From bcd4fab259c358e4bddcdb63f868aa5c08fec27a Mon Sep 17 00:00:00 2001 From: vitor-aignosi Date: Mon, 11 May 2026 12:49:04 -0300 Subject: [PATCH] refactor: update input dataset and training parameters - 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. --- input_dataset.csv | 2 +- scripts/run_training_test.py | 8 +++++--- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/input_dataset.csv b/input_dataset.csv index 1d9e1d6..ccaa4ae 100644 --- a/input_dataset.csv +++ b/input_dataset.csv @@ -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 00:01:00,2.0,2.0,5.9 2026-01-01 00:02:00,2.0,3.0,8.3 diff --git a/scripts/run_training_test.py b/scripts/run_training_test.py index 911e0b7..3aaebd4 100644 --- a/scripts/run_training_test.py +++ b/scripts/run_training_test.py @@ -87,6 +87,7 @@ request_data = { 'data_model_kwargs': {}, 'model_kwargs': {}, 'opt_params': {}, + 'date_column': 'timestamp', 'model_metadata': {'schemas': {'components': {'schemas': {}}}}, } @@ -133,8 +134,8 @@ TH, TN, TQ = TEMPORAL_HOST, TEMPORAL_NAMESPACE, TRAIN_TASK_QUEUE _workflow_input = { 'experiment_run_id': EXPERIMENT_RUN_ID, - 'variable_columns': ['feature_a', 'feature_b'], - 'target_variable': 'target', + 'variable_columns': ['Counter', 'Rollout'], + 'target_variable': 'Square', 'bucket_name': MINIO_BUCKET, 'file_name': OBJECT_NAME, 'line_separator': ',', @@ -142,12 +143,13 @@ _workflow_input = { 'train_size': 80, 'shuffle': True, 'random_state': 42, - 'model_name': 'test-runtime-linear-regression-model', + 'model_name': 'test-runtime', 'model_type': 'linear_regression', 'model_id': EXPERIMENT_RUN_ID, 'data_model_kwargs': {}, 'model_kwargs': {}, 'opt_params': {}, + 'date_column': 'timestamp', } c = await client.Client.connect(