445fe643fe
- Added new entries to .gitignore to exclude temporary files and training input datasets, ensuring a cleaner repository. - Included type stubs for psycopg2 in requirements-dev.txt to enhance type checking support for database interactions. - Refactored the run_training_test.py script to implement a structured approach for loading and validating training input JSON files, improving the robustness of the training workflow.
64 lines
1.5 KiB
JSON
64 lines
1.5 KiB
JSON
{
|
|
"experiment": {
|
|
"experiment_run_id": 1002,
|
|
"experiment_name": "test-experiment-xgboost",
|
|
"run_name": "test-run-xgboost",
|
|
"username": "vitor.santos@aignosi.com.br",
|
|
"status": "ORCHESTRATOR_WAITING_PROC"
|
|
},
|
|
"minio": {
|
|
"mc_alias": "suse",
|
|
"bucket_name": "model-training",
|
|
"file_name": "training-sample-dataset-1002.csv",
|
|
"local_csv": "input_dataset.csv"
|
|
},
|
|
"temporal": {
|
|
"task_queue": "train_model-basic-queue",
|
|
"workflow_name": "train_model",
|
|
"execution_timeout_minutes": 5,
|
|
"run_timeout_minutes": 5,
|
|
"task_timeout_minutes": 5
|
|
},
|
|
"payload": {
|
|
"experiment_run_id": 1002,
|
|
"variable_columns": ["Counter", "Rollout"],
|
|
"target_variable": "Square",
|
|
"line_separator": ",",
|
|
"decimal_separator": ".",
|
|
"train_size": 80,
|
|
"shuffle": true,
|
|
"random_state": 42,
|
|
"model_name": "smoke-xgb",
|
|
"model_type": "xgboost",
|
|
"model_id": 1002,
|
|
"data_model_kwargs": {
|
|
"scaler_method": "MinMax",
|
|
"window_size": 3,
|
|
"use_filtering": false,
|
|
"transform_mode": "all"
|
|
},
|
|
"model_kwargs": {},
|
|
"opt_params": {
|
|
"tree_method": "hist",
|
|
"device": "cuda",
|
|
"learning_rate": 0.3,
|
|
"n_estimators": 100,
|
|
"max_depth": 32,
|
|
"subsample": 0.8,
|
|
"colsample_bytree": 0.8,
|
|
"min_child_weight": 5,
|
|
"random_state": 42
|
|
},
|
|
"date_column": "timestamp"
|
|
},
|
|
"db_only": {
|
|
"model_metadata": {
|
|
"schemas": {
|
|
"components": {
|
|
"schemas": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|