forked from moreo/QuaPy
39 lines
1.0 KiB
Plaintext
39 lines
1.0 KiB
Plaintext
Classifiers
|
|
|
|
- Classifiers binary, single-label, OneVsRest or MultiOutput:
|
|
- LR
|
|
- LinearSVC (?)
|
|
|
|
- Classifiers natively multi-label:
|
|
- from scikit-multilearn (x11)
|
|
-
|
|
|
|
Protocols:
|
|
- NPP
|
|
- APP (for each class)
|
|
|
|
|
|
|
|
Things to test:
|
|
- MultiChain for classification, MultiChain for regression...
|
|
- Reimplement stacking with sklearn.ensemble.StackingClassifier? No parece facil.
|
|
|
|
- Independent classifiers + independent quantifiers
|
|
- Stacking + independent quantifiers
|
|
- ClassifierChain + independent quantifiers
|
|
- Independent quantifiers + cross-class regression (independent?)
|
|
- Stacking + cross-class regression
|
|
- ClassifierChain + cross-class regression
|
|
- Covariates (Means, CovMatrix from samples) + multioutput regression?
|
|
- Covariates concatented with quantifiers predictions + cross-class regression?
|
|
|
|
- Model Selection for specific protocols?
|
|
|
|
TODO:
|
|
- decide methods
|
|
- decide classifiers binary
|
|
- decide classifiers multi-label
|
|
- decide quantifiers naive
|
|
- decide quantifiers multi-label
|
|
- decide datasets
|