聚类算法

tab不能缩进，吃枣药丸
`
class bicluster:
def init(self, vec, left=None, right=None, distance=0.0, id=None):
self.left=left
self.right=right
self.vec=vec
self.id=id
self.distance=distance

def hcluster(rows, distance=pearson):
distances=()
currentclustid = -1
clust = [bicluster(rows[i], id = i) for i in range(len(rows))]

遍历每一个配对，寻找最小距离

while len(clust)>1:
    lowestpair = (0,1)
    closest = distance(clust[0].vec, clust[1].vec)
    for i in range(len(clust)):
        for j in range(i+1, len(clust)):
            if (clust[1].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)

计算两个聚类的平均值

    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

    newcluster = bicluster(mergevec,left=clust(lowestpair[0]],right = clust[lowestpair[1]], distance = closest, id = currentclustid)

不在原始集合中的聚类，其id为负数

    currentclustid-=1
    del clust[lowestpair[1]]
    del clust[lowestpair[0]]
    clust.append(newcluster)
return clust[0]

调用：

import clusters
blognames,words,data = clusters.readfile
clust = clusters.hcluster(data)

vec是什么？

markdown格式有毒（