1.Hello 随机森林
#-*- coding:utf-8 -*-
from sklearn.model_selection import cross_val_score
from sklearn.datasets import make_blobs
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.tree import DecisionTreeClassifier
x,y = make_blobs(n_samples=10000,n_features=10,centers=100,random_state=0)
clf = DecisionTreeClassifier(max_depth=None,min_samples_split=2,random_state=0)
scores = cross_val_score(clf,x,y)
print scores.mean()
#以上是决策树算法
#以下是随机森林算法
clf = RandomForestClassifier(n_estimators=10,max_depth=None,min_samples_split=2,random_state=0)
scores = cross_val_score(clf,x,y)
print scores.mean()
输出：
0.979408793821
0.999607843137
随机森林的判决能力优于决策树
2.对比随机森林和决策树 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
from sklearn.ensemble import RandomForestClassifier
import numpy as np
def load_one_file(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_file(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_file(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/")
x=x1+x2
y=y1+y2
vectorizer = CountVectorizer(min_df=1)
x=vectorizer.fit_transform(x)
x=x.toarray()
clf1 = tree.DecisionTreeClassifier()
score=cross_validation.cross_val_score(clf1,x,y,n_jobs=-1,cv=10)
print np.mean(score)
clf2 = RandomForestClassifier(n_estimators=10,max_depth=None,min_samples_split=2,random_state=0)
score=cross_validation.cross_val_score(clf2,x,y,n_jobs=-1,cv=10)
print np.mean(score)
输出：
0.962736573657
0.986898789879
随机森林好于决策树
