{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "outputs": [],
   "source": [
    "#|default_exp app"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/thomas/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.1\n",
      "  warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n"
     ]
    }
   ],
   "source": [
    "#|export\n",
    "from fastai.vision.all import *\n",
    "import gradio as gr\n",
    "\n",
    "def is_cat(x): return x[0].isupper()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [
    {
     "data": {
      "text/plain": "PILImage mode=RGB size=192x124",
      "image/png": "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\n"
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "im = PILImage.create('dog.jpg')\n",
    "im.thumbnail((192,192))\n",
    "im"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "outputs": [],
   "source": [
    "#|export\n",
    "learn = load_learner('model.pkl')"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/thomas/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/torch/cuda/__init__.py:83: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW (Triggered internally at  /opt/conda/conda-bld/pytorch_1659484803030/work/c10/cuda/CUDAFunctions.cpp:109.)\n",
      "  return torch._C._cuda_getDeviceCount() > 0\n"
     ]
    },
    {
     "data": {
      "text/plain": "<IPython.core.display.HTML object>",
      "text/html": "\n<style>\n    /* Turns off some styling */\n    progress {\n        /* gets rid of default border in Firefox and Opera. */\n        border: none;\n        /* Needs to be in here for Safari polyfill so background images work as expected. */\n        background-size: auto;\n    }\n    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n    }\n    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n        background: #F44336;\n    }\n</style>\n"
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": "<IPython.core.display.HTML object>",
      "text/html": "\n    <div>\n      <progress value='0' class='' max='1' style='width:300px; height:20px; vertical-align: middle;'></progress>\n      \n    </div>\n    "
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": "('False', TensorBase(0), TensorBase([9.9999e-01, 5.5343e-06]))"
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "learn.predict(im)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "outputs": [],
   "source": [
    "#|export\n",
    "categories = ('Dog', 'Cat')\n",
    "\n",
    "def classify_image(img):\n",
    "    pred, idx, probs = learn.predict(img)\n",
    "    return dict(zip(categories, map(float, probs)))\n"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "outputs": [
    {
     "data": {
      "text/plain": "<IPython.core.display.HTML object>",
      "text/html": "\n<style>\n    /* Turns off some styling */\n    progress {\n        /* gets rid of default border in Firefox and Opera. */\n        border: none;\n        /* Needs to be in here for Safari polyfill so background images work as expected. */\n        background-size: auto;\n    }\n    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n    }\n    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n        background: #F44336;\n    }\n</style>\n"
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": "<IPython.core.display.HTML object>",
      "text/html": "\n    <div>\n      <progress value='0' class='' max='1' style='width:300px; height:20px; vertical-align: middle;'></progress>\n      \n    </div>\n    "
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": "{'Dog': 0.9999945163726807, 'Cat': 5.534268893825356e-06}"
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classify_image(im)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/thomas/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/gradio/inputs.py:256: UserWarning: Usage of gradio.inputs is deprecated, and will not be supported in the future, please import your component from gradio.components\n",
      "  warnings.warn(\n",
      "/home/thomas/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/gradio/deprecation.py:40: UserWarning: `optional` parameter is deprecated, and it has no effect\n",
      "  warnings.warn(value)\n",
      "/home/thomas/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/gradio/outputs.py:196: UserWarning: Usage of gradio.outputs is deprecated, and will not be supported in the future, please import your components from gradio.components\n",
      "  warnings.warn(\n",
      "/home/thomas/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/gradio/deprecation.py:40: UserWarning: The 'type' parameter has been deprecated. Use the Number component instead.\n",
      "  warnings.warn(value)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860/\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/plain": "(<gradio.routes.App at 0x7f942dd46b90>, 'http://127.0.0.1:7860/', None)"
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#|export\n",
    "image = gr.inputs.Image(shape=(192,192))\n",
    "label = gr.outputs.Label()\n",
    "examples = ['dog.jpg', 'cat.jpg', 'dogcat.png']\n",
    "\n",
