import numpy as np

x = np.random.randint(1,100,20)#产生的20个一到一百的随机整数

y = np.zeros(20)

k = 3

print(x)

print(y)

def initcenter(x,k):#初始化聚类中心数组

    return x[0:k].reshape(k)

kc = initcenter(x,k)

print(kc)

def nearest(kc, i):#定义函数求出kc与i之差最小的数的坐标

    d = (abs(kc - i))

    w = np.where(d == np.min(d))

    return w[0][0]

# print(nearest(kc,66))

# for i in range(x.shape[0]):

#     y[i] = nearest(kc,x[i])

# print(y)

def xclassify(x, y, kc):#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

    for i in range(x.shape[0]):

        y[i] = nearest(kc,x[i])

    return y

y = xclassify(x,y,kc)

print(x)

print(y)

#.用sklearn.cluster.KMeans，鸢尾花完整数据做聚类并用散点图显示.

import matplotlib.pyplot as plt

import numpy as np

from sklearn.datasets import load_iris

iris=load_iris()

print(iris)

X=iris.data

print(X)

from sklearn.cluster import KMeans

est = KMeans(n_clusters=3)

est.fit(X)

kc = est.cluster_centers_

y_kmeans = est.predict(X) #预测每个样本的聚类索引

print(y_kmeans,kc)

print(kc.shape,y_kmeans.shape)

plt.scatter(X[:,0],X[:,1],c=y_kmeans,s=50,cmap='rainbow')

plt.show()

# 鸢尾花完整数据做聚类并用散点图显示.

from sklearn.cluster import KMeans

import numpy as np

from sklearn.datasets import load_iris

import matplotlib.pyplot as plt

data = load_iris()

iris = data.data

petal_len = iris

print(petal_len)

k_means = KMeans(n_clusters=3) #三个聚类中心

result = k_means.fit(petal_len) #Kmeans自动分类

kc = result.cluster_centers_ #自动分类后的聚类中心

y_means = k_means.predict(petal_len) #预测Y值

plt.scatter(petal_len[:,0],petal_len[:,2],c=y_means, marker='p',cmap='rainbow')

plt.show()