代码如下,测试发现,是否对输入数据进行归一化/标准化对于结果没有影响:

import numpy as np
from sklearn.ensemble import IsolationForest
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler def parse_line(s):
s = s.replace("u'", "").replace("'", "").replace("(", "").replace(")", "").replace("[", "").replace("]", "")
s2 = s.split(",")
dat = [float(_) for _ in s2[1:]]
return (s2[0], dat) def get_data():
with open("feature.dat") as f:
lines = f.readlines()
return [parse_line(line) for line in lines] def train(collected_data):
input_data = [c[1] for c in collected_data]
#scaler = StandardScaler().fit(input_data)
#input_data = scaler.transform(input_data) #min_max_scaler = MinMaxScaler()
#input_data = min_max_scaler.fit_transform(input_data)
#print input_data rng = np.random.RandomState(42)
#clf = IsolationForest(max_samples=10*2, random_state=rng)
#clf = IsolationForest(max_features=5)
clf = IsolationForest(max_samples="auto", random_state=rng)
clf.fit(input_data)
pred_y = clf.predict(input_data) bad_domains = set()
for i,y in enumerate(pred_y):
if y == -1:
print "bad domains:", collected_data[i]
bad_domains.add(collected_data[i][0]) if __name__ == "__main__":
dat = get_data()
train(dat)

输出样例:

bad domains: ('openvpn.', [81.0, 5.0, 3.0, 14.0, 0.1728395061728395, 27.493827160493826, 32.76543209876543, 3.2857142857142856, 18.214285714285715, 3.0714285714285716, 3.255427209766844, 0.04938271604938271, 0.0, 0.3950617283950617, 0.12345679012345678, 0.00224517287831163])
bad domains: ('mobily.com.sa', [16.0, 1.0, 4.0, 12.0, 0.75, 47.3125, 108.8125, 1.0, 5.333333333333333, 0.0, 1.9166666666666667, 0.6875, 0.0, 0.375, 0.375, 0.0066050198150594455])
bad domains: ('vcl2728.com', [40.0, 2.0, 10.0, 27.0, 0.675, 67.125, 462.85, 3.3333333333333335, 28.555555555555557, 3.3703703703703702, 3.111111111111111, 0.025, 0.0, 0.0, 0.0, 0.00186219739292365])
bad domains: ('vkcache.com', [598.0, 1.0, 2.0, 528.0, 0.882943143812709, 47.0, 161.65886287625418, 1.0, 6.0, 0.005681818181818182, 2.453875312427234, 0.22909698996655517, 0.0, 0.11371237458193979, 0.0033444816053511705, 0.00017789795773144525])
bad domains: ('nsconcreteblock.info', [18.0, 2.0, 4.0, 18.0, 1.0, 87.0, 43.5, 1.0, 37.0, 5.0, 3.823329582775343, 1.0, 0.0, 0.0, 0.0, 0.0031928480204342275])
bad domains: ('topcdn.org', [52.0, 2.0, 4.0, 13.0, 0.25, 80.92307692307692, 56.38461538461539, 1.0, 40.92307692307692, 0.0, 4.176988788169356, 0.5, 0.0, 0.28846153846153844, 0.21153846153846154, 0.001188212927756654])
bad domains: ('bilibiligame.net', [6472.0, 165.0, 17.0, 32.0, 0.004944375772558714, 46.542954264524106, 88.28522867737948, 1.0, 18.65625, 2.84375, 3.4818361348887463, 0.9610630407911002, 0.0, 0.2376390605686032, 0.0004635352286773795, 1.659883277007961e-05])
bad domains: ('vip.', [2183.0, 386.0, 30.0, 32.0, 0.014658726523133303, 34.78515803939533, 23.834631241410904, 1.9375, 9.6875, 0.0, 2.83937270784057, 0.9436555199267064, 0.0, 0.09894640403114979, 0.011452130096197893, 6.58449220396123e-05])
bad domains: ('ixigua.com', [2707.0, 133.0, 29.0, 17.0, 0.006280014776505356, 33.71222755818249, 123.10749907646841, 1.0, 4.647058823529412, 0.8823529411764706, 1.9781718484300252, 0.9759881787957149, 0.0, 0.28075360177318065, 0.01699298115995567, 5.478911668986072e-05])
bad domains: ('expressvpn.', [890.0, 31.0, 36.0, 165.0, 0.1853932584269663, 41.89887640449438, 0.0, 1.0363636363636364, 11.224242424242425, 0.05454545454545454, 3.0592421535372565, 0.5325842696629214, 0.0, 0.0, 0.0, 0.00013408420488066506])

