無監督學習DBSCAN密度聚類

 

 

 

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__':
    data,cityName = loadData('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])

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