A package for density estimation and clustering using infinite gaussian mixtures with stick-breaking weighting structures
Project description
Project description
Pyrichlet is a package useful for doing data analysis via density estimation and clustering using gaussian mixtures with weighting structures generated with the stick-breaking method.
Installation
This project is hosted in pip, it's enought to do
pip install pyrichlet
Usage
The weighting structure models that this package implements are
DirichletDistribution
DirichletProcess
PitmanYorProcess
GeometricProcess
BetaInBetaProcess
BetaInDirichletProcess
BetaBernoulliProcess
BetaBinomialProcess
They can be imported and initialized as
from pyrichlet import weight_models
wm = weight_models.DirichletProcess()
For each weighting structure there is an associated gaussian mixture model, formerly
DirichletDistributionMixture
DirichletProcessMixture
PitmanYorMixture
GeometricProcessMixture
BetaInBetaMixture
BetaInDirichletProcess
BetaBernoulliMixture
BetaBinomialMixture
The mixture models can fit array or dataframe data
from pyrichlet import mixture_models
mm = mixture_models.DirichletProcessMixture()
y = [1, 2, 3, 4]
mm.fit_gibbs(y)
x = 2.5
f_x = mm.gibbs_eap_density(x)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pyrichlet-0.0.2.tar.gz
(20.1 kB
view hashes)
Built Distribution
pyrichlet-0.0.2-py3-none-any.whl
(30.9 kB
view hashes)
Close
Hashes for pyrichlet-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 04fe7a55185967bfc60dc881912b9be054421fd22542478e5d94150c014bc8ef |
|
MD5 | 21b8b04660261ed8a342c3050654d5dd |
|
BLAKE2b-256 | cdec826849dd38de9325b3459752f313f073d0d7f821ca87c3e597028b21d75c |