import numpy as np
x=np.random.randint(0,52,52)
x
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 intcent(x,k):
return x[0:k].reshape(k)
kc=intcent(x,k)
kc array([21, 8, 45])
d=abs(2-kc)
np.where(d==np.min(d))[0][0] 1
def nearest(kc,i):
d=(abs(kc-i))
w=np.where(d==np.min(d))
return w[0][0]
def xclassfy(x,y,kc):
for i in range(x.shape[0]):
y[i]=nearst(kc,x[i])
return y
from sklearn.datasets import load_iris
iris=load_iris()
iris
x=iris.data
x
Out[1]:
array([[5.1, 3.5, 1.4, 0.2],
[4.9, 3. , 1.4, 0.2],
[4.7, 3.2, 1.3, 0.2],
[4.6, 3.1, 1.5, 0.2],
[5. , 3.6, 1.4, 0.2],
[5.4, 3.9, 1.7, 0.4],
[4.6, 3.4, 1.4, 0.3],
[5. , 3.4, 1.5, 0.2],
[4.4, 2.9, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.1],
[5.4, 3.7, 1.5, 0.2],
[4.8, 3.4, 1.6, 0.2],
[4.8, 3. , 1.4, 0.1],
[4.3, 3. , 1.1, 0.1],
[5.8, 4. , 1.2, 0.2],
[5.7, 4.4, 1.5, 0.4],
[5.4, 3.9, 1.3, 0.4],
[5.1, 3.5, 1.4, 0.3],
[5.7, 3.8, 1.7, 0.3],
[5.1, 3.8, 1.5, 0.3],
[5.4, 3.4, 1.7, 0.2],
[5.1, 3.7, 1.5, 0.4],
[4.6, 3.6, 1. , 0.2],
[5.1, 3.3, 1.7, 0.5],
[4.8, 3.4, 1.9, 0.2],
[5. , 3. , 1.6, 0.2],
[5. , 3.4, 1.6, 0.4],
[5.2, 3.5, 1.5, 0.2],
[5.2, 3.4, 1.4, 0.2],
[4.7, 3.2, 1.6, 0.2],
[4.8, 3.1, 1.6, 0.2],
[5.4, 3.4, 1.5, 0.4],
[5.2, 4.1, 1.5, 0.1],
[5.5, 4.2, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.1],
[5. , 3.2, 1.2, 0.2],
[5.5, 3.5, 1.3, 0.2],
[4.9, 3.1, 1.5, 0.1],
[4.4, 3. , 1.3, 0.2],
[5.1, 3.4, 1.5, 0.2],
[5. , 3.5, 1.3, 0.3],
[4.5, 2.3, 1.3, 0.3],
[4.4, 3.2, 1.3, 0.2],
[5. , 3.5, 1.6, 0.6],
[5.1, 3.8, 1.9, 0.4],
[4.8, 3. , 1.4, 0.3],
[5.1, 3.8, 1.6, 0.2],
[4.6, 3.2, 1.4, 0.2],
[5.3, 3.7, 1.5, 0.2],
[5. , 3.3, 1.4, 0.2],
[7. , 3.2, 4.7, 1.4],
[6.4, 3.2, 4.5, 1.5],
[6.9, 3.1, 4.9, 1.5],
[5.5, 2.3, 4. , 1.3],
[6.5, 2.8, 4.6, 1.5],
[5.7, 2.8, 4.5, 1.3],
[6.3, 3.3, 4.7, 1.6],
[4.9, 2.4, 3.3, 1. ],
[6.6, 2.9, 4.6, 1.3],
[5.2, 2.7, 3.9, 1.4],
[5. , 2. , 3.5, 1. ],
[5.9, 3. , 4.2, 1.5],
[6. , 2.2, 4. , 1. ],
[6.1, 2.9, 4.7, 1.4],
[5.6, 2.9, 3.6, 1.3],
[6.7, 3.1, 4.4, 1.4],
[5.6, 3. , 4.5, 1.5],
[5.8, 2.7, 4.1, 1. ],
[6.2, 2.2, 4.5, 1.5],
[5.6, 2.5, 3.9, 1.1],
[5.9, 3.2, 4.8, 1.8],
[6.1, 2.8, 4. , 1.3],
[6.3, 2.5, 4.9, 1.5],
[6.1, 2.8, 4.7, 1.2],
[6.4, 2.9, 4.3, 1.3],
[6.6, 3. , 4.4, 1.4],
[6.8, 2.8, 4.8, 1.4],
[6.7, 3. , 5. , 1.7],
[6. , 2.9, 4.5, 1.5],
[5.7, 2.6, 3.5, 1. ],
[5.5, 2.4, 3.8, 1.1],
[5.5, 2.4, 3.7, 1. ],
[5.8, 2.7, 3.9, 1.2],
[6. , 2.7, 5.1, 1.6],
[5.4, 3. , 4.5, 1.5],
[6. , 3.4, 4.5, 1.6],
[6.7, 3.1, 4.7, 1.5],
[6.3, 2.3, 4.4, 1.3],
[5.6, 3. , 4.1, 1.3],
[5.5, 2.5, 4. , 1.3],
[5.5, 2.6, 4.4, 1.2],
[6.1, 3. , 4.6, 1.4],
[5.8, 2.6, 4. , 1.2],
[5. , 2.3, 3.3, 1. ],
[5.6, 2.7, 4.2, 1.3],
[5.7, 3. , 4.2, 1.2],
