diff --git a/laborious/utils/repository/model_repository.py b/laborious/utils/repository/model_repository.py index 2f10a9d..888b5c8 100644 --- a/laborious/utils/repository/model_repository.py +++ b/laborious/utils/repository/model_repository.py @@ -135,7 +135,12 @@ class MLFlowRepository(): target_name = data_model.target_variable y = data[target_name] 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) experiment = self.get_experiment_by_run_id(latest_production_id) mlflow.set_experiment(experiment)