{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# PIPA 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": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "fp_in_api_photo_id = '/data_store_hdd/datasets/people/pipa/research/flickr_api_photo_id.csv'\n",
    "fp_out_filepaths = '/data_store_hdd/datasets/people/pipa/research/pipa_filepaths.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(fp_in_api_photo_id)\n",
    "records = df.to_dict('records')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "results = []\n",
    "for record in records:\n",
    "  obj = {\n",
    "    'photo_id': record.get('photo_id'),\n",
    "    'nsid': record.get('nsid'),\n",
    "    'url': record.get('url'),\n",
    "    'secret': record.get('secret'),\n",
    "    'filepath': f'{photo_id}_{secret}.jpg'\n",
    "  }\n",
    "  results.append(obj)\n",
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.DataFrame.from_dict(results).to_csv(fp_out_filepaths, index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Create metadata csv output\n",
    "\n",
    "|nsid|path_alias|count|"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_flickr_meta = pd.read_csv(fp_in)\n",
    "df_flickr_meta.fillna('', inplace=True)\n",
    "flickr_metas = df_flickr_meta.to_dict('records')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create nsid lookup table\n",
    "nsid_lookup = {}\n",
    "alias_lookup = {}\n",
    "for flickr_meta in flickr_metas:\n",
    "  nsid = flickr_meta['nsid']\n",
    "  nsid_lookup[nsid] = flickr_meta\n",
    "  alias_lookup[nsid] = flickr_meta['path_alias']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "nsid_groups = df_flickr_meta.groupby('nsid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "items = []\n",
    "for nsid, nsid_group in nsid_groups:\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": 35,
   "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
}