gitea_admin/sientia-dataops-model-manager
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: update input dataset and training parameters

Browse Source 
- Renamed columns in `input_dataset.csv` from `feature_a`, `feature_b`, and `target` to `Counter`, `Rollout`, and `Square` for better clarity.
- Updated the `run_training_test.py` script to reflect the new column names in the workflow input, ensuring consistency in data processing.
- Added `date_column` parameter to the workflow input for improved data handling.
This commit is contained in:
vitor-aignosi
2026-05-11 12:49:04 -03:00
parent 544c768ef4
commit bcd4fab259
2 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
input_dataset.csv
View File

@@ -1,4 +1,4 @@
timestamp,feature_a,feature_b,target timestamp,Counter,Rollout,Square
2026-01-01 00:00:00,1.0,2.0,5.1 2026-01-01 00:00:00,1.0,2.0,5.1
2026-01-01 00:01:00,2.0,2.0,5.9 2026-01-01 00:01:00,2.0,2.0,5.9
2026-01-01 00:02:00,2.0,3.0,8.3 2026-01-01 00:02:00,2.0,3.0,8.3
1 timestamp feature_a Counter feature_b Rollout target Square
2 2026-01-01 00:00:00 1.0 2.0 5.1
3 2026-01-01 00:01:00 2.0 2.0 5.9
4 2026-01-01 00:02:00 2.0 3.0 8.3

8
scripts/run_training_test.py
View File

@@ -87,6 +87,7 @@ request_data = {
'data_model_kwargs': {}, 'data_model_kwargs': {},
'model_kwargs': {}, 'model_kwargs': {},
'opt_params': {}, 'opt_params': {},
'date_column': 'timestamp',
'model_metadata': {'schemas': {'components': {'schemas': {}}}}, 'model_metadata': {'schemas': {'components': {'schemas': {}}}},
} }
@@ -133,8 +134,8 @@ TH, TN, TQ = TEMPORAL_HOST, TEMPORAL_NAMESPACE, TRAIN_TASK_QUEUE
_workflow_input = { _workflow_input = {
'experiment_run_id': EXPERIMENT_RUN_ID, 'experiment_run_id': EXPERIMENT_RUN_ID,
'variable_columns': ['feature_a', 'feature_b'], 'variable_columns': ['Counter', 'Rollout'],
'target_variable': 'target', 'target_variable': 'Square',
'bucket_name': MINIO_BUCKET, 'bucket_name': MINIO_BUCKET,
'file_name': OBJECT_NAME, 'file_name': OBJECT_NAME,
'line_separator': ',', 'line_separator': ',',
@@ -142,12 +143,13 @@ _workflow_input = {
'train_size': 80, 'train_size': 80,
'shuffle': True, 'shuffle': True,
'random_state': 42, 'random_state': 42,
'model_name': 'test-runtime-linear-regression-model', 'model_name': 'test-runtime',
'model_type': 'linear_regression', 'model_type': 'linear_regression',
'model_id': EXPERIMENT_RUN_ID, 'model_id': EXPERIMENT_RUN_ID,
'data_model_kwargs': {}, 'data_model_kwargs': {},
'model_kwargs': {}, 'model_kwargs': {},
'opt_params': {}, 'opt_params': {},
'date_column': 'timestamp',
} }
c = await client.Client.connect( c = await client.Client.connect(