diff --git a/your-code/main.ipynb b/your-code/main.ipynb
index bad6d94..dcab503 100644
--- a/your-code/main.ipynb
+++ b/your-code/main.ipynb
@@ -9,10 +9,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import pandas as pd"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -23,10 +25,325 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 55,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "users = pd.read_csv('users_table.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "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>Id</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>CreationDate</th>\n",
+       "      <th>DisplayName</th>\n",
+       "      <th>LastAccessDate</th>\n",
+       "      <th>WebsiteUrl</th>\n",
+       "      <th>Location</th>\n",
+       "      <th>AboutMe</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>AccountId</th>\n",
+       "      <th>Age</th>\n",
+       "      <th>ProfileImageUrl</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>Community</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>http://meta.stackexchange.com/</td>\n",
+       "      <td>on the server farm</td>\n",
+       "      <td>&lt;p&gt;Hi, I'm not really a person.&lt;/p&gt;\\r\\n\\r\\n&lt;p&gt;...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 14:01:36</td>\n",
+       "      <td>Geoff Dalgas</td>\n",
+       "      <td>2013-11-12 22:07:23</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>Corvallis, OR</td>\n",
+       "      <td>&lt;p&gt;Developer on the StackOverflow team.  Find ...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>37.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 15:34:50</td>\n",
+       "      <td>Jarrod Dixon</td>\n",
+       "      <td>2014-08-08 06:42:58</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;&lt;a href=\"http://blog.stackoverflow.com/2009...</td>\n",
+       "      <td>22</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 19:03:27</td>\n",
+       "      <td>Emmett</td>\n",
+       "      <td>2014-01-02 09:31:02</td>\n",
+       "      <td>http://minesweeperonline.com</td>\n",
+       "      <td>San Francisco, CA</td>\n",
+       "      <td>&lt;p&gt;currently at a startup in SF&lt;/p&gt;\\r\\n\\r\\n&lt;p&gt;...</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1998</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>http://i.stack.imgur.com/d1oHX.jpg</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>6792</td>\n",
+       "      <td>2010-07-19 19:03:57</td>\n",
+       "      <td>Shane</td>\n",
+       "      <td>2014-08-13 00:23:47</td>\n",
+       "      <td>http://www.statalgo.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;Quantitative researcher focusing on statist...</td>\n",
+       "      <td>1145</td>\n",
+       "      <td>662</td>\n",
+       "      <td>5</td>\n",
+       "      <td>54503</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40320</th>\n",
+       "      <td>55743</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2014-09-13 21:03:50</td>\n",
+       "      <td>AussieMeg</td>\n",
+       "      <td>2014-09-13 21:18:52</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5026902</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>http://graph.facebook.com/665821703/picture?ty...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40321</th>\n",
+       "      <td>55744</td>\n",
+       "      <td>6</td>\n",
+       "      <td>2014-09-13 21:39:30</td>\n",
+       "      <td>Mia Maria</td>\n",
+       "      <td>2014-09-13 21:39:30</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5026998</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40322</th>\n",
+       "      <td>55745</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2014-09-13 23:45:27</td>\n",
+       "      <td>tronbabylove</td>\n",
+       "      <td>2014-09-13 23:45:27</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>United States</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>481766</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>https://www.gravatar.com/avatar/faa7a3fdbd8308...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40323</th>\n",
+       "      <td>55746</td>\n",
+       "      <td>106</td>\n",
+       "      <td>2014-09-14 00:29:41</td>\n",
+       "      <td>GPP</td>\n",
+       "      <td>2014-09-14 02:05:17</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;Stats noobie, product, marketing &amp;amp; medi...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>976289</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>https://www.gravatar.com/avatar/6d9e9fa6b783a3...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40324</th>\n",
+       "      <td>55747</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2014-09-14 01:01:44</td>\n",
+       "      <td>Shivam Agrawal</td>\n",
+       "      <td>2014-09-14 01:19:04</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>India</td>\n",
+       "      <td>&lt;p&gt;Maths Enthusiast &lt;/p&gt;\\r\\n</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5027354</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>https://lh4.googleusercontent.com/-ZsXhwVaFmiY...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>40325 rows × 14 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          Id  Reputation         CreationDate     DisplayName  \\\n",
+       "0         -1           1  2010-07-19 06:55:26       Community   \n",
+       "1          2         101  2010-07-19 14:01:36    Geoff Dalgas   \n",
+       "2          3         101  2010-07-19 15:34:50    Jarrod Dixon   \n",
+       "3          4         101  2010-07-19 19:03:27          Emmett   \n",
+       "4          5        6792  2010-07-19 19:03:57           Shane   \n",
+       "...      ...         ...                  ...             ...   \n",
+       "40320  55743           1  2014-09-13 21:03:50       AussieMeg   \n",
+       "40321  55744           6  2014-09-13 21:39:30       Mia Maria   \n",
+       "40322  55745         101  2014-09-13 23:45:27    tronbabylove   \n",
+       "40323  55746         106  2014-09-14 00:29:41             GPP   \n",
+       "40324  55747           1  2014-09-14 01:01:44  Shivam Agrawal   \n",
+       "\n",
+       "            LastAccessDate                      WebsiteUrl  \\\n",
+       "0      2010-07-19 06:55:26  http://meta.stackexchange.com/   \n",
+       "1      2013-11-12 22:07:23        http://stackoverflow.com   \n",
+       "2      2014-08-08 06:42:58        http://stackoverflow.com   \n",
+       "3      2014-01-02 09:31:02    http://minesweeperonline.com   \n",
+       "4      2014-08-13 00:23:47         http://www.statalgo.com   \n",
+       "...                    ...                             ...   \n",
+       "40320  2014-09-13 21:18:52                             NaN   \n",
+       "40321  2014-09-13 21:39:30                             NaN   \n",
+       "40322  2014-09-13 23:45:27                             NaN   \n",
+       "40323  2014-09-14 02:05:17                             NaN   \n",
+       "40324  2014-09-14 01:19:04                             NaN   \n",
+       "\n",
+       "                 Location                                            AboutMe  \\\n",
+       "0      on the server farm  <p>Hi, I'm not really a person.</p>\\r\\n\\r\\n<p>...   \n",
+       "1           Corvallis, OR  <p>Developer on the StackOverflow team.  Find ...   \n",
+       "2            New York, NY  <p><a href=\"http://blog.stackoverflow.com/2009...   \n",
+       "3       San Francisco, CA  <p>currently at a startup in SF</p>\\r\\n\\r\\n<p>...   \n",
+       "4            New York, NY  <p>Quantitative researcher focusing on statist...   \n",
+       "...                   ...                                                ...   \n",
+       "40320                 NaN                                                NaN   \n",
+       "40321                 NaN                                                NaN   \n",
+       "40322       United States                                                NaN   \n",
+       "40323                 NaN  <p>Stats noobie, product, marketing &amp; medi...   \n",
+       "40324               India                       <p>Maths Enthusiast </p>\\r\\n   \n",
+       "\n",
+       "       Views  UpVotes  DownVotes  AccountId   Age  \\\n",
+       "0          0     5007       1920         -1   NaN   \n",
+       "1         25        3          0          2  37.0   \n",
+       "2         22       19          0          3  35.0   \n",
+       "3         11        0          0       1998  28.0   \n",
+       "4       1145      662          5      54503  35.0   \n",
+       "...      ...      ...        ...        ...   ...   \n",
+       "40320      0        0          0    5026902   NaN   \n",
+       "40321      1        0          0    5026998   NaN   \n",
+       "40322      0        0          0     481766   NaN   \n",
+       "40323      1        0          0     976289   NaN   \n",
+       "40324      0        0          0    5027354   NaN   \n",
+       "\n",
+       "                                         ProfileImageUrl  \n",
+       "0                                                    NaN  \n",
+       "1                                                    NaN  \n",
+       "2                                                    NaN  \n",
+       "3                     http://i.stack.imgur.com/d1oHX.jpg  \n",
+       "4                                                    NaN  \n",
+       "...                                                  ...  \n",
+       "40320  http://graph.facebook.com/665821703/picture?ty...  \n",
+       "40321                                                NaN  \n",
+       "40322  https://www.gravatar.com/avatar/faa7a3fdbd8308...  \n",
+       "40323  https://www.gravatar.com/avatar/6d9e9fa6b783a3...  \n",
+       "40324  https://lh4.googleusercontent.com/-ZsXhwVaFmiY...  \n",
+       "\n",
+       "[40325 rows x 14 columns]"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "users"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -37,10 +354,317 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 57,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "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>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>CreationDate</th>\n",
+       "      <th>DisplayName</th>\n",
+       "      <th>LastAccessDate</th>\n",
+       "      <th>WebsiteUrl</th>\n",
+       "      <th>Location</th>\n",
+       "      <th>AboutMe</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>AccountId</th>\n",
+       "      <th>Age</th>\n",
+       "      <th>ProfileImageUrl</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>Community</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>http://meta.stackexchange.com/</td>\n",
+       "      <td>on the server farm</td>\n",
+       "      <td>&lt;p&gt;Hi, I'm not really a person.&lt;/p&gt;\\r\\n\\r\\n&lt;p&gt;...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 14:01:36</td>\n",
+       "      <td>Geoff Dalgas</td>\n",
+       "      <td>2013-11-12 22:07:23</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>Corvallis, OR</td>\n",
+       "      <td>&lt;p&gt;Developer on the StackOverflow team.  Find ...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>37.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 15:34:50</td>\n",
+       "      <td>Jarrod Dixon</td>\n",
+       "      <td>2014-08-08 06:42:58</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;&lt;a href=\"http://blog.stackoverflow.com/2009...</td>\n",
+       "      <td>22</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 19:03:27</td>\n",
+       "      <td>Emmett</td>\n",
+       "      <td>2014-01-02 09:31:02</td>\n",
+       "      <td>http://minesweeperonline.com</td>\n",
+       "      <td>San Francisco, CA</td>\n",
+       "      <td>&lt;p&gt;currently at a startup in SF&lt;/p&gt;\\r\\n\\r\\n&lt;p&gt;...</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1998</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>http://i.stack.imgur.com/d1oHX.jpg</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>6792</td>\n",
+       "      <td>2010-07-19 19:03:57</td>\n",
+       "      <td>Shane</td>\n",
+       "      <td>2014-08-13 00:23:47</td>\n",
+       "      <td>http://www.statalgo.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;Quantitative researcher focusing on statist...</td>\n",
+       "      <td>1145</td>\n",
+       "      <td>662</td>\n",
+       "      <td>5</td>\n",
+       "      <td>54503</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40320</th>\n",
+       "      <td>55743</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2014-09-13 21:03:50</td>\n",
+       "      <td>AussieMeg</td>\n",
+       "      <td>2014-09-13 21:18:52</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5026902</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>http://graph.facebook.com/665821703/picture?ty...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40321</th>\n",
+       "      <td>55744</td>\n",
+       "      <td>6</td>\n",
+       "      <td>2014-09-13 21:39:30</td>\n",
+       "      <td>Mia Maria</td>\n",
+       "      <td>2014-09-13 21:39:30</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5026998</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40322</th>\n",
+       "      <td>55745</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2014-09-13 23:45:27</td>\n",
+       "      <td>tronbabylove</td>\n",
+       "      <td>2014-09-13 23:45:27</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>United States</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>481766</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>https://www.gravatar.com/avatar/faa7a3fdbd8308...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40323</th>\n",
+       "      <td>55746</td>\n",
+       "      <td>106</td>\n",
+       "      <td>2014-09-14 00:29:41</td>\n",
+       "      <td>GPP</td>\n",
+       "      <td>2014-09-14 02:05:17</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;Stats noobie, product, marketing &amp;amp; medi...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>976289</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>https://www.gravatar.com/avatar/6d9e9fa6b783a3...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40324</th>\n",
+       "      <td>55747</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2014-09-14 01:01:44</td>\n",
+       "      <td>Shivam Agrawal</td>\n",
+       "      <td>2014-09-14 01:19:04</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>India</td>\n",
+       "      <td>&lt;p&gt;Maths Enthusiast &lt;/p&gt;\\r\\n</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5027354</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>https://lh4.googleusercontent.com/-ZsXhwVaFmiY...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>40325 rows × 14 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       userId  Reputation         CreationDate     DisplayName  \\\n",
+       "0          -1           1  2010-07-19 06:55:26       Community   \n",
+       "1           2         101  2010-07-19 14:01:36    Geoff Dalgas   \n",
+       "2           3         101  2010-07-19 15:34:50    Jarrod Dixon   \n",
+       "3           4         101  2010-07-19 19:03:27          Emmett   \n",
+       "4           5        6792  2010-07-19 19:03:57           Shane   \n",
+       "...       ...         ...                  ...             ...   \n",
+       "40320   55743           1  2014-09-13 21:03:50       AussieMeg   \n",
+       "40321   55744           6  2014-09-13 21:39:30       Mia Maria   \n",
+       "40322   55745         101  2014-09-13 23:45:27    tronbabylove   \n",
+       "40323   55746         106  2014-09-14 00:29:41             GPP   \n",
+       "40324   55747           1  2014-09-14 01:01:44  Shivam Agrawal   \n",
+       "\n",
+       "            LastAccessDate                      WebsiteUrl  \\\n",
+       "0      2010-07-19 06:55:26  http://meta.stackexchange.com/   \n",
+       "1      2013-11-12 22:07:23        http://stackoverflow.com   \n",
+       "2      2014-08-08 06:42:58        http://stackoverflow.com   \n",
+       "3      2014-01-02 09:31:02    http://minesweeperonline.com   \n",
+       "4      2014-08-13 00:23:47         http://www.statalgo.com   \n",
+       "...                    ...                             ...   \n",
+       "40320  2014-09-13 21:18:52                             NaN   \n",
+       "40321  2014-09-13 21:39:30                             NaN   \n",
+       "40322  2014-09-13 23:45:27                             NaN   \n",
+       "40323  2014-09-14 02:05:17                             NaN   \n",
+       "40324  2014-09-14 01:19:04                             NaN   \n",
+       "\n",
+       "                 Location                                            AboutMe  \\\n",
+       "0      on the server farm  <p>Hi, I'm not really a person.</p>\\r\\n\\r\\n<p>...   \n",
+       "1           Corvallis, OR  <p>Developer on the StackOverflow team.  Find ...   \n",
+       "2            New York, NY  <p><a href=\"http://blog.stackoverflow.com/2009...   \n",
+       "3       San Francisco, CA  <p>currently at a startup in SF</p>\\r\\n\\r\\n<p>...   \n",
+       "4            New York, NY  <p>Quantitative researcher focusing on statist...   \n",
+       "...                   ...                                                ...   \n",
+       "40320                 NaN                                                NaN   \n",
+       "40321                 NaN                                                NaN   \n",
+       "40322       United States                                                NaN   \n",
+       "40323                 NaN  <p>Stats noobie, product, marketing &amp; medi...   \n",
