聚类--K均值算法:自主实现与sklearn.cluster.KMeans调用
import numpy as np x = np.random.randint(1,50,[20,1]) y = np.zeros(20) k = 3 def initcen(x,k): #选取数据空间中的K个对象作为初始中心,每个对象代表一个聚类中心 return x[:k] def nearest(kc,i): #对于样本中的数据对象,根据它们与这些聚类中心的欧氏距离,按距离最近的准则将它们分到距离它们最近的聚类中心(最相似)所对应的类; p = abs(kc-i) q = np.where(p == np.min(p)) return q[0][0] def xclassify(x,y,kc): for i in range(x.shape[0]): y[i]= nearest(kc,x[i]) return y def kcmean(x,y,kc,k): #更新聚类中心:将每个类别中所有对象所对应的均值作为该类别的聚类中心,计算目标函数的值 l = list(kc) flag = False for c in range(k): m = np.where(y == 0) n = np.mean(x[m]) if l[c] != n: l[c] = n flag = True print(l,flag) return(np.array(l),flag) kc = initcen(x,k) #判断聚类中心和目标函数的值是否发生改变,若不变,则输出结果,若改变,则返回2) flag = True print(x,y,kc,flag) while flag: y = xclassify(x,y,kc) kc,flag = kcmean(x,y,kc,k) print(y,kc)
运行结果:
from sklearn.datasets import load_iris # 导入鸢尾花数据集,鸢尾花花瓣长度数据做聚类并用散点图显示 iris = load_iris() datas = iris.data iris_length=datas[:,2] x = np.array(iris_length) #用鸢尾花花瓣长度做分析 y = np.zeros(x.shape[0]) kc = initcen(x,3) flag = True while flag: y = xclassify(x,y,kc) kc,flag = kcmean(x,y,kc,3) print(kc,flag) import matplotlib.pyplot as plt plt.scatter(iris_length, iris_length, marker='D', c=y, alpha=0.5) #散点图 plt.show()
运行结果:
from sklearn.cluster import KMeans #用sklearn.cluster.KMeans,鸢尾花花瓣长度数据做聚类并用散点图显示 iris_length = datas[:, 2:3] k_means = KMeans(n_clusters=3) result = k_means.fit(iris_length) kc1 = result.cluster_centers_ y_kmeans = k_means.predict(iris_length) plt.scatter(iris_length,np.linspace(1,150,150),c=y_kmeans,marker='D') #散点图 plt.show()
运行结果:
k_means1 = KMeans(n_clusters=3) #鸢尾花完整数据做聚类并用散点图显示 result1 = k_means1.fit(datas) kc2 = result1.cluster_centers_ y_kmeans1 = k_means1.predict(datas) print(y_kmeans1, kc2) print(kc2.shape, y_kmeans1.shape, datas.shape) plt.scatter(datas[:, 0], datas[:, 1], c=y_kmeans1, marker='p') plt.show()
运行结果: