discrimintools 0.0.1

Python package dedicated to Discriminant Analysis (DA) distributed under the MIT License

discrimintools : Python library for discriminant analysis

About discrimintools

discrimintools is a Python package dedicated to Discriminant Analysis (DA) distributed under the MIT License.

Overview

Discriminant analysis is a classification problem, where two or more groups or clusters or populations are known a priori and one or more new observations are classified into one of the known populations based on the measured characteristics.

Why use discrimintools?

With this discrimintools package, you can perform :

• Canonical Discriminant Analysis (CANDISC)
• Linear Discriminant Analysis (LDA)
• Principal Components Analysis - Discriminant Analysis (PCADA)
• Discriminant Analysis for qualitatives/categoricals variables (DISQUAL)
• Discriminant Analysis of Mixed Data (DISMIX)
• Discriminant Correspondence Analysis (DISCA)
• Stepwise Discriminant Analysis (STEPDISC)

Installation

Dependencies

discrimintools requires

Python >= 3.10
numpy >= 1.26.4
pandas >=2.2.2
scikit-learn >=1.2.2
polars >= 0.19.2
plotnine >= 0.10.1
mapply >= 0.1.21
scientisttools >= 0.1.4
statsmodels >= 0.14.0
scipy >= 1.10.1

User installation

You can install discrimintools using pip :

pip install discrimintools

Documentation

The docstring is written in english

References

http://www.math.wpi.edu/saspdf/stat/chap25.pdf

https://support.sas.com/documentation/cdl/en/statugdiscrim/61779/PDF/default/statugdiscrim.pdf

https://online.stat.psu.edu/stat505/lesson/10

https://eric.univ-lyon2.fr/ricco/cours/slides/analyse_discriminante.pdf

https://eric.univ-lyon2.fr/ricco/cours/cours/Pratique_Analyse_Discriminante_Lineaire.pdf

Authors

Duvérier DJIFCK ZEBAZE [e-mail]