mlpy.knowledgerep.cbr.features.BoolFeature.retrieval_algorithm¶
-
BoolFeature.
retrieval_algorithm
¶ The internal indexing structure of the training data.
The retrieval algorithm is only relevant for
NeighborSimilarity
. Valid algorithms are:- ball_tree
- A ball tree data structure is used for computational efficiency of the calculation of the distances between pairs of points.
- kd_tree
- A K-D Tree data structure is used for computational efficiency of the calculation of the distances between pairs of points.
- brute
- The nearest neighbors are determined by brute-force computation of distances between all pairs of points in the dataset.
- auto
- When
auto
is passed, the algorithm attempts to determine the best approach from the training data.
Returns: str :
The retrieval algorithm.