Experimental data mining (h): DBSCAN clustering R language

First, the purpose of the experiment

1. Understand the basic principles of DBSCAN;
2. DBSCAN write code and implement algorithms for data clustering

Second, the experimental procedures

1. Using data sets: R factoextra bag multishapes language data set
   
2. Function first determines two parameters:
   (. 1) Epsilon: radius around a point adjacent the area
   (2) minPts: adjacent to the inner region comprises at least a number of points
   according to the above two parameters, sample points can be divided into three categories:

Nuclear Point: meet point within the field> = minPts, compared sample points nuclear
boundary points: points that satisfy <minPts in the art, but this point may be a number of core points obtained
noise points: neither nucleation point is an edge point is not, it is point does not belong to this category

• DisMatrix distance matrix between the calculation point and the point from European
• Add the data set columns visited, unvisited represents 0, 1 visited
• Type judgment points stored in data_N
• Delete noise points stored in data_C
• Recalculated from the field, associated with the intersection of
• For different types of point labels
• Draw

Third, the experiment code

library(factoextra)
library(ggplot2)

data<-data.frame(multishapes[,1:2])

ggplot(data,aes(x,y))+geom_point()

#主函数
DBSCAN = function(data,eps,MinPts){

rows = nrow(data)
disMatrix<-as.matrix(dist(data, method = "euclidean"))#求距离

data$visited <- rep(0,rows)
names(data)<-c("x","y","visited")

data_N = data.frame(matrix(NA,nrow =rows,ncol=3)) #领域集N，存放索引、领域内的点数、点的类型
names(data_N)<-c("index","pts","cluster")
 
#判断点的类型，1核心点，2边界点，0噪声点

for(i in 1:rows){
  if(data$visited[i] == 0){ #未被访问的点
    data$visited[i] = 1  #标记已经被访问
    index <- which( disMatrix[i,] <= eps)
    pts <- length(index)
     
   
     if(pts >= MinPts){
      data_N[i,]<-c(i,pts,"1")
    }else if(pts>1 && pts< MinPts){
      data_N[i,]<-c(i,pts,"2")
    }else{
      data_N[i,]<-c(i,pts,"0")
    }
  }
}

   #删除噪声点
  data_C<-data[which(data_N$cluster!=0),]
  
  #去掉噪声点之后的领域
  disMatrix2<-as.matrix(dist(data_C, method = "euclidean"))
  Cluster<-list()
  for(i in 1:nrow(data_C)){
    Cluster[[i]]<-names(which(disMatrix2[i,]<= eps))
  }
  
#合并有交集的邻域，生成一个新簇

  for(i in 1:length(Cluster)){
    for(j in 1:length(Cluster)){
      if(i!=j && any(Cluster[[j]] %in% Cluster[[i]])){
        if(data_N[Cluster[[i]][1],]$cluster=="1"){
          Cluster[[i]]<-unique(append(Cluster[[i]],Cluster[[j]])) #合并，删除重复
          Cluster[[j]]<-list()
        }
      }
    }
  }

  newCluster<-list()       #去掉空列表
  for(i in 1:length(Cluster)){
    if(length(Cluster[[i]])>0){
      newCluster[[length(newCluster)+1]]<-Cluster[[i]]
    }
  }
  
  #为相同簇中的对象赋相同的标签

  
  data_C[,4]<-as.character()
  for(i in 1:length(newCluster)){
    for(j in 1:length(newCluster[[i]])){
      data_C[newCluster[[i]][j],4]<-i
    }
    
  }
  return(data_C)
}


  
  
  #运行
test<-DBSCAN(data,0.15,6)  #设定eps为0.15，minpts为6


ggplot(test,aes(x,y,colour=factor(test[,4])))+
  geom_point(shape=factor(test[,4]))

Fourth, operating results

The original data

after clustering