+       "40324               India                       <p>Maths Enthusiast </p>\\r\\n   \n",
+       "\n",
+       "       Views  UpVotes  DownVotes  AccountId   Age  \\\n",
+       "0          0     5007       1920         -1   NaN   \n",
+       "1         25        3          0          2  37.0   \n",
+       "2         22       19          0          3  35.0   \n",
+       "3         11        0          0       1998  28.0   \n",
+       "4       1145      662          5      54503  35.0   \n",
+       "...      ...      ...        ...        ...   ...   \n",
+       "40320      0        0          0    5026902   NaN   \n",
+       "40321      1        0          0    5026998   NaN   \n",
+       "40322      0        0          0     481766   NaN   \n",
+       "40323      1        0          0     976289   NaN   \n",
+       "40324      0        0          0    5027354   NaN   \n",
+       "\n",
+       "                                         ProfileImageUrl  \n",
+       "0                                                    NaN  \n",
+       "1                                                    NaN  \n",
+       "2                                                    NaN  \n",
+       "3                     http://i.stack.imgur.com/d1oHX.jpg  \n",
+       "4                                                    NaN  \n",
+       "...                                                  ...  \n",
+       "40320  http://graph.facebook.com/665821703/picture?ty...  \n",
+       "40321                                                NaN  \n",
+       "40322  https://www.gravatar.com/avatar/faa7a3fdbd8308...  \n",
+       "40323  https://www.gravatar.com/avatar/6d9e9fa6b783a3...  \n",
+       "40324  https://lh4.googleusercontent.com/-ZsXhwVaFmiY...  \n",
+       "\n",
+       "[40325 rows x 14 columns]"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "users.rename(columns={'Id': 'userId'}, inplace=True)\n",
+    "users\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -51,40 +675,785 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 58,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "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>Id</th>\n",
+       "      <th>PostTypeId</th>\n",
+       "      <th>AcceptedAnswerId</th>\n",
+       "      <th>CreaionDate</th>\n",
+       "      <th>Score</th>\n",
+       "      <th>ViewCount</th>\n",
+       "      <th>Body</th>\n",
+       "      <th>OwnerUserId</th>\n",
+       "      <th>LasActivityDate</th>\n",
+       "      <th>Title</th>\n",
+       "      <th>...</th>\n",
+       "      <th>AnswerCount</th>\n",
+       "      <th>CommentCount</th>\n",
+       "      <th>FavoriteCount</th>\n",
+       "      <th>LastEditorUserId</th>\n",
+       "      <th>LastEditDate</th>\n",
+       "      <th>CommunityOwnedDate</th>\n",
+       "      <th>ParentId</th>\n",
+       "      <th>ClosedDate</th>\n",
+       "      <th>OwnerDisplayName</th>\n",
+       "      <th>LastEditorDisplayName</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>2010-07-19 19:12:12</td>\n",
+       "      <td>23</td>\n",
+       "      <td>1278.0</td>\n",
+       "      <td>&lt;p&gt;How should I elicit prior distributions fro...</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>2010-09-15 21:08:26</td>\n",
+       "      <td>Eliciting priors from experts</td>\n",
+       "      <td>...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14.0</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",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>59.0</td>\n",
+       "      <td>2010-07-19 19:12:57</td>\n",
+       "      <td>22</td>\n",
+       "      <td>8198.0</td>\n",
+       "      <td>&lt;p&gt;In many different statistical methods there...</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>2012-11-12 09:21:54</td>\n",
+       "      <td>What is normality?</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>2010-08-07 17:56:44</td>\n",
+       "      <td>NaN</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>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>2010-07-19 19:13:28</td>\n",
+       "      <td>54</td>\n",
+       "      <td>3613.0</td>\n",
+       "      <td>&lt;p&gt;What are some valuable Statistical Analysis...</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>2013-05-27 14:48:36</td>\n",
+       "      <td>What are some valuable Statistical Analysis op...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>36.0</td>\n",
+       "      <td>183.0</td>\n",
+       "      <td>2011-02-12 05:50:03</td>\n",
+       "      <td>2010-07-19 19:13:28</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>4</td>\n",
+       "      <td>1</td>\n",
+       "      <td>135.0</td>\n",
+       "      <td>2010-07-19 19:13:31</td>\n",
+       "      <td>13</td>\n",
+       "      <td>5224.0</td>\n",
+       "      <td>&lt;p&gt;I have two groups of data.  Each with a dif...</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>2010-09-08 03:00:19</td>\n",
+       "      <td>Assessing the significance of differences in d...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2.0</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",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2010-07-19 19:14:43</td>\n",
+       "      <td>81</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;The R-project&lt;/p&gt;\\n\\n&lt;p&gt;&lt;a href=\"http://www...</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>2010-07-19 19:21:15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>2010-07-19 19:21:15</td>\n",
+       "      <td>2010-07-19 19:14:43</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39995</th>\n",
+       "      <td>48321</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2013-01-23 09:00:01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;you can use the matlab codes for svm and co...</td>\n",
+       "      <td>19966.0</td>\n",
+       "      <td>2013-01-23 09:00:01</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>45118.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39996</th>\n",
+       "      <td>48322</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2013-01-23 09:09:34</td>\n",
+       "      <td>3</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;I use &lt;a href=\"http://www.gnu.org/software/...</td>\n",
+       "      <td>892.0</td>\n",
+       "      <td>2013-01-23 13:13:30</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>892.0</td>\n",
+       "      <td>2013-01-23 13:13:30</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>48311.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39997</th>\n",
+       "      <td>48323</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2013-01-23 09:16:44</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;If I understand your question correctly, yo...</td>\n",
+       "      <td>2020.0</td>\n",
+       "      <td>2013-01-23 09:16:44</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>48247.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39998</th>\n",
+       "      <td>48324</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2013-01-23 09:36:07</td>\n",
+       "      <td>3</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;Doesn't really help you with your question,...</td>\n",
+       "      <td>19914.0</td>\n",
+       "      <td>2013-01-23 09:36:07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>48297.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39999</th>\n",
+       "      <td>48325</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2013-01-23 09:44:07</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>116.0</td>\n",
+       "      <td>&lt;p&gt;I have 10 vectors each having 100,000 point...</td>\n",
+       "      <td>19968.0</td>\n",
+       "      <td>2013-02-22 11:23:54</td>\n",
+       "      <td>are data sets obtained from a Normal distribut...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>4</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",
+       "<p>40000 rows × 21 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          Id  PostTypeId  AcceptedAnswerId          CreaionDate  Score  \\\n",
+       "0          1           1              15.0  2010-07-19 19:12:12     23   \n",
+       "1          2           1              59.0  2010-07-19 19:12:57     22   \n",
+       "2          3           1               5.0  2010-07-19 19:13:28     54   \n",
+       "3          4           1             135.0  2010-07-19 19:13:31     13   \n",
+       "4          5           2               NaN  2010-07-19 19:14:43     81   \n",
+       "...      ...         ...               ...                  ...    ...   \n",
+       "39995  48321           2               NaN  2013-01-23 09:00:01      0   \n",
+       "39996  48322           2               NaN  2013-01-23 09:09:34      3   \n",
+       "39997  48323           2               NaN  2013-01-23 09:16:44      1   \n",
+       "39998  48324           2               NaN  2013-01-23 09:36:07      3   \n",
