Smarter settings for ensembles fitting only one large sample

ContinuumIO / elm

Phase I & part of Phase II of NASA SBIR - Parallel Machine Learning on Satellite Data

http://ensemble-learning-models.readthedocs.io

43 stars 27 forks source link

Smarter settings for ensembles fitting only one large sample #98

Closed PeterDSteinberg closed 6 years ago

PeterDSteinberg commented 7 years ago

In the case of X given to fit_ensemble or fit_ea, or when an args_list of len==1 is given to these methods, X should be easily passed to predict_many without redoing the Pipeline sampler and transformations.

PeterDSteinberg commented 6 years ago

Fixed by #192