    "intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)\n",
    "intf.launch(inline=False)\n"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "outputs": [],
   "source": [
    "from nbdev import nbdev_export\n"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Export"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "outputs": [
    {
     "ename": "InterpolationMissingOptionError",
     "evalue": "Bad value substitution: option 'doc_host' in section 'DEFAULT' contains an interpolation key 'user' which is not a valid option name. Raw value: 'https://%(user)s.github.io'",
     "output_type": "error",
     "traceback": [
      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
      "\u001B[0;31mInterpolationMissingOptionError\u001B[0m           Traceback (most recent call last)",
      "Input \u001B[0;32mIn [10]\u001B[0m, in \u001B[0;36m<cell line: 1>\u001B[0;34m()\u001B[0m\n\u001B[0;32m----> 1\u001B[0m \u001B[43mnbdev_export\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/fastcore/script.py:107\u001B[0m, in \u001B[0;36mcall_parse.<locals>._f\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    104\u001B[0m \u001B[38;5;129m@wraps\u001B[39m(func)\n\u001B[1;32m    105\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_f\u001B[39m(\u001B[38;5;241m*\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs):\n\u001B[1;32m    106\u001B[0m     mod \u001B[38;5;241m=\u001B[39m inspect\u001B[38;5;241m.\u001B[39mgetmodule(inspect\u001B[38;5;241m.\u001B[39mcurrentframe()\u001B[38;5;241m.\u001B[39mf_back)\n\u001B[0;32m--> 107\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m mod: \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mfunc\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    108\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m SCRIPT_INFO\u001B[38;5;241m.\u001B[39mfunc \u001B[38;5;129;01mand\u001B[39;00m mod\u001B[38;5;241m.\u001B[39m\u001B[38;5;18m__name__\u001B[39m\u001B[38;5;241m==\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m__main__\u001B[39m\u001B[38;5;124m\"\u001B[39m: SCRIPT_INFO\u001B[38;5;241m.\u001B[39mfunc \u001B[38;5;241m=\u001B[39m func\u001B[38;5;241m.\u001B[39m\u001B[38;5;18m__name__\u001B[39m\n\u001B[1;32m    109\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(sys\u001B[38;5;241m.\u001B[39margv)\u001B[38;5;241m>\u001B[39m\u001B[38;5;241m1\u001B[39m \u001B[38;5;129;01mand\u001B[39;00m sys\u001B[38;5;241m.\u001B[39margv[\u001B[38;5;241m1\u001B[39m]\u001B[38;5;241m==\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124m'\u001B[39m: sys\u001B[38;5;241m.\u001B[39margv\u001B[38;5;241m.\u001B[39mpop(\u001B[38;5;241m1\u001B[39m)\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/nbdev/doclinks.py:149\u001B[0m, in \u001B[0;36mnbdev_export\u001B[0;34m(path, recursive, symlinks, file_re, folder_re, skip_file_glob, skip_file_re)\u001B[0m\n\u001B[1;32m    147\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m f \u001B[38;5;129;01min\u001B[39;00m files: nb_export(f)\n\u001B[1;32m    148\u001B[0m add_init(get_config()\u001B[38;5;241m.\u001B[39mpath(\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mlib_path\u001B[39m\u001B[38;5;124m'\u001B[39m))\n\u001B[0;32m--> 149\u001B[0m \u001B[43mbuild_modidx\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/nbdev/doclinks.py:118\u001B[0m, in \u001B[0;36mbuild_modidx\u001B[0;34m()\u001B[0m\n\u001B[1;32m    116\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m contextlib\u001B[38;5;241m.\u001B[39msuppress(\u001B[38;5;167;01mFileNotFoundError\u001B[39;00m): _fn\u001B[38;5;241m.\u001B[39munlink()\n\u001B[1;32m    117\u001B[0m cfg \u001B[38;5;241m=\u001B[39m get_config()\n\u001B[0;32m--> 118\u001B[0m doc_func \u001B[38;5;241m=\u001B[39m partial(_doc_link, urljoin(\u001B[43mcfg\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mdoc_host\u001B[49m,cfg\u001B[38;5;241m.\u001B[39mdoc_baseurl))\n\u001B[1;32m    119\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m file \u001B[38;5;129;01min\u001B[39;00m dest\u001B[38;5;241m.\u001B[39mglob(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m**/*.py\u001B[39m\u001B[38;5;124m\"\u001B[39m):\n\u001B[1;32m    120\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m file\u001B[38;5;241m.\u001B[39mname[\u001B[38;5;241m0\u001B[39m]\u001B[38;5;241m!=\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124m_\u001B[39m\u001B[38;5;124m'\u001B[39m: DocLinks(file, doc_func, _fn)\u001B[38;5;241m.\u001B[39mbuild_index()\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/fastcore/foundation.py:268\u001B[0m, in \u001B[0;36mConfig.