+       "39999  48325           1               NaN  2013-01-23 09:44:07     -1   \n",
+       "\n",
+       "       ViewCount                                               Body  \\\n",
+       "0         1278.0  <p>How should I elicit prior distributions fro...   \n",
+       "1         8198.0  <p>In many different statistical methods there...   \n",
+       "2         3613.0  <p>What are some valuable Statistical Analysis...   \n",
+       "3         5224.0  <p>I have two groups of data.  Each with a dif...   \n",
+       "4            NaN  <p>The R-project</p>\\n\\n<p><a href=\"http://www...   \n",
+       "...          ...                                                ...   \n",
+       "39995        NaN  <p>you can use the matlab codes for svm and co...   \n",
+       "39996        NaN  <p>I use <a href=\"http://www.gnu.org/software/...   \n",
+       "39997        NaN  <p>If I understand your question correctly, yo...   \n",
+       "39998        NaN  <p>Doesn't really help you with your question,...   \n",
+       "39999      116.0  <p>I have 10 vectors each having 100,000 point...   \n",
+       "\n",
+       "       OwnerUserId      LasActivityDate  \\\n",
+       "0              8.0  2010-09-15 21:08:26   \n",
+       "1             24.0  2012-11-12 09:21:54   \n",
+       "2             18.0  2013-05-27 14:48:36   \n",
+       "3             23.0  2010-09-08 03:00:19   \n",
+       "4             23.0  2010-07-19 19:21:15   \n",
+       "...            ...                  ...   \n",
+       "39995      19966.0  2013-01-23 09:00:01   \n",
+       "39996        892.0  2013-01-23 13:13:30   \n",
+       "39997       2020.0  2013-01-23 09:16:44   \n",
+       "39998      19914.0  2013-01-23 09:36:07   \n",
+       "39999      19968.0  2013-02-22 11:23:54   \n",
+       "\n",
+       "                                                   Title  ... AnswerCount  \\\n",
+       "0                          Eliciting priors from experts  ...         5.0   \n",
+       "1                                     What is normality?  ...         7.0   \n",
+       "2      What are some valuable Statistical Analysis op...  ...        19.0   \n",
+       "3      Assessing the significance of differences in d...  ...         5.0   \n",
+       "4                                                    NaN  ...         NaN   \n",
+       "...                                                  ...  ...         ...   \n",
+       "39995                                                NaN  ...         NaN   \n",
+       "39996                                                NaN  ...         NaN   \n",
+       "39997                                                NaN  ...         NaN   \n",
+       "39998                                                NaN  ...         NaN   \n",
+       "39999  are data sets obtained from a Normal distribut...  ...         2.0   \n",
+       "\n",
+       "       CommentCount  FavoriteCount  LastEditorUserId         LastEditDate  \\\n",
+       "0                 1           14.0               NaN                  NaN   \n",
+       "1                 1            8.0              88.0  2010-08-07 17:56:44   \n",
+       "2                 4           36.0             183.0  2011-02-12 05:50:03   \n",
+       "3                 2            2.0               NaN                  NaN   \n",
+       "4                 3            NaN              23.0  2010-07-19 19:21:15   \n",
+       "...             ...            ...               ...                  ...   \n",
+       "39995             0            NaN               NaN                  NaN   \n",
+       "39996             2            NaN             892.0  2013-01-23 13:13:30   \n",
+       "39997             0            NaN               NaN                  NaN   \n",
+       "39998             0            NaN               NaN                  NaN   \n",
+       "39999             4            NaN               NaN                  NaN   \n",
+       "\n",
+       "        CommunityOwnedDate ParentId  ClosedDate OwnerDisplayName  \\\n",
+       "0                      NaN      NaN         NaN              NaN   \n",
+       "1                      NaN      NaN         NaN              NaN   \n",
+       "2      2010-07-19 19:13:28      NaN         NaN              NaN   \n",
+       "3                      NaN      NaN         NaN              NaN   \n",
+       "4      2010-07-19 19:14:43      3.0         NaN              NaN   \n",
+       "...                    ...      ...         ...              ...   \n",
+       "39995                  NaN  45118.0         NaN              NaN   \n",
+       "39996                  NaN  48311.0         NaN              NaN   \n",
+       "39997                  NaN  48247.0         NaN              NaN   \n",
+       "39998                  NaN  48297.0         NaN              NaN   \n",
+       "39999                  NaN      NaN         NaN              NaN   \n",
+       "\n",
+       "      LastEditorDisplayName  \n",
+       "0                       NaN  \n",
+       "1                       NaN  \n",
+       "2                       NaN  \n",
+       "3                       NaN  \n",
+       "4                       NaN  \n",
+       "...                     ...  \n",
+       "39995                   NaN  \n",
+       "39996                   NaN  \n",
+       "39997                   NaN  \n",
+       "39998                   NaN  \n",
+       "39999                   NaN  \n",
+       "\n",
+       "[40000 rows x 21 columns]"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "posts = pd.read_csv('posts_table.csv')\n",
+    "posts"
+   ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 27,
    "metadata": {},
+   "outputs": [],
    "source": [
     "#### 5. Rename Id column to postId and OwnerUserId to userId"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 59,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "posts.rename(columns={'Id': 'postId', 'OwnerUserId': 'userId'}, inplace=True)\n"
+   ]
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
+   "outputs": [],
    "source": [
-    "#### 6. Define new dataframes for users and posts with the following selected columns:\n",
+    "# 6. Define new dataframes for users and posts with the following selected columns:\n",
     "    **users columns**: userId, Reputation,Views,UpVotes,DownVotes\n",
     "    **posts columns**: postId, Score,userId,ViewCount,CommentCount"
    ]
   },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": []
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 71,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "users_new = users.loc[:, ['userId', 'Reputation', 'Views', 'UpVotes', 'DownVotes']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "posts_new = posts.loc[:, ['postId', 'Score', 'userId', 'ViewCount', 'CommentCount']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "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>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>101</td>\n",
+       "      <td>25</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>101</td>\n",
+       "      <td>22</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>101</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>6792</td>\n",
+       "      <td>1145</td>\n",
+       "      <td>662</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40320</th>\n",
+       "      <td>55743</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40321</th>\n",
+       "      <td>55744</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40322</th>\n",
+       "      <td>55745</td>\n",
+       "      <td>101</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40323</th>\n",
+       "      <td>55746</td>\n",
+       "      <td>106</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40324</th>\n",
+       "      <td>55747</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>40325 rows × 5 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       userId  Reputation  Views  UpVotes  DownVotes\n",
+       "0          -1           1      0     5007       1920\n",
+       "1           2         101     25        3          0\n",
+       "2           3         101     22       19          0\n",
+       "3           4         101     11        0          0\n",
+       "4           5        6792   1145      662          5\n",
+       "...       ...         ...    ...      ...        ...\n",
+       "40320   55743           1      0        0          0\n",
+       "40321   55744           6      1        0          0\n",
+       "40322   55745         101      0        0          0\n",
+       "40323   55746         106      1        0          0\n",
+       "40324   55747           1      0        0          0\n",
+       "\n",
+       "[40325 rows x 5 columns]"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "users_new"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "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>postId</th>\n",
