ModelTraining.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "ModelTraining.ipynb",
      "provenance": [],
      "mount_file_id": "1zjtx2ZpQXWpPiOT2P8PGHAQMiHXLxhiz",
      "authorship_tag": "ABX9TyOA/fZK/5kv3cUROPQzGr9u",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/AndroGari/IntrusionDetectionSystem/blob/master/ModelTraining.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "858QJoij9m1F"
      },
      "outputs": [],
      "source": [
        "%matplotlib inline\n",
        "import matplotlib\n",
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import seaborn as sns \n",
        "import sklearn \n",
        "import imblearn \n",
        "\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore') \n",
        "\n",
        "pdf=pd.read_csv('/content/drive/MyDrive/Subdataset1.csv') \n",
        "ndf=pd.read_csv('/content/drive/MyDrive/Subdataset2.csv')\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import LabelEncoder\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import classification_report,confusion_matrix,plot_confusion_matrix,accuracy_score,precision_recall_fscore_support\n",
        "from sklearn.metrics import f1_score,roc_auc_score\n",
        "from sklearn.ensemble import RandomForestClassifier,ExtraTreesClassifier\n"
      ],
      "metadata": {
        "id": "1xy3o2XKNnqF"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "ndf[[\"date\",\"time\"]]=ndf[\"DATETIME\"].str.split(\" \",expand=True)\n",
        "ndf[[\"date\",\"month\",\"year\"]]=ndf[\"date\"].str.split(\"/\",expand=True)\n"
      ],
      "metadata": {
        "id": "3b9gFbGiHT5U"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "ndf[[\"date&time\"]]=\"20\"+ndf[\"year\"].astype(str)+\"-\"+ndf[\"month\"]+\"-\"+ndf[\"date\"]+\" \"+ndf[\"time\"]+\":00:00\"\n",
        "ndf.drop([\"date\",\"month\",\"year\",\"time\"],axis=1,inplace=True)\n"
      ],
      "metadata": {
        "id": "4d-Ri3Iom-uz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import datetime as dt\n",
        "ndf[\"date&time\"]=pd.to_datetime(ndf[\"date&time\"])\n",
        "timestamp=[]\n",
        "timestamp=ndf[\"date&time\"]\n",
        "LABEL=[] \n",
        " \n",
        "dt1=dt.datetime(2020,9,13,23)\n",
        "td1=dt.datetime(2020,9,16,00)\n",
        "dt2=dt.datetime(2020,9,26,11)\n",
        "td2=dt.datetime(2020,9,27,10)\n",
        "dt3=dt.datetime(2020,10,9,9)\n",
        "td3=dt.datetime(2020,10,11,20)\n",
        "dt4=dt.datetime(2020,10,29,19)\n",
        "td4=dt.datetime(2020,11,2,16)\n",
        "dt5=dt.datetime(2020,11,26,17)\n",
        "td5=dt.datetime(2020,11,29,4)\n",
        "dt6=dt.datetime(2020,12,6,7)\n",
        "td6=dt.datetime(2020,12,10,4)\n",
        "dt7=dt.datetime(2020,12,14,15)\n",
        "td7=dt.datetime(2020,12,19,4)\n",
        "\n",
        "\n",
        "for i in range(len(timestamp)):\n",
        "  if timestamp[i]>=dt1 and timestamp[i]<=td1:\n",
        "    LABEL.append(1)\n",
        "  elif timestamp[i]>=dt2 and timestamp[i]<=td2:\n",
        "    LABEL.append(1)\n",
        "  elif timestamp[i]>=dt3 and timestamp[i]<=td3:\n",
        "    LABEL.append(1)\n",
        "  elif timestamp[i]>=dt4 and timestamp[i]<=td4:\n",
        "    LABEL.append(1)\n",
        "  elif timestamp[i]>=dt5 and timestamp[i]<=td5:\n",
        "    LABEL.append(1)\n",
        "  elif timestamp[i]>=dt6 and timestamp[i]<=dt6:\n",
        "    LABEL.append(1)\n",
        "  elif timestamp[i]>=dt7 and timestamp[i]<=td7: \n",
        "    LABEL.append(1) \n",
        "  else: \n",
        "    LABEL.append(0) \n",
        "  "
      ],
      "metadata": {
        "id": "QXYYrFKh7iOx"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "ndf.drop([\"date&time\"],axis=1,inplace=True)\n",
        "ndf[\"LABEL\"]=LABEL"
      ],
      "metadata": {
        "id": "aSBHkDoYmO5O"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "le = LabelEncoder()\n",
        "datetime = le.fit_transform(ndf['DATETIME'])\n",
        "datetime2= le.fit_transform(pdf['DATETIME'])\n",
        "ndf[\"DATETIME\"]=datetime\n",
        "pdf[\"DATETIME\"]=datetime2\n",
        "\n",
        "# ndf.drop([\"datetime\"],axis=1,inplace=True)\n",
        "ndf"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "bIHJ7Fvlao5N",
        "outputId": "a21ed669-7773-4c6c-f09e-429e22703ab6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-e298977f-6210-4880-8087-9dd213fa06c1\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>DATETIME</th>\n",
              "      <th>L_T1</th>\n",
              "      <th>L_T2</th>\n",
              "      <th>L_T3</th>\n",
              "      <th>L_T4</th>\n",
              "      <th>L_T5</th>\n",
              "      <th>L_T6</th>\n",
              "      <th>L_T7</th>\n",
              "      <th>F_PU1</th>\n",
              "      <th>S_PU1</th>\n",
              "      <th>F_PU2</th>\n",
              "      <th>S_PU2</th>\n",
              "      <th>F_PU3</th>\n",
              "      <th>S_PU3</th>\n",
              "      <th>F_PU4</th>\n",
              "      <th>S_PU4</th>\n",
              "      <th>F_PU5</th>\n",
              "      <th>S_PU5</th>\n",
              "      <th>F_PU6</th>\n",
              "      <th>S_PU6</th>\n",
              "      <th>F_PU7</th>\n",
              "      <th>S_PU7</th>\n",
              "      <th>F_PU8</th>\n",
              "      <th>S_PU8</th>\n",
              "      <th>F_PU9</th>\n",
              "      <th>S_PU9</th>\n",
              "      <th>F_PU10</th>\n",
              "      <th>S_PU10</th>\n",
              "      <th>F_PU11</th>\n",
              "      <th>S_PU11</th>\n",
              "      <th>F_V2</th>\n",
              "      <th>S_V2</th>\n",
              "      <th>P_J280</th>\n",
              "      <th>P_J269</th>\n",
              "      <th>P_J300</th>\n",
              "      <th>P_J256</th>\n",
              "      <th>P_J289</th>\n",
              "      <th>P_J415</th>\n",
              "      <th>P_J302</th>\n",
              "      <th>P_J306</th>\n",
              "      <th>P_J307</th>\n",
              "      <th>P_J317</th>\n",
              "      <th>P_J14</th>\n",
              "      <th>P_J422</th>\n",
              "      <th>LABEL</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>360</td>\n",
              "      <td>2.44</td>\n",
              "      <td>5.24</td>\n",
              "      <td>3.19</td>\n",
              "      <td>4.10</td>\n",
              "      <td>2.86</td>\n",
              "      <td>5.50</td>\n",
              "      <td>4.39</td>\n",
              "      <td>93.63</td>\n",
              "      <td>1</td>\n",
              "      <td>93.65</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>49.84</td>\n",
              "      <td>1</td>\n",
              "      <td>35.54</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>29.87</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>2.98</td>\n",
              "      <td>36.38</td>\n",
              "      <td>28.26</td>\n",
              "      <td>70.00</td>\n",
              "      <td>28.22</td>\n",
              "      <td>85.87</td>\n",
              "      <td>21.69</td>\n",
              "      <td>82.72</td>\n",
              "      <td>21.58</td>\n",
              "      <td>71.99</td>\n",
              "      <td>39.33</td>\n",
              "      <td>29.64</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>361</td>\n",
              "      <td>2.66</td>\n",
              "      <td>4.53</td>\n",
              "      <td>3.20</td>\n",
              "      <td>4.18</td>\n",
              "      <td>3.29</td>\n",
              "      <td>5.44</td>\n",
              "      <td>4.53</td>\n",
              "      <td>89.41</td>\n",
              "      <td>1</td>\n",
              "      <td>89.43</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>34.26</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>48.38</td>\n",
              "      <td>1</td>\n",
              "      <td>37.83</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>2.98</td>\n",
              "      <td>38.60</td>\n",
              "      <td>24.39</td>\n",
              "      <td>87.73</td>\n",
              "      <td>24.45</td>\n",
              "      <td>84.87</td>\n",
              "      <td>29.81</td>\n",
              "      <td>86.62</td>\n",
              "      <td>29.81</td>\n",
              "      <td>59.76</td>\n",
              "      <td>42.17</td>\n",
              "      <td>26.15</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>362</td>\n",
              "      <td>3.11</td>\n",
              "      <td>3.66</td>\n",
              "      <td>3.66</td>\n",
              "      <td>4.21</td>\n",
              "      <td>3.87</td>\n",
              "      <td>5.15</td>\n",
              "      <td>3.22</td>\n",
              "      <td>89.88</td>\n",
              "      <td>1</td>\n",
              "      <td>89.89</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.97</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>46.84</td>\n",
              "      <td>1</td>\n",
              "      <td>37.31</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>2.98</td>\n",
              "      <td>38.36</td>\n",
              "      <td>23.84</td>\n",
              "      <td>89.29</td>\n",
              "      <td>23.90</td>\n",
              "      <td>87.11</td>\n",
              "      <td>29.85</td>\n",
              "      <td>87.64</td>\n",
              "      <td>29.85</td>\n",
              "      <td>58.50</td>\n",
              "      <td>42.00</td>\n",
              "      <td>25.56</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>363</td>\n",
              "      <td>3.62</td>\n",
              "      <td>3.04</td>\n",
              "      <td>4.17</td>\n",
              "      <td>4.04</td>\n",
              "      <td>3.56</td>\n",
              "      <td>4.98</td>\n",
              "      <td>2.40</td>\n",
              "      <td>88.10</td>\n",
              "      <td>1</td>\n",
              "      <td>88.12</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>33.27</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.68</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>2.98</td>\n",
              "      <td>39.29</td>\n",
              "      <td>27.00</td>\n",
              "      <td>91.98</td>\n",
              "      <td>27.10</td>\n",
              "      <td>68.75</td>\n",
              "      <td>31.60</td>\n",
              "      <td>64.25</td>\n",
              "      <td>31.47</td>\n",
              "      <td>72.30</td>\n",
              "      <td>43.24</td>\n",
              "      <td>28.38</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>364</td>\n",
              "      <td>4.08</td>\n",
              "      <td>2.68</td>\n",
              "      <td>4.73</td>\n",
              "      <td>3.20</td>\n",
              "      <td>3.11</td>\n",
              "      <td>5.39</td>\n",
              "      <td>3.46</td>\n",
              "      <td>87.01</td>\n",
              "      <td>1</td>\n",
              "      <td>87.03</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.99</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.81</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>2.98</td>\n",
              "      <td>39.85</td>\n",
              "      <td>26.67</td>\n",
              "      <td>92.11</td>\n",
              "      <td>26.76</td>\n",
              "      <td>68.74</td>\n",
              "      <td>32.30</td>\n",
              "      <td>64.23</td>\n",
              "      <td>32.17</td>\n",
              "      <td>72.53</td>\n",
              "      <td>44.00</td>\n",
              "      <td>28.04</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4172</th>\n",
              "      <td>3380</td>\n",
              "      <td>2.65</td>\n",
              "      <td>2.37</td>\n",
              "      <td>3.85</td>\n",
              "      <td>3.04</td>\n",
              "      <td>3.82</td>\n",
              "      <td>4.94</td>\n",
              "      <td>2.19</td>\n",
              "      <td>120.08</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>50.30</td>\n",
              "      <td>1</td>\n",
              "      <td>34.27</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>30.71</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>67.23</td>\n",
              "      <td>1</td>\n",
              "      <td>2.99</td>\n",
              "      <td>21.70</td>\n",
              "      <td>27.42</td>\n",
              "      <td>70.03</td>\n",
              "      <td>27.38</td>\n",
              "      <td>84.14</td>\n",
              "      <td>18.45</td>\n",
              "      <td>81.67</td>\n",
              "      <td>18.34</td>\n",
              "      <td>66.04</td>\n",
              "      <td>29.88</td>\n",
              "      <td>28.98</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4173</th>\n",
              "      <td>3381</td>\n",
              "      <td>2.24</td>\n",
              "      <td>2.56</td>\n",
              "      <td>3.42</td>\n",
              "      <td>2.92</td>\n",
              "      <td>3.69</td>\n",
              "      <td>5.02</td>\n",
              "      <td>1.97</td>\n",
              "      <td>119.12</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>50.78</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.47</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>70.89</td>\n",
              "      <td>1</td>\n",
              "      <td>2.99</td>\n",
              "      <td>22.25</td>\n",
              "      <td>27.71</td>\n",
              "      <td>68.60</td>\n",
              "      <td>27.66</td>\n",
              "      <td>83.46</td>\n",
              "      <td>25.40</td>\n",
              "      <td>60.85</td>\n",
              "      <td>25.28</td>\n",
              "      <td>66.89</td>\n",
              "      <td>30.19</td>\n",
              "      <td>29.29</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4174</th>\n",
              "      <td>3382</td>\n",
              "      <td>1.91</td>\n",
              "      <td>2.76</td>\n",
              "      <td>2.95</td>\n",
              "      <td>2.49</td>\n",
              "      <td>2.70</td>\n",
              "      <td>5.14</td>\n",
              "      <td>1.87</td>\n",
              "      <td>120.71</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>36.84</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>50.69</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.43</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>66.71</td>\n",
              "      <td>1</td>\n",
              "      <td>2.99</td>\n",
              "      <td>21.33</td>\n",
              "      <td>26.77</td>\n",
              "      <td>85.63</td>\n",
              "      <td>26.84</td>\n",
              "      <td>82.82</td>\n",
              "      <td>24.46</td>\n",
              "      <td>59.56</td>\n",
              "      <td>24.34</td>\n",
              "      <td>66.08</td>\n",
              "      <td>29.68</td>\n",
              "      <td>28.78</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4175</th>\n",
              "      <td>3383</td>\n",
              "      <td>1.52</td>\n",
              "      <td>2.52</td>\n",
              "      <td>3.33</td>\n",
              "      <td>2.03</td>\n",
              "      <td>1.69</td>\n",
              "      <td>5.10</td>\n",
              "      <td>1.39</td>\n",
              "      <td>120.02</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>35.98</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>36.94</td>\n",
              "      <td>1</td>\n",
              "      <td>36.92</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>32.42</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>76.14</td>\n",
              "      <td>1</td>\n",
              "      <td>2.99</td>\n",
              "      <td>21.74</td>\n",
              "      <td>25.75</td>\n",
              "      <td>86.15</td>\n",
              "      <td>25.78</td>\n",
              "      <td>103.63</td>\n",
              "      <td>24.77</td>\n",
              "      <td>59.01</td>\n",
              "      <td>24.65</td>\n",
              "      <td>66.42</td>\n",
              "      <td>28.98</td>\n",
              "      <td>28.08</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4176</th>\n",
              "      <td>3504</td>\n",
              "      <td>1.10</td>\n",
              "      <td>2.12</td>\n",
              "      <td>3.73</td>\n",
              "      <td>2.73</td>\n",
              "      <td>1.58</td>\n",
              "      <td>5.13</td>\n",
              "      <td>1.19</td>\n",
              "      <td>120.33</td>\n",
              "      <td>1</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>34.19</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>34.84</td>\n",
              "      <td>1</td>\n",
              "      <td>34.81</td>\n",
              "      <td>1</td>\n",
              "      <td>34.70</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>30.23</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>74.17</td>\n",
              "      <td>1</td>\n",
              "      <td>2.99</td>\n",
              "      <td>21.55</td>\n",
              "      <td>25.62</td>\n",
              "      <td>89.08</td>\n",
              "      <td>25.64</td>\n",
              "      <td>105.91</td>\n",
              "      <td>18.16</td>\n",
              "      <td>80.65</td>\n",
              "      <td>18.06</td>\n",
              "      <td>67.32</td>\n",
              "      <td>28.75</td>\n",
              "      <td>27.85</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>4177 rows × 45 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e298977f-6210-4880-8087-9dd213fa06c1')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-e298977f-6210-4880-8087-9dd213fa06c1 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-e298977f-6210-4880-8087-9dd213fa06c1');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "      DATETIME   L_T1   L_T2   L_T3  ...   P_J317   P_J14   P_J422  LABEL\n",
              "0          360   2.44   5.24   3.19  ...    71.99   39.33    29.64      0\n",
              "1          361   2.66   4.53   3.20  ...    59.76   42.17    26.15      0\n",
              "2          362   3.11   3.66   3.66  ...    58.50   42.00    25.56      0\n",
              "3          363   3.62   3.04   4.17  ...    72.30   43.24    28.38      0\n",
              "4          364   4.08   2.68   4.73  ...    72.53   44.00    28.04      0\n",
              "...        ...    ...    ...    ...  ...      ...     ...      ...    ...\n",
              "4172      3380   2.65   2.37   3.85  ...    66.04   29.88    28.98      0\n",
              "4173      3381   2.24   2.56   3.42  ...    66.89   30.19    29.29      0\n",
              "4174      3382   1.91   2.76   2.95  ...    66.08   29.68    28.78      0\n",
              "4175      3383   1.52   2.52   3.33  ...    66.42   28.98    28.08      0\n",
              "4176      3504   1.10   2.12   3.73  ...    67.32   28.75    27.85      0\n",
              "\n",
              "[4177 rows x 45 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "ndf.info(), pdf.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jqUpbqCt0bcv",
        "outputId": "eb4f5f72-9f49-45a0-c1b0-1752495b7a90"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 4177 entries, 0 to 4176\n",
            "Data columns (total 45 columns):\n",
            " #   Column    Non-Null Count  Dtype  \n",
            "---  ------    --------------  -----  \n",
            " 0   DATETIME  4177 non-null   int64  \n",
            " 1    L_T1     4177 non-null   float64\n",
            " 2    L_T2     4177 non-null   float64\n",
            " 3    L_T3     4177 non-null   float64\n",
            " 4    L_T4     4177 non-null   float64\n",
            " 5    L_T5     4177 non-null   float64\n",
            " 6    L_T6     4177 non-null   float64\n",
            " 7    L_T7     4177 non-null   float64\n",
            " 8    F_PU1    4177 non-null   float64\n",
            " 9    S_PU1    4177 non-null   int64  \n",
            " 10   F_PU2    4177 non-null   float64\n",
            " 11   S_PU2    4177 non-null   int64  \n",
            " 12   F_PU3    4177 non-null   int64  \n",
            " 13   S_PU3    4177 non-null   int64  \n",
            " 14   F_PU4    4177 non-null   float64\n",
            " 15   S_PU4    4177 non-null   int64  \n",
            " 16   F_PU5    4177 non-null   int64  \n",
            " 17   S_PU5    4177 non-null   int64  \n",
            " 18   F_PU6    4177 non-null   float64\n",
            " 19   S_PU6    4177 non-null   int64  \n",
            " 20   F_PU7    4177 non-null   float64\n",
            " 21   S_PU7    4177 non-null   int64  \n",
            " 22   F_PU8    4177 non-null   float64\n",
            " 23   S_PU8    4177 non-null   int64  \n",
            " 24   F_PU9    4177 non-null   int64  \n",
            " 25   S_PU9    4177 non-null   int64  \n",
            " 26   F_PU10   4177 non-null   float64\n",
            " 27   S_PU10   4177 non-null   int64  \n",
            " 28   F_PU11   4177 non-null   float64\n",
            " 29   S_PU11   4177 non-null   int64  \n",
            " 30   F_V2     4177 non-null   float64\n",
            " 31   S_V2     4177 non-null   int64  \n",
            " 32   P_J280   4177 non-null   float64\n",
            " 33   P_J269   4177 non-null   float64\n",
            " 34   P_J300   4177 non-null   float64\n",
            " 35   P_J256   4177 non-null   float64\n",
            " 36   P_J289   4177 non-null   float64\n",
            " 37   P_J415   4177 non-null   float64\n",
            " 38   P_J302   4177 non-null   float64\n",
            " 39   P_J306   4177 non-null   float64\n",
            " 40   P_J307   4177 non-null   float64\n",
            " 41   P_J317   4177 non-null   float64\n",
            " 42   P_J14    4177 non-null   float64\n",
            " 43   P_J422   4177 non-null   float64\n",
            " 44  LABEL     4177 non-null   int64  \n",
            "dtypes: float64(28), int64(17)\n",
            "memory usage: 1.4 MB\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 8761 entries, 0 to 8760\n",
            "Data columns (total 44 columns):\n",
            " #   Column    Non-Null Count  Dtype  \n",
            "---  ------    --------------  -----  \n",
            " 0   DATETIME  8761 non-null   int64  \n",
            " 1   L_T1      8761 non-null   float64\n",
            " 2   L_T2      8761 non-null   float64\n",
            " 3   L_T3      8761 non-null   float64\n",
            " 4   L_T4      8761 non-null   float64\n",
            " 5   L_T5      8761 non-null   float64\n",
            " 6   L_T6      8761 non-null   float64\n",
            " 7   L_T7      8761 non-null   float64\n",
            " 8   F_PU1     8761 non-null   float64\n",
            " 9   S_PU1     8761 non-null   int64  \n",
            " 10  F_PU2     8761 non-null   float64\n",
            " 11  S_PU2     8761 non-null   int64  \n",
            " 12  F_PU3     8761 non-null   int64  \n",
            " 13  S_PU3     8761 non-null   int64  \n",
            " 14  F_PU4     8761 non-null   float64\n",
            " 15  S_PU4     8761 non-null   int64  \n",
            " 16  F_PU5     8761 non-null   int64  \n",
            " 17  S_PU5     8761 non-null   int64  \n",
            " 18  F_PU6     8761 non-null   float64\n",
            " 19  S_PU6     8761 non-null   int64  \n",
            " 20  F_PU7     8761 non-null   float64\n",
            " 21  S_PU7     8761 non-null   int64  \n",
            " 22  F_PU8     8761 non-null   float64\n",
            " 23  S_PU8     8761 non-null   int64  \n",
            " 24  F_PU9     8761 non-null   int64  \n",
            " 25  S_PU9     8761 non-null   int64  \n",
            " 26  F_PU10    8761 non-null   float64\n",
            " 27  S_PU10    8761 non-null   int64  \n",
            " 28  F_PU11    8761 non-null   float64\n",
            " 29  S_PU11    8761 non-null   int64  \n",
            " 30  F_V2      8761 non-null   float64\n",
            " 31  S_V2      8761 non-null   int64  \n",
            " 32  P_J280    8761 non-null   float64\n",
            " 33  P_J269    8761 non-null   float64\n",
            " 34  P_J300    8761 non-null   float64\n",
            " 35  P_J256    8761 non-null   float64\n",
            " 36  P_J289    8761 non-null   float64\n",
            " 37  P_J415    8761 non-null   float64\n",
            " 38  P_J302    8761 non-null   float64\n",
            " 39  P_J306    8761 non-null   float64\n",
            " 40  P_J307    8761 non-null   float64\n",
            " 41  P_J317    8761 non-null   float64\n",
            " 42  P_J14     8761 non-null   float64\n",
            " 43  P_J422    8761 non-null   float64\n",
            "dtypes: float64(28), int64(16)\n",
            "memory usage: 2.9 MB\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(None, None)"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        " ndf.shape, pdf.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JEHMLXY1f3iP",
        "outputId": "229aa0d5-2772-4826-caf0-d0ff79b8469e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "((4177, 45), (8761, 44))"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X = ndf.drop([\"LABEL\"],axis=1).values\n",
        "Y = ndf.iloc[:, -1].values\n",
        "Y=np.ravel(Y)\n",
        "X_train, X_test, Y_train, Y_test = train_test_split(X,Y, train_size = 0.7, test_size = 0.3, random_state = 0,stratify = Y)"
      ],
      "metadata": {
        "id": "c0KuAROhGoCQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "ndf.LABEL.value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0mS8lWAtOgrM",
        "outputId": "529afda1-6ac6-47a7-975f-5cb707f6352f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    3778\n",
              "1     399\n",
              "Name: LABEL, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "XM=pdf\n",
        "print(f\"X_train dimensions: {X_train.shape}\")\n",
        "print(f\"Y_train dimensions: {Y_train.shape}\\n\")\n",
        "\n",
        "print(f\"X_test dimensions: {X_test.shape}\")\n",
        "print(f\"Y_test dimensions: {Y_test.shape}\\n\")\n",
        "\n",
        "print(f\"XM dimensions: {XM.shape}\")"
      ],
      "metadata": {
        "id": "TMcrTOGvOwZ6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ed3564f4-8986-4c69-e188-7c455b13c389"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "X_train dimensions: (2923, 44)\n",
            "Y_train dimensions: (2923,)\n",
            "\n",
            "X_test dimensions: (1254, 44)\n",
            "Y_test dimensions: (1254,)\n",
            "\n",
            "XM dimensions: (8761, 44)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Visualize class distribution\n",
        "ndf.LABEL.value_counts().plot(kind='bar')\n",
        "plt.xticks([0,1], ['NORMAL', 'ATTACK'])\n",
        "plt.ylabel('Count')"
      ],
      "metadata": {
        "id": "PU3Xo3RLSvsX",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 315
        },
        "outputId": "b5029f87-a49e-4cd6-800c-fc9ed02dd4ea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0, 0.5, 'Count')"
            ]
          },
          "metadata": {},
          "execution_count": 13
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEZCAYAAABmTgnDAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAWLElEQVR4nO3df7DddX3n8efLAOoKliC3bEywSW06FrUN7BVsdaf8GCFgHdTxB+jUrEObdhZ3tbpu0Z1ZWi2zOhbp2LGscU0Fx0pTlTEqLUahdt1R4aIpEJDhLj+WZKKJBn+tFSf0vX+cT5aTm3vv90LvOecm5/mYOXO/5/35fr/nnZmbvPL9fj/f70lVIUnSfJ406gYkSUufYSFJ6mRYSJI6GRaSpE6GhSSp01GjbmAQTjzxxFq9evWo25Ckw8ptt9323aqamG3siAyL1atXMzU1Neo2JOmwkuTBucY8DSVJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqdETewX24WH3Z50fdwhHlgfe8dNQtSEcsjywkSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUybCQJHUyLCRJnQwLSVInw0KS1GlgYZHkKUluSfKPSXYk+eNW/2iS+5Nsb691rZ4kH0gyneT2JKf17WtDknvba8OgepYkzW6QDxJ8BDi7qn6c5GjgK0n+to29vao+OWP984G17XUGcDVwRpITgMuBSaCA25JsraqHB9i7JKnPwI4squfH7e3R7VXzbHIhcG3b7mvA8UlWAOcB26pqXwuIbcD6QfUtSTrUQK9ZJFmWZDuwh94/+F9vQ1e0U01XJXlyq60EHurbfGerzVWf+Vkbk0wlmdq7d++i/1kkaZwNNCyq6tGqWgesAk5P8jzgHcBzgBcAJwB/uEiftamqJqtqcmJiYjF2KUlqhjIbqqq+D9wMrK+q3e1U0yPAXwKnt9V2ASf3bbaq1eaqS5KGZJCzoSaSHN+Wnwq8BPhWuw5BkgAvB+5sm2wF3tBmRb0Q+EFV7QZuBM5NsjzJcuDcVpMkDckgZ0OtAK5JsoxeKG2pqs8luSnJBBBgO/D7bf0bgAuAaeAnwBsBqmpfkncDt7b13lVV+wbYtyRphoGFRVXdDpw6S/3sOdYv4NI5xjYDmxe1QUnSgnkHtySpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoZFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqNLCwSPKUJLck+cckO5L8cauvSfL1JNNJ/jrJMa3+5PZ+uo2v7tvXO1r9niTnDapnSdLsBnlk8QhwdlX9GrAOWJ/khcB7gauq6peAh4FL2vqXAA+3+lVtPZKcAlwEPBdYD/xFkmUD7FuSNMPAwqJ6ftzeHt1eBZwNfLLVrwFe3pYvbO9p4+ckSatfV1WPVNX9wDRw+qD6liQdaqDXLJIsS7Id2ANsA/438P2q2t9W2QmsbMsrgYcA2vgPgGf012fZpv+zNiaZSjK1d+/eQfxxJGlsDTQsqurRqloHrKJ3NPCcAX7WpqqarKrJiYmJQX2MJI2locyGqqrvAzcDvw4cn+SoNrQK2NWWdwEnA7TxnwO+11+fZRtJ0hAMcjbURJLj2/JTgZcAd9MLjVe11TYAn2nLW9t72vhNVVWtflGbLbUGWAvcMqi+JUmHOqp7lSdsBXBNm7n0JGBLVX0uyV3AdUn+BPgm8JG2/keAjyWZBvbRmwFFVe1IsgW4C9gPXFpVjw6wb0nSDAMLi6q6HTh1lvp9zDKbqap+Crx6jn1dAVyx2D1KkhbGO7glSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUybCQJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUaWBhkeTkJDcnuSvJjiRvbvU/SrIryfb2uqBvm3ckmU5yT5Lz+urrW206yWWD6lmSNLujBrjv/cDbquobSY4DbkuyrY1dVVV/2r9yklOAi4DnAs8Evpjkl9vwB4GXADuBW5Nsraq7Bti7JKnPwMKiqnYDu9vyj5LcDaycZ5MLgeuq6hHg/iTTwOltbLqq7gNIcl1b17CQpCEZyjWLJKuBU4Gvt9KbktyeZHOS5a22Eniob7OdrTZXfeZnbEwylWRq7969i/wnkKTxNvCwSHIs8CngLVX1Q+Bq4NnAOnpHHlcuxudU1aaqmqyqyYmJicXYpSSpGeQ1C5IcTS8oPl5Vnwaoqu/0jX8Y+Fx7uws4uW/zVa3GPHVJ0hAMcjZUgI8Ad1fV+/vqK/pWewVwZ1veClyU5MlJ1gBrgVuAW4G1SdYkOYbeRfCtg+pbknSoQR5ZvAj4beCOJNtb7Z3AxUnWAQU8APweQFXtSLKF3oXr/cClVfUoQJI3ATcCy4DNVbVjgH1LkmYY5GyorwCZZeiGeba5ArhilvoN820nSRos7+CWJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSJ8NCktTJsJAkdTIsJEmdFhQWSV60kJok6ci00COLP19gTZJ0BJr3QYJJfh34DWAiyVv7hp5O7wmwkqQx0PXU2WOAY9t6x/XVfwi8alBNSZKWlnnDoqq+DHw5yUer6sEh9SRJWmIW+n0WT06yCVjdv01VnT2IpiRJS8tCw+JvgP8O/A/g0cG1I0laihYaFvur6uqBdiJJWrIWOnX2s0n+fZIVSU448JpvgyQnJ7k5yV1JdiR5c6ufkGRbknvbz+WtniQfSDKd5PYkp/Xta0Nb/94kG57wn1aS9IQs9MjiwD/Qb++rFfCL82yzH3hbVX0jyXHAbUm2Af8O+FJVvSfJZcBlwB8C5wNr2+sM4GrgjBZKlwOT7TNvS7K1qh5eYO+SpH+hBYVFVa15vDuuqt3A7rb8oyR3AyuBC4Ez22rXAH9PLywuBK6tqgK+luT4JCvautuqah9AC5z1wCceb0+SpCdmQWGR5A2z1avq2gVuvxo4Ffg6cFILEoBvAye15ZXAQ32b7Wy1ueozP2MjsBHgWc961kLakiQt0EJPQ72gb/kpwDnAN4DOsEhyLPAp4C1V9cMk/3+sqipJLbzduVXVJmATwOTk5KLsU5LUs9DTUP+h/32S44HrurZLcjS9oPh4VX26lb+TZEVV7W6nmfa0+i7g5L7NV7XaLh47bXWg/vcL6VuStDie6CPK/y8w73WM9A4hPgLcXVXv7xvaymMXzDcAn+mrv6HNinoh8IN2uupG4Nwky9vMqXNbTZI0JAu9ZvFZejORoPcAwV8BtnRs9iLgt4E7kmxvtXcC7wG2JLkEeBB4TRu7AbgAmAZ+ArwRoKr2JXk3cGtb710HLnZLkoZjodcs/rRveT/wYFXtnG+DqvoKkDmGz5ll/QIunWNfm4HNC2tVkrTYFnQaqj1Q8Fv0njy7HPjZIJuSJC0tC/2mvNcAtwCvpnfa6OtJfES5JI2JhZ6G+i/AC6pqD0CSCeCLwCcH1ZgkaelY6GyoJx0IiuZ7j2NbSdJhbqFHFn+X5EYee8TGa+nNXpIkjYGu7+D+JXqP53h7klcCL25DXwU+PujmJElLQ9eRxZ8B7wBod2B/GiDJ89vYywbanSRpSei67nBSVd0xs9hqqwfSkSRpyekKi+PnGXvqYjYiSVq6usJiKsnvziwm+R3gtsG0JElaarquWbwFuD7J63ksHCaBY4BXDLIxSdLSMW9YVNV3gN9IchbwvFb+fFXdNPDOJElLxkK/z+Jm4OYB9yJJWqK8C1uS1MmwkCR1MiwkSZ0MC0lSJ8NCktRpYGGRZHOSPUnu7Kv9UZJdSba31wV9Y+9IMp3kniTn9dXXt9p0kssG1a8kaW6DPLL4KLB+lvpVVbWuvW4ASHIKcBHw3LbNXyRZlmQZ8EHgfOAU4OK2riRpiBb6fRaPW1X9Q5LVC1z9QuC6qnoEuD/JNHB6G5uuqvsAklzX1r1rkduVJM1jFNcs3pTk9naaanmrrQQe6ltnZ6vNVT9Eko1JppJM7d27dxB9S9LYGnZYXA08G1gH7AauXKwdV9WmqpqsqsmJiYnF2q0kiQGehppNe9YUAEk+DHyuvd0FnNy36qpWY566JGlIhnpkkWRF39tXAAdmSm0FLkry5CRrgLXALcCtwNoka5IcQ+8i+NZh9ixJGuCRRZJPAGcCJybZCVwOnJlkHVDAA8DvAVTVjiRb6F243g9cWlWPtv28CbgRWAZsrqodg+pZkjS7Qc6GuniW8kfmWf8K4IpZ6jcANyxia5Kkx8k7uCVJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUybCQJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSJ8NCktRpYGGRZHOSPUnu7KudkGRbknvbz+WtniQfSDKd5PYkp/Vts6Gtf2+SDYPqV5I0t0EeWXwUWD+jdhnwpapaC3ypvQc4H1jbXhuBq6EXLsDlwBnA6cDlBwJGkjQ8AwuLqvoHYN+M8oXANW35GuDlffVrq+drwPFJVgDnAduqal9VPQxs49AAkiQN2LCvWZxUVbvb8reBk9rySuChvvV2ttpc9UMk2ZhkKsnU3r17F7drSRpzI7vAXVUF1CLub1NVTVbV5MTExGLtVpLE8MPiO+30Eu3nnlbfBZzct96qVpurLkkaomGHxVbgwIymDcBn+upvaLOiXgj8oJ2uuhE4N8nydmH73FaTJA3RUYPacZJPAGcCJybZSW9W03uALUkuAR4EXtNWvwG4AJgGfgK8EaCq9iV5N3BrW+9dVTXzorkkacAGFhZVdfEcQ+fMsm4Bl86xn83A5kVsTZL0OHkHtySpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqZFhIkjoZFpKkToaFJKmTYSFJ6mRYSJI6GRaSpE6GhSSpk2EhSepkWEiSOhkWkqROhoUkqZNhIUnqNJKwSPJAkjuSbE8y1WonJNmW5N72c3mrJ8kHkkwnuT3JaaPoWZLG2SiPLM6qqnVVNdneXwZ8qarWAl9q7wHOB9a210bg6qF3KkljbimdhroQuKYtXwO8vK9+bfV8DTg+yYpRNChJ42pUYVHAF5LclmRjq51UVbvb8reBk9rySuChvm13ttpBkmxMMpVkau/evYPqW5LG0lEj+twXV9WuJD8PbEvyrf7Bqqok9Xh2WFWbgE0Ak5OTj2tbSdL8RnJkUVW72s89wPXA6cB3Dpxeaj/3tNV3ASf3bb6q1SRJQzL0sEjytCTHHVgGzgXuBLYCG9pqG4DPtOWtwBvarKgXAj/oO10lSRqCUZyGOgm4PsmBz/+rqvq7JLcCW5JcAjwIvKatfwNwATAN/AR44/BblqTxNvSwqKr7gF+bpf494JxZ6gVcOoTWJElzGNUFbklL3OrLPj/qFo4YD7znpaNu4V9sKd1nIUlaogwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSJ8NCktTJsJAkdTIsJEmdDAtJUifDQpLUybCQJHUyLCRJnQwLSVInw0KS1MmwkCR1MiwkSZ0MC0lSp8MmLJKsT3JPkukkl426H0kaJ4dFWCRZBnwQOB84Bbg4ySmj7UqSxsdhERbA6cB0Vd1XVT8DrgMuHHFPkjQ2jhp1Awu0Enio7/1O4Iz+FZJsBDa2tz9Ocs+QehsHJwLfHXUTXfLeUXegEVnyv5+H0e/mL8w1cLiERaeq2gRsGnUfR6IkU1U1Oeo+pNn4+zkch8tpqF3AyX3vV7WaJGkIDpewuBVYm2RNkmOAi4CtI+5JksbGYXEaqqr2J3kTcCOwDNhcVTtG3NY48fSeljJ/P4cgVTXqHiRJS9zhchpKkjRChoUkqZNhIUnqZFhowZI8c9Q9aHwl+bl5xrzPYsAMCz0eXxt1AxprX0yyfGYxybnA9SPoZ6wYFno8MuoGNNY2ATcnmThQSPI64EPAS0fW1Zg4LO6z0JLhPGuNTFV9OMlPgZva0cRrgd8HzqqqB0ba3BgwLHSQJH/O7KEQ4PghtyMdpKo+1gLjm8D/AV5cVUv6IYJHCsNCM009wTFpoJLcQe8/MgH+FfAMekcZAaqqfnWU/R3pvINbC5LkKcDLqupvRt2LxlOSOR+fDVBVDw6rl3HkBW7NKcmyJBck+RjwIL1zxNKoHA2sqqoH+1/0nkLtWZIBMyx0iCS/meRDwAPAJcBLgDVV9aqRNqZx92fAD2ep/7CNaYBMYx0kyU56Fw6vBv5TVf0oyf1V9ZMRtyadVFV3zCxW1R1JVg+/nfHikYVm+iTwTHqnnF6W5Gk4ZVZLw3yz8Z46tC7GlGGhg1TVW4A1wJXAmcA9wESS1yQ5dpS9aexNJfndmcUkvwPcNoJ+xoqzoTSvJEcD6+l9O+F5VXXiiFvSmEpyEr3HevyMx8JhEjgGeGVV7R5Vb+PAsNCCJXlqVf3TqPvQeEtyFvC89nZHVd00yn7GhWGhgyS5fb5xb3zSUpLk2cDrgIuq6rmj7udI5mwozfTP9C5o/xXwWcAjCS0p7VH5r6UXEs8H/hu906QaII8sdIgkzwEuBl4G3EUvOL5QVftH2pjGWpKN9H4vVwJb2uszVbVmpI2NCcNC80ryWuCDwHur6n2j7kfjK8nPgK8Cb6uqqVa7r6p+cbSdjQdPQ+kQSVbSO6x/BfAw8Af45TIavRXAq4Erk/xrekcWR4+2pfHhkYUOkuTLwHH0/iJ+Cvhe/3hV7RtFX1KSow6cCk2yit51i4uBpwHXV9U7R9nfkc6w0EGSPMBjd2z3/3IceAy0h/waiSTfqKrTZqn/Mr3ZUO8aQVtjw7CQdFhI8s2qOnXUfYwrr1loQdr/3t5eVYc8bkEakokkb51rsKreP8xmxo3PhtJBkvxqki8kuTPJnyRZkeRTwE30ptFKo7IMOJbeNbXZXhogjyw004fpPZ78q/SeCbUduAZ4fVX9dJSNaezt9rrE6HjNQgdJsr2q1vW9dx67loQk+6rqhFH3Ma48stBMT0lyKr3ZTwCP9L+vqm+MrDONu52jbmCceWShgyS5eZ7hqqqzh9aM1GeuqbMaDsNC0mEhyR7gurnGq+o/DrGdseNpKB0iyc8DlwIHHvm8A/hgVe0ZXVcS/8Tc34jn/3oHzLDQQZK8iN5TZj8KXNvK/wa4Jcnrq+p/jao3jb3vVdU1M4tJ/i29Z5lde+gmWiyGhWa6Enh5VX2zr7Y1yfXAh4AzRtOWxM8OLLRJF6+j92DB++k9x0wDZFhopqfPCAoAqmp7Em980ihtSHI5vYcHfhf4a3rXXc8abVvjwbDQTEmyvKoenlE8Ae/412jdDfxP4LeqahogyR+MtqXx4V9+zXQV8IUkv5nkuPY6E/jbNiaNyiuB3cDNST6c5Bweux9IA+bUWR0iyW8B/5mDZ0O9r6o+O7qupJ4kTwMupHc66mx6F7avr6ovjLSxI5xhIemwlWQ5vYvcr62qc0bdz5HMsNBBkvzXeYarqt49tGYkLRmGhQ6S5G2zlJ8GXAI8o6qOHXJLkpYAw0JzalNl30wvKLYAV3oXtzSenDqrQ7Rpsm8FXk/vuyxOmzmVVtJ4MSx0kCTvozdFcRPw/Kr68YhbkrQEeBpKB0nyz8AjwH4Ofjhb6F3gfvpIGpM0UoaFJKmTd3BLkjoZFpKkToaFJKmTYSFJ6vT/AFHMHq7YrfHAAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "relation = ndf.corr()\n",
