Merge pull request #117 from Hestia-Homes/sap-dev

Sap dev

MODEL_REGISTRY.md

@@ -8,9 +8,9 @@
         "active": true
     },
     "sap": {
-        "version": "v0.12.0",
+        "version": "v0.14.0",
         "stage": {
-            "dev": "v0.12.0"
+            "dev": "v0.14.0"
         },
         "registered": true,
         "active": true

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

@@ -6,6 +6,8 @@ default:
       # - s3://retrofit-data-dev/scenario_data/22-03-2024-19-20-09/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/24-03-2024-20-23-25/recommendations_scoring_data.parquet
       # - s3://retrofit-data-dev/scenario_data/27-03-2024-11-38-15/recommendations_scoring_data.parquet
-      - s3://retrofit-data-dev/scenario_data/26-05-2024-08-47-45/recommendations_scoring_data.parquet
+      # - s3://retrofit-data-dev/scenario_data/26-05-2024-08-47-45/recommendations_scoring_data.parquet
+      # - s3://retrofit-data-dev/scenario_data/26-05-2024-10-44-53/recommendations_scoring_data.parquet
+      - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/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 +19,9 @@ default:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
     # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet
-    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-25-08-36-36/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-25-08-36-36/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-26-10-31-39/dataset_rooms.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/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

@@ -40,7 +40,7 @@ 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/2024-05-25-08-36-36/dataset_rooms.parquet
+          s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/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
@@ -49,8 +49,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 26bbe6b1dafae18eb50689604b925c87.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45002224
+      size: 45056059
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -61,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 26bbe6b1dafae18eb50689604b925c87.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45002224
+      size: 45056059
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -94,18 +94,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 7ba44b4af6ecedf3ffebcf7512731d3d.dir
+      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
-      size: 3348905
+      size: 3349989
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: ef62a6f9b9336fb5b648589d6e0d54d6.dir
+      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 737305293
+      size: 773523079
-      nfiles: 35
+      nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 38600703e1ece1447e5d0fd80b4de8b7
+      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
-      size: 217
+      size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,13 +115,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: ef62a6f9b9336fb5b648589d6e0d54d6.dir
+      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 737305293
+      size: 773523079
-      nfiles: 35
+      nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: 26bbe6b1dafae18eb50689604b925c87.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45002224
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,8 +133,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 7d88320b1cd3c690032438fad6cb2200.dir
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463523
+      size: 463197
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -145,13 +145,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 7d88320b1cd3c690032438fad6cb2200.dir
+      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463523
+      size: 463197
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 26bbe6b1dafae18eb50689604b925c87.dir
+      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45002224
+      size: 45056059
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,30 +161,30 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: e17ee59f3a04178a153c5746bf897e74
+      md5: 3e08df02fd5c5d094bcf936e1338d596
       size: 223
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
     - path: 5_generate_scenarios.py
       hash: md5
-      md5: a18f6c6ae2082f038df47386cf3e418e
+      md5: 40506749fefd926d47c60ff5b16db307
-      size: 4896
+      size: 5337
     params:
       configs/scenarios.yaml:
         default.scenarios:
           input_dataclient_type: aws-s3
           output_dataclient_type: local
           scenario_data_filepaths:
-          - s3://retrofit-data-dev/scenario_data/26-05-2024-08-47-45/recommendations_scoring_data.parquet
+          - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/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: 84fcae91af1480ee0c8fc1616af359b3
+      md5: fa4d6d7bbd7818613800da5f8f37ea96
       size: 363
     - path: metrics/scenario_table.md
       hash: md5
-      md5: 8571ff812c2f7c71eb0b1534ff6ecff5
+      md5: d6baf100a1623cc2467c2f8221d314c9
       size: 2133