-
Notifications
You must be signed in to change notification settings - Fork 87
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
Update package #78
Comments
Are you referring to any Pull Request you have made or some other updates? Can you please make it clearer?Ram On Wednesday, September 6, 2023 at 11:32:22 PM EDT, arturdaraujo ***@***.***> wrote:
First, thanks very much for this package. I can't thank you enough.
Some updates from the dependencies of this package are already available, it would be nice to have an update.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>
|
Have you contemplated using some validation dataset for tuning the features selected? This way it is possible to select the features that are more representative of the real target on the test dataset. |
Hello: Thanks for the suggestion. But I have a doubt.
The way recursive XGBoost algorithm works is by sampling features multiple times. If you want more than that, it will take a longer time to run and may be redundant.
Has someone tested to see if your suggested approach is better than featurewiz' current approach? Can you provide some proof?
ThanksAuto Vimal
On Tuesday, September 12, 2023 at 05:19:23 PM EDT, arturdaraujo ***@***.***> wrote:
Have you contemplated using some validation dataset for tuning the features selected?
This way it is possible to select the features that are more representative of the real target on the test dataset.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Hey:
I have added a cross_validate.py which shows how to cross-validate features selected using featurewiz. Take a look and see if it is what you are looking for.
https://github.com/AutoViML/featurewiz/blob/main/examples/cross_validate.py
Auto Vimal
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
First, thanks very much for this package. I can't thank you enough.
Some updates from the dependencies of this package are already available, it would be nice to have an update.
The text was updated successfully, but these errors were encountered: