# -*- coding: utf-8 -*-
from sklearn.cluster import KMeans
from sklearn.externals import joblib
import numpy
final = open('c:/test/final.dat' , 'r')
data = [line.strip().split('\t') for line in final]
feature = [[float(x) for x in row[3:]] for row in data]
#è°ç¨kmeansç±»
clf = KMeans(n_clusters=9)
s = clf.fit(feature)
print s
#9个ä¸å¿
print clf.cluster_centers_
#æ¯ä¸ªæ ·æ¬æå±çç°
print clf.labels_
#ç¨æ¥è¯ä¼°ç°ç个æ°æ¯å¦åéï¼è·ç¦»è¶å°è¯´æç°åçè¶å¥½ï¼éå临çç¹çç°ä¸ªæ°
print clf.inertia_
#è¿è¡é¢æµ
print clf.predict(feature)
#ä¿å模å
joblib.dump(clf , 'c:/km.pkl')
#è½½å
¥ä¿åç模å
clf = joblib.load('c:/km.pkl')
'''
#ç¨æ¥è¯ä¼°ç°ç个æ°æ¯å¦åéï¼è·ç¦»è¶å°è¯´æç°åçè¶å¥½ï¼éå临çç¹çç°ä¸ªæ°
for i in range(5,30,1):
clf = KMeans(n_clusters=i)
s = clf.fit(feature)
print i , clf.inertia_
'''
温馨提示:内容为网友见解,仅供参考