commit first heat-model

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

@@ -13,7 +13,7 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 4000
+      time_limit: 400
       presets: medium_quality
       excluded_model_types: ['KNN', 'RF']
       infer_limit: 0.05

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

@@ -5,8 +5,8 @@ stages:
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: c9f030df733e318b80d1fa91b7732f79
-      size: 5132
+      md5: 896d3d88a4a9f68d174efe71dc089517
+      size: 4222
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
@@ -20,7 +20,7 @@ stages:
         default.feature_processor.feature_processor_config.subsample_seed: 0
         default.feature_processor.feature_processor_config.target: HEAT_DEMAND_ENDING
         default.feature_processor.feature_processor_type: dataframe
-        default.prepare_data.data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
+        default.prepare_data.data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_test.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
@@ -29,20 +29,20 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: e0be70d5025e40dd0d655d9949f72130.dir
-      size: 31800776
+      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
+      size: 34480114
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
     deps:
     - path: 2_build_model.py
       hash: md5
-      md5: 84699d208874c52accaff61c6af9bb0a
-      size: 5359
+      md5: b824822475c222521516493e68eef9c5
+      size: 4149
     - path: data/prepared_data
       hash: md5
-      md5: e0be70d5025e40dd0d655d9949f72130.dir
-      size: 31800776
+      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
+      size: 34480114
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -58,37 +58,39 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 4000
+              time_limit: 400
               presets: medium_quality
               excluded_model_types:
               - KNN
               - RF
+              infer_limit: 0.05
+              infer_limit_batch_size: 10000
     outs:
     - path: data/model/
       hash: md5
-      md5: 14ca33cde5e86770135f768abaf84978.dir
-      size: 422447808
-      nfiles: 27
+      md5: 452eba2d92233e81d321814aacefe5c2.dir
+      size: 323127043
+      nfiles: 24
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 41bfb8d2da8f06d1864d73ce125cc6aa
-      size: 221
+      md5: 888124b56e0c5008a6423e290fc5cc71
+      size: 222
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
     - path: 3_generate_predictions.py
       hash: md5
-      md5: 5ef2856a5a977304f1ec01f9b4205262
-      size: 3028
+      md5: 0a70ad4dfe99414a75d1261c75a177b9
+      size: 2464
     - path: data/model
       hash: md5
-      md5: 14ca33cde5e86770135f768abaf84978.dir
-      size: 422447808
-      nfiles: 27
+      md5: 452eba2d92233e81d321814aacefe5c2.dir
+      size: 323127043
+      nfiles: 24
     - path: data/prepared_data
       hash: md5
-      md5: e0be70d5025e40dd0d655d9949f72130.dir
-      size: 31800776
+      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
+      size: 34480114
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -100,25 +102,25 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 40d0c7a7fd4a15add0615e322cf341a0.dir
-      size: 352151
+      md5: f852550a0a51f0c2b120b0680c1a9b54.dir
+      size: 325890
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: 2c9fb78955a8c19cff0a098976f81d1b
-      size: 4487
+      md5: 567b1acb819e2ff432b989cdbdd4a2bf
+      size: 3448
     - path: data/predictions
       hash: md5
-      md5: 40d0c7a7fd4a15add0615e322cf341a0.dir
-      size: 352151
+      md5: f852550a0a51f0c2b120b0680c1a9b54.dir
+      size: 325890
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: e0be70d5025e40dd0d655d9949f72130.dir
-      size: 31800776
+      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
+      size: 34480114
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -128,15 +130,15 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 4e023650240e78d6ad761f1db7aac922
-      size: 220
+      md5: ed3012943593fac4ac7ad9a5499ac18f
+      size: 219
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps:
     - path: 0_startup_cleanup.py
       hash: md5
-      md5: fbb7e3b1b98b517c870f3e1df3e7f695
-      size: 1676
+      md5: b1b12f6b6393fbf8b83d23684df0a3d4
+      size: 1220
     params:
       configs/settings.yaml:
         default.startup_cleanup.artefacts: ./data