Gaussian Mixtures

Overview

This project has two objectives:

1. Provide a set of functions for working with univariate Gaussian Mixture distributions similar to dmixnorm of the KScorrect R package.

2. Provide a recipe for implementing conditional density estimation (CDE) using (Gaussian) kernel methods combined with neural networks.

Dependencies

• (required) numpy (1.17)

• (required) scipy (1.3.1)

• (needed for plotting) pandas (0.25.1)

• (needed for plotting) plotnine (0.6.0)

• (needed for CDE and demo) TensorFlow (1.15)

• (needed for CDE and demo) TensorFlow Probability

• (needed for CDE and demo) Keras (2.3.1)

• (needed to make kernel centers using the Jenks algorithm) jenkspy (0.1.5)

A full list of packages, not all of which are required, are given in the requirements file.

Install

The project is not currently on PyPI. The easiest way to use or install the project is to clone it or via pip using its native Git support. Note you will need a working C++ compiler.

pip install git+https://bitbucket.org/reidswanson/gmix.git

Contents:

• Gaussian Mixture Distributions
  • Overview
  • Examples
• Conditional Density Estimation
  • Network Architecture
  • Alternative Implementations
• Demo
  • Command Line Options

Module Documentation:

• cde
  • cde package

Indices and tables

• Index

• Module Index

• Search Page