assignment_context.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e4770bb6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from pandas.core.indexing import _ScalarAccessIndexer\n",
    "\n",
    "\n",
    "class AssignmentContext(object):\n",
    "\n",
    "    def __init__(self, pandas_obj, li=None, include_loc=True):\n",
    "        self._obj = pandas_obj\n",
    "        self._set = set(li)\n",
    "        self.include_loc = include_loc\n",
    "        self._transforms = {}\n",
    "\n",
    "    def _wrapper(self, old_func):\n",
    "        def new_func(obj, key, val):\n",
    "            res = old_func(obj, key, val)\n",
    "            nonlocal self\n",
    "            if isinstance(key, (pd.Series, np.ndarray, list, pd.Index)):\n",
    "                self._set.union(key)\n",
    "            else:\n",
    "                self._set.add(key)\n",
    "            return res\n",
    "        return new_func\n",
    "\n",
    "    def _wrap(self, o):\n",
    "        old = o.__setitem__\n",
    "        o.__setitem__ = self._wrapper(o.__setitem__)\n",
    "        self._transforms[o.__setitem__] = old\n",
    "\n",
    "    def _unwrap(self, o):\n",
    "        o.__setitem__ = self._transforms.pop(o.__setitem__, None)\n",
    "\n",
    "    def __enter__(self):\n",
    "        self._wrap(pd.Series)\n",
    "        self._wrap(pd.DataFrame)\n",
    "        if self.include_loc:\n",
    "            self._wrap(_ScalarAccessIndexer)\n",
    "        return self._set\n",
    "\n",
    "    def __exit__(self, *args):\n",
    "        self._unwrap(pd.Series)\n",
    "        self._unwrap(pd.DataFrame)\n",
    "        if self.include_loc:\n",
    "            self._unwrap(_ScalarAccessIndexer)\n",
    "\n",
    "\n",
    "@pd.api.extensions.register_dataframe_accessor(\"assignment_context\")\n",
    "class AssignmentContextAccessor(object):\n",
    "\n",
    "    def __init__(self, pandas_obj):\n",
    "        self._obj = pandas_obj\n",
    "\n",
    "    def __call__(self, *args, **kwargs):\n",
    "        return AssignmentContext(self._obj, *args, **kwargs)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c01896fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame({\n",
    "    \"foo\":  [4,   5,   7,   6,   7,   7,   5],\n",
    "    \"bar\": [12,  63,  23,  36,  21,  28,  42]\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "33f22945",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"a\"] = \"please ignore me\"\n",
    "\n",
    "# Do feature transformations...\n",
    "\n",
    "with df.assignment_context() as features:\n",
    "    df[\"fizz\"] = df[\"foo\"] + df[\"bar\"]\n",
    "    df.loc[:, \"buzz\"] = 2\n",
    "\n",
    "df[\"b\"] = \"please ignore me too\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1e1793b9",
   "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>foo</th>\n",
       "      <th>bar</th>\n",
       "      <th>a</th>\n",
       "      <th>fizz</th>\n",
       "      <th>buzz</th>\n",
       "      <th>b</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4</td>\n",
       "      <td>12</td>\n",
       "      <td>please ignore me</td>\n",
       "      <td>16</td>\n",
       "      <td>2</td>\n",
       "      <td>please ignore me too</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>63</td>\n",
       "      <td>please ignore me</td>\n",
       "      <td>68</td>\n",
       "      <td>2</td>\n",
       "      <td>please ignore me too</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>23</td>\n",
       "      <td>please ignore me</td>\n",
       "      <td>30</td>\n",
       "      <td>2</td>\n",
       "      <td>please ignore me too</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6</td>\n",
       "      <td>36</td>\n",
       "      <td>please ignore me</td>\n",
       "      <td>42</td>\n",
       "      <td>2</td>\n",
       "      <td>please ignore me too</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7</td>\n",
       "      <td>21</td>\n",
       "      <td>please ignore me</td>\n",
       "      <td>28</td>\n",
       "      <td>2</td>\n",
       "      <td>please ignore me too</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   foo  bar                 a  fizz  buzz                     b\n",
       "0    4   12  please ignore me    16     2  please ignore me too\n",
       "1    5   63  please ignore me    68     2  please ignore me too\n",
       "2    7   23  please ignore me    30     2  please ignore me too\n",
       "3    6   36  please ignore me    42     2  please ignore me too\n",
       "4    7   21  please ignore me    28     2  please ignore me too"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c4e52961",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'fizz', 'buzz'}\n"
     ]
    }
   ],
   "source": [
    "# All the new variables you created within the context are here:\n",
    "\n",
    "print(features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1567016d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}