《Web安全之机器学习入门》笔记：第六章 6.6随机森林检测FTP暴力破解

1.对比决策树与随机森林的性能，参考6.4节暴力破解源码，对其进行部分修改

（1）在6.4节基础修改，决策树复用6.4节内容

clf1 = tree.DecisionTreeClassifier()
    score = model_selection.cross_val_score(clf1, x, y, n_jobs=1, cv=10)
    print(np.mean(score))

（2）增加随机森林代码逻辑，如下所示：

clf2 = RandomForestClassifier(n_estimators=10, max_depth=None,min_samples_split=2, random_state=0)
    score = model_selection.cross_val_score(clf2, x, y, n_jobs=1, cv=10)
    print(np.mean(score))

需要注意的是，这里讲n_jobs值均改为1

2.完整源码如下所示：

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

import re
from sklearn.feature_extraction.text import CountVectorizer
from sklearn import model_selection
import os
from sklearn import tree
from sklearn.ensemble import RandomForestClassifier
import numpy as np


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

file_prefix = r"../data/ADFA-LD/Attack_Data_Master/Hydra_FTP_"
def load_adfa_hydra_ftp_files(rootdir):
    x=[]
    y=[]
    allfile=dirlist(rootdir,[])
    for file in allfile:
        if re.match(file_prefix,file):
            x.append(load_one_flle(file))
            y.append(1)
    return x,y

if __name__ == '__main__':

    x1,y1=load_adfa_training_files("../data/ADFA-LD/Training_Data_Master/")
    x2,y2=load_adfa_hydra_ftp_files("../data/ADFA-LD/Attack_Data_Master/")

    x=x1+x2
    y=y1+y2

    vectorizer = CountVectorizer(min_df=1)
    x=vectorizer.fit_transform(x)
    x=x.toarray()

    clf1 = tree.DecisionTreeClassifier()
    score = model_selection.cross_val_score(clf1, x, y, n_jobs=1, cv=10)
    print(score)
    print(np.mean(score))

    clf2 = RandomForestClassifier(n_estimators=10, max_depth=None,min_samples_split=2, random_state=0)
    score = model_selection.cross_val_score(clf2, x, y, n_jobs=1, cv=10)
    print(score)
    print(np.mean(score))

3.运行结果

[1.         0.97029703 0.95       0.96969697 0.96969697 0.90909091
 0.98989899 0.97979798 0.95959596 0.93939394]
0.9637468746874689
[1.         0.99009901 0.98       0.97979798 0.97979798 0.93939394
 0.98989899 0.98989899 1.         1.        ]
0.9848886888688868