tabular-data.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Tabular models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting fastai\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/94/58/d78c39b2fcbe3358a54a4042219eaf78bc196e771dc02a6f540ee2194a2e/fastai-1.0.59.tar.gz (3.5MB)\n",
      "\u001b[K     |████████████████████████████████| 3.5MB 800kB/s eta 0:00:01\n",
      "\u001b[?25hRequirement already satisfied: bottleneck in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (1.2.1)\n",
      "Collecting fastprogress>=0.1.19 (from fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/f0/4f/eb76f71e7da768325e029b10a443aa015236a04217ec482e861fae7ccb8f/fastprogress-0.1.22-py3-none-any.whl\n",
      "Requirement already satisfied: beautifulsoup4 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (4.7.1)\n",
      "Requirement already satisfied: matplotlib in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (3.1.0)\n",
      "Requirement already satisfied: numexpr in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (2.6.9)\n",
      "Requirement already satisfied: numpy>=1.15 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (1.16.4)\n",
      "Collecting nvidia-ml-py3 (from fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/6d/64/cce82bddb80c0b0f5c703bbdafa94bfb69a1c5ad7a79cff00b482468f0d3/nvidia-ml-py3-7.352.0.tar.gz\n",
      "Requirement already satisfied: pandas in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (0.24.2)\n",
      "Requirement already satisfied: packaging in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (19.0)\n",
      "Requirement already satisfied: Pillow in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (6.1.0)\n",
      "Requirement already satisfied: pyyaml in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (5.1.1)\n",
      "Requirement already satisfied: requests in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (2.22.0)\n",
      "Requirement already satisfied: scipy in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from fastai) (1.3.0)\n",
      "Collecting torch>=1.0.0 (from fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/7e/94/0ed9f7899aa0f5e7ff753a3a2b6944c146eef3f4cd51c59ab07c4575992b/torch-1.3.1-cp37-none-macosx_10_7_x86_64.whl (71.1MB)\n",
      "\u001b[K     |████████████████████████████████| 71.1MB 108kB/s eta 0:00:01     |███████▍                        | 16.3MB 1.2MB/s eta 0:00:45     |████████████████████▎           | 45.1MB 852kB/s eta 0:00:31     |██████████████████████▏         | 49.1MB 491kB/s eta 0:00:45\n",
      "\u001b[?25hCollecting spacy>=2.0.18 (from fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/b9/d8/26120ca4a5b1a6fe215ccb01185cee41098eb61386b3fd3a7b28c085146a/spacy-2.2.3-cp37-cp37m-macosx_10_6_intel.whl (14.2MB)\n",
      "\u001b[K     |████████████████████████████████| 14.2MB 1.0MB/s eta 0:00:01\n",
      "\u001b[?25hCollecting torchvision (from fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/fa/71/0e76ba50c8c9aeb8349d827d02278c1b5eb4da9cdc17ca26b5bd47ec034a/torchvision-0.4.2-cp37-cp37m-macosx_10_7_x86_64.whl (641kB)\n",
      "\u001b[K     |████████████████████████████████| 645kB 802kB/s eta 0:00:01\n",
      "\u001b[?25hCollecting pynvx>=1.0.0 (from fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/03/b7/37ffbba4b792a49e781322b22045f4bbd0fc6598ebf5c07a31a36b52a0b6/pynvx-1.0.0-cp37-cp37m-macosx_10_7_x86_64.whl (118kB)\n",
      "\u001b[K     |████████████████████████████████| 122kB 697kB/s eta 0:00:01\n",
      "\u001b[?25hRequirement already satisfied: soupsieve>=1.2 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from beautifulsoup4->fastai) (1.8)\n",
      "Requirement already satisfied: cycler>=0.10 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from matplotlib->fastai) (0.10.0)\n",
      "Requirement already satisfied: kiwisolver>=1.0.1 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from matplotlib->fastai) (1.1.0)\n",
      "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from matplotlib->fastai) (2.4.0)\n",
      "Requirement already satisfied: python-dateutil>=2.1 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from matplotlib->fastai) (2.8.0)\n",
      "Requirement already satisfied: pytz>=2011k in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from pandas->fastai) (2019.1)\n",
      "Requirement already satisfied: six in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from packaging->fastai) (1.12.0)\n",
      "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from requests->fastai) (3.0.4)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from requests->fastai) (2019.6.16)\n",
      "Requirement already satisfied: idna<2.9,>=2.5 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from requests->fastai) (2.8)\n",
      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from requests->fastai) (1.24.2)\n",
      "Collecting srsly<1.1.0,>=0.1.0 (from spacy>=2.0.18->fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/44/ab/fa09de5430537c12f445d049f3a2bad75cee160e81aae3455d34977c1e0e/srsly-0.2.0-cp37-cp37m-macosx_10_6_intel.whl (275kB)\n",
      "\u001b[K     |████████████████████████████████| 276kB 1.1MB/s eta 0:00:01\n",
      "\u001b[?25hCollecting catalogue<1.1.0,>=0.0.7 (from spacy>=2.0.18->fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/4f/d5/46ff975f0d7d055cf95557b944fd5d29d9dfb37a4341038e070f212b24fe/catalogue-0.0.8-py2.py3-none-any.whl\n",
      "Collecting murmurhash<1.1.0,>=0.28.0 (from spacy>=2.0.18->fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/b9/bd/faace403086ee922afc74e5615cb8c21020fcf5d5667314e943c08f71fde/murmurhash-1.0.2-cp37-cp37m-macosx_10_6_intel.macosx_10_9_intel.macosx_10_9_x86_64.macosx_10_10_intel.macosx_10_10_x86_64.whl\n",
      "Collecting thinc<7.4.0,>=7.3.0 (from spacy>=2.0.18->fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/a6/87/c7da01c45bf3c138242f19f09b987d0ffa632ac7e8508527ee34d3ebbd81/thinc-7.3.1-cp37-cp37m-macosx_10_6_intel.whl (3.0MB)\n",
      "\u001b[K     |████████████████████████████████| 3.0MB 687kB/s eta 0:00:01\n",
      "\u001b[?25hCollecting plac<1.2.0,>=0.9.6 (from spacy>=2.0.18->fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/86/85/40b8f66c2dd8f4fd9f09d59b22720cffecf1331e788b8a0cab5bafb353d1/plac-1.1.3-py2.py3-none-any.whl\n",
      "Collecting wasabi<1.1.0,>=0.4.0 (from spacy>=2.0.18->fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/3f/35/6dc35bc3b49e160a016e420eb4bdcf1c887db6fd33a463959c06a508c339/wasabi-0.4.0-py3-none-any.whl\n",
      "Requirement already satisfied: setuptools in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from spacy>=2.0.18->fastai) (41.0.1)\n",
      "Collecting blis<0.5.0,>=0.4.0 (from spacy>=2.0.18->fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/85/d8/f0be9d8ebec9cbeea1427de6ac0ecc919c0bfe881eff2d2965dbc310ca8b/blis-0.4.1-cp37-cp37m-macosx_10_6_intel.macosx_10_9_intel.macosx_10_9_x86_64.macosx_10_10_intel.macosx_10_10_x86_64.whl (4.0MB)\n",
      "\u001b[K     |████████████████████████████████| 4.0MB 897kB/s eta 0:00:01     |█████████████████████████████▉  | 3.7MB 897kB/s eta 0:00:01\n",
      "\u001b[?25hCollecting cymem<2.1.0,>=2.0.2 (from spacy>=2.0.18->fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/63/34/a8b682ee9b57db35a5fe4e179b77c1bda0f6a09745669a99cfc27aa2bed7/cymem-2.0.3-cp37-cp37m-macosx_10_6_intel.whl (54kB)\n",
      "\u001b[K     |████████████████████████████████| 61kB 1.0MB/s eta 0:00:011\n",
      "\u001b[?25hCollecting preshed<3.1.0,>=3.0.2 (from spacy>=2.0.18->fastai)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/c7/3e/9aaba1f8c0cb69e57ebeb411cc1b65b3f6bfc3572dd68969a6d3e59288f6/preshed-3.0.2-cp37-cp37m-macosx_10_6_intel.macosx_10_9_intel.macosx_10_9_x86_64.macosx_10_10_intel.macosx_10_10_x86_64.whl (211kB)\n",
      "\u001b[K     |████████████████████████████████| 215kB 691kB/s eta 0:00:01\n",
      "\u001b[?25hCollecting importlib-metadata>=0.20; python_version < \"3.8\" (from catalogue<1.1.0,>=0.0.7->spacy>=2.0.18->fastai)\n",
      "  Downloading https://files.pythonhosted.org/packages/f6/d2/40b3fa882147719744e6aa50ac39cf7a22a913cbcba86a0371176c425a3b/importlib_metadata-0.23-py2.py3-none-any.whl\n",
      "Requirement already satisfied: tqdm<5.0.0,>=4.10.0 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from thinc<7.4.0,>=7.3.0->spacy>=2.0.18->fastai) (4.32.1)\n",
      "Requirement already satisfied: zipp>=0.5 in /Users/mbutler/anaconda3/lib/python3.7/site-packages (from importlib-metadata>=0.20; python_version < \"3.8\"->catalogue<1.1.0,>=0.0.7->spacy>=2.0.18->fastai) (0.5.1)\n",
      "Building wheels for collected packages: fastai, nvidia-ml-py3\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  Building wheel for fastai (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Stored in directory: /Users/mbutler/Library/Caches/pip/wheels/45/3e/33/2286dfb90e4d3e197356552c0743678bb158d47f6e05540029\n",
      "  Building wheel for nvidia-ml-py3 (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Stored in directory: /Users/mbutler/Library/Caches/pip/wheels/e4/1d/06/640c93f5270d67d0247f30be91f232700d19023f9e66d735c7\n",
      "Successfully built fastai nvidia-ml-py3\n",
      "Installing collected packages: fastprogress, nvidia-ml-py3, torch, srsly, importlib-metadata, catalogue, murmurhash, plac, cymem, preshed, blis, wasabi, thinc, spacy, torchvision, pynvx, fastai\n",
      "  Found existing installation: importlib-metadata 0.17\n",
      "    Uninstalling importlib-metadata-0.17:\n",
      "      Successfully uninstalled importlib-metadata-0.17\n",
      "Successfully installed blis-0.4.1 catalogue-0.0.8 cymem-2.0.3 fastai-1.0.59 fastprogress-0.1.22 importlib-metadata-0.23 murmurhash-1.0.2 nvidia-ml-py3-7.352.0 plac-1.1.3 preshed-3.0.2 pynvx-1.0.0 spacy-2.2.3 srsly-0.2.0 thinc-7.3.1 torch-1.3.1 torchvision-0.4.2 wasabi-0.4.0\n"
