Justin Shenk

Results 20 issues of Justin Shenk

Add space after hashtag

Please provide results for testing on a Keras implementation of a linear regression task.

good first issue

Demonstrate Traja with a stock market price forecasting example. Good place to start is the Colab notebook: https://colab.research.google.com/github/justinshenk/traja/blob/master/demo.ipynb

enhancement
good first issue

`num_future` is included as an argument but not actually used. https://github.com/traja-team/traja/blob/659c8e0978042d561f8e13a4b0786d28c2ed7a41/traja/models/predictive_models/lstm.py#L31 @Saran-nns can you please remove or implement this?

reset_state is included throughout code base but not used. https://github.com/traja-team/traja/blob/659c8e0978042d561f8e13a4b0786d28c2ed7a41/traja/models/predictive_models/lstm.py#L38 Can this be removed @Saran-nns ?

Duration for functional tests can be shortened by using [pytest fixtures](https://realpython.com/pytest-python-testing/) and reducing epochs from 10 in neural network tests (`test_models`). Here are some extensive durations: ``` 154.86s call traja/tests/test_models.py::test_ae_jaguar...

enhancement

Assertion in `test_ae_classification_network_converges` in `test_models.py` fails in [CI on Python 3.8](https://travis-ci.org/github/traja-team/traja/jobs/765577067 ) for unknown reason. ``` > assert classification_loss_post_training < classification_loss_pre_training E assert 0.04000916234824969 < 0.040007756348105446 ```

bug

HybridTrainer docstring includes several unimplemented args, like [`device`](https://github.com/traja-team/traja/blob/f87978d02042503ebba57a2f1d1a3b7263a96893/traja/models/train.py#L18). These should be cleaned to reflect the imlemented arguments.

invalid