jlgarridol/sslearn: 1.1.0

[1.1.0] - 2025-05-26

Added

• Included get_dataset_regresion for separation of labeled and unlabeled data. For the regression dataset, the unlabeled instances are marked with NaN; by @aliciaolivaresgil.
• Includes check_regressor in the sslearn.utils module to check if the estimator is a regressor or not; by @aliciaolivaresgil.
• The regressor CoReg is now included, described in the paper "Semi-supervised regression with co-training" by Zhi-Hua Zhou and Ming Li. Implemented in the sslearn.wrapper module; by @aliciaolivaresgil.
• The regression TriTrainingRegressor is now included, made by adapting the TriTraining method to regression tasks created by Alicia Olivares Gil. Implemented in the sslearn.wrapper module; by @aliciaolivaresgil.

Changed

• The functions read_keel and read_csv from the sslearn.datasets module now has a new parameter is_regression to indicate if the dataset is for regression or classification. This will change the way the dataset is processed and returned; by @aliciaolivaresgil.

Fixed

• Repaired restricted.feature_fusion and restricted.probability_fusion when the instances that cannot link are not consecutive.

Testing

• Added tests for the new regression methods and the changes in the dataset reading functions; by @aliciaolivaresgil.