SIENTIAPDE-1646

Update README, requirements, and E2E tests for improved configuration and functionality

- Enhanced the README with updated model configuration examples, including the addition of an alias for production.
- Removed the `requirements-light.txt` file and updated `requirements-local.txt` and `requirements.txt` to replace `asyncua` with `opcua`.
- Refactored E2E test scenarios to utilize scenario input files for better maintainability and clarity.
- Improved test coverage for MinIO offload functionality and added new helper functions for loading scenario inputs.
- Updated `values.yaml` to reflect new global configurations and environment variables for the laborious worker.

e2e/scenario_inputs/drift_base.json

@@ -0,0 +1,14 @@
+{
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "source_table_name": "laborious_data",
+  "target_table_name": "drift",
+  "interval": 60,
+  "drift_metrics": ["kolmogorov_smirnov", "jensen_shannon", "wasserstein"],
+  "chunk_period": "min",
+  "model_config": {
+    "target": "sensor_1"
+  }
+}

e2e/scenario_inputs/format_export_base.json

@@ -0,0 +1,37 @@
+{
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data",
+  "input_filters": {
+    "EMPTY_DATA": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_transform_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_predict_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "path_priority": ["STOP", "CONTINUE", "REPEAT"],
+  "opc_output_config": {},
+  "pi_web_api_output_config": {},
+  "save_transform": true,
+  "prediction_store_policy": "lts:1",
+  "model_config": {
+    "retention_minutes": 0,
+    "target": "sensor_1"
+  },
+  "datetime_columns": ["timestamp", "created_at"]
+}

e2e/scenario_inputs/main_happy_path.json

@@ -0,0 +1,45 @@
+{
+  "metadata": {
+    "metadata": {
+      "model_id": "{{MODEL_ID}}",
+      "model_name": "test_model",
+      "schedule_name": "test-schedule",
+      "workflow_name": "predictions_batch"
+    }
+  },
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data",
+  "input_filters": {
+    "EMPTY_DATA": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_transform_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_predict_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "path_priority": ["STOP", "CONTINUE", "REPEAT"],
+  "opc_output_config": {},
+  "pi_web_api_output_config": {},
+  "save_transform": true,
+  "prediction_store_policy": "lts:1",
+  "model_config": {
+    "target": "sensor_1",
+    "retention_minutes": 0
+  },
+  "datetime_columns": ["timestamp", "created_at"]
+}

e2e/scenario_inputs/main_invalid_datetime.json

@@ -0,0 +1,45 @@
+{
+  "metadata": {
+    "metadata": {
+      "model_id": "{{MODEL_ID}}",
+      "model_name": "test_model",
+      "schedule_name": "test-schedule",
+      "workflow_name": "predictions_batch"
+    }
+  },
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT timestamp, variable, value FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data",
+  "input_filters": {
+    "EMPTY_DATA": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_transform_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_predict_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "path_priority": ["STOP", "CONTINUE", "REPEAT"],
+  "opc_output_config": {},
+  "pi_web_api_output_config": {},
+  "save_transform": true,
+  "prediction_store_policy": "lts:1",
+  "model_config": {
+    "target": "sensor_1",
+    "retention_minutes": 0
+  },
+  "datetime_columns": ["nonexistent_column"]
+}

e2e/scenario_inputs/main_missing_required.json

@@ -0,0 +1,16 @@
+{
+  "metadata": {
+    "metadata": {
+      "model_id": "{{MODEL_ID}}",
+      "model_name": "test_model",
+      "schedule_name": "test-schedule",
+      "workflow_name": "predictions_batch"
+    }
+  },
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data"
+}

e2e/scenario_inputs/main_sql_error.json

@@ -0,0 +1,44 @@
+{
+  "metadata": {
+    "metadata": {
+      "model_id": "{{MODEL_ID}}",
+      "model_name": "test_model",
+      "schedule_name": "test-schedule",
+      "workflow_name": "predictions_batch"
+    }
+  },
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT * FROM nonexistent_table WHERE invalid_syntax =",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data",
+  "input_filters": {
+    "EMPTY_DATA": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_transform_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_predict_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "path_priority": ["STOP", "CONTINUE", "REPEAT"],
+  "opc_output_config": {},
+  "pi_web_api_output_config": {},
+  "save_transform": true,
+  "prediction_store_policy": "lts:1",
+  "model_config": {
+    "target": "sensor_1",
+    "retention_minutes": 0
+  }
+}

e2e/scenario_inputs/minimal_retrain_base.json

@@ -0,0 +1,12 @@
+{
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "retrain_reports",
+  "datetime_columns": ["timestamp", "created_at"],
+  "model_config": {
+    "target": "sensor_1"
+  }
+}

e2e/scenario_inputs/minio_offload_load_query.json

@@ -0,0 +1,11 @@
+{
+  "metadata": {
+    "schedule_name": "test-schedule",
+    "model_name": "test_model",
+    "model_id": "{{MODEL_ID}}",
+    "workflow_name": "predictions_batch"
+  },
+  "query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "model_name": "test_model",
+  "datetime_columns": ["timestamp", "created_at"]
+}

e2e/scenario_inputs/minio_offload_workflow.json

@@ -0,0 +1,37 @@
+{
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data",
+  "input_filters": {
+    "EMPTY_DATA": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_transform_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_predict_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "path_priority": ["STOP", "CONTINUE", "REPEAT"],
+  "opc_output_config": {},
+  "pi_web_api_output_config": {},
+  "save_transform": false,
+  "prediction_store_policy": "lts:1",
+  "model_config": {
+    "retention_minutes": 0,
+    "target": "sensor_1"
+  },
+  "datetime_columns": ["timestamp", "created_at"]
+}

e2e/scenario_inputs/prediction_process_base.json

@@ -0,0 +1,39 @@
+{
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "query": "SELECT timestamp, variable, value, created_at FROM predictions_schema.laborious_data WHERE model_id = {{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "table_name": "predictions",
+  "transform_table_name": "transformed_data",
+  "input_filters": {
+    "SPECIFIC_VARIABLES_NULL_VALUES": {
+      "POLICY": "CONTINUE",
+      "CONFIG": {
+        "variables": ["sensor_1"]
+      }
+    }
+  },
+  "mlflow_transform_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "mlflow_predict_filters": {
+    "API_ERROR": {
+      "POLICY": "STOP",
+      "CONFIG": {}
+    }
+  },
+  "path_priority": ["STOP", "CONTINUE", "REPEAT"],
+  "opc_output_config": {},
+  "pi_web_api_output_config": {},
+  "save_transform": true,
+  "prediction_store_policy": "lts:1",
+  "model_config": {
+    "retention_minutes": 0,
+    "target": "sensor_1"
+  },
+  "datetime_columns": ["timestamp", "created_at"]
+}

e2e/scenario_inputs/simple_metrics_base.json

@@ -0,0 +1,14 @@
+{
+  "schedule_name": "test-schedule",
+  "model_name": "test_model",
+  "model_id": "{{MODEL_ID}}",
+  "schema": "predictions_schema",
+  "predictions_table_name": "predictions",
+  "data_table_name": "laborious_data",
+  "target_table_name": "simple_metrics_data",
+  "interval_minutes": 60,
+  "metrics": ["rmse", "mse", "mae", "r2"],
+  "model_config": {
+    "target": "sensor_target"
+  }
+}