SIENTIAPDE-1646

SIENTIAPDE-1646 Add new scheduling configurations and remove outdated documentation

- Introduced new scheduling configurations for minimal retrain, drift analysis, and simple metrics in `input_sample.json`.
- Removed obsolete documentation files related to drift analysis and E2E test reports to streamline project resources.
- Updated E2E tests for minimal retrain to enhance reporting and error handling during model retraining processes.
This commit is contained in:
vitor-aignosi
2026-05-11 17:02:08 -03:00
parent 16ea436e45
commit 4989cfcb3c
5 changed files with 182 additions and 131 deletions

View File

@@ -67,6 +67,77 @@
"timestamp",
"created_at"
]
},
{
"schedule_name": "minimal-retrain-test-runtime",
"model_id": "1001",
"model_name": "test-runtime",
"workflow_type": "minimal_retrain",
"frequency": "1h",
"max_retry_policy": 1,
"query": "select * from sientia_data.laborious_data where model_id = 1 and \"timestamp\" > NOW() - INTERVAL '60 minutes' order by \"timestamp\" desc;",
"schema": "sientia_data",
"table_name": "log_retrain",
"datetime_columns": ["timestamp", "created_at"],
"model_config": {
"target": "Square"
},
"active": true,
"updated_at": {
"$date": "2026-05-07T23:35:01.600Z"
}
},
{
"schedule_name": "drift-test-runtime",
"model_id": "1001",
"model_name": "test-runtime",
"workflow_type": "drift",
"frequency": "5m",
"offset": "2m",
"max_retry_policy": 1,
"execution_timeout_seconds": 300,
"task_timeout_seconds": 300,
"interval": 5,
"drift_metrics": [
"kolmogorov_smirnov",
"jensen_shannon",
"wasserstein"
],
"chunk_period": "min",
"schema": "sientia_data",
"source_table_name": "laborious_data",
"target_table_name": "drift_metrics",
"model_config": {
"target": "Square"
},
"active": true,
"updated_at": {
"$date": "2026-05-07T23:35:01.600Z"
}
},
{
"schedule_name": "simple-metrics-test-runtime",
"model_id": "1001",
"model_name": "test-runtime",
"workflow_type": "simple_metrics",
"frequency": "5m",
"offset": "2m",
"max_retry_policy": 1,
"execution_timeout_seconds": 300,
"task_timeout_seconds": 300,
"interval_minutes": 5,
"metrics": ["rmse", "mse", "mae", "r2"],
"schema": "sientia_data",
"predictions_table_name": "predictions",
"data_table_name": "laborious_data",
"target_table_name": "simple_metrics",
"model_config": {
"target": "Square"
},
"active": true,
"updated_at": {
"$date": "2026-05-07T23:35:01.600Z"
}
}
]
}