python与机器学习聚类：31省市居民家庭消费水平和学生月上网

31省市居民家庭消费水平

#建立工程，导入sklearn相关包
import numpy as np
from sklearn.cluster import KMeans
#加载数据，创建k-means算法实例，并进行训练，获得标签
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__':
    data,cityName = loadData('E:\coding\sklearn\city.txt')
    km = KMeans(n_clusters=4)
    label = km.fit_predict(data)
    expenses = np.sum(km.cluster_centers_,axis=1)
    #print(expense)
#将城市按label分成设定的簇，将每个簇的城市和平均花费输出
    CityCluster = [[],[],[],[]]
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i])
#输出标签，查看结果
    for i in range(len(CityCluster)):
        print("Expenses:%.2f" % expenses[i])
        print(CityCluster[i])

• 聚成四类

Expenses:5678.62
['天津', '浙江', '福建', '重庆', '西藏']
Expenses:4512.27
['江苏', '安徽', '湖南', '湖北', '广西', '海南', '四川', '云南']
Expenses:7754.66
['北京', '上海', '广东']
Expenses:3788.76
['河北', '山西', '内蒙古', '辽宁', '吉林', '黑龙江', '江西', '山东', '河南', '贵州', '陕西', '甘肃', '青海', '宁夏', '新疆']

• 聚成三类

Expenses:5113.54
['天津', '江苏', '浙江', '福建', '湖南', '广西', '海南', '重庆', '四川', '云南', '西藏']
Expenses:3827.87
['河北', '山西', '内蒙古', '辽宁', '吉林', '黑龙江', '安徽', '江西', '山东', '河南', '湖北', '贵州', '陕西', '甘肃', '青海', '宁夏', '新疆']
Expenses:7754.66
['北京', '上海', '广东']

学生月上网时间分布

#建立工程，导入sklearn相关包
import numpy as np
import sklearn.cluster as skc
from sklearn import metrics
import matplotlib.pyplot as plt

#读入数据并进行处理
mac2id = dict()
onlinetimes = []
f = open('E:\coding\sklearn\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))
#上网时间聚类，创建DBSCAN算法实例，并进行训练，获得标签
X = real_X[:,0:1]

db = skc.DBSCAN(eps=0.01,min_samples=20).fit(X)
labels = db.labels_
#打印数据被记上的标签，计算标签为-1，即噪声数据的比例
print('Labels:')
print(labels)

ratio = len(labels[labels[:]==-1])/len(labels)
print('Noise ratio:',format(ratio,'.2%'))
#计算簇的个数并打印，评价聚类效果
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
print('Estamated 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()))
#画直方图，分析实验结果
plt.hist(X,24)
plt.show()

#每个数据被划分的簇的分类
Labels:
[ 0 -1  0  1 -1  1  0  1  2 -1  1  0  1  1  3 -1 -1  3 -1  1  1 -1  1  3
  4 -1  1  1  2  0  2  2 -1  0  1  0  0  0  1  3 -1  0  1  1  0  0  2 -1
  1  3  1 -1  3 -1  3  0  1  1  2  3  3 -1 -1 -1  0  1  2  1 -1  3  1  1
  2  3  0  1 -1  2  0  0  3  2  0  1 -1  1  3 -1  4  2 -1 -1  0 -1  3 -1
  0  2  1 -1 -1  2  1  1  2  0  2  1  1  3  3  0  1  2  0  1  0 -1  1  1
  3 -1  2  1  3  1  1  1  2 -1  5 -1  1  3 -1  0  1  0  0  1 -1 -1 -1  2
  2  0  1  1  3  0  0  0  1  4  4 -1 -1 -1 -1  4 -1  4  4 -1  4 -1  1  2
  2  3  0  1  0 -1  1  0  0  1 -1 -1  0  2  1  0  2 -1  1  1 -1 -1  0  1
  1 -1  3  1  1 -1  1  1  0  0 -1  0 -1  0  0  2 -1  1 -1  1  0 -1  2  1
  3  1  1 -1  1  0  0 -1  0  0  3  2  0  0  5 -1  3  2 -1  5  4  4  4 -1
  5  5 -1  4  0  4  4  4  5  4  4  5  5  0  5  4 -1  4  5  5  5  1  5  5
  0  5  4  4 -1  4  4  5  4  0  5  4 -1  0  5  5  5 -1  4  5  5  5  5  4
  4]
#噪声数据的比例
Noise ratio: 22.15%
#簇的个数
Estamated number of clusters: 6
#聚类效果评价指标
Silhouette Coefficient: 0.710
Cluster  0 :
[22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22]
[23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23]
Cluster  2 :
[20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20]      
Cluster  3 :
[21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21]
Cluster  4 :
[8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8]
Cluster  5 :
[7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7]

kmeans实现图像分割

#建立工程并导入sklearn包
import numpy as np
import PIL.Image as image
from sklearn.cluster import KMeans
#加载图片并进行预处理
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
#加载kmeans聚类算法
km = KMeans(n_clusters=3)
imgData,row,col = loadData('sklearn/bull.jpg')
#对像素点进行聚类并输出
label = km.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("sklearn/result-bull.jpg","JPEG")