GitHub - gift-exe/MultiLabel-Encoding: Multilabel Encoding. Found out about this concept while checking out Alexey Grigorev's free ML course. Decided to explore it (^_^ )

Simple Tool For Encoding Multilabeled Columns

The MultiLabelEncoder class from main.py, takes care of encoding the multilabeled column.

To use, create a MultiLabelEncoder object, parameters are:

multilabel_column type: pd.Series
unique_labels type:set [optional]
delimiter type:str [optional]

As of 22.07.2024 the Encoder works best on csv files, where the columns are strings.
Typically looking like this:

TAGS
"Factory Tuner,Luxury,High-Performance"
"Luxury,Performance"
"Luxury,High-Performance"

Here the delimiter is a comma ','

For sample usage, check out thte mlc.ipynb notebook Thank you (^_^ )

Name		Name	Last commit message	Last commit date
Latest commit History 32 Commits
__pycache__		__pycache__
README.md		README.md
data.csv		data.csv
main.py		main.py
mlc.ipynb		mlc.ipynb
playing_around_eda.ipynb		playing_around_eda.ipynb
processed_data.csv		processed_data.csv