Pytho集体智慧编程之聚类算法2

#tanamoto系数，适用于1和0
def tanamoto(v1, v2):
    c1, c2, shr = 0, 0, 0

    for i in range(len(v1)):
        if v1[i] != 0: c1 += 1  # in v1
        if v2[i] != 0: c2 += 1  # in v2
        if v1[i] != 0 and v2[i] != 0: shr += 1  # in both

    return 1.0 - (float(shr) / (c1 + c2 - shr))

#wants,people,data=readfile('zebo.txt')
#clust=hcluster(data,distance=tanamoto)
#drawdendrogram(clust,wants,jpeg='zeboclusters.jpg')

def scaledown(data, distance=pearson, rate=0.01):
    n = len(data)

    # 每一对群组的真实距离
    realdist = [[distance(data[i], data[j]) for j in range(n)] #nxn的一个数组
                for i in range(0, n)]

    # 随机初始化节点在2维空间的坐标，将一个群组的多维数据投影成2维
    loc = [[random.random(), random.random()] for i in range(n)]#2xn的一个数组
    fakedist = [[0.0 for j in range(n)] for i in range(n)]#nxn的一个数组

    lasterror = None
    for m in range(0, 1000):
        # 寻找投影后的每两点距离（有重复计算，A1--》A2与A2--》A1）
        for i in range(n):
            for j in range(n):
                fakedist[i][j] = sqrt(sum([pow(loc[i][x] - loc[j][x], 2)
                                           for x in range(len(loc[i]))]))

        # 移动节点
        grad = [[0.0, 0.0] for i in range(n)]

        totalerror = 0
        for k in range(n):
            for j in range(n):
                if j == k: continue
                # 误差值等于（目标距离-实际距离）/实际距离
                errorterm = (fakedist[j][k] - realdist[j][k]) / realdist[j][k]

                # 每个节点根据误差，按比例移动靠近或远离其他节点（与其他节点的差值的累积和）
                grad[k][0] += ((loc[k][0] - loc[j][0]) / fakedist[j][k]) * errorterm
                grad[k][1] += ((loc[k][1] - loc[j][1]) / fakedist[j][k]) * errorterm

                # 记录总误差
                totalerror += abs(errorterm)
        #print(totalerror)

        # 如果结果变差，结束
        if lasterror and lasterror < totalerror: break
        lasterror = totalerror

        # 根据 rate 和 gradient乘积，移动每一个节点
        for k in range(n):
            loc[k][0] -= rate * grad[k][0]
            loc[k][1] -= rate * grad[k][1]

    return loc


def draw2d(data, labels, jpeg='mds2d.jpg'):
    img = Image.new('RGB', (2000, 2000), (255, 255, 255))
    draw = ImageDraw.Draw(img)
    for i in range(len(data)):
        x = (data[i][0] + 0.5) * 1000
        y = (data[i][1] + 0.5) * 1000
        draw.text((x, y), labels[i], (0, 0, 0))
    img.save(jpeg, 'JPEG')

coords=scaledown(data)
draw2d(coords,blognames,jpeg="blogs2d.jpg")