• K-means聚類算法

• 測試：

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 31 10:59:20 2017

@author: Administrator
"""

‘‘‘
現有1999年全國31個省份城鎮居民家庭平均每人全年消費性支出的八個主
要變量數據，這八個變量分別是：食品、 衣著、 家庭設備用品及服務、 醫療
保健、 交通和通訊、 娛樂教育文化服務、 居住以及雜項商品和服務。 利用已
有數據，對31個省份進行聚類。
‘‘‘

import numpy as np
 
from sklearn.cluster import KMeans
 
 
def loadData(filePath):
    fr = open(filePath,‘r+‘)
    lines = fr.readlines()
    retData = []
    retCityName = []
    for line in lines:
        items = line.strip().split(",")
        retCityName.append(items[0])
        retData.append([float(items[i]) 
 
for i in range(1,len(items))])
    return retData,retCityName
 
     
if __name__ == ‘__main__‘:
    
    fpath=‘F:\RANJIEWEN\MachineLearning\Python機器學習實戰_mooc\data\聚類\\‘
    data,cityName = loadData(fpath+‘city.txt‘)
    km = KMeans(n_clusters=4)
    label = km.fit_predict(data)
    expenses 
 
= np.sum(km.cluster_centers_,axis=1)
    #print(expenses)
    CityCluster = [[],[],[],[]]
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i])
    for i in range(len(CityCluster)):
        print("Expenses:%.2f" % expenses[i])
        print(CityCluster[i])

• DBSCAN密度聚類

• 測試

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 31 11:14:37 2017

@author: Administrator
"""

‘‘‘
現有大學校園網的日誌數據，290條大學生的校園網使用情況數據，數據包
括用戶ID，設備的MAC地址，IP地址，開始上網時間，停止上網時間，上
網時長，校園網套餐等。 利用已有數據，分析學生上網的模式。
實驗目的：
通過DBSCAN聚類，分析學生上網時間和上網時長的模式。

‘‘‘

import numpy as np
import sklearn.cluster as skc
from sklearn import metrics
import matplotlib.pyplot as plt
 
 
mac2id=dict()
onlinetimes=[]

fpath=‘F:\RANJIEWEN\MachineLearning\Python機器學習實戰_mooc\data\聚類\\‘
f=open(fpath+‘TestData.txt‘,encoding=‘utf-8‘)
for line in f:
    mac=line.split(‘,‘)[2]
    onlinetime=int(line.split(‘,‘)[6])
    starttime=int(line.split(‘,‘)[4].split(‘ ‘)[1].split(‘:‘)[0])
    if mac not in mac2id:
        mac2id[mac]=len(onlinetimes)
        onlinetimes.append((starttime,onlinetime))
    else:
        onlinetimes[mac2id[mac]]=[(starttime,onlinetime)]
real_X=np.array(onlinetimes).reshape((-1,2))
 
X=real_X[:,0:1]

## 聚類數據變換技巧
# X=np.log(1+real_X[:,1:])
 
db=skc.DBSCAN(eps=0.01,min_samples=20).fit(X)
labels = db.labels_
 
print(‘Labels:‘)
print(labels)
raito=len(labels[labels[:] == -1]) / len(labels)
print(‘Noise raito:‘,format(raito, ‘.2%‘))
 
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
 
print(‘Estimated number of clusters: %d‘ % n_clusters_)
print("Silhouette Coefficient: %0.3f"% metrics.silhouette_score(X, labels))
 
for i in range(n_clusters_):
    print(‘Cluster ‘,i,‘:‘)
    print(list(X[labels == i].flatten()))
     
plt.hist(X,24)

• 基於聚類的圖像分割

• 測試

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 31 15:03:11 2017

@author: Administrator
"""

‘‘‘
目標：利用K-means聚類算法對圖像像素點顏色進行聚類實現簡單的圖像分割
輸出：同一聚類中的點使用相同顏色標記，不同聚類顏色不同
‘‘‘

import numpy as np
import PIL.Image as image
from sklearn.cluster import KMeans
 
def loadData(filePath):
    f = open(filePath,‘rb‘)
    data = []
    img = image.open(f)
    m,n = img.size
    for i in range(m):
        for j in range(n):
            x,y,z = img.getpixel((i,j))
            data.append([x/256.0,y/256.0,z/256.0])
    f.close()
    return np.mat(data),m,n
 
imPath=‘F:\RANJIEWEN\MachineLearning\Python機器學習實戰_mooc\data\基於聚類的整圖分割\\‘
imgData,row,col = loadData(imPath+‘bull.jpg‘)
label = KMeans(n_clusters=4).fit_predict(imgData)
 
label = label.reshape([row,col])
pic_new = image.new("L", (row, col))
for i in range(row):
    for j in range(col):
        pic_new.putpixel((i,j), int(256/(label[i][j]+1)))
pic_new.save("result-bull-4.jpg", "JPEG")

Python機器學習--聚類