        "print (relation['LABEL'].sort_values(ascending=False)[:5], '\\n')\n",
        "print (relation['LABEL'].sort_values(ascending=False)[-3:])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dzzmizzLiQ39",
        "outputId": "6847b38b-3db4-4736-ea0e-67f4534447ea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "LABEL       1.000000\n",
            " F_PU11     0.261713\n",
            " S_PU11     0.261028\n",
            "DATETIME    0.088547\n",
            " P_J14      0.072457\n",
            "Name: LABEL, dtype: float64 \n",
            "\n",
            " S_PU5   NaN\n",
            " F_PU9   NaN\n",
            " S_PU9   NaN\n",
            "Name: LABEL, dtype: float64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "ndf.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 364
        },
        "id": "HLFm4NJVjN4G",
        "outputId": "464d50dd-b37b-4778-b5c7-022879537639"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-bb812fa0-a8ab-4c3b-a1a7-34a34aa56097\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>DATETIME</th>\n",
              "      <th>L_T1</th>\n",
              "      <th>L_T2</th>\n",
              "      <th>L_T3</th>\n",
              "      <th>L_T4</th>\n",
              "      <th>L_T5</th>\n",
              "      <th>L_T6</th>\n",
              "      <th>L_T7</th>\n",
              "      <th>F_PU1</th>\n",
              "      <th>S_PU1</th>\n",
              "      <th>F_PU2</th>\n",
              "      <th>S_PU2</th>\n",
              "      <th>F_PU3</th>\n",
              "      <th>S_PU3</th>\n",
              "      <th>F_PU4</th>\n",
              "      <th>S_PU4</th>\n",
              "      <th>F_PU5</th>\n",
              "      <th>S_PU5</th>\n",
              "      <th>F_PU6</th>\n",
              "      <th>S_PU6</th>\n",
              "      <th>F_PU7</th>\n",
              "      <th>S_PU7</th>\n",
              "      <th>F_PU8</th>\n",
              "      <th>S_PU8</th>\n",
              "      <th>F_PU9</th>\n",
              "      <th>S_PU9</th>\n",
              "      <th>F_PU10</th>\n",
              "      <th>S_PU10</th>\n",
              "      <th>F_PU11</th>\n",
              "      <th>S_PU11</th>\n",
              "      <th>F_V2</th>\n",
              "      <th>S_V2</th>\n",
              "      <th>P_J280</th>\n",
              "      <th>P_J269</th>\n",
              "      <th>P_J300</th>\n",
              "      <th>P_J256</th>\n",
              "      <th>P_J289</th>\n",
              "      <th>P_J415</th>\n",
              "      <th>P_J302</th>\n",
              "      <th>P_J306</th>\n",
              "      <th>P_J307</th>\n",
              "      <th>P_J317</th>\n",
              "      <th>P_J14</th>\n",
              "      <th>P_J422</th>\n",
              "      <th>LABEL</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.0</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>2088.000000</td>\n",
              "      <td>2.707446</td>\n",
              "      <td>3.287965</td>\n",
              "      <td>4.204496</td>\n",
              "      <td>3.556232</td>\n",
              "      <td>2.748377</td>\n",
              "      <td>5.368429</td>\n",
              "      <td>3.323352</td>\n",
              "      <td>100.839069</td>\n",
              "      <td>1.0</td>\n",
              "      <td>69.385904</td>\n",
              "      <td>0.730907</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>14.495743</td>\n",
              "      <td>0.421116</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.987656</td>\n",
              "      <td>0.020828</td>\n",
              "      <td>40.695432</td>\n",
              "      <td>0.830979</td>\n",
              "      <td>21.071535</td>\n",
              "      <td>0.593967</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>24.969457</td>\n",
              "      <td>0.809193</td>\n",
              "      <td>0.186754</td>\n",
              "      <td>0.007661</td>\n",
              "      <td>56.359191</td>\n",
              "      <td>0.726837</td>\n",
              "      <td>2.980898</td>\n",
              "      <td>32.413653</td>\n",
              "      <td>27.762849</td>\n",
              "      <td>79.404214</td>\n",
              "      <td>27.772894</td>\n",
              "      <td>82.665293</td>\n",
              "      <td>24.574898</td>\n",
              "      <td>74.463383</td>\n",
              "      <td>24.482049</td>\n",
              "      <td>68.024829</td>\n",
              "      <td>33.906174</td>\n",
              "      <td>29.447544</td>\n",
              "      <td>0.095523</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>1205.940366</td>\n",
              "      <td>1.209627</td>\n",
              "      <td>1.470462</td>\n",
              "      <td>0.681352</td>\n",
              "      <td>0.544905</td>\n",
              "      <td>0.735800</td>\n",
              "      <td>0.177560</td>\n",
              "      <td>0.838134</td>\n",
              "      <td>10.217831</td>\n",
              "      <td>0.0</td>\n",
              "      <td>42.180931</td>\n",
              "      <td>0.443541</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>17.019697</td>\n",
              "      <td>0.493797</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>6.803157</td>\n",
              "      <td>0.142827</td>\n",
              "      <td>18.578030</td>\n",
              "      <td>0.374815</td>\n",
              "      <td>17.442386</td>\n",
              "      <td>0.491150</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>12.176915</td>\n",
              "      <td>0.392984</td>\n",
              "      <td>2.129031</td>\n",
              "      <td>0.087202</td>\n",
              "      <td>36.199971</td>\n",
              "      <td>0.445637</td>\n",
              "      <td>0.006665</td>\n",
              "      <td>5.640353</td>\n",
              "      <td>2.760860</td>\n",
              "      <td>8.475271</td>\n",
              "      <td>2.740362</td>\n",
              "      <td>7.577549</td>\n",
              "      <td>4.712136</td>\n",
              "      <td>10.020099</td>\n",
              "      <td>4.734871</td>\n",
              "      <td>5.631171</td>\n",
              "      <td>4.599987</td>\n",
              "      <td>2.679226</td>\n",
              "      <td>0.293971</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.320000</td>\n",
              "      <td>0.310000</td>\n",
              "      <td>2.880000</td>\n",
              "      <td>1.920000</td>\n",
              "      <td>1.280000</td>\n",
              "      <td>4.770000</td>\n",
              "      <td>0.430000</td>\n",
              "      <td>38.920000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>-0.880000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>2.970000</td>\n",
              "      <td>20.250000</td>\n",
              "      <td>19.440000</td>\n",
              "      <td>66.060000</td>\n",
              "      <td>19.460000</td>\n",
              "      <td>53.940000</td>\n",
              "      <td>13.910000</td>\n",
              "      <td>58.070000</td>\n",
              "      <td>13.640000</td>\n",
              "      <td>51.410000</td>\n",
              "      <td>27.820000</td>\n",
              "      <td>21.320000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>1044.000000</td>\n",
              "      <td>1.650000</td>\n",
              "      <td>2.150000</td>\n",
              "      <td>3.620000</td>\n",
              "      <td>3.130000</td>\n",
              "      <td>2.130000</td>\n",
              "      <td>5.240000</td>\n",
              "      <td>2.660000</td>\n",
              "      <td>94.170000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>47.570000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>29.460000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>2.980000</td>\n",
              "      <td>26.250000</td>\n",
              "      <td>26.640000</td>\n",
              "      <td>71.960000</td>\n",
              "      <td>26.670000</td>\n",
              "      <td>83.860000</td>\n",
              "      <td>20.510000</td>\n",
              "      <td>62.930000</td>\n",
              "      <td>20.400000</td>\n",
              "      <td>66.680000</td>\n",
              "      <td>30.690000</td>\n",
              "      <td>28.430000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>2088.000000</td>\n",
              "      <td>2.820000</td>\n",
              "      <td>3.490000</td>\n",
              "      <td>4.230000</td>\n",
              "      <td>3.550000</td>\n",
              "      <td>2.750000</td>\n",
              "      <td>5.500000</td>\n",
              "      <td>3.280000</td>\n",
              "      <td>96.650000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>93.860000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>49.160000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>34.560000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>30.520000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>69.960000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>2.980000</td>\n",
              "      <td>34.770000</td>\n",
              "      <td>28.150000</td>\n",
              "      <td>75.810000</td>\n",
              "      <td>28.140000</td>\n",
              "      <td>85.190000</td>\n",
              "      <td>23.160000</td>\n",
              "      <td>81.170000</td>\n",
              "      <td>23.050000</td>\n",
              "      <td>68.890000</td>\n",
              "      <td>32.250000</td>\n",
              "      <td>29.830000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>3132.000000</td>\n",
              "      <td>3.780000</td>\n",
              "      <td>4.580000</td>\n",
              "      <td>4.800000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>3.370000</td>\n",
              "      <td>5.500000</td>\n",
              "      <td>4.040000</td>\n",
              "      <td>112.140000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>96.510000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>33.990000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>50.030000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>35.550000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>31.360000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>82.810000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>2.990000</td>\n",
              "      <td>36.100000</td>\n",
              "      <td>29.590000</td>\n",
              "      <td>88.170000</td>\n",
              "      <td>29.570000</td>\n",
              "      <td>86.380000</td>\n",
              "      <td>28.580000</td>\n",
              "      <td>82.650000</td>\n",
              "      <td>28.490000</td>\n",
              "      <td>71.360000</td>\n",
              "      <td>38.230000</td>\n",
              "      <td>31.290000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>4176.000000</td>\n",
              "      <td>5.730000</td>\n",
              "      <td>5.670000</td>\n",
              "      <td>5.430000</td>\n",
              "      <td>4.700000</td>\n",
              "      <td>4.160000</td>\n",
              "      <td>5.500000</td>\n",
              "      <td>5.000000</td>\n",
              "      <td>122.570000</td>\n",
              "      <td>1.0</td>\n",
              "      <td>99.920000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>38.010000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>51.440000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>51.690000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>45.620000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>37.350000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>27.020000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>122.390000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>61.880000</td>\n",
              "      <td>34.260000</td>\n",
              "      <td>94.870000</td>\n",
              "      <td>34.260000</td>\n",
              "      <td>107.950000</td>\n",
              "      <td>71.110000</td>\n",
              "      <td>95.270000</td>\n",
              "      <td>71.110000</td>\n",
              "      <td>93.730000</td>\n",
              "      <td>77.410000</td>\n",
              "      <td>35.680000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-bb812fa0-a8ab-4c3b-a1a7-34a34aa56097')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-bb812fa0-a8ab-4c3b-a1a7-34a34aa56097 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-bb812fa0-a8ab-4c3b-a1a7-34a34aa56097');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ],
            "text/plain": [
              "          DATETIME         L_T1  ...       P_J422        LABEL\n",
              "count  4177.000000  4177.000000  ...  4177.000000  4177.000000\n",
              "mean   2088.000000     2.707446  ...    29.447544     0.095523\n",
              "std    1205.940366     1.209627  ...     2.679226     0.293971\n",
