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

Fitting PCA on AbstractArrays #141

Closed
oxinabox opened this issue Feb 17, 2021 · 1 comment
Closed

Fitting PCA on AbstractArrays #141

oxinabox opened this issue Feb 17, 2021 · 1 comment

Comments

@oxinabox
Copy link
Contributor

It would be good if PCA supported any type of array that support the required methods.
and sored what ever projection matrix those methods came up with.

For example:
NamedDims.jl supports svd and will give you a partially named projection matrix.
Which can be pretty useful; since it will enforce and propagate it's names/
But if you use it with PCA here, then it works but the result is converted to a Matrix

#140 would help with this, though not solve the full problem.

#139 is also related

@wildart
Copy link
Collaborator

wildart commented Feb 25, 2021

Almost all fit functions accept AbstarctArray data (expept Whitening & MulticlassLDA). Problems arise from particular implementations (e.g. #140). We need to review the code to remove any type constrains, and allow to fail on missing implementations of the specific dependent functions for various array types (e.g. svd or cov)

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

No branches or pull requests

2 participants