聚类算法之层次聚类

分级聚类就是一棵树

加入我们有如下一张图

那么通过聚类之后形成一颗如下的树：

现在就分好了级，而且还能看出距离关系， 很明显ab之间的距离比de之间的距离要短

#coding:utf-8
import os
import sys
import chardet
from math import sqrt
from PIL import Image, ImageDraw
import random

def readFile(fileName):
    lines = [line for line in file(fileName)]
    colNames = lines[0].strip().split('\t')[1:]
    rowNames = []
    data = []
    for line in lines[1:]:
        p = line.strip().split('\t')
        rowNames.append(p[0])
        data.append([float(x) for x in p[1:]])
    return rowNames, colNames, data

def pearsonBeta(v1, v2):
    sum1 = sum(v1)
    sum2 = sum(v2)
    
    sum1Sq = sum([pow(v, 2) for v in v1])
    sum2Sq = sum([pow(v, 2) for v in v2])
    
    pSum = sum([v1[i] * v2[i] for i in range(len(v1))])
    
    nums = pSum - (sum1 * sum2 / len(v1))
    den = sqrt((sum1Sq - pow(sum1, 2) / len(v1)) * (sum2Sq - pow(sum2, 2) / len(v2)))
    if(den == 0):
        return 0
    return 1.0 - nums/den

#距离函数
def pearson(v1, v2):
    sum1 = sum(v1)
    sum2 = sum(v2)
    eSum1 = sum1 / len(v1)