XicorPy is a Python package implementing Chatterjee's Xi, and its various offshoots. You can use the package with raw python objects, NumPy arrays, or Pandas DataFrames.
Please see the Documentation for an introductory tutorial and a full user guide.
The package currently implements:
- Chatterjee's Xi from [1]
- Modified Xi from [2]
- Codependence Coefficient from [3]
- Feature Ordering by Conditional Independence (FOCI) for Feature Selection from [3]
The package is available on PyPI. You can install using pip: pip install xicorpy
.
import xicorpy
x = [10, 8, 13, 9, 11, 14, 6, 4, 12, 7, 5]
y = [8.04, 6.95, 7.58, 8.81, 8.33, 9.96, 7.24, 4.26, 10.84, 4.82, 5.68]
xi = xicorpy.compute_xi_correlation(x, y)
xi, p_value = xicorpy.compute_xi_correlation(x, y, get_p_values=True)
Refer to the Docs for more details.
Any help with the package is greatly appreciated! Pull requests and bug reports are greatly welcome!