum_value(
-    data: pd.DataFrame, predictions: pd.Series, minimum_value: int = 1
+    data: pd.DataFrame,
+    predictions: pd.Series,
 ) -> pd.Series:
 
     series_name = predictions.name
     predictions.name = "predictions"
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
-    replace_index = predictions_df["SAP_STARTING"] + 1 > predictions_df["predictions"]
-    predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "SAP_STARTING"] + minimum_value
-    )
+    replace_index = predictions_df["predictions"] > predictions_df["carbon_starting"]
+    predictions_df.loc[replace_index, "predictions"] = predictions_df.loc[
+        replace_index, "carbon_starting"
+    ]
 
     predictions_new = predictions_df["predictions"]
     predictions_new.name = series_name

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

@@ -21,7 +21,7 @@ default:
     # 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
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
@@ -31,9 +31,9 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: SAP_ENDING
-      identifier_columns: ["UPRN"]
-      drop_columns: ["HEAT_DEMAND_CHANGE", "CARBON_CHANGE", "RDSAP_CHANGE", "HEAT_DEMAND_ENDING", "CARBON_ENDING"]
+      target: carbon_ending
+      identifier_columns: ["uprn"]
+      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_ending"]
       # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
 

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

@@ -5,20 +5,20 @@ stages:
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: c9f030df733e318b80d1fa91b7732f79
-      size: 5132
+      md5: 896d3d88a4a9f68d174efe71dc089517
+      size: 4222
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
-        - HEAT_DEMAND_CHANGE
-        - CARBON_CHANGE
-        - RDSAP_CHANGE
-        - HEAT_DEMAND_ENDING
-        - CARBON_ENDING
+        - heat_demand_change
+        - carbon_change
+        - rdsap_change
+        - heat_demand_ending
+        - sap_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: 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/dataset.parquet
         default.prepare_data.input_dataclient_type: aws-s3
@@ -29,20 +29,20 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
-      size: 33881619
+      md5: 70d79ba4a6f0648439dc55031c944d47.dir
+      size: 32673907
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
     deps:
     - path: 2_build_model.py
       hash: md5
-      md5: 84699d208874c52accaff61c6af9bb0a
-      size: 5359
+      md5: b824822475c222521516493e68eef9c5
+      size: 4149
     - path: data/prepared_data
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
-      size: 33881619
+      md5: 70d79ba4a6f0648439dc55031c944d47.dir
+      size: 32673907
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -58,37 +58,39 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 4000
+              time_limit: 600
               presets: medium_quality
               excluded_model_types:
               - KNN
               - RF
+              infer_limit: 0.05
+              infer_limit_batch_size: 10000
     outs:
     - path: data/model/
       hash: md5
-      md5: 7bb5156243b4db39349e80a01ffecde4.dir
-      size: 473398662
+      md5: 2fc9223da8b72e61d81f06665e75019e.dir
+      size: 324532985
       nfiles: 27
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2bb16ac67de8778fbc08171d562b34d5
-      size: 184
+      md5: 7d2f226251ce6f8e92af73d50dadb890
+      size: 228
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
     - path: 3_generate_predictions.py
       hash: md5
-      md5: 5ef2856a5a977304f1ec01f9b4205262
-      size: 3028
+      md5: 0a70ad4dfe99414a75d1261c75a177b9
+      size: 2464
     - path: data/model
       hash: md5
-      md5: 7bb5156243b4db39349e80a01ffecde4.dir
-      size: 473398662
+      md5: 2fc9223da8b72e61d81f06665e75019e.dir
+      size: 324532985
       nfiles: 27
     - path: data/prepared_data
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
-      size: 33881619
+      md5: 70d79ba4a6f0648439dc55031c944d47.dir
+      size: 32673907
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -100,25 +102,25 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 0bb3cf991906953def81c8204cdcfaf0.dir
-      size: 374532
+      md5: 8bfc33c14aba5abf5ac4bdba32ff3c4c.dir
+      size: 412880
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: 2c9fb78955a8c19cff0a098976f81d1b
-      size: 4487
+      md5: d09a80dd55f1f69e2a832b1991b3c406
+      size: 3485
     - path: data/predictions
       hash: md5
-      md5: 0bb3cf991906953def81c8204cdcfaf0.dir
-      size: 374532
+      md5: 8bfc33c14aba5abf5ac4bdba32ff3c4c.dir
+      size: 412880
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
-      size: 33881619
+      md5: 70d79ba4a6f0648439dc55031c944d47.dir
+      size: 32673907
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -128,15 +130,15 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 2e13ae67759a64261d03224f1c0d4bf4
-      size: 185
+      md5: 9a0b57244dfdbd6dab0392a4fd618123
+      size: 225
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps:
     - path: 0_startup_cleanup.py
       hash: md5
-      md5: fbb7e3b1b98b517c870f3e1df3e7f695
-      size: 1676
+      md5: b1b12f6b6393fbf8b83d23684df0a3d4
+      size: 1220
     params:
       configs/settings.yaml:
         default.startup_cleanup.artefacts: ./data

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

@@ -1,4 +1,4 @@
-dvc==3.18.0
-dvc-s3==2.23.0
-gto==1.0.4
-pyOpenSSL==23.2.0
+dvc==3.36.0
+dvc-s3==3.0.1
+gto==1.6.1
+pyOpenSSL==23.3.0