Model selection#
Classes for efficient hyperparameter optimization of fingerprint-based models.
Hyperparameter optimization:
Exhaustive search over specified hyperparameter values for a pipeline of a molecular fingerprint and scikit-learn estimator. |
|
Randomized search over specified hyperparameter distributions for a pipeline of a molecular fingerprint and scikit-learn estimator. |
Splitters:
Split using Taylor-Butina clustering. |
|
Split using Taylor-Butina clustering. |
|
Split using MaxMin algorithm. |
|
Split using MaxMin algorithm. |
|
Split using randomized groups of Bemis-Murcko scaffolds. |
|
Split using randomized groups of Bemis-Murcko scaffolds. |
|
Split using groups of Bemis-Murcko scaffolds. |
|
Split using groups of Bemis-Murcko scaffolds. |