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

Plans for a Confusion matrix? #37

Closed
cgnarendiran opened this issue Jul 3, 2020 · 3 comments
Closed

Plans for a Confusion matrix? #37

cgnarendiran opened this issue Jul 3, 2020 · 3 comments
Labels
question Further information is requested

Comments

@cgnarendiran
Copy link

Are there any plans to implement a confusion matrix computation for NER labels?
I see that the classification report already gives a lot of information required for evaluation. A confusion matrix would be a nice addition to present the prediction errors.

@icoxfog417 icoxfog417 added the question Further information is requested label Jul 9, 2020
@Querela
Copy link

Querela commented Jul 16, 2020

https://github.com/chakki-works/seqeval/blob/445d99798f6969f606dbf5978d936d5a8b33bbd1/seqeval/metrics/sequence_labeling.py#L255L285

performance_measure

should be this?

@Hironsan
Copy link
Member

Please use performance_measure function.

@mustfkeskin
Copy link

performance_measure function returns only TP,FP,FN,TN
{'TP': 16617, 'FP': 199, 'FN': 38, 'TN': 1377}

I would like to see which entities is are conflicted

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

No branches or pull requests

5 participants