SIENTIAPDE-1646

Refactor ModelMetrics to utilize DriftAnalysis for drift detection

- Replaced ModelAnalysis with DriftAnalysis in the ModelMetrics class to enhance drift detection capabilities.
- Updated method signatures and documentation to reflect the changes in target_name and return values.
- Adjusted data handling to ensure compatibility with the new analysis methods and improved clarity in the drift metrics dataframe preparation.

e2e/test_minimal_retrain.py

@@ -7,9 +7,14 @@ test container; we only validate that the workflow:
 - Loads training data via ``load_query_with_minio_offload``.
 - Calls ``retrain_model`` with a payload pointing at MinIO.
 - Calls ``update_production_model`` only when retrain succeeds.
-- Persists ``retrain_reports`` rows with all required columns; success rows
-  carry the new ``version`` / ``mlflow_run_id`` / ``mlflow_experiment_id``
-  while failure rows leave them ``NULL``.
+- Persists ``sientia_data.log_retrain`` rows with all required columns;
+  success rows carry the new ``version`` / ``mlflow_run_id`` /
+  ``mlflow_experiment_id`` while failure rows leave them ``NULL``.
+
+The production DDL drops the legacy ``id`` / ``created_at`` columns and
+moves ``mlflow_experiment_id`` to ``int8`` and ``model_id`` to ``text``.
+The stubs used here therefore emit ``experiment_id`` as an integer to fit
+the new column type.
 """
 
 from contextlib import contextmanager
@@ -30,16 +35,18 @@ from e2e.helpers import (
 from laborious.activities.activities import Activities
 from laborious.workflows.minimal_retrain import MinimalRetrain
 
+# Columns defined by the production DDL for ``sientia_data.log_retrain``.
+# The legacy ``retrain_reports`` table had ``id`` and ``created_at``; the new
+# DDL drops both. ``mlflow_experiment_id`` is ``int8`` and ``model_id`` is
+# ``text``.
 EXPECTED_RETRAIN_REPORT_COLUMNS = [
-    'id',
+    'mlflow_experiment_id',
+    'mlflow_run_id',
     'model_id',
     'model_name',
-    'timestamp',
     'status',
+    'timestamp',
     'version',
-    'mlflow_run_id',
-    'mlflow_experiment_id',
-    'created_at',
 ]
 
 
@@ -106,7 +113,9 @@ def _configure_retrain_happy_path(mlflow_repository_stub) -> None:
     def fake_start_run(**kwargs):
         run_info = MagicMock()
         run_info.run_id = 'retrain-run-id'
-        run_info.experiment_id = 'experiment-id'
+        # ``mlflow_experiment_id`` is ``int8`` in the new DDL, so we feed an
+        # integer-compatible id from the stubbed run info.
+        run_info.experiment_id = 4242
         yield run_info
 
     mlflow_repository_stub.start_run.side_effect = fake_start_run
@@ -125,10 +134,10 @@ async def test_minimal_retrain_happy_path_writes_success_report(
     mlflow_repository_stub,
 ):
     """
-    Scenario MR.1.1: Retrain succeeds. ``retrain_reports`` must contain a
-    success row with version/mlflow_run_id/mlflow_experiment_id populated and
-    the registry must have been told to promote the new version to the
-    configured alias.
+    Scenario MR.1.1: Retrain succeeds. ``sientia_data.log_retrain`` must
+    contain a success row with version/mlflow_run_id/mlflow_experiment_id
+    populated and the registry must have been told to promote the new version
+    to the configured alias.
     """
     client = temporal_test_env.client
     model_id = 711
@@ -152,10 +161,10 @@ async def test_minimal_retrain_happy_path_writes_success_report(
         rows = (
             conn.execute(
                 text(
-                    'SELECT * FROM predictions_schema.retrain_reports '
+                    'SELECT * FROM sientia_data.log_retrain '
                     'WHERE model_id = :m'
                 ),
-                {'m': model_id},
+                {'m': str(model_id)},
             )
             .mappings()
             .all()
@@ -163,17 +172,19 @@ async def test_minimal_retrain_happy_path_writes_success_report(
 
     assert len(rows) == 1
     for column in EXPECTED_RETRAIN_REPORT_COLUMNS:
-        assert column in rows[0], f'Missing retrain report column: {column}'
+        assert column in rows[0], f'Missing log_retrain column: {column}'
 
     row = rows[0]
-    assert row['model_id'] == model_id
+    # ``model_id`` is now ``text``; compare against the stringified id.
+    assert row['model_id'] == str(model_id)
     assert row['model_name'] == 'test_model'
     assert row['status'] == 'Model retrained successfully.'
     assert row['version'] == '7'
     assert row['mlflow_run_id'] == 'retrain-run-id'
-    assert row['mlflow_experiment_id'] == 'experiment-id'
+    # ``mlflow_experiment_id`` is now ``int8``; assert the integer value
+    # provided by the stubbed run info.
+    assert row['mlflow_experiment_id'] == 4242
     assert row['timestamp'] is not None
-    assert row['created_at'] is not None
 
     mlflow_repository_stub.promote_to_alias.assert_called_once()
     promote_kwargs = mlflow_repository_stub.promote_to_alias.call_args.kwargs
@@ -220,10 +231,10 @@ async def test_minimal_retrain_failure_writes_report_without_version_columns(
         rows = (
             conn.execute(
                 text(
-                    'SELECT * FROM predictions_schema.retrain_reports '
+                    'SELECT * FROM sientia_data.log_retrain '
                     'WHERE model_id = :m'
                 ),
-                {'m': model_id},
+                {'m': str(model_id)},
             )
             .mappings()
             .all()
@@ -231,7 +242,7 @@ async def test_minimal_retrain_failure_writes_report_without_version_columns(
 
     assert len(rows) == 1
     row = rows[0]
-    assert row['model_id'] == model_id
+    assert row['model_id'] == str(model_id)
     assert row['model_name'] == 'test_model'
     assert 'training did not converge' in row['status']
     assert row['version'] is None
@@ -275,10 +286,10 @@ async def test_minimal_retrain_missing_target_writes_failure_report(
         row = (
             conn.execute(
                 text(
-                    'SELECT * FROM predictions_schema.retrain_reports '
+                    'SELECT * FROM sientia_data.log_retrain '
                     'WHERE model_id = :m'
                 ),
-                {'m': model_id},
+                {'m': str(model_id)},
             )
             .mappings()
             .first()
@@ -313,7 +324,7 @@ async def test_minimal_retrain_no_training_data_does_not_persist_report(
     model_id = 731
 
     with postgres_engine.begin() as conn:
-        conn.execute(text(f'DELETE FROM predictions_schema.laborious_data WHERE model_id = {model_id}'))
+        conn.execute(text(f'DELETE FROM sientia_data.laborious_data WHERE model_id = {model_id}'))
 
     _configure_retrain_happy_path(mlflow_repository_stub)
 
@@ -329,7 +340,7 @@ async def test_minimal_retrain_no_training_data_does_not_persist_report(
 
     with postgres_engine.connect() as conn:
         count = conn.execute(
-            text('SELECT COUNT(*) FROM predictions_schema.retrain_reports WHERE model_id = :m'),
-            {'m': model_id},
+            text('SELECT COUNT(*) FROM sientia_data.log_retrain WHERE model_id = :m'),
+            {'m': str(model_id)},
         ).scalar()
     assert count == 0