liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-17 09:24:34 +08:00
Code Activity

Update tft and readme

Browse Source
This commit is contained in:
Jactus
2020-12-02 18:00:26 +08:00
parent 91c3dfddf5
commit 703ae5d4aa
3 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -27,10 +27,10 @@ For more details, please refer to our paper ["Qlib: An AI-oriented Quantitative
- [Data Preparation](#data-preparation) - [Data Preparation](#data-preparation)
- [Auto Quant Research Workflow](#auto-quant-research-workflow) - [Auto Quant Research Workflow](#auto-quant-research-workflow)
- [Building Customized Quant Research Workflow by Code](#building-customized-quant-research-workflow-by-code) - [Building Customized Quant Research Workflow by Code](#building-customized-quant-research-workflow-by-code)
- [**Quant Model Zoo**](#quant-model-zoo) - [Quant Model Zoo](#quant-model-zoo)
- [Run a single model](#run-a-single-model) - [Run a single model](#run-a-single-model)
- [Run multiple models](#run-multiple-models) - [Run multiple models](#run-multiple-models)
- [**Quant Dataset Zoo**](#quant-dataset-zoo) - [Quant Dataset Zoo](#quant-dataset-zoo)
- [More About Qlib](#more-about-qlib) - [More About Qlib](#more-about-qlib)
- [Offline Mode and Online Mode](#offline-mode-and-online-mode) - [Offline Mode and Online Mode](#offline-mode-and-online-mode)
- [Performance of Qlib Data Server](#performance-of-qlib-data-server) - [Performance of Qlib Data Server](#performance-of-qlib-data-server)
@@ -218,7 +218,7 @@ All the models listed above are runnable with ``Qlib``. Users can find the confi
## Run multiple models ## Run multiple models
`Qlib` also provides a script [`run_all_model.py`](examples/run_all_model.py) which can run multiple models for several iterations. (**Note**: the script only supprots *Linux* now. Other OS will be supported in the future.) `Qlib` also provides a script [`run_all_model.py`](examples/run_all_model.py) which can run multiple models for several iterations. (**Note**: the script only supprots *Linux* now. Other OS will be supported in the future.)
The script will create a unique virtual environment for each model, and delete the environments after training. Thus, only experiment results such as `IC` and `backtest` results will be generated and stored. (**Note**: the script will erase your previous experiment records created by running itself.) The script will create a unique virtual environment for each model, and delete the environments after training. Thus, only experiment results such as `IC` and `backtest` results will be generated and stored.
Here is an example of running all the models for 10 iterations: Here is an example of running all the models for 10 iterations:
```python ```python

2
examples/benchmarks/TFT/data_formatters/qlib_Alpha158.py
View File

@@ -208,7 +208,7 @@ class Alpha158Formatter(GenericDataFormatter):
model_params = { model_params = {
"dropout_rate": 0.4, "dropout_rate": 0.4,
"hidden_layer_size": 16, "hidden_layer_size": 160,
"learning_rate": 0.0001, "learning_rate": 0.0001,
"minibatch_size": 128, "minibatch_size": 128,
"max_gradient_norm": 0.0135, "max_gradient_norm": 0.0135,

3
examples/run_all_model.py
View File

@@ -291,7 +291,8 @@ def run(times=1, models=None, exclude=False):
pprint(errors) pprint(errors)
sys.stderr.write("\n") sys.stderr.write("\n")
# move results folder # move results folder
shutil.move(exp_path, exp_path + f"_{datetime.now().strftime("%Y-%m-%d_%H:%M:%S")}") shutil.move(exp_path, exp_path + f"_{datetime.now().strftime('%Y-%m-%d_%H:%M:%S')}")
if __name__ == "__main__": if __name__ == "__main__":
fire.Fire(run) # run all the model fire.Fire(run) # run all the model