sap model with changed u values data

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

@@ -5,6 +5,7 @@ default:
     scenario_data_filepaths:
       # - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/07-10-2024-16-26-06/recommendations_scoring_data.parquet
-      - s3://retrofit-data-dev/scenario_data/08-10-2024-15-07-33/recommendations_scoring_data.parquet
+      # - s3://retrofit-data-dev/scenario_data/08-10-2024-15-07-33/recommendations_scoring_data.parquet
+      - s3://retrofit-data-dev/scenario_data/08-10-2024-22-18-44/recommendations_scoring_data.parquet
     comparison_output_filepath: ./metrics/scenario_table.md
     metrics_output_filepath: ./metrics/scenario_metrics.md

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

@@ -19,7 +19,8 @@ default:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
     # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
-    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-10-03-22-57-23/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-10-03-22-57-23/dataset_rooms.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-10-08-21-58-03/dataset_rooms.parquet
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet

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

@@ -46,7 +46,7 @@ stages:
         default.feature_processor.feature_processor_config.target: sap_ending
         default.feature_processor.feature_processor_type: dataframe
         default.prepare_data.data_filepath:
-          s3://retrofit-data-dev/sap_change_model/2024-10-03-22-57-23/dataset_rooms.parquet
+          s3://retrofit-data-dev/sap_change_model/2024-10-08-21-58-03/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
@@ -55,8 +55,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 8ce9c629a531d54fa9b0bfc305391400.dir
-      size: 49665833
+      md5: cd82e70e3cfcd0421cddf9a2c4b3e476.dir
+      size: 49655735
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -67,8 +67,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 8ce9c629a531d54fa9b0bfc305391400.dir
-      size: 49665833
+      md5: cd82e70e3cfcd0421cddf9a2c4b3e476.dir
+      size: 49655735
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -100,18 +100,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 9dafd875d76676a06890af9be8778567.dir
-      size: 3617506
+      md5: a1c97fa17adae60ee97696c95cfebe7e.dir
+      size: 3618488
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 36fb8323508e968a297d650954ccbc58.dir
-      size: 800833479
-      nfiles: 36
+      md5: 7e6f38163a2cfe208ace26702ae28793.dir
+      size: 762167138
+      nfiles: 35
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: e2bc34ae26afbb854f0b021d12b1b569
-      size: 223
+      md5: 8a6db7d72f9b4b8a5e411beaa3a2a413
+      size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -121,13 +121,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 36fb8323508e968a297d650954ccbc58.dir
-      size: 800833479
-      nfiles: 36
+      md5: 7e6f38163a2cfe208ace26702ae28793.dir
+      size: 762167138
+      nfiles: 35
     - path: data/prepared_data
       hash: md5
-      md5: 8ce9c629a531d54fa9b0bfc305391400.dir
-      size: 49665833
+      md5: cd82e70e3cfcd0421cddf9a2c4b3e476.dir
+      size: 49655735
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -139,8 +139,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 8f4de36de171006cb6d9eacff7718ba3.dir
-      size: 508400
+      md5: 14729e943275748a19e86cf47d6561ee.dir
+      size: 508468
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -151,13 +151,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 8f4de36de171006cb6d9eacff7718ba3.dir
-      size: 508400
+      md5: 14729e943275748a19e86cf47d6561ee.dir
+      size: 508468
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 8ce9c629a531d54fa9b0bfc305391400.dir
-      size: 49665833
+      md5: cd82e70e3cfcd0421cddf9a2c4b3e476.dir
+      size: 49655735
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -167,8 +167,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 58e25eb5e1699dbb33e78af9ba4c2964
-      size: 222
+      md5: e076cba5f5737fd6d95931931411fdd0
+      size: 225
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
@@ -182,15 +182,15 @@ stages:
           input_dataclient_type: aws-s3
           output_dataclient_type: local
           scenario_data_filepaths:
-          - s3://retrofit-data-dev/scenario_data/08-10-2024-15-07-33/recommendations_scoring_data.parquet
+          - s3://retrofit-data-dev/scenario_data/08-10-2024-22-18-44/recommendations_scoring_data.parquet
           comparison_output_filepath: ./metrics/scenario_table.md
           metrics_output_filepath: ./metrics/scenario_metrics.md
     outs:
     - path: metrics/scenario_metrics.md
       hash: md5
-      md5: 746ffa7d10fcdceaf2330d07c7ee623b
-      size: 363
+      md5: 3e1047665bc18e92bf0f4216b9cc0c88
+      size: 356
     - path: metrics/scenario_table.md
       hash: md5
-      md5: 3b7dfc36054bce065f849423abf31a5d
-      size: 969
+      md5: 71d4052f1ab986253bce9268644cc421
+      size: 872