Anomaly Detection with sklearn using Guassian Distribution #MachineLearning

Anomaly Detection using Gaussian Distribution.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from matplotlib import pyplot\n",
    "from sklearn import svm\n",
    "from numpy import genfromtxt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define the function we are gonna use to label our predirected data \n",
    "\n",
    "# It returns a tuple of normal and abornal data plus the indexes from the dataset variable \n",
    "# that was setted as anomalies\n",
    "\n",
    "def label_data(prediction, dataset):\n",
    "    # inliers are labeled 1, outliers are labeled -1\n",
    "    normal = dataset[prediction == 1]\n",
    "    abnormal = dataset[prediction == -1]\n",
    "    abnormal_indexes = [i for i, x in enumerate(prediction) if x == -1]\n",
    "    return normal, abnormal, abnormal_indexes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# our dataset consist on HTTP_STATUS_CODE, ELEPSED_TIME_IN_SECONDS\n",
    "# ex: 200,0.314\n",
    "training_data = genfromtxt('sample.csv', delimiter=',')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "classifier = svm.OneClassSVM(nu=0.01, kernel=\"rbf\", gamma=0.1)\n",
    "classifier.fit(training_data)\n",
    "prediction = classifier.predict(training_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Abnormal indexes on training_data var:  [496, 497]\n"
     ]
    }
   ],
   "source": [
    "normal, abnormal, abnormal_indexes = label_data(prediction, training_data)\n",
    "print('Abnormal indexes on training_data var: ', abnormal_indexes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEWCAYAAACXGLsWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nlIOFmZmVcrAwM7NSDhZmZlbq/wNsvWfdnTDBPwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f756c1778d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pyplot.figure()\n",
    "pyplot.plot(normal[:,0],normal[:,1],'bx')\n",
    "pyplot.plot(abnormal[:,0],abnormal[:,1],'ro')\n",
    "pyplot.title('Anomaly Detection - Guassian Distribution')\n",
    "pyplot.xlabel('HTTP Status Code') # training_data[:,0]\n",
    "pyplot.ylabel('Eleapsed Time') # training_data[:,1]\n",
    "pyplot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

requirements.txt

sklearn
numpy
matplotlib
jupyter

sample.csv