Merge pull request #93 from Hestia-Homes/heat-dev-model

Heat dev model

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: 400
+      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

@@ -9,22 +9,22 @@ 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]
+    df = df[df["heat_demand_change"] < 0]
     return df
 
 
 def keep_negative_carbon_change(df):
-    df = df[df["CARBON_CHANGE"] < 0]
+    df = df[df["carbon_change"] < 0]
     return df
 
 
@@ -34,7 +34,7 @@ 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["total_floor_area_ending"] / df["number_habitable_rooms"] >= 6.5
     )
     df = df[minimum_room_size_index]
     return df
@@ -43,14 +43,14 @@ def remove_unreasonable_habitable_rooms(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]
+    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]
+    df = df[df["carbon_starting"] < threshold_value]
     return df
 
 

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

@@ -13,10 +13,10 @@ 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["predictions"] > predictions_df["HEAT_DEMAND_STARTING"] - 1
+        predictions_df["predictions"] > predictions_df["heat_demand_starting"] - 1
     )
     predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "HEAT_DEMAND_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

@@ -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: HEAT_DEMAND_ENDING
+      target: heat_demand_ending
-      identifier_columns: ["UPRN"]
+      identifier_columns: ["uprn"]
-      drop_columns: ["HEAT_DEMAND_CHANGE", "CARBON_CHANGE", "RDSAP_CHANGE", "SAP_ENDING", "CARBON_ENDING"]
+      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "sap_ending", "carbon_ending"]
       # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
 

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

@@ -10,17 +10,17 @@ stages:
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
-        - HEAT_DEMAND_CHANGE
+        - heat_demand_change
-        - CARBON_CHANGE
+        - carbon_change
-        - RDSAP_CHANGE
+        - rdsap_change
-        - SAP_ENDING
+        - sap_ending
-        - CARBON_ENDING
+        - carbon_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: HEAT_DEMAND_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-data-dev/sap_change_model/dataset_test.parquet
+        default.prepare_data.data_filepath: s3://retrofit-data-dev/sap_change_model/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
@@ -29,8 +29,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      md5: 613ddd198a29002e6e05a2d60275d924.dir
-      size: 30774760
+      size: 32746979
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +41,8 @@ stages:
       size: 4149
     - path: data/prepared_data
       hash: md5
-      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      md5: 613ddd198a29002e6e05a2d60275d924.dir
-      size: 30774760
+      size: 32746979
       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: 400
+              time_limit: 600
               presets: medium_quality
               excluded_model_types:
               - KNN
@@ -68,13 +68,13 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: a868845999b46e0272dc27f5cb5bc618.dir
+      md5: 837a42a0655862229620495c645d5fed.dir
-      size: 310555147
+      size: 342382387
-      nfiles: 24
+      nfiles: 26
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 809f27735c77cbcb62866b96018eedea
+      md5: f8a394b86c33dc1b3ce97abed803c8f1
-      size: 216
+      size: 220
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -84,13 +84,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: a868845999b46e0272dc27f5cb5bc618.dir
+      md5: 837a42a0655862229620495c645d5fed.dir
-      size: 310555147
+      size: 342382387
-      nfiles: 24
+      nfiles: 26
     - path: data/prepared_data
       hash: md5
-      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      md5: 613ddd198a29002e6e05a2d60275d924.dir
-      size: 30774760
+      size: 32746979
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -102,8 +102,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 2098fe82304751025e427f2cc241a2ff.dir
+      md5: 75f8326e99eb9e1032728208229ec37b.dir
-      size: 295849
+      size: 314002
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -114,13 +114,13 @@ stages:
       size: 3448
     - path: data/predictions
       hash: md5
-      md5: 2098fe82304751025e427f2cc241a2ff.dir
+      md5: 75f8326e99eb9e1032728208229ec37b.dir
-      size: 295849
+      size: 314002
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      md5: 613ddd198a29002e6e05a2d60275d924.dir
-      size: 30774760
+      size: 32746979
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -130,8 +130,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: aa671878e1bd8c6a8d4b5f9788c817c4
+      md5: 269e89593f5e7ceb507c31dac2c2dd35
-      size: 219
+      size: 220
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps:

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

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