|
pulsatrix 1.1.0
|
TwoNNDimension()'s result. More...
#include <representation_geometry.hpp>
Public Attributes | |
| double | dimension = 0 |
| Facco et al.'s estimate: the slope through the origin of -log(1 - F(mu)) against log(mu), over the points left after discarding the largest ratios. scikit-dimension's TwoNN and DADApy's compute_id_2NN compute the same. | |
| double | mle_dimension = 0 |
The maximum-likelihood estimate over all points, (N - 1) / sum log(mu), as DADApy's algorithm="ml" gives it. | |
| int64_t | points = 0 |
| Distinct points used. | |
| int64_t | duplicates = 0 |
| Rows dropped because they repeat an earlier row exactly. | |
TwoNNDimension()'s result.
| double pulsatrix::TwoNNResult::dimension = 0 |
Facco et al.'s estimate: the slope through the origin of -log(1 - F(mu)) against log(mu), over the points left after discarding the largest ratios. scikit-dimension's TwoNN and DADApy's compute_id_2NN compute the same.
| int64_t pulsatrix::TwoNNResult::duplicates = 0 |
Rows dropped because they repeat an earlier row exactly.
| double pulsatrix::TwoNNResult::mle_dimension = 0 |
The maximum-likelihood estimate over all points, (N - 1) / sum log(mu), as DADApy's algorithm="ml" gives it.
| int64_t pulsatrix::TwoNNResult::points = 0 |
Distinct points used.