{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b966f798",
   "metadata": {},
   "source": [
    "# Data Extraction from the downloaded the dataset\n",
    "Defining the base directory."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2f2df227",
   "metadata": {},
   "outputs": [],
   "source": [
    "BASE_PATH = \"dataset\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8b6673c8",
   "metadata": {},
   "source": [
    "Read the CSV's present in the dataset using *Pandas*."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5d885cf1",
   "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>Unnamed: 0</th>\n",
       "      <th>file_name</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>train_data/a6dcb93f596a43249135678dfcfc17ea.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>train_data/041be3153810433ab146bc97d5af505c.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>train_data/615df26ce9494e5db2f70e57ce7a3a4f.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>train_data/8542fe161d9147be8e835e50c0de39cd.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>train_data/5d81fa12bc3b4cea8c94a6700a477cf2.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79945</th>\n",
       "      <td>79945</td>\n",
       "      <td>train_data/9283b107f6274279b6f15bbe77c523aa.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79946</th>\n",
       "      <td>79946</td>\n",
       "      <td>train_data/4c6b17fe6dd743428a45773135a10508.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79947</th>\n",
       "      <td>79947</td>\n",
       "      <td>train_data/1ccbf96d04e342fd9f629ad55466b29e.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79948</th>\n",
       "      <td>79948</td>\n",
       "      <td>train_data/ff960b55f296445abb3c5f304b52e104.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79949</th>\n",
       "      <td>79949</td>\n",
       "      <td>train_data/3abd1876472f4ec988aa78f76664fbd6.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>79950 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Unnamed: 0                                        file_name  label\n",
       "0               0  train_data/a6dcb93f596a43249135678dfcfc17ea.jpg      1\n",
       "1               1  train_data/041be3153810433ab146bc97d5af505c.jpg      0\n",
       "2               2  train_data/615df26ce9494e5db2f70e57ce7a3a4f.jpg      1\n",
       "3               3  train_data/8542fe161d9147be8e835e50c0de39cd.jpg      0\n",
       "4               4  train_data/5d81fa12bc3b4cea8c94a6700a477cf2.jpg      1\n",
       "...           ...                                              ...    ...\n",
       "79945       79945  train_data/9283b107f6274279b6f15bbe77c523aa.jpg      0\n",
       "79946       79946  train_data/4c6b17fe6dd743428a45773135a10508.jpg      1\n",
       "79947       79947  train_data/1ccbf96d04e342fd9f629ad55466b29e.jpg      0\n",
       "79948       79948  train_data/ff960b55f296445abb3c5f304b52e104.jpg      1\n",
       "79949       79949  train_data/3abd1876472f4ec988aa78f76664fbd6.jpg      0\n",
       "\n",
       "[79950 rows x 3 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "\n",
    "train_data = pd.read_csv(os.path.join(BASE_PATH, \"train.csv\"))\n",
    "train_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "227b6827",
   "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>id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>test_data_v2/1a2d9fd3e21b4266aea1f66b30aed157.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>test_data_v2/ab5df8f441fe4fbf9dc9c6baae699dc7.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>test_data_v2/eb364dd2dfe34feda0e52466b7ce7956.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>test_data_v2/f76c2580e9644d85a741a42c6f6b39c0.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>test_data_v2/a16495c578b7494683805484ca27cf9f.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5535</th>\n",
       "      <td>test_data_v2/483412064ff74d9d9472d606b65976d9.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5536</th>\n",
       "      <td>test_data_v2/c0b49ba4081a4197b422dac7c15aea7f.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5537</th>\n",
       "      <td>test_data_v2/01454aaedec140c0a3ca1f48028c41cf.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5538</th>\n",
       "      <td>test_data_v2/e9adfea8b67e4791968c4c2bdd8ec343.jpg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5539</th>\n",
       "      <td>test_data_v2/ba8f4198e8d74d3394fa56c56af23442.jpg</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5540 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                     id\n",
