dirty_cat
dirty_cat is a Python module for machine-learning on dirty categorical variables.
Website: https://dirty-cat.github.io/
Installation
Dependencies
dirty_cat requires:
- Python (>= 3.5)
- NumPy (>= 1.8.2)
- SciPy (>= 0.13.3)
- scikit-learn
Optional dependency:
- python-Levenshtein for faster edit distances (not used for the n-gram distance)
User installation
If you already have a working installation of NumPy and SciPy,
the easiest way to install dirty_cat is using pip
pip install -U ...
Citation
If you use this module in a scientific publication, please cite the following: (coming soon :))