Wzzz
/
NLP

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "991235a0-5e53-4c8c-99ab-fdd24415983a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "495e20b0-5de1-4a37-85dd-549b39fb3562",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_json('SIR_train_set.json')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e9c6b2b8-ac62-428e-a3e7-b08f0a608a93",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>exploitabilityScore</th>\n",
       "      <th>baseScore</th>\n",
       "      <th>impactScore</th>\n",
       "      <th>severity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.9</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.9</td>\n",
       "      <td>9.8</td>\n",
       "      <td>5.9</td>\n",
       "      <td>CRITICAL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.9</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.2</td>\n",
       "      <td>8.1</td>\n",
       "      <td>5.9</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.8</td>\n",
       "      <td>8.8</td>\n",
       "      <td>5.9</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5619</th>\n",
       "      <td>3.9</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5620</th>\n",
       "      <td>2.8</td>\n",
       "      <td>6.1</td>\n",
       "      <td>2.7</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5621</th>\n",
       "      <td>2.8</td>\n",
       "      <td>6.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5622</th>\n",
       "      <td>2.8</td>\n",
       "      <td>6.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5623</th>\n",
       "      <td>2.3</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.7</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5624 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      exploitabilityScore  baseScore  impactScore  severity\n",
       "0                     3.9        7.5          3.6      HIGH\n",
       "1                     3.9        9.8          5.9  CRITICAL\n",
       "2                     3.9        7.5          3.6      HIGH\n",
       "3                     2.2        8.1          5.9      HIGH\n",
       "4                     2.8        8.8          5.9      HIGH\n",
       "...                   ...        ...          ...       ...\n",
       "5619                  3.9        7.5          3.6      HIGH\n",
       "5620                  2.8        6.1          2.7    MEDIUM\n",
       "5621                  2.8        6.5          3.6    MEDIUM\n",
       "5622                  2.8        6.5          3.6    MEDIUM\n",
       "5623                  2.3        5.4          2.7    MEDIUM\n",
       "\n",
       "[5624 rows x 4 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns_1 = ['exploitabilityScore', 'baseScore', 'impactScore', 'severity']\n",
    "train_data = data[columns_1]\n",
    "train_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c2b23c41-5667-4103-ae3e-628bd72c222b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\n",
       "1       CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\n",
       "2       CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\n",
       "3       CVSS:3.0/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H\n",
       "4       CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\n",
       "                            ...                     \n",
       "5619    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H\n",
       "5620    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N\n",
       "5621    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N\n",
       "5622    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N\n",
       "5623    CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:L/A:N\n",
       "Name: vectorString, Length: 5624, dtype: object"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vectorString = data['vectorString']\n",
    "vectorString"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "83092a68-11a6-4a0d-b8d2-447be678076f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'AV': {'network': 2897, 'adjacent': 5516, 'local': 2334},\n",
       " 'AC': {'low': 2659, 'medium': 5396, 'high': 2152},\n",
       " 'Au': {'none': 3904, 'single': 2309, 'multiple': 3674},\n",
       " 'C': {'none': 3904, 'partial': 7704, 'complete': 3143},\n",
       " 'I': {'none': 3904, 'partial': 7704, 'complete': 3143},\n",
       " 'A': {'none': 3904, 'partial': 7704, 'complete': 3143},\n",
       " 'severity': {'low': 2659, 'medium': 5396, 'high': 2152}}"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 打开并读取JSON文件\n",
    "with open('label_word_ids_CVSS2.json', 'r') as file:\n",
    "    # 解析JSON文件\n",
    "    cvss2 = json.load(file)\n",
    "cvss2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "e420f177-ce45-45cf-b1ce-89a8876e6e6e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 打开并读取JSON文件\n",
    "with open('label_word_ids.json', 'r') as file:\n",
    "    # 解析JSON文件\n",
    "    cvss = json.load(file)\n",
    "cvss['AV']\n",
    "len(cvss)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "f32a7cd0-5b49-448d-90f5-1abcb1e13890",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'AV': {'N': 0.20251660258650825,\n",
       "  'A': 0.3855994407549808,\n",
       "  'L': 0.1631597343586159,\n",
       "  'P': 0.24872422229989516},\n",
       " 'AC': {'L': 0.5526917480773228, 'H': 0.4473082519226772},\n",
       " 'PR': {'N': 0.44796328169822147,\n",
       "  'L': 0.3051061388410786,\n",
       "  'H': 0.24693057946069993},\n",
       " 'UI': {'N': 0.5477760628595482, 'R': 0.4522239371404518},\n",
       " 'S': {'U': 0.8439380911435942, 'C': 0.15606190885640583},\n",
       " 'C': {'N': 0.44796328169822147,\n",
       "  'L': 0.3051061388410786,\n",
       "  'H': 0.24693057946069993},\n",
       " 'I': {'N': 0.44796328169822147,\n",
       "  'L': 0.3051061388410786,\n",
       "  'H': 0.24693057946069993},\n",
       " 'A': {'N': 0.44796328169822147,\n",
       "  'L': 0.3051061388410786,\n",
       "  'H': 0.24693057946069993},\n",
       " 'severity': {'low': 0.18472974850632207,\n",
       "  'medium': 0.37487842156454076,\n",
       "  'high': 0.14950673891899402,\n",
       "  'critical': 0.2908850910101431}}"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns_2 = ['AV', 'AC', 'PR', 'UI', 'S', 'C', 'I', 'A']\n",
    "for column in columns_2:\n",
    "    cvss[column] = {k[0].upper(): v for k, v in cvss[column].items()}\n",
    "# 计算每一行的总值\n",
    "summ = {key: sum(values.values()) for key, values in cvss.items()}\n",
    "\n",
    "# 计算每个值除以总值\n",
    "cvss = {\n",
    "    key: {subkey: value / summ[key] for subkey, value in values.items()}\n",
    "    for key, values in cvss.items()\n",
    "}\n",
    "cvss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "34b69fad-1643-4732-9184-8411eb99e314",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>AV</th>\n",
       "      <th>AC</th>\n",
       "      <th>PR</th>\n",
       "      <th>UI</th>\n",
       "      <th>S</th>\n",
       "      <th>C</th>\n",
       "      <th>I</th>\n",
       "      <th>A</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>U</td>\n",
       "      <td>H</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>U</td>\n",
       "      <td>H</td>\n",
       "      <td>H</td>\n",
       "      <td>H</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>U</td>\n",
       "      <td>H</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>N</td>\n",
       "      <td>H</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>U</td>\n",
       "      <td>H</td>\n",
       "      <td>H</td>\n",
       "      <td>H</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>R</td>\n",
       "      <td>U</td>\n",
       "      <td>H</td>\n",
       "      <td>H</td>\n",
       "      <td>H</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5619</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>U</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>H</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5620</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>R</td>\n",
       "      <td>C</td>\n",
       "      <td>L</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5621</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>R</td>\n",
       "      <td>U</td>\n",
       "      <td>N</td>\n",
       "      <td>H</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5622</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "      <td>R</td>\n",
       "      <td>U</td>\n",
       "      <td>N</td>\n",
       "      <td>H</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5623</th>\n",
       "      <td>N</td>\n",
       "      <td>L</td>\n",
       "      <td>L</td>\n",
       "      <td>R</td>\n",
       "      <td>C</td>\n",
       "      <td>L</td>\n",
       "      <td>L</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5624 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     AV AC PR UI  S  C  I  A\n",
       "0     N  L  N  N  U  H  N  N\n",
       "1     N  L  N  N  U  H  H  H\n",
       "2     N  L  N  N  U  H  N  N\n",
       "3     N  H  N  N  U  H  H  H\n",
       "4     N  L  N  R  U  H  H  H\n",
       "...  .. .. .. .. .. .. .. ..\n",
       "5619  N  L  N  N  U  N  N  H\n",
       "5620  N  L  N  R  C  L  L  N\n",
       "5621  N  L  N  R  U  N  H  N\n",
       "5622  N  L  N  R  U  N  H  N\n",
       "5623  N  L  L  R  C  L  L  N\n",
       "\n",
       "[5624 rows x 8 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#转换数据\n",
    "def transform_value(val):\n",
    "    return val.split(':')[1]\n",
    "temp = []\n",
    "for i in range(vectorString.size):\n",
    "    part =  vectorString[i].split('/')\n",
    "    list_items = part[1::]\n",
    "    temp.append(list_items)\n",
    "train_data_temp = pd.DataFrame(temp, columns=columns_2)\n",
    "train_data_temp = train_data_temp.applymap(transform_value)\n",
    "train_data_temp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "ad6d24ea-2f6b-465c-9516-77bd88f0d01b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>AV</th>\n",
       "      <th>AC</th>\n",
       "      <th>PR</th>\n",
       "      <th>UI</th>\n",
       "      <th>S</th>\n",
       "      <th>C</th>\n",
       "      <th>I</th>\n",
       "      <th>A</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.447963</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.447963</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.447308</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5619</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.246931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5620</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.156062</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.447963</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5621</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5622</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5623</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.156062</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.447963</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5624 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            AV        AC        PR        UI         S         C         I  \\\n",
       "0     0.202517  0.552692  0.447963  0.547776  0.843938  0.246931  0.447963   \n",
       "1     0.202517  0.552692  0.447963  0.547776  0.843938  0.246931  0.246931   \n",
       "2     0.202517  0.552692  0.447963  0.547776  0.843938  0.246931  0.447963   \n",
       "3     0.202517  0.447308  0.447963  0.547776  0.843938  0.246931  0.246931   \n",
       "4     0.202517  0.552692  0.447963  0.452224  0.843938  0.246931  0.246931   \n",
       "...        ...       ...       ...       ...       ...       ...       ...   \n",
       "5619  0.202517  0.552692  0.447963  0.547776  0.843938  0.447963  0.447963   \n",
       "5620  0.202517  0.552692  0.447963  0.452224  0.156062  0.305106  0.305106   \n",
       "5621  0.202517  0.552692  0.447963  0.452224  0.843938  0.447963  0.246931   \n",
       "5622  0.202517  0.552692  0.447963  0.452224  0.843938  0.447963  0.246931   \n",
       "5623  0.202517  0.552692  0.305106  0.452224  0.156062  0.305106  0.305106   \n",
       "\n",
       "             A  \n",
       "0     0.447963  \n",
       "1     0.246931  \n",
       "2     0.447963  \n",
       "3     0.246931  \n",
       "4     0.246931  \n",
       "...        ...  \n",
       "5619  0.246931  \n",
       "5620  0.447963  \n",
       "5621  0.447963  \n",
       "5622  0.447963  \n",
       "5623  0.447963  \n",
       "\n",
       "[5624 rows x 8 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 替换 DataFrame 中的值\n",
    "train_data_temp.replace(cvss, inplace=True)\n",
    "train_data_temp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "d33ba418-4964-4d8b-8410-e420cde1589b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>AV</th>\n",
       "      <th>AC</th>\n",
       "      <th>PR</th>\n",
       "      <th>UI</th>\n",
       "      <th>S</th>\n",
       "      <th>C</th>\n",
       "      <th>I</th>\n",
       "      <th>A</th>\n",
       "      <th>exploitabilityScore</th>\n",
       "      <th>baseScore</th>\n",
       "      <th>impactScore</th>\n",
       "      <th>severity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>3.9</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>3.9</td>\n",
       "      <td>9.8</td>\n",
       "      <td>5.9</td>\n",
       "      <td>CRITICAL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>3.9</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.447308</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>2.2</td>\n",
       "      <td>8.1</td>\n",
       "      <td>5.9</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>2.8</td>\n",
       "      <td>8.8</td>\n",
       "      <td>5.9</td>\n",
       "      <td>HIGH</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5619</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.547776</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>3.9</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>HIGH</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5620</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.156062</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>2.8</td>\n",
       "      <td>6.1</td>\n",
       "      <td>2.7</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5621</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>2.8</td>\n",
       "      <td>6.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5622</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.843938</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>0.246931</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>2.8</td>\n",
       "      <td>6.5</td>\n",
       "      <td>3.6</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5623</th>\n",
       "      <td>0.202517</td>\n",
       "      <td>0.552692</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.452224</td>\n",
       "      <td>0.156062</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.305106</td>\n",
       "      <td>0.447963</td>\n",
       "      <td>2.3</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.7</td>\n",
       "      <td>MEDIUM</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5624 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            AV        AC        PR        UI         S         C         I  \\\n",
       "0     0.202517  0.552692  0.447963  0.547776  0.843938  0.246931  0.447963   \n",
       "1     0.202517  0.552692  0.447963  0.547776  0.843938  0.246931  0.246931   \n",
       "2     0.202517  0.552692  0.447963  0.547776  0.843938  0.246931  0.447963   \n",
       "3     0.202517  0.447308  0.447963  0.547776  0.843938  0.246931  0.246931   \n",
       "4     0.202517  0.552692  0.447963  0.452224  0.843938  0.246931  0.246931   \n",
       "...        ...       ...       ...       ...       ...       ...       ...   \n",
       "5619  0.202517  0.552692  0.447963  0.547776  0.843938  0.447963  0.447963   \n",
       "5620  0.202517  0.552692  0.447963  0.452224  0.156062  0.305106  0.305106   \n",
       "5621  0.202517  0.552692  0.447963  0.452224  0.843938  0.447963  0.246931   \n",
       "5622  0.202517  0.552692  0.447963  0.452224  0.843938  0.447963  0.246931   \n",
       "5623  0.202517  0.552692  0.305106  0.452224  0.156062  0.305106  0.305106   \n",
       "\n",
       "             A  exploitabilityScore  baseScore  impactScore  severity  \n",
       "0     0.447963                  3.9        7.5          3.6      HIGH  \n",
       "1     0.246931                  3.9        9.8          5.9  CRITICAL  \n",
       "2     0.447963                  3.9        7.5          3.6      HIGH  \n",
       "3     0.246931                  2.2        8.1          5.9      HIGH  \n",
       "4     0.246931                  2.8        8.8          5.9      HIGH  \n",
       "...        ...                  ...        ...          ...       ...  \n",
       "5619  0.246931                  3.9        7.5          3.6      HIGH  \n",
       "5620  0.447963                  2.8        6.1          2.7    MEDIUM  \n",
       "5621  0.447963                  2.8        6.5          3.6    MEDIUM  \n",
       "5622  0.447963                  2.8        6.5          3.6    MEDIUM  \n",
       "5623  0.447963                  2.3        5.4          2.7    MEDIUM  \n",
       "\n",
       "[5624 rows x 12 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data = pd.concat([train_data_temp, train_data], axis=1)\n",
    "train_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1d4077ea-ab43-4bd6-9a19-e74c98cad80d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}