{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "df1 = pd.read_csv('../data/concat_1.csv')\n",
    "df2 = pd.read_csv('../data/concat_2.csv')\n",
    "df3 = pd.read_csv('../data/concat_3.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\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>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  a0  b0  c0  d0\n",
       "1  a1  b1  c1  d1\n",
       "2  a2  b2  c2  d2\n",
       "3  a3  b3  c3  d3"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  a4  b4  c4  d4\n",
       "1  a5  b5  c5  d5\n",
       "2  a6  b6  c6  d6\n",
       "3  a7  b7  c7  d7"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a9</td>\n",
       "      <td>b9</td>\n",
       "      <td>c9</td>\n",
       "      <td>d9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a10</td>\n",
       "      <td>b10</td>\n",
       "      <td>c10</td>\n",
       "      <td>d10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a11</td>\n",
       "      <td>b11</td>\n",
       "      <td>c11</td>\n",
       "      <td>d11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B    C    D\n",
       "0   a8   b8   c8   d8\n",
       "1   a9   b9   c9   d9\n",
       "2  a10  b10  c10  d10\n",
       "3  a11  b11  c11  d11"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\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>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a9</td>\n",
       "      <td>b9</td>\n",
       "      <td>c9</td>\n",
       "      <td>d9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a10</td>\n",
       "      <td>b10</td>\n",
       "      <td>c10</td>\n",
       "      <td>d10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a11</td>\n",
       "      <td>b11</td>\n",
       "      <td>c11</td>\n",
       "      <td>d11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B    C    D\n",
       "0   a0   b0   c0   d0\n",
       "1   a1   b1   c1   d1\n",
       "2   a2   b2   c2   d2\n",
       "3   a3   b3   c3   d3\n",
       "0   a4   b4   c4   d4\n",
       "1   a5   b5   c5   d5\n",
       "2   a6   b6   c6   d6\n",
       "3   a7   b7   c7   d7\n",
       "0   a8   b8   c8   d8\n",
       "1   a9   b9   c9   d9\n",
       "2  a10  b10  c10  d10\n",
       "3  a11  b11  c11  d11"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "row_concat = pd.concat([df1, df2, df3])\n",
    "row_concat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\n",
       "      <td>a0</td>\n",
       "      <td>b0</td>\n",
       "      <td>c0</td>\n",
       "      <td>d0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  a0  b0  c0  d0\n",
       "0  a4  b4  c4  d4\n",
       "0  a8  b8  c8  d8"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "row_concat.loc[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    a0\n",
       "B    b0\n",
       "C    c0\n",
       "D    d0\n",
       "Name: 0, dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "row_concat.iloc[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Danie\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:1: DeprecationWarning: \n",
      ".ix is deprecated. Please use\n",
      ".loc for label based indexing or\n",
      ".iloc for positional indexing\n",
      "\n",
      "See the documentation here:\n",
      "http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated\n",
      "  \"\"\"Entry point for launching an IPython kernel.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\n",
       "      <td>a0</td>\n",
       "      <td>b0</td>\n",
       "      <td>c0</td>\n",
       "      <td>d0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  a0  b0  c0  d0\n",
       "0  a4  b4  c4  d4\n",
       "0  a8  b8  c8  d8"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "row_concat.ix[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\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>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>a9</td>\n",
       "      <td>b9</td>\n",
       "      <td>c9</td>\n",
       "      <td>d9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>a10</td>\n",
       "      <td>b10</td>\n",
       "      <td>c10</td>\n",
       "      <td>d10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>a11</td>\n",
       "      <td>b11</td>\n",
       "      <td>c11</td>\n",
       "      <td>d11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      A    B    C    D\n",
       "0    a0   b0   c0   d0\n",
       "1    a1   b1   c1   d1\n",
       "2    a2   b2   c2   d2\n",
       "3    a3   b3   c3   d3\n",
       "4    a4   b4   c4   d4\n",
       "5    a5   b5   c5   d5\n",
       "6    a6   b6   c6   d6\n",
       "7    a7   b7   c7   d7\n",
       "8    a8   b8   c8   d8\n",
       "9    a9   b9   c9   d9\n",
       "10  a10  b10  c10  d10\n",
       "11  a11  b11  c11  d11"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "row_concat_reset = pd.concat([df1, df2, df3], ignore_index=True)\n",
    "row_concat_reset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    n1\n",
       "1    n2\n",
       "2    n3\n",
       "3    n4\n",
       "dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_row_series = pd.Series(['n1', 'n2', 'n3', 'n4'])\n",
    "new_row_series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a0</td>\n",
       "      <td>b0</td>\n",
       "      <td>c0</td>\n",
       "      <td>d0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a2</td>\n",
       "      <td>b2</td>\n",
       "      <td>c2</td>\n",
       "      <td>d2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>n1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>n2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>n3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>n4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B    C    D    0\n",
       "0   a0   b0   c0   d0  NaN\n",
       "1   a1   b1   c1   d1  NaN\n",
       "2   a2   b2   c2   d2  NaN\n",
       "3   a3   b3   c3   d3  NaN\n",
       "0  NaN  NaN  NaN  NaN   n1\n",
       "1  NaN  NaN  NaN  NaN   n2\n",
       "2  NaN  NaN  NaN  NaN   n3\n",
       "3  NaN  NaN  NaN  NaN   n4"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([df1, new_row_series])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\n",
       "      <td>n1</td>\n",
       "      <td>n2</td>\n",
       "      <td>n3</td>\n",
       "      <td>n4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  n1  n2  n3  n4"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_row_data = pd.DataFrame([['n1', 'n2', 'n3', 'n4']],\n",
    "                            columns=['A', 'B', 'C', 'D'])\n",
    "new_row_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\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>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>n1</td>\n",
       "      <td>n2</td>\n",
       "      <td>n3</td>\n",
       "      <td>n4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  a0  b0  c0  d0\n",
       "1  a1  b1  c1  d1\n",
       "2  a2  b2  c2  d2\n",
       "3  a3  b3  c3  d3\n",
       "0  n1  n2  n3  n4"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([df1, new_row_data])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "      <th>D</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>a0</td>\n",
       "      <td>b0</td>\n",
       "      <td>c0</td>\n",
       "      <td>d0</td>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "      <td>a9</td>\n",
       "      <td>b9</td>\n",
       "      <td>c9</td>\n",
       "      <td>d9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a2</td>\n",
       "      <td>b2</td>\n",
       "      <td>c2</td>\n",
       "      <td>d2</td>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "      <td>a10</td>\n",
       "      <td>b10</td>\n",
       "      <td>c10</td>\n",
       "      <td>d10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "      <td>a11</td>\n",
       "      <td>b11</td>\n",
       "      <td>c11</td>\n",
       "      <td>d11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D   A   B   C   D    A    B    C    D\n",
       "0  a0  b0  c0  d0  a4  b4  c4  d4   a8   b8   c8   d8\n",
       "1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9\n",
       "2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10\n",
       "3  a3  b3  c3  d3  a7  b7  c7  d7  a11  b11  c11  d11"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "col_concat = pd.concat([df1, df2, df3], axis=1)\n",
    "col_concat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>A</th>\n",
       "      <th>A</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a0</td>\n",
       "      <td>a4</td>\n",
       "      <td>a8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a1</td>\n",
       "      <td>a5</td>\n",
       "      <td>a9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a2</td>\n",
       "      <td>a6</td>\n",
       "      <td>a10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a3</td>\n",
       "      <td>a7</td>\n",
       "      <td>a11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   A    A\n",
       "0  a0  a4   a8\n",
       "1  a1  a5   a9\n",
       "2  a2  a6  a10\n",
       "3  a3  a7  a11"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "col_concat['A']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a0</td>\n",
       "      <td>b0</td>\n",
       "      <td>c0</td>\n",
       "      <td>d0</td>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "      <td>a9</td>\n",
       "      <td>b9</td>\n",
       "      <td>c9</td>\n",
       "      <td>d9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a2</td>\n",
       "      <td>b2</td>\n",
       "      <td>c2</td>\n",
       "      <td>d2</td>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "      <td>a10</td>\n",
       "      <td>b10</td>\n",
       "      <td>c10</td>\n",
       "      <td>d10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "      <td>a11</td>\n",
       "      <td>b11</td>\n",
       "      <td>c11</td>\n",
       "      <td>d11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   0   1   2   3   4   5   6   7    8    9    10   11\n",
       "0  a0  b0  c0  d0  a4  b4  c4  d4   a8   b8   c8   d8\n",
       "1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9\n",
       "2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10\n",
       "3  a3  b3  c3  d3  a7  b7  c7  d7  a11  b11  c11  d11"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "col_concat_ignore = pd.concat([df1, df2, df3], axis=1, ignore_index=True)\n",
    "col_concat_ignore"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "df1.columns=['A','B','C','D']\n",
    "df2.columns=['E','F','G','H']\n",
    "df3.columns=['A','H','F','C']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>0</th>\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>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    A   B   C   D\n",
       "0  a0  b0  c0  d0\n",
       "1  a1  b1  c1  d1\n",
       "2  a2  b2  c2  d2\n",
       "3  a3  b3  c3  d3"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>E</th>\n",
       "      <th>F</th>\n",
       "      <th>G</th>\n",
       "      <th>H</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    E   F   G   H\n",
       "0  a4  b4  c4  d4\n",
       "1  a5  b5  c5  d5\n",
       "2  a6  b6  c6  d6\n",
       "3  a7  b7  c7  d7"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>H</th>\n",
       "      <th>F</th>\n",
       "      <th>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a8</td>\n",
       "      <td>b8</td>\n",
       "      <td>c8</td>\n",
       "      <td>d8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a9</td>\n",
       "      <td>b9</td>\n",
       "      <td>c9</td>\n",
       "      <td>d9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a10</td>\n",
       "      <td>b10</td>\n",
       "      <td>c10</td>\n",
       "      <td>d10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a11</td>\n",
       "      <td>b11</td>\n",
       "      <td>c11</td>\n",
       "      <td>d11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    H    F    C\n",
       "0   a8   b8   c8   d8\n",
       "1   a9   b9   c9   d9\n",
       "2  a10  b10  c10  d10\n",
       "3  a11  b11  c11  d11"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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",
       "      <th>E</th>\n",
       "      <th>F</th>\n",
       "      <th>G</th>\n",
       "      <th>H</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a0</td>\n",
       "      <td>b0</td>\n",
       "      <td>c0</td>\n",
       "      <td>d0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a1</td>\n",
       "      <td>b1</td>\n",
       "      <td>c1</td>\n",
       "      <td>d1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>c2</td>\n",
       "      <td>d2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a3</td>\n",
       "      <td>b3</td>\n",
       "      <td>c3</td>\n",
       "      <td>d3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a4</td>\n",
       "      <td>b4</td>\n",
       "      <td>c4</td>\n",
       "      <td>d4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a5</td>\n",
       "      <td>b5</td>\n",
       "      <td>c5</td>\n",
       "      <td>d5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a6</td>\n",
       "      <td>b6</td>\n",
       "      <td>c6</td>\n",
       "      <td>d6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>a7</td>\n",
       "      <td>b7</td>\n",
       "      <td>c7</td>\n",
       "      <td>d7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>d8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>c8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>b8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>d9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>c9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>b9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>d10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>c10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>b10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a11</td>\n",
       "      <td>NaN</td>\n",
       "      <td>d11</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>c11</td>\n",
       "      <td>NaN</td>\n",
       "      <td>b11</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     A    B    C    D    E    F    G    H\n",
       "0   a0   b0   c0   d0  NaN  NaN  NaN  NaN\n",
       "1   a1   b1   c1   d1  NaN  NaN  NaN  NaN\n",
       "2   a2   b2   c2   d2  NaN  NaN  NaN  NaN\n",
       "3   a3   b3   c3   d3  NaN  NaN  NaN  NaN\n",
       "0  NaN  NaN  NaN  NaN   a4   b4   c4   d4\n",
       "1  NaN  NaN  NaN  NaN   a5   b5   c5   d5\n",
       "2  NaN  NaN  NaN  NaN   a6   b6   c6   d6\n",
       "3  NaN  NaN  NaN  NaN   a7   b7   c7   d7\n",
       "0   a8  NaN   d8  NaN  NaN   c8  NaN   b8\n",
       "1   a9  NaN   d9  NaN  NaN   c9  NaN   b9\n",
       "2  a10  NaN  d10  NaN  NaN  c10  NaN  b10\n",
       "3  a11  NaN  d11  NaN  NaN  c11  NaN  b11"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([df1, df2, df3])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# merging"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "person=pd.read_csv('../data/survey_person.csv')\n",
    "site=pd.read_csv('../data/survey_site.csv')\n",
    "survey=pd.read_csv('../data/survey_survey.csv')\n",
    "visited=pd.read_csv('../data/survey_visited.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident</th>\n",
       "      <th>personal</th>\n",
       "      <th>family</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>roe</td>\n",
       "      <td>Valentina</td>\n",
       "      <td>Roerich</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>danforth</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Danforth</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      ident   personal    family\n",
       "0      dyer    William      Dyer\n",
       "1        pb      Frank   Pabodie\n",
       "2      lake   Anderson      Lake\n",
       "3       roe  Valentina   Roerich\n",
       "4  danforth      Frank  Danforth"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "person"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name    lat    long\n",
       "0   DR-1 -49.85 -128.57\n",
       "1   DR-3 -47.15 -126.72\n",
       "2  MSK-4 -48.87 -123.40"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "site"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>taken</th>\n",
       "      <th>person</th>\n",
       "      <th>quant</th>\n",
       "      <th>reading</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>619</td>\n",
       "      <td>dyer</td>\n",
       "      <td>rad</td>\n",
       "      <td>9.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>619</td>\n",
       "      <td>dyer</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>622</td>\n",
       "      <td>dyer</td>\n",
       "      <td>rad</td>\n",
       "      <td>7.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>622</td>\n",
       "      <td>dyer</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>734</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>8.41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>734</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>734</td>\n",
       "      <td>pb</td>\n",
       "      <td>temp</td>\n",
       "      <td>-21.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>735</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>7.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>735</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>735</td>\n",
       "      <td>NaN</td>\n",
       "      <td>temp</td>\n",
       "      <td>-26.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>751</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>4.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>751</td>\n",
       "      <td>pb</td>\n",
       "      <td>temp</td>\n",
       "      <td>-18.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>751</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>752</td>\n",
       "      <td>lake</td>\n",
       "      <td>rad</td>\n",
       "      <td>2.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>752</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>752</td>\n",
       "      <td>lake</td>\n",
       "      <td>temp</td>\n",
       "      <td>-16.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>752</td>\n",
       "      <td>roe</td>\n",
       "      <td>sal</td>\n",
       "      <td>41.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>837</td>\n",
       "      <td>lake</td>\n",
       "      <td>rad</td>\n",
       "      <td>1.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>837</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>837</td>\n",
       "      <td>roe</td>\n",
       "      <td>sal</td>\n",
       "      <td>22.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>844</td>\n",
       "      <td>roe</td>\n",
       "      <td>rad</td>\n",
       "      <td>11.25</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    taken person quant  reading\n",
       "0     619   dyer   rad     9.82\n",
       "1     619   dyer   sal     0.13\n",
       "2     622   dyer   rad     7.80\n",
       "3     622   dyer   sal     0.09\n",
       "4     734     pb   rad     8.41\n",
       "5     734   lake   sal     0.05\n",
       "6     734     pb  temp   -21.50\n",
       "7     735     pb   rad     7.22\n",
       "8     735    NaN   sal     0.06\n",
       "9     735    NaN  temp   -26.00\n",
       "10    751     pb   rad     4.35\n",
       "11    751     pb  temp   -18.50\n",
       "12    751   lake   sal     0.10\n",
       "13    752   lake   rad     2.19\n",
       "14    752   lake   sal     0.09\n",
       "15    752   lake  temp   -16.00\n",
       "16    752    roe   sal    41.60\n",
       "17    837   lake   rad     1.46\n",
       "18    837   lake   sal     0.21\n",
       "19    837    roe   sal    22.50\n",
       "20    844    roe   rad    11.25"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "survey"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>619</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>622</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>734</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>735</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>751</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-02-26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>752</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>837</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>844</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1932-03-22</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ident   site       dated\n",
       "0    619   DR-1  1927-02-08\n",
       "1    622   DR-1  1927-02-10\n",
       "2    734   DR-3  1939-01-07\n",
       "3    735   DR-3  1930-01-12\n",
       "4    751   DR-3  1930-02-26\n",
       "5    752   DR-3         NaN\n",
       "6    837  MSK-4  1932-01-14\n",
       "7    844   DR-1  1932-03-22"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "visited"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>619</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>734</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>837</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ident   site       dated\n",
       "0    619   DR-1  1927-02-08\n",
       "2    734   DR-3  1939-01-07\n",
       "6    837  MSK-4  1932-01-14"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "visited_sub = visited.loc[[0, 2, 6]]\n",
    "visited_sub"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name    lat    long\n",
       "0   DR-1 -49.85 -128.57\n",
       "1   DR-3 -47.15 -126.72\n",
       "2  MSK-4 -48.87 -123.40"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "site"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "o2o = site.merge(visited_sub, left_on=['name'], right_on='site')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "      <th>ident</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "      <td>619</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "      <td>734</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "      <td>837</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name    lat    long  ident   site       dated\n",
       "0   DR-1 -49.85 -128.57    619   DR-1  1927-02-08\n",
       "1   DR-3 -47.15 -126.72    734   DR-3  1939-01-07\n",
       "2  MSK-4 -48.87 -123.40    837  MSK-4  1932-01-14"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "o2o"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3, 6)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "o2o.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>619</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>622</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>734</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>735</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>751</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-02-26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>752</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>837</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>844</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1932-03-22</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ident   site       dated\n",
       "0    619   DR-1  1927-02-08\n",
       "1    622   DR-1  1927-02-10\n",
       "2    734   DR-3  1939-01-07\n",
       "3    735   DR-3  1930-01-12\n",
       "4    751   DR-3  1930-02-26\n",
       "5    752   DR-3         NaN\n",
       "6    837  MSK-4  1932-01-14\n",
       "7    844   DR-1  1932-03-22"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "visited"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name    lat    long\n",
       "0   DR-1 -49.85 -128.57\n",
       "1   DR-3 -47.15 -126.72\n",
       "2  MSK-4 -48.87 -123.40"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "site"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "m2o = site.merge(visited, left_on='name', right_on='site')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "      <th>ident</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "      <td>619</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "      <td>622</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "      <td>844</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1932-03-22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "      <td>734</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "      <td>735</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "      <td>751</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-02-26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "      <td>752</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "      <td>837</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name    lat    long  ident   site       dated\n",
       "0   DR-1 -49.85 -128.57    619   DR-1  1927-02-08\n",
       "1   DR-1 -49.85 -128.57    622   DR-1  1927-02-10\n",
       "2   DR-1 -49.85 -128.57    844   DR-1  1932-03-22\n",
       "3   DR-3 -47.15 -126.72    734   DR-3  1939-01-07\n",
       "4   DR-3 -47.15 -126.72    735   DR-3  1930-01-12\n",
       "5   DR-3 -47.15 -126.72    751   DR-3  1930-02-26\n",
       "6   DR-3 -47.15 -126.72    752   DR-3         NaN\n",
       "7  MSK-4 -48.87 -123.40    837  MSK-4  1932-01-14"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m2o"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# many to many"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(8, 6)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m2o.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5, 3)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "person.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(21, 4)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "survey.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(8, 3)"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "visited.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      ident   personal    family\n",
      "0      dyer    William      Dyer\n",
      "1        pb      Frank   Pabodie\n",
      "2      lake   Anderson      Lake\n",
      "3       roe  Valentina   Roerich\n",
      "4  danforth      Frank  Danforth\n",
      "   taken person quant  reading\n",
      "0    619   dyer   rad     9.82\n",
      "1    619   dyer   sal     0.13\n",
      "2    622   dyer   rad     7.80\n",
      "3    622   dyer   sal     0.09\n",
      "4    734     pb   rad     8.41\n",
      "   ident  site       dated\n",
      "0    619  DR-1  1927-02-08\n",
      "1    622  DR-1  1927-02-10\n",
      "2    734  DR-3  1939-01-07\n",
      "3    735  DR-3  1930-01-12\n",
      "4    751  DR-3  1930-02-26\n",
      "    name    lat    long\n",
      "0   DR-1 -49.85 -128.57\n",
      "1   DR-3 -47.15 -126.72\n",
      "2  MSK-4 -48.87 -123.40\n"
     ]
    }
   ],
   "source": [
    "print(person.head())\n",
    "print(survey.head())\n",
    "print(visited.head())\n",
    "print(site.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "ps = person.merge(survey, left_on='ident', right_on='person', how='outer')\n",
    "vs = visited.merge(site, left_on='site', right_on='name', how='outer')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(22, 7)"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident</th>\n",
       "      <th>personal</th>\n",
       "      <th>family</th>\n",
       "      <th>taken</th>\n",
       "      <th>person</th>\n",
       "      <th>quant</th>\n",
       "      <th>reading</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>619.0</td>\n",
       "      <td>dyer</td>\n",
       "      <td>rad</td>\n",
       "      <td>9.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>619.0</td>\n",
       "      <td>dyer</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>622.0</td>\n",
       "      <td>dyer</td>\n",
       "      <td>rad</td>\n",
       "      <td>7.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>622.0</td>\n",
       "      <td>dyer</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "      <td>734.0</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>8.41</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  ident personal   family  taken person quant  reading\n",
       "0  dyer  William     Dyer  619.0   dyer   rad     9.82\n",
       "1  dyer  William     Dyer  619.0   dyer   sal     0.13\n",
       "2  dyer  William     Dyer  622.0   dyer   rad     7.80\n",
       "3  dyer  William     Dyer  622.0   dyer   sal     0.09\n",
       "4    pb    Frank  Pabodie  734.0     pb   rad     8.41"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(8, 6)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>619</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>622</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-10</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>844</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1932-03-22</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>734</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>735</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ident  site       dated  name    lat    long\n",
       "0    619  DR-1  1927-02-08  DR-1 -49.85 -128.57\n",
       "1    622  DR-1  1927-02-10  DR-1 -49.85 -128.57\n",
       "2    844  DR-1  1932-03-22  DR-1 -49.85 -128.57\n",
       "3    734  DR-3  1939-01-07  DR-3 -47.15 -126.72\n",
       "4    735  DR-3  1930-01-12  DR-3 -47.15 -126.72"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vs.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "ps_vs = ps.merge(vs,\n",
    "                 left_on=['taken'],\n",
    "                 right_on=['ident'],\n",
    "                how='outer')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(22, 13)"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps_vs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ident_x</th>\n",
       "      <th>personal</th>\n",
       "      <th>family</th>\n",
       "      <th>taken</th>\n",
       "      <th>person</th>\n",
       "      <th>quant</th>\n",
       "      <th>reading</th>\n",
       "      <th>ident_y</th>\n",
       "      <th>site</th>\n",
       "      <th>dated</th>\n",
       "      <th>name</th>\n",
       "      <th>lat</th>\n",
       "      <th>long</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>619</td>\n",
       "      <td>dyer</td>\n",
       "      <td>rad</td>\n",
       "      <td>9.82</td>\n",
       "      <td>619.0</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>619</td>\n",
       "      <td>dyer</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.13</td>\n",
       "      <td>619.0</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-08</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>622</td>\n",
       "      <td>dyer</td>\n",
       "      <td>rad</td>\n",
       "      <td>7.80</td>\n",
       "      <td>622.0</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-10</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>dyer</td>\n",
       "      <td>William</td>\n",
       "      <td>Dyer</td>\n",
       "      <td>622</td>\n",
       "      <td>dyer</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.09</td>\n",
       "      <td>622.0</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1927-02-10</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "      <td>734</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>8.41</td>\n",
       "      <td>734.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "      <td>734</td>\n",
       "      <td>pb</td>\n",
       "      <td>temp</td>\n",
       "      <td>-21.50</td>\n",
       "      <td>734.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>734</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.05</td>\n",
       "      <td>734.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1939-01-07</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "      <td>735</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>7.22</td>\n",
       "      <td>735.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>735</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.06</td>\n",
       "      <td>735.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>735</td>\n",
       "      <td>NaN</td>\n",
       "      <td>temp</td>\n",
       "      <td>-26.00</td>\n",
       "      <td>735.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-01-12</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "      <td>751</td>\n",
       "      <td>pb</td>\n",
       "      <td>rad</td>\n",
       "      <td>4.35</td>\n",
       "      <td>751.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-02-26</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>pb</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Pabodie</td>\n",
       "      <td>751</td>\n",
       "      <td>pb</td>\n",
       "      <td>temp</td>\n",
       "      <td>-18.50</td>\n",
       "      <td>751.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-02-26</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>751</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.10</td>\n",
       "      <td>751.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>1930-02-26</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>752</td>\n",
       "      <td>lake</td>\n",
       "      <td>rad</td>\n",
       "      <td>2.19</td>\n",
       "      <td>752.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>752</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.09</td>\n",
       "      <td>752.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>752</td>\n",
       "      <td>lake</td>\n",
       "      <td>temp</td>\n",
       "      <td>-16.00</td>\n",
       "      <td>752.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>roe</td>\n",
       "      <td>Valentina</td>\n",
       "      <td>Roerich</td>\n",
       "      <td>752</td>\n",
       "      <td>roe</td>\n",
       "      <td>sal</td>\n",
       "      <td>41.60</td>\n",
       "      <td>752.0</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>DR-3</td>\n",
       "      <td>-47.15</td>\n",
       "      <td>-126.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>837</td>\n",
       "      <td>lake</td>\n",
       "      <td>rad</td>\n",
       "      <td>1.46</td>\n",
       "      <td>837.0</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>lake</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>Lake</td>\n",
       "      <td>837</td>\n",
       "      <td>lake</td>\n",
       "      <td>sal</td>\n",
       "      <td>0.21</td>\n",
       "      <td>837.0</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>roe</td>\n",
       "      <td>Valentina</td>\n",
       "      <td>Roerich</td>\n",
       "      <td>837</td>\n",
       "      <td>roe</td>\n",
       "      <td>sal</td>\n",
       "      <td>22.50</td>\n",
       "      <td>837.0</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>1932-01-14</td>\n",
       "      <td>MSK-4</td>\n",
       "      <td>-48.87</td>\n",
       "      <td>-123.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>roe</td>\n",
       "      <td>Valentina</td>\n",
       "      <td>Roerich</td>\n",
       "      <td>844</td>\n",
       "      <td>roe</td>\n",
       "      <td>rad</td>\n",
       "      <td>11.25</td>\n",
       "      <td>844.0</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>1932-03-22</td>\n",
       "      <td>DR-1</td>\n",
       "      <td>-49.85</td>\n",
       "      <td>-128.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>danforth</td>\n",
       "      <td>Frank</td>\n",
       "      <td>Danforth</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     ident_x   personal    family taken person quant  reading  ident_y   site  \\\n",
       "0       dyer    William      Dyer   619   dyer   rad     9.82    619.0   DR-1   \n",
       "1       dyer    William      Dyer   619   dyer   sal     0.13    619.0   DR-1   \n",
       "2       dyer    William      Dyer   622   dyer   rad     7.80    622.0   DR-1   \n",
       "3       dyer    William      Dyer   622   dyer   sal     0.09    622.0   DR-1   \n",
       "4         pb      Frank   Pabodie   734     pb   rad     8.41    734.0   DR-3   \n",
       "5         pb      Frank   Pabodie   734     pb  temp   -21.50    734.0   DR-3   \n",
       "6       lake   Anderson      Lake   734   lake   sal     0.05    734.0   DR-3   \n",
       "7         pb      Frank   Pabodie   735     pb   rad     7.22    735.0   DR-3   \n",
       "8        NaN        NaN       NaN   735    NaN   sal     0.06    735.0   DR-3   \n",
       "9        NaN        NaN       NaN   735    NaN  temp   -26.00    735.0   DR-3   \n",
       "10        pb      Frank   Pabodie   751     pb   rad     4.35    751.0   DR-3   \n",
       "11        pb      Frank   Pabodie   751     pb  temp   -18.50    751.0   DR-3   \n",
       "12      lake   Anderson      Lake   751   lake   sal     0.10    751.0   DR-3   \n",
       "13      lake   Anderson      Lake   752   lake   rad     2.19    752.0   DR-3   \n",
       "14      lake   Anderson      Lake   752   lake   sal     0.09    752.0   DR-3   \n",
       "15      lake   Anderson      Lake   752   lake  temp   -16.00    752.0   DR-3   \n",
       "16       roe  Valentina   Roerich   752    roe   sal    41.60    752.0   DR-3   \n",
       "17      lake   Anderson      Lake   837   lake   rad     1.46    837.0  MSK-4   \n",
       "18      lake   Anderson      Lake   837   lake   sal     0.21    837.0  MSK-4   \n",
       "19       roe  Valentina   Roerich   837    roe   sal    22.50    837.0  MSK-4   \n",
       "20       roe  Valentina   Roerich   844    roe   rad    11.25    844.0   DR-1   \n",
       "21  danforth      Frank  Danforth   NaN    NaN   NaN      NaN      NaN    NaN   \n",
       "\n",
       "         dated   name    lat    long  \n",
       "0   1927-02-08   DR-1 -49.85 -128.57  \n",
       "1   1927-02-08   DR-1 -49.85 -128.57  \n",
       "2   1927-02-10   DR-1 -49.85 -128.57  \n",
       "3   1927-02-10   DR-1 -49.85 -128.57  \n",
       "4   1939-01-07   DR-3 -47.15 -126.72  \n",
       "5   1939-01-07   DR-3 -47.15 -126.72  \n",
       "6   1939-01-07   DR-3 -47.15 -126.72  \n",
       "7   1930-01-12   DR-3 -47.15 -126.72  \n",
       "8   1930-01-12   DR-3 -47.15 -126.72  \n",
       "9   1930-01-12   DR-3 -47.15 -126.72  \n",
       "10  1930-02-26   DR-3 -47.15 -126.72  \n",
       "11  1930-02-26   DR-3 -47.15 -126.72  \n",
       "12  1930-02-26   DR-3 -47.15 -126.72  \n",
       "13         NaN   DR-3 -47.15 -126.72  \n",
       "14         NaN   DR-3 -47.15 -126.72  \n",
       "15         NaN   DR-3 -47.15 -126.72  \n",
       "16         NaN   DR-3 -47.15 -126.72  \n",
       "17  1932-01-14  MSK-4 -48.87 -123.40  \n",
       "18  1932-01-14  MSK-4 -48.87 -123.40  \n",
       "19  1932-01-14  MSK-4 -48.87 -123.40  \n",
       "20  1932-03-22   DR-1 -49.85 -128.57  \n",
       "21         NaN    NaN    NaN     NaN  "
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps_vs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>a1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>a5</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    a  b\n",
       "0  a1  1\n",
       "1  a2  1\n",
       "2  a3  2\n",
       "3  a4  2\n",
       "4  a5  3"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame({\n",
    "    'a': ['a1', 'a2', 'a3', 'a4', 'a5'],\n",
    "    'b': [1, 1, 2, 2, 3]\n",
    "})\n",
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a2</th>\n",
       "      <th>b2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2a1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2a2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2a3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2a4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2a5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    a2  b2\n",
       "0  2a1   1\n",
       "1  2a2   1\n",
       "2  2a3   1\n",
       "3  2a4   2\n",
       "4  2a5   2"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df2 = pd.DataFrame({\n",
    "    'a2': ['2a1', '2a2', '2a3', '2a4', '2a5'],\n",
    "    'b2': [1, 1, 1, 2, 2]\n",
    "})\n",
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>a2</th>\n",
       "      <th>b2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a1</td>\n",
       "      <td>1</td>\n",
       "      <td>2a1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a1</td>\n",
       "      <td>1</td>\n",
       "      <td>2a2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a1</td>\n",
       "      <td>1</td>\n",
       "      <td>2a3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>a2</td>\n",
       "      <td>1</td>\n",
       "      <td>2a1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>a2</td>\n",
       "      <td>1</td>\n",
       "      <td>2a2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>a2</td>\n",
       "      <td>1</td>\n",
       "      <td>2a3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>a3</td>\n",
       "      <td>2</td>\n",
       "      <td>2a4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>a3</td>\n",
       "      <td>2</td>\n",
       "      <td>2a5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>a4</td>\n",
       "      <td>2</td>\n",
       "      <td>2a4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>a4</td>\n",
       "      <td>2</td>\n",
       "      <td>2a5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    a  b   a2  b2\n",
       "0  a1  1  2a1   1\n",
       "1  a1  1  2a2   1\n",
       "2  a1  1  2a3   1\n",
       "3  a2  1  2a1   1\n",
       "4  a2  1  2a2   1\n",
       "5  a2  1  2a3   1\n",
       "6  a3  2  2a4   2\n",
       "7  a3  2  2a5   2\n",
       "8  a4  2  2a4   2\n",
       "9  a4  2  2a5   2"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m2m = pd.merge(df1, df2, left_on=['b'], right_on=['b2'])\n",
    "m2m"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "ename": "AssertionError",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-94-3c656ec3a9a1>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32massert\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf1\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mm2m\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;31mAssertionError\u001b[0m: "
     ]
    }
   ],
   "source": [
    "assert len(df1) == len(m2m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true,
    "jupyter": {
     "outputs_hidden": true
    }
   },
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}