The component uses Adaptive Synthetic (ADASYN) sampling method to balance imbalanced data. Minority class is oversampled. ADASYN covers some of the gaps found in SMOTE. See the explanation given in the following Kaggle link to understand why ADASYN is better than SMOTE. Requires python 'imblearn' library besides 'pandas' and 'numpy'.
Ref:
1. imblearn library docs: https://imbalanced-learn.readthedocs.io/en/stable/index.html
2. Graphical explanations: ADASYN vs SMOTE: https://www.kaggle.com/residentmario/oversampling-with-smote-and-adasyn
- Type: TablePort 1Input dataset, as for example from KNIME csv reader. Dataframe must include 'target' column. All data columns must be of type integer or float. 'target' column may be string but in integer format.