How to understand expectation maximization clustering in R language clustering algorithm

Today, I will talk to you about how to understand expectation maximization clustering in R language clustering algorithm, which may not be well understood by many people. in order to make you understand better, the editor has summarized the following contents for you. I hope you can get something from this article.

1. Principle analysis:

It regards the data set as a probability model with hidden variables, and for the purpose of realizing the model optimization, that is, to obtain the clustering method that best matches the properties of the data itself, it finds the optimal solution by "repeatedly estimating" the model parameters. at the same time, the corresponding optimal category k is given. The process of "repeated estimation" is the essence of EM algorithm, which is realized alternately by two steps: E-step (Expectation) and M-step (Maximization).

two。 Application in R language

Expectation maximization clustering is mainly applied to the Mclust function in the mcluster package.

Mclust (data,G=NULL,modelNames=NULL,prior=NULL,control=emControl (), initialization=NULL,warn=FALSE, …)

3. Taking iris dataset as an example for analysis

1) apply the model and view the corresponding parameters of the model

Fit_EM=Mclust (iris [,-5])

Fit_ EM [1: length (fit_EM)]

After reading the above, do you have any further understanding of how to understand expectation maximization clustering in R language clustering algorithm? If you want to know more knowledge or related content, please follow the industry information channel, thank you for your support.