US_baby_names.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fictitious Names"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Introduction:\n",
    "\n",
    "This time you will create a data again \n",
    "\n",
    "Special thanks to [Chris Albon](http://chrisalbon.com/) for sharing the dataset and materials.\n",
    "All the credits to this exercise belongs to him.  \n",
    "\n",
    "In order to understand about it go [here](https://blog.codinghorror.com/a-visual-explanation-of-sql-joins/).\n",
    "\n",
    "### Step 1. Import the necessary libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 2. Create the 3 DataFrames based on the following raw data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "raw_data_1 = {\n",
    "        'subject_id': ['1', '2', '3', '4', '5'],\n",
    "        'first_name': ['Alex', 'Amy', 'Allen', 'Alice', 'Ayoung'], \n",
    "        'last_name': ['Anderson', 'Ackerman', 'Ali', 'Aoni', 'Atiches']}\n",
    "\n",
    "raw_data_2 = {\n",
    "        'subject_id': ['4', '5', '6', '7', '8'],\n",
    "        'first_name': ['Billy', 'Brian', 'Bran', 'Bryce', 'Betty'], \n",
    "        'last_name': ['Bonder', 'Black', 'Balwner', 'Brice', 'Btisan']}\n",
    "\n",
    "raw_data_3 = {\n",
    "        'subject_id': ['1', '2', '3', '4', '5', '7', '8', '9', '10', '11'],\n",
    "        'test_id': [51, 15, 15, 61, 16, 14, 15, 1, 61, 16]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "data1 = pd.DataFrame(raw_data_1)\n",
    "data2 = pd.DataFrame(raw_data_2)\n",
    "data3 = pd.DataFrame(raw_data_3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id first_name last_name\n",
       "0          1       Alex  Anderson\n",
       "1          2        Amy  Ackerman\n",
       "2          3      Allen       Ali\n",
       "3          4      Alice      Aoni\n",
       "4          5     Ayoung   Atiches"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data1 \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>Bran</td>\n",
       "      <td>Balwner</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id first_name last_name\n",
       "0          4      Billy    Bonder\n",
       "1          5      Brian     Black\n",
       "2          6       Bran   Balwner\n",
       "3          7      Bryce     Brice\n",
       "4          8      Betty    Btisan"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>test_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>7</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>10</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>11</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id  test_id\n",
       "0          1       51\n",
       "1          2       15\n",
       "2          3       15\n",
       "3          4       61\n",
       "4          5       16\n",
       "5          7       14\n",
       "6          8       15\n",
       "7          9        1\n",
       "8         10       61\n",
       "9         11       16"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 4. Join the two dataframes along rows and assign all_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This process is named \"concatenation\" -->Joining dataframes with similiar data structure(like data1, data 2)  can be acommplished using function concat().\n",
    "We assign it to \"all_data\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_data = pd.concat([data1,data2], axis=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- axis = 0 : This parametre means concatenation along the rows, which stacks the DataFrames on top of each other.If we had axis = 1 , it would concatenate along the columns which is not what we want in this case."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After concatenating the raw data into one dataframe we must make sure the combined DataFrame is re-indexed in order to maintain consistency. The reset_index method is used to reindex the combined dataframe. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "all_data.reset_index(drop=True, inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- drop=True in reset_index: This parametre controls whether to drop the old index after reseting it .When we concatenate Dataframes the resulting dataframe retains the original indices from the input dataframes.This can result to a non sequencial merged DataFrame .\n",
    "- By using reset_index(drop=True), we reset the index to a default integer index (0, 1, 2, ...), and by setting drop=True, we ensure the old index is not added as a new column.\n",
    "\n",
    "By using axis=0 and drop=True, we ensure a clean and orderly concatenated dataframe without duplicated or misaligned indices."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>6</td>\n",
       "      <td>Bran</td>\n",
       "      <td>Balwner</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id first_name last_name\n",
       "0          1       Alex  Anderson\n",
       "1          2        Amy  Ackerman\n",
       "2          3      Allen       Ali\n",
       "3          4      Alice      Aoni\n",
       "4          5     Ayoung   Atiches\n",
       "5          4      Billy    Bonder\n",
       "6          5      Brian     Black\n",
       "7          6       Bran   Balwner\n",
       "8          7      Bryce     Brice\n",
       "9          8      Betty    Btisan"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Display the result\n",
    "all_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 5. Join the two dataframes along columns and assing to all_data_col"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here we can see the difference when we set axis=0 and axis=1 :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "all_data_col = pd.concat([data1,data2], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "      <td>6</td>\n",
       "      <td>Bran</td>\n",
       "      <td>Balwner</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id first_name last_name subject_id first_name last_name\n",
       "0          1       Alex  Anderson          4      Billy    Bonder\n",
       "1          2        Amy  Ackerman          5      Brian     Black\n",
       "2          3      Allen       Ali          6       Bran   Balwner\n",
       "3          4      Alice      Aoni          7      Bryce     Brice\n",
       "4          5     Ayoung   Atiches          8      Betty    Btisan"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_data_col"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 6. Print data3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "  subject_id  test_id\n",
      "0          1       51\n",
      "1          2       15\n",
      "2          3       15\n",
      "3          4       61\n",
      "4          5       16\n",
      "5          7       14\n",
      "6          8       15\n",
      "7          9        1\n",
      "8         10       61\n",
      "9         11       16\n"
     ]
    }
   ],
   "source": [
    "print(data3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 7. Merge all_data and data3 along the subject_id value"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This task asks us to merge the joined dataframes \"all_data\" with a specific column : We can do that using pd.merge() and specify the join type  (inner, outer, left, right).\n",
    "\n",
    "notes :\n",
    "\n",
    "- #### on='subject_id': This parameter specifies that the merge should be done based on the subject_id column.\n",
    "- #### how='inner': This parameter specifies the type of join. The options are:\n",
    "1. 'inner': Only include rows with matching subject_id in both dataframes.\n",
    "2. 'outer': Include all rows from both dataframes, filling with NaN where there are no matches.\n",
    "3. 'left': Include all rows from df1 and matching rows from df3.\n",
    "4. 'right': Include all rows from df3 and matching rows from df1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "merged_data = pd.merge(all_data, data3, on= \"subject_id\", how= \"inner\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>test_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id first_name last_name  test_id\n",
       "0          1       Alex  Anderson       51\n",
       "1          2        Amy  Ackerman       15\n",
       "2          3      Allen       Ali       15\n",
       "3          4      Alice      Aoni       61\n",
       "4          5     Ayoung   Atiches       16\n",
       "5          4      Billy    Bonder       61\n",
       "6          5      Brian     Black       16\n",
       "7          7      Bryce     Brice       14\n",
       "8          8      Betty    Btisan       15"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>test_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>51.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>11</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>6</td>\n",
       "      <td>Bran</td>\n",
       "      <td>Balwner</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id first_name last_name  test_id\n",
       "0           1       Alex  Anderson     51.0\n",
       "1          10        NaN       NaN     61.0\n",
       "2          11        NaN       NaN     16.0\n",
       "3           2        Amy  Ackerman     15.0\n",
       "4           3      Allen       Ali     15.0\n",
       "5           4      Alice      Aoni     61.0\n",
       "6           4      Billy    Bonder     61.0\n",
       "7           5     Ayoung   Atiches     16.0\n",
       "8           5      Brian     Black     16.0\n",
       "9           6       Bran   Balwner      NaN\n",
       "10          7      Bryce     Brice     14.0\n",
       "11          8      Betty    Btisan     15.0\n",
       "12          9        NaN       NaN      1.0"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_data = pd.merge(all_data, data3, on= \"subject_id\", how= \"outer\")\n",
    "merged_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>test_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>51.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "      <td>16.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>6</td>\n",
       "      <td>Bran</td>\n",
       "      <td>Balwner</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "      <td>14.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  subject_id first_name last_name  test_id\n",
       "0          1       Alex  Anderson     51.0\n",
       "1          2        Amy  Ackerman     15.0\n",
       "2          3      Allen       Ali     15.0\n",
       "3          4      Alice      Aoni     61.0\n",
       "4          5     Ayoung   Atiches     16.0\n",
       "5          4      Billy    Bonder     61.0\n",
       "6          5      Brian     Black     16.0\n",
       "7          6       Bran   Balwner      NaN\n",
       "8          7      Bryce     Brice     14.0\n",
       "9          8      Betty    Btisan     15.0"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_data = pd.merge(all_data, data3, on= \"subject_id\", how= \"left\")\n",
    "merged_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>subject_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>test_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Alex</td>\n",
       "      <td>Anderson</td>\n",
       "      <td>51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Amy</td>\n",
       "      <td>Ackerman</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Allen</td>\n",
       "      <td>Ali</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Alice</td>\n",
       "      <td>Aoni</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>Billy</td>\n",
       "      <td>Bonder</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>Ayoung</td>\n",
       "      <td>Atiches</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>Brian</td>\n",
       "      <td>Black</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7</td>\n",
       "      <td>Bryce</td>\n",
       "      <td>Brice</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>8</td>\n",
       "      <td>Betty</td>\n",
       "      <td>Btisan</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>11</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   subject_id first_name last_name  test_id\n",
       "0           1       Alex  Anderson       51\n",
       "1           2        Amy  Ackerman       15\n",
       "2           3      Allen       Ali       15\n",
       "3           4      Alice      Aoni       61\n",
       "4           4      Billy    Bonder       61\n",
       "5           5     Ayoung   Atiches       16\n",
       "6           5      Brian     Black       16\n",
       "7           7      Bryce     Brice       14\n",
       "8           8      Betty    Btisan       15\n",
       "9           9        NaN       NaN        1\n",
       "10         10        NaN       NaN       61\n",
       "11         11        NaN       NaN       16"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged_data = pd.merge(all_data, data3, on= \"subject_id\", how= \"right\")\n",
    "merged_data"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "test_env_py",
   "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}