{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3a7dd7d8",
   "metadata": {},
   "source": [
    "## Import Statement"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "86fc25e6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fac53e88",
   "metadata": {},
   "source": [
    "### read the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "dc33b13b",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"../all_port_labelled.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "31f58fd1",
   "metadata": {
    "scrolled": true
   },
   "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>Unnamed: 0</th>\n",
       "      <th>Index</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>Headline</th>\n",
       "      <th>Details</th>\n",
       "      <th>Severity</th>\n",
       "      <th>Category</th>\n",
       "      <th>Region</th>\n",
       "      <th>Datetime</th>\n",
       "      <th>Year</th>\n",
       "      <th>...</th>\n",
       "      <th>IT</th>\n",
       "      <th>EP</th>\n",
       "      <th>NEW</th>\n",
       "      <th>CSD</th>\n",
       "      <th>RPE</th>\n",
       "      <th>MN</th>\n",
       "      <th>NM</th>\n",
       "      <th>if_labeled</th>\n",
       "      <th>Month</th>\n",
       "      <th>Week</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>Grasberg Mine- Grasberg mine workers extend st...</td>\n",
       "      <td>Media sources indicate that workers at the Gra...</td>\n",
       "      <td>Moderate</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>Indonesia</td>\n",
       "      <td>28/5/17 17:08</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>False</td>\n",
       "      <td>5.0</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>63.0</td>\n",
       "      <td>Indonesia: Undersea internet cables damaged by...</td>\n",
       "      <td>News sources are stating that recent typhoons ...</td>\n",
       "      <td>Minor</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>Indonesia</td>\n",
       "      <td>4/9/17 14:30</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>False</td>\n",
       "      <td>4.0</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 46 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Index  Unnamed: 0.1  \\\n",
       "0         0.0    8.0          34.0   \n",
       "1         1.0   10.0          63.0   \n",
       "\n",
       "                                            Headline  \\\n",
       "0  Grasberg Mine- Grasberg mine workers extend st...   \n",
       "1  Indonesia: Undersea internet cables damaged by...   \n",
       "\n",
       "                                             Details  Severity  \\\n",
       "0  Media sources indicate that workers at the Gra...  Moderate   \n",
       "1  News sources are stating that recent typhoons ...     Minor   \n",
       "\n",
       "              Category     Region       Datetime    Year  ...   IT   EP  NEW  \\\n",
       "0  Mine Workers Strike  Indonesia  28/5/17 17:08  2017.0  ...  0.0  0.0  0.0   \n",
       "1       Travel Warning  Indonesia   4/9/17 14:30  2017.0  ...  0.0  0.0  0.0   \n",
       "\n",
       "   CSD  RPE   MN   NM if_labeled  Month  Week  \n",
       "0  0.0  0.0  0.0  1.0      False    5.0  21.0  \n",
       "1  0.0  0.0  1.0  0.0      False    4.0  14.0  \n",
       "\n",
       "[2 rows x 46 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9bff68c9",
   "metadata": {},
   "source": [
    "### Clean empty data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "41aa751c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "from nltk.tokenize import word_tokenize\n",
    "from nltk.stem import WordNetLemmatizer\n",
    "import string\n",
    "\n",
    "# nltk.download('punkt')\n",
    "# nltk.download('stopwords')\n",
    "# nltk.download('wordnet')\n",
    "\n",
    "\n",
    "def clean_text(text):\n",
    "    # Lowercase\n",
    "    text = text.lower()\n",
    "    # Tokenization\n",
    "    tokens = word_tokenize(text)\n",
    "    # Removing punctuation\n",
    "    tokens = [word for word in tokens if word not in string.punctuation]\n",
    "    # Removing stop words\n",
    "    stop_words = set(stopwords.words(\"english\"))\n",
    "    tokens = [word for word in tokens if word not in stop_words]\n",
    "    # Lemmatization\n",
    "    lemmatizer = WordNetLemmatizer()\n",
    "    tokens = [lemmatizer.lemmatize(word) for word in tokens]\n",
    "\n",
    "    return \" \".join(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6293f613",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package omw-1.4 to\n",
      "[nltk_data]     C:\\Users\\ellay\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package omw-1.4 is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import nltk\n",
    "\n",
    "nltk.download(\"omw-1.4\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fad3210d",
   "metadata": {},
   "source": [
    "### The Details column has an issue\n",
    "\n",
    "some of the data are of the type float and none of the text processing functions can be applied to it therefore we have to process it"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b1799269",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5782 entries, 0 to 5781\n",
      "Data columns (total 2 columns):\n",
      " #   Column    Non-Null Count  Dtype \n",
      "---  ------    --------------  ----- \n",
      " 0   Details   5781 non-null   object\n",
      " 1   Category  5780 non-null   object\n",
      "dtypes: object(2)\n",
      "memory usage: 90.5+ KB\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5782 entries, 0 to 5781\n",
      "Data columns (total 4 columns):\n",
      " #   Column            Non-Null Count  Dtype \n",
      "---  ------            --------------  ----- \n",
      " 0   Details           5781 non-null   object\n",
      " 1   Category          5780 non-null   object\n",
      " 2   Details_cleaned   5781 non-null   object\n",
      " 3   Category_cleaned  5780 non-null   object\n",
      "dtypes: object(4)\n",
      "memory usage: 180.8+ KB\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\AppData\\Local\\Temp\\ipykernel_13216\\1896834377.py:3: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  text_df['Details_cleaned'] = text_df['Details'].apply(lambda x: clean_text(x) if not isinstance(x, float) else None)\n",
      "C:\\Users\\ellay\\AppData\\Local\\Temp\\ipykernel_13216\\1896834377.py:4: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  text_df['Category_cleaned'] = text_df['Category'].apply(lambda x: None if isinstance(x, float) else x)\n"
     ]
    }
   ],
   "source": [
    "text_df = df[[\"Details\", \"Category\"]]\n",
    "text_df.info()\n",
    "text_df[\"Details_cleaned\"] = text_df[\"Details\"].apply(\n",
    "    lambda x: clean_text(x) if not isinstance(x, float) else None\n",
    ")\n",
    "text_df[\"Category_cleaned\"] = text_df[\"Category\"].apply(\n",
    "    lambda x: None if isinstance(x, float) else x\n",
    ")\n",
    "\n",
    "# no_nan_df[no_nan_df[\"Details\"].apply(lambda x: print(type(x)))]\n",
    "# cleaned_df = text_df[text_df[\"Details\"].apply(lambda x: clean_text(x))]\n",
    "# cleaned_df = df['Details'][1:2]\n",
    "# type(no_nan_df[\"Details\"][0])\n",
    "# print(clean_text(no_nan_df[\"Details\"][0]))\n",
    "text_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5fcc3b33",
   "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>Details</th>\n",
       "      <th>Category</th>\n",
       "      <th>Details_cleaned</th>\n",
       "      <th>Category_cleaned</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Media sources indicate that workers at the Gra...</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>medium source indicate worker grasberg mine ex...</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>News sources are stating that recent typhoons ...</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>news source stating recent typhoon impact hong...</td>\n",
       "      <td>Travel Warning</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>The persisting port congestion at Shanghai’s Y...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>persisting port congestion shanghai ’ yangshan...</td>\n",
       "      <td>Port Congestion</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Updated local media sources from Jakarta indic...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>updated local medium source jakarta indicate e...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>According to local police in Jakarta, two expl...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>according local police jakarta two explosion c...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Severe winds have downed billboards and trees ...</td>\n",
       "      <td>Roadway Closure / Disruption, Flooding, Severe...</td>\n",
       "      <td>severe wind downed billboard tree bandung wedn...</td>\n",
       "      <td>Roadway Closure / Disruption, Flooding, Severe...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Local media sources indicated on October 29 th...</td>\n",
       "      <td>Cargo/Warehouse Theft</td>\n",
