Merge pull request #71 from Hestia-Homes/carbon-dev-model

400 second model

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

@@ -13,6 +13,6 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 4000
+      time_limit: 400
       presets: medium_quality
       excluded_model_types: ['KNN', 'RF']

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

@@ -18,6 +18,11 @@ def remove_starting_columns(df):
     return df
 
 
+def keep_negative_carbon_change(df):
+    df = df[df["CARBON_CHANGE"] < 0]
+    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 +32,7 @@ def remove_starting_columns(df):
 #     return df
 
 business_logic = {
+    "keep_negative_carbon_change": keep_negative_carbon_change
     # "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"]
+    replace_index = predictions_df["predictions"] > predictions_df["CARBON_STARTING"]
-    predictions_df.loc[replace_index, "predictions"] = (
+    predictions_df.loc[replace_index, "predictions"] = predictions_df.loc[
-        predictions_df.loc[replace_index, "SAP_STARTING"] + minimum_value
+        replace_index, "CARBON_STARTING"
-    )
+    ]
 
     predictions_new = predictions_df["predictions"]
     predictions_new.name = series_name

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

@@ -31,9 +31,9 @@ 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"]
+      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

@@ -14,11 +14,11 @@ stages:
         - CARBON_CHANGE
         - RDSAP_CHANGE
         - HEAT_DEMAND_ENDING
-        - CARBON_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
@@ -29,8 +29,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
-      size: 33881619
+      size: 30137355
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +41,8 @@ stages:
       size: 5359
     - path: data/prepared_data
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
-      size: 33881619
+      size: 30137355
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -58,7 +58,7 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 4000
+              time_limit: 400
               presets: medium_quality
               excluded_model_types:
               - KNN
@@ -66,13 +66,13 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: 7bb5156243b4db39349e80a01ffecde4.dir
+      md5: 4b49c12395a645e35e50a9de8840f08d.dir
-      size: 473398662
+      size: 282024140
-      nfiles: 27
+      nfiles: 24
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2bb16ac67de8778fbc08171d562b34d5
+      md5: a6d139fa59f5ddf75023bb7d3364f6d2
-      size: 184
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -82,13 +82,13 @@ stages:
       size: 3028
     - path: data/model
       hash: md5
-      md5: 7bb5156243b4db39349e80a01ffecde4.dir
+      md5: 4b49c12395a645e35e50a9de8840f08d.dir
-      size: 473398662
+      size: 282024140
-      nfiles: 27
+      nfiles: 24
     - path: data/prepared_data
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
-      size: 33881619
+      size: 30137355
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -100,8 +100,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 0bb3cf991906953def81c8204cdcfaf0.dir
+      md5: 8f724261b3d17bf87067e91a1ff99077.dir
-      size: 374532
+      size: 441423
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -112,13 +112,13 @@ stages:
       size: 4487
     - path: data/predictions
       hash: md5
-      md5: 0bb3cf991906953def81c8204cdcfaf0.dir
+      md5: 8f724261b3d17bf87067e91a1ff99077.dir
-      size: 374532
+      size: 441423
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      md5: 5fd3c01804ee2994ee77fc501d178be4.dir
-      size: 33881619
+      size: 30137355
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -128,8 +128,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 2e13ae67759a64261d03224f1c0d4bf4
+      md5: 38787835f838f65c6cc75654843eb311
-      size: 185
+      size: 223
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps: