Pandas_class4.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "42efe5a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f7a245dc",
   "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>key</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   A   B\n",
       "0  K0  A0  B0\n",
       "1  K1  A1  B1\n",
       "2  K2  A2  B2\n",
       "3  K3  A3  B3"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame(\n",
    "    {\n",
    "        \"key\": [\"K0\", \"K1\", \"K2\", \"K3\"],\n",
    "        \"A\": [\"A0\", \"A1\", \"A2\", \"A3\"],\n",
    "        \"B\": [\"B0\", \"B1\", \"B2\", \"B3\"],\n",
    "    }\n",
    ")\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "31f39c1a",
   "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>key</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   C   D\n",
       "0  K0  C0  D0\n",
       "1  K1  C1  D1\n",
       "2  K2  C2  D2\n",
       "3  K3  C3  D3"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame(\n",
    "    {\n",
    "        \"key\": [\"K0\", \"K1\", \"K2\", \"K3\"],\n",
    "        \"C\": [\"C0\", \"C1\", \"C2\", \"C3\"],\n",
    "        \"D\": [\"D0\", \"D1\", \"D2\", \"D3\"],\n",
    "    }\n",
    ")\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1379a63d",
   "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>key</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   A   B   C   D\n",
       "0  K0  A0  B0  C0  D0\n",
       "1  K1  A1  B1  C1  D1\n",
       "2  K2  A2  B2  C2  D2\n",
       "3  K3  A3  B3  C3  D3"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, on=\"key\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4b1ae4d1",
   "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>key</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K3</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key   A   B   C   D\n",
       "0  K0  A0  B0  C0  D0\n",
       "1  K1  A1  B1  C1  D1\n",
       "2  K2  A2  B2  C2  D2\n",
       "3  K3  A3  B3  C3  D3"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left.merge(right, on=\"key\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b4d970d6",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K0</td>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K2</td>\n",
       "      <td>K1</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   A   B\n",
       "0   K0   K0  A0  B0\n",
       "1   K0   K1  A1  B1\n",
       "2   K1   K0  A2  B2\n",
       "3   K2   K1  A3  B3"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame(\n",
    "    {\n",
    "        \"key1\": [\"K0\", \"K0\", \"K1\", \"K2\"],\n",
    "        \"key2\": [\"K0\", \"K1\", \"K0\", \"K1\"],\n",
    "        \"A\": [\"A0\", \"A1\", \"A2\", \"A3\"],\n",
    "        \"B\": [\"B0\", \"B1\", \"B2\", \"B3\"],\n",
    "    }\n",
    ")\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "70773b8e",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K2</td>\n",
       "      <td>K0</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   C   D\n",
       "0   K0   K0  C0  D0\n",
       "1   K1   K0  C1  D1\n",
       "2   K1   K0  C2  D2\n",
       "3   K2   K0  C3  D3"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame(\n",
    "    {\n",
    "        \"key1\": [\"K0\", \"K1\", \"K1\", \"K2\"],\n",
    "        \"key2\": [\"K0\", \"K0\", \"K0\", \"K0\"],\n",
    "        \"C\": [\"C0\", \"C1\", \"C2\", \"C3\"],\n",
    "        \"D\": [\"D0\", \"D1\", \"D2\", \"D3\"],\n",
    "    }\n",
    ")\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d89fad9d",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   A   B   C   D\n",
       "0   K0   K0  A0  B0  C0  D0\n",
       "1   K1   K0  A2  B2  C1  D1\n",
       "2   K1   K0  A2  B2  C2  D2"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "87a59628",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   A   B   C   D\n",
       "0   K0   K0  A0  B0  C0  D0\n",
       "1   K1   K0  A2  B2  C1  D1\n",
       "2   K1   K0  A2  B2  C2  D2"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left.merge(right,on=[\"key1\",\"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "357598a6",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K0</td>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>K2</td>\n",
       "      <td>K1</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   A   B    C    D\n",
       "0   K0   K0  A0  B0   C0   D0\n",
       "1   K0   K1  A1  B1  NaN  NaN\n",
       "2   K1   K0  A2  B2   C1   D1\n",
       "3   K1   K0  A2  B2   C2   D2\n",
       "4   K2   K1  A3  B3  NaN  NaN"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, how=\"left\", on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e9c467c2",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K2</td>\n",
       "      <td>K0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2    A    B   C   D\n",
       "0   K0   K0   A0   B0  C0  D0\n",
       "1   K1   K0   A2   B2  C1  D1\n",
       "2   K1   K0   A2   B2  C2  D2\n",
       "3   K2   K0  NaN  NaN  C3  D3"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, how=\"right\", on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "7026ee60",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K0</td>\n",
       "      <td>K1</td>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>K2</td>\n",
       "      <td>K1</td>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>K2</td>\n",
       "      <td>K0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2    A    B    C    D\n",
       "0   K0   K0   A0   B0   C0   D0\n",
       "1   K0   K1   A1   B1  NaN  NaN\n",
       "2   K1   K0   A2   B2   C1   D1\n",
       "3   K1   K0   A2   B2   C2   D2\n",
       "4   K2   K1   A3   B3  NaN  NaN\n",
       "5   K2   K0  NaN  NaN   C3   D3"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, how=\"outer\", on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "7a7f2a86",
   "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>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key1 key2   A   B   C   D\n",
       "0   K0   K0  A0  B0  C0  D0\n",
       "1   K1   K0  A2  B2  C1  D1\n",
       "2   K1   K0  A2  B2  C2  D2"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " pd.merge(left, right, how=\"inner\", on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "12a78057",
   "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>Let</th>\n",
       "      <th>Num</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Let  Num\n",
       "0   A    1\n",
       "1   B    2\n",
       "2   C    3"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\"Let\": [\"A\", \"B\", \"C\"], \"Num\": [1, 2, 3]})\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "0f2169d7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Let  Num\n",
       "A    1      a\n",
       "B    2      b\n",
       "C    3      c\n",
       "A    4      d\n",
       "B    5      e\n",
       "C    6      f\n",
       "dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser = pd.Series(\n",
    "    [\"a\", \"b\", \"c\", \"d\", \"e\", \"f\"],\n",
    "    index=pd.MultiIndex.from_arrays(\n",
    "        [[\"A\", \"B\", \"C\"] * 2, [1, 2, 3, 4, 5, 6]], names=[\"Let\", \"Num\"]\n",
    "    ),\n",
    ")\n",
    "ser"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "c7f06fdc",
   "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>Let</th>\n",
       "      <th>Num</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A</td>\n",
       "      <td>1</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>b</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C</td>\n",
       "      <td>3</td>\n",
       "      <td>c</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A</td>\n",
       "      <td>4</td>\n",
       "      <td>d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>B</td>\n",
       "      <td>5</td>\n",
       "      <td>e</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>C</td>\n",
       "      <td>6</td>\n",
       "      <td>f</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Let  Num  0\n",
       "0   A    1  a\n",
       "1   B    2  b\n",
       "2   C    3  c\n",
       "3   A    4  d\n",
       "4   B    5  e\n",
       "5   C    6  f"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ser.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "df99eb0f",
   "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>Let</th>\n",
       "      <th>Num</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A</td>\n",
       "      <td>1</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>b</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C</td>\n",
       "      <td>3</td>\n",
       "      <td>c</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Let  Num  0\n",
       "0   A    1  a\n",
       "1   B    2  b\n",
       "2   C    3  c"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(df, ser.reset_index(), on=[\"Let\", \"Num\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "33f2d88b",
   "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></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Let</th>\n",
       "      <th>Num</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <th>2</th>\n",
       "      <td>b</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <th>3</th>\n",
       "      <td>c</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <th>4</th>\n",
       "      <td>d</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <th>5</th>\n",
       "      <td>e</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</th>\n",
       "      <th>6</th>\n",
       "      <td>f</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         0\n",
       "Let Num   \n",
       "A   1    a\n",
       "B   2    b\n",
       "C   3    c\n",
       "A   4    d\n",
       "B   5    e\n",
       "C   6    f"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(ser)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "90018a0b",
   "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>Let</th>\n",
       "      <th>Num</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A</td>\n",
       "      <td>1</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>B</td>\n",
       "      <td>2</td>\n",
       "      <td>b</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>C</td>\n",
       "      <td>3</td>\n",
       "      <td>c</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Let  Num  0\n",
       "0   A    1  a\n",
       "1   B    2  b\n",
       "2   C    3  c"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(df, pd.DataFrame(ser), left_on=[\"Let\", \"Num\"], right_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "24dac29c",
   "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</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   A  B\n",
       "0  1  2\n",
       "1  2  2"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame({\"A\": [1, 2], \"B\": [2, 2]})\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "307dac42",
   "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</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   A  B\n",
       "0  1  1\n",
       "1  2  2"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame({\"A\": [1, 2], \"B\": [1, 2]})\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "675e986b",
   "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</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   A  B\n",
       "0  4  2\n",
       "1  5  2\n",
       "2  6  2"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame({\"A\": [4, 5, 6], \"B\": [2, 2, 2]})\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "67ac23d2",
   "metadata": {},
   "outputs": [
    {
     "ename": "MergeError",
     "evalue": "Merge keys are not unique in right dataset; not a one-to-one merge",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mMergeError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32mC:\\Users\\STUDEN~1\\AppData\\Local\\Temp/ipykernel_17196/2603084156.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmerge\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mleft\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mright\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mon\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"B\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhow\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"outer\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalidate\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"one_to_one\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\reshape\\merge.py\u001b[0m in \u001b[0;36mmerge\u001b[1;34m(left, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator, validate)\u001b[0m\n\u001b[0;32m    104\u001b[0m     \u001b[0mvalidate\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mstr\u001b[0m \u001b[1;33m|\u001b[0m \u001b[1;32mNone\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    105\u001b[0m ) -> DataFrame:\n\u001b[1;32m--> 106\u001b[1;33m     op = _MergeOperation(\n\u001b[0m\u001b[0;32m    107\u001b[0m         \u001b[0mleft\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    108\u001b[0m         \u001b[0mright\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\reshape\\merge.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, left, right, how, on, left_on, right_on, axis, left_index, right_index, sort, suffixes, copy, indicator, validate)\u001b[0m\n\u001b[0;32m    707\u001b[0m         \u001b[1;31m# are in fact unique.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    708\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mvalidate\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 709\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_validate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalidate\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    710\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    711\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mget_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m->\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\pandas\\core\\reshape\\merge.py\u001b[0m in \u001b[0;36m_validate\u001b[1;34m(self, validate)\u001b[0m\n\u001b[0;32m   1427\u001b[0m                 )\n\u001b[0;32m   1428\u001b[0m             \u001b[1;32melif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mright_unique\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1429\u001b[1;33m                 raise MergeError(\n\u001b[0m\u001b[0;32m   1430\u001b[0m                     \u001b[1;34m\"Merge keys are not unique in right dataset; not a one-to-one merge\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1431\u001b[0m                 )\n",
      "\u001b[1;31mMergeError\u001b[0m: Merge keys are not unique in right dataset; not a one-to-one merge"
     ]
    }
   ],
   "source": [
    "pd.merge(left, right, on=\"B\", how=\"outer\", validate=\"one_to_one\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "802986f9",
   "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_x</th>\n",
       "      <th>B</th>\n",
       "      <th>A_y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   A_x  B  A_y\n",
       "0    1  1  NaN\n",
       "1    2  2  4.0\n",
       "2    2  2  5.0\n",
       "3    2  2  6.0"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, on=\"B\", how=\"outer\", validate=\"one_to_many\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "d5b6107e",
   "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>col1</th>\n",
       "      <th>col_left</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>b</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1 col_left\n",
       "0     0        a\n",
       "1     1        b"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame({\"col1\": [0, 1], \"col_left\": [\"a\", \"b\"]})\n",
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "b4072b74",
   "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>col1</th>\n",
       "      <th>col_right</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1  col_right\n",
       "0     1          2\n",
       "1     2          2\n",
       "2     2          2"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2 = pd.DataFrame({\"col1\": [1, 2, 2], \"col_right\": [2, 2, 2]})\n",
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "a14423aa",
   "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>col1</th>\n",
       "      <th>col_left</th>\n",
       "      <th>col_right</th>\n",
       "      <th>_merge</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>a</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>b</td>\n",
       "      <td>2.0</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>right_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>right_only</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1 col_left  col_right      _merge\n",
       "0     0        a        NaN   left_only\n",
       "1     1        b        2.0        both\n",
       "2     2      NaN        2.0  right_only\n",
       "3     2      NaN        2.0  right_only"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(df1, df2, on=\"col1\", how=\"outer\", indicator=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "91bb8ad1",
   "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>col1</th>\n",
       "      <th>col_left</th>\n",
       "      <th>col_right</th>\n",
       "      <th>indicator_column</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>a</td>\n",
       "      <td>NaN</td>\n",
       "      <td>left_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>b</td>\n",
       "      <td>2.0</td>\n",
       "      <td>both</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>right_only</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>right_only</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   col1 col_left  col_right indicator_column\n",
       "0     0        a        NaN        left_only\n",
       "1     1        b        2.0             both\n",
       "2     2      NaN        2.0       right_only\n",
       "3     2      NaN        2.0       right_only"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(df1, df2, on=\"col1\", how=\"outer\", indicator=\"indicator_column\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "ccc0b251",
   "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>key</th>\n",
       "      <th>v1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   key  v1\n",
       "0    1  10"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame({\"key\": [1], \"v1\": [10]})\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "5b6f3f88",
   "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>key</th>\n",
       "      <th>v1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   key  v1\n",
       "0    1  20\n",
       "1    2  30"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame({\"key\": [1, 2], \"v1\": [20, 30]})\n",
    "\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "81f43b62",
   "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>key</th>\n",
       "      <th>v1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   key  v1\n",
       "0    1  10\n",
       "1    1  20\n",
       "2    2  30"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge(left, right, how=\"outer\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "a28034f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    bar\n",
       "1    bar\n",
       "2    bar\n",
       "3    foo\n",
       "4    foo\n",
       "5    bar\n",
       "6    bar\n",
       "7    foo\n",
       "8    foo\n",
       "9    foo\n",
       "dtype: object"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from pandas.api.types import CategoricalDtype\n",
    "X = pd.Series(np.random.choice([\"foo\", \"bar\"], size=(10,)))\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "c8ad695d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    bar\n",
       "1    bar\n",
       "2    bar\n",
       "3    foo\n",
       "4    foo\n",
       "5    bar\n",
       "6    bar\n",
       "7    foo\n",
       "8    foo\n",
       "9    foo\n",
       "dtype: category\n",
       "Categories (2, object): ['foo', 'bar']"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = X.astype(CategoricalDtype(categories=[\"foo\", \"bar\"]))\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "2376d839",
   "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>X</th>\n",
       "      <th>Y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>bar</td>\n",
       "      <td>three</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>bar</td>\n",
       "      <td>one</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>bar</td>\n",
       "      <td>two</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>foo</td>\n",
       "      <td>two</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>foo</td>\n",
       "      <td>two</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>bar</td>\n",
       "      <td>two</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>bar</td>\n",
       "      <td>one</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>foo</td>\n",
       "      <td>one</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>foo</td>\n",
       "      <td>two</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>foo</td>\n",
       "      <td>one</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     X      Y\n",
       "0  bar  three\n",
       "1  bar    one\n",
       "2  bar    two\n",
       "3  foo    two\n",
       "4  foo    two\n",
       "5  bar    two\n",
       "6  bar    one\n",
       "7  foo    one\n",
       "8  foo    two\n",
       "9  foo    one"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame(\n",
    "    {\"X\": X, \"Y\": np.random.choice([\"one\", \"two\", \"three\"], size=(10,))}\n",
    ")\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "06853484",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "X    category\n",
       "Y      object\n",
       "dtype: object"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "df6f8b74",
   "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>X</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>foo</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>bar</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     X  Z\n",
       "0  foo  1\n",
       "1  bar  2"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame(\n",
    "    {\n",
    "        \"X\": pd.Series([\"foo\", \"bar\"], dtype=CategoricalDtype([\"foo\", \"bar\"])),\n",
    "        \"Z\": [1, 2],\n",
    "    }\n",
    ")\n",
    "\n",
    "\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "9ec1ef51",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "X    category\n",
       "Z       int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "cb6d0bf6",
   "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>X</th>\n",
       "      <th>Y</th>\n",
       "      <th>Z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>bar</td>\n",
       "      <td>three</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>bar</td>\n",
       "      <td>one</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>bar</td>\n",
       "      <td>two</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>bar</td>\n",
       "      <td>two</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>bar</td>\n",
       "      <td>one</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>foo</td>\n",
       "      <td>two</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>foo</td>\n",
       "      <td>two</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>foo</td>\n",
       "      <td>one</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>foo</td>\n",
       "      <td>two</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>foo</td>\n",
       "      <td>one</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     X      Y  Z\n",
       "0  bar  three  2\n",
       "1  bar    one  2\n",
       "2  bar    two  2\n",
       "3  bar    two  2\n",
       "4  bar    one  2\n",
       "5  foo    two  1\n",
       "6  foo    two  1\n",
       "7  foo    one  1\n",
       "8  foo    two  1\n",
       "9  foo    one  1"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = pd.merge(left, right, how=\"outer\")\n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "f54e4820",
