gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-07-28 19:27:47 +00:00
Code Issues Packages Projects Releases Wiki Activity
34 Commits 1 Branch 0 Tags
6440ced32c3e91f1541749b104dc3c25ce79bd21
Commit Graph

14 Commits

Author SHA1 Message Date
Mark Aron Szulyovszky 6440ced32c feat(Tests): added basic unit tests for walk_forward_train_test() (#22) 
* feat(Tests): added basic unit tests for walk_forward_train_test()

* fix(Tests): inherit from BaseEstimator, fix index problems in walk_forward_train_test

* fix(WalkForward): predictions were mistakenly removed, oops

* fix(WalkForward): mistakenly re-assiging model
 2021-12-15 17:54:03 +01:00
Mark Aron Szulyovszky beb281fc3a feat(Evaluation): created a unified evaluation framework for both regression / classification 2021-12-14 21:25:43 +01:00
Mark Aron Szulyovszky 1ef314c034 fix(WalkForward): major bug where we passed in "window of windows of data" is resolved, refactored walk_forward_train_test() and load_data() 2021-12-14 21:07:03 +01:00
Mark Aron Szulyovszky d047b7417e feat(WalkForward): added regression/classification switch, archived old experiments, wrapped the process into run_whole_pipeline() (#10) 
* refactor(WalkForward): cleaned up training & evaluation code

* refactor: added run_whole_pipeline(), moved all previous models to archive
 2021-12-14 18:16:17 +01:00
Mark Aron Szulyovszky 7aedb91069 feat(Data): added various data loading config options, walk forward method draft (#9) 
* feat(Eval): added format_data_for_backtest()

* feat(Data): added many configurable parameters to load_files to reduce boilerplate and prepare for HPO

* feat(Core): added walk forward method of training/testing

* fix(Model): remove the unnecessary softmax activation from the keras models

* feat(Core): added walk_forward_train_test()
 2021-12-01 09:28:24 +01:00
Mark Aron Szulyovszky 6e192ebc8a feat(Models): added a basic sktime model and missing USD crypto currency pairs (#7) 2021-11-17 22:28:34 +01:00
Mark Aron Szulyovszky 3fec439c08 feat(Data): added new derived features + asset pairs for crypto tickers (#6) 2021-11-17 12:07:49 +01:00
Mark Aron Szulyovszky 1d6eed3a94 feat(Core): added the first classification model & the feature necessary (#4) 
* feat(Core): added the first classification model & the feature necessary

* feat(Models): added basic transformers model
 2021-11-16 10:02:02 +01:00
Mark Aron Szulyovszky 797791d2f4 feat(Forecasting): pytorch-forecasting scaffolding is now working, added narrow data format, fixed missing time column index name (#5) 
* feat: Started implementing pytorch-forecasting.

* feat(Forecasting): pytorch-forecasting scaffolding is now working, added narrow data format, fixed missing `time` column index name

Co-authored-by: Daniel Szemerey <szemy2@gmail.com>
 2021-11-16 10:00:26 +01:00
Mark Aron Szulyovszky 07302a7541 feat(Models): added MAE & RMSE metrics, fixed NaN & Inf values in data, 2021-11-14 23:50:25 +01:00
Mark Aron Szulyovszky 5f8efc97fa feat(Model): now successfully training the basic LSTM model 2021-11-11 18:29:05 +01:00
Mark Aron Szulyovszky 78b3c07420 feat(Model): trying to get to a model that can train 2021-11-11 17:53:24 +01:00
Mark Aron Szulyovszky 3188aab220 feat(Model): continued with the keras model scaffolding 2021-11-10 14:51:12 +01:00
Mark Aron Szulyovszky 51b7d35660 feat(Data): downloading data for pre-defined tickers 2021-11-09 15:21:22 +01:00