{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sort Embassy Flickr Images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "import shutil\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "fp_files = '/data_store/datasets/msc/embassies/embassy_counts_images.csv'\n",
    "fp_dir_dst = '/data_store/datasets/msc/images_sorted/'\n",
    "fp_dir_src = '/data_store/datasets/msc/images/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_flickr = pd.read_csv(fp_files)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "groups_username = df_flickr.groupby('path_alias')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "for group_username, df_group in groups_username:\n",
    "  for idx, df in df_group.iterrows():\n",
    "    fp_dst = Path(fp_dir_dst) / group_username / df.dataset_key\n",
    "    fp_src = Path(fp_dir_src) / df.filepath\n",
    "    if fp_src.exists():\n",
    "      fp_dst.mkdir(exist_ok=True, parents=True)\n",
    "      shutil.copy(fp_src, fp_dst)"
   ]
  },
  {
   "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
}