{
 "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": [
    "| photo_id |\n",
    "|:---|\n",
    "| 12234 |"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# flickr api data\n",
    "fp_in_flickr_meta = '/data_store_hdd/datasets/people/ibm_dif/research/flickr_api_query_dump.csv'\n",
    "# ibm count data\n",
    "fp_in_ibm_meta = '/data_store_hdd/datasets/people/ibm_dif/research/ibm_dif_metadata.csv'\n",
    "# output\n",
    "fp_out = '/data_store_hdd/datasets/people/ibm_dif/research/ibm_dif_metadata.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "# load ibm data and create count lookup with photoid\n",
    "df_ibm_meta = pd.read_csv(fp_in_ibm_meta)\n",
    "ibm_meta_records = df_ibm_meta.to_dict('records')\n",
    "count_lookup = {}\n",
    "for ibm_meta_record in ibm_meta_records:\n",
    "  photo_id = int(Path(ibm_meta_record['url']).stem.split('_')[0])\n",
    "  count_lookup[photo_id] = ibm_meta_record['count']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "100438"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(count_lookup)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "results = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_flickr_meta = pd.read_csv(fp_in_flickr_meta, dtype={'count': int, 'username': str, 'sha256': str}).fillna('')\n",
    "flickr_meta_records = df_flickr_meta.to_dict('records')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Error: invalid literal for int() with base 10: '', {'country': '', 'description': 'Haircut Next...', 'lat': '', 'lon': '', 'nsid': '', 'owner_location': '', 'path_alias': '', 'photo_id': '', 'place': '', 'place_id': '', 'posted': '', 'realname': '', 'taken': '', 'username': '', 'woeid': ''}\n",
      "Error: invalid literal for int() with base 10: '', {'country': '', 'description': '', 'lat': '86085317@N00', 'lon': 'New York', 'nsid': 'anonymousthomas', 'owner_location': '4975598', 'path_alias': '', 'photo_id': '', 'place': '1108685469', 'place_id': 'Thomas', 'posted': '2005-02-18 00:11:09', 'realname': 'anonymousthomas', 'taken': '', 'username': '', 'woeid': ''}\n"
     ]
    }
   ],
   "source": [
    "# load flickr data\n",
    "for flickr_meta_record in flickr_meta_records:\n",
    "  try:\n",
    "    nsid = flickr_meta_record['nsid']\n",
    "    photo_id = int(flickr_meta_record['photo_id'])\n",
    "    count = count_lookup[photo_id]\n",
    "  except Exception as e:\n",
    "    print(f'Error: {e}, {flickr_meta_record}')\n",
    "    continue\n",
    "  obj = {\n",
    "    'photo_id': photo_id,\n",
    "    'nsid': nsid,\n",
    "    'count': count \n",
    "  }\n",
    "  results.append(obj)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_out = pd.DataFrame.from_dict(results)\n",
    "df_out.to_csv(fp_out, index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create meta count file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "fp_flickr_api_dump = '/data_store_hdd/datasets/people/ibm_dif/research/flickr_api_query_dump.csv'\n",
    "fp_out_meta = '/data_store_hdd/datasets/people/ibm_dif/research/ibm_dif_flickr_meta.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/adam/anaconda3/envs/megapixels/lib/python3.6/site-packages/IPython/core/interactiveshell.py:3020: DtypeWarning: Columns (2,3,10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv(fp_flickr_api_dump)\n",
    "groups = df.groupby('nsid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "results = []\n",
    "for nsid, group in groups:\n",
    "  obj = {\n",
    "    'nsid': nsid,\n",
    "    'count': len(group)\n",
    "  }\n",
    "  results.append(obj)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.DataFrame.from_dict(results).to_csv(fp_out_meta, 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
}