[5.7, 2.9, 4.2, 1.3],
[6.2, 2.9, 4.3, 1.3],
[5.1, 2.5, 3. , 1.1],
[5.7, 2.8, 4.1, 1.3],
[6.3, 3.3, 6. , 2.5],
[5.8, 2.7, 5.1, 1.9],
[7.1, 3. , 5.9, 2.1],
[6.3, 2.9, 5.6, 1.8],
[6.5, 3. , 5.8, 2.2],
[7.6, 3. , 6.6, 2.1],
[4.9, 2.5, 4.5, 1.7],
[7.3, 2.9, 6.3, 1.8],
[6.7, 2.5, 5.8, 1.8],
[7.2, 3.6, 6.1, 2.5],
[6.5, 3.2, 5.1, 2. ],
[6.4, 2.7, 5.3, 1.9],
[6.8, 3. , 5.5, 2.1],
[5.7, 2.5, 5. , 2. ],
[5.8, 2.8, 5.1, 2.4],
[6.4, 3.2, 5.3, 2.3],
[6.5, 3. , 5.5, 1.8],
[7.7, 3.8, 6.7, 2.2],
[7.7, 2.6, 6.9, 2.3],
[6. , 2.2, 5. , 1.5],
[6.9, 3.2, 5.7, 2.3],
[5.6, 2.8, 4.9, 2. ],
[7.7, 2.8, 6.7, 2. ],
[6.3, 2.7, 4.9, 1.8],
[6.7, 3.3, 5.7, 2.1],
[7.2, 3.2, 6. , 1.8],
[6.2, 2.8, 4.8, 1.8],
[6.1, 3. , 4.9, 1.8],
[6.4, 2.8, 5.6, 2.1],
[7.2, 3. , 5.8, 1.6],
[7.4, 2.8, 6.1, 1.9],
[7.9, 3.8, 6.4, 2. ],
[6.4, 2.8, 5.6, 2.2],
[6.3, 2.8, 5.1, 1.5],
[6.1, 2.6, 5.6, 1.4],
[7.7, 3. , 6.1, 2.3],
[6.3, 3.4, 5.6, 2.4],
[6.4, 3.1, 5.5, 1.8],
[6. , 3. , 4.8, 1.8],
[6.9, 3.1, 5.4, 2.1],
[6.7, 3.1, 5.6, 2.4],
[6.9, 3.1, 5.1, 2.3],
[5.8, 2.7, 5.1, 1.9],
[6.8, 3.2, 5.9, 2.3],
[6.7, 3.3, 5.7, 2.5],
[6.7, 3. , 5.2, 2.3],
[6.3, 2.5, 5. , 1.9],
[6.5, 3. , 5.2, 2. ],
[6.2, 3.4, 5.4, 2.3],
[5.9, 3. , 5.1, 1.8]])
x1=x[:,0]
x1 array([5.1, 4.9, 4.7, 4.6, 5. , 5.4, 4.6, 5. , 4.4, 4.9, 5.4, 4.8, 4.8,
4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5. ,
5. , 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5. , 5.5, 4.9, 4.4,
5.1, 5. , 4.5, 4.4, 5. , 5.1, 4.8, 5.1, 4.6, 5.3, 5. , 7. , 6.4,
6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5. , 5.9, 6. , 6.1, 5.6,
6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7,
6. , 5.7, 5.5, 5.5, 5.8, 6. , 5.4, 6. , 6.7, 6.3, 5.6, 5.5, 5.5,
6.1, 5.8, 5. , 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3,
6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5,
7.7, 7.7, 6. , 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2,
7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6. , 6.9, 6.7, 6.9, 5.8,
6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9])
from sklearn.cluster import KMeans
est=KMeans(n_clusters=3)
est.fit(x)
est.cluster_centers_
y=est.predict(x)
y array([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, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 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, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 2, 2, 2, 2, 1, 2, 2, 2,
2, 2, 2, 1, 1, 2, 2, 2, 2, 1, 2, 1, 2, 1, 2, 2, 1, 1, 2, 2, 2, 2,
2, 1, 2, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 1])
import matplotlib.pyplot as plt
plt.scatter(x[:,0],x[:,1],c=y,cmap='rainbow')
plt.show()
est1=KMeans(n_clusters=4)
x1=x[:,0].reshape(-1,1)
