{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create Name List"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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",
    "import requests\n",
    "import json\n",
    "from urllib.parse import unquote\n",
    "\n",
    "from tqdm import tqdm_notebook as tqdm\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "import sys\n",
    "sys.path.append('/work/megapixels_dev/megapixels')\n",
    "from app.utils import api_utils, identity_utils\n",
    "from app.settings import app_cfg\n",
    "from app.settings import types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "fp_yfcc = '/data_store_hdd/datasets/people/yfcc100m/downloads/usernames.txt'\n",
    "fp_yfcc_clean = '/data_store_hdd/datasets/people/yfcc100m/downloads/usernames_clean.txt'\n",
    "fp_dir_research = '/data_store_hdd/datasets/people/ibm_dif/research/'\n",
    "fp_usernames = join(fp_dir_research, 'usernames_decoded.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Convert YFCC to Unique Name List"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(fp_yfcc, 'r') as fp:\n",
    "  usernames_raw = fp.readlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ea6b4e8d2a8145f2b7efb559575862b8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=100000000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "usernames = []\n",
    "for username in tqdm(usernames_raw):\n",
    "  un_clean = unquote(username.strip().lower().replace(' ', '+'))\n",
    "  usernames.append(un_clean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(fp_yfcc_clean, 'w') as fp:\n",
    "  for username in usernames:\n",
    "    fp.write(username + \"\\n\")"
   ]
  },
  {
   "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
}