   "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</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A   B\n",
       "K0  A0  B0\n",
       "K1  A1  B1\n",
       "K2  A2  B2"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame(\n",
    "    {\"A\": [\"A0\", \"A1\", \"A2\"], \"B\": [\"B0\", \"B1\", \"B2\"]}, index=[\"K0\", \"K1\", \"K2\"]\n",
    ")\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "ec080167",
   "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>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K3</th>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     C   D\n",
       "K0  C0  D0\n",
       "K2  C2  D2\n",
       "K3  C3  D3"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame(\n",
    "    {\"C\": [\"C0\", \"C2\", \"C3\"], \"D\": [\"D0\", \"D2\", \"D3\"]}, index=[\"K0\", \"K2\", \"K3\"]\n",
    ")\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "0d5d5613",
   "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</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A   B    C    D\n",
       "K0  A0  B0   C0   D0\n",
       "K1  A1  B1  NaN  NaN\n",
       "K2  A2  B2   C2   D2"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = left.join(right)\n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "7d9d8641",
   "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</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      A    B    C    D\n",
       "K0   A0   B0   C0   D0\n",
       "K1   A1   B1  NaN  NaN\n",
       "K2   A2   B2   C2   D2\n",
       "K3  NaN  NaN   C3   D3"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = left.join(right, how=\"outer\")\n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "ec854b29",
   "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</th>\n",
       "      <th>key1</th>\n",
       "      <th>key2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>K0</td>\n",
       "      <td>K1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>K2</td>\n",
       "      <td>K1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B key1 key2\n",
       "0  A0  B0   K0   K0\n",
       "1  A1  B1   K0   K1\n",
       "2  A2  B2   K1   K0\n",
       "3  A3  B3   K2   K1"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame(\n",
    "    {\n",
    "        \"A\": [\"A0\", \"A1\", \"A2\", \"A3\"],\n",
    "        \"B\": [\"B0\", \"B1\", \"B2\", \"B3\"],\n",
    "        \"key1\": [\"K0\", \"K0\", \"K1\", \"K2\"],\n",
    "        \"key2\": [\"K0\", \"K1\", \"K0\", \"K1\"],\n",
    "    }\n",
    ")\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "acb1e8cc",
   "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></th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>K0</th>\n",
       "      <th>K0</th>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <th>K0</th>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">K2</th>\n",
       "      <th>K0</th>\n",
       "      <td>C2</td>\n",
       "      <td>D2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>K1</th>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        C   D\n",
       "K0 K0  C0  D0\n",
       "K1 K0  C1  D1\n",
       "K2 K0  C2  D2\n",
       "   K1  C3  D3"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index = pd.MultiIndex.from_tuples(\n",
    "    [(\"K0\", \"K0\"), (\"K1\", \"K0\"), (\"K2\", \"K0\"), (\"K2\", \"K1\")]\n",
    ")\n",
    "\n",
    "right = pd.DataFrame(\n",
    "    {\"C\": [\"C0\", \"C1\", \"C2\", \"C3\"], \"D\": [\"D0\", \"D1\", \"D2\", \"D3\"]}, index=index\n",
    ")\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "8877fbbe",
   "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</th>\n",
       "      <th>key1</th>\n",
       "      <th>key2</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>A0</td>\n",
       "      <td>B0</td>\n",
       "      <td>K0</td>\n",
       "      <td>K0</td>\n",
       "      <td>C0</td>\n",
       "      <td>D0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>A1</td>\n",
       "      <td>B1</td>\n",
       "      <td>K0</td>\n",
       "      <td>K1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>A2</td>\n",
       "      <td>B2</td>\n",
       "      <td>K1</td>\n",
       "      <td>K0</td>\n",
       "      <td>C1</td>\n",
       "      <td>D1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>A3</td>\n",
       "      <td>B3</td>\n",
       "      <td>K2</td>\n",
       "      <td>K1</td>\n",
       "      <td>C3</td>\n",
       "      <td>D3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B key1 key2    C    D\n",
       "0  A0  B0   K0   K0   C0   D0\n",
       "1  A1  B1   K0   K1  NaN  NaN\n",
       "2  A2  B2   K1   K0   C1   D1\n",
       "3  A3  B3   K2   K1   C3   D3"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left.join(right, on=[\"key1\", \"key2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "895815b7",
   "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>k</th>\n",
       "      <th>lv</th>\n",
       "      <th>s</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>1</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>2</td>\n",
       "      <td>b</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K1</td>\n",
       "      <td>3</td>\n",
       "      <td>c</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K2</td>\n",
       "      <td>4</td>\n",
       "      <td>d</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    k  lv  s\n",
       "0  K0   1  a\n",
       "1  K1   2  b\n",
       "2  K1   3  c\n",
       "3  K2   4  d"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "left = pd.DataFrame(\n",
    "    {\"k\": [\"K0\", \"K1\", \"K1\", \"K2\"], \"lv\": [1, 2, 3, 4], \"s\": [\"a\", \"b\", \"c\", \"d\"]}\n",
    ")\n",
    "left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "e442c016",
   "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>k</th>\n",
       "      <th>rv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K4</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    k  rv\n",
       "0  K1   1\n",
       "1  K2   2\n",
       "2  K4   3"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "right = pd.DataFrame({\"k\": [\"K1\", \"K2\", \"K4\"], \"rv\": [1, 2, 3]})\n",
    "right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "91d91791",
   "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>k</th>\n",
       "      <th>lv</th>\n",
       "      <th>s</th>\n",
       "      <th>rv</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>K0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>a</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>K1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>a</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>K2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>a</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>K4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>a</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>K1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>b</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>K2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>b</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>K4</td>\n",
       "      <td>2.0</td>\n",
       "      <td>b</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>K1</td>\n",
       "      <td>3.0</td>\n",
       "      <td>c</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>K2</td>\n",
       "      <td>3.0</td>\n",
       "      <td>c</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>K4</td>\n",
       "      <td>3.0</td>\n",
       "      <td>c</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>K1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>d</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>K2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>d</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>K4</td>\n",
       "      <td>4.0</td>\n",
       "      <td>d</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     k   lv  s   rv\n",
       "0   K0  1.0  a  NaN\n",
       "1   K1  1.0  a  1.0\n",
       "2   K2  1.0  a  2.0\n",
       "3   K4  1.0  a  3.0\n",
       "4   K1  2.0  b  1.0\n",
       "5   K2  2.0  b  2.0\n",
       "6   K4  2.0  b  3.0\n",
       "7   K1  3.0  c  1.0\n",
       "8   K2  3.0  c  2.0\n",
       "9   K4  3.0  c  3.0\n",
       "10  K1  NaN  d  1.0\n",
       "11  K2  4.0  d  2.0\n",
       "12  K4  4.0  d  3.0"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge_ordered(left, right, fill_method=\"ffill\", left_by=\"s\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b2b7adb",
   "metadata": {},
   "source": [
    "# Timeseries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "734ce35e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5 entries, 0 to 4\n",
      "Data columns (total 4 columns):\n",
      " #   Column    Non-Null Count  Dtype         \n",
      "---  ------    --------------  -----         \n",
      " 0   time      5 non-null      datetime64[ns]\n",
      " 1   ticker    5 non-null      object        \n",
      " 2   price     5 non-null      float64       \n",
      " 3   quantity  5 non-null      int64         \n",
      "dtypes: datetime64[ns](1), float64(1), int64(1), object(1)\n",
      "memory usage: 288.0+ bytes\n"
     ]
    },
    {
     "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>time</th>\n",
       "      <th>ticker</th>\n",
       "      <th>price</th>\n",
       "      <th>quantity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-05-25 13:30:00.023</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016-05-25 13:30:00.038</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.77</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.92</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>98.00</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     time ticker   price  quantity\n",
       "0 2016-05-25 13:30:00.023   MSFT   51.95        75\n",
       "1 2016-05-25 13:30:00.038   MSFT   51.95       155\n",
       "2 2016-05-25 13:30:00.048   GOOG  720.77       100\n",
       "3 2016-05-25 13:30:00.048   GOOG  720.92       100\n",
       "4 2016-05-25 13:30:00.048   AAPL   98.00       100"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trades = pd.DataFrame(\n",
    "    {\n",
    "        \"time\": pd.to_datetime(\n",
    "            [\n",
    "                \"20160525 13:30:00.023\",\n",
    "                \"20160525 13:30:00.038\",\n",
    "                \"20160525 13:30:00.048\",\n",
    "                \"20160525 13:30:00.048\",\n",
    "                \"20160525 13:30:00.048\",\n",
    "            ]\n",
    "        ),\n",
    "        \"ticker\": [\"MSFT\", \"MSFT\", \"GOOG\", \"GOOG\", \"AAPL\"],\n",
    "        \"price\": [51.95, 51.95, 720.77, 720.92, 98.00],\n",
    "        \"quantity\": [75, 155, 100, 100, 100],\n",
    "    },\n",
    "    columns=[\"time\", \"ticker\", \"price\", \"quantity\"],\n",
    ")\n",
    "trades.info()\n",
    "trades"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "a4847e01",
   "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>time</th>\n",
       "      <th>ticker</th>\n",
       "      <th>bid</th>\n",
       "      <th>ask</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-05-25 13:30:00.023</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016-05-25 13:30:00.023</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>51.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2016-05-25 13:30:00.030</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.97</td>\n",
       "      <td>51.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016-05-25 13:30:00.041</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.99</td>\n",
       "      <td>52.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2016-05-25 13:30:00.049</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>97.99</td>\n",
       "      <td>98.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2016-05-25 13:30:00.072</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.88</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2016-05-25 13:30:00.075</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>52.01</td>\n",
       "      <td>52.03</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     time ticker     bid     ask\n",
       "0 2016-05-25 13:30:00.023   GOOG  720.50  720.93\n",
       "1 2016-05-25 13:30:00.023   MSFT   51.95   51.96\n",
       "2 2016-05-25 13:30:00.030   MSFT   51.97   51.98\n",
       "3 2016-05-25 13:30:00.041   MSFT   51.99   52.00\n",
       "4 2016-05-25 13:30:00.048   GOOG  720.50  720.93\n",
       "5 2016-05-25 13:30:00.049   AAPL   97.99   98.01\n",
       "6 2016-05-25 13:30:00.072   GOOG  720.50  720.88\n",
       "7 2016-05-25 13:30:00.075   MSFT   52.01   52.03"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "quotes = pd.DataFrame(\n",
    "    {\n",
    "        \"time\": pd.to_datetime(\n",
    "            [\n",
    "                \"20160525 13:30:00.023\",\n",
    "                \"20160525 13:30:00.023\",\n",
    "                \"20160525 13:30:00.030\",\n",
    "                \"20160525 13:30:00.041\",\n",
    "                \"20160525 13:30:00.048\",\n",
    "                \"20160525 13:30:00.049\",\n",
    "                \"20160525 13:30:00.072\",\n",
    "                \"20160525 13:30:00.075\",\n",
    "            ]\n",
    "        ),\n",
    "        \"ticker\": [\"GOOG\", \"MSFT\", \"MSFT\", \"MSFT\", \"GOOG\", \"AAPL\", \"GOOG\", \"MSFT\"],\n",
    "        \"bid\": [720.50, 51.95, 51.97, 51.99, 720.50, 97.99, 720.50, 52.01],\n",
    "        \"ask\": [720.93, 51.96, 51.98, 52.00, 720.93, 98.01, 720.88, 52.03],\n",
    "    },\n",
    "    columns=[\"time\", \"ticker\", \"bid\", \"ask\"],\n",
    ")\n",
    "quotes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "4ba18d1c",
   "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>time</th>\n",
       "      <th>ticker</th>\n",
       "      <th>price</th>\n",
       "      <th>quantity</th>\n",
       "      <th>bid</th>\n",
       "      <th>ask</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-05-25 13:30:00.023</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>75</td>\n",
       "      <td>51.95</td>\n",
       "      <td>51.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016-05-25 13:30:00.038</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>155</td>\n",
       "      <td>51.97</td>\n",
       "      <td>51.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.77</td>\n",
       "      <td>100</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.92</td>\n",
       "      <td>100</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>98.00</td>\n",
       "      <td>100</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     time ticker   price  quantity     bid     ask\n",
       "0 2016-05-25 13:30:00.023   MSFT   51.95        75   51.95   51.96\n",
       "1 2016-05-25 13:30:00.038   MSFT   51.95       155   51.97   51.98\n",
       "2 2016-05-25 13:30:00.048   GOOG  720.77       100  720.50  720.93\n",
       "3 2016-05-25 13:30:00.048   GOOG  720.92       100  720.50  720.93\n",
       "4 2016-05-25 13:30:00.048   AAPL   98.00       100     NaN     NaN"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge_asof(trades, quotes, on=\"time\", by=\"ticker\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "ab466f96",
   "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>time</th>\n",
       "      <th>ticker</th>\n",
       "      <th>price</th>\n",
       "      <th>quantity</th>\n",
       "      <th>bid</th>\n",
       "      <th>ask</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-05-25 13:30:00.023</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>75</td>\n",
       "      <td>51.95</td>\n",
       "      <td>51.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016-05-25 13:30:00.038</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>155</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.77</td>\n",
       "      <td>100</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.92</td>\n",
       "      <td>100</td>\n",
       "      <td>720.50</td>\n",
       "      <td>720.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>98.00</td>\n",
       "      <td>100</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     time ticker   price  quantity     bid     ask\n",
       "0 2016-05-25 13:30:00.023   MSFT   51.95        75   51.95   51.96\n",
       "1 2016-05-25 13:30:00.038   MSFT   51.95       155     NaN     NaN\n",
       "2 2016-05-25 13:30:00.048   GOOG  720.77       100  720.50  720.93\n",
       "3 2016-05-25 13:30:00.048   GOOG  720.92       100  720.50  720.93\n",
       "4 2016-05-25 13:30:00.048   AAPL   98.00       100     NaN     NaN"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge_asof(trades, quotes, on=\"time\", by=\"ticker\", tolerance=pd.Timedelta(\"2ms\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "98eb5dd7",
   "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>time</th>\n",
       "      <th>ticker</th>\n",
       "      <th>price</th>\n",
       "      <th>quantity</th>\n",
       "      <th>bid</th>\n",
       "      <th>ask</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-05-25 13:30:00.023</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>75</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016-05-25 13:30:00.038</td>\n",
       "      <td>MSFT</td>\n",
       "      <td>51.95</td>\n",
       "      <td>155</td>\n",
       "      <td>51.97</td>\n",
       "      <td>51.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.77</td>\n",
       "      <td>100</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>GOOG</td>\n",
       "      <td>720.92</td>\n",
       "      <td>100</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2016-05-25 13:30:00.048</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>98.00</td>\n",
       "      <td>100</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     time ticker   price  quantity    bid    ask\n",
       "0 2016-05-25 13:30:00.023   MSFT   51.95        75    NaN    NaN\n",
       "1 2016-05-25 13:30:00.038   MSFT   51.95       155  51.97  51.98\n",
       "2 2016-05-25 13:30:00.048   GOOG  720.77       100    NaN    NaN\n",
       "3 2016-05-25 13:30:00.048   GOOG  720.92       100    NaN    NaN\n",
       "4 2016-05-25 13:30:00.048   AAPL   98.00       100    NaN    NaN"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.merge_asof(\n",
    "    trades,\n",
    "    quotes,\n",
    "    on=\"time\",\n",
    "    by=\"ticker\",\n",
    "    tolerance=pd.Timedelta(\"10ms\"),\n",
    "    allow_exact_matches=False,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "07a3a71f",
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>b</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>b</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>a</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  col1  col2  col3\n",
       "0    a   1.0   1.0\n",
       "1    a   2.0   2.0\n",
       "2    b   3.0   3.0\n",
       "3    b   NaN   4.0\n",
       "4    a   5.0   5.0"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(\n",
    "    {\n",
    "        \"col1\": [\"a\", \"a\", \"b\", \"b\", \"a\"],\n",
    "        \"col2\": [1.0, 2.0, 3.0, np.nan, 5.0],\n",
    "        \"col3\": [1.0, 2.0, 3.0, 4.0, 5.0],\n",
    "    },\n",
    "    columns=[\"col1\", \"col2\", \"col3\"],\n",
    ")\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "b6e20282",
   "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>col1</th>\n",
       "      <th>col2</th>\n",
       "      <th>col3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>c</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>b</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>b</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>a</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  col1  col2  col3\n",
       "0    c   1.0   1.0\n",
       "1    a   2.0   2.0\n",
       "2    b   3.0   4.0\n",
       "3    b   NaN   4.0\n",
       "4    a   5.0   5.0"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2 = df.copy()\n",
    "df2.loc[0, \"col1\"] = \"c\"\n",
    "df2.loc[2, \"col3\"] = 4.0\n",
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "16343d9a",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"2\" halign=\"left\">col1</th>\n",
       "      <th colspan=\"2\" halign=\"left\">col3</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>self</th>\n",
       "      <th>other</th>\n",
       "      <th>self</th>\n",
       "      <th>other</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "      <td>c</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  col1       col3      \n",
       "  self other self other\n",
       "0    a     c  NaN   NaN\n",
       "2  NaN   NaN  3.0   4.0"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.compare(df2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "7c5b8e37",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas._testing as tm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "63bce4c2",
   "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>date</th>\n",
       "      <th>variable</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2000-01-03</td>\n",
       "      <td>A</td>\n",
       "      <td>0.688302</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2000-01-04</td>\n",
       "      <td>A</td>\n",
       "      <td>-0.537509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2000-01-05</td>\n",
       "      <td>A</td>\n",
       "      <td>0.504792</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2000-01-03</td>\n",
       "      <td>B</td>\n",
       "      <td>1.021045</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2000-01-04</td>\n",
       "      <td>B</td>\n",
       "      <td>-0.986063</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2000-01-05</td>\n",
       "      <td>B</td>\n",
       "      <td>-0.851493</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2000-01-03</td>\n",
       "      <td>C</td>\n",
       "      <td>1.035432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2000-01-04</td>\n",
       "      <td>C</td>\n",
       "      <td>-0.037097</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2000-01-05</td>\n",
       "      <td>C</td>\n",
       "      <td>-0.122934</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2000-01-03</td>\n",
       "      <td>D</td>\n",
       "      <td>-0.681756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2000-01-04</td>\n",
       "      <td>D</td>\n",
       "      <td>1.372213</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>2000-01-05</td>\n",
       "      <td>D</td>\n",
       "      <td>-1.308477</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date variable     value\n",
       "0  2000-01-03        A  0.688302\n",
       "1  2000-01-04        A -0.537509\n",
       "2  2000-01-05        A  0.504792\n",
       "3  2000-01-03        B  1.021045\n",
       "4  2000-01-04        B -0.986063\n",
       "5  2000-01-05        B -0.851493\n",
       "6  2000-01-03        C  1.035432\n",
       "7  2000-01-04        C -0.037097\n",
       "8  2000-01-05        C -0.122934\n",
       "9  2000-01-03        D -0.681756\n",
       "10 2000-01-04        D  1.372213\n",
       "11 2000-01-05        D -1.308477"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def unpivot(frame):\n",
    "    N, K = frame.shape\n",
    "    data = {\n",
    "        \"value\": frame.to_numpy().ravel(\"F\"),\n",
    "        \"variable\": np.asarray(frame.columns).repeat(N),\n",
    "        \"date\": np.tile(np.asarray(frame.index), K),\n",
    "    }\n",
    "    return pd.DataFrame(data, columns=[\"date\", \"variable\", \"value\"])\n",
    "df = unpivot(tm.makeTimeDataFrame(3))\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "84fde2e2",
   "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</th>\n",
       "      <th>C</th>\n",
       "      <th>D</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2000-01-03</th>\n",
       "      <td>0.255721</td>\n",
       "      <td>-0.223551</td>\n",
       "      <td>0.109370</td>\n",
       "      <td>0.235514</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-04</th>\n",
       "      <td>-0.694514</td>\n",
       "      <td>-0.028784</td>\n",
       "      <td>1.498927</td>\n",