输入数据样例(已经提取了特征):

(u'abfxsc.com', (24, 1, 4, 11, 0.4583333333333333, 48.0, 56.041666666666664, 1.0, 8.0, 0.0, 3.0, 0.5, 0.0, 0.20833333333333334, 0.08333333333333333, 0.004340277777777778))
(u'dqdkws.cn', (71, 2, 7, 50, 0.704225352112676, 45.0, 79.859154929577471, 1.0, 6.0, 0.0, 2.4132632507067329, 0.5915492957746479, 0.0, 0.0, 0.0, 0.0015649452269170579))
(u'tcdnvod.com', (701, 51, 17, 40, 0.05706134094151213, 55.266761768901567, 56.370898716119832, 3.1749999999999998, 17.399999999999999, 0.125, 3.4810606143066232, 0.9714693295292439, 0.0, 0.39514978601997147, 0.0442225392296719, 0.00012905890248309329))
(u'0937jyg.com', (68, 4, 7, 19, 0.27941176470588236, 46.25, 67.529411764705884, 1.0, 5.3684210526315788, 0.0, 2.2469056830015672, 0.6323529411764706, 0.0, 0.0, 0.0, 0.001589825119236884))
(u'jcloud-cdn.com', (61, 3, 3, 11, 0.18032786885245902, 67.278688524590166, 66.311475409836063, 4.5454545454545459, 24.363636363636363, 0.18181818181818182, 3.5244668708659161, 0.4262295081967213, 0.0, 0.08196721311475409, 0.03278688524590164, 0.0012183235867446393))
(u'omacloud.com', (545, 8, 20, 29, 0.05321100917431193, 46.315596330275227, 30.722935779816513, 1.9655172413793103, 17.793103448275861, 0.0, 3.3836270422458083, 1.0, 0.0, 0.10825688073394496, 0.022018348623853212, 0.00019808256081134618))
(u'serverss.top', (144, 1, 15, 22, 0.1527777777777778, 46.604166666666664, 50.145833333333336, 1.0, 4.5909090909090908, 0.0, 2.1594720075625, 0.5277777777777778, 0.0, 0.2777777777777778, 0.06944444444444445, 0.00074504544777231408))
(u'ctripgslb.com', (601, 9, 10, 34, 0.056572379367720464, 60.512479201331118, 157.12479201331115, 3.0588235294117645, 17.911764705882351, 0.91176470588235292, 3.3912394967901913, 0.8585690515806988, 0.0, 0.3594009983361065, 0.016638935108153077, 0.00013748350197976243))
(u'kas-labs.com', (54, 2, 8, 15, 0.2777777777777778, 55.888888888888886, 142.37037037037038, 1.0, 12.466666666666667, 1.6000000000000001, 3.0989151803147923, 0.5, 0.0, 0.09259259259259259, 0.09259259259259259, 0.0016567263088137839))
(u'mccdnglb.com', (365, 4, 6, 21, 0.057534246575342465, 51.161643835616438, 98.161643835616445, 3.5238095238095237, 18.428571428571427, 0.19047619047619047, 3.4116298602195974, 0.989041095890411, 0.0, 0.16164383561643836, 0.01643835616438356, 0.00026775195458926852))
(u'localhost.', (28, 4, 3, 10, 0.35714285714285715, 41.142857142857146, 172.35714285714286, 1.8999999999999999, 10.9, 1.8999999999999999, 2.3999999999999999, 0.14285714285714285, 0.0, 0.0, 0.0, 0.004340277777777778))
(u'xdy-cdn.cn', (473, 5, 2, 50, 0.10570824524312897, 54.780126849894295, 46.545454545454547, 3.0, 14.74, 0.0, 3.1343677127142864, 0.5750528541226215, 0.0, 0.0, 0.0, 0.00019296823742811933))
(u'labkas.com', (24, 2, 6, 10, 0.4166666666666667, 56.666666666666664, 66.833333333333329, 2.0, 17.399999999999999, 1.7, 3.6751008468322333, 0.08333333333333333, 0.0, 0.0, 0.0, 0.0036764705882352941))
