第七次作业
import numpy as np x=np.random.randint(0,12,20) x
array([ 5, 1, 7, 2, 3, 10, 9, 9, 5, 8, 9, 0, 8, 9, 2, 6, 6, 5, 8, 9])
k=3 y=np.zeros(20) y
array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
def initcent(x,k):#初始聚类中心数组 return x[0:k].reshape(k) kc=initcent(x,k) kc
array([5, 1, 7])
def nearset(kc,i):#距离绝对值 d=(abs(kc-i)) w=np.where(d==np.min(d)) return w[0][0] def xclassify(x,y,kc): for i in range(x.shape[0]):#对数组的每个值进行分类 y[i]=nearset(kc,x[i]) return y kc=initcent(x,k) y=xclassify(x,y,kc) print(kc,y)
[5 1 7] [0. 1. 2. 1. 0. 2. 2. 2. 0. 2. 2. 1. 2. 2. 1. 0. 0. 0. 2. 2.]
import numpy as np from sklearn.datasets import load_iris iris=load_iris() x=iris.data[:,1] y=np.zeros(150) def initcenter(x,k): return x[0:k].reshape(k) def nearest(kc,i): d=(abs(kc-i)) w=np.where(d == np.min(d)) return w[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): l=list(kc) flag=False for c in range(k): print(c) m=np.where(y == c) n=np.mean(x[m]) if l[c] !=n: l[c]=n flag=True print(l,flag) return (np.array(l),flag) k=3 kc=initcenter(x,k) flag=True print(x,y,kc,flag) #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 while flag: y=xclassify(x,y,kc) kc,flag = kcmean(x,y,kc,k) print(y,kc,type(kc)) print(x,y) import matplotlib.pyplot as plt plt.scatter(x,x,c=y,s=50,cmap="rainbow"); plt.show()
[3.5 3. 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 3.7 3.4 3. 3. 4. 4.4 3.9 3.5 3.8 3.8 3.4 3.7 3.6 3.3 3.4 3. 3.4 3.5 3.4 3.2 3.1 3.4 4.1 4.2 3.1 3.2 3.5 3.1 3. 3.4 3.5 2.3 3.2 3.5 3.8 3. 3.8 3.2 3.7 3.3 3.2 3.2 3.1 2.3 2.8 2.8 3.3 2.4 2.9 2.7 2. 3. 2.2 2.9 2.9 3.1 3. 2.7 2.2 2.5 3.2 2.8 2.5 2.8 2.9 3. 2.8 3. 2.9 2.6 2.4 2.4 2.7 2.7 3. 3.4 3.1 2.3 3. 2.5 2.6 3. 2.6 2.3 2.7 3. 2.9 2.9 2.5 2.8 3.3 2.7 3. 2.9 3. 3. 2.5 2.9 2.5 3.6 3.2 2.7 3. 2.5 2.8 3.2 3. 3.8 2.6 2.2 3.2 2.8 2.8 2.7 3.3 3.2 2.8 3. 2.8 3. 2.8 3.8 2.8 2.8 2.6 3. 3.4 3.1 3. 3.1 3.1 3.1 2.7 3.2 3.3 3. 2.5 3. 3.4 3. ] [0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.] [3.5 3. 3.2] True 0 [3.638888888888889, 3.0, 3.2] True 1 [3.638888888888889, 2.7968421052631576, 3.2] True 2 [3.638888888888889, 2.7968421052631576, 3.2315789473684213] True [0. 1. 2. 1. 0. 0. 0. 0. 1. 1. 0. 0. 1. 1. 0. 0. 0. 0. 0. 0. 0. 0. 0. 2. 0. 1. 0. 0. 0. 2. 1. 0. 0. 0. 1. 2. 0. 1. 1. 0. 0. 1. 2. 0. 0. 1. 0. 2. 0. 2. 2. 2. 1. 1. 1. 1. 2. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 2. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 2. 1. 1. 1. 1. 1. 1. 1. 1. 0. 2. 1. 1. 1. 1. 2. 1. 0. 1. 1. 2. 1. 1. 1. 2. 2. 1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 0. 1. 1. 1. 1. 1. 1. 2. 2. 1. 1. 1. 0. 1.] [3.63888889 2.79684211 3.23157895] <class 'numpy.ndarray'> 0 [3.7583333333333333, 2.7968421052631576, 3.2315789473684213] True 1 [3.7583333333333333, 2.753012048192771, 3.2315789473684213] True 2 [3.7583333333333333, 2.753012048192771, 3.2418604651162792] True [0. 1. 2. 2. 0. 0. 2. 2. 1. 2. 0. 2. 1. 1. 0. 0. 0. 0. 0. 0. 2. 0. 0. 2. 2. 1. 2. 0. 2. 2. 2. 2. 0. 0. 2. 2. 0. 2. 1. 2. 0. 1. 2. 0. 0. 1. 0. 2. 0. 2. 2. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 1. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 2. 2. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 2. 1. 1. 1. 1. 1. 1. 1. 1. 0. 2. 1. 1. 1. 1. 2. 1. 0. 1. 1. 2. 1. 1. 1. 2. 2. 1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 2. 2. 1. 2. 2. 2. 1. 2. 2. 1. 1. 1. 2. 1.] [3.75833333 2.75301205 3.24186047] <class 'numpy.ndarray'> 0 [3.8444444444444437, 2.753012048192771, 3.2418604651162792] True 1 [3.8444444444444437, 2.6403508771929824, 3.2418604651162792] True 2 [3.8444444444444437, 2.6403508771929824, 3.1786666666666665] True [2. 2. 2. 2. 0. 0. 2. 2. 1. 2. 0. 2. 2. 2. 0. 0. 0. 2. 0. 0. 2. 0. 0. 2. 2. 2. 2. 2. 2. 2. 2. 2. 0. 0. 2. 2. 2. 2. 2. 2. 2. 1. 2. 2. 0. 2. 0. 2. 0. 2. 2. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 1. 1. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 2. 1. 1. 1. 1. 1. 1. 2. 2. 2. 1. 2. 1. 1. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 2. 1. 2. 2. 1. 1. 1. 0. 2. 1. 2. 1. 1. 2. 2. 0. 1. 1. 2. 1. 1. 1. 2. 2. 1. 2. 1. 2. 1. 0. 1. 1. 1. 2. 2. 2. 2. 2. 2. 2. 1. 2. 2. 2. 1. 2. 2. 2.] [3.84444444 2.64035088 3.17866667] <class 'numpy.ndarray'> 0 1 2 [2. 2. 2. 2. 0. 0. 2. 2. 1. 2. 0. 2. 2. 2. 0. 0. 0. 2. 0. 0. 2. 0. 0. 2. 2. 2. 2. 2. 2. 2. 2. 2. 0. 0. 2. 2. 2. 2. 2. 2. 2. 1. 2. 2. 0. 2. 0. 2. 0. 2. 2. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 1. 1. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 2. 1. 1. 1. 1. 1. 1. 2. 2. 2. 1. 2. 1. 1. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 2. 1. 2. 2. 1. 1. 1. 0. 2. 1. 2. 1. 1. 2. 2. 0. 1. 1. 2. 1. 1. 1. 2. 2. 1. 2. 1. 2. 1. 0. 1. 1. 1. 2. 2. 2. 2. 2. 2. 2. 1. 2. 2. 2. 1. 2. 2. 2.] [3.84444444 2.64035088 3.17866667] <class 'numpy.ndarray'> [3.5 3. 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 3.7 3.4 3. 3. 4. 4.4 3.9 3.5 3.8 3.8 3.4 3.7 3.6 3.3 3.4 3. 3.4 3.5 3.4 3.2 3.1 3.4 4.1 4.2 3.1 3.2 3.5 3.1 3. 3.4 3.5 2.3 3.2 3.5 3.8 3. 3.8 3.2 3.7 3.3 3.2 3.2 3.1 2.3 2.8 2.8 3.3 2.4 2.9 2.7 2. 3. 2.2 2.9 2.9 3.1 3. 2.7 2.2 2.5 3.2 2.8 2.5 2.8 2.9 3. 2.8 3. 2.9 2.6 2.4 2.4 2.7 2.7 3. 3.4 3.1 2.3 3. 2.5 2.6 3. 2.6 2.3 2.7 3. 2.9 2.9 2.5 2.8 3.3 2.7 3. 2.9 3. 3. 2.5 2.9 2.5 3.6 3.2 2.7 3. 2.5 2.8 3.2 3. 3.8 2.6 2.2 3.2 2.8 2.8 2.7 3.3 3.2 2.8 3. 2.8 3. 2.8 3.8 2.8 2.8 2.6 3. 3.4 3.1 3. 3.1 3.1 3.1 2.7 3.2 3.3 3. 2.5 3. 3.4 3. ] [2. 2. 2. 2. 0. 0. 2. 2. 1. 2. 0. 2. 2. 2. 0. 0. 0. 2. 0. 0. 2. 0. 0. 2. 2. 2. 2. 2. 2. 2. 2. 2. 0. 0. 2. 2. 2. 2. 2. 2. 2. 1. 2. 2. 0. 2. 0. 2. 0. 2. 2. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 1. 1. 2. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 2. 1. 1. 1. 1. 1. 1. 2. 2. 2. 1. 2. 1. 1. 2. 1. 1. 1. 2. 1. 1. 1. 1. 2. 1. 2. 1. 2. 2. 1. 1. 1. 0. 2. 1. 2. 1. 1. 2. 2. 0. 1. 1. 2. 1. 1. 1. 2. 2. 1. 2. 1. 2. 1. 0. 1. 1. 1. 2. 2. 2. 2. 2. 2. 2. 1. 2. 2. 2. 1. 2. 2. 2.]
import matplotlib.pyplot as plt import numpy as np from sklearn.datasets import load_iris iris=load_iris() X=iris.data X from sklearn.cluster import KMeans est = KMeans(n_clusters = 3) est.fit(X) kc = est.cluster_centers_ y_kmeans = est.predict(X) print(y_kmeans,kc) print(kc.shape,y_kmeans.shape,np.shape) plt.scatter(X[:,0],X[:,1],c=y_kmeans,s=50,cmap='rainbow'); plt.show()
