DESlib
DESlib copied to clipboard
scikit-learn-contrib
A Python library for dynamic classifier and ensemble selection
check_estimator is failing for instances, since during clone the pool of classifiers are not being properly copied. Need to investigate how this problem is addressed in sklearn (e.g. on sklearn.ensembles)
By default, if the pool of classifiers is not informed in the constructor of the DS methods, a Bagging Classifier (with 10 decision trees) is used to generate the pool....
This implementation should be updated to batch processing in order to have a much faster method, and follow the same structure and method signature of DESlib ver 0.2+
Create unit tests for The Online Local Pool technique. Tests can be inspired by the examples presented in: Souza, M. A., Cavalcanti, G. D., Cruz, R. M., & Sabourin, R....
Add a section in the documentation containing all information for development: - Guidelines for contributing - How to add a DS method/class - Specific details about implementation like Label encoders
Dear Developers: Deslib package is a really excellent framework which could be used by researchers and scientists and contributory to the community. But I have a few questions revelant to...
I try to use `METADES` to predict the testing data, however it shows the index error. The shape of the data is X_train.shape = (5040, 192) X_test.shape = (1260, 192)...
A package I help maintain, [julearn](https://github.com/juaml/julearn)'s 0.3.0 version depends on `DESlib`. We are getting our package on [conda-forge](https://conda-forge.org) but the [build](https://github.com/conda-forge/staged-recipes/pull/23821) fails due to unavailability of `DESlib` on official `conda`...
Metadata
Owner
Metadata
A Python library for dynamic classifier and ensemble selection