【无标题】

层次聚类法

运行结果

Kmeans方法

数据点的分布

聚类结果

代码

import numpy as np
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import linkage,dendrogram,fcluster
from sklearn.cluster import KMeans
def hierarchy_way():
    #生成数据
    data = []
    for i in range(1,11):
        data.append(np.random.randint(10*(i-1),10*i,size=(5,)))
    #画图
    mergings = linkage(data,method="average")
    print(data)
    fig = plt.figure(figsize=(10,6))
    dendrogram(mergings)
    plt.show()
def Kmeans_way():
    #生成数据
    x = []
    y = []
    for i in range(1,10,3):
        tx = np.random.randn(50,) 
        ty = np.random.randn(50,)
        x += [item+i for item in tx]
        y += [item+i for item in ty]
    point = []
    for i in range(len(x)):
        t = [ x[i],y[i] ]
        point.append(t)
    model = KMeans(n_clusters=3)
    model.fit(point)#分组

    centers = model.cluster_centers_
    print(centers)
    labels = model.labels_
    print(labels)
    center_x = centers[:,0]
    center_y = centers[:,1]
    plt.scatter(x,y,c=labels)
    plt.scatter(center_x,center_y,marker='X',s=100,c='r')
    plt.show()

if __name__ == '__main__':
    Kmeans_way()

说明

​ 通过随机函数生成数据进行聚类分析，了解了Python关于聚类分析的相关库。

​ 然后…哎呀~谁的头发