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

T

Mark Aron Szulyovszky f85ee6bb9c fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

* fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction

* fix(Evaluate): print results

* fix(Evaluate): make sure we have numerical stability in returns

* fix(Inference): only output and print stats in training mode

* fix(Evaluate): don't add miniscule amount to result

2022-02-01 13:09:00 +01:00

.github/workflows

Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187 )

2022-01-29 06:41:40 +01:00

.vscode

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

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

archive

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

config

fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

2022-02-01 13:09:00 +01:00

data

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

data_loader

Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187 )

2022-01-29 06:41:40 +01:00

feature_extractors

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

labeling

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

models

Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187 )

2022-01-29 06:41:40 +01:00

output

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

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

reporting

Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187 )

2022-01-29 06:41:40 +01:00

tests

fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

2022-02-01 13:09:00 +01:00

training

fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

2022-02-01 13:09:00 +01:00

transformations

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

utils

fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

2022-02-01 13:09:00 +01:00

.gitignore

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +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

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

exploration.ipynb

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +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(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +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_minute.py

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

run_inference.py

fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

2022-02-01 13:09:00 +01:00

run_model_dev.py

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

run_pipeline.py

fix(MetaLabeling): previously misinterpreted meta-labeling, now also multiplying base model's prediction with the meta model's prediction (#193 )

2022-02-01 13:09:00 +01:00

run_portfolio_reporting.py

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +01:00

run_sweep.py

feat(Events): added EventFilter, EventLabeller (#186 )

2022-01-26 23:22:43 +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.