gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-07-28 03:08:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 034bc1f213 fix(Training): major bug in scaling, we only scaled training data, not the ones we're predicting from (#45) Mark Aron Szulyovszky 2021-12-19 13:14:14 +01:00
  • b456ec3cb7 feat(Data): added feature extractors, and feature extractor presets, removed a bunch of custom arguments from load_data (#42) Mark Aron Szulyovszky 2021-12-19 12:14:59 +01:00
  • b8b7375c30 feat(Tests): added test for evaluate_predictions() (#41) Mark Aron Szulyovszky 2021-12-18 22:23:07 +01:00
  • 0963df2087 refactor(Project): move out load_data to utils, rename fetch_data to run_fetch_data, got classifiers to work (#38) Mark Aron Szulyovszky 2021-12-17 17:41:50 +01:00
  • cc7061b456 feat(Core): ensemble models, correct forward returns calculation, scaling, only train from when asset returns are available, major bug fixed in walk_forward_train_test (#35) Mark Aron Szulyovszky 2021-12-17 14:32:17 +01:00
  • 1eaba0c221 fix(Evaluate): ignore empty data at evaluation time, add backtesting metrics (sharpe, etc), fixed crash when predicting 0.0 (#23) Mark Aron Szulyovszky 2021-12-15 21:11:12 +01:00
  • 6440ced32c feat(Tests): added basic unit tests for walk_forward_train_test() (#22) Mark Aron Szulyovszky 2021-12-15 17:54:03 +01:00
  • 64721330a3 feat(Pipeline): save results, train on all assets Mark Aron Szulyovszky 2021-12-14 22:59:44 +01:00
  • 7a6ddcec08 fix(Data): one-hot encode date features Mark Aron Szulyovszky 2021-12-14 22:58:43 +01:00
  • beb281fc3a feat(Evaluation): created a unified evaluation framework for both regression / classification Mark Aron Szulyovszky 2021-12-14 21:25:43 +01:00
  • 1ef314c034 fix(WalkForward): major bug where we passed in "window of windows of data" is resolved, refactored walk_forward_train_test() and load_data() Mark Aron Szulyovszky 2021-12-14 21:07:03 +01:00
  • d047b7417e feat(WalkForward): added regression/classification switch, archived old experiments, wrapped the process into run_whole_pipeline() (#10) Mark Aron Szulyovszky 2021-12-14 18:16:17 +01:00
  • 7aedb91069 feat(Data): added various data loading config options, walk forward method draft (#9) Mark Aron Szulyovszky 2021-12-01 09:28:24 +01:00
  • d4676e099b feat(Pytorch): added custom model to pytorch-forecasting (#8) Daniel Szemerey 2021-11-18 10:59:06 +01:00
  • 6e192ebc8a feat(Models): added a basic sktime model and missing USD crypto currency pairs (#7) Mark Aron Szulyovszky 2021-11-17 22:28:34 +01:00
  • 3fec439c08 feat(Data): added new derived features + asset pairs for crypto tickers (#6) Mark Aron Szulyovszky 2021-11-17 12:07:49 +01:00
  • b0b0d5bbba feat: Added normalizaton. Daniel Szemerey 2021-11-16 10:20:35 +01:00
  • 1d6eed3a94 feat(Core): added the first classification model & the feature necessary (#4) Mark Aron Szulyovszky 2021-11-16 10:02:02 +01:00
  • 797791d2f4 feat(Forecasting): pytorch-forecasting scaffolding is now working, added narrow data format, fixed missing time column index name (#5) Mark Aron Szulyovszky 2021-11-16 10:00:26 +01:00
  • a59e705f02 Merge pull request #3 from applied-exploration/feature/feature-engineering Daniel Szemerey 2021-11-15 11:01:52 +01:00
  • 07302a7541 feat(Models): added MAE & RMSE metrics, fixed NaN & Inf values in data, Mark Aron Szulyovszky 2021-11-14 23:50:25 +01:00
  • 3581c8db83 chore(Models): remove separate model for forecasting for 10 days in advance Mark Aron Szulyovszky 2021-11-14 17:28:36 +01:00
  • ead7db3a85 feat(Data): added create_target_cum_forward_returns, now using it for FF & LSTM models, with success Mark Aron Szulyovszky 2021-11-14 17:25:32 +01:00
  • 478a15a7cb feat(Data): added day/month/dayofweek features Mark Aron Szulyovszky 2021-11-14 17:24:56 +01:00
  • 9d342d6039 feat(Data): added day_month, month, day_week columns as features Mark Aron Szulyovszky 2021-11-14 11:59:59 +01:00
  • 1429051c4c feat(Modles): lstm model now using StandardScaler Mark Aron Szulyovszky 2021-11-12 23:25:38 +01:00
  • 58bef94769 Merge pull request #2 from applied-exploration/feature/10-day-projection Daniel Szemerey 2021-11-12 16:42:54 +01:00
  • baf7d261e8 feat(Models): added model that predicts 10 days ahead Mark Aron Szulyovszky 2021-11-12 16:10:55 +01:00
  • ce45288315 feat(Models): added lstm tutorial from mlmastery.com Mark Aron Szulyovszky 2021-11-12 12:30:04 +01:00
  • 67d830ca09 feat(Models): added simple Feed forward layer Mark Aron Szulyovszky 2021-11-11 18:42:23 +01:00
  • 5f8efc97fa feat(Model): now successfully training the basic LSTM model Mark Aron Szulyovszky 2021-11-11 18:29:05 +01:00
  • 78b3c07420 feat(Model): trying to get to a model that can train Mark Aron Szulyovszky 2021-11-11 17:53:24 +01:00
  • 0e5fe227f7 fix(Model): drop index before feeding into keras.dataset Mark Aron Szulyovszky 2021-11-10 19:35:46 +01:00
  • 3188aab220 feat(Model): continued with the keras model scaffolding Mark Aron Szulyovszky 2021-11-10 14:51:12 +01:00
  • 20aa1474d6 feat(Data): added extra features, exploration notebook Mark Aron Szulyovszky 2021-11-09 17:16:40 +01:00
  • d5086a4785 feat(Data): added load_data, to aggregate everything into one dataframe Mark Aron Szulyovszky 2021-11-09 16:12:48 +01:00
  • 51b7d35660 feat(Data): downloading data for pre-defined tickers Mark Aron Szulyovszky 2021-11-09 15:21:22 +01:00
  • 58137a0f36 feat(Data): fetch prices from cryptocompare (and alphavantage) Mark Aron Szulyovszky 2021-11-09 12:58:05 +01:00
  • 9f54cdc81f feat(Data): added csv downloaded from oecd website, prototype preprocessing script Mark Aron Szulyovszky 2021-11-07 15:16:45 +01:00
  • 842e99e4c7 Initial commit Mark Aron Szulyovszky 2021-11-06 13:50:13 +01:00