       "0     test_data_v2/1a2d9fd3e21b4266aea1f66b30aed157.jpg\n",
       "1     test_data_v2/ab5df8f441fe4fbf9dc9c6baae699dc7.jpg\n",
       "2     test_data_v2/eb364dd2dfe34feda0e52466b7ce7956.jpg\n",
       "3     test_data_v2/f76c2580e9644d85a741a42c6f6b39c0.jpg\n",
       "4     test_data_v2/a16495c578b7494683805484ca27cf9f.jpg\n",
       "...                                                 ...\n",
       "5535  test_data_v2/483412064ff74d9d9472d606b65976d9.jpg\n",
       "5536  test_data_v2/c0b49ba4081a4197b422dac7c15aea7f.jpg\n",
       "5537  test_data_v2/01454aaedec140c0a3ca1f48028c41cf.jpg\n",
       "5538  test_data_v2/e9adfea8b67e4791968c4c2bdd8ec343.jpg\n",
       "5539  test_data_v2/ba8f4198e8d74d3394fa56c56af23442.jpg\n",
       "\n",
       "[5540 rows x 1 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data = pd.read_csv(os.path.join(BASE_PATH, \"test.csv\"))\n",
    "test_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8335ac2e",
   "metadata": {},
   "source": [
    "Dropping the unneccessary column from the `train_data`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "dd0b89f9",
   "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>file_name</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>train_data/a6dcb93f596a43249135678dfcfc17ea.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>train_data/041be3153810433ab146bc97d5af505c.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>train_data/615df26ce9494e5db2f70e57ce7a3a4f.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>train_data/8542fe161d9147be8e835e50c0de39cd.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>train_data/5d81fa12bc3b4cea8c94a6700a477cf2.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79945</th>\n",
       "      <td>train_data/9283b107f6274279b6f15bbe77c523aa.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79946</th>\n",
       "      <td>train_data/4c6b17fe6dd743428a45773135a10508.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79947</th>\n",
       "      <td>train_data/1ccbf96d04e342fd9f629ad55466b29e.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79948</th>\n",
       "      <td>train_data/ff960b55f296445abb3c5f304b52e104.jpg</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79949</th>\n",
       "      <td>train_data/3abd1876472f4ec988aa78f76664fbd6.jpg</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>79950 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             file_name  label\n",
       "0      train_data/a6dcb93f596a43249135678dfcfc17ea.jpg      1\n",
       "1      train_data/041be3153810433ab146bc97d5af505c.jpg      0\n",
       "2      train_data/615df26ce9494e5db2f70e57ce7a3a4f.jpg      1\n",
       "3      train_data/8542fe161d9147be8e835e50c0de39cd.jpg      0\n",
       "4      train_data/5d81fa12bc3b4cea8c94a6700a477cf2.jpg      1\n",
       "...                                                ...    ...\n",
       "79945  train_data/9283b107f6274279b6f15bbe77c523aa.jpg      0\n",
       "79946  train_data/4c6b17fe6dd743428a45773135a10508.jpg      1\n",
       "79947  train_data/1ccbf96d04e342fd9f629ad55466b29e.jpg      0\n",
       "79948  train_data/ff960b55f296445abb3c5f304b52e104.jpg      1\n",
       "79949  train_data/3abd1876472f4ec988aa78f76664fbd6.jpg      0\n",
       "\n",
       "[79950 rows x 2 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data.drop(\"Unnamed: 0\", axis=1, inplace=True)\n",
    "train_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bd94641",
   "metadata": {},
   "source": [
    "Separating the *AI-Generated Images* and the *Real Images* into the separate folders.<br>\n",
    "We will be using the **shutil** module."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "b368403e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import shutil\n",
    "\n",
    "for i in range(len(train_data)):\n",
    "    source = os.path.join(BASE_PATH, train_data.iloc[i,][\"file_name\"])\n",
    "    if train_data.iloc[i,][\"label\"] == 1:\n",
    "        destination = os.path.join(BASE_PATH, \"train\", \"ai\")\n",
    "    else:\n",
    "        destination = os.path.join(BASE_PATH, \"train\", \"real\")\n",
    "    shutil.copy2(source, destination)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1442bf12",
   "metadata": {},
   "source": [
    "We have separated the *AI-Generated* and *Real* Images based on the *CSV File* provided in the dataset.<br>\n",
    "Now, the further things will be done in another Notebook."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "myenv",
   "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": "3.14.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}