Python集体智慧编程之发现群组--聚类算法

from PIL import Image, ImageDraw


def readfile(filename):
    with open(filename, 'r') as file:
        lines = [line for line in file]

        # 第一列作为标题
        colnames = lines[0].strip().split('\t')[1:]
        rownames = []
        data = []
        for line in lines[1:]:
            p = line.strip().split('\t')
            # 每行第一列作为行名
            rownames.append(p[0])
            # 每行统计的数量
            data.append([float(x) for x in p[1:]])
    return rownames, colnames, data


from math import sqrt


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])

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

    # 1-皮尔逊相关度，两个元素越相似，距离越短
    num = pSum - (sum1 * sum2 / len(v1))
    den = sqrt((sum1Sq - pow(sum1, 2) / len(v1)) * (sum2Sq - pow