机器学习学习笔记--随机森林算法

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