分级聚类

根据皮尔逊相关系数获取所有数据的相关性，相关性最强的进行聚类，一层层处理完毕数据。

python代码：

读取数据

#读取数据
def readfile(filename):
    lines = [line for line in open(filename)]

    # 列标题
    colnames = lines[0].strip().split('\t')[1:]
    rownames = []
    data = []
    for line in lines[1:]:
        p = line.strip().split('\t')
        # 第一列是标题
        rownames.append(p[0])
        # 数据
        data.append([float(x) for x in p[1:]])
    return rownames, colnames, data

#皮尔逊相关系数用于找寻相关度最高的博客
def pearson(v1, v2):
    # 求和
    sum1 = sum(v1)
    sum2 = sum(v2)

    # 求平方和
    sum1Sq = sum([pow(v, 2) for v in v1])
    sum2Sq = sum([pow(v, 2) for v in v2])

    # 乘积和
    pSum = sum([v1[i] * v2[i] for i in range(len(v1))])

    # 皮尔逊系数
    num = pSum - (sum1 * sum2 / len(v1))
    den = sqrt((sum1Sq - pow(sum1, 2) / len(v1)) * (sum2Sq - pow(sum2, 2) / len(v1)))
    if den == 0: return 0

    return 1.0 - num / den

#聚类计算
def hcluster(rows,distance=pearson):
  distances={}
  currentclustid=-1

  # 存储带聚类数据
  clust=[bicluster(rows[i],id=i) for i in range(len(rows))]

  while len(clust)>1:
    #存储pearson最相关数据ID
    lowestpair=(0,1)
    closest=distance(clust[0].vec,clust[1].vec)

    # 遍历寻找最小距离
    for i in range(len(clust)):
      for j in range(i+1,len(clust)):
        # distances 存储所有数据pearson数据
        if (clust[i].id,clust[j].id) not in distances:
          distances[(clust[i].id,clust[j].id)]=distance(clust[i].vec,clust[j].vec)

        d=distances[(clust[i].id,clust[j].id)]
        if d<closest:
          closest=d
          lowestpair=(i,j)

    # 计算聚类的平均值
    mergevec=[
    (clust[lowestpair[0]].vec[i]+clust[lowestpair[1]].vec[i])/2.0
    for i in range(len(clust[0].vec))]

    # 建立新的聚类（排除下级最相关pearson）
    newcluster=bicluster(mergevec,left=clust[lowestpair[0]],
                         right=clust[lowestpair[1]],
                         distance=closest,id=currentclustid)

    # 不在原始聚类中ID为负数
    currentclustid-=1
    del clust[lowestpair[1]]
    del clust[lowestpair[0]]
    clust.append(newcluster)
    for c in clust:
        print(c.id,c.left,c.right,c.distance,c.vec)
    print('finish')

  return clust[0]