{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GPU is available: True\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\kimi\\anaconda3\\envs\\torch\\lib\\site-packages\\spacy\\util.py:910: UserWarning: [W095] Model 'en_core_web_sm' (3.5.0) was trained with spaCy v3.5.0 and may not be 100% compatible with the current version (3.7.2). If you see errors or degraded performance, download a newer compatible model or retrain your custom model with the current spaCy version. For more details and available updates, run: python -m spacy validate\n",
      "  warnings.warn(warn_msg)\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "import pandas as pd\n",
    "from model import LSTMModel\n",
    "from preprocessing import preprocess_text\n",
    "from data_loader import create_data_loader\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import f1_score, roc_auc_score\n",
    "from keras.preprocessing.text import Tokenizer\n",
    "from keras_preprocessing.sequence import pad_sequences\n",
    "import pickle\n",
    "import train as tr\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from data_loader import NewsDataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fake_path = './data_1/Fake.csv'\n",
    "true_path = './data_1/True.csv'\n",
    "\n",
    "print(\"No cleaned data found. Cleaning data now...\")\n",
    "# Load the datasets\n",
    "true_news = pd.read_csv('data_1/True.csv')\n",
    "fake_news = pd.read_csv('data_1/Fake.csv')\n",
    "\n",
    "# Add labels\n",
    "true_news['label'] = 1\n",
    "fake_news['label'] = 0\n",
    "\n",
    "# Combine the datasets\n",
    "df = pd.concat([true_news, fake_news], ignore_index=True)\n",
    "\n",
    "# Drop unnecessary columns\n",
    "df.drop(columns=['subject', 'date'], inplace=True)\n",
    "\n",
    "df['title'] = df[0]['title'].apply(preprocess_text)\n",
    "df['text'] = df[0]['text'].apply(preprocess_text)\n",
    "\n",
    "df.to_csv('test.csv', index=False)"
   ]
  }
 ],
 "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
}