{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "origin_data_dir = os.path.normpath(\"./dataset/origin/yolo_seg_1612\")\n",
    "target_data_dir = os.path.normpath(os.path.join(\"../datasets/\",\"yolo_seg_1612\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Looking in indexes: https://mirrors.aliyun.com/pypi/simple\n",
      "Requirement already satisfied: pandas in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (2.2.3)\n",
      "Requirement already satisfied: scikit-learn in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (1.5.2)\n",
      "Requirement already satisfied: numpy>=1.22.4 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from pandas) (1.26.4)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from pandas) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from pandas) (2024.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from pandas) (2024.2)\n",
      "Requirement already satisfied: scipy>=1.6.0 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from scikit-learn) (1.14.1)\n",
      "Requirement already satisfied: joblib>=1.2.0 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from scikit-learn) (1.4.2)\n",
      "Requirement already satisfied: threadpoolctl>=3.1.0 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from scikit-learn) (3.5.0)\n",
      "Requirement already satisfied: six>=1.5 in d:\\projects\\test\\palmprint-recognition\\.venv\\lib\\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "%pip install  pandas scikit-learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1607</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1608</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1609</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1610</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1611</th>\n",
       "      <td>data/images/train/Birjand University Mobile Pa...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1612 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                      0\n",
       "0     data/images/train/Birjand University Mobile Pa...\n",
       "1     data/images/train/Birjand University Mobile Pa...\n",
       "2     data/images/train/Birjand University Mobile Pa...\n",
       "3     data/images/train/Birjand University Mobile Pa...\n",
       "4     data/images/train/Birjand University Mobile Pa...\n",
       "...                                                 ...\n",
       "1607  data/images/train/Birjand University Mobile Pa...\n",
       "1608  data/images/train/Birjand University Mobile Pa...\n",
       "1609  data/images/train/Birjand University Mobile Pa...\n",
       "1610  data/images/train/Birjand University Mobile Pa...\n",
       "1611  data/images/train/Birjand University Mobile Pa...\n",
       "\n",
       "[1612 rows x 1 columns]"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(os.path.join(origin_data_dir, \"train.txt\"),header=None)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       images/train/Birjand University Mobile Palmpri...\n",
       "1       images/train/Birjand University Mobile Palmpri...\n",
       "2       images/train/Birjand University Mobile Palmpri...\n",
       "3       images/train/Birjand University Mobile Palmpri...\n",
       "4       images/train/Birjand University Mobile Palmpri...\n",
       "                              ...                        \n",
       "1607    images/train/Birjand University Mobile Palmpri...\n",
       "1608    images/train/Birjand University Mobile Palmpri...\n",
       "1609    images/train/Birjand University Mobile Palmpri...\n",
       "1610    images/train/Birjand University Mobile Palmpri...\n",
       "1611    images/train/Birjand University Mobile Palmpri...\n",
       "Name: 0, Length: 1612, dtype: object"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[0] = df[0].apply(lambda x: x.lstrip(\"/data\"))\n",
    "df[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                                      0\n",
      "1138  images/train/Birjand University Mobile Palmpri...\n",
      "316   images/train/Birjand University Mobile Palmpri...\n",
      "303   images/train/Birjand University Mobile Palmpri...\n",
      "545   images/train/Birjand University Mobile Palmpri...\n",
      "744   images/train/Birjand University Mobile Palmpri...\n",
      "...                                                 ...\n",
      "406   images/train/Birjand University Mobile Palmpri...\n",
      "1414  images/train/Birjand University Mobile Palmpri...\n",
      "143   images/train/Birjand University Mobile Palmpri...\n",
      "1265  images/train/Birjand University Mobile Palmpri...\n",
      "623   images/train/Birjand University Mobile Palmpri...\n",
      "\n",
      "[1289 rows x 1 columns]\n",
      "                                                      0  \\\n",
      "1574  images/train/Birjand University Mobile Palmpri...   \n",
      "1097  images/train/Birjand University Mobile Palmpri...   \n",
      "141   images/train/Birjand University Mobile Palmpri...   \n",
      "958   images/train/Birjand University Mobile Palmpri...   \n",
      "609   images/train/Birjand University Mobile Palmpri...   \n",
      "...                                                 ...   \n",
      "750   images/train/Birjand University Mobile Palmpri...   \n",
      "1547  images/train/Birjand University Mobile Palmpri...   \n",
      "817   images/train/Birjand University Mobile Palmpri...   \n",
      "1514  images/train/Birjand University Mobile Palmpri...   \n",
      "1164  images/train/Birjand University Mobile Palmpri...   \n",
      "\n",
      "                                                      1  \n",
      "1574  images/val/Birjand University Mobile Palmprint...  \n",
      "1097  images/val/Birjand University Mobile Palmprint...  \n",
      "141   images/val/Birjand University Mobile Palmprint...  \n",
      "958   images/val/Birjand University Mobile Palmprint...  \n",
      "609   images/val/Birjand University Mobile Palmprint...  \n",
      "...                                                 ...  \n",
      "750   images/val/Birjand University Mobile Palmprint...  \n",
      "1547  images/val/Birjand University Mobile Palmprint...  \n",
      "817   images/val/Birjand University Mobile Palmprint...  \n",
      "1514  images/val/Birjand University Mobile Palmprint...  \n",
      "1164  images/val/Birjand University Mobile Palmprint...  \n",
      "\n",
      "[323 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "train,test = train_test_split(df,test_size=0.2,random_state=17)\n",
    "test[1]=test[0].apply(lambda x: \"images/val/\" + x.lstrip(\"images/train\"))\n",
    "print(train)\n",
    "print(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not os.path.exists(target_data_dir):\n",
    "    os.makedirs(target_data_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "train.to_csv(os.path.join(target_data_dir,\"train.txt\"),index=False,header=None)\n",
    "test[1].to_csv(os.path.join(target_data_dir,\"val.txt\"),index=False,header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "import shutil"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "def copy_images(df:pd.DataFrame,target:str,labels:bool):\n",
    "    kind = \"labels\" if labels else \"images\"\n",
    "    targetRoot = os.path.join(target_data_dir,kind,target)\n",
    "    if os.path.exists(targetRoot):\n",
    "        shutil.rmtree(targetRoot)\n",
    "    for _,it in df.iterrows():\n",
    "        f:str = it[0]\n",
    "        f = re.sub(r'\\.[^.]+$', '.txt', f) if labels else f\n",
    "        f = kind + f.lstrip(\"images\")\n",
    "        # print(f)\n",
    "        source_f = os.path.normpath(os.path.join(origin_data_dir,f))\n",
    "        target_f = os.path.normpath(os.path.join(targetRoot,f.lstrip(kind + \"/train\")))\n",
    "        os.makedirs(os.path.dirname(target_f), exist_ok=True)\n",
    "        shutil.copyfile(source_f,target_f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_images(df=train,target=\"train\",labels=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_images(df=test,target=\"val\",labels=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_images(df=train,target=\"train\",labels=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_images(df=test,target=\"val\",labels=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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
}