       "      <td>local medium source indicated october 29 wareh...</td>\n",
       "      <td>Cargo/Warehouse Theft</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Tropical Storm Rumbia had dissipated after tra...</td>\n",
       "      <td>Tropical Cyclone / Storm</td>\n",
       "      <td>tropical storm rumbia dissipated travelling ar...</td>\n",
       "      <td>Tropical Cyclone / Storm</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Tropical Depression Yutu, also referred to as ...</td>\n",
       "      <td>Storm</td>\n",
       "      <td>tropical depression yutu also referred `` '' r...</td>\n",
       "      <td>Storm</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>A magnitude 4.5 earthquake was detected 14 mil...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>magnitude 4.5 earthquake detected 14 mile nort...</td>\n",
       "      <td>Earthquake</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Details  \\\n",
       "0  Media sources indicate that workers at the Gra...   \n",
       "1  News sources are stating that recent typhoons ...   \n",
       "2  The persisting port congestion at Shanghai’s Y...   \n",
       "3  Updated local media sources from Jakarta indic...   \n",
       "4  According to local police in Jakarta, two expl...   \n",
       "5  Severe winds have downed billboards and trees ...   \n",
       "6  Local media sources indicated on October 29 th...   \n",
       "7  Tropical Storm Rumbia had dissipated after tra...   \n",
       "8  Tropical Depression Yutu, also referred to as ...   \n",
       "9  A magnitude 4.5 earthquake was detected 14 mil...   \n",
       "\n",
       "                                            Category  \\\n",
       "0                                Mine Workers Strike   \n",
       "1                                     Travel Warning   \n",
       "2                                    Port Congestion   \n",
       "3                         Bombing, Police Operations   \n",
       "4                         Bombing, Police Operations   \n",
       "5  Roadway Closure / Disruption, Flooding, Severe...   \n",
       "6                              Cargo/Warehouse Theft   \n",
       "7                           Tropical Cyclone / Storm   \n",
       "8                                              Storm   \n",
       "9                                         Earthquake   \n",
       "\n",
       "                                     Details_cleaned  \\\n",
       "0  medium source indicate worker grasberg mine ex...   \n",
       "1  news source stating recent typhoon impact hong...   \n",
       "2  persisting port congestion shanghai ’ yangshan...   \n",
       "3  updated local medium source jakarta indicate e...   \n",
       "4  according local police jakarta two explosion c...   \n",
       "5  severe wind downed billboard tree bandung wedn...   \n",
       "6  local medium source indicated october 29 wareh...   \n",
       "7  tropical storm rumbia dissipated travelling ar...   \n",
       "8  tropical depression yutu also referred `` '' r...   \n",
       "9  magnitude 4.5 earthquake detected 14 mile nort...   \n",
       "\n",
       "                                    Category_cleaned  \n",
       "0                                Mine Workers Strike  \n",
       "1                                     Travel Warning  \n",
       "2                                    Port Congestion  \n",
       "3                         Bombing, Police Operations  \n",
       "4                         Bombing, Police Operations  \n",
       "5  Roadway Closure / Disruption, Flooding, Severe...  \n",
       "6                              Cargo/Warehouse Theft  \n",
       "7                           Tropical Cyclone / Storm  \n",
       "8                                              Storm  \n",
       "9                                         Earthquake  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "processed_data = text_df.dropna()\n",
    "processed_data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d02b4b00",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "857"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "processed_data[\"Category\"].nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9ee856a1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 5780 entries, 0 to 5781\n",
      "Data columns (total 4 columns):\n",
      " #   Column            Non-Null Count  Dtype \n",
      "---  ------            --------------  ----- \n",
      " 0   Details           5780 non-null   object\n",
      " 1   Category          5780 non-null   object\n",
      " 2   Details_cleaned   5780 non-null   object\n",
      " 3   Category_cleaned  5780 non-null   object\n",
      "dtypes: object(4)\n",
      "memory usage: 225.8+ KB\n"
     ]
    }
   ],
   "source": [
    "processed_data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f6d478f",
   "metadata": {},
   "source": [
    "## Process the Category column\n",
    "this is not seldom done as we don't usually process the y of the data\n",
    "However, the category is too complex and requires processing if not the labels are just too much"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "285013d3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "111\n"
     ]
    }
   ],
   "source": [
    "# Create a function that will split the labels into individual\n",
    "import re\n",
    "\n",
    "\n",
    "def split_string(text):\n",
    "    # Split the string using either \"/\" or \",\" as separator\n",
    "    words = re.split(r\"[\\/,]\", text)\n",
    "    # Remove any leading or trailing whitespace from each word\n",
    "    words = [word.strip() for word in words if word.strip()]\n",
    "    return words\n",
    "\n",
    "\n",
    "# Example usage:\n",
    "# input_str = \"Roadway Closure / Disruption, Flooding, Severe Winds, Weather Advisory\"\n",
    "# result = split_string(input_str)\n",
    "# print(result)\n",
    "\n",
    "# create a list to find the number of unique individual labels\n",
    "label_list = []\n",
    "\n",
    "for i in processed_data[\"Category_cleaned\"]:\n",
    "    for j in split_string(i):\n",
    "        if j not in label_list:\n",
    "            label_list.append(j)\n",
    "\n",
    "# print(label)\n",
    "print(len(label_list))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e7b48e8",
   "metadata": {},
   "source": [
    "#### After filtering out the unique labels in the Category column we are still left with 111 labels which is still considered too much"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33234f8c",
   "metadata": {},
   "source": [
    "#### The next step would be to to reduce a data's category label into 1 single label \n",
    "Previously the data looks like Roadway Closure / Disruption, Flooding, Severe... we need to reduce it to 1 single label \n",
    "The next process we are going to use in is that we assume the first label in is the most prominent category then we will remove the other categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "12f9b9b4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 5780 entries, 0 to 5781\n",
      "Data columns (total 5 columns):\n",
      " #   Column            Non-Null Count  Dtype \n",
      "---  ------            --------------  ----- \n",
      " 0   Details           5780 non-null   object\n",
      " 1   Category          5780 non-null   object\n",
      " 2   Details_cleaned   5780 non-null   object\n",
      " 3   Category_cleaned  5780 non-null   object\n",
      " 4   Category_single   5780 non-null   object\n",
      "dtypes: object(5)\n",
      "memory usage: 270.9+ KB\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\AppData\\Local\\Temp\\ipykernel_13216\\2344116627.py:25: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  text_df['Category_single'] = text_df['Category_cleaned'].apply(lambda x: split_and_get_first(x))\n"
     ]
    }
   ],
   "source": [
    "def split_and_get_first(text):\n",
    "    # Split the string using either \"/\" or \",\" as separator\n",
    "    if text == None:\n",
    "        return None\n",
    "    words = re.split(r\"[\\/,]\", text)\n",
    "    # Remove any leading or trailing whitespace from each word\n",
    "    words = [word.strip() for word in words if word.strip()]\n",
    "    # Return the first word after split\n",
    "    if words:\n",
    "        return words[0]\n",
    "    else:\n",
    "        return None\n",
    "\n",
    "\n",
    "def remove_none_rows(df, column_name):\n",
    "    # Iterate through the DataFrame\n",
    "    for index, value in enumerate(df[column_name]):\n",
    "        # Check if the value is None\n",
    "        if value is None:\n",
    "            # Remove the row where the data belongs to\n",
    "            df = df.drop(index, axis=0)\n",
    "    return df\n",
    "\n",
    "\n",
    "# Example usage:\n",
    "# input_str = \"Roadway Closure / Disruption, Flooding, Severe Winds, Weather Advisory\"\n",
    "# result = split_and_get_first(input_str)\n",
    "# print(result)\n",
    "text_df[\"Category_single\"] = text_df[\"Category_cleaned\"].apply(\n",
    "    lambda x: split_and_get_first(x)\n",
    ")\n",
    "result_df = remove_none_rows(text_df, \"Category_cleaned\")\n",
    "result_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "b5931fe1",
   "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>Details</th>\n",
       "      <th>Category</th>\n",
       "      <th>Details_cleaned</th>\n",
       "      <th>Category_cleaned</th>\n",
       "      <th>Category_single</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Media sources indicate that workers at the Gra...</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>medium source indicate worker grasberg mine ex...</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>News sources are stating that recent typhoons ...</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>news source stating recent typhoon impact hong...</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>Travel Warning</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>The persisting port congestion at Shanghai’s Y...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>persisting port congestion shanghai ’ yangshan...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>Port Congestion</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Updated local media sources from Jakarta indic...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>updated local medium source jakarta indicate e...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>Bombing</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>According to local police in Jakarta, two expl...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>according local police jakarta two explosion c...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>Bombing</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Severe winds have downed billboards and trees ...</td>\n",
       "      <td>Roadway Closure / Disruption, Flooding, Severe...</td>\n",
       "      <td>severe wind downed billboard tree bandung wedn...</td>\n",
       "      <td>Roadway Closure / Disruption, Flooding, Severe...</td>\n",
       "      <td>Roadway Closure</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Local media sources indicated on October 29 th...</td>\n",
       "      <td>Cargo/Warehouse Theft</td>\n",
       "      <td>local medium source indicated october 29 wareh...</td>\n",
       "      <td>Cargo/Warehouse Theft</td>\n",
       "      <td>Cargo</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Tropical Storm Rumbia had dissipated after tra...</td>\n",
       "      <td>Tropical Cyclone / Storm</td>\n",
       "      <td>tropical storm rumbia dissipated travelling ar...</td>\n",
       "      <td>Tropical Cyclone / Storm</td>\n",
       "      <td>Tropical Cyclone</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Tropical Depression Yutu, also referred to as ...</td>\n",
       "      <td>Storm</td>\n",
       "      <td>tropical depression yutu also referred `` '' r...</td>\n",
       "      <td>Storm</td>\n",
       "      <td>Storm</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>A magnitude 4.5 earthquake was detected 14 mil...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>magnitude 4.5 earthquake detected 14 mile nort...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>Earthquake</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Multiple sources report that a magnitude 5.5 e...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>multiple source report magnitude 5.5 earthquak...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>Earthquake</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Post-Tropical Cyclone Michael is approximately...</td>\n",
       "      <td>Tropical Cyclone / Storm</td>\n",
       "      <td>post-tropical cyclone michael approximately 18...</td>\n",
       "      <td>Tropical Cyclone / Storm</td>\n",
       "      <td>Tropical Cyclone</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Industry sources indicate on September 11 that...</td>\n",
       "      <td>Workplace Accident</td>\n",
       "      <td>industry source indicate september 11 2 worker...</td>\n",
       "      <td>Workplace Accident</td>\n",
       "      <td>Workplace Accident</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Government sources are reporting a tornado has...</td>\n",
       "      <td>Tornado</td>\n",
       "      <td>government source reporting tornado touched tw...</td>\n",
       "      <td>Tornado</td>\n",
       "      <td>Tornado</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Media sources are informing on September 24 th...</td>\n",
       "      <td>Industrial Action</td>\n",
       "      <td>medium source informing september 24 oil worke...</td>\n",
       "      <td>Industrial Action</td>\n",
       "      <td>Industrial Action</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>A magnitude 4.5 earthquake was detected in cen...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>magnitude 4.5 earthquake detected central taiw...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>Earthquake</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Industry sources indicate on August 31 that th...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>industry source indicate august 31 port durban...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>Port Congestion</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Tropical Depression Gordon continues to weaken...</td>\n",
       "      <td>Storm</td>\n",
       "      <td>tropical depression gordon continues weaken mo...</td>\n",
       "      <td>Storm</td>\n",
       "      <td>Storm</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Local media sources indicated on November 8 th...</td>\n",
       "      <td>Public Safety / Security</td>\n",
       "      <td>local medium source indicated november 8 270 k...</td>\n",
       "      <td>Public Safety / Security</td>\n",
       "      <td>Public Safety</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>The European-Mediterranean Seismological Centr...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>european-mediterranean seismological centre re...</td>\n",
       "      <td>Earthquake</td>\n",
       "      <td>Earthquake</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              Details  \\\n",
       "0   Media sources indicate that workers at the Gra...   \n",
       "1   News sources are stating that recent typhoons ...   \n",
       "2   The persisting port congestion at Shanghai’s Y...   \n",
       "3   Updated local media sources from Jakarta indic...   \n",
       "4   According to local police in Jakarta, two expl...   \n",
       "5   Severe winds have downed billboards and trees ...   \n",
       "6   Local media sources indicated on October 29 th...   \n",
       "7   Tropical Storm Rumbia had dissipated after tra...   \n",
       "8   Tropical Depression Yutu, also referred to as ...   \n",
       "9   A magnitude 4.5 earthquake was detected 14 mil...   \n",
       "10  Multiple sources report that a magnitude 5.5 e...   \n",
       "11  Post-Tropical Cyclone Michael is approximately...   \n",
       "12  Industry sources indicate on September 11 that...   \n",
       "13  Government sources are reporting a tornado has...   \n",
       "14  Media sources are informing on September 24 th...   \n",
       "15  A magnitude 4.5 earthquake was detected in cen...   \n",
       "16  Industry sources indicate on August 31 that th...   \n",
       "17  Tropical Depression Gordon continues to weaken...   \n",
       "18  Local media sources indicated on November 8 th...   \n",
       "19  The European-Mediterranean Seismological Centr...   \n",
       "\n",
       "                                             Category  \\\n",
       "0                                 Mine Workers Strike   \n",
       "1                                      Travel Warning   \n",
       "2                                     Port Congestion   \n",
       "3                          Bombing, Police Operations   \n",
       "4                          Bombing, Police Operations   \n",
       "5   Roadway Closure / Disruption, Flooding, Severe...   \n",
       "6                               Cargo/Warehouse Theft   \n",
       "7                            Tropical Cyclone / Storm   \n",
       "8                                               Storm   \n",
       "9                                          Earthquake   \n",
       "10                                         Earthquake   \n",
       "11                           Tropical Cyclone / Storm   \n",
       "12                                 Workplace Accident   \n",
       "13                                            Tornado   \n",
       "14                                  Industrial Action   \n",
       "15                                         Earthquake   \n",
       "16                                    Port Congestion   \n",
       "17                                              Storm   \n",
       "18                           Public Safety / Security   \n",
       "19                                         Earthquake   \n",
       "\n",
       "                                      Details_cleaned  \\\n",
       "0   medium source indicate worker grasberg mine ex...   \n",
       "1   news source stating recent typhoon impact hong...   \n",
       "2   persisting port congestion shanghai ’ yangshan...   \n",
       "3   updated local medium source jakarta indicate e...   \n",
       "4   according local police jakarta two explosion c...   \n",
       "5   severe wind downed billboard tree bandung wedn...   \n",
       "6   local medium source indicated october 29 wareh...   \n",
       "7   tropical storm rumbia dissipated travelling ar...   \n",
       "8   tropical depression yutu also referred `` '' r...   \n",
       "9   magnitude 4.5 earthquake detected 14 mile nort...   \n",
       "10  multiple source report magnitude 5.5 earthquak...   \n",
       "11  post-tropical cyclone michael approximately 18...   \n",
       "12  industry source indicate september 11 2 worker...   \n",
       "13  government source reporting tornado touched tw...   \n",
       "14  medium source informing september 24 oil worke...   \n",
       "15  magnitude 4.5 earthquake detected central taiw...   \n",
       "16  industry source indicate august 31 port durban...   \n",
       "17  tropical depression gordon continues weaken mo...   \n",
       "18  local medium source indicated november 8 270 k...   \n",
       "19  european-mediterranean seismological centre re...   \n",
       "\n",
       "                                     Category_cleaned      Category_single  \n",
       "0                                 Mine Workers Strike  Mine Workers Strike  \n",
       "1                                      Travel Warning       Travel Warning  \n",
       "2                                     Port Congestion      Port Congestion  \n",
       "3                          Bombing, Police Operations              Bombing  \n",
       "4                          Bombing, Police Operations              Bombing  \n",
       "5   Roadway Closure / Disruption, Flooding, Severe...      Roadway Closure  \n",
       "6                               Cargo/Warehouse Theft                Cargo  \n",
       "7                            Tropical Cyclone / Storm     Tropical Cyclone  \n",
       "8                                               Storm                Storm  \n",
       "9                                          Earthquake           Earthquake  \n",
       "10                                         Earthquake           Earthquake  \n",
       "11                           Tropical Cyclone / Storm     Tropical Cyclone  \n",
       "12                                 Workplace Accident   Workplace Accident  \n",
       "13                                            Tornado              Tornado  \n",
       "14                                  Industrial Action    Industrial Action  \n",
       "15                                         Earthquake           Earthquake  \n",
       "16                                    Port Congestion      Port Congestion  \n",
       "17                                              Storm                Storm  \n",
       "18                           Public Safety / Security        Public Safety  \n",
       "19                                         Earthquake           Earthquake  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_df.head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "9c19b11a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "94"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_df[\"Category_single\"].nunique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "29d4037f",
   "metadata": {},
   "source": [
    "### After taking out the first label in the Category column we are still left with 94 unique labels\n",
    "This is still unacceptable amount of labels the next step we are planning to use is to manually group the labels in more generalize label by using a rule based system"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "10f07d05",
   "metadata": {},
   "outputs": [],
   "source": [
    "### first export the unique labels into excel for better visualization\n",
    "unique_labels_df = pd.DataFrame({\"String\": label_list})\n",
    "file_path = \"label_list.xlsx\"\n",
    "\n",
    "# Save DataFrame to Excel\n",
    "unique_labels_df.to_excel(file_path, index=False)"
   ]
  },
  {
   "attachments": {
    "converstion.png": {
     "image/png": "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"
    }
   },
   "cell_type": "markdown",
   "id": "398e6da8",
   "metadata": {},
   "source": [
    "![converstion.png](attachment:converstion.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "d4357af0",
   "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>Weather</th>\n",
       "      <th>Worker Strike</th>\n",
       "      <th>Administrative Issue</th>\n",
       "      <th>Human Error</th>\n",
       "      <th>Cyber Attack</th>\n",
       "      <th>Terrorism</th>\n",
       "      <th>Accident</th>\n",
       "      <th>Others</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Flooding</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>Workplace Accident</td>\n",
       "      <td>Network Disruption</td>\n",
       "      <td>Bombing</td>\n",
       "      <td>Maritime Accident</td>\n",
       "      <td>Miscellaneous Events</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Severe Winds</td>\n",
       "      <td>Production Halt</td>\n",
       "      <td>Police Operations</td>\n",
       "      <td>Individuals in Focus</td>\n",
       "      <td>Ransomware</td>\n",
       "      <td>Warehouse Theft</td>\n",
       "      <td>Vehicle Accident</td>\n",
       "      <td>Miscellaneous Strikes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Weather Advisory</td>\n",
       "      <td>Protest</td>\n",
       "      <td>Roadway Closure</td>\n",
       "      <td>Military Operations</td>\n",
       "      <td>Data breach</td>\n",
       "      <td>Public Safety</td>\n",
       "      <td>Death</td>\n",
       "      <td>Outbreak of disease</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Tropical Cyclone</td>\n",
       "      <td>Riot</td>\n",
       "      <td>Disruption</td>\n",
       "      <td>Flight Delays</td>\n",
       "      <td>Phishing</td>\n",
       "      <td>Security</td>\n",
       "      <td>Injury</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Storm</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>Cargo</td>\n",
       "      <td>Cancellations</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Organized Crime</td>\n",
       "      <td>Non-industrial Fire</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Weather        Worker Strike Administrative Issue  \\\n",
       "0          Flooding  Mine Workers Strike      Port Congestion   \n",
       "1      Severe Winds      Production Halt    Police Operations   \n",
       "2  Weather Advisory              Protest      Roadway Closure   \n",
       "3  Tropical Cyclone                 Riot           Disruption   \n",
       "4             Storm          Port Strike                Cargo   \n",
       "\n",
       "            Human Error        Cyber Attack        Terrorism  \\\n",
       "0    Workplace Accident  Network Disruption          Bombing   \n",
       "1  Individuals in Focus          Ransomware  Warehouse Theft   \n",
       "2   Military Operations         Data breach    Public Safety   \n",
       "3         Flight Delays            Phishing         Security   \n",
       "4         Cancellations                 NaN  Organized Crime   \n",
       "\n",
       "              Accident                 Others  \n",
       "0    Maritime Accident   Miscellaneous Events  \n",
       "1     Vehicle Accident  Miscellaneous Strikes  \n",
       "2                Death    Outbreak of disease  \n",
       "3               Injury                    NaN  \n",
       "4  Non-industrial Fire                    NaN  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_labels_df = pd.read_excel(\"new_labels.xlsx\")\n",
    "new_labels_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "407189c9",
   "metadata": {},
   "source": [
    "#### convert them into lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "73939327",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "Weather\n",
      "\n",
      "['Flooding', 'Severe Winds', 'Weather Advisory', 'Tropical Cyclone', 'Storm', 'Earthquake', 'Tornado', 'Typhoon', 'Landslide', 'Water', 'Hurricane', 'Wildfire', 'Blizzard', 'Hail']\n",
      "\n",
      "\n",
      "Worker Strike\n",
      "\n",
      "['Mine Workers Strike', 'Production Halt', 'Protest', 'Riot', 'Port Strike', 'General Strike', 'Civil Service Strike', 'Civil Unrest Advisory', 'Cargo Transportation Strike', 'Energy Sector Strike']\n",
      "\n",
      "\n",
      "Administrative Issue\n",
      "\n",
      "['Port Congestion', 'Police Operations', 'Roadway Closure', 'Disruption', 'Cargo', 'Industrial Action', 'Port Disruption', 'Cargo Disruption', 'Power Outage', 'Port Closure', 'Maritime Advisory', 'Train Delays', 'Ground Transportation Advisory', 'Public Transportation Disruption', 'Trade Regulation', 'Customs Regulation', 'Regulatory Advisory', 'Industry Directives', 'Security Advisory', 'Public Holidays', 'Customs Delay', 'Public Health Advisory', 'Detention', 'Aviation Advisory', 'Waterway closure', 'Waterway Closure', 'Plant Closure', 'Border Closure', 'Delay', 'Industrial zone shutdown', 'Trade Restrictions', 'Closure', 'Truck Driving Ban', 'Insolvency', 'Environmental Regulations', 'Postal Disruption', 'Ice Storm', 'Travel Warning']\n",
      "\n",
      "\n",
      "Human Error\n",
      "\n",
      "['Workplace Accident', 'Individuals in Focus', 'Military Operations', 'Flight Delays', 'Cancellations', 'Political Info', 'Event']\n",
      "\n",
      "\n",
      "Cyber Attack\n",
      "\n",
      "['Network Disruption', 'Ransomware', 'Data breach', 'Phishing']\n",
      "\n",
      "\n",
      "Terrorism\n",
      "\n",
      "['Bombing', 'Warehouse Theft', 'Public Safety', 'Security', 'Organized Crime', 'Hazmat Response', 'Piracy', 'Kidnap', 'Shooting', 'Robbery', 'Cargo theft', 'Bomb Detonation', 'Terror Attack', 'Outbreak Of War', 'Militant Action']\n",
      "\n",
      "\n",
      "Accident\n",
      "\n",
      "['Maritime Accident', 'Vehicle Accident', 'Death', 'Injury', 'Non-industrial Fire', 'Chemical Spill', 'Industrial Fire', 'Fuel Disruption', 'Airline Incident', 'Crash', 'Explosion', 'Train Accident', 'Derailment', 'Sewage Disruption', 'Barge Accident', 'Bridge Collapse', 'Structure Collapse', 'Airport Accident', 'Force Majeure', 'Telecom Outage']\n",
      "\n",
      "\n",
      "Others\n",
      "\n",
      "['Miscellaneous Events', 'Miscellaneous Strikes', 'Outbreak of disease']\n"
     ]
    }
   ],
   "source": [
    "new_labels_dict = new_labels_df.to_dict(orient=\"list\")\n",
    "\n",
    "\n",
    "for key, value in new_labels_dict.items():\n",
    "    new_labels_dict[key] = [item for item in value if not pd.isnull(item)]\n",
    "\n",
    "for category in new_labels_dict:\n",
    "    print(\"\\n\")\n",
    "    print(category + \"\\n\")\n",
    "    print(new_labels_dict[category])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8516af0e",
   "metadata": {},
   "source": [
    "### create a new column with the summarized label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "0d316bb4",
   "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>Details</th>\n",
       "      <th>Category</th>\n",
       "      <th>Details_cleaned</th>\n",
       "      <th>Category_cleaned</th>\n",
       "      <th>Category_single</th>\n",
       "      <th>Summarized_label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Media sources indicate that workers at the Gra...</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>medium source indicate worker grasberg mine ex...</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>Mine Workers Strike</td>\n",
       "      <td>Worker Strike</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>News sources are stating that recent typhoons ...</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>news source stating recent typhoon impact hong...</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>Travel Warning</td>\n",
       "      <td>Administrative Issue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>The persisting port congestion at Shanghai’s Y...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>persisting port congestion shanghai ’ yangshan...</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>Port Congestion</td>\n",
       "      <td>Administrative Issue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Updated local media sources from Jakarta indic...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>updated local medium source jakarta indicate e...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>Bombing</td>\n",
       "      <td>Terrorism</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>According to local police in Jakarta, two expl...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>according local police jakarta two explosion c...</td>\n",
       "      <td>Bombing, Police Operations</td>\n",
       "      <td>Bombing</td>\n",
       "      <td>Terrorism</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5777</th>\n",
       "      <td>Intelligence received by Everstream Analytics ...</td>\n",
       "      <td>Ice Storm</td>\n",
       "      <td>intelligence received everstream analytics ind...</td>\n",
       "      <td>Ice Storm</td>\n",
       "      <td>Ice Storm</td>\n",
       "      <td>Administrative Issue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5778</th>\n",
       "      <td>Meteorological sources indicate that a series ...</td>\n",
       "      <td>Roadway Closure / Disruption, Ground Transport...</td>\n",
       "      <td>meteorological source indicate series winter s...</td>\n",
       "      <td>Roadway Closure / Disruption, Ground Transport...</td>\n",
       "      <td>Roadway Closure</td>\n",
       "      <td>Administrative Issue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5779</th>\n",
       "      <td>Industry sources report on December 7 that Svi...</td>\n",
       "      <td>Industrial Action</td>\n",
       "      <td>industry source report december 7 svitzer aust...</td>\n",
       "      <td>Industrial Action</td>\n",
       "      <td>Industrial Action</td>\n",
       "      <td>Administrative Issue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5780</th>\n",
       "      <td>Industry sources indicate on December 14 that ...</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>industry source indicate december 14 worker dp...</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>Worker Strike</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5781</th>\n",
       "      <td>On November 17, Dutch media sources reported t...</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>november 17 dutch medium source reported worke...</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>Port Strike</td>\n",
       "      <td>Worker Strike</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5780 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                Details  \\\n",
       "0     Media sources indicate that workers at the Gra...   \n",
       "1     News sources are stating that recent typhoons ...   \n",
       "2     The persisting port congestion at Shanghai’s Y...   \n",
       "3     Updated local media sources from Jakarta indic...   \n",
       "4     According to local police in Jakarta, two expl...   \n",
       "...                                                 ...   \n",
       "5777  Intelligence received by Everstream Analytics ...   \n",
       "5778  Meteorological sources indicate that a series ...   \n",
       "5779  Industry sources report on December 7 that Svi...   \n",
       "5780  Industry sources indicate on December 14 that ...   \n",
       "5781  On November 17, Dutch media sources reported t...   \n",
       "\n",
       "                                               Category  \\\n",
       "0                                   Mine Workers Strike   \n",
       "1                                        Travel Warning   \n",
       "2                                       Port Congestion   \n",
       "3                            Bombing, Police Operations   \n",
       "4                            Bombing, Police Operations   \n",
       "...                                                 ...   \n",
       "5777                                          Ice Storm   \n",
       "5778  Roadway Closure / Disruption, Ground Transport...   \n",
       "5779                                  Industrial Action   \n",
       "5780                                        Port Strike   \n",
       "5781                                        Port Strike   \n",
       "\n",
       "                                        Details_cleaned  \\\n",
       "0     medium source indicate worker grasberg mine ex...   \n",
       "1     news source stating recent typhoon impact hong...   \n",
       "2     persisting port congestion shanghai ’ yangshan...   \n",
       "3     updated local medium source jakarta indicate e...   \n",
       "4     according local police jakarta two explosion c...   \n",
       "...                                                 ...   \n",
       "5777  intelligence received everstream analytics ind...   \n",
       "5778  meteorological source indicate series winter s...   \n",
       "5779  industry source report december 7 svitzer aust...   \n",
       "5780  industry source indicate december 14 worker dp...   \n",
       "5781  november 17 dutch medium source reported worke...   \n",
       "\n",
       "                                       Category_cleaned      Category_single  \\\n",
       "0                                   Mine Workers Strike  Mine Workers Strike   \n",
       "1                                        Travel Warning       Travel Warning   \n",
       "2                                       Port Congestion      Port Congestion   \n",
       "3                            Bombing, Police Operations              Bombing   \n",
       "4                            Bombing, Police Operations              Bombing   \n",
       "...                                                 ...                  ...   \n",
       "5777                                          Ice Storm            Ice Storm   \n",
       "5778  Roadway Closure / Disruption, Ground Transport...      Roadway Closure   \n",
       "5779                                  Industrial Action    Industrial Action   \n",
       "5780                                        Port Strike          Port Strike   \n",
       "5781                                        Port Strike          Port Strike   \n",
       "\n",
       "          Summarized_label  \n",
       "0            Worker Strike  \n",
       "1     Administrative Issue  \n",
       "2     Administrative Issue  \n",
       "3                Terrorism  \n",
       "4                Terrorism  \n",
       "...                    ...  \n",
       "5777  Administrative Issue  \n",
       "5778  Administrative Issue  \n",
       "5779  Administrative Issue  \n",
       "5780         Worker Strike  \n",
       "5781         Worker Strike  \n",
       "\n",
       "[5780 rows x 6 columns]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_df[\"Summarized_label\"] = None\n",
    "\n",
    "for index, row in result_df.iterrows():\n",
    "    value = row[\"Category_single\"]\n",
    "    for key, values in new_labels_dict.items():\n",
    "        if value in values:\n",
    "            result_df.at[index, \"Summarized_label\"] = key\n",
    "            break  # No need to check other keys if match found\n",
    "result_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "607a0996",
   "metadata": {},
   "source": [
    "## Naive Bayes Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "b8c331bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "\n",
    "# from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.metrics import accuracy_score, classification_report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "ca8d53af",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = result_df[\"Details_cleaned\"]\n",
    "y = result_df[\"Summarized_label\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "432e793e",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "119b6c46",
   "metadata": {},
   "outputs": [],
   "source": [
    "# vectorizer = CountVectorizer()\n",
    "# X_train_vec = vectorizer.fit_transform(X_train)\n",
    "# X_test_vec = vectorizer.transform(X_test)\n",
    "\n",
    "tfidf_vectorizer = TfidfVectorizer(max_features=1000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "18cf6e8e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultinomialNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MultinomialNB()"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "naive_bayes = MultinomialNB()\n",
    "naive_bayes.fit(X_train_tfidf, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "4e4d6e2e",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = naive_bayes.predict(X_test_tfidf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "abd1d4a6",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Naive Bayes model: 0.763840830449827\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.71      0.74      0.72       129\n",
      "Administrative Issue       0.83      0.89      0.86       662\n",
      "        Cyber Attack       0.00      0.00      0.00         4\n",
      "         Human Error       0.00      0.00      0.00        18\n",
      "              Others       0.41      0.24      0.30        79\n",
      "           Terrorism       0.42      0.15      0.23        52\n",
      "             Weather       0.77      0.92      0.84        92\n",
      "       Worker Strike       0.61      0.69      0.65       120\n",
      "\n",
      "            accuracy                           0.76      1156\n",
      "           macro avg       0.47      0.46      0.45      1156\n",
      "        weighted avg       0.73      0.76      0.74      1156\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    }
   ],
   "source": [
    "accuracy = accuracy_score(y_test, predictions)\n",
    "print(\"Accuracy of Naive Bayes model:\", accuracy)\n",
    "print(classification_report(y_test, predictions))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0bb9d98b",
   "metadata": {},
   "source": [
    "Find the optimal Alpha parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "f4eead05",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Alpha: 0.1\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultinomialNB(alpha=0.1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB(alpha=0.1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "MultinomialNB(alpha=0.1)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "param_grid = {\"alpha\": [0.1, 0.5, 1.0, 2.0]}\n",
    "\n",
    "# Initialize the grid search\n",
    "grid_search = GridSearchCV(MultinomialNB(), param_grid, cv=5, scoring=\"accuracy\")\n",
    "\n",
    "# Perform the grid search\n",
    "grid_search.fit(X_train_tfidf, y_train)\n",
    "\n",
    "# Get the best hyperparameters\n",
    "best_alpha = grid_search.best_params_[\"alpha\"]\n",
    "print(\"Best Alpha:\", best_alpha)\n",
    "\n",
    "# Train the model with the best alpha\n",
    "naive_bayes_tuned = MultinomialNB(alpha=best_alpha)\n",
    "naive_bayes_tuned.fit(X_train_tfidf, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c747eab",
   "metadata": {},
   "source": [
    "Change the Alpha to 0.1 and max_features to 4000 for better performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "71d0742f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "b22c1073",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Naive Bayes model: 0.7923875432525952\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.74      0.84      0.79       129\n",
      "Administrative Issue       0.89      0.87      0.88       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.67      0.22      0.33        18\n",
      "              Others       0.45      0.35      0.40        79\n",
      "           Terrorism       0.54      0.40      0.46        52\n",
      "             Weather       0.77      0.93      0.85        92\n",
      "       Worker Strike       0.65      0.75      0.69       120\n",
      "\n",
      "            accuracy                           0.79      1156\n",
      "           macro avg       0.71      0.58      0.60      1156\n",
      "        weighted avg       0.79      0.79      0.79      1156\n",
      "\n",
      "Total Runtime: 0.2993302345275879\n"
     ]
    }
   ],
   "source": [
    "X = result_df[\"Details_cleaned\"]\n",
    "y = result_df[\"Summarized_label\"]\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "start_time = time.time()\n",
    "tfidf_vectorizer = TfidfVectorizer(max_features=4000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)\n",
    "\n",
    "naive_bayes = MultinomialNB(alpha=0.1)\n",
    "naive_bayes.fit(X_train_tfidf, y_train)\n",
    "\n",
    "predictions = naive_bayes.predict(X_test_tfidf)\n",
    "\n",
    "end_time = time.time()\n",
    "total_runtime = end_time - start_time\n",
    "\n",
    "accuracy = accuracy_score(y_test, predictions)\n",
    "print(\"Accuracy of Naive Bayes model:\", accuracy)\n",
    "print(classification_report(y_test, predictions))\n",
    "\n",
    "print(\"Total Runtime:\", total_runtime)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aa011ad5",
   "metadata": {},
   "source": [
    "## Logistic Regression model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "6e735f18",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "e266616c",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "b1314e98",
   "metadata": {},
   "outputs": [],
   "source": [
    "tfidf_vectorizer = TfidfVectorizer(max_features=1000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "87905c28",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = LogisticRegression()\n",
    "model.fit(X_train_tfidf, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "c4bf008a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Logistic Regression Model: 0.7975778546712803\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.79      0.80      0.80       129\n",
      "Administrative Issue       0.83      0.93      0.88       662\n",
      "        Cyber Attack       0.00      0.00      0.00         4\n",
      "         Human Error       0.00      0.00      0.00        18\n",
      "              Others       0.64      0.34      0.45        79\n",
      "           Terrorism       0.46      0.21      0.29        52\n",
      "             Weather       0.84      0.87      0.86        92\n",
      "       Worker Strike       0.69      0.71      0.70       120\n",
      "\n",
      "            accuracy                           0.80      1156\n",
      "           macro avg       0.53      0.48      0.50      1156\n",
      "        weighted avg       0.77      0.80      0.78      1156\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
      "  _warn_prf(average, modifier, msg_start, len(result))\n"
     ]
    }
   ],
   "source": [
    "y_pred = model.predict(X_test_tfidf)\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of Logistic Regression Model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "69b1b25a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n",
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Parameters: {'model__C': 10.0, 'tfidf__max_features': 2000}\n",
      "Accuracy of Tuned Logistic Regression Model: 0.8192041522491349\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.81      0.86      0.83       129\n",
      "Administrative Issue       0.86      0.91      0.88       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.60      0.17      0.26        18\n",
      "              Others       0.61      0.43      0.50        79\n",
      "           Terrorism       0.59      0.42      0.49        52\n",
      "             Weather       0.87      0.90      0.89        92\n",
      "       Worker Strike       0.73      0.75      0.74       120\n",
      "\n",
      "            accuracy                           0.82      1156\n",
      "           macro avg       0.76      0.59      0.63      1156\n",
      "        weighted avg       0.81      0.82      0.81      1156\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    }
   ],
   "source": [
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "param_grid = {\n",
    "    \"tfidf__max_features\": [500, 1000, 2000, 3000, 4000],\n",
    "    \"model__C\": [0.1, 1.0, 10.0],\n",
    "}\n",
    "\n",
    "pipeline = Pipeline([(\"tfidf\", TfidfVectorizer()), (\"model\", LogisticRegression())])\n",
    "\n",
    "grid_search = GridSearchCV(pipeline, param_grid, cv=5, scoring=\"accuracy\")\n",
    "\n",
    "grid_search.fit(X_train, y_train)\n",
    "\n",
    "best_params = grid_search.best_params_\n",
    "print(\"Best Parameters:\", best_params)\n",
    "\n",
    "best_model = grid_search.best_estimator_\n",
    "best_model.fit(X_train, y_train)\n",
    "\n",
    "y_pred = best_model.predict(X_test)\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of Tuned Logistic Regression Model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c74436a2",
   "metadata": {},
   "source": [
    "The best parameters are 'model__C': 10.0, 'tfidf__max_features': 2000"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "7d7e7e31",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Logistic Regression Model: 0.8192041522491349\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.81      0.86      0.83       129\n",
      "Administrative Issue       0.86      0.91      0.88       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.60      0.17      0.26        18\n",
      "              Others       0.61      0.43      0.50        79\n",
      "           Terrorism       0.59      0.42      0.49        52\n",
      "             Weather       0.87      0.90      0.89        92\n",
      "       Worker Strike       0.73      0.75      0.74       120\n",
      "\n",
      "            accuracy                           0.82      1156\n",
      "           macro avg       0.76      0.59      0.63      1156\n",
      "        weighted avg       0.81      0.82      0.81      1156\n",
      "\n",
      "Total Runtime: 1.053201675415039\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ellay\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "start_time = time.time()\n",
    "tfidf_vectorizer = TfidfVectorizer(max_features=2000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)\n",
    "\n",
    "model = LogisticRegression(C=10.0)\n",
    "model.fit(X_train_tfidf, y_train)\n",
    "\n",
    "y_pred = model.predict(X_test_tfidf)\n",
    "\n",
    "end_time = time.time()\n",
    "total_runtime = end_time - start_time\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of Logistic Regression Model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "print(\"Total Runtime:\", total_runtime)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "482d0503",
   "metadata": {},
   "source": [
    "## Support Vector Machine (SVM) model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "9a2b2117",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "f8e29f39",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "246cca7a",
   "metadata": {},
   "outputs": [],
   "source": [
    "tfidf_vectorizer = TfidfVectorizer(max_features=1000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "393b87b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(kernel=&#x27;linear&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(kernel=&#x27;linear&#x27;)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "SVC(kernel='linear')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm_model = SVC(kernel=\"linear\")\n",
    "svm_model.fit(X_train_tfidf, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "fc25cdcf",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = svm_model.predict(X_test_tfidf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "2960279a",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of SVM model: 0.8183391003460208\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.78      0.82      0.80       129\n",
      "Administrative Issue       0.87      0.92      0.89       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.67      0.11      0.19        18\n",
      "              Others       0.62      0.42      0.50        79\n",
      "           Terrorism       0.55      0.31      0.40        52\n",
      "             Weather       0.82      0.90      0.86        92\n",
      "       Worker Strike       0.72      0.80      0.76       120\n",
      "\n",
      "            accuracy                           0.82      1156\n",
      "           macro avg       0.75      0.57      0.60      1156\n",
      "        weighted avg       0.81      0.82      0.80      1156\n",
      "\n"
     ]
    }
   ],
   "source": [
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of SVM model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "4e9fee70",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best C: 10\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "param_grid = {\"C\": [0.1, 1, 10]}\n",
    "svm = SVC()\n",
    "grid_search = GridSearchCV(svm, param_grid, cv=5, scoring=\"accuracy\")\n",
    "grid_search.fit(X_train_tfidf, y_train)\n",
    "best_c = grid_search.best_params_[\"C\"]\n",
    "print(\"Best C:\", best_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "65fd932b-63e8-4041-b7aa-0fae14e48efe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of SVM model: 0.782871972318339\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.72      0.84      0.77       129\n",
      "Administrative Issue       0.86      0.86      0.86       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.62      0.28      0.38        18\n",
      "              Others       0.51      0.46      0.48        79\n",
      "           Terrorism       0.49      0.38      0.43        52\n",
      "             Weather       0.81      0.87      0.84        92\n",
      "       Worker Strike       0.69      0.69      0.69       120\n",
      "\n",
      "            accuracy                           0.78      1156\n",
      "           macro avg       0.71      0.58      0.61      1156\n",
      "        weighted avg       0.78      0.78      0.78      1156\n",
      "\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "tfidf_vectorizer = TfidfVectorizer(max_features=1000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)\n",
    "\n",
    "svm_model = SVC(kernel=\"linear\", C=10)\n",
    "svm_model.fit(X_train_tfidf, y_train)\n",
    "\n",
    "y_pred = svm_model.predict(X_test_tfidf)\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of SVM model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a2843fa9",
   "metadata": {},
   "source": [
    "But when C is set to 10, the accuracy drops, it may be due to overfitting. We will still use the defaul value C=1.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "afffe960",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of SVM model: 0.8217993079584776\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.82      0.86      0.84       129\n",
      "Administrative Issue       0.86      0.93      0.89       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.00      0.00      0.00        18\n",
      "              Others       0.64      0.41      0.50        79\n",
      "           Terrorism       0.61      0.33      0.42        52\n",
      "             Weather       0.83      0.90      0.86        92\n",
      "       Worker Strike       0.71      0.77      0.74       120\n",
      "\n",
      "            accuracy                           0.82      1156\n",
      "           macro avg       0.68      0.55      0.58      1156\n",
      "        weighted avg       0.80      0.82      0.81      1156\n",
      "\n",
      "Total Runtime: 7.0570642948150635\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "start_time = time.time()\n",
    "tfidf_vectorizer = TfidfVectorizer(max_features=2000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)\n",
    "\n",
    "svm_model = SVC(kernel=\"linear\")\n",
    "svm_model.fit(X_train_tfidf, y_train)\n",
    "\n",
    "y_pred = svm_model.predict(X_test_tfidf)\n",
    "\n",
    "end_time = time.time()\n",
    "total_runtime = end_time - start_time\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of SVM model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "print(\"Total Runtime:\", total_runtime)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "deac9dd7",
   "metadata": {},
   "source": [
    "## Random Forest Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "fba3d3c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "390399c2",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "74d99fe7",
   "metadata": {},
   "outputs": [],
   "source": [
    "tfidf_vectorizer = TfidfVectorizer(max_features=1000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "f37ceeae",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-5 {color: black;background-color: white;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" checked><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(random_state=42)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(random_state=42)"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_model = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "rf_model.fit(X_train_tfidf, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "51cbc1c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = rf_model.predict(X_test_tfidf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "688925b0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Random Forest Model: 0.801038062283737\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.77      0.80      0.79       129\n",
      "Administrative Issue       0.84      0.92      0.88       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.50      0.06      0.10        18\n",
      "              Others       0.72      0.39      0.51        79\n",
      "           Terrorism       0.67      0.19      0.30        52\n",
      "             Weather       0.79      0.86      0.82        92\n",
      "       Worker Strike       0.66      0.77      0.71       120\n",
      "\n",
      "            accuracy                           0.80      1156\n",
      "           macro avg       0.74      0.53      0.56      1156\n",
      "        weighted avg       0.79      0.80      0.78      1156\n",
      "\n"
     ]
    }
   ],
   "source": [
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of Random Forest Model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b919b55",
   "metadata": {},
   "source": [
    "Fine tuning by adjusting the hyperparamters. After testing on the hyperparameters, below are the best parameters for this model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "6b4868ef",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Random Forest Model: 0.8070934256055363\n",
      "                      precision    recall  f1-score   support\n",
      "\n",
      "            Accident       0.80      0.79      0.80       129\n",
      "Administrative Issue       0.83      0.94      0.88       662\n",
      "        Cyber Attack       1.00      0.25      0.40         4\n",
      "         Human Error       0.50      0.06      0.10        18\n",
      "              Others       0.74      0.41      0.52        79\n",
      "           Terrorism       0.86      0.12      0.20        52\n",
      "             Weather       0.82      0.85      0.83        92\n",
      "       Worker Strike       0.67      0.78      0.72       120\n",
      "\n",
      "            accuracy                           0.81      1156\n",
      "           macro avg       0.78      0.52      0.56      1156\n",
      "        weighted avg       0.80      0.81      0.78      1156\n",
      "\n",
      "Total Runtime: 17.173302173614502\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "start_time = time.time()\n",
    "tfidf_vectorizer = TfidfVectorizer(max_features=2000)\n",
    "X_train_tfidf = tfidf_vectorizer.fit_transform(X_train)\n",
    "X_test_tfidf = tfidf_vectorizer.transform(X_test)\n",
    "\n",
    "rf_model = RandomForestClassifier(\n",
    "    n_estimators=300, min_samples_split=5, random_state=42\n",
    ")\n",
    "rf_model.fit(X_train_tfidf, y_train)\n",
    "\n",
    "y_pred = rf_model.predict(X_test_tfidf)\n",
    "end_time = time.time()\n",
    "total_runtime = end_time - start_time\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy of Random Forest Model:\", accuracy)\n",
    "print(classification_report(y_test, y_pred))\n",
    "\n",
    "print(\"Total Runtime:\", total_runtime)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7df52b09",
   "metadata": {},
   "source": [
    "### KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "b8822f38",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "368a2dd1",
   "metadata": {},
   "outputs": [],
   "source": [
    "vectorizer = TfidfVectorizer(max_features=2000)\n",
    "X = vectorizer.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "ae8bae0b",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "3ef3809f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7889273356401384\n"
     ]
    }
   ],
   "source": [
    "# Step 4: Apply KNN Algorithm\n",
    "k = 5  # Number of neighbors\n",
    "knn_model = KNeighborsClassifier(n_neighbors=k)\n",
    "knn_model.fit(X_train, y_train)\n",
    "\n",
    "# Step 5: Make Predictions and Evaluate Performance\n",
    "y_pred = knn_model.predict(X_test)\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy:\", accuracy)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cca13522-7877-4f1f-9b15-d8fb6fd55d12",
   "metadata": {},
   "source": [
    "Plot the model's performance against values of k to find the optimal k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "67102a37-2286-442f-b270-d3c00614dd9c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.datasets import load_iris\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "k_values = range(1, 21)\n",
    "\n",
    "train_scores = []\n",
    "test_scores = []\n",
    "\n",
    "# Iterate over each k value\n",
    "for k in k_values:\n",
    "    # Train KNN classifier\n",
    "    knn = KNeighborsClassifier(n_neighbors=k)\n",
    "    knn.fit(X_train, y_train)\n",
    "\n",
    "    # Calculate training and testing accuracy\n",
    "    train_score = knn.score(X_train, y_train)\n",
    "    test_score = knn.score(X_test, y_test)\n",
    "\n",
    "    train_scores.append(train_score)\n",
    "    test_scores.append(test_score)\n",
    "\n",
    "# Plot the performance scores\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(k_values, train_scores, label=\"Train Accuracy\", marker=\"o\")\n",
    "plt.plot(k_values, test_scores, label=\"Test Accuracy\", marker=\"o\")\n",
    "plt.xlabel(\"Number of Neighbors (k)\")\n",
    "plt.ylabel(\"Accuracy\")\n",
    "plt.title(\"KNN Classifier Performance\")\n",
    "plt.xticks(np.arange(1, 21, step=1))\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "38fbfc18-9f0f-405f-952e-74725d3fb6ed",
   "metadata": {},
   "source": [
    "k=5 is an optimal value"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f2e34a7b-6c6b-4308-874e-f74899336c61",
   "metadata": {},
   "source": [
    "Find other optimal hyperparameters by using grid search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "5725954c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Parameters: {'p': 2, 'weights': 'distance'}\n",
      "Test Accuracy: 0.7993079584775087\n"
     ]
    }
   ],
   "source": [
    "knn = KNeighborsClassifier()\n",
    "\n",
    "param_grid = {\"weights\": [\"uniform\", \"distance\"], \"p\": [1, 2]}\n",
    "\n",
    "grid_search = GridSearchCV(\n",
    "    estimator=knn, param_grid=param_grid, cv=5, scoring=\"accuracy\"\n",
    ")\n",
    "\n",
    "grid_search.fit(X_train, y_train)\n",
    "\n",
    "best_params = grid_search.best_params_\n",
    "\n",
    "best_model = grid_search.best_estimator_\n",
    "\n",
    "test_accuracy = best_model.score(X_test, y_test)\n",
    "print(\"Best Parameters:\", best_params)\n",
    "print(\"Test Accuracy:\", test_accuracy)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b7449ea-16e7-4660-89c6-24fe635f2880",
   "metadata": {},
   "source": [
    "Lastly, run the model with optimal hyperparameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "50fb3195-fe1c-499a-9157-0be8dc7be3e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "dbd33ce9-ebc7-42d8-a190-013c1d889286",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7993079584775087\n",
      "Total Runtime: 1.559605598449707\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "start_time = time.time()\n",
    "\n",
    "k = 5\n",
    "knn_model = KNeighborsClassifier(n_neighbors=k, weights=\"distance\")\n",
    "knn_model.fit(X_train, y_train)\n",
    "\n",
    "y_pred = knn_model.predict(X_test)\n",
    "\n",
    "end_time = time.time()\n",
    "total_runtime = end_time - start_time\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(\"Accuracy:\", accuracy)\n",
    "print(\"Total Runtime:\", total_runtime)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c21cc057-cfc5-4f18-80ba-aa29cf5b7b78",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}