kiez.hubness_reduction.DisSimLocal¶
- class kiez.hubness_reduction.DisSimLocal(squared: bool = True, **kwargs)[source]¶
Hubness reduction with DisSimLocal.
Uses the formula presented in [1].
- Parameters:
squared (bool, default = True) – DisSimLocal operates on squared Euclidean distances. If True, return (quasi) squared Euclidean distances; if False, return (quasi) Eucldean distances.
References
Methods
__init__
([squared])fit
(source[, target])kneighbors
([k])transform
(neigh_dist, neigh_ind, query)Transform distance between test and training data with DisSimLocal.
- transform(neigh_dist, neigh_ind, query) Tuple[T, T] [source]¶
Transform distance between test and training data with DisSimLocal.
- Parameters:
neigh_dist (shape (n_query, n_neighbors)) – Distance matrix of test objects (rows) against their individual k nearest neighbors among the training data (columns).
neigh_ind (shape (n_query, n_neighbors)) – Neighbor indices corresponding to the values in neigh_dist
query (shape (n_query, n_features)) – Query entities that were used to obtain neighbors If none is provided use source that was provided in fit step
- Returns:
DisSimLocal distances, and corresponding neighbor indices
- Return type:
hub_reduced_dist, neigh_ind
Notes
The returned distances are NOT sorted! If you use this class directly, you will need to sort the returned matrices according to hub_reduced_dist.