{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Given two dataframes df1 and df2, each with two columns a and b, the idea is to create a new dataframe with values in\n",
    "* df1 if an entry exists only in df1\n",
    "* df2 if an entry exists in both df1 and df2\n",
    "* df2 if an entry exists only in df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "df1\n",
      "   a   b\n",
      "0  1  18\n",
      "1  2  19\n",
      "2  3  20\n",
      "3  4  21\n",
      "4  5  22\n",
      "df2\n",
      "   a   b\n",
      "0  5  23\n",
      "1  4  24\n",
      "2  6  25\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df1 = pd.DataFrame({'a': [1,2,3,4,5], 'b': [18, 19, 20, 21, 22]})\n",
    "print('df1')\n",
    "print(df1)\n",
    "df2 = pd.DataFrame({'a': [5,4,6], 'b': [23, 24, 25]})\n",
    "print('df2')\n",
    "print(df2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>a</th>\n",
       "      <th>b_x</th>\n",
       "      <th>b_y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>18.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>19.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>20.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>21.0</td>\n",
       "      <td>24.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>22.0</td>\n",
       "      <td>23.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>NaN</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   a   b_x   b_y\n",
       "0  1  18.0   NaN\n",
       "1  2  19.0   NaN\n",
       "2  3  20.0   NaN\n",
       "3  4  21.0  24.0\n",
       "4  5  22.0  23.0\n",
       "5  6   NaN  25.0"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3 = pd.merge(df1, df2, how='outer', on='a')\n",
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "df3\n",
      "   a     b\n",
      "0  1  18.0\n",
      "1  2  19.0\n",
      "2  3  20.0\n",
      "3  4  24.0\n",
      "4  5  23.0\n",
      "5  6  25.0\n"
     ]
    }
   ],
   "source": [
    "df3.loc[df3['b_y'].isna(), 'b_y'] = df3['b_x']\n",
    "df3.drop(['b_x'], axis=1, inplace=True)\n",
    "df3.rename(columns={'b_y':'b'}, inplace=True)\n",
    "print('df3')\n",
    "print(df3)"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}