sklearn庫kmeans實現實例

# -*- coding: utf-8 -*-
from sklearn.cluster import KMeans
from sklearn.externals import joblib
import numpy
import pandas as pd
def kmeans(inputfile,n):
    
    final = open('data/dataset.csv' , 'r')

    data = [line.strip().split(',') for line in final]
    feature = [[float(x) for x in row[1]] for row in data]
    # print feature
    #調用kmeans類
    clf = KMeans(n_clusters=n)  #給定類別個數為3
    s = clf.fit(feature)
    # print s
    #聚類中心坐標
    print '聚類中心',clf.cluster_centers_
    #每個樣本所屬的簇
    print '每個樣本所屬的簇',clf.labels_ #每個點的分類
    #用來評估簇的個數是否合適，距離越小說明簇分的越好，選取臨界點的簇個數
    print clf.inertia_ #每個點到其簇的質心的距離之和
    #進行預測
    df = pd.read_csv('data/dataset1.csv')  #未添加類標簽的數據集
    label = clf.predict(feature)
    labelpre = pd.DataFrame(label,columns=['label'])
    df['label'] = labelpre  #將聚類之后的類標簽添加到數據集中
    # print clf.predict(feature)
    print df
    #保存模型
    joblib.dump(clf , 'data/km.pkl')

    #載入保存的模型
    clf = joblib.load('data/km.pkl')
    print 'clf',clf
    '''
    #用來評估簇的個數是否合適，距離越小說明簇分的越好，選取臨界點的簇個數
    for i in range(5,30,1):
        clf = KMeans(n_clusters=i)
        s = clf.fit(feature)
        print i , clf.inertia_
    '''
kmeans('data/danger.csv',3)