Skip to content

Conversation

@Abdur-Rahim-sheikh
Copy link

I implemented the whole code from scratch,
And as you asked to give a pull request. So I did. Thank you for your great service.

F1 score for,
Undersampling = 74%
Oversampling = 78%
smote = 81%

F1 score for,
Undersampling = 74%
Oversampling = 78%
smote = 81%
And yes, I implemented this from scratch
@dhavalsays
Copy link
Contributor

Hey, thanks for the pull request. Please make following changes,

  1. Rename the file to follow the snake case convention.
  2. Perform undersampling, oversampling, etc. on the training set, not the entire dataset. I know that's what I did in the original tutorial but that was an oversight. Ideally, we need to perform these operations on a training set only to avoid data leakage.

@Abdur-Rahim-sheikh
Copy link
Author

Sir, i renamed the file in snake case format. And only sampled data on train set. My latest push has the update.

I'm glad that, i'm following since 2021. And the pull request was 3 years ago and you are still reviewing it.

@Abdur-Rahim-sheikh Abdur-Rahim-sheikh closed this by deleting the head repository May 24, 2025
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

Successfully merging this pull request may close these issues.

2 participants