Joseph Lizier
|
938dd7c4fb
|
Implementing multiple data sets in the nearest neighbour searches, to facilitate dynamic correlation exclusion only for points within the same data set
|
2023-10-09 13:12:07 +11:00 |
|
jlizier
|
1bb67f0840
|
Adding neighbour search utilities in preparation for attempting fast surrogate generation (performing multiple neighbour searches at once where we can); in particular adding a countPointsWithinR with a remapping of the point's indices. Unit test added as well for this.
|
2017-11-22 20:48:30 +11:00 |
|
jlizier
|
9a7ff306c8
|
Adding utilities for fast nearest neighbour searchers to handle calculations on new samples and prepare for conditional MI fast surrogates computation
|
2016-10-20 09:26:12 +11:00 |
|
joseph.lizier
|
a6f0e2d2ed
|
Added new unit test for KdTree to check validity of counting neighbours when one variable has been pre-checked, and different radii are used for each variable. Verifies issue 39.
|
2015-01-21 12:28:19 +00:00 |
|
joseph.lizier
|
33ea4f6136
|
Unit tests for Dynamic correlation exclusion, or Theiler window, in all Kraskov estimators, plus direct validation against values from using Theiler window in TRENTOOL. Validates issue 35
|
2014-11-25 12:34:49 +00:00 |
|
joseph.lizier
|
12faf78200
|
New unit tests for new methods in nearest neighbour search classes to return collections of points within ranges via arrays, and to use additional criteria in searching or take arguments for one variable that has already been tested.
|
2014-11-03 04:58:14 +00:00 |
|
joseph.lizier
|
758d9dc0c9
|
Unit test for inlining norms in Nearest Neighbour search classes, and adding methods to return Collections of points within ranges
|
2014-10-31 12:04:12 +00:00 |
|
joseph.lizier
|
9aa0e9ca0e
|
Unit tests for Kraskov multi-info calculators using fast neighbour search and common multi-info class. Additional mutual info unit test added also on larger data set, and unit tests for the UnivariateNearestNeighbourSearcher.
|
2014-10-30 04:24:42 +00:00 |
|
joseph.lizier
|
9ef43ae753
|
Verifies issue 32 -- adds unit test for neighbour search within different radii for each variable to the k-d tree class. This is used for fast neighbour search to Kraskov conditional MI calculators (and by implication to TE calculators). Existing unit tests for these calculators complete the verification.
|
2014-10-15 10:39:11 +00:00 |
|
joseph.lizier
|
f09cc221a4
|
Verifies issue 31 -- adding unit tests for KdTree structure (in conjunction with existing unit tests for the results of MI calculations)
|
2014-10-15 04:49:40 +00:00 |