fix: downgrade sientia_do version and update CSV saving logic

- Downgraded `sientia_do` version to 1.11.0 in `requirements.txt` to address compatibility issues.
- Updated `data_manager_repository.py` to save training and test data CSVs using float-cast versions of the data, ensuring consistency in the saved outputs.
- Enhanced test coverage in `test_data_manager_repository.py` to verify the presence of the target alias in the generated CSV files.

model_manager/utils/repository/data_manager_repository.py

@@ -597,13 +597,14 @@ class DataManagerRepository(SientiaMonitoring):
         data.report_path = path.join(data.run_dir, 'report.html')
         report.save_all_sections_html(data.report_path)
 
-        # Save training data CSV
+        # Save training / validation CSVs using the same frames as the report (includes
+        # literal `target` alias for Evidently, plus predictions and float-cast features).
         data.train_data_path = path.join(data.run_dir, 'train_data.csv')
-        reference_data.to_csv(data.train_data_path, index=False)
+        reference_data_float.to_csv(data.train_data_path, index=False)
 
         # Save test data CSV
         data.test_data_path = path.join(data.run_dir, 'test_data.csv')
-        current_data.to_csv(data.test_data_path, index=False)
+        current_data_float.to_csv(data.test_data_path, index=False)
 
         # Save equation as JSON
         if data.equation is not None and data.params.model_type == 'linear_regression':

requirements.txt

@@ -3,7 +3,7 @@ psycopg2-binary==2.9.11
 sqlalchemy==2.0.49
 boto3==1.42.70
 botocore==1.42.70
-sientia_do==1.12.0
+sientia_do==1.11.0
 sientia_model==0.8.1
 prometheus-client==0.23.1
 beautifulsoup4==4.12.3

tests/utils/repository/test_data_manager_repository.py

@@ -494,7 +494,7 @@ def test_generate_report_adds_target_alias_for_reports(tmp_path):
     ):
         instance = mrep.return_value
         instance.save_all_sections_html = Mock()
-        repo.generate_report(tmr, {})
+        out = repo.generate_report(tmr, {})
 
         kwargs = mrep.call_args.kwargs
         reference_data = kwargs['reference_data']
@@ -504,6 +504,15 @@ def test_generate_report_adds_target_alias_for_reports(tmp_path):
         assert reference_data['target'].equals(reference_data['t'])
         assert current_data['target'].equals(current_data['t'])
 
+        assert out.train_data_path is not None
+        assert out.test_data_path is not None
+        train_csv = pd.read_csv(out.train_data_path)
+        test_csv = pd.read_csv(out.test_data_path)
+        assert 'target' in train_csv.columns
+        assert 'target' in test_csv.columns
+        assert train_csv['target'].equals(train_csv['t'])
+        assert test_csv['target'].equals(test_csv['t'])
+
 
 def test_generate_report_skips_equation_file_when_not_linear(tmp_path):
     repo = dmr.DataManagerRepository(MagicMock())