gavindiaz/drift

mirror of https://github.com/webclinic017/drift.git synced 2026-07-27 18:57:55 +00:00

T

Mark Aron Szulyovszky 1042c82333 Update README.md

2022-01-26 22:06:40 +01:00

.github/workflows

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

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

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

fix(FeatureExtractor): use a rolling z-score instead of StandardScaler with unavoidable lookahead bias (#146 )

2022-01-10 14:24:51 +01:00

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

feat(Data): added daily_glassnode DataCollection (#99 )

2022-01-03 13:57:36 +01:00

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

feature_extractors

fix(FeatureExtractor): use a rolling z-score instead of StandardScaler with unavoidable lookahead bias (#146 )

2022-01-10 14:24:51 +01:00

feat(Inference): Inference now runs on the entire pipeline, only train/predict one asset, adjust trading costs (#173 )

2022-01-23 11:38:40 +01:00

chore(Project): added output folder (#124 )

2022-01-07 19:03:17 +01:00

refactor(Config): use a Config object instead of dictionary of dictionaries! (#184 )

2022-01-23 18:37:43 +01:00

refactor(Project): removed regression method (we can still use regression models, but we'll need map them to classification later) (#182 )

2022-01-23 17:15:08 +01:00

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

transformations

feat(Transformations): replaced feature selection pre-processing step with online version (with cache) (#170 )

2022-01-17 11:43:51 +01:00

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

.gitignore

feature(Inference): Created the inference process, added model saving. (#153 )

2022-01-11 19:15:58 +01:00

conftest.py

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

2021-12-15 17:54:03 +01:00

environment.yml

refactor(Config): use a Config object instead of dictionary of dictionaries! (#184 )

2022-01-23 18:37:43 +01:00

exploration.ipynb

refactor(Config): use a Config object instead of dictionary of dictionaries! (#184 )

2022-01-23 18:37:43 +01:00

README.md

Update README.md

2022-01-26 22:06:40 +01:00

run_clear_cache.py

fix(Selection): dynamic step size for feature selection (#123 )

2022-01-07 18:45:03 +01:00

run_evaluate_robustness.py

feat(Inference): pipeline wired up (#171 )

2022-01-14 10:34:28 +01:00

run_fetch_data_daily.py

feat(Data): create DataSource, DataCollection, added hourly crypto data (#96 )

2021-12-31 19:04:27 +01:00

run_fetch_data_glassnode.py

feat(Data): added daily_glassnode DataCollection (#99 )

2022-01-03 13:57:36 +01:00

run_fetch_data_hourly.py

feat(Data): create DataSource, DataCollection, added hourly crypto data (#96 )

2021-12-31 19:04:27 +01:00

run_inference.py

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

run_model_dev.py

refactor(Naming): use new convention, added Ensemble model parameter back, support multiple Meta-Labeling models (#132 )

2022-01-09 17:21:06 +01:00

run_pipeline.py

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

run_portfolio_reporting.py

refactor(Training): use date indexes instead of integers, need this to prepare for Events (#185 )

2022-01-24 12:22:30 +01:00

run_sweep.py

refactor(Naming): use new convention, added Ensemble model parameter back, support multiple Meta-Labeling models (#132 )

2022-01-09 17:21:06 +01:00

wandb_setup.py

feature: Added Weights and Biases configuration to the repo. (#48 )

2021-12-20 14:01:14 +01:00

README.md

Financial time series prediction

And end-to-end pipeline to train predictive Machine Learning models on financial (non-stationary, regime changing) time series. Includes feature selection and meta labelling.