# 聚类:DBSCAN算法实现(无需人为指定分成几类)
#1.建立工程,导入sklearn相关包
import numpy as np
import sklearn.cluster as skc
from sklearn import metrics # 用于评价指标
import matplotlib.pyplot as plt
#2.读取数据并进行处理
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)) # n行2列
'''
mat (or array).reshape(c, -1) 必须是矩阵格式或者数组格式,才能使用 .reshape(c, -1) 函数, 表示将此矩阵或者数组重组