航空公司
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

data=pd.read_csv("air_data.csv",header=0)
data.head()

k=5
kmodel=KMeans(max_iter=30,n_clusters=5,random_state=
None,tol=0.0001)
kmodel.fit(data)

r1=pd.Series(kmodel.labels_).value_counts()
print('',r1)
r2=pd.DataFrame(kmodel.cluster_centers_)
print('',r2)
r=pd.concat([r2,r1],axis=1)
r.columns=list(data.columns)+[u'']
print('',r)

plt.xlabel("ZL-ZR-ZF-ZM-ZC")
plt.ylabel("Custer-center-value")
plt.rcParams['font.sans-serif']=['SimHei']
plt.title("title")
clu=kmodel.cluster_centers_
colors=['red','green','yellow','blue','black']
x=[1,2,3,4,5]
for i in range(len(clu)):
plt.plot(x,clu[i],label=
u'cluster'+str(i),color=
colors[i],marker='o')
plt.legend()
plt.show()