hfs.HNB¶
- class hfs.HNB(hierarchy=None, k=0)[source]¶
Select the k non-redundant features with the highest relevance following the algorithm proposed by Wan and Freitas.
- __init__(hierarchy=None, k=0)[source]¶
Initializes a HNB-Selector.
- Parameters
- hierarchynp.ndarray
The hierarchy graph as an adjacency matrix.
- kint
The numbers of features to select.
- select_and_predict(predict=True, saveFeatures=False, estimator=BernoulliNB())[source]¶
Select features lazy for each test instance amd optionally predict target value of test instances. It selects the top-k-ranked features, such that redundancy along each path is removed, in descending order of their individual predictive power measured by their relevance defined in helpers.py.
- Parameters
- predictbool
true if predictions shall be obtained.
- saveFeaturesbool
true if features selected for each test instance shall be saved.
- estimatorsklearn-compatible estimator
Estimator to use for predictions.
- Returns
- predictions for test input samples, if predict = false, returns empty array.