est1.fit(x1)
y=est1.labels_
plt.scatter(x1,x1)
plt.show()
est1=KMeans(n_clusters=4)
x1=x[:,0]
est=KMeans(n_clusters=4)
est.fit(x) KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,
n_clusters=4, n_init=10, n_jobs=1, precompute_distances='auto',
random_state=None, tol=0.0001, verbose=0)
est1=KMeans(n_clusters=4)
x1=x[:,0].reshape(-1,1)
x1 array([[5.1],
[4.9],
[4.7],
[4.6],
[5. ],
[5.4],
[4.6],
[5. ],
[4.4],
[4.9],
[5.4],
[4.8],
[4.8],
[4.3],
[5.8],
[5.7],
[5.4],
[5.1],
[5.7],
[5.1],
[5.4],
[5.1],
[4.6],
[5.1],
[4.8],
[5. ],
[5. ],
[5.2],
[5.2],
[4.7],
[4.8],
[5.4],
[5.2],
[5.5],
[4.9],
[5. ],
[5.5],
[4.9],
[4.4],
[5.1],
[5. ],
[4.5],
[4.4],
[5. ],
[5.1],
[4.8],
[5.1],
[4.6],
[5.3],
[5. ],
[7. ],
[6.4],
[6.9],
[5.5],
[6.5],
[5.7],
[6.3],
[4.9],
[6.6],
[5.2],
[5. ],
[5.9],
[6. ],
[6.1],
[5.6],
[6.7],
[5.6],
[5.8],
[6.2],
[5.6],
[5.9],
[6.1],
[6.3],
[6.1],
[6.4],
[6.6],
[6.8],
[6.7],
[6. ],
[5.7],
[5.5],
[5.5],
[5.8],
[6. ],
[5.4],
[6. ],
[6.7],
[6.3],
[5.6],
[5.5],
[5.5],
[6.1],
[5.8],
[5. ],
[5.6],
[5.7],
[5.7],
[6.2],
[5.1],
[5.7],
[6.3],
[5.8],
[7.1],
[6.3],
[6.5],
[7.6],
[4.9],
[7.3],
[6.7],
[7.2],
[6.5],
[6.4],
[6.8],
[5.7],
[5.8],
[6.4],
[6.5],
[7.7],
[7.7],
[6. ],
[6.9],
[5.6],
[7.7],
[6.3],
[6.7],
[7.2],
[6.2],
[6.1],
[6.4],
[7.2],
[7.4],
[7.9],
[6.4],
[6.3],
[6.1],
[7.7],
[6.3],
[6.4],
[6. ],
[6.9],
[6.7],
[6.9],
[5.8],
[6.8],
[6.7],
[6.7],
[6.3],
[6.5],
[6.2],
[5.9]])
est1=KMeans(n_clusters=4)
x1=x[:,0].reshape(-1,1)
est1=KMeans(n_clusters=4)
est1.fit(x1)
est1.labels_ array([1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 2, 3, 3, 0, 3, 0, 3, 1, 3, 1, 1, 0, 0, 0, 0, 3,
0, 0, 3, 0, 0, 0, 3, 0, 3, 3, 3, 3, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3,
0, 0, 0, 0, 0, 1, 0, 0, 0, 3, 1, 0, 3, 0, 2, 3, 3, 2, 1, 2, 3, 2,
3, 3, 3, 0, 0, 3, 3, 2, 2, 0, 3, 0, 2, 3, 3, 2, 3, 0, 3, 2, 2, 2,
3, 3, 0, 2, 3, 3, 0, 3, 3, 3, 0, 3, 3, 3, 3, 3, 3, 0])
1)设定好K的大小，随机选取K个点作为初始中心点；
(2)计算每个点到这K个中心点的距离大小，选取最近的中心点，划分到以该中心点为中心的集群中去；
(3)重新计算K个新集群的中心点；
(4)如果中心点保持不变，则结束K-Means过程。否则，重复进行(2)、(3)步；
复制代码
import numpy as np
x = np.random.randint(1,50,[20,1])
y = np.zeros(20)
k = 3
#1） 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；
def initcen(x,k):
return x[:k]
#2） 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；
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 #3） 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； def kcmean(x,y,kc,k):
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)
#4） 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）
kc = initcen(x,k) flag = True
print(x,y,kc,flag)
while flag:
y = xclassify(x,y,kc)
kc,flag = kcmean(x,y,kc,k)
print(y,kc)
复制代码