     ]
    }
   ],
   "source": [
    "!pip install fastai\n",
    "from fastai.tabular import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "optionally write a custom proc parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# @dataclass\n",
    "# class MyFillMissing(FillMissing):\n",
    "#     fill_strategy:FillStrategy=FillStrategy.CONSTANT\n",
    "#     add_col:bool=True\n",
    "#     fill_val:float=0."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "imported tabular data should be converted to a pandas DataFrame. optionally clean up column headers by converting to lc and underscores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>caliber</th>\n",
       "      <th>range</th>\n",
       "      <th>ammo</th>\n",
       "      <th>pen</th>\n",
       "      <th>length</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.62</td>\n",
       "      <td>10</td>\n",
       "      <td>fmj</td>\n",
       "      <td>13.0</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7.62</td>\n",
       "      <td>20</td>\n",
       "      <td>fmj</td>\n",
       "      <td>13.0</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.62</td>\n",
       "      <td>40</td>\n",
       "      <td>fmj</td>\n",
       "      <td>12.0</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7.62</td>\n",
       "      <td>70</td>\n",
       "      <td>fmj</td>\n",
       "      <td>11.0</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.62</td>\n",
       "      <td>100</td>\n",
       "      <td>fmj</td>\n",
       "      <td>9.7</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   caliber  range ammo   pen  length\n",
       "0     7.62     10  fmj  13.0      39\n",
       "1     7.62     20  fmj  13.0      39\n",
       "2     7.62     40  fmj  12.0      39\n",
       "3     7.62     70  fmj  11.0      39\n",
       "4     7.62    100  fmj   9.7      39"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "path = Path('/Desktop')\n",
    "df = pd.read_csv('gunpredict.csv')\n",
    "# df.columns = df.columns.str.strip().str.lower().str.replace(' ', '_').str.replace('(', '').str.replace(')', '')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* dep_var is the dependant variable we are trying to predict\n",
    "* cat_names are categorical names\n",
    "* cont_names are continuous values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "dep_var = 'pen'\n",
    "cat_names = ['ammo']\n",
    "cont_names = ['caliber', 'range', 'length']\n",
    "procs = [FillMissing, Categorify, Normalize]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "You can deactivate this warning by passing `no_check=True`.\n"
     ]
    }
   ],
   "source": [
    "data = (TabularList.from_df(df, path=path, cat_names=cat_names, cont_names=cont_names, procs=procs)\n",
    "                           .split_by_idx(list(range(1,32)))\n",
    "                           .label_from_df(cols=dep_var)\n",
    "                           .databunch())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "ename": "StopIteration",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mStopIteration\u001b[0m                             Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-18-0ef5bf68f37d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshow_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/fastai/basic_data.py\u001b[0m in \u001b[0;36mshow_batch\u001b[0;34m(self, rows, ds_type, reverse, **kwargs)\u001b[0m\n\u001b[1;32m    183\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mshow_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrows\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mds_type\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mDatasetType\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mDatasetType\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTrain\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreverse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mbool\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m->\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    184\u001b[0m         \u001b[0;34m\"Show a batch of data in `ds_type` on a few `rows`.