Shulou(Shulou.com)06/01 Report--

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

1. Principle analysis:

1. Select an unprocessed sample point from the dataset

two。 Taking 1 as the center of the circle and making the circle with radius E, because the number of points in the circle is 3, which satisfies the density threshold Minpts, point 1 is called the core object (black solid dot), and the four points in the circle are formed into a cluster, in which the direct density of point 1 can reach the three gray solid origin around it.

3. Repeat step 2 several times, in which the direct density of point 1 can reach core object 3, and the density of point 2 can reach point 3.

4. When the process is carried out to the graph Ⅳ, there are only two points in the E neighborhood of 4, the drizzle threshold MinPts, so point 4 is the edge point (non-core object), marked as ⓧ, and continue to investigate other points.

5. When all the objects are examined, the process ends and the graph Ⅷ. There are several core objects and edge points in the ellipse, all of which are connected by density.

6. For point classification, such as figure Ⅸ: point set black circle mutual density can reach, belong to category 1: point set black triangle mutual density can reach, belong to a new category, recorded as category 2; point set white circle and category 1 sample point density connected, belong to category 3; point set white triangle and category 2 sample point density connected, belong to category 4; point ⓧ neither core object, nor density connected, for noise.

two。 Application in R language

Density clustering (Density-based Methods) is mainly applied to the dbscan function in fpc packets.

Dbscan (data,eps,MinPts=5,scale=FALSE,method=c ("hybird", "raw", "dist"), seeds=TRUE,showplot=FALSE,countmode=NULL)

3. Taking iris dataset as an example for analysis

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

Ds=dbscan (iris [,-5], eps=0.3,MinPts=4)

DS [1: length (ds)]

After reading the above, do you have any further understanding of how to understand the density 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.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.