(u'site.', (62, 5, 22, 14, 0.22580645161290322, 43.322580645161288, 50.774193548387096, 1.9285714285714286, 11.785714285714286, 0.21428571428571427, 3.0365341332026929, 0.5806451612903226, 0.0, 0.11290322580645161, 0.06451612903225806, 0.0018615040953090098))
(u'ft25882.com', (39, 2, 5, 20, 0.5128205128205128, 49.0, 92.871794871794876, 1.0, 8.0, 0.0, 3.0, 0.5384615384615384, 0.0, 0.3076923076923077, 0.05128205128205128, 0.0026164311878597592))
(u'douyuyuba.com', (232, 4, 7, 115, 0.4956896551724138, 62.650862068965516, 97.504310344827587, 2.0, 21.530434782608694, 0.97391304347826091, 3.4599350912323117, 0.5560344827586207, 0.0, 0.25, 0.008620689655172414, 0.00034399724802201581))
(u'win.', (334, 7, 39, 23, 0.0688622754491018, 42.604790419161674, 60.008982035928142, 1.8695652173913044, 13.217391304347826, 0.21739130434782608, 2.9398183078690807, 0.7904191616766467, 0.0, 0.3772455089820359, 0.041916167664670656, 0.00035137034434293746))
(u'affise.com', (73, 3, 10, 10, 0.136986301369863, 49.246575342465754, 146.56164383561645, 1.0, 8.5, 0.0, 2.5368841208873407, 0.6027397260273972, 0.0, 0.273972602739726, 0.0547945205479452, 0.0013908205841446453))
(u'stripcdn.com', (46, 3, 8, 17, 0.3695652173913043, 44.043478260869563, 160.54347826086956, 1.0, 3.8823529411764706, 0.52941176470588236, 1.8718920798583554, 0.391304347826087, 0.0, 0.10869565217391304, 0.10869565217391304, 0.0024679170779861796))
(u'doonoo.cn', (198, 1, 8, 19, 0.09595959595959595, 42.111111111111114, 66.060606060606062, 1.0, 3.1052631578947367, 0.0, 1.6286506585399816, 0.5, 0.0, 0.2222222222222222, 0.025252525252525252, 0.00059966418805468941))
(u'nii.ac.jp', (34, 3, 8, 16, 0.47058823529411764, 43.029411764705884, 34.529411764705884, 1.3125, 7.3125, 0.1875, 2.4667777025215347, 0.4411764705882353, 0.0, 0.08823529411764706, 0.08823529411764706, 0.0034176349965823649))
(u'78dm.net', (41, 5, 6, 11, 0.2682926829268293, 39.146341463414636, 66.634146341463421, 1.0, 3.3636363636363638, 0.18181818181818182, 1.3510446035661767, 0.7317073170731707, 0.0, 0.3170731707317073, 0.04878048780487805, 0.0031152647975077881))
(u'gosuncdn.com', (587, 5, 36, 40, 0.06814310051107325, 53.325383304940374, 204.61328790459967, 3.25, 15.699999999999999, 0.0, 3.3370338393801235, 0.5724020442930153, 0.0, 0.09540034071550256, 0.010221465076660987, 0.00015973420228739378))
(u'gfnormal04aj.com', (68, 2, 2, 33, 0.4852941176470588, 62.0, 58.970588235294116, 1.0, 16.0, 0.0, 3.4444634232339926, 0.5147058823529411, 0.0, 0.25, 0.058823529411764705, 0.0011859582542694497))
(u'mediatoday.co.kr', (13, 1, 3, 12, 0.9230769230769231, 50.46153846153846, 100.61538461538461, 1.0, 4.583333333333333, 0.0, 1.7623953076615158, 1.0, 0.0, 0.23076923076923078, 0.23076923076923078, 0.007621951219512195))
(u'qinsx.cn', (127, 4, 8, 14, 0.11023622047244094, 29.811023622047244, 51.362204724409452, 1.0, 1.9285714285714286, 0.0, 0.9285714285714286, 0.5905511811023622, 0.0, 0.30708661417322836, 0.06299212598425197, 0.0013206550449022716))

