Merge pull request #95 from Hestia-Homes/heat-dev-model

Heat dev model

modules/ml-pipeline/src/pipeline/1_prepare_data.py

@@ -87,7 +87,8 @@ def prepare_data(
 
     if train_proportion == 1:
         train = data
-        test = None
+        # Sample 10% of the data for testing
+        test = data.sample(round(len(data) * 0.1))
     else:
         train, test = train_test_split(
             data, train_size=train_proportion, test_size=(1 - train_proportion)

modules/ml-pipeline/src/pipeline/2_build_model.py

@@ -26,9 +26,12 @@ prepare_data_params = settings.prepare_data
 build_model_params = settings.build_model
 feature_process_params = settings.feature_processor
 generate_metrics_params = settings.generate_metrics
+generate_predictions_params = settings.generate_predictions
 
 model_type = build_model_params["model_type"]
 target = feature_process_params["feature_processor_config"]["target"]
+fit_predictions_filepath = build_model_params["fit_predictions_filepath"]
+predictions_column_name = generate_predictions_params["predictions_column_name"]
 identifier_columns = feature_process_params["feature_processor_config"][
     "identifier_columns"
 ]
@@ -60,6 +63,8 @@ def build_model(
     identifier_columns: List[str],
     model_save_location: str,
     model_hyperparameters: dict,
+    fit_predictions_filepath: str,
+    predictions_column_name: str,
     fit_metrics_filepath: str,
     train_filepath: Union[str, None] = None,
     test_filepath: Union[str, None] = None,
@@ -93,6 +98,15 @@ def build_model(
         data=train_data, post_prediction_logic=post_prediction_logic
     )
 
+    logger.info("--- Saving fit predictions ---")
+
+    predictions_df = pd.DataFrame(fit_predictions)
+    predictions_df.columns = [predictions_column_name]
+
+    dataclient.save_data(
+        obj=predictions_df, location=fit_predictions_filepath, save_config=None
+    )
+
     logger.info("--- Generating fit metrics ---")
 
     metrics_output = metrics.generate_metrics(
@@ -128,6 +142,8 @@ if __name__ == "__main__":
         train_filepath=train_filepath,
         test_filepath=test_filepath,
         fit_metrics_filepath=fit_metrics_filepath,
+        fit_predictions_filepath=fit_predictions_filepath,
+        predictions_column_name=predictions_column_name,
     )
 
     logger.info(f"--- {__file__} - Complete! ---")

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

@@ -3,6 +3,7 @@ default:
     model_type: AutogluonAutoML
     model_save_filepath: ./data/model/optimised/
     fit_metrics_filepath: ./metrics/fit_metrics.json
+    fit_predictions_filepath: ./data/fit_predictions/predictions.parquet
 
     SKLearnLinearRegression: null
 
@@ -13,8 +14,8 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 600
+      time_limit: 4000
       presets: medium_quality
-      excluded_model_types: ['KNN', 'RF']
+      excluded_model_types: ['RF', 'FASTAI', 'CAT', 'NN_TORCH', 'KNN', 'XT']
       infer_limit: 0.05
       infer_limit_batch_size: 10000

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

@@ -5,7 +5,7 @@ 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, minimum_value: int = 0
 ) -> pd.Series:
 
     series_name = predictions.name
@@ -13,7 +13,8 @@ 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"] - minimum_value
     )
     predictions_df.loc[replace_index, "predictions"] = (
         predictions_df.loc[replace_index, "heat_demand_starting"] - minimum_value

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

@@ -21,8 +21,9 @@ 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.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
-    train_proportion: 0.9
+    data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
+    train_proportion: 1
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
 

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

@@ -5,8 +5,8 @@ stages:
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: 896d3d88a4a9f68d174efe71dc089517
+      md5: 11a3b8bfdfe199ab7ecc39ccc5652649
-      size: 4222
+      size: 4298
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
@@ -20,29 +20,29 @@ stages:
         default.feature_processor.feature_processor_config.subsample_seed: 0
         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.parquet
+        default.prepare_data.data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.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: 0.9
+        default.prepare_data.train_proportion: 1
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 613ddd198a29002e6e05a2d60275d924.dir
+      md5: dcd41f841c67b474a81a14e683646237.dir
-      size: 32746979
+      size: 36317761
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
     deps:
     - path: 2_build_model.py
       hash: md5
-      md5: b824822475c222521516493e68eef9c5
+      md5: 7231450b78920b0c5e7c6bada496b24a
-      size: 4149
+      size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 613ddd198a29002e6e05a2d60275d924.dir
+      md5: dcd41f841c67b474a81a14e683646237.dir
-      size: 32746979
+      size: 36317761
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -51,6 +51,7 @@ stages:
             model_type: AutogluonAutoML
             model_save_filepath: ./data/model/optimised/
             fit_metrics_filepath: ./metrics/fit_metrics.json
+            fit_predictions_filepath: ./data/fit_predictions/predictions.parquet
             SKLearnLinearRegression:
             SKLearnSVMRegression:
               kernel: linear
@@ -58,23 +59,32 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 600
+              time_limit: 4000
               presets: medium_quality
               excluded_model_types:
-              - KNN
               - RF
+              - FASTAI
+              - CAT
+              - NN_TORCH
+              - KNN
+              - XT
               infer_limit: 0.05
               infer_limit_batch_size: 10000
     outs:
+    - path: data/fit_predictions/
+      hash: md5
+      md5: 89063bb3b725afe61b6ed5edb724bb06.dir
+      size: 3090627
+      nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 837a42a0655862229620495c645d5fed.dir
+      md5: c90eef03b5a76175506c048e88a401dd.dir
-      size: 342382387
+      size: 783489255
-      nfiles: 26
+      nfiles: 32
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: f8a394b86c33dc1b3ce97abed803c8f1
+      md5: 33f18fa6b7dda535de09733d4792c0fc
-      size: 220
+      size: 217
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -84,13 +94,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 837a42a0655862229620495c645d5fed.dir
+      md5: c90eef03b5a76175506c048e88a401dd.dir
-      size: 342382387
+      size: 783489255
-      nfiles: 26
+      nfiles: 32
     - path: data/prepared_data
       hash: md5
-      md5: 613ddd198a29002e6e05a2d60275d924.dir
+      md5: dcd41f841c67b474a81a14e683646237.dir
-      size: 32746979
+      size: 36317761
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -102,8 +112,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 75f8326e99eb9e1032728208229ec37b.dir
+      md5: 406e2ebe33d6abed9042f137d8c0d2bf.dir
-      size: 314002
+      size: 520735
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -114,13 +124,13 @@ stages:
       size: 3448
     - path: data/predictions
       hash: md5
-      md5: 75f8326e99eb9e1032728208229ec37b.dir
+      md5: 406e2ebe33d6abed9042f137d8c0d2bf.dir
-      size: 314002
+      size: 520735
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 613ddd198a29002e6e05a2d60275d924.dir
+      md5: dcd41f841c67b474a81a14e683646237.dir
-      size: 32746979
+      size: 36317761
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -130,8 +140,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 269e89593f5e7ceb507c31dac2c2dd35
+      md5: cc1ad408f2d9d3128df71822a38ea85e
-      size: 220
+      size: 218
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps:

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

@@ -38,6 +38,7 @@ stages:
     - configs/build_model.yaml:
     outs:
     - data/model/
+    - data/fit_predictions/
     - metrics/fit_metrics.json
     always_changed: true
   generate_predictions: