✔️ Linting Passed

All linting checks passed. Your pull request is in excellent shape! ☀️

_{Generated for commit: b051377. Link to the linter CI: here}

Hi @StefanieSenger. Please let me know if the changes I've made in this PR are correct. I modify it if needed. Thank you.

The link is alright, but looking at the example, it looks really poor, and really old in terms of lack of notebook styling, good explanation of the example, and lacking any plots.

How do you think we can improve the example @StefanieSenger ?

So if you are up to it you could take on improving this example, @elhambbi.

It could be something minimal as in #30476 or something more elaborated as in #30990, or something in between as in #29788, #29788 or #29149 (so you have some idea of how improving an example could look like).

In terms of content I could imagine to

• a bar chart can compare the f1 scores from eval_and_print_metrics()
• describe how adding SelfTrainingClassifier or LabelSpreading to the pipeline improves performance compared to training a supervised model on only on 20 % of the data
• add sub captions and short descriptions or comments to describe what is happening

More on the technical side, you could

• remove the if __name__ == "__main__":
• convert old string representations (like "%d documents" % ...) into f-strings
• stop printing verbose output for all the iteration in SelfTrainingClassifier

Would you be willing to work on that, @elhambbi?

So if you are up to it you could take on improving this example, @elhambbi.

It could be something minimal as in #30476 or something more elaborated as in #30990, or something in between as in #29788, #29788 or #29149 (so you have some idea of how improving an example could look like).

In terms of content I could imagine to

• a bar chart can compare the f1 scores from eval_and_print_metrics()
• describe how adding SelfTrainingClassifier or LabelSpreading to the pipeline improves performance compared to training a supervised model on only on 20 % of the data
• add sub captions and short descriptions or comments to describe what is happening

More on the technical side, you could

• remove the if __name__ == "__main__":
• convert old string representations (like "%d documents" % ...) into f-strings
• stop printing verbose output for all the iteration in SelfTrainingClassifier

Would you be willing to work on that, @elhambbi?

Hi @StefanieSenger . Sure, thank you. I'd be happy to help with improving this example. As soon as I have something done, I'll let you know.

@adrinjalali, can we merge this PR already? The example is updated in another PR.

I think the link can be added in the same PR as #31104, so that the link is added at the same time as the example is improved. Therefore closing this PR.