mirror of https://github.com/webclinic017/drift.git synced 2026-07-28 03:08:01 +00:00

T

Mark Aron Szulyovszky 1eaba0c221 fix(Evaluate): ignore empty data at evaluation time, add backtesting metrics (sharpe, etc), fixed crash when predicting 0.0 (#23 )

* fix(Evaluate): ignore empty data at evaluation time, so we don't inflate the model's performance

* refactor(Pipeline): pass in data_loader arguments to the pipeline

* feat(Evaluation): added sharpe, sortino, etc

* fix: Took out the method to fill NaN numbers with 0s. This way in evaluation we can ignore NaN values.

* fix: Fix of the fix added fillna back. Either we root out NaN lines in the very beginning or we stick with the method you created.

Co-authored-by: Daniel Szemerey <szemy2@gmail.com>

2021-12-15 21:11:12 +01:00

.vscode

feat(Pipeline): save results, train on all assets

2021-12-14 22:59:44 +01:00

archive

feat(WalkForward): added regression/classification switch, archived old experiments, wrapped the process into run_whole_pipeline() (#10 )

2021-12-14 18:16:17 +01:00

data

feat(WalkForward): added regression/classification switch, archived old experiments, wrapped the process into run_whole_pipeline() (#10 )

2021-12-14 18:16:17 +01:00

tests

feat(Tests): added basic unit tests for walk_forward_train_test() (#22 )