use 0.9 training data

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

@@ -19,7 +19,7 @@ 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
-    train_proportion: 1
+    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

@@ -45,12 +45,12 @@ stages:
         default.prepare_data.output_dataclient_type: local
         default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet
         default.prepare_data.output_train_filepath: ./data/prepared_data/train.parquet
-        default.prepare_data.train_proportion: 1
+        default.prepare_data.train_proportion: 0.9
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 35d7daa8144434e188ba3b1da4bcf328.dir
-      size: 33946500
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
+      size: 36691842
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -61,8 +61,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 35d7daa8144434e188ba3b1da4bcf328.dir
-      size: 33946500
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
+      size: 36691842
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -95,18 +95,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 19d033f5abfa9b064c3e52815e607ced.dir
-      size: 3927492
+      md5: 5a3091120d3497fa00b994d91bc7e5eb.dir
+      size: 3664806
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: f159d40353b01ffdcf1b1b490c019f1f.dir
-      size: 787748148
-      nfiles: 32
+      md5: 074da8dcfa515b9f3d082b21c7d76616.dir
+      size: 721558897
+      nfiles: 31
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: e69d56ab9d82f23f2aa66001bd9bebbc
-      size: 229
+      md5: 728a49dcef5a98182325df455f929a33
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -116,13 +116,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: f159d40353b01ffdcf1b1b490c019f1f.dir
-      size: 787748148
-      nfiles: 32
+      md5: 074da8dcfa515b9f3d082b21c7d76616.dir
+      size: 721558897
+      nfiles: 31
     - path: data/prepared_data
       hash: md5
-      md5: 35d7daa8144434e188ba3b1da4bcf328.dir
-      size: 33946500
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
+      size: 36691842
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -134,8 +134,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 50d0c76fc56c6290babeff1c84750316.dir
-      size: 651956
+      md5: 680f51234d214d4cab9e6a064c75fc5d.dir
+      size: 499546
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -146,13 +146,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 50d0c76fc56c6290babeff1c84750316.dir
-      size: 651956
+      md5: 680f51234d214d4cab9e6a064c75fc5d.dir
+      size: 499546
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 35d7daa8144434e188ba3b1da4bcf328.dir
-      size: 33946500
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
+      size: 36691842
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -162,5 +162,5 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 542b982d6aa9fe0fdb89611e4299cb1e
-      size: 228
+      md5: 67b7ab30a4b0839d20bc6eb0c84e4dd1
+      size: 226