Aifred-Health / VulcanAI

A high level deep learning framework for quickly prototyping networks with added tools in data visualisation, model interpretability and performance metrics
https://www.aifredhealth.com
GNU Affero General Public License v3.0
17 stars 8 forks source link

Tabular Dataset Improvements #164

Closed nirtiac closed 5 years ago

nirtiac commented 5 years ago

All new code with the exception of the data storage problem is here, need to test tomorrow. Added new method, cleaned up split and added stratified sampling.

Not ready for real code review, just concept review :)

nirtiac commented 5 years ago

Yes, the tests for those that I reversed are failing :) fixes coming soon.

nirtiac commented 5 years ago

@rfratila this is ready for real review. This is an intermediate push to restore functionality for all methods for now, before any more intensive updates are made to the data storage behind the class.

nirtiac commented 5 years ago

@joemehltretter would you mind doing a quick review based on your experience using stratified splitting? Just if you could verify that it all works as expected for you.