__getattr__\u001B[0;34m(self, k)\u001B[0m\n\u001B[0;32m--> 268\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m__getattr__\u001B[39m(\u001B[38;5;28mself\u001B[39m,k):   \u001B[38;5;28;01mreturn\u001B[39;00m stop(\u001B[38;5;167;01mAttributeError\u001B[39;00m(k)) \u001B[38;5;28;01mif\u001B[39;00m k\u001B[38;5;241m==\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124md\u001B[39m\u001B[38;5;124m'\u001B[39m \u001B[38;5;129;01mor\u001B[39;00m k \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39md \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget\u001B[49m\u001B[43m(\u001B[49m\u001B[43mk\u001B[49m\u001B[43m)\u001B[49m\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/site-packages/fastcore/foundation.py:270\u001B[0m, in \u001B[0;36mConfig.get\u001B[0;34m(self, k, default)\u001B[0m\n\u001B[0;32m--> 270\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mget\u001B[39m(\u001B[38;5;28mself\u001B[39m,k,default\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mNone\u001B[39;00m): \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43md\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget\u001B[49m\u001B[43m(\u001B[49m\u001B[43mk\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdefault\u001B[49m\u001B[43m)\u001B[49m\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/configparser.py:1307\u001B[0m, in \u001B[0;36mSectionProxy.get\u001B[0;34m(self, option, fallback, raw, vars, _impl, **kwargs)\u001B[0m\n\u001B[1;32m   1305\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m _impl:\n\u001B[1;32m   1306\u001B[0m     _impl \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parser\u001B[38;5;241m.\u001B[39mget\n\u001B[0;32m-> 1307\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43m_impl\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_name\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43moption\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mraw\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mraw\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mvars\u001B[39;49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mvars\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1308\u001B[0m \u001B[43m             \u001B[49m\u001B[43mfallback\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mfallback\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/configparser.py:800\u001B[0m, in \u001B[0;36mRawConfigParser.get\u001B[0;34m(self, section, option, raw, vars, fallback)\u001B[0m\n\u001B[1;32m    798\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m value\n\u001B[1;32m    799\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m--> 800\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_interpolation\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbefore_get\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43msection\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43moption\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mvalue\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    801\u001B[0m \u001B[43m                                          \u001B[49m\u001B[43md\u001B[49m\u001B[43m)\u001B[49m\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/configparser.py:395\u001B[0m, in \u001B[0;36mBasicInterpolation.before_get\u001B[0;34m(self, parser, section, option, value, defaults)\u001B[0m\n\u001B[1;32m    393\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mbefore_get\u001B[39m(\u001B[38;5;28mself\u001B[39m, parser, section, option, value, defaults):\n\u001B[1;32m    394\u001B[0m     L \u001B[38;5;241m=\u001B[39m []\n\u001B[0;32m--> 395\u001B[0m     \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_interpolate_some\u001B[49m\u001B[43m(\u001B[49m\u001B[43mparser\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43moption\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mL\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mvalue\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43msection\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdefaults\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m1\u001B[39;49m\u001B[43m)\u001B[49m\n\u001B[1;32m    396\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;124m'\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;241m.\u001B[39mjoin(L)\n",
      "File \u001B[0;32m~/anaconda3/envs/huggingfacegradiotest/lib/python3.10/configparser.py:434\u001B[0m, in \u001B[0;36mBasicInterpolation._interpolate_some\u001B[0;34m(self, parser, option, accum, rest, section, map, depth)\u001B[0m\n\u001B[1;32m    432\u001B[0m     v \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mmap\u001B[39m[var]\n\u001B[1;32m    433\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mKeyError\u001B[39;00m:\n\u001B[0;32m--> 434\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m InterpolationMissingOptionError(\n\u001B[1;32m    435\u001B[0m         option, section, rawval, var) \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;28mNone\u001B[39m\n\u001B[1;32m    436\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m%\u001B[39m\u001B[38;5;124m\"\u001B[39m \u001B[38;5;129;01min\u001B[39;00m v:\n\u001B[1;32m    437\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_interpolate_some(parser, option, accum, v,\n\u001B[1;32m    438\u001B[0m                            section, \u001B[38;5;28mmap\u001B[39m, depth \u001B[38;5;241m+\u001B[39m \u001B[38;5;241m1\u001B[39m)\n",
      "\u001B[0;31mInterpolationMissingOptionError\u001B[0m: Bad value substitution: option 'doc_host' in section 'DEFAULT' contains an interpolation key 'user' which is not a valid option name. Raw value: 'https://%(user)s.github.io'"
     ]
    }
   ],
   "source": [
    "nbdev_export()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}