算法实现之----聚类KMeans

样本数据为：

程序为：

'''

import numpy as np
x1=np.array([1, 2, 3, 1, 5, 6, 5, 5, 6, 7, 8, 9, 9])
x2=np.array([1, 3, 2, 2, 8, 6, 7, 6, 7, 1, 2, 1, 3])
x=np.array(list(zip(x1,x2))).reshape(len(x1), 2)
print(x)
'''

import numpy as np
import pandas as pd
data=pd.read_csv("test.csv",header=None,usecols=[1,2]).values
print(data)

from sklearn.cluster import KMeans
kmeans=KMeans(n_clusters=3)
kmeans.fit(data)
print(kmeans.labels_)

import matplotlib.pyplot as plt
plt.figure(figsize=(100,100))
colors = ['b', 'g', 'r']
markers = ['o', 's', 'D']
for i,l in enumerate(kmeans.labels_):
    plt.plot(data[i,0],data[i,1],color=colors[l],marker=markers[l],ls='None')

plt.show()

运行结果：

[[80 23]
 [79 24]
 [79 25]
 [76 23]
 [78 24]
 [81 25]
 [82 23]
 [81 80]
 [84 25]
 [85 23]
 [80 24]
 [76 25]
 [82 23]
 [80 24]
 [79 25]
 [99 23]
 [30 24]
 [25 25]]

[0 0 0 0 0 0 0 2 0 0 0 0 0 0 0 0 1 1]