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 185\u001b[0;31m         \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mone_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mds_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    186\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mreverse\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    187\u001b[0m         \u001b[0mn_items\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrows\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0;36m2\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_ds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_square_show\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mrows\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/fastai/basic_data.py\u001b[0m in \u001b[0;36mone_batch\u001b[0;34m(self, ds_type, detach, denorm, cpu)\u001b[0m\n\u001b[1;32m    166\u001b[0m         \u001b[0mw\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_workers\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    167\u001b[0m         \u001b[0mdl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_workers\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 168\u001b[0;31m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m     \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdl\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    169\u001b[0m         \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mdl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_workers\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mw\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    170\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mdetach\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_detach\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcpu\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcpu\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mto_detach\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcpu\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcpu\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mStopIteration\u001b[0m: "
     ]
    }
   ],
   "source": [
    "data.show_batch(rows=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn = tabular_learner(data, layers=[200,100], metrics=accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "ename": "AssertionError",
     "evalue": "Your training dataloader is empty, can't train a model.\n        Use a smaller batch size (batch size=64 for 2 elements).",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-14-c6076a6ce3f3>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mlearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1e-2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/fastai/basic_train.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, epochs, lr, wd, callbacks)\u001b[0m\n\u001b[1;32m    198\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwd\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mwd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    199\u001b[0m         \u001b[0mcallbacks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mcb\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mcb\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_fns\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlistify\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdefaults\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextra_callback_fns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlistify\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 200\u001b[0;31m         \u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mepochs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    201\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    202\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mcreate_opt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mFloats\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwd\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mFloats\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m->\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/fastai/basic_train.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(epochs, learn, callbacks, metrics)\u001b[0m\n\u001b[1;32m     86\u001b[0m     \u001b[0;34m\"Fit the `model` on `data` and learn using `loss_func` and `opt`.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     87\u001b[0m     assert len(learn.data.train_dl) != 0, f\"\"\"Your training dataloader is empty, can't train a model.\n\u001b[0;32m---> 88\u001b[0;31m         Use a smaller batch size (batch size={learn.data.train_dl.batch_size} for {len(learn.data.train_dl.dataset)} elements).\"\"\"\n\u001b[0m\u001b[1;32m     89\u001b[0m     \u001b[0mcb_handler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCallbackHandler\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     90\u001b[0m     \u001b[0mpbar\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmaster_bar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mepochs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mAssertionError\u001b[0m: Your training dataloader is empty, can't train a model.\n        Use a smaller batch size (batch size=64 for 2 elements)."
     ]
    }
   ],
   "source": [
    "learn.fit(1, 1e-2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {},
   "outputs": [],
   "source": [
    "row = df.iloc[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Category  Married-civ-spouse"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = learn.predict(row)\n",
    "result[0]\n",
    "# result"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}