Python决策树和随机森林算法实例详解

#决策树的helloworld 使用决策树对iris数据集进行分类
from sklearn.datasets import load_iris
from sklearn import tree
import pydotplus
#导入iris数据集
iris = load_iris()
#初始化DecisionTreeClassifier
clf = tree.DecisionTreeClassifier()
#适配数据
clf = clf.fit(iris.data, iris.target)
#将决策树以pdf格式可视化
dot_data = tree.export_graphviz(clf, out_file=None)
graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_pdf("iris.pdf")

#使用决策树算法检测POP3暴力破解
import re
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import cross_val_score
import os
from sklearn.datasets import load_iris
from sklearn import tree
import pydotplus
#加载kdd数据集
def load_kdd99(filename):
  X=[]
  with open(filename) as f:
    for line in f:
      line = line.strip('\n')
      line = line.split(',')
      X.append(line)
  return X
#找到训练数据集
def get_guess_passwdandNormal(x):
  v=[]
  features=[]
  targets=[]
  #找到标记为guess-passwd和normal且是POP3协议的数据
  for x1 in x:
    if ( x1[41] in ['guess_passwd.','normal.'] ) and ( x1[2] == 'pop_3' ):
      if x1[41] == 'guess_passwd.':
        targets.append(1)
      else:
        targets.append(0)
    #挑选与POP3密码破解相关的网络特征和TCP协议内容的特征作为样本特征
      x1 = [x1[0]] + x1[4:8]+x1[22:30]
      v.append(x1)
  for x1 in v :
    v1=[]
    for x2 in x1:
      v1.append(float(x2))
    features.append(v1)
  return features,targets
if __name__ == '__main__':
  v=load_kdd99("../../data/kddcup99/corrected")
  x,y=get_guess_passwdandNormal(v)
  clf = tree.DecisionTreeClassifier()
  print(cross_val_score(clf, x, y, n_jobs=-1, cv=10))
  clf = clf.fit(x, y)
  dot_data = tree.export_graphviz(clf, out_file=None)
  graph = pydotplus.graph_from_dot_data(dot_data)
  graph.write_pdf("POP3Detector.pdf")

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("决策树准确率；",scores.mean())
clf = RandomForestClassifier(n_estimators=10,max_depth = None,min_samples_split=2,random_state = 0)
scores = cross_val_score(clf,X,y)
print("随机森林准确率：",scores.mean())

# -*- coding:utf-8 -*-
#使用随机森林算法检测FTP暴力破解
import re
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import cross_val_score
import os
from sklearn import tree
import pydotplus
import numpy as np
from sklearn.ensemble import RandomForestClassifier
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 = path+filename
    if os.path.isdir(filepath):
      #处理路径异常
      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:
    #正则表达式匹配hydra异常ftp文件
    if re.match(r"../../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("../../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()
  #clf = tree.DecisionTreeClassifier()
  clf = RandomForestClassifier(n_estimators=10, max_depth=None,min_samples_split=2, random_state=0)
  clf = clf.fit(x,y)
  score = cross_val_score(clf, x, y, n_jobs=-1, cv=10)
  print(score)
  print('平均正确率为：',np.mean(score))