+       "      <th>Score</th>\n",
+       "      <th>userId</th>\n",
+       "      <th>ViewCount</th>\n",
+       "      <th>CommentCount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>23</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>1278.0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>22</td>\n",
+       "      <td>24.0</td>\n",
+       "      <td>8198.0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>54</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>3613.0</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>13</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>5224.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>81</td>\n",
+       "      <td>23.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39995</th>\n",
+       "      <td>48321</td>\n",
+       "      <td>0</td>\n",
+       "      <td>19966.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39996</th>\n",
+       "      <td>48322</td>\n",
+       "      <td>3</td>\n",
+       "      <td>892.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39997</th>\n",
+       "      <td>48323</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2020.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39998</th>\n",
+       "      <td>48324</td>\n",
+       "      <td>3</td>\n",
+       "      <td>19914.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39999</th>\n",
+       "      <td>48325</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>19968.0</td>\n",
+       "      <td>116.0</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>40000 rows × 5 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       postId  Score   userId  ViewCount  CommentCount\n",
+       "0           1     23      8.0     1278.0             1\n",
+       "1           2     22     24.0     8198.0             1\n",
+       "2           3     54     18.0     3613.0             4\n",
+       "3           4     13     23.0     5224.0             2\n",
+       "4           5     81     23.0        NaN             3\n",
+       "...       ...    ...      ...        ...           ...\n",
+       "39995   48321      0  19966.0        NaN             0\n",
+       "39996   48322      3    892.0        NaN             2\n",
+       "39997   48323      1   2020.0        NaN             0\n",
+       "39998   48324      3  19914.0        NaN             0\n",
+       "39999   48325     -1  19968.0      116.0             4\n",
+       "\n",
+       "[40000 rows x 5 columns]"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "posts_new"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -96,10 +1465,429 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 83,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "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>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>CreationDate</th>\n",
+       "      <th>DisplayName</th>\n",
+       "      <th>LastAccessDate</th>\n",
+       "      <th>WebsiteUrl</th>\n",
+       "      <th>Location</th>\n",
+       "      <th>AboutMe</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>...</th>\n",
+       "      <th>AnswerCount</th>\n",
+       "      <th>CommentCount</th>\n",
+       "      <th>FavoriteCount</th>\n",
+       "      <th>LastEditorUserId</th>\n",
+       "      <th>LastEditDate</th>\n",
+       "      <th>CommunityOwnedDate</th>\n",
+       "      <th>ParentId</th>\n",
+       "      <th>ClosedDate</th>\n",
+       "      <th>OwnerDisplayName</th>\n",
+       "      <th>LastEditorDisplayName</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>Community</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>http://meta.stackexchange.com/</td>\n",
+       "      <td>on the server farm</td>\n",
+       "      <td>&lt;p&gt;Hi, I'm not really a person.&lt;/p&gt;\\r\\n\\r\\n&lt;p&gt;...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>-1.0</td>\n",
+       "      <td>2014-04-23 13:43:43</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>123</th>\n",
+       "      <td>5</td>\n",
+       "      <td>6792</td>\n",
+       "      <td>2010-07-19 19:03:57</td>\n",
+       "      <td>Shane</td>\n",
+       "      <td>2014-08-13 00:23:47</td>\n",
+       "      <td>http://www.statalgo.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;Quantitative researcher focusing on statist...</td>\n",
+       "      <td>1145</td>\n",
+       "      <td>662</td>\n",
+       "      <td>...</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>22047.0</td>\n",
+       "      <td>2013-06-07 06:38:10</td>\n",
+       "      <td>2010-08-09 13:05:50</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>240</th>\n",
+       "      <td>6</td>\n",
+       "      <td>457</td>\n",
+       "      <td>2010-07-19 19:04:07</td>\n",
+       "      <td>Harlan</td>\n",
+       "      <td>2014-08-07 19:49:44</td>\n",
+       "      <td>http://www.harlan.harris.name</td>\n",
+       "      <td>District of Columbia</td>\n",
+       "      <td>&lt;ul&gt;\\r\\n&lt;li&gt;PhD in CS/AI/Machine Learning/Cogn...</td>\n",
+       "      <td>114</td>\n",
+       "      <td>47</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>252</th>\n",
+       "      <td>7</td>\n",
+       "      <td>429</td>\n",
+       "      <td>2010-07-19 19:04:37</td>\n",
+       "      <td>Vince</td>\n",
+       "      <td>2014-09-10 21:14:12</td>\n",
+       "      <td>http://bioinformatics.ucdavis.edu</td>\n",
+       "      <td>Davis, CA</td>\n",
+       "      <td>I'm a recent graduate of UC Davis in Economics...</td>\n",
+       "      <td>56</td>\n",
+       "      <td>20</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>2010-10-19 06:42:19</td>\n",
+       "      <td>2011-06-02 11:09:11</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>254</th>\n",
+       "      <td>8</td>\n",
+       "      <td>6764</td>\n",
+       "      <td>2010-07-19 19:04:52</td>\n",
+       "      <td>csgillespie</td>\n",
+       "      <td>2014-09-09 21:15:08</td>\n",
+       "      <td>http://www.mas.ncl.ac.uk/~ncsg3/</td>\n",
+       "      <td>Newcastle, United Kingdom</td>\n",
+       "      <td>&lt;p&gt;I'm a statistics lecturer at Newcastle Univ...</td>\n",
+       "      <td>1089</td>\n",
+       "      <td>604</td>\n",
+       "      <td>...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14.0</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",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38957</th>\n",
+       "      <td>45934</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2014-05-21 17:13:23</td>\n",
+       "      <td>jasonweiyi</td>\n",
+       "      <td>2014-06-08 13:36:47</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>805.0</td>\n",
+       "      <td>2013-05-13 04:41:41</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>jasonweiyi</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38958</th>\n",
+       "      <td>46192</td>\n",
+       "      <td>36</td>\n",
+       "      <td>2014-05-26 15:29:30</td>\n",
+       "      <td>user1738753</td>\n",
+       "      <td>2014-09-10 19:52:34</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>930.0</td>\n",
+       "      <td>2012-10-18 15:07:40</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>user1738753</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38959</th>\n",
+       "      <td>46522</td>\n",
+       "      <td>235</td>\n",
+       "      <td>2014-06-01 17:25:18</td>\n",
+       "      <td>Andy Blankertz</td>\n",
+       "      <td>2014-09-13 18:03:07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>&lt;p&gt;Actuary for a life insurance company.&lt;/p&gt;\\r\\n</td>\n",
+       "      <td>13</td>\n",
+       "      <td>27</td>\n",
+       "      <td>...</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0</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>user1009703</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38960</th>\n",
+       "      <td>52371</td>\n",
+       "      <td>221</td>\n",
+       "      <td>2014-07-19 13:36:58</td>\n",
+       "      <td>Karel Petranek</td>\n",
+       "      <td>2014-07-20 09:32:16</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2014-07-30 20:09:14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>dark_charlie</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38961</th>\n",
+       "      <td>55226</td>\n",
+       "      <td>119</td>\n",
+       "      <td>2014-09-04 07:34:48</td>\n",
+       "      <td>Klas Lindbäck</td>\n",
+       "      <td>2014-09-08 11:07:33</td>\n",
+       "      <td>http://N/A</td>\n",
+       "      <td>Sweden</td>\n",
+       "      <td>&lt;p&gt;Working with a wide range of languages, but...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16174.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Klas Lindbäck</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>8138 rows × 34 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       userId  Reputation         CreationDate     DisplayName  \\\n",