       "      <td>0.182244</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2000-01-05</th>\n",
       "      <td>-0.154954</td>\n",
       "      <td>-0.834596</td>\n",
       "      <td>-1.118079</td>\n",
       "      <td>0.088687</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   A         B         C         D\n",
       "2000-01-03  0.255721 -0.223551  0.109370  0.235514\n",
       "2000-01-04 -0.694514 -0.028784  1.498927  0.182244\n",
       "2000-01-05 -0.154954 -0.834596 -1.118079  0.088687"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tm.makeTimeDataFrame(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "f7532538",
   "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></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th>second</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">bar</th>\n",
       "      <th>one</th>\n",
       "      <td>-1.230439</td>\n",
       "      <td>-0.279879</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>-0.278642</td>\n",
       "      <td>0.135579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">baz</th>\n",
       "      <th>one</th>\n",
       "      <td>0.158262</td>\n",
       "      <td>-0.492528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>0.754294</td>\n",
       "      <td>0.726975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     A         B\n",
       "first second                    \n",
       "bar   one    -1.230439 -0.279879\n",
       "      two    -0.278642  0.135579\n",
       "baz   one     0.158262 -0.492528\n",
       "      two     0.754294  0.726975"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tuples = list(\n",
    "    zip(\n",
    "        *[\n",
    "            [\"bar\", \"bar\", \"baz\", \"baz\", \"foo\", \"foo\", \"qux\", \"qux\"],\n",
    "            [\"one\", \"two\", \"one\", \"two\", \"one\", \"two\", \"one\", \"two\"],\n",
    "        ]\n",
    "    )\n",
    ")\n",
    "\n",
    "\n",
    "index = pd.MultiIndex.from_tuples(tuples, names=[\"first\", \"second\"])\n",
    "\n",
    "df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=[\"A\", \"B\"])\n",
    "\n",
    "df2 = df[:4]\n",
    "\n",
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "93f7b9f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "first  second   \n",
       "bar    one     A   -1.230439\n",
       "               B   -0.279879\n",
       "       two     A   -0.278642\n",
       "               B    0.135579\n",
       "baz    one     A    0.158262\n",
       "               B   -0.492528\n",
       "       two     A    0.754294\n",
       "               B    0.726975\n",
       "dtype: float64"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stacked = df2.stack()\n",
    "\n",
    "stacked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "1310d6a3",
   "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></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th>second</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">bar</th>\n",
       "      <th>one</th>\n",
       "      <td>-1.230439</td>\n",
       "      <td>-0.279879</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>-0.278642</td>\n",
       "      <td>0.135579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">baz</th>\n",
       "      <th>one</th>\n",
       "      <td>0.158262</td>\n",
       "      <td>-0.492528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>0.754294</td>\n",
       "      <td>0.726975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     A         B\n",
       "first second                    \n",
       "bar   one    -1.230439 -0.279879\n",
       "      two    -0.278642  0.135579\n",
       "baz   one     0.158262 -0.492528\n",
       "      two     0.754294  0.726975"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stacked.unstack()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "b454e8a6",
   "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>second</th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">bar</th>\n",
       "      <th>A</th>\n",
       "      <td>-1.230439</td>\n",
       "      <td>-0.278642</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-0.279879</td>\n",
       "      <td>0.135579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">baz</th>\n",
       "      <th>A</th>\n",
       "      <td>0.158262</td>\n",
       "      <td>0.754294</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-0.492528</td>\n",
       "      <td>0.726975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "second        one       two\n",
       "first                      \n",
       "bar   A -1.230439 -0.278642\n",
       "      B -0.279879  0.135579\n",
       "baz   A  0.158262  0.754294\n",
       "      B -0.492528  0.726975"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stacked.unstack(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "0ff01fc6",
   "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></th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th>second</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">bar</th>\n",
       "      <th>one</th>\n",
       "      <td>-1.230439</td>\n",
       "      <td>-0.279879</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>-0.278642</td>\n",
       "      <td>0.135579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">baz</th>\n",
       "      <th>one</th>\n",
       "      <td>0.158262</td>\n",
       "      <td>-0.492528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>0.754294</td>\n",
       "      <td>0.726975</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     A         B\n",
       "first second                    \n",
       "bar   one    -1.230439 -0.279879\n",
       "      two    -0.278642  0.135579\n",
       "baz   one     0.158262 -0.492528\n",
       "      two     0.754294  0.726975"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stacked.unstack()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "8a0982d2",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>exp</th>\n",
       "      <th>A</th>\n",
       "      <th colspan=\"2\" halign=\"left\">B</th>\n",
       "      <th>A</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>animal</th>\n",
       "      <th>cat</th>\n",
       "      <th>dog</th>\n",
       "      <th>cat</th>\n",
       "      <th>dog</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th>second</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">bar</th>\n",
       "      <th>one</th>\n",
       "      <td>1.085138</td>\n",
       "      <td>-0.304281</td>\n",
       "      <td>1.397974</td>\n",
       "      <td>-0.712037</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>1.640976</td>\n",
       "      <td>-0.932649</td>\n",
       "      <td>-0.479171</td>\n",
       "      <td>-0.115656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>baz</th>\n",
       "      <th>one</th>\n",
       "      <td>1.457866</td>\n",
       "      <td>-1.339071</td>\n",
       "      <td>0.031853</td>\n",
       "      <td>0.595333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">foo</th>\n",
       "      <th>one</th>\n",
       "      <td>1.372629</td>\n",
       "      <td>0.073561</td>\n",
       "      <td>-0.919377</td>\n",
       "      <td>-0.670125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>-0.865772</td>\n",
       "      <td>0.695429</td>\n",
       "      <td>0.270404</td>\n",
       "      <td>-0.900696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qux</th>\n",
       "      <th>two</th>\n",
       "      <td>1.443268</td>\n",
       "      <td>-0.427578</td>\n",
       "      <td>0.507008</td>\n",
       "      <td>-0.124691</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "exp                  A         B                   A\n",
       "animal             cat       dog       cat       dog\n",
       "first second                                        \n",
       "bar   one     1.085138 -0.304281  1.397974 -0.712037\n",
       "      two     1.640976 -0.932649 -0.479171 -0.115656\n",
       "baz   one     1.457866 -1.339071  0.031853  0.595333\n",
       "foo   one     1.372629  0.073561 -0.919377 -0.670125\n",