参考:http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.IsolationForest.html#sklearn.ensemble.IsolationForest

使用isolation forest进行dns网络流量异常检测的更多相关文章

  1. 5-Spark高级数据分析-第五章 基于K均值聚类的网络流量异常检测

    据我们所知,有‘已知的已知’,有些事,我们知道我们知道:我们也知道,有 ‘已知的未知’,也就是说,有些事,我们现在知道我们不知道.但是,同样存在‘不知的不知’——有些事,我们不知道我们不知道. 上一章 ...

  2. 基于PySpark的网络服务异常检测系统 阶段总结(二)

    在上篇博文中介绍了网络服务异常检测的大概,本篇将详细介绍SVDD和Isolation Forest这两种算法 1. SVDD算法 SVDD的英文全称是Support Vector Data Descr ...

  3. alluxio网络流量异常分析【转】

    1. 介绍 2. 准备工作 2.1 tcpdump 2.2 winshark 2.3 安装iftop 2.4 alluxio网络通信相关的端口 3.iftop 锁定消耗流量最大的端口 4. dump数 ...

  4. activeMQ消费消息时网络流量异常大的问题

    http://www.cnblogs.com/baibaluo/archive/2012/12/24/2748468.html#2590289 公司有一个应用,多个线程从activeMQ中取消息,随着 ...

  5. 基于PySpark的网络服务异常检测系统 (四) Mysql与SparkSQL对接同步数据 kmeans算法计算预测异常

    基于Django Restframework和Spark的异常检测系统,数据库为MySQL.Redis, 消息队列为Celery,分析服务为Spark SQL和Spark Mllib,使用kmeans ...

  6. 网络KPI异常检测之时序分解算法

    时间序列数据伴随着我们的生活和工作.从牙牙学语时的“1, 2, 3, 4, 5, ……”到房价的走势变化,从金融领域的刷卡记录到运维领域的核心网性能指标.时间序列中的规律能加深我们对事物和场景的认识, ...

  7. Python机器学习笔记 异常点检测算法——Isolation Forest

    Isolation,意为孤立/隔离,是名词,其动词为isolate,forest是森林,合起来就是“孤立森林”了,也有叫“独异森林”,好像并没有统一的中文叫法.可能大家都习惯用其英文的名字isolat ...

  8. isolation forest进行异常点检测

    一.简介 孤立森林(Isolation Forest)是另外一种高效的异常检测算法,它和随机森林类似,但每次选择划分属性和划分点(值)时都是随机的,而不是根据信息增益或者基尼指数来选择.在建树过程中, ...

  9. (转)isolation forest进行异常点检测

    原文链接:https://www.cnblogs.com/gczr/p/9156971.html 一.简介 孤立森林(Isolation Forest)是另外一种高效的异常检测算法,它和随机森林类似, ...

随机推荐

  1. 记一次在BroadcastReceiver或Service里弹窗的“完美”实践

    事情是这样的,目前在做一个医疗项目,需要定时在某个时间段比如午休时间和晚上让我们的App休眠,那么这个时候在休眠时间段如果用户按了电源键点亮屏幕了,我们就需要弹出一个全屏的窗口去做一个人性化的提示,“ ...

  2. 匿名訪问之(一)web application级别

    假设用SharePoint做一个对外开放的公共站点,比方公司展示站点.那么浏览站点的人不须要注冊和登陆.就应该能看到内容.这个时候就须要对站点开启匿名訪问. SharePoint的匿名訪问是从上而下的 ...

  3. hello world to php( mac 配置 xmapp virtual host)

    一.安装xmapp.安装完以后查看,服务是否都能启动(数据库和server) 二.配置自己的virtualhost       1.系统host文件加入server的域名(在浏览器中输入域名后会先通过 ...

  4. HDU1061_Rightmost Digit【高速幂取余】

    Rightmost Digit Time Limit: 2000/1000 MS (Java/Others)    Memory Limit: 65536/32768 K (Java/Others) ...

  5. 文件类似性推断 -- SimHash

    近期调研了一下simhash算法,它主要用在谷歌网页去重中.网上有非常多原理性的介绍. 既然能够用来推断文件的相似性,就想知道效果怎么样.simhash的准确度是否依赖于分词算法?是否和simhash ...

  6. shadowOffset 具体解释

    x向右为正,y向下为正 1.y<0 UILabel *label=[[UILabelalloc] initWithFrame:CGRectMake(40,40, 250,50)]; label. ...

  7. Binary Tree Inorder Traversal--leetcode

    原题链接:https://oj.leetcode.com/problems/binary-tree-inorder-traversal/ 题目大意:中序遍历二叉树 解题思路:中序遍历二叉树.中序遍历二 ...

  8. 对Shell几个冷知识的总结(IFS,数组,替换,分割,查找)

    IFS: 对IFS的用处直接进行说明,详细IFS是干什么的...自行谷歌 首先创建一个 "a a",和"a"的文件: 然后我们 ls查看一下: --> l ...

  9. Qt Quick Controls 与 Qt Quick Controls 2的区别(详细对照)

    Qt Quick Controls 原本是为支持桌面平台而开发的,后来又加入了移动平台和嵌入式平台的支持.它们应用非常广泛,因为它们提供了足够灵活的样式系统,以允许开发具有平台相关或者无关风格的应用程 ...

  10. 显示解析svg

    g公司代码显示svg: SVGParserRenderer drawable = new SVGParserRenderer(context, String svgContent); String s ...