try the scenario cml

MODEL_REGISTRY.md

@@ -8,9 +8,9 @@
         "active": true
     },
     "sap": {
-        "version": "v0.9.0",
+        "version": "v0.10.0",
         "stage": {
-            "dev": "v0.9.0"
+            "dev": "v0.10.0"
         },
         "registered": true,
         "active": true

modules/ml-pipeline/src/pipeline/README.md

@@ -37,3 +37,4 @@ Workflow:
     - This experiment will have the corresponding .dvc files for the hashed model and data
 - Use version control as normal
     - git add, git commit etc
+- To revert change, use `git checkout {COMMIT_HASH}`, followed by `git switch -c {NEW_BRANCH_NAME}`

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

@@ -16,6 +16,6 @@ default:
       eval_metric: mean_squared_error #mean_absolute_error
       time_limit: 60
       presets: medium_quality
-      excluded_model_types: ['RF', 'NN_TORCH', 'KNN', 'XT', 'CAT', 'FASTAI']
+      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/settings.yaml

@@ -22,8 +22,7 @@ default:
     # 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
-    data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_rooms.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
     # data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
     train_proportion: 1
     output_train_filepath: ./data/prepared_data/train.parquet

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

@@ -22,7 +22,7 @@ stages:
         default.feature_processor.feature_processor_config.subsample_seed: 0
         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/dataset_rooms.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
@@ -65,11 +65,11 @@ stages:
               presets: medium_quality
               excluded_model_types:
               - RF
+              - FASTAI
+              - CAT
               - NN_TORCH
               - KNN
               - XT
-              - CAT
-              - FASTAI
               infer_limit: 0.05
               infer_limit_batch_size: 10000
     outs: