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

Create Encoding step #4

Merged
merged 25 commits into from
Apr 12, 2024
Merged

Create Encoding step #4

merged 25 commits into from
Apr 12, 2024

Conversation

diegomarvid
Copy link
Collaborator

@diegomarvid diegomarvid commented Apr 2, 2024

This solves the notion card Implement default passthrough encoding step

At the moment:

  • Target Encoding for high cardinality features.
  • Ordinal Encoding for low cardinality features.
  • Passthrough for numeric features.

To Do:

  • Personalize encoding selection in config.json
  • More advanced encoding for high cardinality features. For later on according to @Ludecan

I had to change some lib structure to address the need to save the fitted encoders for prediction if we don't have the target. Now we save the data container with some important keys and load them from prediction. Like it was some time ago.

@diegomarvid diegomarvid self-assigned this Apr 2, 2024
@diegomarvid diegomarvid force-pushed the encoding branch 2 times, most recently from 828844c to 8024ca5 Compare April 2, 2024 04:36
@diegomarvid diegomarvid marked this pull request as draft April 2, 2024 14:03
@diegomarvid diegomarvid requested a review from Ludecan April 3, 2024 16:53
@diegomarvid diegomarvid added the enhancement New feature or request label Apr 3, 2024
@diegomarvid diegomarvid marked this pull request as ready for review April 4, 2024 17:10
@diegomarvid diegomarvid merged commit 0cb6b3a into main Apr 12, 2024
1 check passed
@diegomarvid diegomarvid deleted the encoding branch April 12, 2024 21:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants