diff --git a/main.ipynb b/main.ipynb
new file mode 100644
index 0000000..6702a25
--- /dev/null
+++ b/main.ipynb
@@ -0,0 +1,843 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 1. Import pandas library"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 2. Import users table:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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;\\n\\n&lt;p&gt;I'm ...</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;\\n\\n&lt;p&gt;form...</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",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Id  Reputation         CreationDate   DisplayName       LastAccessDate  \\\n",
+       "0  -1           1  2010-07-19 06:55:26     Community  2010-07-19 06:55:26   \n",
+       "1   2         101  2010-07-19 14:01:36  Geoff Dalgas  2013-11-12 22:07:23   \n",
+       "2   3         101  2010-07-19 15:34:50  Jarrod Dixon  2014-08-08 06:42:58   \n",
+       "3   4         101  2010-07-19 19:03:27        Emmett  2014-01-02 09:31:02   \n",
+       "4   5        6792  2010-07-19 19:03:57         Shane  2014-08-13 00:23:47   \n",
+       "\n",
+       "                       WebsiteUrl            Location  \\\n",
+       "0  http://meta.stackexchange.com/  on the server farm   \n",
+       "1        http://stackoverflow.com       Corvallis, OR   \n",
+       "2        http://stackoverflow.com        New York, NY   \n",
+       "3    http://minesweeperonline.com   San Francisco, CA   \n",
+       "4         http://www.statalgo.com        New York, NY   \n",
+       "\n",
+       "                                             AboutMe  Views  UpVotes  \\\n",
+       "0  <p>Hi, I'm not really a person.</p>\\n\\n<p>I'm ...      0     5007   \n",
+       "1  <p>Developer on the StackOverflow team.  Find ...     25        3   \n",
+       "2  <p><a href=\"http://blog.stackoverflow.com/2009...     22       19   \n",
+       "3  <p>currently at a startup in SF</p>\\n\\n<p>form...     11        0   \n",
+       "4  <p>Quantitative researcher focusing on statist...   1145      662   \n",
+       "\n",
+       "   DownVotes  AccountId   Age                     ProfileImageUrl  \n",
+       "0       1920         -1   NaN                                 NaN  \n",
+       "1          0          2  37.0                                 NaN  \n",
+       "2          0          3  35.0                                 NaN  \n",
+       "3          0       1998  28.0  http://i.stack.imgur.com/d1oHX.jpg  \n",
+       "4          5      54503  35.0                                 NaN  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "users= pd.read_csv('users_table.csv')\n",
+    "users.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 3. Rename Id column to userId"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "users.rename(columns={\"Id\": \"userId\"}, inplace= True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 4. Import posts table:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "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>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",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 21 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Id  PostTypeId  AcceptedAnswerId          CreaionDate  Score  ViewCount  \\\n",
+       "0   1           1              15.0  2010-07-19 19:12:12     23     1278.0   \n",
+       "1   2           1              59.0  2010-07-19 19:12:57     22     8198.0   \n",
+       "2   3           1               5.0  2010-07-19 19:13:28     54     3613.0   \n",
+       "3   4           1             135.0  2010-07-19 19:13:31     13     5224.0   \n",
+       "4   5           2               NaN  2010-07-19 19:14:43     81        NaN   \n",
+       "\n",
+       "                                                Body  OwnerUserId  \\\n",
+       "0  <p>How should I elicit prior distributions fro...          8.0   \n",
+       "1  <p>In many different statistical methods there...         24.0   \n",
+       "2  <p>What are some valuable Statistical Analysis...         18.0   \n",
+       "3  <p>I have two groups of data.  Each with a dif...         23.0   \n",
+       "4  <p>The R-project</p>\\n\\n<p><a href=\"http://www...         23.0   \n",
+       "\n",
+       "       LasActivityDate                                              Title  \\\n",
+       "0  2010-09-15 21:08:26                      Eliciting priors from experts   \n",
+       "1  2012-11-12 09:21:54                                 What is normality?   \n",
+       "2  2013-05-27 14:48:36  What are some valuable Statistical Analysis op...   \n",
+       "3  2010-09-08 03:00:19  Assessing the significance of differences in d...   \n",
+       "4  2010-07-19 19:21:15                                                NaN   \n",
+       "\n",
+       "   ... AnswerCount  CommentCount  FavoriteCount  LastEditorUserId  \\\n",
+       "0  ...         5.0             1           14.0               NaN   \n",
+       "1  ...         7.0             1            8.0              88.0   \n",
+       "2  ...        19.0             4           36.0             183.0   \n",
+       "3  ...         5.0             2            2.0               NaN   \n",
+       "4  ...         NaN             3            NaN              23.0   \n",
+       "\n",
+       "          LastEditDate   CommunityOwnedDate ParentId  ClosedDate  \\\n",
+       "0                  NaN                  NaN      NaN         NaN   \n",
+       "1  2010-08-07 17:56:44                  NaN      NaN         NaN   \n",
+       "2  2011-02-12 05:50:03  2010-07-19 19:13:28      NaN         NaN   \n",
+       "3                  NaN                  NaN      NaN         NaN   \n",
+       "4  2010-07-19 19:21:15  2010-07-19 19:14:43      3.0         NaN   \n",
+       "\n",
+       "  OwnerDisplayName LastEditorDisplayName  \n",
+       "0              NaN                   NaN  \n",
+       "1              NaN                   NaN  \n",
+       "2              NaN                   NaN  \n",
+       "3              NaN                   NaN  \n",
+       "4              NaN                   NaN  \n",
+       "\n",
+       "[5 rows x 21 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "posts= pd.read_csv('posts_table.csv')\n",
+    "posts.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 5. Rename Id column to postId and OwnerUserId to userId"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "posts.rename(columns={\"Id\": \"postId\", 'OwnerUserId': 'userId'}, inplace= True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 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": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "users= users[['userId', 'Reputation','Views','UpVotes','DownVotes']]\n",
+    "posts= posts[['postId', 'Score','userId','ViewCount','CommentCount']]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 7. Merge both dataframes, users and posts. \n",
+    "You will need to make a [merge](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.merge.html) of posts and users dataframes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>postId</th>\n",
+       "      <th>Score</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>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>2175</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8576</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8578</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8981</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8982</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   userId  Reputation  Views  UpVotes  DownVotes  postId  Score  ViewCount  \\\n",
+       "0      -1           1      0     5007       1920    2175      0        NaN   \n",
+       "1      -1           1      0     5007       1920    8576      0        NaN   \n",
+       "2      -1           1      0     5007       1920    8578      0        NaN   \n",
+       "3      -1           1      0     5007       1920    8981      0        NaN   \n",
+       "4      -1           1      0     5007       1920    8982      0        NaN   \n",
+       "\n",
+       "   CommentCount  \n",
+       "0             0  \n",
+       "1             0  \n",
+       "2             0  \n",
+       "3             0  \n",
+       "4             0  "
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "merged_df = users.merge(posts, how='inner', on='userId')\n",
+    "merged_df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 8. How many missing values do you have in your merged dataframe? On which columns?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId              0\n",
+       "Reputation          0\n",
+       "Views               0\n",
+       "UpVotes             0\n",
+       "DownVotes           0\n",
+       "postId              0\n",
+       "Score               0\n",
+       "ViewCount       23572\n",
+       "CommentCount        0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "merged_df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "ViewCount has 23572 missing values"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 9. You will need to make something with missing values.  Will you clean or filling them? Explain. \n",
+    "**Remember** to check the results of your code before passing to the next step"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(38962, 9)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "merged_df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "98.0      43\n",
+       "150.0     43\n",
+       "122.0     42\n",
+       "156.0     41\n",
+       "108.0     41\n",
+       "          ..\n",
+       "2153.0     1\n",
+       "4410.0     1\n",
+       "1682.0     1\n",
+       "4045.0     1\n",
+       "2150.0     1\n",
+       "Name: ViewCount, Length: 3402, dtype: int64"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "merged_df['ViewCount'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "merged_df['ViewCount'].fillna(0 , inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Filling missing values with 0 as there are many values present in the dataset."
+   ]
+  },
+  {
+   "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": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 38962 entries, 0 to 38961\n",
+      "Data columns (total 9 columns):\n",
+      " #   Column        Non-Null Count  Dtype  \n",
+      "---  ------        --------------  -----  \n",
+      " 0   userId        38962 non-null  int64  \n",
+      " 1   Reputation    38962 non-null  int64  \n",
+      " 2   Views         38962 non-null  int64  \n",
+      " 3   UpVotes       38962 non-null  int64  \n",
+      " 4   DownVotes     38962 non-null  int64  \n",
+      " 5   postId        38962 non-null  int64  \n",
+      " 6   Score         38962 non-null  int64  \n",
+      " 7   ViewCount     38962 non-null  float64\n",
+      " 8   CommentCount  38962 non-null  int64  \n",
+      "dtypes: float64(1), int64(8)\n",
+      "memory usage: 3.0 MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "merged_df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "merged_df['ViewCount'] = merged_df['ViewCount'].astype(int)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "Int64Index: 38962 entries, 0 to 38961\n",
+      "Data columns (total 9 columns):\n",
+      " #   Column        Non-Null Count  Dtype\n",
+      "---  ------        --------------  -----\n",
+      " 0   userId        38962 non-null  int64\n",
+      " 1   Reputation    38962 non-null  int64\n",
+      " 2   Views         38962 non-null  int64\n",
+      " 3   UpVotes       38962 non-null  int64\n",
+      " 4   DownVotes     38962 non-null  int64\n",
+      " 5   postId        38962 non-null  int64\n",
+      " 6   Score         38962 non-null  int64\n",
+      " 7   ViewCount     38962 non-null  int32\n",
+      " 8   CommentCount  38962 non-null  int64\n",
+      "dtypes: int32(1), int64(8)\n",
+      "memory usage: 2.8 MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "merged_df.info()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/weather.ipynb b/weather.ipynb
new file mode 100644
index 0000000..9bd2905
--- /dev/null
+++ b/weather.ipynb
@@ -0,0 +1,742 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Global Historical Climatology Network Dataset\n",
+    "Variables are stored in both rows and columns\n",
+    "This dataset represents the daily weather records for a weather station (MX17004) in Mexico for five months in 2010."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>year</th>\n",
+       "      <th>month</th>\n",
+       "      <th>element</th>\n",
+       "      <th>d1</th>\n",
+       "      <th>d2</th>\n",
+       "      <th>d3</th>\n",
+       "      <th>d4</th>\n",
+       "      <th>d5</th>\n",
+       "      <th>d6</th>\n",
+       "      <th>...</th>\n",
+       "      <th>d22</th>\n",
+       "      <th>d23</th>\n",
+       "      <th>d24</th>\n",
+       "      <th>d25</th>\n",
+       "      <th>d26</th>\n",
+       "      <th>d27</th>\n",
+       "      <th>d28</th>\n",
+       "      <th>d29</th>\n",
+       "      <th>d30</th>\n",
+       "      <th>d31</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmax</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>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.8</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmin</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>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.5</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.3</td>\n",
+       "      <td>24.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>29.9</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",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.4</td>\n",
+       "      <td>14.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10.7</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",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>3</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>32.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 35 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        id  year  month element  d1    d2    d3  d4    d5  d6  ...  d22   d23  \\\n",
+       "0  MX17004  2010      1    tmax NaN   NaN   NaN NaN   NaN NaN  ...  NaN   NaN   \n",
+       "1  MX17004  2010      1    tmin NaN   NaN   NaN NaN   NaN NaN  ...  NaN   NaN   \n",
+       "2  MX17004  2010      2    tmax NaN  27.3  24.1 NaN   NaN NaN  ...  NaN  29.9   \n",
+       "3  MX17004  2010      2    tmin NaN  14.4  14.4 NaN   NaN NaN  ...  NaN  10.7   \n",
+       "4  MX17004  2010      3    tmax NaN   NaN   NaN NaN  32.1 NaN  ...  NaN   NaN   \n",
+       "\n",
+       "   d24  d25  d26  d27  d28  d29   d30  d31  \n",
+       "0  NaN  NaN  NaN  NaN  NaN  NaN  27.8  NaN  \n",
+       "1  NaN  NaN  NaN  NaN  NaN  NaN  14.5  NaN  \n",
+       "2  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "3  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "4  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "\n",
+       "[5 rows x 35 columns]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mx_df= pd.read_csv('weather-raw.csv')\n",
+    "mx_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 22 entries, 0 to 21\n",
+      "Data columns (total 35 columns):\n",
+      " #   Column   Non-Null Count  Dtype  \n",
+      "---  ------   --------------  -----  \n",
+      " 0   id       22 non-null     object \n",
+      " 1   year     22 non-null     int64  \n",
+      " 2   month    22 non-null     int64  \n",
+      " 3   element  22 non-null     object \n",
+      " 4   d1       2 non-null      float64\n",
+      " 5   d2       4 non-null      float64\n",
+      " 6   d3       4 non-null      float64\n",
+      " 7   d4       2 non-null      float64\n",
+      " 8   d5       8 non-null      float64\n",
+      " 9   d6       2 non-null      float64\n",
+      " 10  d7       2 non-null      float64\n",
+      " 11  d8       2 non-null      float64\n",
+      " 12  d9       0 non-null      float64\n",
+      " 13  d10      2 non-null      float64\n",
+      " 14  d11      2 non-null      float64\n",
+      " 15  d12      0 non-null      float64\n",
+      " 16  d13      2 non-null      float64\n",
+      " 17  d14      4 non-null      float64\n",
+      " 18  d15      2 non-null      float64\n",
+      " 19  d16      2 non-null      float64\n",
+      " 20  d17      2 non-null      float64\n",
+      " 21  d18      0 non-null      float64\n",
+      " 22  d19      0 non-null      float64\n",
+      " 23  d20      0 non-null      float64\n",
+      " 24  d21      0 non-null      float64\n",
+      " 25  d22      0 non-null      float64\n",
+      " 26  d23      4 non-null      float64\n",
+      " 27  d24      0 non-null      float64\n",
+      " 28  d25      2 non-null      float64\n",
+      " 29  d26      2 non-null      float64\n",
+      " 30  d27      6 non-null      float64\n",
+      " 31  d28      2 non-null      float64\n",
+      " 32  d29      4 non-null      float64\n",
+      " 33  d30      2 non-null      float64\n",
+      " 34  d31      2 non-null      float64\n",
+      "dtypes: float64(31), int64(2), object(2)\n",
+      "memory usage: 6.1+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "mx_df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(22, 35)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mx_df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "id          0\n",
+       "year        0\n",
+       "month       0\n",
+       "element     0\n",
+       "d1         20\n",
+       "d2         18\n",
+       "d3         18\n",
+       "d4         20\n",
+       "d5         14\n",
+       "d6         20\n",
+       "d7         20\n",
+       "d8         20\n",
+       "d10        20\n",
+       "d11        20\n",
+       "d13        20\n",
+       "d14        18\n",
+       "d15        20\n",
+       "d16        20\n",
+       "d17        20\n",
+       "d23        18\n",
+       "d24        22\n",
+       "d25        20\n",
+       "d26        20\n",
+       "d27        16\n",
+       "d28        20\n",
+       "d29        18\n",
+       "d30        20\n",
+       "d31        20\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mx_df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mx_df.drop(['d9','d12','d18','d19','d20','d21','d22'], axis= 1, inplace= True)\n",
+    "#Dropping this columns as all values in the column are null."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#using melt method to convert columns into row \n",
+    "mx_df = mx_df.melt(['id','year', 'month','element'],['d1', 'd2','d3','d4','d5','d6','d7','d8','d10','d11','d13','d14','d15','d16','d17','d23','d24','d25','d26','d27','d28','d29','d30','d31'], 'prev cols') "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "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>year</th>\n",
+       "      <th>month</th>\n",
+       "      <th>element</th>\n",
+       "      <th>prev cols</th>\n",
+       "      <th>value</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d1</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d1</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d1</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d1</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>3</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d1</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>523</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>10</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>524</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>11</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>525</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>11</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>526</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>12</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>527</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>12</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>528 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          id  year  month element prev cols  value\n",
+       "0    MX17004  2010      1    tmax        d1    NaN\n",
+       "1    MX17004  2010      1    tmin        d1    NaN\n",
+       "2    MX17004  2010      2    tmax        d1    NaN\n",
+       "3    MX17004  2010      2    tmin        d1    NaN\n",
+       "4    MX17004  2010      3    tmax        d1    NaN\n",
+       "..       ...   ...    ...     ...       ...    ...\n",
+       "523  MX17004  2010     10    tmin       d31    NaN\n",
+       "524  MX17004  2010     11    tmax       d31    NaN\n",
+       "525  MX17004  2010     11    tmin       d31    NaN\n",
+       "526  MX17004  2010     12    tmax       d31    NaN\n",
+       "527  MX17004  2010     12    tmin       d31    NaN\n",
+       "\n",
+       "[528 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mx_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mx_df['value'].fillna(np.nan, inplace= True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "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>year</th>\n",
+       "      <th>month</th>\n",
+       "      <th>element</th>\n",
+       "      <th>prev cols</th>\n",
+       "      <th>value</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>12</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d1</td>\n",
+       "      <td>29.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>12</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d1</td>\n",
+       "      <td>13.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d2</td>\n",
+       "      <td>27.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d2</td>\n",
+       "      <td>14.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>11</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d2</td>\n",
+       "      <td>31.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>477</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>8</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d29</td>\n",
+       "      <td>15.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>484</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d30</td>\n",
+       "      <td>27.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>485</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d30</td>\n",
+       "      <td>14.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>520</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>8</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>25.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>521</th>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>8</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>d31</td>\n",
+       "      <td>15.4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>66 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          id  year  month element prev cols  value\n",
+       "20   MX17004  2010     12    tmax        d1   29.9\n",
+       "21   MX17004  2010     12    tmin        d1   13.8\n",
+       "24   MX17004  2010      2    tmax        d2   27.3\n",
+       "25   MX17004  2010      2    tmin        d2   14.4\n",
+       "40   MX17004  2010     11    tmax        d2   31.3\n",
+       "..       ...   ...    ...     ...       ...    ...\n",
+       "477  MX17004  2010      8    tmin       d29   15.3\n",
+       "484  MX17004  2010      1    tmax       d30   27.8\n",
+       "485  MX17004  2010      1    tmin       d30   14.5\n",
+       "520  MX17004  2010      8    tmax       d31   25.4\n",
+       "521  MX17004  2010      8    tmin       d31   15.4\n",
+       "\n",
+       "[66 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Dropping rows where value column has NAN\n",
+    "mx_df.dropna(subset=['value'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mx_df.to_csv('')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/your-code/data_cleaning.ipynb b/your-code/data_cleaning.ipynb
new file mode 100644
index 0000000..3cc6d26
--- /dev/null
+++ b/your-code/data_cleaning.ipynb
@@ -0,0 +1,3351 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr th {\n",
+       "        text-align: left;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>Rank</th>\n",
+       "      <th>Country ordependent territory</th>\n",
+       "      <th colspan=\"2\" halign=\"left\">Area</th>\n",
+       "      <th>Population</th>\n",
+       "      <th colspan=\"2\" halign=\"left\">Density</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>Rank</th>\n",
+       "      <th>Country ordependent territory</th>\n",
+       "      <th>km2</th>\n",
+       "      <th>sq. mi.</th>\n",
+       "      <th>Population</th>\n",
+       "      <th>per km2</th>\n",
+       "      <th>per sq.mi.</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Macau (China)</td>\n",
+       "      <td>30.50</td>\n",
+       "      <td>12.00</td>\n",
+       "      <td>650834</td>\n",
+       "      <td>21339</td>\n",
+       "      <td>55268</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Monaco</td>\n",
+       "      <td>2.02</td>\n",
+       "      <td>0.78</td>\n",
+       "      <td>37550</td>\n",
+       "      <td>18589</td>\n",
+       "      <td>48145</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Singapore</td>\n",
+       "      <td>719.90</td>\n",
+       "      <td>278.00</td>\n",
+       "      <td>5612300</td>\n",
+       "      <td>7796</td>\n",
+       "      <td>20192</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Hong Kong (China)</td>\n",
+       "      <td>1106.30</td>\n",
+       "      <td>427.00</td>\n",
+       "      <td>7409800</td>\n",
+       "      <td>6698</td>\n",
+       "      <td>17348</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Gibraltar (UK)[12]</td>\n",
+       "      <td>6.80</td>\n",
+       "      <td>2.60</td>\n",
+       "      <td>33140</td>\n",
+       "      <td>4874</td>\n",
+       "      <td>12624</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>6</td>\n",
+       "      <td>Bahrain</td>\n",
+       "      <td>757.00</td>\n",
+       "      <td>292.00</td>\n",
+       "      <td>1451200</td>\n",
+       "      <td>1917</td>\n",
+       "      <td>4965</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Vatican City</td>\n",
+       "      <td>0.44</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>800</td>\n",
+       "      <td>1818</td>\n",
+       "      <td>4709</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Malta</td>\n",
+       "      <td>315.00</td>\n",
+       "      <td>122.00</td>\n",
+       "      <td>475701</td>\n",
+       "      <td>1510</td>\n",
+       "      <td>3911</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>9</td>\n",
+       "      <td>Maldives</td>\n",
+       "      <td>298.00</td>\n",
+       "      <td>115.00</td>\n",
+       "      <td>378114</td>\n",
+       "      <td>1269</td>\n",
+       "      <td>3287</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Bermuda (UK)</td>\n",
+       "      <td>52.00</td>\n",
+       "      <td>20.00</td>\n",
+       "      <td>63779</td>\n",
+       "      <td>1227</td>\n",
+       "      <td>3178</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  Rank Country ordependent territory     Area         Population Density  \\\n",
+       "  Rank Country ordependent territory      km2 sq. mi. Population per km2   \n",
+       "0    1                 Macau (China)    30.50   12.00     650834   21339   \n",
+       "1    2                        Monaco     2.02    0.78      37550   18589   \n",
+       "2    3                     Singapore   719.90  278.00    5612300    7796   \n",
+       "3    4             Hong Kong (China)  1106.30  427.00    7409800    6698   \n",
+       "4    5            Gibraltar (UK)[12]     6.80    2.60      33140    4874   \n",
+       "5    6                       Bahrain   757.00  292.00    1451200    1917   \n",
+       "6    7                  Vatican City     0.44    0.17        800    1818   \n",
+       "7    8                         Malta   315.00  122.00     475701    1510   \n",
+       "8    9                      Maldives   298.00  115.00     378114    1269   \n",
+       "9   10                  Bermuda (UK)    52.00   20.00      63779    1227   \n",
+       "\n",
+       "              \n",
+       "  per sq.mi.  \n",
+       "0      55268  \n",
+       "1      48145  \n",
+       "2      20192  \n",
+       "3      17348  \n",
+       "4      12624  \n",
+       "5       4965  \n",
+       "6       4709  \n",
+       "7       3911  \n",
+       "8       3287  \n",
+       "9       3178  "
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x = pd.read_html('https://en.wikipedia.org/wiki/Population_density')[0]\n",
+    "x\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Rank', 'Country ordependent territory', 'km2', 'sq. mi.', 'Population',\n",
+       "       'per km2', 'per sq.mi.'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x.columns.droplevel()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr th {\n",
+       "        text-align: left;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>Rank</th>\n",
+       "      <th>Country ordependent territory</th>\n",
+       "      <th colspan=\"2\" halign=\"left\">Area</th>\n",
+       "      <th>Population</th>\n",
+       "      <th colspan=\"2\" halign=\"left\">Density</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>Rank</th>\n",
+       "      <th>Country ordependent territory</th>\n",
+       "      <th>km2</th>\n",
+       "      <th>sq. mi.</th>\n",
+       "      <th>Population</th>\n",
+       "      <th>per km2</th>\n",
+       "      <th>per sq.mi.</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Macau (China)</td>\n",
+       "      <td>30.50</td>\n",
+       "      <td>12.00</td>\n",
+       "      <td>650834</td>\n",
+       "      <td>21339</td>\n",
+       "      <td>55268</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Monaco</td>\n",
+       "      <td>2.02</td>\n",
+       "      <td>0.78</td>\n",
+       "      <td>37550</td>\n",
+       "      <td>18589</td>\n",
+       "      <td>48145</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Singapore</td>\n",
+       "      <td>719.90</td>\n",
+       "      <td>278.00</td>\n",
+       "      <td>5612300</td>\n",
+       "      <td>7796</td>\n",
+       "      <td>20192</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Hong Kong (China)</td>\n",
+       "      <td>1106.30</td>\n",
+       "      <td>427.00</td>\n",
+       "      <td>7409800</td>\n",
+       "      <td>6698</td>\n",
+       "      <td>17348</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Gibraltar (UK)[12]</td>\n",
+       "      <td>6.80</td>\n",
+       "      <td>2.60</td>\n",
+       "      <td>33140</td>\n",
+       "      <td>4874</td>\n",
+       "      <td>12624</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>6</td>\n",
+       "      <td>Bahrain</td>\n",
+       "      <td>757.00</td>\n",
+       "      <td>292.00</td>\n",
+       "      <td>1451200</td>\n",
+       "      <td>1917</td>\n",
+       "      <td>4965</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Vatican City</td>\n",
+       "      <td>0.44</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>800</td>\n",
+       "      <td>1818</td>\n",
+       "      <td>4709</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Malta</td>\n",
+       "      <td>315.00</td>\n",
+       "      <td>122.00</td>\n",
+       "      <td>475701</td>\n",
+       "      <td>1510</td>\n",
+       "      <td>3911</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>9</td>\n",
+       "      <td>Maldives</td>\n",
+       "      <td>298.00</td>\n",
+       "      <td>115.00</td>\n",
+       "      <td>378114</td>\n",
+       "      <td>1269</td>\n",
+       "      <td>3287</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Bermuda (UK)</td>\n",
+       "      <td>52.00</td>\n",
+       "      <td>20.00</td>\n",
+       "      <td>63779</td>\n",
+       "      <td>1227</td>\n",
+       "      <td>3178</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  Rank Country ordependent territory     Area         Population Density  \\\n",
+       "  Rank Country ordependent territory      km2 sq. mi. Population per km2   \n",
+       "0    1                 Macau (China)    30.50   12.00     650834   21339   \n",
+       "1    2                        Monaco     2.02    0.78      37550   18589   \n",
+       "2    3                     Singapore   719.90  278.00    5612300    7796   \n",
+       "3    4             Hong Kong (China)  1106.30  427.00    7409800    6698   \n",
+       "4    5            Gibraltar (UK)[12]     6.80    2.60      33140    4874   \n",
+       "5    6                       Bahrain   757.00  292.00    1451200    1917   \n",
+       "6    7                  Vatican City     0.44    0.17        800    1818   \n",
+       "7    8                         Malta   315.00  122.00     475701    1510   \n",
+       "8    9                      Maldives   298.00  115.00     378114    1269   \n",
+       "9   10                  Bermuda (UK)    52.00   20.00      63779    1227   \n",
+       "\n",
+       "              \n",
+       "  per sq.mi.  \n",
+       "0      55268  \n",
+       "1      48145  \n",
+       "2      20192  \n",
+       "3      17348  \n",
+       "4      12624  \n",
+       "5       4965  \n",
+       "6       4709  \n",
+       "7       3911  \n",
+       "8       3287  \n",
+       "9       3178  "
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "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>Make</th>\n",
+       "      <th>Model</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Engine Displacement</th>\n",
+       "      <th>Cylinders</th>\n",
+       "      <th>Transmission</th>\n",
+       "      <th>Drivetrain</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Fuel Type</th>\n",
+       "      <th>Fuel Barrels/Year</th>\n",
+       "      <th>City MPG</th>\n",
+       "      <th>Highway MPG</th>\n",
+       "      <th>Combined MPG</th>\n",
+       "      <th>CO2 Emission Grams/Mile</th>\n",
+       "      <th>Fuel Cost/Year</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>DJ Po Vehicle 2WD</td>\n",
+       "      <td>1984</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>2-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>19.388824</td>\n",
+       "      <td>18</td>\n",
+       "      <td>17</td>\n",
+       "      <td>17</td>\n",
+       "      <td>522.764706</td>\n",
+       "      <td>1950</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>FJ8c Post Office</td>\n",
+       "      <td>1984</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>2-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>25.354615</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>683.615385</td>\n",
+       "      <td>2550</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>Post Office DJ5 2WD</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>16</td>\n",
+       "      <td>17</td>\n",
+       "      <td>16</td>\n",
+       "      <td>555.437500</td>\n",
+       "      <td>2100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>Post Office DJ8 2WD</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>25.354615</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>683.615385</td>\n",
+       "      <td>2550</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ASC Incorporated</td>\n",
+       "      <td>GNX</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>3.8</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>Automatic 4-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Midsize Cars</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>14</td>\n",
+       "      <td>21</td>\n",
+       "      <td>16</td>\n",
+       "      <td>555.437500</td>\n",
+       "      <td>2550</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35947</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2013</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>244.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35948</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>243.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35949</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2015</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>244.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35950</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM6)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>39</td>\n",
+       "      <td>36</td>\n",
+       "      <td>246.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35951</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Manual 5-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.417429</td>\n",
+       "      <td>32</td>\n",
+       "      <td>39</td>\n",
+       "      <td>35</td>\n",
+       "      <td>255.000000</td>\n",
+       "      <td>1150</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>35952 rows × 15 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   Make                Model  Year  Engine Displacement  \\\n",
+       "0            AM General    DJ Po Vehicle 2WD  1984                  2.5   \n",
+       "1            AM General     FJ8c Post Office  1984                  4.2   \n",
+       "2            AM General  Post Office DJ5 2WD  1985                  2.5   \n",
+       "3            AM General  Post Office DJ8 2WD  1985                  4.2   \n",
+       "4      ASC Incorporated                  GNX  1987                  3.8   \n",
+       "...                 ...                  ...   ...                  ...   \n",
+       "35947             smart         fortwo coupe  2013                  1.0   \n",
+       "35948             smart         fortwo coupe  2014                  1.0   \n",
+       "35949             smart         fortwo coupe  2015                  1.0   \n",
+       "35950             smart         fortwo coupe  2016                  0.9   \n",
+       "35951             smart         fortwo coupe  2016                  0.9   \n",
+       "\n",
+       "       Cylinders     Transmission        Drivetrain  \\\n",
+       "0            4.0  Automatic 3-spd     2-Wheel Drive   \n",
+       "1            6.0  Automatic 3-spd     2-Wheel Drive   \n",
+       "2            4.0  Automatic 3-spd  Rear-Wheel Drive   \n",
+       "3            6.0  Automatic 3-spd  Rear-Wheel Drive   \n",
+       "4            6.0  Automatic 4-spd  Rear-Wheel Drive   \n",
+       "...          ...              ...               ...   \n",
+       "35947        3.0        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35948        3.0        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35949        3.0        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35950        3.0        Auto(AM6)  Rear-Wheel Drive   \n",
+       "35951        3.0     Manual 5-spd  Rear-Wheel Drive   \n",
+       "\n",
+       "                     Vehicle Class Fuel Type  Fuel Barrels/Year  City MPG  \\\n",
+       "0      Special Purpose Vehicle 2WD   Regular          19.388824        18   \n",
+       "1      Special Purpose Vehicle 2WD   Regular          25.354615        13   \n",
+       "2      Special Purpose Vehicle 2WD   Regular          20.600625        16   \n",
+       "3      Special Purpose Vehicle 2WD   Regular          25.354615        13   \n",
+       "4                     Midsize Cars   Premium          20.600625        14   \n",
+       "...                            ...       ...                ...       ...   \n",
+       "35947                  Two Seaters   Premium           9.155833        34   \n",
+       "35948                  Two Seaters   Premium           9.155833        34   \n",
+       "35949                  Two Seaters   Premium           9.155833        34   \n",
+       "35950                  Two Seaters   Premium           9.155833        34   \n",
+       "35951                  Two Seaters   Premium           9.417429        32   \n",
+       "\n",
+       "       Highway MPG  Combined MPG  CO2 Emission Grams/Mile  Fuel Cost/Year  \n",
+       "0               17            17               522.764706            1950  \n",
+       "1               13            13               683.615385            2550  \n",
+       "2               17            16               555.437500            2100  \n",
+       "3               13            13               683.615385            2550  \n",
+       "4               21            16               555.437500            2550  \n",
+       "...            ...           ...                      ...             ...  \n",
+       "35947           38            36               244.000000            1100  \n",
+       "35948           38            36               243.000000            1100  \n",
+       "35949           38            36               244.000000            1100  \n",
+       "35950           39            36               246.000000            1100  \n",
+       "35951           39            35               255.000000            1150  \n",
+       "\n",
+       "[35952 rows x 15 columns]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('data_set/vehicles/vehicles_tab.txt', sep='\\t')\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "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>Make</th>\n",
+       "      <th>Model</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Engine Displacement</th>\n",
+       "      <th>Cylinders</th>\n",
+       "      <th>Transmission</th>\n",
+       "      <th>Drivetrain</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Fuel Type</th>\n",
+       "      <th>Fuel Barrels/Year</th>\n",
+       "      <th>City MPG</th>\n",
+       "      <th>Highway MPG</th>\n",
+       "      <th>Combined MPG</th>\n",
+       "      <th>CO2 Emission Grams/Mile</th>\n",
+       "      <th>Fuel Cost/Year</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>DJ Po Vehicle 2WD</td>\n",
+       "      <td>1984</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>2-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>19.388824</td>\n",
+       "      <td>18</td>\n",
+       "      <td>17</td>\n",
+       "      <td>17</td>\n",
+       "      <td>522.764706</td>\n",
+       "      <td>1950</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>FJ8c Post Office</td>\n",
+       "      <td>1984</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>2-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>25.354615</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>683.615385</td>\n",
+       "      <td>2550</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>Post Office DJ5 2WD</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>16</td>\n",
+       "      <td>17</td>\n",
+       "      <td>16</td>\n",
+       "      <td>555.437500</td>\n",
+       "      <td>2100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>Post Office DJ8 2WD</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>25.354615</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>683.615385</td>\n",
+       "      <td>2550</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ASC Incorporated</td>\n",
+       "      <td>GNX</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>3.8</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>Automatic 4-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Midsize Cars</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>14</td>\n",
+       "      <td>21</td>\n",
+       "      <td>16</td>\n",
+       "      <td>555.437500</td>\n",
+       "      <td>2550</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35947</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2013</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>244.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35948</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>243.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35949</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2015</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>244.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35950</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Auto(AM6)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>39</td>\n",
+       "      <td>36</td>\n",
+       "      <td>246.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35951</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>Manual 5-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.417429</td>\n",
+       "      <td>32</td>\n",
+       "      <td>39</td>\n",
+       "      <td>35</td>\n",
+       "      <td>255.000000</td>\n",
+       "      <td>1150</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>35952 rows × 15 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   Make                Model  Year  Engine Displacement  \\\n",
+       "0            AM General    DJ Po Vehicle 2WD  1984                  2.5   \n",
+       "1            AM General     FJ8c Post Office  1984                  4.2   \n",
+       "2            AM General  Post Office DJ5 2WD  1985                  2.5   \n",
+       "3            AM General  Post Office DJ8 2WD  1985                  4.2   \n",
+       "4      ASC Incorporated                  GNX  1987                  3.8   \n",
+       "...                 ...                  ...   ...                  ...   \n",
+       "35947             smart         fortwo coupe  2013                  1.0   \n",
+       "35948             smart         fortwo coupe  2014                  1.0   \n",
+       "35949             smart         fortwo coupe  2015                  1.0   \n",
+       "35950             smart         fortwo coupe  2016                  0.9   \n",
+       "35951             smart         fortwo coupe  2016                  0.9   \n",
+       "\n",
+       "       Cylinders     Transmission        Drivetrain  \\\n",
+       "0            4.0  Automatic 3-spd     2-Wheel Drive   \n",
+       "1            6.0  Automatic 3-spd     2-Wheel Drive   \n",
+       "2            4.0  Automatic 3-spd  Rear-Wheel Drive   \n",
+       "3            6.0  Automatic 3-spd  Rear-Wheel Drive   \n",
+       "4            6.0  Automatic 4-spd  Rear-Wheel Drive   \n",
+       "...          ...              ...               ...   \n",
+       "35947        3.0        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35948        3.0        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35949        3.0        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35950        3.0        Auto(AM6)  Rear-Wheel Drive   \n",
+       "35951        3.0     Manual 5-spd  Rear-Wheel Drive   \n",
+       "\n",
+       "                     Vehicle Class Fuel Type  Fuel Barrels/Year  City MPG  \\\n",
+       "0      Special Purpose Vehicle 2WD   Regular          19.388824        18   \n",
+       "1      Special Purpose Vehicle 2WD   Regular          25.354615        13   \n",
+       "2      Special Purpose Vehicle 2WD   Regular          20.600625        16   \n",
+       "3      Special Purpose Vehicle 2WD   Regular          25.354615        13   \n",
+       "4                     Midsize Cars   Premium          20.600625        14   \n",
+       "...                            ...       ...                ...       ...   \n",
+       "35947                  Two Seaters   Premium           9.155833        34   \n",
+       "35948                  Two Seaters   Premium           9.155833        34   \n",
+       "35949                  Two Seaters   Premium           9.155833        34   \n",
+       "35950                  Two Seaters   Premium           9.155833        34   \n",
+       "35951                  Two Seaters   Premium           9.417429        32   \n",
+       "\n",
+       "       Highway MPG  Combined MPG  CO2 Emission Grams/Mile  Fuel Cost/Year  \n",
+       "0               17            17               522.764706            1950  \n",
+       "1               13            13               683.615385            2550  \n",
+       "2               17            16               555.437500            2100  \n",
+       "3               13            13               683.615385            2550  \n",
+       "4               21            16               555.437500            2550  \n",
+       "...            ...           ...                      ...             ...  \n",
+       "35947           38            36               244.000000            1100  \n",
+       "35948           38            36               243.000000            1100  \n",
+       "35949           38            36               244.000000            1100  \n",
+       "35950           39            36               246.000000            1100  \n",
+       "35951           39            35               255.000000            1150  \n",
+       "\n",
+       "[35952 rows x 15 columns]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('data_set/vehicles/vehicles_pipe.txt', sep='|')\n",
+    "data "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Make</th>\n",
+       "      <th>Model</th>\n",
+       "      <th>Year</th>\n",
+       "      <th>Engine Displacement</th>\n",
+       "      <th>Cylinders</th>\n",
+       "      <th>Transmission</th>\n",
+       "      <th>Drivetrain</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Fuel Type</th>\n",
+       "      <th>Fuel Barrels/Year</th>\n",
+       "      <th>City MPG</th>\n",
+       "      <th>Highway MPG</th>\n",
+       "      <th>Combined MPG</th>\n",
+       "      <th>CO2 Emission Grams/Mile</th>\n",
+       "      <th>Fuel Cost/Year</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>DJ Po Vehicle 2WD</td>\n",
+       "      <td>1984</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>2-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>19.388824</td>\n",
+       "      <td>18</td>\n",
+       "      <td>17</td>\n",
+       "      <td>17</td>\n",
+       "      <td>522.764706</td>\n",
+       "      <td>1950</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>FJ8c Post Office</td>\n",
+       "      <td>1984</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>2-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>25.354615</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>683.615385</td>\n",
+       "      <td>2550</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>Post Office DJ5 2WD</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>16</td>\n",
+       "      <td>17</td>\n",
+       "      <td>16</td>\n",
+       "      <td>555.437500</td>\n",
+       "      <td>2100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>AM General</td>\n",
+       "      <td>Post Office DJ8 2WD</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Special Purpose Vehicle 2WD</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>25.354615</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>13</td>\n",
+       "      <td>683.615385</td>\n",
+       "      <td>2550</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ASC Incorporated</td>\n",
+       "      <td>GNX</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>3.8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Automatic 4-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Midsize Cars</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>14</td>\n",
+       "      <td>21</td>\n",
+       "      <td>16</td>\n",
+       "      <td>555.437500</td>\n",
+       "      <td>2550</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35947</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2013</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>244.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35948</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>243.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35949</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2015</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Auto(AM5)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>38</td>\n",
+       "      <td>36</td>\n",
+       "      <td>244.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35950</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Auto(AM6)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.155833</td>\n",
+       "      <td>34</td>\n",
+       "      <td>39</td>\n",
+       "      <td>36</td>\n",
+       "      <td>246.000000</td>\n",
+       "      <td>1100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35951</th>\n",
+       "      <td>smart</td>\n",
+       "      <td>fortwo coupe</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>0.9</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Manual 5-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>9.417429</td>\n",
+       "      <td>32</td>\n",
+       "      <td>39</td>\n",
+       "      <td>35</td>\n",
+       "      <td>255.000000</td>\n",
