{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "BUTFBYKgAsSV"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.metrics import silhouette_score\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "ykmjXu5-A6FH"
   },
   "outputs": [],
   "source": [
    "malware_dataset = pd.read_csv(\"MalwareArtifacts.csv\", delimiter=',')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "-kbytUCHA8j6"
   },
   "outputs": [],
   "source": [
    "# Extracting artifacts smaples fields # MajourLinkerVersion, MajorImageVersion, MajorOperatingSystemVersion,DllCharacteristics\n",
    "samples = malware_dataset.iloc[:, [1,2,3,4]].values\n",
    "targets = malware_dataset.iloc[:, 8].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "jXBwP8eLBijT",
    "outputId": "f03022bb-020b-4227-a407-c9199da4f747"
   },
   "outputs": [],
   "source": [
    "k_means = KMeans(n_clusters=2, max_iter=100)\n",
    "k_means.fit(samples)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "nWi4BxSTDGDQ",
    "outputId": "2485d298-eeb0-4906-c0ec-c6f91baec6f1"
   },
   "outputs": [],
   "source": [
    "print(\"K-Means labels: \" + str(k_means.labels_))\n",
    "print(\"\\n K-means clustering reulsts \\n\\n\", pd.crosstab(targets, k_means.labels_, rownames = [\"Observerd\"], colnames=[\"Predicted\"]))\n",
    "print (\"\\nSilhouette coefficient: %0.3f\" % silhouette_score(samples, k_means.labels_, metric='euclidean')) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Udemy Malware detection with K-Means.ipynb",
   "provenance": []
  },
  "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": "3.8.8"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}