search

lina-usc / pylossless

🧠 EEG Processing pipeline that annotates continuous data
https://pylossless.readthedocs.io/en/latest/
MIT License
20 stars 8 forks source link

initial test: flag_outlier_chs #49

Closed scott-huberty closed 1 year ago

scott-huberty commented 1 year ago

Here is a first test.

I am generating a simulated raw object, and adding noise to 3 channels: 'EEG 001' , 'EEG 005', and 'EEG 009'.

b389e379-2b0f-4e6a-8064-c41759c0e082

then I run pylossless.pipeline.flag_outlier_chs, and test that the method indeed flags those 3 channels. It does.

I think this modules tests/test_simulated, is a great way to test that each of our pipeline methods behaves as expected in a controlled environment, . After this, I will generate a test module using real data (even more important).

scott-huberty commented 1 year ago

Once this test is merged. I will finish developing the CI branch and make another pull request so that we have a running CI pipeline on main.

After that I will add more tests in sequential PR's.

christian-oreilly commented 1 year ago

I think this modules tests/test_simulated, is a great way to test that each of our pipeline methods behaves as expected in a controlled environment, .

Yes, this is pretty cool if we can simulate the different steps with controlled simulated data as you propose. Good idea.