Skip to content

ShuffleStratified splitting + uncertainty quantification added

Lupo Pasini, Massimiliano requested to merge max_proposed_changes_atomic_features into atomic_feature_binary_prediction

Shuffle stratified splitting to:

  • ensure that all bins are equally represented in training and testing portion of dataset
  • K-fold cross validation

Average calculated to improve robustness of accuracy and precision evaluation Standard deviation calculated to provide uncertainty of predictive performance of machine learning models

Merge request reports