{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Prepare Flickr API Batch CSV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%reload_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "import os\n",
    "from os.path import join\n",
    "from glob import glob, iglob\n",
    "from pathlib import Path\n",
    "from tqdm import tqdm_notebook as tqdm\n",
    "\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create CSV for API"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "| filepath | query | count |\n",
    "|:---|:---|:---|\n",
    "| 12234 | 12234@123| 10 |"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "fp_in_dir = '/data_store/datasets/people/adience/dataset/'\n",
    "fp_out_queries = '/data_store/datasets/people/adience/research/adience_flickr_api_queries.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "9\n"
     ]
    }
   ],
   "source": [
    "fp_files = glob(join(fp_in_dir, '*.txt'))\n",
    "print(len(fp_files))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images = pd.DataFrame()\n",
    "for fp_file in fp_files:\n",
    "  df = pd.read_csv(fp_file, delimiter='\\t')\n",
    "  if 'user_id' in df.keys():\n",
    "    df = df[['user_id', 'original_image']]\n",
    "    df_images = dfs.append(df, ignore_index=True)  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images.drop_duplicates(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "images = df_images.to_dict('records')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "for image in images:\n",
    "  image['photo_id'] = image['original_image'].split('_')[0]\n",
    "  image['filename'] = f'{image[\"photo_id\"]}.json'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images = pd.DataFrame.from_dict(images)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images.drop(columns=['original_image'], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10804\n"
     ]
    }
   ],
   "source": [
    "print(len(df_images))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_images.to_csv(fp_out_queries, index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "megapixels",
   "language": "python",
   "name": "megapixels"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}