+       "0          -1           1  2010-07-19 06:55:26       Community   \n",
+       "123         5        6792  2010-07-19 19:03:57           Shane   \n",
+       "240         6         457  2010-07-19 19:04:07          Harlan   \n",
+       "252         7         429  2010-07-19 19:04:37           Vince   \n",
+       "254         8        6764  2010-07-19 19:04:52     csgillespie   \n",
+       "...       ...         ...                  ...             ...   \n",
+       "38957   45934          11  2014-05-21 17:13:23      jasonweiyi   \n",
+       "38958   46192          36  2014-05-26 15:29:30     user1738753   \n",
+       "38959   46522         235  2014-06-01 17:25:18  Andy Blankertz   \n",
+       "38960   52371         221  2014-07-19 13:36:58  Karel Petranek   \n",
+       "38961   55226         119  2014-09-04 07:34:48   Klas Lindbäck   \n",
+       "\n",
+       "            LastAccessDate                         WebsiteUrl  \\\n",
+       "0      2010-07-19 06:55:26     http://meta.stackexchange.com/   \n",
+       "123    2014-08-13 00:23:47            http://www.statalgo.com   \n",
+       "240    2014-08-07 19:49:44      http://www.harlan.harris.name   \n",
+       "252    2014-09-10 21:14:12  http://bioinformatics.ucdavis.edu   \n",
+       "254    2014-09-09 21:15:08   http://www.mas.ncl.ac.uk/~ncsg3/   \n",
+       "...                    ...                                ...   \n",
+       "38957  2014-06-08 13:36:47                                NaN   \n",
+       "38958  2014-09-10 19:52:34                                NaN   \n",
+       "38959  2014-09-13 18:03:07                                NaN   \n",
+       "38960  2014-07-20 09:32:16                                NaN   \n",
+       "38961  2014-09-08 11:07:33                         http://N/A   \n",
+       "\n",
+       "                        Location  \\\n",
+       "0             on the server farm   \n",
+       "123                 New York, NY   \n",
+       "240         District of Columbia   \n",
+       "252                    Davis, CA   \n",
+       "254    Newcastle, United Kingdom   \n",
+       "...                          ...   \n",
+       "38957                        NaN   \n",
+       "38958                        NaN   \n",
+       "38959                        NaN   \n",
+       "38960                        NaN   \n",
+       "38961                     Sweden   \n",
+       "\n",
+       "                                                 AboutMe  Views  UpVotes  ...  \\\n",
+       "0      <p>Hi, I'm not really a person.</p>\\r\\n\\r\\n<p>...      0     5007  ...   \n",
+       "123    <p>Quantitative researcher focusing on statist...   1145      662  ...   \n",
+       "240    <ul>\\r\\n<li>PhD in CS/AI/Machine Learning/Cogn...    114       47  ...   \n",
+       "252    I'm a recent graduate of UC Davis in Economics...     56       20  ...   \n",
+       "254    <p>I'm a statistics lecturer at Newcastle Univ...   1089      604  ...   \n",
+       "...                                                  ...    ...      ...  ...   \n",
+       "38957                                                NaN      1        0  ...   \n",
+       "38958                                                NaN      1        0  ...   \n",
+       "38959   <p>Actuary for a life insurance company.</p>\\r\\n     13       27  ...   \n",
+       "38960                                                NaN      2        0  ...   \n",
+       "38961  <p>Working with a wide range of languages, but...      2        3  ...   \n",
+       "\n",
+       "       AnswerCount  CommentCount  FavoriteCount LastEditorUserId  \\\n",
+       "0              NaN             0            NaN             -1.0   \n",
+       "123           15.0             5          137.0          22047.0   \n",
+       "240            NaN             0            NaN              NaN   \n",
+       "252            7.0             2            7.0             88.0   \n",
+       "254            5.0             1           14.0              NaN   \n",
+       "...            ...           ...            ...              ...   \n",
+       "38957          1.0             2            NaN            805.0   \n",
+       "38958          1.0             2            1.0            930.0   \n",
+       "38959          3.0             0            NaN              NaN   \n",
+       "38960          7.0             5            8.0              NaN   \n",
+       "38961          NaN             0            NaN              NaN   \n",
+       "\n",
+       "              LastEditDate   CommunityOwnedDate  ParentId ClosedDate  \\\n",
+       "0      2014-04-23 13:43:43                  NaN       NaN        NaN   \n",
+       "123    2013-06-07 06:38:10  2010-08-09 13:05:50       NaN        NaN   \n",
+       "240                    NaN                  NaN       1.0        NaN   \n",
+       "252    2010-10-19 06:42:19  2011-06-02 11:09:11       NaN        NaN   \n",
+       "254                    NaN                  NaN       NaN        NaN   \n",
+       "...                    ...                  ...       ...        ...   \n",
+       "38957  2013-05-13 04:41:41                  NaN       NaN        NaN   \n",
+       "38958  2012-10-18 15:07:40                  NaN       NaN        NaN   \n",
+       "38959                  NaN                  NaN       NaN        NaN   \n",
+       "38960                  NaN  2014-07-30 20:09:14       NaN        NaN   \n",
+       "38961                  NaN                  NaN   16174.0        NaN   \n",
+       "\n",
+       "       OwnerDisplayName  LastEditorDisplayName  \n",
+       "0                   NaN                    NaN  \n",
+       "123                 NaN                    NaN  \n",
+       "240                 NaN                    NaN  \n",
+       "252                 NaN                    NaN  \n",
+       "254                 NaN                    NaN  \n",
+       "...                 ...                    ...  \n",
+       "38957        jasonweiyi                    NaN  \n",
+       "38958       user1738753                    NaN  \n",
+       "38959       user1009703                    NaN  \n",
+       "38960      dark_charlie                    NaN  \n",
+       "38961     Klas Lindbäck                    NaN  \n",
+       "\n",
+       "[8138 rows x 34 columns]"
+      ]
+     },
+     "execution_count": 83,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "merged_df = pd.merge(users, posts, how = 'inner',on='userId')\n",
+    "merged_df = merged_df.drop_duplicates(subset='userId')\n",
+    "\n",
+    "merged_df"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -110,10 +1898,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 84,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Columns with missing values:\n",
+      "['DisplayName', 'WebsiteUrl', 'Location', 'AboutMe', 'Age', 'ProfileImageUrl', 'AcceptedAnswerId', 'ViewCount', 'Title', 'Tags', 'AnswerCount', 'FavoriteCount', 'LastEditorUserId', 'LastEditDate', 'CommunityOwnedDate', 'ParentId', 'ClosedDate', 'OwnerDisplayName', 'LastEditorDisplayName']\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "missing_mask = merged_df.isna()\n",
+    "cols_with_missing = missing_mask.any(axis=0)\n",
+    "\n",
+    "print(\"Columns with missing values:\")\n",
+    "print(cols_with_missing[cols_with_missing == True].index.tolist())\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -123,6 +1927,489 @@
     "**Remember** to check the results of your code before passing to the next step"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "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>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>CreationDate</th>\n",
+       "      <th>DisplayName</th>\n",
+       "      <th>LastAccessDate</th>\n",
+       "      <th>WebsiteUrl</th>\n",
+       "      <th>Location</th>\n",
+       "      <th>AboutMe</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>...</th>\n",
+       "      <th>AnswerCount</th>\n",
+       "      <th>CommentCount</th>\n",
+       "      <th>FavoriteCount</th>\n",
+       "      <th>LastEditorUserId</th>\n",
+       "      <th>LastEditDate</th>\n",
+       "      <th>CommunityOwnedDate</th>\n",
+       "      <th>ParentId</th>\n",
+       "      <th>ClosedDate</th>\n",
+       "      <th>OwnerDisplayName</th>\n",
+       "      <th>LastEditorDisplayName</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>Community</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>http://meta.stackexchange.com/</td>\n",
+       "      <td>on the server farm</td>\n",
+       "      <td>&lt;p&gt;Hi, I'm not really a person.&lt;/p&gt;\\r\\n\\r\\n&lt;p&gt;...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>...</td>\n",
+       "      <td>-</td>\n",
