Carlos Ramos Carreño
Carlos Ramos Carreño
### Motivation In some cases, such as in the Gaussian (RBF) kernel we compute the squared of the L2 distance, which undoes the last sqrt made in the distance. ###...
### Motivation The covariance functions in scikit-fda were originally used to generate Gaussian processes. Now, their inputs will be generalized to accept also `FData` objects, in order to compute a...
**Is your feature request related to a problem? Please describe.** Currently the implementation of `AgglomerativeClustering` wraps scikit-learn's version, adding support for functional metrics. We should attempt to expose all additional...
**Is your feature request related to a problem? Please describe.** We currently are checking the performance of our methods in a very informal case-by-case way. This mean that we do...
**Is your feature request related to a problem? Please describe.** Currently the call method of the hat matrix code is overloaded and tries to do several things at once. This...
Tests are not currently passing with SciPy version 1.11, as the results for Simpson quadrature have been changed in this version (https://github.com/scipy/scipy/pull/18209). We need to update the test results and...
Currently the name `gradient_criteria` is used in the `plot` function to determine the values used to define a color gradient (e.g. the target values in regression, or the depth of...
Methods such as `RKHSVariableSelection` or `MaximaHunting` are often abbreviated as RK-VS or MH respectively. This should be explained in the documentation.
**Describe the bug** By default, it is natural that FPCA returns as many components as possible. The current behaviour is to return only 3, which is not a good default....
**Is your feature request related to a problem? Please describe.** We need a `FData` subclass capable of storing discretized functions where: - The points in which the functions are measured...