new model

.github/workflows/MLPipelinePullRequest.yml

@@ -85,7 +85,7 @@ jobs:
 
     - name: Test Lambda endpoint
       run: |
-        sleep 5
+        sleep 2
         curl -X POST "http://localhost:9000/2015-03-31/functions/function/invocations" \
           -H "Content-Type: application/json" \
           -d "{\"body\": \"{\\\"file_location\\\": \\\"s3://retrofit-data-dev/sap_change_model/sample_data_for_cicd/${timestamp}/sample_test.parquet\\\", \\\"property_id\\\": 1, \\\"portfolio_id\\\": 4, \\\"created_at\\\": \\\"now\\\", \\\"testing\\\": true}\"}"

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

@@ -14,10 +14,10 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 1800
+      time_limit: 3600
       presets: medium_quality
       excluded_model_types: ['RF', 'CAT', 'NN_TORCH', 'KNN', 'XT']
-      infer_limit: 0.0005
+      infer_limit: 1
       infer_limit_batch_size: 10000
       fit_strategy: "parallel"
       ag_args_ensemble: {'num_folds_parallel': 2}

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

@@ -61,8 +61,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: bdf32829fa7d4084293e54f73084a25c.dir
-      size: 46126494
+      md5: 54204b6a31ba369cfbd26b9b25bfa355.dir
+      size: 46095230
       nfiles: 3
   build_model:
     cmd: python 2_build_model.py
@@ -73,8 +73,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: bdf32829fa7d4084293e54f73084a25c.dir
-      size: 46126494
+      md5: 54204b6a31ba369cfbd26b9b25bfa355.dir
+      size: 46095230
       nfiles: 3
     params:
       configs/build_model.yaml:
@@ -91,7 +91,7 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 1800
+              time_limit: 3600
               presets: medium_quality
               excluded_model_types:
               - RF
@@ -99,7 +99,7 @@ stages:
               - NN_TORCH
               - KNN
               - XT
-              infer_limit: 0.0005
+              infer_limit: 1
               infer_limit_batch_size: 10000
               fit_strategy: parallel
               ag_args_ensemble:
@@ -174,18 +174,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: bb3a39098652aee04227b8157cffe6dc.dir
-      size: 3475209
+      md5: f29cfa6a2dadf4fbe81813b3d517fd10.dir
+      size: 3474971
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 057ecca4ca9b6cabc60d81b36f5efee1.dir
-      size: 719633310
-      nfiles: 33
+      md5: 1156f526fe9d11134e49f805c41c3781.dir
+      size: 763384978
+      nfiles: 35
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 5b63b6c51867279dea639df1c50b4416
-      size: 225
+      md5: 24b2f7c34e5e08b66f39289afac5d795
+      size: 226
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -195,13 +195,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 057ecca4ca9b6cabc60d81b36f5efee1.dir
-      size: 719633310
-      nfiles: 33
+      md5: 1156f526fe9d11134e49f805c41c3781.dir
+      size: 763384978
+      nfiles: 35
     - path: data/prepared_data
       hash: md5
-      md5: bdf32829fa7d4084293e54f73084a25c.dir
-      size: 46126494
+      md5: 54204b6a31ba369cfbd26b9b25bfa355.dir
+      size: 46095230
       nfiles: 3
     params:
       configs/settings.yaml:
@@ -215,8 +215,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 76dd44be410b11c62f701c645a9003a9.dir
-      size: 484698
+      md5: e9b1d9b94d1e44c999c17b7a2d096db9.dir
+      size: 484818
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -227,13 +227,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 76dd44be410b11c62f701c645a9003a9.dir
-      size: 484698
+      md5: e9b1d9b94d1e44c999c17b7a2d096db9.dir
+      size: 484818
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: bdf32829fa7d4084293e54f73084a25c.dir
-      size: 46126494
+      md5: 54204b6a31ba369cfbd26b9b25bfa355.dir
+      size: 46095230
       nfiles: 3
     params:
       configs/settings.yaml:
@@ -243,8 +243,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: de4098ee21d5efbf8b769471ae2fa20f
-      size: 224
+      md5: 88a4e49229cc3c329faf5bf0fcae3318
+      size: 226
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps:
@@ -264,9 +264,9 @@ stages:
     outs:
     - path: metrics/scenario_metrics.md
       hash: md5
-      md5: d4f3c1eeee96720270e2467fc50b0b29
+      md5: 3326cc2e59ac1671d99d3e1f27131f54
       size: 356
     - path: metrics/scenario_table.md
       hash: md5
-      md5: 56e39ca1f444b0a97ce894cf9ff90d32
+      md5: 0a434e055463ec9ade5de2de9bde7154
       size: 872