-
-
Notifications
You must be signed in to change notification settings - Fork 25.8k
ENH Speed up sgdclassifier example plot_sgd_early_stopping.py #21627
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
Conversation
Can you please fix the code style to get the linting work in the CI status summary? Look at the logs of the failed CI jobs for details. Please also report your analysis of the before/after of your proposed change:
|
Interestingly, at least on the CI, this example doesn't run faster than what we have. You also need to run black on your code as I said before @johgreen |
I think this example might be completely reworked to be much more elegant and efficient once me make some progress on the callback API #16925 that itself is being worked on by @jeremiedbb. |
I agree @ogrisel , but this cuts over 30s from the example, we can merge as is, and let @jeremiedbb rework the example as a part of the callback work. WDYT? |
ping @ogrisel |
As is, this PR doesn't seem to change the speed of the example that much (33s vs 30s) |
Closing this PR since we have already tackled the problem (23s in |
Reference Issues/PRs
Speeding up
../examples/linear_model/plot_sgd_early_stopping.py
in #21598What does this implement/fix? Explain your changes.
Reduced n_samples from 10000 to 5000 to speed up runtime.