灰色关联分析(Grey Relation Analysis,GRA)中国经济社会发展指标

##生成数据
#
  # 异常控制 #
  if (any(is.na(df))) stop("'df' have NA" )
  if (distingCoeff<0 | distingCoeff>1) stop("'distingCoeff' must be in range of \[0,1\]" )
  

  
  
  diff = X  #设置差学列矩阵空间
  
  for (i in 
  mx = max(diff)
  
  
  #计算关联系数#
  relations = (mi+distingCoeff\*mx) / (diff + distingCoeff\*mx)
  
  #计算关联度#
  # 暂时简单处理, 等权
  relDegree = rep(NA, nc)
  for (i in 1:nc) {
    relDegree\[i\] = mean(relations\[,i\])  # 等权
  }
  
  
  #排序: 按关联度大到小#
  X_order = X\[order(relDegree, 
  relDes = rep(NA, nc) #分配空间  关联关系描述(说明谁和谁的关联度)
  X\_names = names(X\_o
  names(relationalDegree) = relDes
  
  
  if (cluster) {
    
    greyRelDegree = GRA(economyC
    
      
    # 得到差异率矩阵 #
    grey_diff = matrix(0
        
        grey_diff\[i,j\] = abs(rel
    #得到距离矩阵#
    grey_dist = matrix(0, nrow
iff\[i,j\]+grey_diff\[j,i\]
      }
    }
    
    # 得到灰色相关系数矩阵 #
    grey\_dist\_max = max(grey_dist)
    grey_correl = matrix(0, nrow = nc, ncol = nc)
    for (i in 1:nc) {
      for (j in 1:nc) {
        grey\_correl\[i,j\] = 1 - grey\_dist\[i,j\] / grey\_dist\_max
      }
    }
    

    
    d = as.dist(1-grey_correl)  # 得到无对角线的下三角矩阵(数值意义反向了, 值越小表示越相关 )
    # 主对角线其实表示了各个对象的相近程度, 画图的时候, 相近的对象放在一起
    
    hc = hclust(d, method = clusterMethod)  # 系统聚类(分层聚类)函数, single: 单一连接(最短距离法/最近邻) 
    # hc$height, 是上面矩阵的对角元素升序
    # hc$order, 层次树图上横轴个体序号
    plot(hc,hang=-1)  #hang: 设置标签悬挂位置
    
  }
  
  #输出#
  
  if (cluster)  {
    lst = list(relationalDegree=relationalDegree, 
  
  return(lst)
  
}

## 生成数据
rownames(economyCompare) = c("indGV", "indVA", "profit", "incomeTax")
## 灰色关联度
greyRelDegree = greya(economyCompare)
greyRelDegree

## 灰色聚类

greya(economyCompare, cluster = T)