              "min       0.000000     0.320000  ...    21.320000     0.000000\n",
              "25%    1044.000000     1.650000  ...    28.430000     0.000000\n",
              "50%    2088.000000     2.820000  ...    29.830000     0.000000\n",
              "75%    3132.000000     3.780000  ...    31.290000     0.000000\n",
              "max    4176.000000     5.730000  ...    35.680000     1.000000\n",
              "\n",
              "[8 rows x 45 columns]"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "clfr = RandomForestClassifier(n_estimators = 50)\n",
        "clfr.fit(X_train, Y_train.ravel())\n",
        "Y_test_pred = clfr.predict(X_test)\n",
        "print(clfr.score(X_train, Y_train))\n",
        "print(clfr.score(X_test, Y_test))\n",
        "print(classification_report(Y_test, Y_test_pred))\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pjutKORLoew2",
        "outputId": "6dfb9d25-5c96-4d2d-cf08-561ed685a309"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.9986315429353404\n",
            "0.9401913875598086\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.94      1.00      0.97      1134\n",
            "           1       0.96      0.39      0.56       120\n",
            "\n",
            "    accuracy                           0.94      1254\n",
            "   macro avg       0.95      0.69      0.76      1254\n",
            "weighted avg       0.94      0.94      0.93      1254\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_hat_test = clfr.predict(X_test)\n",
        "y_hat_train = clfr.predict(X_train)\n",
        "\n",
        "train_f1 = f1_score(Y_train, y_hat_train)\n",
        "test_f1 = f1_score(Y_test, y_hat_test)\n",
        "\n",
        "print(f\"Train f1 Score: {train_f1}\")\n",
        "print(f\"Test f1 Score: {test_f1}\")\n",
        "clfr.predict_proba(X_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NwRTQuIPt0lu",
        "outputId": "05767d7f-226a-48ba-c436-8fa64fb61049"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Train f1 Score: 0.9927797833935018\n",
            "Test f1 Score: 0.5562130177514794\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[1.  , 0.  ],\n",
              "       [1.  , 0.  ],\n",
              "       [1.  , 0.  ],\n",
              "       ...,\n",
              "       [0.8 , 0.2 ],\n",
              "       [1.  , 0.  ],\n",
              "       [0.98, 0.02]])"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plot_confusion_matrix(clfr, X_test, Y_test, normalize='true',\n",
        "                     display_labels=['NORMAL', 'ATTACK']); \n",
        "confusion_matrix(Y_test,Y_test_pred)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 314
        },
        "id": "ZhJzXl4nrCX7",
        "outputId": "8aa94f4b-00e4-49e9-9c49-7b82dd27fb34"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[1132,    2],\n",
              "       [  73,   47]])"
            ]
          },
          "metadata": {},
          "execution_count": 18
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_unlabeled=pdf\n",
        "pred_probs = clfr.predict_proba(X_unlabeled)\n",
        "pred_probs"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fENgCuMSzdim",
        "outputId": "79f80463-016c-43dd-8e9f-7f352048f92d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.84, 0.16],\n",
              "       [0.72, 0.28],\n",
              "       [0.72, 0.28],\n",
              "       ...,\n",
              "       [0.94, 0.06],\n",
              "       [1.  , 0.  ],\n",
              "       [1.  , 0.  ]])"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        " iterations = 0\n",
        "\n",
        "train_f1s = []\n",
        "test_f1s = []\n",
        "pseudo_labels = [] \n",
        "\n",
        "high_prob = [1] \n",
        "\n",
        "while len(high_prob) > 0:\n",
        "        \n",
        "    clf = RandomForestClassifier(n_estimators = 50)\n",
        "    clf.fit(X_train, Y_train)\n",
        "    y_hat_train = clf.predict(X_train)\n",
        "    y_hat_test = clf.predict(X_test)\n",
        "\n",
        "    train_f1 = f1_score(Y_train, y_hat_train)\n",
        "    test_f1 = f1_score(Y_test, y_hat_test)\n",
        "    print(f\"Iteration {iterations}\")\n",
        "    print(f\"Train f1: {train_f1}\")\n",
        "    print(f\"Test f1: {test_f1}\")\n",
        "    train_f1s.append(train_f1)\n",
        "    test_f1s.append(test_f1)\n",
        "   \n",
        "    print(f\"Now predicting labels for unlabeled data...\")\n",
        "\n",
        "    pred_probs = pd.DataFrame([])\n",
        "    pred_probs = clf.predict_proba(X_unlabeled)   \n",
        "    preds = clf.predict(X_unlabeled)\n",
        "    prob_0 = pred_probs[:,0] \n",
        "    prob_1 = pred_probs[:,1]\n",
        "\n",
        "    df_pred_prob = pd.DataFrame([])\n",
        "    df_pred_prob['preds'] = preds\n",
        "    df_pred_prob['prob_0'] = prob_0\n",
        "    df_pred_prob['prob_1'] = prob_1\n",
        "    df_pred_prob.index = X_unlabeled.index\n",
        "    \n",
        "    high_prob = pd.concat([df_pred_prob.loc[df_pred_prob['prob_0'] > 0.99],\n",
        "                           df_pred_prob.loc[df_pred_prob['prob_1'] > 0.99]],\n",
        "                          axis=0)\n",
        "    \n",
        "    print(f\"{len(high_prob)} high-probability predictions added to training data.\")\n",
        "    \n",
        "    pseudo_labels.append(len(high_prob))\n",
        "    \n",
        "\n",
        "    X_train = pd.concat([X_unlabeled.loc[high_prob.index]], axis=0)\n",
        "    Y_train = pd.concat([high_prob.preds])      \n",
        "    \n",
        "\n",
        "    X_unlabeled = X_unlabeled.drop(index=high_prob.index)\n",
        "    print(f\"{len(X_unlabeled)} unlabeled instances remaining.\\n\")\n",
        "    \n",
        "    iterations += 1 \n",
        "    if train_f1 and test_f1:\n",
        "        break"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YdW38QBksbkR",
        "outputId": "b1b779d4-6b16-4b16-8980-3cd3e4417dda"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Iteration 0\n",
            "Train f1: 1.0\n",
            "Test f1: 0.5443786982248521\n",
            "Now predicting labels for unlabeled data...\n",
            "1011 high-probability predictions added to training data.\n",
            "7750 unlabeled instances remaining.\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plot_confusion_matrix(clf, X_test, Y_test, cmap='Blues', normalize='true',\n",
        "                     display_labels=['NORMAL', 'ATTACK']);"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 279
        },
        "id": "2Ut2_UaCiOJu",
        "outputId": "cfaa73fb-3d06-4aac-a536-6446f2403c4f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        ""
      ],
      "metadata": {
        "id": "i-3z_g4GKgBP"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}