pyclustering.cluster.ema.ema_init_type Class Reference

Enumeration of initialization types for Expectation-Maximization algorithm. More...

+ Inheritance diagram for pyclustering.cluster.ema.ema_init_type:
+ Collaboration diagram for pyclustering.cluster.ema.ema_init_type:

Static Public Attributes

int RANDOM_INITIALIZATION = 0
 Means are randomly taken from input dataset and variance or covariance is calculated based on spherical data that belongs to the chosen means. More...
 
int KMEANS_INITIALIZATION = 1
 Two step initialization. More...
 

Detailed Description

Enumeration of initialization types for Expectation-Maximization algorithm.

Definition at line 84 of file ema.py.

Member Data Documentation

◆ KMEANS_INITIALIZATION

int pyclustering.cluster.ema.ema_init_type.KMEANS_INITIALIZATION = 1
static

Two step initialization.

The first is calculation of initial centers using K-Means++ method. The second is K-Means clustering using obtained centers in the first step. Obtained clusters and its centers are used for calculation of variance (covariance in case of multi-dimensional) data.

Definition at line 98 of file ema.py.

◆ RANDOM_INITIALIZATION

int pyclustering.cluster.ema.ema_init_type.RANDOM_INITIALIZATION = 0
static

Means are randomly taken from input dataset and variance or covariance is calculated based on spherical data that belongs to the chosen means.

Definition at line 92 of file ema.py.


The documentation for this class was generated from the following file: