{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Adience Flickr Metadata Cleanup"
   ]
  },
  {
   "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\n",
    "from pathlib import Path\n",
    "\n",
    "from tqdm import tqdm_notebook as tqdm\n",
    "import pandas as pd\n",
    "\n",
    "import sys\n",
    "sys.path.append('/work/megapixels_dev/megapixels')\n",
    "from app.utils import file_utils"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load CSV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "fp_in_files = '/data_store_hdd/datasets/people/adience/research/adience_flickr_api_queries.csv'\n",
    "fp_in_nsid_urls = '/data_store_hdd/datasets/people/adience/research/adience_flickr_nsid_url.csv'\n",
    "fp_in_nsid_profiles = '/data_store_hdd/datasets/people/adience/research/adience_flickr_nsid_profile.csv'\n",
    "fp_out = '/data_store_hdd/datasets/people/adience/research/adience_flickr_meta.csv'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Create metadata csv output\n",
    "\n",
    "|nsid|path_alias|count|"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# files\n",
    "df_files = pd.read_csv(fp_in_files)\n",
    "df_files.fillna('', inplace=True)\n",
    "files = df_files.to_dict('records')\n",
    "\n",
    "# nsid urls\n",
    "df_urls = pd.read_csv(fp_in_nsid_urls)\n",
    "df_urls.fillna('', inplace=True)\n",
    "urls = df_urls.to_dict('records')\n",
    "\n",
    "# nsid profiles\n",
    "df_profiles = pd.read_csv(fp_in_nsid_profiles)\n",
    "df_profiles.fillna('', inplace=True)\n",
    "profiles = df_profiles.to_dict('records')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create nsid lookup table\n",
    "alias_lookup = {}\n",
    "for url_meta in urls:\n",
    "  alias_lookup[url_meta['nsid']] = str(Path(url_meta['url']).stem)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "nsid_groups = df_files.groupby('nsid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Skipping: 10693681@N00\n",
      "Skipping: 10743505@N04\n",
      "Skipping: 113728563@N05\n",
      "Skipping: 7648211@N03\n"
     ]
    }
   ],
   "source": [
    "items = []\n",
    "for nsid, nsid_group in nsid_groups:\n",
    "  if nsid not in alias_lookup.keys():\n",
    "    print(f'Skipping: {nsid}')\n",
    "    continue\n",
    "  path_alias = alias_lookup[nsid]\n",
    "  obj = {'nsid': nsid, 'path_alias': path_alias, 'count': len(nsid_group)}\n",
    "  items.append(obj)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_out = pd.DataFrame.from_dict(items)\n",
    "df_out.to_csv(fp_out, 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
}