+       "      <td>0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-1.0</td>\n",
+       "      <td>2014-04-23 13:43:43</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>123</th>\n",
+       "      <td>5</td>\n",
+       "      <td>6792</td>\n",
+       "      <td>2010-07-19 19:03:57</td>\n",
+       "      <td>Shane</td>\n",
+       "      <td>2014-08-13 00:23:47</td>\n",
+       "      <td>http://www.statalgo.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;Quantitative researcher focusing on statist...</td>\n",
+       "      <td>1145</td>\n",
+       "      <td>662</td>\n",
+       "      <td>...</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>22047.0</td>\n",
+       "      <td>2013-06-07 06:38:10</td>\n",
+       "      <td>2010-08-09 13:05:50</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>240</th>\n",
+       "      <td>6</td>\n",
+       "      <td>457</td>\n",
+       "      <td>2010-07-19 19:04:07</td>\n",
+       "      <td>Harlan</td>\n",
+       "      <td>2014-08-07 19:49:44</td>\n",
+       "      <td>http://www.harlan.harris.name</td>\n",
+       "      <td>District of Columbia</td>\n",
+       "      <td>&lt;ul&gt;\\r\\n&lt;li&gt;PhD in CS/AI/Machine Learning/Cogn...</td>\n",
+       "      <td>114</td>\n",
+       "      <td>47</td>\n",
+       "      <td>...</td>\n",
+       "      <td>-</td>\n",
+       "      <td>0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>252</th>\n",
+       "      <td>7</td>\n",
+       "      <td>429</td>\n",
+       "      <td>2010-07-19 19:04:37</td>\n",
+       "      <td>Vince</td>\n",
+       "      <td>2014-09-10 21:14:12</td>\n",
+       "      <td>http://bioinformatics.ucdavis.edu</td>\n",
+       "      <td>Davis, CA</td>\n",
+       "      <td>I'm a recent graduate of UC Davis in Economics...</td>\n",
+       "      <td>56</td>\n",
+       "      <td>20</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>2010-10-19 06:42:19</td>\n",
+       "      <td>2011-06-02 11:09:11</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>254</th>\n",
+       "      <td>8</td>\n",
+       "      <td>6764</td>\n",
+       "      <td>2010-07-19 19:04:52</td>\n",
+       "      <td>csgillespie</td>\n",
+       "      <td>2014-09-09 21:15:08</td>\n",
+       "      <td>http://www.mas.ncl.ac.uk/~ncsg3/</td>\n",
+       "      <td>Newcastle, United Kingdom</td>\n",
+       "      <td>&lt;p&gt;I'm a statistics lecturer at Newcastle Univ...</td>\n",
+       "      <td>1089</td>\n",
+       "      <td>604</td>\n",
+       "      <td>...</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38957</th>\n",
+       "      <td>45934</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2014-05-21 17:13:23</td>\n",
+       "      <td>jasonweiyi</td>\n",
+       "      <td>2014-06-08 13:36:47</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>-</td>\n",
+       "      <td>805.0</td>\n",
+       "      <td>2013-05-13 04:41:41</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>jasonweiyi</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38958</th>\n",
+       "      <td>46192</td>\n",
+       "      <td>36</td>\n",
+       "      <td>2014-05-26 15:29:30</td>\n",
+       "      <td>user1738753</td>\n",
+       "      <td>2014-09-10 19:52:34</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>930.0</td>\n",
+       "      <td>2012-10-18 15:07:40</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>user1738753</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38959</th>\n",
+       "      <td>46522</td>\n",
+       "      <td>235</td>\n",
+       "      <td>2014-06-01 17:25:18</td>\n",
+       "      <td>Andy Blankertz</td>\n",
+       "      <td>2014-09-13 18:03:07</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>&lt;p&gt;Actuary for a life insurance company.&lt;/p&gt;\\r\\n</td>\n",
+       "      <td>13</td>\n",
+       "      <td>27</td>\n",
+       "      <td>...</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>user1009703</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38960</th>\n",
+       "      <td>52371</td>\n",
+       "      <td>221</td>\n",
+       "      <td>2014-07-19 13:36:58</td>\n",
+       "      <td>Karel Petranek</td>\n",
+       "      <td>2014-07-20 09:32:16</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>2014-07-30 20:09:14</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>dark_charlie</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38961</th>\n",
+       "      <td>55226</td>\n",
+       "      <td>119</td>\n",
+       "      <td>2014-09-04 07:34:48</td>\n",
+       "      <td>Klas Lindbäck</td>\n",
+       "      <td>2014-09-08 11:07:33</td>\n",
+       "      <td>http://N/A</td>\n",
+       "      <td>Sweden</td>\n",
+       "      <td>&lt;p&gt;Working with a wide range of languages, but...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "      <td>...</td>\n",
+       "      <td>-</td>\n",
+       "      <td>0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>-</td>\n",
+       "      <td>16174.0</td>\n",
+       "      <td>-</td>\n",
+       "      <td>Klas Lindbäck</td>\n",
+       "      <td>-</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>8138 rows × 34 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       userId  Reputation         CreationDate     DisplayName  \\\n",
+       "0          -1           1  2010-07-19 06:55:26       Community   \n",
+       "123         5        6792  2010-07-19 19:03:57           Shane   \n",
+       "240         6         457  2010-07-19 19:04:07          Harlan   \n",
+       "252         7         429  2010-07-19 19:04:37           Vince   \n",
+       "254         8        6764  2010-07-19 19:04:52     csgillespie   \n",
+       "...       ...         ...                  ...             ...   \n",
+       "38957   45934          11  2014-05-21 17:13:23      jasonweiyi   \n",
+       "38958   46192          36  2014-05-26 15:29:30     user1738753   \n",
+       "38959   46522         235  2014-06-01 17:25:18  Andy Blankertz   \n",
+       "38960   52371         221  2014-07-19 13:36:58  Karel Petranek   \n",
+       "38961   55226         119  2014-09-04 07:34:48   Klas Lindbäck   \n",
+       "\n",
+       "            LastAccessDate                         WebsiteUrl  \\\n",
+       "0      2010-07-19 06:55:26     http://meta.stackexchange.com/   \n",
+       "123    2014-08-13 00:23:47            http://www.statalgo.com   \n",
+       "240    2014-08-07 19:49:44      http://www.harlan.harris.name   \n",
+       "252    2014-09-10 21:14:12  http://bioinformatics.ucdavis.edu   \n",
+       "254    2014-09-09 21:15:08   http://www.mas.ncl.ac.uk/~ncsg3/   \n",
+       "...                    ...                                ...   \n",
+       "38957  2014-06-08 13:36:47                                  -   \n",
+       "38958  2014-09-10 19:52:34                                  -   \n",
+       "38959  2014-09-13 18:03:07                                  -   \n",
+       "38960  2014-07-20 09:32:16                                  -   \n",
+       "38961  2014-09-08 11:07:33                         http://N/A   \n",
+       "\n",
+       "                        Location  \\\n",
+       "0             on the server farm   \n",
+       "123                 New York, NY   \n",
+       "240         District of Columbia   \n",
+       "252                    Davis, CA   \n",
+       "254    Newcastle, United Kingdom   \n",
+       "...                          ...   \n",
+       "38957                          -   \n",
+       "38958                          -   \n",
+       "38959                          -   \n",
+       "38960                          -   \n",
+       "38961                     Sweden   \n",
+       "\n",
+       "                                                 AboutMe  Views  UpVotes  ...  \\\n",
+       "0      <p>Hi, I'm not really a person.</p>\\r\\n\\r\\n<p>...      0     5007  ...   \n",
+       "123    <p>Quantitative researcher focusing on statist...   1145      662  ...   \n",
+       "240    <ul>\\r\\n<li>PhD in CS/AI/Machine Learning/Cogn...    114       47  ...   \n",
+       "252    I'm a recent graduate of UC Davis in Economics...     56       20  ...   \n",
+       "254    <p>I'm a statistics lecturer at Newcastle Univ...   1089      604  ...   \n",
+       "...                                                  ...    ...      ...  ...   \n",
+       "38957                                                  -      1        0  ...   \n",
+       "38958                                                  -      1        0  ...   \n",
+       "38959   <p>Actuary for a life insurance company.</p>\\r\\n     13       27  ...   \n",
+       "38960                                                  -      2        0  ...   \n",
+       "38961  <p>Working with a wide range of languages, but...      2        3  ...   \n",
+       "\n",
+       "       AnswerCount  CommentCount FavoriteCount LastEditorUserId  \\\n",
