{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2111\n",
      "                                            name  class     file_name\n",
      "0     Loperamide Hydrochloride 2 MG Oral Capsule   1052  26211358.jpg\n",
      "1                 Minocycline 50 MG Oral Capsule   1137  36231B28.jpg\n",
      "2               Nortriptyline 10 MG Oral Capsule   1193  24231228.jpg\n",
      "3               Nortriptyline 25 MG Oral Capsule   1194  20231018.jpg\n",
      "4               Nortriptyline 50 MG Oral Capsule   1195  2D2316D8.jpg\n",
      "...                                          ...    ...           ...\n",
      "4327        Enalapril Maleate 2.5 MG Oral Tablet    708  DC4D6E2B.jpg\n",
      "4328                  quinapril 5 MG Oral Tablet   1844  EA507553.jpg\n",
      "4329         trospium chloride 20 MG Oral Tablet   1959  3C519E2C.jpg\n",
      "4330               metaxalone 400 MG Oral Tablet   1749  C6506353.jpg\n",
      "4331              naratriptan 2.5 MG Oral Tablet   1775  66453369.jpg\n",
      "\n",
      "[4332 rows x 3 columns]\n",
      "4332\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv('image_class.csv')\n",
    "df = df[['name', 'class']]\n",
    "df.drop_duplicates(inplace=True)\n",
    "print(len(df))\n",
    "df1 = pd.read_csv('image_class.csv')\n",
    "df1 = df1[['name', 'class', 'im_file']]\n",
    "df1['file_name'] = df1['im_file'].apply(lambda v: v.split('_')[-1])\n",
    "df1.drop(columns='im_file', inplace=True)\n",
    "df1.drop_duplicates(inplace=True)\n",
    "print(df1)\n",
    "print(len(df1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>name</th>\n",
       "      <th>class</th>\n",
       "      <th>file_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>213</th>\n",
       "      <td>pregabalin 75 MG Oral Capsule [Lyrica]</td>\n",
       "      <td>1831</td>\n",
       "      <td>5715ABFD.jpg</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       name  class     file_name\n",
       "213  pregabalin 75 MG Oral Capsule [Lyrica]   1831  5715ABFD.jpg"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# df1[df1.file_name.str.endswith('26211358.jpg')]\n",
    "df1[df1.file_name.str.endswith('5715ABFD.jpg')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "'StringMethods' object is not callable",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[8], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# file_name = '00071-1014-68_NLMIMAGE10_5715ABFD.jpeg'\u001b[39;00m\n\u001b[1;32m      2\u001b[0m file_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m23155-0055-19_NLMIMAGE10_66453369.jpg\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m----> 3\u001b[0m df1[\u001b[43mdf1\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mfile_name\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;241m1\u001b[39m)[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\u001b[38;5;241m==\u001b[39mfile_name]\n",
      "\u001b[0;31mTypeError\u001b[0m: 'StringMethods' object is not callable"
     ]
    }
   ],
   "source": [
    "# file_name = '00071-1014-68_NLMIMAGE10_5715ABFD.jpeg'\n",
    "file_name = '23155-0055-19_NLMIMAGE10_66453369.jpg'\n",
    "df1[df1['file_name'].str().split('_',1)[-1]==file_name]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       [00093-0311-01, RXNAVIMAGE10, 26211358.jpg]\n",
       "1       [00093-3165-01, RXNAVIMAGE10, 36231B28.jpg]\n",
       "2       [00093-0810-01, RXNAVIMAGE10, 24231228.jpg]\n",
       "3       [00093-0811-01, RXNAVIMAGE10, 20231018.jpg]\n",
       "4       [00093-0812-01, RXNAVIMAGE10, 2D2316D8.jpg]\n",
       "                           ...                     \n",
       "8629      [16714-0442-01, NLMIMAGE10, DC4D6E2B.jpg]\n",
       "8630      [31722-0267-90, NLMIMAGE10, EA507553.jpg]\n",
       "8631      [00574-0145-60, NLMIMAGE10, 3C519E2C.jpg]\n",
       "8632      [64720-0126-10, NLMIMAGE10, C6506353.jpg]\n",
       "8633      [23155-0055-19, NLMIMAGE10, 66453369.jpg]\n",
       "Name: file_name, Length: 8634, dtype: object"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.file_name.str.split('_')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "yolov9",
   "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": "3.9.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}