CDiscount - Error

Extract-Images.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import bson\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import os\n",
    "from tqdm import tqdm_notebook"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test Files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ff0cef286f9f427d96004de64e06285b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/html": [
       "<p>Failed to display Jupyter Widget of type <code>HBox</code>.</p>\n",
       "<p>\n",
       "  If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
       "  that the widgets JavaScript is still loading. If this message persists, it\n",
       "  likely means that the widgets JavaScript library is either not installed or\n",
       "  not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
       "  Widgets Documentation</a> for setup instructions.\n",
       "</p>\n",
       "<p>\n",
       "  If you're reading this message in another frontend (for example, a static\n",
       "  rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
       "  it may mean that your frontend doesn't currently support widgets.\n",
       "</p>\n"
      ],
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1768182), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "out_folder = 'data/Cdiscount/test'\n",
    "\n",
    "# Create output folder\n",
    "if not os.path.exists(out_folder):\n",
    "    os.makedirs(out_folder)\n",
    "\n",
    "num_products = 1768182  # 7069896 for train and 1768182 for test\n",
    "\n",
    "bar = tqdm_notebook(total=num_products)\n",
    "with open('data/cdiscount/test.bson', 'rb') as fbson:\n",
    "\n",
    "    data = bson.decode_file_iter(fbson)\n",
    "    \n",
    "    for c, d in enumerate(data):\n",
    "        _id = d['_id']\n",
    "        for e, pic in enumerate(d['imgs']):\n",
    "            fname = os.path.join(out_folder, '{}-{}.jpg'.format(_id, e))\n",
    "            with open(fname, 'wb') as f:\n",
    "                f.write(pic['picture'])\n",
    "\n",
    "        bar.update()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train Files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "out_folder = 'data/cdiscount/train'\n",
    "\n",
    "# Create output folder\n",
    "if not os.path.exists(out_folder):\n",
    "    os.makedirs(out_folder)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "68b2c0e61aaa4275862113914a68a152",
       "version_major": 2,
       "version_minor": 0
      },
      "text/html": [
       "<p>Failed to display Jupyter Widget of type <code>HBox</code>.</p>\n",
       "<p>\n",
       "  If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
       "  that the widgets JavaScript is still loading. If this message persists, it\n",
       "  likely means that the widgets JavaScript library is either not installed or\n",
       "  not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
       "  Widgets Documentation</a> for setup instructions.\n",
       "</p>\n",
       "<p>\n",
       "  If you're reading this message in another frontend (for example, a static\n",
       "  rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
       "  it may mean that your frontend doesn't currently support widgets.\n",
       "</p>\n"
      ],
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5270), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Create categories folders\n",
    "categories = pd.read_csv('data/cdiscount/category_names.csv', index_col='category_id')\n",
    "\n",
    "for category in tqdm_notebook(categories.index):\n",
    "    os.mkdir(os.path.join(out_folder, str(category)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cd9ddd1cf1124bc2ae2a449042354792",
       "version_major": 2,
       "version_minor": 0
      },
      "text/html": [
       "<p>Failed to display Jupyter Widget of type <code>HBox</code>.</p>\n",
       "<p>\n",
       "  If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
       "  that the widgets JavaScript is still loading. If this message persists, it\n",
       "  likely means that the widgets JavaScript library is either not installed or\n",
       "  not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
       "  Widgets Documentation</a> for setup instructions.\n",
       "</p>\n",
       "<p>\n",
       "  If you're reading this message in another frontend (for example, a static\n",
       "  rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
       "  it may mean that your frontend doesn't currently support widgets.\n",
       "</p>\n"
      ],
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=7069896), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Exception in thread Thread-4:\n",
      "Traceback (most recent call last):\n",
      "  File \"/home/paperspace/anaconda3/envs/fastai/lib/python3.6/threading.py\", line 916, in _bootstrap_inner\n",
      "    self.run()\n",
      "  File \"/home/paperspace/anaconda3/envs/fastai/lib/python3.6/site-packages/tqdm/_tqdm.py\", line 144, in run\n",
      "    for instance in self.tqdm_cls._instances:\n",
      "  File \"/home/paperspace/anaconda3/envs/fastai/lib/python3.6/_weakrefset.py\", line 60, in __iter__\n",
      "    for itemref in self.data:\n",
      "RuntimeError: Set changed size during iteration\n",
      "\n"
     ]
    }
   ],
   "source": [
    "num_products = 7069896  # 7069896 for train and 1768182 for test\n",
    "\n",
    "bar = tqdm_notebook(total=num_products)\n",
    "with open('data/cdiscount/train.bson', 'rb') as fbson:\n",
    "\n",
    "    data = bson.decode_file_iter(fbson)\n",
    "    \n",
    "    for c, d in enumerate(data):\n",
    "        category = d['category_id']\n",
    "        _id = d['_id']\n",
    "        for e, pic in enumerate(d['imgs']):\n",
    "            fname = os.path.join(out_folder, str(category), '{}-{}.jpg'.format(_id, e))\n",
    "            with open(fname, 'wb') as f:\n",
    "                f.write(pic['picture'])\n",
    "\n",
    "        bar.update()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

Issue.ipynb