* Intermediate version
* Fix yaml template & Successfully run rolling
* Be compatible with benchmark
* Get same results with previous linear model
* Black formatting
* Update black
* Update the placeholder mechanism
* Update CI
* Update CI
* Upgrade Black
* Fix CI and simplify code
* Fix CI
* Move the data processing caching mechanism into utils.
* Adjusting DDG-DA
* Organize import
* move config file to benchmark_dynamic & switch default sim task model to GBDT
* Update benchmark_dynamic results
* Change the default value of alpha of DDG-DA
* transpose dimension 1 and 2 to match nn.Conv1d input
* 1.update TCN benchmarks;
2.Emphasize updating the benchmark table;
* replace specific version with main
---------
Co-authored-by: lijinhui <362237642@qq.com>
* 1.specify group_keys=False to avoid FutureWarning;
2.fix get train_start from dict unexpected problem;
* fix black
* Add comments
* Add make file
---------
Co-authored-by: Young <afe.young@gmail.com>
* Remove lr_decay and lr_decay_steps params
More flexible way to pass a scheduler (via callable function) is already
supported
* remove lr_decay and lr_decay_steps from mlp workflow configs
* wip
* wip
* wip
* Fix naming errors
* Backtest test passed
* Why training stuck?
* Minor
* Refine train configs
* Use dummy in training
* Remove pickle_dataframe
* CI
* CI
* Add more strict condition to filter orders
* Pass test
* Add TODO in example
---------
Co-authored-by: Young <afe.young@gmail.com>
* update ubuntu CI version;
(End of standard support for 18.04 LTS - 31 May 2023)
* update ubuntu CI version;
---------
Co-authored-by: lijinhui <362237642@qq.com>
* Waiting for bin data
* Complete readme
* CI
* Add inst filter by time
* Update qlib/data/dataset/processor.py
* typo
* Fix time filter bug
* Add Filter and set Universe
* Complete data pipeline
* Fix Provider Logger Info Args
* Add DQN; a minor bugfix in ppo reward.
* update readme. modify assertion logic in strategy check.
* Fix Doc issues and fix black
* Fix pylint Error
---------
Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
* Update test_qlib_from_source.yml
* add ipynb format check to workflow
* test ipynb CI
* modify nbqa check path
* add pylint flake8 mypy check to ipynb
* check ipynb with black and pylint
* reformat .ipynb files
* format line length
nbqa black . -l 120
* update nbqa .ipynb format CI
* format old ipynb files
* add nbconvert check to CI
* adjust CI order to avoid repeating download data
* Workflow runnable
* CI
* Slight changes to make the workflow runnable. The changes of handler/provider should be reverted before merging.
* Train experiment successful
* Refine handler & provider
* test passed
* Ready to test on server
* Minor
* Test passed
* TWAP training
* Add PPOReward
* Add a FIXME
* Refine PPO reward according to PR comments
* Minor
* Resolve PR comments
* CI issues
* CI issues
* CI issues
* Workflow runnable
* CI
* Slight changes to make the workflow runnable. The changes of handler/provider should be reverted before merging.
* Train experiment successful
* Refine handler & provider
* CI issues
* Resolve PR comments
* Resolve PR comments
* CI issues
* Fix test issue
* Black
* 1) check limit_up/down should consider direction; 2) fix some typo, typehint etc
* fix error
* Update test_all_pipeline.py
Believe it's just some arbitrary number.
The excess return is expected to change when trading logic changes.
* add flag forbid_all_trade_at_limit to keep previous behivour for backward compatibility
