chore: bump version to 2.0.3

SIENTIAPDE-2201: Keep the timestamp column in train/test data CSVs

.github/workflows/deploy.yml

@@ -20,7 +20,7 @@ jobs:
       branch_name: ${{ github.event.pull_request.head.ref }}
       project_name: 'model-manager'
       chart_name: 'model-manager'
-      env_list_path: '.global.env'
+      env_list_path: '[".global.env"]'
       update_version_in: '["pyproject"]'
       create_tarball: ${{ github.event_name == 'pull_request' }}
       mirror: true

model_manager/utils/repository/data_manager_repository.py

@@ -527,6 +527,32 @@ class DataManagerRepository(SientiaMonitoring):
             self.error(error_msg, metadata)
             raise OSError(error_msg) from e
 
+    def _save_data_csv(
+        self, frame: pd.DataFrame, file_path: str, metadata: dict[str, Any] | None = None
+    ) -> None:
+        """
+        Write a train/test frame to CSV with its time index as a ``timestamp`` column.
+
+        laborious drift reads ``test_data.csv`` from MLflow as its reference and needs
+        ``timestamp`` (SIENTIAPDE-2201). If a column already has that name, the frame is
+        written without the index and that model's drift keeps falling back to the target
+        window: training never fails over drift.
+
+        Args:
+            frame: Frame indexed by the UTC training timestamps.
+            file_path: Destination CSV path.
+            metadata: Workflow metadata for logging.
+        """
+        if 'timestamp' in frame.columns:
+            self.warning(
+                f"Column 'timestamp' already exists; {path.basename(file_path)} saved without "
+                'the time column (drift reference falls back to the target window)',
+                metadata,
+            )
+            frame.to_csv(file_path, index=False)
+            return
+        frame.to_csv(file_path, index_label='timestamp')
+
     def generate_report(
         self, data: TrainModelResult, metadata: dict[str, Any] | None = None
     ) -> TrainModelResult:
@@ -598,11 +624,11 @@ class DataManagerRepository(SientiaMonitoring):
         # 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_float.to_csv(data.train_data_path, index=False)
+        self._save_data_csv(reference_data_float, data.train_data_path, metadata)
 
         # Save test data CSV
         data.test_data_path = path.join(data.run_dir, 'test_data.csv')
-        current_data_float.to_csv(data.test_data_path, index=False)
+        self._save_data_csv(current_data_float, data.test_data_path, metadata)
 
         # Save equation as JSON
         if data.equation is not None and data.params.model_type == 'linear_regression':

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "model-manager"
-version = "2.0.2"
+version = "2.0.3"
 description = "Sientia DataOps Model Manager - ML Model Orchestration System"
 readme = "README.md"
 requires-python = ">=3.11"

tests/utils/repository/test_data_manager_repository.py

@@ -514,6 +514,58 @@ def test_generate_report_adds_target_alias_for_reports(tmp_path):
         assert test_csv['target'].equals(test_csv['t'])
 
 
+_UTC_INDEX = pd.DatetimeIndex(['2024-01-01 02:00', '2024-01-01 01:00'], tz='UTC')
+
+
+def _dated_result(**train_columns: list[float]) -> TrainModelResult:
+    """Frames indexed by UTC time, like prepare_training_data + predict produce them."""
+    columns = train_columns or {'v1': [1.0, 2.0], 't': [1.0, 2.0]}
+    return TrainModelResult(
+        params=TrainModelParams.from_dict(_minimal_dict_for_prepare()),
+        train_data=pd.DataFrame(columns, index=_UTC_INDEX),
+        val_data=pd.DataFrame(columns, index=_UTC_INDEX),
+        y_train_pred=pd.DataFrame({'t': [1.0, 2.0]}, index=_UTC_INDEX),
+        y_pred=pd.DataFrame({'t': [1.0, 2.0]}, index=_UTC_INDEX),
+        run_name='testrun',
+    )
+
+
+def _generate_report(repo, tmr: TrainModelResult, tmp_path) -> TrainModelResult:
+    with (
+        patch.object(repo, '_get_reports_directory', return_value=str(tmp_path)),
+        patch('model_manager.utils.repository.data_manager_repository.Reports'),
+    ):
+        return repo.generate_report(tmr, {})
+
+
+def test_generate_report_csvs_keep_the_time_index_as_timestamp(tmp_path):
+    """laborious drift reads test_data.csv as its reference and needs ``timestamp``."""
+    repo = dmr.DataManagerRepository(MagicMock())
+
+    out = _generate_report(repo, _dated_result(), tmp_path)
+
+    for csv_path in (out.train_data_path, out.test_data_path):
+        csv = pd.read_csv(csv_path)
+        assert list(csv.columns) == ['timestamp', 'prediction', 'v1', 't', 'target']
+        assert pd.to_datetime(csv['timestamp']).tolist() == list(_UTC_INDEX)
+
+
+def test_generate_report_csvs_skip_timestamp_when_a_column_already_has_the_name(tmp_path):
+    """A variable literally named ``timestamp`` wins; training must not fail over drift."""
+    repo = dmr.DataManagerRepository(MagicMock())
+    tmr = _dated_result(timestamp=[5.0, 6.0], v1=[1.0, 2.0], t=[1.0, 2.0])
+
+    with patch.object(repo, 'warning') as warning:
+        out = _generate_report(repo, tmr, tmp_path)
+
+    for csv_path in (out.train_data_path, out.test_data_path):
+        csv = pd.read_csv(csv_path)
+        assert list(csv.columns) == ['prediction', 'timestamp', 'v1', 't', 'target']
+        assert csv['timestamp'].tolist() == [5.0, 6.0]
+    assert warning.call_count == 2
+    assert "Column 'timestamp' already exists" in warning.call_args.args[0]
+
+
 def test_generate_report_skips_equation_file_when_not_linear(tmp_path):
     repo = dmr.DataManagerRepository(MagicMock())
     p = TrainModelParams.from_dict(_minimal_dict_for_prepare())