+       "0                -             0             -             -1.0   \n",
+       "123           15.0             5         137.0          22047.0   \n",
+       "240              -             0             -                -   \n",
+       "252            7.0             2           7.0             88.0   \n",
+       "254            5.0             1          14.0                -   \n",
+       "...            ...           ...           ...              ...   \n",
+       "38957          1.0             2             -            805.0   \n",
+       "38958          1.0             2           1.0            930.0   \n",
+       "38959          3.0             0             -                -   \n",
+       "38960          7.0             5           8.0                -   \n",
+       "38961            -             0             -                -   \n",
+       "\n",
+       "              LastEditDate   CommunityOwnedDate ParentId ClosedDate  \\\n",
+       "0      2014-04-23 13:43:43                    -        -          -   \n",
+       "123    2013-06-07 06:38:10  2010-08-09 13:05:50        -          -   \n",
+       "240                      -                    -      1.0          -   \n",
+       "252    2010-10-19 06:42:19  2011-06-02 11:09:11        -          -   \n",
+       "254                      -                    -        -          -   \n",
+       "...                    ...                  ...      ...        ...   \n",
+       "38957  2013-05-13 04:41:41                    -        -          -   \n",
+       "38958  2012-10-18 15:07:40                    -        -          -   \n",
+       "38959                    -                    -        -          -   \n",
+       "38960                    -  2014-07-30 20:09:14        -          -   \n",
+       "38961                    -                    -  16174.0          -   \n",
+       "\n",
+       "       OwnerDisplayName LastEditorDisplayName  \n",
+       "0                     -                     -  \n",
+       "123                   -                     -  \n",
+       "240                   -                     -  \n",
+       "252                   -                     -  \n",
+       "254                   -                     -  \n",
+       "...                 ...                   ...  \n",
+       "38957        jasonweiyi                     -  \n",
+       "38958       user1738753                     -  \n",
+       "38959       user1009703                     -  \n",
+       "38960      dark_charlie                     -  \n",
+       "38961     Klas Lindbäck                     -  \n",
+       "\n",
+       "[8138 rows x 34 columns]"
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Fill missing values in the merged data frame with 0\n",
+    "merged_df.fillna('-', inplace=True)\n",
+    "merged_df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 10. Adjust the data types in order to avoid future issues. Which ones should be changed? "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "userId                            int64\n",
+      "Reputation                        int64\n",
+      "CreationDate             datetime64[ns]\n",
+      "DisplayName                      object\n",
+      "LastAccessDate                   object\n",
+      "WebsiteUrl                       object\n",
+      "Location                         object\n",
+      "AboutMe                          object\n",
+      "Views                             int64\n",
+      "UpVotes                           int64\n",
+      "DownVotes                         int64\n",
+      "AccountId                         int64\n",
+      "Age                              object\n",
+      "ProfileImageUrl                  object\n",
+      "postId                            int64\n",
+      "PostTypeId                        int64\n",
+      "AcceptedAnswerId                 object\n",
+      "CreaionDate                      object\n",
+      "Score                             int64\n",
+      "ViewCount                        object\n",
+      "Body                             object\n",
+      "LasActivityDate                  object\n",
+      "Title                            object\n",
+      "Tags                             object\n",
+      "AnswerCount                      object\n",
+      "CommentCount                      int64\n",
+      "FavoriteCount                    object\n",
+      "LastEditorUserId                 object\n",
+      "LastEditDate                     object\n",
+      "CommunityOwnedDate               object\n",
+      "ParentId                         object\n",
+      "ClosedDate                       object\n",
+      "OwnerDisplayName                 object\n",
+      "LastEditorDisplayName            object\n",
+      "dtype: object\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(merged_df.dtypes)\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -131,10 +2418,83 @@
    "source": []
   },
   {
-   "cell_type": "markdown",
+   "cell_type": "code",
+   "execution_count": 90,
    "metadata": {},
+   "outputs": [],
    "source": [
-    "#### 10. Adjust the data types in order to avoid future issues. Which ones should be changed? "
+    "# Convert columns to appropriate data types\n",
+    "\n",
+    "# Convert columns to appropriate data types\n",
+    "merged_df['CreationDate'] = pd.to_datetime(merged_df['CreationDate'])\n",
+    "merged_df['LastAccessDate'] = merged_df['LastAccessDate'].astype(str)\n",
+    "merged_df['WebsiteUrl'] = merged_df['WebsiteUrl'].astype(str)\n",
+    "merged_df['Location'] = merged_df['Location'].astype(str)\n",
+    "merged_df['AboutMe'] = merged_df['AboutMe'].astype(str)\n",
+    "merged_df['ProfileImageUrl'] = merged_df['ProfileImageUrl'].astype(str)\n",
+    "merged_df['Age'] = pd.to_numeric(merged_df['Age'], errors='coerce')\n",
+    "merged_df['AcceptedAnswerId'] = merged_df['AcceptedAnswerId'].astype(str)\n",
+    "merged_df['CreaionDate'] = merged_df['CreaionDate'].astype(str)\n",
+    "merged_df['ViewCount'] = pd.to_numeric(merged_df['ViewCount'], errors='coerce')\n",
+    "merged_df['LasActivityDate'] = merged_df['LasActivityDate'].astype(str)\n",
+    "merged_df['AnswerCount'] = pd.to_numeric(merged_df['AnswerCount'], errors='coerce')\n",
+    "merged_df['FavoriteCount'] = pd.to_numeric(merged_df['FavoriteCount'], errors='coerce')\n",
+    "merged_df['LastEditorUserId'] = merged_df['LastEditorUserId'].astype(str)\n",
+    "merged_df['ParentId'] = merged_df['ParentId'].astype(str)\n",
+    "merged_df['CreationDate'] = pd.to_datetime(merged_df['CreationDate'])\n",
+    "merged_df['LastEditDate'] = pd.to_datetime(merged_df['LastEditDate'], errors='coerce')\n",
+    "merged_df['CommunityOwnedDate'] = pd.to_datetime(merged_df['CommunityOwnedDate'], errors='coerce')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 92,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "userId                            int64\n",
+      "Reputation                        int64\n",
+      "CreationDate             datetime64[ns]\n",
+      "DisplayName                      object\n",
+      "LastAccessDate                   object\n",
+      "WebsiteUrl                       object\n",
+      "Location                         object\n",
+      "AboutMe                          object\n",
+      "Views                             int64\n",
+      "UpVotes                           int64\n",
+      "DownVotes                         int64\n",
+      "AccountId                         int64\n",
+      "Age                             float64\n",
+      "ProfileImageUrl                  object\n",
+      "postId                            int64\n",
+      "PostTypeId                        int64\n",
+      "AcceptedAnswerId                 object\n",
+      "CreaionDate                      object\n",
+      "Score                             int64\n",
+      "ViewCount                       float64\n",
+      "Body                             object\n",
+      "LasActivityDate                  object\n",
+      "Title                            object\n",
+      "Tags                             object\n",
+      "AnswerCount                     float64\n",
+      "CommentCount                      int64\n",
+      "FavoriteCount                   float64\n",
+      "LastEditorUserId                 object\n",
+      "LastEditDate             datetime64[ns]\n",
+      "CommunityOwnedDate       datetime64[ns]\n",
+      "ParentId                         object\n",
+      "ClosedDate                       object\n",
+      "OwnerDisplayName                 object\n",
+      "LastEditorDisplayName            object\n",
+      "dtype: object\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(merged_df.dtypes)"
    ]
   },
   {
@@ -147,7 +2507,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -161,7 +2521,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.9.13"
   }
  },
  "nbformat": 4,