Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Local score low pass filtering #151

Open
wants to merge 8 commits into
base: main
Choose a base branch
from

Conversation

JacobGlennAyers
Copy link
Contributor

Added in the ability of a user to filter the local score arrays using a butterworth low pass filter.

TODO

  1. Run some experiments to see how low pass filtering affects results. BirdClef 2020 dataset seems like a solid place to start
  2. Merge changes Teo made in the ctrl-C changes to this branch prior.
  3. Stuff I might be forgetting

- Created a function for building low pass filter
- Created a function that performs convolution (filters data with low pass filter)
- Added in a function that encapsulates the two functions mentioned above
- Added in docstrings
- Added in asssert statements
- Allows a user to define whether or not to filter the local score arrays
- they must define a normalized cutoff frequency and the order of the filter
- A future feature could be to find some default numbers that seem to work well enough and allow a user to just pick True
- fixed some type assertion problems in all files
@JacobGlennAyers
Copy link
Contributor Author

It should also be verified that these results work with the tweetynet pipeline. The way I wrote it, I think it is fine, but needs to be verified.

@JacobGlennAyers
Copy link
Contributor Author

We will also need to update the readme.md file with the new isolation parameter.

@JacobGlennAyers
Copy link
Contributor Author

It works with the tweetynet pipeline! The readme file just needs to be updated with the new isolation parameters.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant