{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the datasets\n",
    "df_1 = pd.read_csv(\"data_2/WELFake_Dataset.csv\")\n",
    "df_2 = pd.read_csv(\"data_3/news_articles.csv\")\n",
    "\n",
    "# Drop index\n",
    "df_1.drop(df_1.columns[0], axis=1, inplace=True)\n",
    "df_1.dropna(inplace=True)\n",
    "\n",
    "# Swapping labels around since it originally is the opposite\n",
    "df_1[\"label\"] = df_1[\"label\"].map({0: 1, 1: 0})\n",
    "\n",
    "# Add labels\n",
    "df_2.drop(\n",
    "    columns=[\n",
    "        \"author\",\n",
    "        \"published\",\n",
    "        \"site_url\",\n",
    "        \"main_img_url\",\n",
    "        \"type\",\n",
    "        \"text_without_stopwords\",\n",
    "        \"title_without_stopwords\",\n",
    "        \"hasImage\",\n",
    "    ],\n",
    "    inplace=True,\n",
    ")\n",
    "# Map Real to 1 and Fake to 0\n",
    "df_2[\"label\"] = df_2[\"label\"].map({\"Real\": 1, \"Fake\": 0})\n",
    "df_2 = df_2[df_2[\"label\"].isin([1, 0])]\n",
    "\n",
    "# Drop rows where the language is not 'english'\n",
    "df_2 = df_2[df_2[\"language\"] == \"english\"]\n",
    "df_2.drop(columns=[\"language\"], inplace=True)\n",
    "\n",
    "# Convert \"no title\" to empty string\n",
    "df_2[\"title\"] = df_2[\"title\"].apply(lambda x: \"\" if x == \"no title\" else x)\n",
    "\n",
    "df_2.dropna(inplace=True)\n",
    "\n",
    "random_1 = df_1.sample(n=500, random_state=42)\n",
    "random_2 = df_2.sample(n=500, random_state=42)\n",
    "\n",
    "# Combine the datasets\n",
    "df = pd.concat([random_1, random_2], ignore_index=True)\n",
    "\n",
    "df[\"label\"] = df[\"label\"].astype(int)\n",
    "\n",
    "df.to_csv(\"sampled_data.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>title</th>\n",
       "      <th>text</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Live at Truthdig: Robert Scheer and Thomas Fra...</td>\n",
       "      <td>Live at Truthdig: Robert Scheer and Thomas Fra...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>The Mirage of a Return to Manufacturing Greatn...</td>\n",
       "      <td>Half a century ago, harvesting California’s 2....</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>British PM expected to offer to fill post-Brex...</td>\n",
       "      <td>(Reuters) - The British government has told Ge...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Checkmating Obama</td>\n",
       "      <td>Originally published by the Jerusalem Post . \\...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Thirty-eight injured in police charges in Cata...</td>\n",
       "      <td>MADRID (Reuters) - Emergency services have att...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               title  \\\n",
       "0  Live at Truthdig: Robert Scheer and Thomas Fra...   \n",
       "1  The Mirage of a Return to Manufacturing Greatn...   \n",
       "2  British PM expected to offer to fill post-Brex...   \n",
       "3                                  Checkmating Obama   \n",
       "4  Thirty-eight injured in police charges in Cata...   \n",
       "\n",
       "                                                text  label  \n",
       "0  Live at Truthdig: Robert Scheer and Thomas Fra...      0  \n",
       "1  Half a century ago, harvesting California’s 2....      1  \n",
       "2  (Reuters) - The British government has told Ge...      1  \n",
       "3  Originally published by the Jerusalem Post . \\...      0  \n",
       "4  MADRID (Reuters) - Emergency services have att...      1  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "torch",
   "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}