{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "name": "#%% Imporintg packages\n"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "from sklearn.preprocessing import OrdinalEncoder\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import *\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "pycharm": {
     "name": "#%% Reading befign dataset\n"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('D://OneDrive - Higher Education Commission//Collaborations//Daud Khan//Paper02//CICBellEXFDNS2021//Attack_heavy_Benign - Copy//Dataset-stateless_attack_heavyAll.csv', header=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "pycharm": {
     "name": "#%% Printing dataset summary\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "       timestamp  FQDN_count  subdomain_length  upper  lower  numeric  \\\n0        52:31.2          25                 8      0     10        9   \n1        52:31.7          25                 8      0     10        9   \n2        52:31.9          15                 0     11      0        3   \n3        52:32.1          24                 7      0     10        8   \n4        52:32.5          24                 7      0     10        8   \n...          ...         ...               ...    ...    ...      ...   \n433359   53:18.0          26                 9      0     10       10   \n433360   53:18.4          27                10      0     10       11   \n433361   53:18.8          27                10      0     10       11   \n433362   53:20.1          24                 7      0     10        8   \n433363   53:20.5          24                 7      0     10        8   \n\n         entropy  special  labels  labels_max  labels_average longest_word  \\\n0       2.556642        6       6           7        3.333333            2   \n1       2.556642        6       6           7        3.333333            2   \n2       3.625000        1       1          15       15.000000            C   \n3       2.054029        6       6           7        3.166667            4   \n4       2.054029        6       6           7        3.166667            4   \n...          ...      ...     ...         ...             ...          ...   \n433359  2.742338        6       6           7        3.500000            2   \n433360  2.767195        6       6           7        3.666667            2   \n433361  2.767195        6       6           7        3.666667            2   \n433362  2.054029        6       6           7        3.166667            4   \n433363  2.054029        6       6           7        3.166667            4   \n\n                    sld  len  subdomain  Class  \n0                   192   12          1      1  \n1                   192   12          1      1  \n2       DESKTOP-3JF04TC   16          0      1  \n3                   224   11          1      1  \n4                   224   11          1      1  \n...                 ...  ...        ...    ...  \n433359              192   13          1      0  \n433360              192   14          1      0  \n433361              192   14          1      0  \n433362              224   11          1      0  \n433363              224   11          1      0  \n\n[433364 rows x 16 columns]",
      "text/html": "<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>timestamp</th>\n      <th>FQDN_count</th>\n      <th>subdomain_length</th>\n      <th>upper</th>\n      <th>lower</th>\n      <th>numeric</th>\n      <th>entropy</th>\n      <th>special</th>\n      <th>labels</th>\n      <th>labels_max</th>\n      <th>labels_average</th>\n      <th>longest_word</th>\n      <th>sld</th>\n      <th>len</th>\n      <th>subdomain</th>\n      <th>Class</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>52:31.2</td>\n      <td>25</td>\n      <td>8</td>\n      <td>0</td>\n      <td>10</td>\n      <td>9</td>\n      <td>2.556642</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.333333</td>\n      <td>2</td>\n      <td>192</td>\n      <td>12</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>52:31.7</td>\n      <td>25</td>\n      <td>8</td>\n      <td>0</td>\n      <td>10</td>\n      <td>9</td>\n      <td>2.556642</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.333333</td>\n      <td>2</td>\n      <td>192</td>\n      <td>12</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>52:31.9</td>\n      <td>15</td>\n      <td>0</td>\n      <td>11</td>\n      <td>0</td>\n      <td>3</td>\n      <td>3.625000</td>\n      <td>1</td>\n      <td>1</td>\n      <td>15</td>\n      <td>15.000000</td>\n      <td>C</td>\n      <td>DESKTOP-3JF04TC</td>\n      <td>16</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>52:32.1</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>224</td>\n      <td>11</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>52:32.5</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>224</td>\n      <td>11</td>\n      <td>1</td>\n      <td>1</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    </tr>\n    <tr>\n      <th>433359</th>\n      <td>53:18.0</td>\n      <td>26</td>\n      <td>9</td>\n      <td>0</td>\n      <td>10</td>\n      <td>10</td>\n      <td>2.742338</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.500000</td>\n      <td>2</td>\n      <td>192</td>\n      <td>13</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433360</th>\n      <td>53:18.4</td>\n      <td>27</td>\n      <td>10</td>\n      <td>0</td>\n      <td>10</td>\n      <td>11</td>\n      <td>2.767195</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.666667</td>\n      <td>2</td>\n      <td>192</td>\n      <td>14</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433361</th>\n      <td>53:18.8</td>\n      <td>27</td>\n      <td>10</td>\n      <td>0</td>\n      <td>10</td>\n      <td>11</td>\n      <td>2.767195</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.666667</td>\n      <td>2</td>\n      <td>192</td>\n      <td>14</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433362</th>\n      <td>53:20.1</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>224</td>\n      <td>11</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433363</th>\n      <td>53:20.5</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>224</td>\n      <td>11</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>433364 rows × 16 columns</p>\n</div>"
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "pycharm": {
     "name": "#%% Printing dataset header\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "  timestamp  FQDN_count  subdomain_length  upper  lower  numeric   entropy  \\\n0   52:31.2          25                 8      0     10        9  2.556642   \n1   52:31.7          25                 8      0     10        9  2.556642   \n2   52:31.9          15                 0     11      0        3  3.625000   \n3   52:32.1          24                 7      0     10        8  2.054029   \n4   52:32.5          24                 7      0     10        8  2.054029   \n\n   special  labels  labels_max  labels_average longest_word              sld  \\\n0        6       6           7        3.333333            2              192   \n1        6       6           7        3.333333            2              192   \n2        1       1          15       15.000000            C  DESKTOP-3JF04TC   \n3        6       6           7        3.166667            4              224   \n4        6       6           7        3.166667            4              224   \n\n   len  subdomain  Class  \n0   12          1      1  \n1   12          1      1  \n2   16          0      1  \n3   11          1      1  \n4   11          1      1  ",
      "text/html": "<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>timestamp</th>\n      <th>FQDN_count</th>\n      <th>subdomain_length</th>\n      <th>upper</th>\n      <th>lower</th>\n      <th>numeric</th>\n      <th>entropy</th>\n      <th>special</th>\n      <th>labels</th>\n      <th>labels_max</th>\n      <th>labels_average</th>\n      <th>longest_word</th>\n      <th>sld</th>\n      <th>len</th>\n      <th>subdomain</th>\n      <th>Class</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>52:31.2</td>\n      <td>25</td>\n      <td>8</td>\n      <td>0</td>\n      <td>10</td>\n      <td>9</td>\n      <td>2.556642</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.333333</td>\n      <td>2</td>\n      <td>192</td>\n      <td>12</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>52:31.7</td>\n      <td>25</td>\n      <td>8</td>\n      <td>0</td>\n      <td>10</td>\n      <td>9</td>\n      <td>2.556642</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.333333</td>\n      <td>2</td>\n      <td>192</td>\n      <td>12</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>52:31.9</td>\n      <td>15</td>\n      <td>0</td>\n      <td>11</td>\n      <td>0</td>\n      <td>3</td>\n      <td>3.625000</td>\n      <td>1</td>\n      <td>1</td>\n      <td>15</td>\n      <td>15.000000</td>\n      <td>C</td>\n      <td>DESKTOP-3JF04TC</td>\n      <td>16</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>52:32.1</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>224</td>\n      <td>11</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>52:32.5</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>224</td>\n      <td>11</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "pycharm": {
     "name": "#%% Printing dataset information\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 433364 entries, 0 to 433363\n",
      "Data columns (total 16 columns):\n",
      " #   Column            Non-Null Count   Dtype  \n",
      "---  ------            --------------   -----  \n",
      " 0   timestamp         433364 non-null  object \n",
      " 1   FQDN_count        433364 non-null  int64  \n",
      " 2   subdomain_length  433364 non-null  int64  \n",
      " 3   upper             433364 non-null  int64  \n",
      " 4   lower             433364 non-null  int64  \n",
      " 5   numeric           433364 non-null  int64  \n",
      " 6   entropy           433364 non-null  float64\n",
      " 7   special           433364 non-null  int64  \n",
      " 8   labels            433364 non-null  int64  \n",
      " 9   labels_max        433364 non-null  int64  \n",
      " 10  labels_average    433364 non-null  float64\n",
      " 11  longest_word      433354 non-null  object \n",
      " 12  sld               433364 non-null  object \n",
      " 13  len               433364 non-null  int64  \n",
      " 14  subdomain         433364 non-null  int64  \n",
      " 15  Class             433364 non-null  int64  \n",
      "dtypes: float64(2), int64(11), object(3)\n",
      "memory usage: 52.9+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "pycharm": {
     "name": "#%% Selection of columns for encoding\n"
    }
   },
   "outputs": [],
   "source": [
    "cat_cols=['timestamp','longest_word','sld']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "pycharm": {
     "name": "#%% Selection of encoder\n"
    }
   },
   "outputs": [],
   "source": [
    "encoder = OrdinalEncoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "pd.options.mode.chained_assignment = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "pycharm": {
     "name": "#%% Data ending function for IP addresses and dateTime columns\n"
    }
   },
   "outputs": [],
   "source": [
    "def encode(data):\n",
    "    '''function to encode non-null data and replace it in the original data'''\n",
    "    #retains only non-null values\n",
    "    nonulls = np.array(data.dropna())\n",
    "    #reshapes the data for encoding\n",
    "    impute_reshape = nonulls.reshape(-1,1)\n",
    "    #encode date\n",
    "    impute_ordinal = encoder.fit_transform(impute_reshape)\n",
    "    #Assign back encoded values to non-null values\n",
    "    data.loc[data.notnull()] = np.squeeze(impute_ordinal)\n",
    "    return data\n",
    "#create a for loop to iterate through each column in the data\n",
    "for columns in cat_cols:\n",
    "    encode(df[columns])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "pycharm": {
     "name": "#%% Printing dataset header\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 433364 entries, 0 to 433363\n",
      "Data columns (total 16 columns):\n",
      " #   Column            Non-Null Count   Dtype  \n",
      "---  ------            --------------   -----  \n",
      " 0   timestamp         433364 non-null  float64\n",
      " 1   FQDN_count        433364 non-null  int64  \n",
      " 2   subdomain_length  433364 non-null  int64  \n",
      " 3   upper             433364 non-null  int64  \n",
      " 4   lower             433364 non-null  int64  \n",
      " 5   numeric           433364 non-null  int64  \n",
      " 6   entropy           433364 non-null  float64\n",
      " 7   special           433364 non-null  int64  \n",
      " 8   labels            433364 non-null  int64  \n",
      " 9   labels_max        433364 non-null  int64  \n",
      " 10  labels_average    433364 non-null  float64\n",
      " 11  longest_word      433354 non-null  object \n",
      " 12  sld               433364 non-null  float64\n",
      " 13  len               433364 non-null  int64  \n",
      " 14  subdomain         433364 non-null  int64  \n",
      " 15  Class             433364 non-null  int64  \n",
      "dtypes: float64(4), int64(11), object(1)\n",
      "memory usage: 52.9+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "pycharm": {
     "name": "#%% Removinf NA values\n"
    }
   },
   "outputs": [],
   "source": [
    "df=df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "pycharm": {
     "name": "#%% Selection of features from the dataset\n"
    }
   },
   "outputs": [],
   "source": [
    "X=df.loc[1:,:'subdomain']\n",
    "y=df.loc[1:,'Class']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "pycharm": {
     "name": "#%% Splitting the dataset into train and test parts\n"
    }
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.33, random_state = 42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "outputs": [
    {
     "data": {
      "text/plain": "        timestamp  FQDN_count  subdomain_length  upper  lower  numeric  \\\n0         31504.0          25                 8      0     10        9   \n1         31509.0          25                 8      0     10        9   \n2         31511.0          15                 0     11      0        3   \n3         31513.0          24                 7      0     10        8   \n4         31517.0          24                 7      0     10        8   \n...           ...         ...               ...    ...    ...      ...   \n433359    31972.0          26                 9      0     10       10   \n433360    31976.0          27                10      0     10       11   \n433361    31980.0          27                10      0     10       11   \n433362    31993.0          24                 7      0     10        8   \n433363    31997.0          24                 7      0     10        8   \n\n         entropy  special  labels  labels_max  labels_average longest_word  \\\n0       2.556642        6       6           7        3.333333            2   \n1       2.556642        6       6           7        3.333333            2   \n2       3.625000        1       1          15       15.000000           11   \n3       2.054029        6       6           7        3.166667            4   \n4       2.054029        6       6           7        3.166667            4   \n...          ...      ...     ...         ...             ...          ...   \n433359  2.742338        6       6           7        3.500000            2   \n433360  2.767195        6       6           7        3.666667            2   \n433361  2.767195        6       6           7        3.666667            2   \n433362  2.054029        6       6           7        3.166667            4   \n433363  2.054029        6       6           7        3.166667            4   \n\n          sld  len  subdomain  Class  \n0       110.0   12          1      1  \n1       110.0   12          1      1  \n2       467.0   16          0      1  \n3       178.0   11          1      1  \n4       178.0   11          1      1  \n...       ...  ...        ...    ...  \n433359  110.0   13          1      0  \n433360  110.0   14          1      0  \n433361  110.0   14          1      0  \n433362  178.0   11          1      0  \n433363  178.0   11          1      0  \n\n[433354 rows x 16 columns]",
      "text/html": "<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>timestamp</th>\n      <th>FQDN_count</th>\n      <th>subdomain_length</th>\n      <th>upper</th>\n      <th>lower</th>\n      <th>numeric</th>\n      <th>entropy</th>\n      <th>special</th>\n      <th>labels</th>\n      <th>labels_max</th>\n      <th>labels_average</th>\n      <th>longest_word</th>\n      <th>sld</th>\n      <th>len</th>\n      <th>subdomain</th>\n      <th>Class</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>31504.0</td>\n      <td>25</td>\n      <td>8</td>\n      <td>0</td>\n      <td>10</td>\n      <td>9</td>\n      <td>2.556642</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.333333</td>\n      <td>2</td>\n      <td>110.0</td>\n      <td>12</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>31509.0</td>\n      <td>25</td>\n      <td>8</td>\n      <td>0</td>\n      <td>10</td>\n      <td>9</td>\n      <td>2.556642</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.333333</td>\n      <td>2</td>\n      <td>110.0</td>\n      <td>12</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>31511.0</td>\n      <td>15</td>\n      <td>0</td>\n      <td>11</td>\n      <td>0</td>\n      <td>3</td>\n      <td>3.625000</td>\n      <td>1</td>\n      <td>1</td>\n      <td>15</td>\n      <td>15.000000</td>\n      <td>11</td>\n      <td>467.0</td>\n      <td>16</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>31513.0</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>178.0</td>\n      <td>11</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>31517.0</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>178.0</td>\n      <td>11</td>\n      <td>1</td>\n      <td>1</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    </tr>\n    <tr>\n      <th>433359</th>\n      <td>31972.0</td>\n      <td>26</td>\n      <td>9</td>\n      <td>0</td>\n      <td>10</td>\n      <td>10</td>\n      <td>2.742338</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.500000</td>\n      <td>2</td>\n      <td>110.0</td>\n      <td>13</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433360</th>\n      <td>31976.0</td>\n      <td>27</td>\n      <td>10</td>\n      <td>0</td>\n      <td>10</td>\n      <td>11</td>\n      <td>2.767195</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.666667</td>\n      <td>2</td>\n      <td>110.0</td>\n      <td>14</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433361</th>\n      <td>31980.0</td>\n      <td>27</td>\n      <td>10</td>\n      <td>0</td>\n      <td>10</td>\n      <td>11</td>\n      <td>2.767195</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.666667</td>\n      <td>2</td>\n      <td>110.0</td>\n      <td>14</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433362</th>\n      <td>31993.0</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>178.0</td>\n      <td>11</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>433363</th>\n      <td>31997.0</td>\n      <td>24</td>\n      <td>7</td>\n      <td>0</td>\n      <td>10</td>\n      <td>8</td>\n      <td>2.054029</td>\n      <td>6</td>\n      <td>6</td>\n      <td>7</td>\n      <td>3.166667</td>\n      <td>4</td>\n      <td>178.0</td>\n      <td>11</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>433354 rows × 16 columns</p>\n</div>"
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "outputs": [],
   "source": [
    "df.to_csv('Dataset-stateless_attack_heavyAllProcessed.csv')"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  }
 ],
 "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": "3.6.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}