[go: nahoru, domu]
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.

Sign up for GitHub

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

Jump to bottom

scanpy.external.pp.dca results still need normolize,scale,and log1p ? #2626

Open
rdf1993 opened this issue Aug 19, 2023 · 1 comment
Open

scanpy.external.pp.dca results still need normolize,scale,and log1p ? #2626

rdf1993 opened this issue Aug 19, 2023 · 1 comment
Labels
Closing candidate Issue that can probably be closed Question

Comments

@rdf1993
Copy link
rdf1993 commented Aug 19, 2023 •
edited by flying-sheep
Loading

What kind of feature would you like to request?

Additional function parameters / changed functionality / changed defaults?

Please describe your wishes

If I run scanpy.external.pp.dca with default parameters, do I still need to perform normalization, scaling, and log1p afterward? How can I obtain the non-normalized values?

scanpy.external.pp.dca(adata, mode='denoise', ae_type='nb-conddisp', normalize_per_cell=True, scale=True, log1p=True, hidden_size=(64, 32, 64), hidden_dropout=0.0, batchnorm=True, activation='relu', init='glorot_uniform', network_kwds=mappingproxy({}), epochs=300, reduce_lr=10, early_stop=15, batch_size=32, optimizer='RMSprop', random_state=0, threads=None, learning_rate=None, verbose=False, training_kwds=mappingproxy({}), return_model=False, return_info=False, copy=False)
@eroell
Copy link
Contributor
eroell commented Oct 5, 2023 •
edited
Loading

Hi, thanks for your interest in scanpy!

For user questions, it would be great if you could ask your question on Discourse; this is the designated discussion forum for user questions regarding scverse tools (such as scanpy).

This way, here at GitHub the focus can be put on development, while on Discourse user questions can be answered in more detail and in a manner that future users can better find previous questions.

If you think your question is related to a development issue or I misinterpreted it as a user question, we're happy to look into it here on GitHub!

Hope this gives you a guidance for receiving helpful support for your question!

@eroell eroell added Closing candidate Issue that can probably be closed Question and removed Enhancement ✨ labels Oct 5, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Closing candidate Issue that can probably be closed Question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@rdf1993 @eroell