DBSCAN密度聚类

def distance(data):
    m, n = np.shape(data)
    dis = np.mat(np.zeros((m, m)))
    for i in range(m):
        for j in range(i, m):
            # 计算i和j之间的欧式距离
            tmp = 0
            for k in range(n):
                tmp += (data[i, k] - data[j, k]) * (data[i, k] - data[j, k])
            dis[i, j] = np.sqrt(tmp)
            dis[j, i] = dis[i, j]
    return dis

def find_eps(distance_D, eps):
    ind = []
    n = np.shape(distance_D)[1]
    for j in range(n):
        if distance_D[0, j] <= eps:
            ind.append(j)
    return ind
def dbscan(data, eps, MinPts):
    m = np.shape(data)[0]
    # 区分核心点1，边界点0和噪音点-1
    types = np.mat(np.zeros((1, m)))
    sub_class = np.mat(np.zeros((1, m)))
    # 用于判断该点是否处理过，0表示未处理过
    dealed = np.mat(np.zeros((m, 1)))
    # 计算每个数据点之间的距离
    dis = distance(data)
    # 用于标记类别
    number = 1

    # 对每一个点进行处理
    for i in range(m):
        # 找到未处理的点
        if dealed[i, 0] == 0:
            # 找到第i个点到其他所有点的距离
            D = dis[i,]
            # 找到半径eps内的所有点
            ind = find_eps(D, eps)
            # 区分点的类型
            # 边界点
            if len(ind) > 1 and len(ind) < MinPts + 1:
                types[0, i] = 0
                sub_class[0, i] = 0
            # 噪音点
            if len(ind) == 1:
                types[0, i] = -1
                sub_class[0, i] = -1
                dealed[i, 0] = 1
            # 核心点
            if len(ind) >= MinPts + 1:
                types[0, i] = 1
                for x in ind:
                    sub_class[0, x] = number
                # 判断核心点是否密度可达
                while len(ind) > 0:
                    dealed[ind[0], 0] = 1
                    D = dis[ind[0],]
                    tmp = ind[0]
                    del ind[0]
                    ind_1 = find_eps(D, eps)

                    if len(ind_1) > 1:  # 处理非噪音点
                        for x1 in ind_1:
                            sub_class[0, x1] = number
                        if len(ind_1) >= MinPts + 1:
                            types[0, tmp] = 1
                        else:
                            types[0, tmp] = 0

                        for j in range(len(ind_1)):
                            if dealed[ind_1[j], 0] == 0:
                                dealed[ind_1[j], 0] = 1
                                ind.append(ind_1[j])
                                sub_class[0, ind_1[j]] = number
                number += 1

    # 最后处理所有未分类的点为噪音点
    ind_2 = ((sub_class == 0).nonzero())[1]
    for x in ind_2:
        sub_class[0, x] = -1
        types[0, x] = -1

    return types, sub_class
from sklearn.datasets.samples_generator import make_moons
X,y_true = make_moons(n_samples=1000,noise=0.15)
# print(X)
# print(y_true)
plt.scatter(X[:,0],X[:,1],c=y_true)
plt.show()
data = X
eps = 0.05
MinPts = 40
type1,class1 = dbscan(data, eps, MinPts)
plt.scatter(X[:,0],X[:,1],c=class1.tolist()[0])
plt.show()

参考链接：http://www.go60.top/view/88.html