Merge pull request #103 from Hestia-Homes/sap-dev-revert

revert change on sap-dev-model

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: 4000
       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
@@ -31,8 +31,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 8f0f5481075094460ab852ace2fa9b7a.dir
-      size: 43692138
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -43,8 +43,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 8f0f5481075094460ab852ace2fa9b7a.dir
-      size: 43692138
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -65,28 +65,28 @@ 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:
     - path: data/fit_predictions/
       hash: md5
-      md5: e2a05a84a14d35516a6cda8e0a1e963c.dir
-      size: 3681005
+      md5: e0a11ac6e4adf69d6180c0217c639a0e.dir
+      size: 3680908
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 7b0382d001ed2bd7aec5c8112f69d129.dir
-      size: 793365790
-      nfiles: 30
+      md5: bdaaf823857f9dc7b6ee2d4b88927cc1.dir
+      size: 805896324
+      nfiles: 31
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: bcfd8d3bd3af858fa3dc26433bc8cd9e
-      size: 224
+      md5: 0ed5b1141bbb8bc3156e7c056b29f3cd
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -96,13 +96,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 7b0382d001ed2bd7aec5c8112f69d129.dir
-      size: 793365790
-      nfiles: 30
+      md5: bdaaf823857f9dc7b6ee2d4b88927cc1.dir
+      size: 805896324
+      nfiles: 31
     - path: data/prepared_data
       hash: md5
-      md5: 8f0f5481075094460ab852ace2fa9b7a.dir
-      size: 43692138
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -114,8 +114,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 90b5275b5d9829a42573ade3f5a025d2.dir
-      size: 648526
+      md5: 38707d16ae1e2330cc03f524db9cdd60.dir
+      size: 648730
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -126,13 +126,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 90b5275b5d9829a42573ade3f5a025d2.dir
-      size: 648526
+      md5: 38707d16ae1e2330cc03f524db9cdd60.dir
+      size: 648730
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 8f0f5481075094460ab852ace2fa9b7a.dir
-      size: 43692138
+      md5: 3c77fa10cd1cd503eb4d2540394629f6.dir
+      size: 42626894
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -142,7 +142,7 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: be48389ba2755e6c18e41243aaa9bb81
+      md5: 145e7ac84ab4a4407b23695a632b4d91
       size: 226
   startup_cleanup:
     cmd: python 0_startup_cleanup.py