       "      two    -0.865772  0.695429  0.270404 -0.900696\n",
       "qux   two     1.443268 -0.427578  0.507008 -0.124691"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns = pd.MultiIndex.from_tuples(\n",
    "    [\n",
    "        (\"A\", \"cat\"),\n",
    "        (\"B\", \"dog\"),\n",
    "        (\"B\", \"cat\"),\n",
    "        (\"A\", \"dog\"),\n",
    "    ],\n",
    "    names=[\"exp\", \"animal\"],\n",
    ")\n",
    "\n",
    "\n",
    "index = pd.MultiIndex.from_product(\n",
    "    [(\"bar\", \"baz\", \"foo\", \"qux\"), (\"one\", \"two\")], names=[\"first\", \"second\"]\n",
    ")\n",
    "\n",
    "\n",
    "df = pd.DataFrame(np.random.randn(8, 4), index=index, columns=columns)\n",
    "\n",
    "df2 = df.iloc[[0, 1, 2, 4, 5, 7]]\n",
    "\n",
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "61861744",
   "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></th>\n",
       "      <th>animal</th>\n",
       "      <th>cat</th>\n",
       "      <th>dog</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th>second</th>\n",
       "      <th>exp</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">bar</th>\n",
       "      <th rowspan=\"2\" valign=\"top\">one</th>\n",
       "      <th>A</th>\n",
       "      <td>1.085138</td>\n",
       "      <td>-0.712037</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>1.397974</td>\n",
       "      <td>-0.304281</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">two</th>\n",
       "      <th>A</th>\n",
       "      <td>1.640976</td>\n",
       "      <td>-0.115656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-0.479171</td>\n",
       "      <td>-0.932649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">baz</th>\n",
       "      <th rowspan=\"2\" valign=\"top\">one</th>\n",
       "      <th>A</th>\n",
       "      <td>1.457866</td>\n",
       "      <td>0.595333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.031853</td>\n",
       "      <td>-1.339071</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"4\" valign=\"top\">foo</th>\n",
       "      <th rowspan=\"2\" valign=\"top\">one</th>\n",
       "      <th>A</th>\n",
       "      <td>1.372629</td>\n",
       "      <td>-0.670125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>-0.919377</td>\n",
       "      <td>0.073561</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">two</th>\n",
       "      <th>A</th>\n",
       "      <td>-0.865772</td>\n",
       "      <td>-0.900696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.270404</td>\n",
       "      <td>0.695429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">qux</th>\n",
       "      <th rowspan=\"2\" valign=\"top\">two</th>\n",
       "      <th>A</th>\n",
       "      <td>1.443268</td>\n",
       "      <td>-0.124691</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.507008</td>\n",
       "      <td>-0.427578</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "animal                 cat       dog\n",
       "first second exp                    \n",
       "bar   one    A    1.085138 -0.712037\n",
       "             B    1.397974 -0.304281\n",
       "      two    A    1.640976 -0.115656\n",
       "             B   -0.479171 -0.932649\n",
       "baz   one    A    1.457866  0.595333\n",
       "             B    0.031853 -1.339071\n",
       "foo   one    A    1.372629 -0.670125\n",
       "             B   -0.919377  0.073561\n",
       "      two    A   -0.865772 -0.900696\n",
       "             B    0.270404  0.695429\n",
       "qux   two    A    1.443268 -0.124691\n",
       "             B    0.507008 -0.427578"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2.stack(\"exp\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "7b5593d3",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>exp</th>\n",
       "      <th colspan=\"2\" halign=\"left\">B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>animal</th>\n",
       "      <th>dog</th>\n",
       "      <th>cat</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th>second</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">bar</th>\n",
       "      <th>one</th>\n",
       "      <td>-0.304281</td>\n",
       "      <td>1.397974</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two</th>\n",
       "      <td>-0.932649</td>\n",
       "      <td>-0.479171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>foo</th>\n",
       "      <th>one</th>\n",
       "      <td>0.073561</td>\n",
       "      <td>-0.919377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qux</th>\n",
       "      <th>two</th>\n",
       "      <td>-0.427578</td>\n",
       "      <td>0.507008</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "exp                  B          \n",
       "animal             dog       cat\n",
       "first second                    \n",
       "bar   one    -0.304281  1.397974\n",
       "      two    -0.932649 -0.479171\n",
       "foo   one     0.073561 -0.919377\n",
       "qux   two    -0.427578  0.507008"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3 = df.iloc[[0, 1, 4, 7], [1, 2]]\n",
    "\n",
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "135fef49",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>exp</th>\n",
       "      <th colspan=\"4\" halign=\"left\">B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>animal</th>\n",
       "      <th colspan=\"2\" halign=\"left\">dog</th>\n",
       "      <th colspan=\"2\" halign=\"left\">cat</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>bar</th>\n",
       "      <td>-0.304281</td>\n",
       "      <td>-0.932649</td>\n",
       "      <td>1.397974</td>\n",
       "      <td>-0.479171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>foo</th>\n",
       "      <td>0.073561</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.919377</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qux</th>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.427578</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.507008</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "exp            B                              \n",
       "animal       dog                 cat          \n",
       "second       one       two       one       two\n",
       "first                                         \n",
       "bar    -0.304281 -0.932649  1.397974 -0.479171\n",
       "foo     0.073561       NaN -0.919377       NaN\n",
       "qux          NaN -0.427578       NaN  0.507008"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.unstack()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "0360fcbb",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th>exp</th>\n",
       "      <th colspan=\"4\" halign=\"left\">B</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>animal</th>\n",
       "      <th colspan=\"2\" halign=\"left\">dog</th>\n",
       "      <th colspan=\"2\" halign=\"left\">cat</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>bar</th>\n",
       "      <td>-0.304281</td>\n",
       "      <td>-0.932649</td>\n",
       "      <td>1.397974</td>\n",
       "      <td>-0.479171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>foo</th>\n",
       "      <td>0.073561</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.919377</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qux</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.427578</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.507008</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "exp            B                              \n",
       "animal       dog                 cat          \n",
       "second       one       two       one       two\n",
       "first                                         \n",
       "bar    -0.304281 -0.932649  1.397974 -0.479171\n",
       "foo     0.073561  0.000000 -0.919377  0.000000\n",
       "qux     0.000000 -0.427578  0.000000  0.507008"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3.unstack(fill_value=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f0c42b58",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}