code/5-3.py · UsingStuding/NBbook

代码拉取完成,页面将自动刷新

扫描微信二维码支付

取消

支付完成

richgiteeai

Watch

不关注关注所有动态仅关注版本发行动态关注但不提醒动态

1 Star 0 Fork 1

UsingStuding/NBbook

forked from zhang_star/NBbook

代码 Issues 0 Pull Requests 0 Wiki 统计流水线

服务

加入 Gitee

与超过 1400万开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)

免费加入

已有帐号? 立即登录

文件

master

分支 (1)

管理

master

该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。

项目仓库所选许可证以仓库主分支所使用许可证为准

克隆/下载

HTTPS SSH SVN SVN+SSH 下载ZIP

提示

下载代码请复制以下命令到终端执行

为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName 
git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥中

在 Gitee 上使用 SVN,请访问使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议配置并使用私人令牌替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

分支 1

标签 0

NBbook

code

5-3.py

5-3.py 2.92 KB

# -*- coding:utf-8 -*-

import sys
import urllib
import urlparse
import re
from hmmlearn import hmm
import numpy as np
from sklearn.externals import joblib
import HTMLParser
import nltk
import csv
import matplotlib.pyplot as plt
from nltk.probability import FreqDist
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report
from sklearn import metrics

#测试样本数
N=100

def load_user_cmd_new(filename):
 cmd_list=[]
 dist=[]
 with open(filename) as f:
 i=0
 x=[]
 for line in f:
 line=line.strip('\n')
 x.append(line)
 dist.append(line)
 i+=1
 if i == 100:
 cmd_list.append(x)
 x=[]
 i=0

fdist = FreqDist(dist).keys()
 return cmd_list,fdist

def load_user_cmd(filename):
 cmd_list=[]
 dist_max=[]
 dist_min=[]
 dist=[]
 with open(filename) as f:
 i=0
 x=[]
 for line in f:
 line=line.strip('\n')
 x.append(line)
 dist.append(line)
 i+=1
 if i == 100:
 cmd_list.append(x)
 x=[]
 i=0

fdist = FreqDist(dist).keys()
 dist_max=set(fdist[0:50])
 dist_min = set(fdist[-50:])
 return cmd_list,dist_max,dist_min

def get_user_cmd_feature(user_cmd_list,dist_max,dist_min):
 user_cmd_feature=[]
 for cmd_block in user_cmd_list:
 f1=len(set(cmd_block))
 fdist = FreqDist(cmd_block).keys()
 f2=fdist[0:10]
 f3=fdist[-10:]
 f2 = len(set(f2) & set(dist_max))
 f3=len(set(f3)&set(dist_min))
 x=[f1,f2,f3]
 user_cmd_feature.append(x)
 return user_cmd_feature

def get_user_cmd_feature_new(user_cmd_list,dist):
 user_cmd_feature=[]

for cmd_list in user_cmd_list:
 v=[0]*len(dist)
 for i in range(0,len(dist)):
 if dist[i] in cmd_list:
 v[i]+=1
 user_cmd_feature.append(v)

return user_cmd_feature

def get_label(filename,index=0):
 x=[]
 with open(filename) as f:
 for line in f:
 line=line.strip('\n')
 x.append( int(line.split()[index]))
 return x

if __name__ == '__main__':
 user_cmd_list,dist=load_user_cmd_new("../data/MasqueradeDat/User3")
 print "Dist:(%s)" % dist
 user_cmd_feature=get_user_cmd_feature_new(user_cmd_list,dist)
 #print user_cmd_feature
 labels=get_label("../data/MasqueradeDat/label.txt",2)
 y=[0]*50+labels

x_train=user_cmd_feature[0:N]
 y_train=y[0:N]

x_test=user_cmd_feature[N:150]
 y_test=y[N:150]

neigh = KNeighborsClassifier(n_neighbors=3)
 neigh.fit(x_train, y_train)
 y_predict=neigh.predict(x_test)

score=np.mean(y_test==y_predict)*100

print score

#print classification_report(y_test, y_predict)

#print metrics.confusion_matrix(y_test, y_predict)

一键复制编辑原始数据按行查看历史

duoergun0729 提交于 2017年11月08日 16:15 +08:00 . update N=100

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123

# -*- coding:utf-8 -*-

import sys
import urllib
import urlparse
import re
from hmmlearn import hmm
import numpy as np
from sklearn.externals import joblib
import HTMLParser
import nltk
import csv
import matplotlib.pyplot as plt
from nltk.probability import FreqDist
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report
from sklearn import metrics

#测试样本数
N=100

def load_user_cmd_new(filename):
 cmd_list=[]
 dist=[]
 with open(filename) as f:
 i=0
 x=[]
 for line in f:
 line=line.strip('\n')
 x.append(line)
 dist.append(line)
 i+=1
 if i == 100:
 cmd_list.append(x)
 x=[]
 i=0

 fdist = FreqDist(dist).keys()
 return cmd_list,fdist

def load_user_cmd(filename):
 cmd_list=[]
 dist_max=[]
 dist_min=[]
 dist=[]
 with open(filename) as f:
 i=0
 x=[]
 for line in f:
 line=line.strip('\n')
 x.append(line)
 dist.append(line)
 i+=1
 if i == 100:
 cmd_list.append(x)
 x=[]
 i=0

 fdist = FreqDist(dist).keys()
 dist_max=set(fdist[0:50])
 dist_min = set(fdist[-50:])
 return cmd_list,dist_max,dist_min

def get_user_cmd_feature(user_cmd_list,dist_max,dist_min):
 user_cmd_feature=[]
 for cmd_block in user_cmd_list:
 f1=len(set(cmd_block))
 fdist = FreqDist(cmd_block).keys()
 f2=fdist[0:10]
 f3=fdist[-10:]
 f2 = len(set(f2) & set(dist_max))
 f3=len(set(f3)&set(dist_min))
 x=[f1,f2,f3]
 user_cmd_feature.append(x)
 return user_cmd_feature

def get_user_cmd_feature_new(user_cmd_list,dist):
 user_cmd_feature=[]

 for cmd_list in user_cmd_list:
 v=[0]*len(dist)
 for i in range(0,len(dist)):
 if dist[i] in cmd_list:
 v[i]+=1
 user_cmd_feature.append(v)

 return user_cmd_feature

def get_label(filename,index=0):
 x=[]
 with open(filename) as f:
 for line in f:
 line=line.strip('\n')
 x.append( int(line.split()[index]))
 return x

if __name__ == '__main__':
 user_cmd_list,dist=load_user_cmd_new("../data/MasqueradeDat/User3")
 print "Dist:(%s)" % dist
 user_cmd_feature=get_user_cmd_feature_new(user_cmd_list,dist)
 #print user_cmd_feature
 labels=get_label("../data/MasqueradeDat/label.txt",2)
 y=[0]*50+labels

 x_train=user_cmd_feature[0:N]
 y_train=y[0:N]

 x_test=user_cmd_feature[N:150]
 y_test=y[N:150]

 neigh = KNeighborsClassifier(n_neighbors=3)
 neigh.fit(x_train, y_train)
 y_predict=neigh.predict(x_test)

 score=np.mean(y_test==y_predict)*100


 print score

 #print classification_report(y_test, y_predict)

 #print metrics.confusion_matrix(y_test, y_predict)