机器学习学习笔记--决策树检测FTP暴力破解

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

import re

import matplotlib.pyplot as plt

import os

from sklearn.feature_extraction.text import CountVectorizer

from sklearn import cross_validation

import os

from sklearn.datasets import load_iris

from sklearn import tree

import pydotplus

def load_one_flle(filename):

x=[]

with open(filename) as f:

line=f.readline()

line=line.strip('\n')

return line

def load_adfa_training_files(rootdir):

x=[]

y=[]

list = os.listdir(rootdir)

for i in range(0, len(list)):

path = os.path.join(rootdir, list[i])

if os.path.isfile(path):

x.append(load_one_flle(path))

y.append(0)

return x,y

def dirlist(path, allfile):

filelist = os.listdir(path)

for filename in filelist:

filepath = os.path.join(path, filename)

if os.path.isdir(filepath):

dirlist(filepath, allfile)

else:

allfile.append(filepath)

return allfile

def load_adfa_hydra_ftp_files(rootdir):

x=[]

y=[]

allfile=dirlist(rootdir,[])

for file in allfile:

if re.match(r"/home/qin/code/python/web-ml/1book-master/data/ADFA-LD/Attack_Data_Master/Hydra_FTP_\d+/UAD-Hydra-FTP*",file):

x.append(load_one_flle(file))

y.append(1)

return x,y

if __name__ == '__main__':

x1,y1=load_adfa_training_files("/home/qin/code/python/web-ml/1book-master/data/ADFA-LD/Training_Data_Master/")

x2,y2=load_adfa_hydra_ftp_files("/home/qin/code/python/web-ml/1book-master/data/ADFA-LD/Attack_Data_Master/")

#以上分别是提取 普通数据（y=0） 和 攻击文件数据 y=1

x=x1+x2

y=y1+y2

print x

#合并数据集

vectorizer = CountVectorizer(min_df=1)

x=vectorizer.fit_transform(x)

x=x.toarray()

print y

clf = tree.DecisionTreeClassifier()

print cross_validation.cross_val_score(clf,x,y,n_jobs=-1,cv=10)

#以上是使用决策树训练数据 并且用十折验证

clf = clf.fit(x,y)

#一下是导出数据

dot_data = tree.export_graphviz(clf,out_file=None)

graph=pydotplus.graph_from_dot_data(dot_data)

graph.write_pdf("./photo/ftp_tree.pdf")

以下是显示的效果：