Mixture-Models: a one-stop Python Library for Model-based Clustering using various Mixture Models
This library addresses the need for a comprehensive, extensible tool for model-based clustering in Python, particularly for high-dimensional data, though it is incremental as it builds on existing mixture model methods.
The authors developed Mixture-Models, a Python library for fitting Gaussian mixture models and variants using optimization routines like gradient descent, enabling high-dimensional data analysis and providing evaluation tools like BIC and AIC. They conducted simulations comparing gradient-based methods to Expectation Maximization to identify the best-suited approaches across various settings.
\texttt{Mixture-Models} is an open-source Python library for fitting Gaussian Mixture Models (GMM) and their variants, such as Parsimonious GMMs, Mixture of Factor Analyzers, MClust models, Mixture of Student's t distributions, etc. It streamlines the implementation and analysis of these models using various first/second order optimization routines such as Gradient Descent and Newton-CG through automatic differentiation (AD) tools. This helps in extending these models to high-dimensional data, which is first of its kind among Python libraries. The library provides user-friendly model evaluation tools, such as BIC, AIC, and log-likelihood estimation. The source-code is licensed under MIT license and can be accessed at \url{https://github.com/kasakh/Mixture-Models}. The package is highly extensible, allowing users to incorporate new distributions and optimization techniques with ease. We conduct a large scale simulation to compare the performance of various gradient based approaches against Expectation Maximization on a wide range of settings and identify the corresponding best suited approach.