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

SIENTIAPDE-1171

Browse Source 
Enhance data merging in MLFlowRepository by specifying merge parameters

- Updated the merge operation in the fit method to include 'how' and 'validate' parameters for improved data integrity and flexibility during model training.
This commit is contained in:
vitor-aignosi
2025-07-24 10:30:20 -03:00
parent c738e8b0df
commit a2492e244d
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
laborious/utils/repository/model_repository.py
View File

@@ -135,7 +135,12 @@ class MLFlowRepository():
target_name = data_model.target_variable target_name = data_model.target_variable
y = data[target_name] y = data[target_name]
treated_data = pd.merge( treated_data = pd.merge(
treated_data, y, left_index=True, right_index=True) treated_data, y,
left_index=True,
right_index=True,
how='left', # or 'inner', depending on your needs
validate='one_to_one' # ensures each index appears only once in both
)
prediction_model = prediction_model.fit(treated_data) prediction_model = prediction_model.fit(treated_data)
experiment = self.get_experiment_by_run_id(latest_production_id) experiment = self.get_experiment_by_run_id(latest_production_id)
mlflow.set_experiment(experiment) mlflow.set_experiment(experiment)