+       "      <td>1150</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>35952 rows × 15 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   Make                Model  Year  Engine Displacement  \\\n",
+       "0            AM General    DJ Po Vehicle 2WD  1984                  2.5   \n",
+       "1            AM General     FJ8c Post Office  1984                  4.2   \n",
+       "2            AM General  Post Office DJ5 2WD  1985                  2.5   \n",
+       "3            AM General  Post Office DJ8 2WD  1985                  4.2   \n",
+       "4      ASC Incorporated                  GNX  1987                  3.8   \n",
+       "...                 ...                  ...   ...                  ...   \n",
+       "35947             smart         fortwo coupe  2013                  1.0   \n",
+       "35948             smart         fortwo coupe  2014                  1.0   \n",
+       "35949             smart         fortwo coupe  2015                  1.0   \n",
+       "35950             smart         fortwo coupe  2016                  0.9   \n",
+       "35951             smart         fortwo coupe  2016                  0.9   \n",
+       "\n",
+       "       Cylinders     Transmission        Drivetrain  \\\n",
+       "0              4  Automatic 3-spd     2-Wheel Drive   \n",
+       "1              6  Automatic 3-spd     2-Wheel Drive   \n",
+       "2              4  Automatic 3-spd  Rear-Wheel Drive   \n",
+       "3              6  Automatic 3-spd  Rear-Wheel Drive   \n",
+       "4              6  Automatic 4-spd  Rear-Wheel Drive   \n",
+       "...          ...              ...               ...   \n",
+       "35947          3        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35948          3        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35949          3        Auto(AM5)  Rear-Wheel Drive   \n",
+       "35950          3        Auto(AM6)  Rear-Wheel Drive   \n",
+       "35951          3     Manual 5-spd  Rear-Wheel Drive   \n",
+       "\n",
+       "                     Vehicle Class Fuel Type  Fuel Barrels/Year  City MPG  \\\n",
+       "0      Special Purpose Vehicle 2WD   Regular          19.388824        18   \n",
+       "1      Special Purpose Vehicle 2WD   Regular          25.354615        13   \n",
+       "2      Special Purpose Vehicle 2WD   Regular          20.600625        16   \n",
+       "3      Special Purpose Vehicle 2WD   Regular          25.354615        13   \n",
+       "4                     Midsize Cars   Premium          20.600625        14   \n",
+       "...                            ...       ...                ...       ...   \n",
+       "35947                  Two Seaters   Premium           9.155833        34   \n",
+       "35948                  Two Seaters   Premium           9.155833        34   \n",
+       "35949                  Two Seaters   Premium           9.155833        34   \n",
+       "35950                  Two Seaters   Premium           9.155833        34   \n",
+       "35951                  Two Seaters   Premium           9.417429        32   \n",
+       "\n",
+       "       Highway MPG  Combined MPG  CO2 Emission Grams/Mile  Fuel Cost/Year  \n",
+       "0               17            17               522.764706            1950  \n",
+       "1               13            13               683.615385            2550  \n",
+       "2               17            16               555.437500            2100  \n",
+       "3               13            13               683.615385            2550  \n",
+       "4               21            16               555.437500            2550  \n",
+       "...            ...           ...                      ...             ...  \n",
+       "35947           38            36               244.000000            1100  \n",
+       "35948           38            36               243.000000            1100  \n",
+       "35949           38            36               244.000000            1100  \n",
+       "35950           39            36               246.000000            1100  \n",
+       "35951           39            35               255.000000            1150  \n",
+       "\n",
+       "[35952 rows x 15 columns]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_json('/Users/chuksfolder/Desktop/data_cleaning/data_set/vehicles/vehicles.json')\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/chuksfolder/opt/anaconda3/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3444: DtypeWarning: Columns (70,71,72,73,74,76,79) have mixed types.Specify dtype option on import or set low_memory=False.\n",
+      "  exec(code_obj, self.user_global_ns, self.user_ns)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>barrels08</th>\n",
+       "      <th>barrelsA08</th>\n",
+       "      <th>charge120</th>\n",
+       "      <th>charge240</th>\n",
+       "      <th>city08</th>\n",
+       "      <th>city08U</th>\n",
+       "      <th>cityA08</th>\n",
+       "      <th>cityA08U</th>\n",
+       "      <th>cityCD</th>\n",
+       "      <th>cityE</th>\n",
+       "      <th>...</th>\n",
+       "      <th>mfrCode</th>\n",
+       "      <th>c240Dscr</th>\n",
+       "      <th>charge240b</th>\n",
+       "      <th>c240bDscr</th>\n",
+       "      <th>createdOn</th>\n",
+       "      <th>modifiedOn</th>\n",
+       "      <th>startStop</th>\n",
+       "      <th>phevCity</th>\n",
+       "      <th>phevHwy</th>\n",
+       "      <th>phevComb</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>15.695714</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>29.964545</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>12.207778</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>3 rows × 83 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   barrels08  barrelsA08  charge120  charge240  city08  city08U  cityA08  \\\n",
+       "0  15.695714         0.0        0.0        0.0      19      0.0        0   \n",
+       "1  29.964545         0.0        0.0        0.0       9      0.0        0   \n",
+       "2  12.207778         0.0        0.0        0.0      23      0.0        0   \n",
+       "\n",
+       "   cityA08U  cityCD  cityE  ...  mfrCode  c240Dscr  charge240b  c240bDscr  \\\n",
+       "0       0.0     0.0    0.0  ...      NaN       NaN         0.0        NaN   \n",
+       "1       0.0     0.0    0.0  ...      NaN       NaN         0.0        NaN   \n",
+       "2       0.0     0.0    0.0  ...      NaN       NaN         0.0        NaN   \n",
+       "\n",
+       "                      createdOn                    modifiedOn  startStop  \\\n",
+       "0  Tue Jan 01 00:00:00 EST 2013  Tue Jan 01 00:00:00 EST 2013        NaN   \n",
+       "1  Tue Jan 01 00:00:00 EST 2013  Tue Jan 01 00:00:00 EST 2013        NaN   \n",
+       "2  Tue Jan 01 00:00:00 EST 2013  Tue Jan 01 00:00:00 EST 2013        NaN   \n",
+       "\n",
+       "   phevCity  phevHwy  phevComb  \n",
+       "0         0        0         0  \n",
+       "1         0        0         0  \n",
+       "2         0        0         0  \n",
+       "\n",
+       "[3 rows x 83 columns]"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds = pd.read_csv('data_set/vehicles/vehicles_messy.csv')\n",
+    "ds.head(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(37843, 83)"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "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>barrels08</th>\n",
+       "      <th>barrelsA08</th>\n",
+       "      <th>charge120</th>\n",
+       "      <th>charge240</th>\n",
+       "      <th>city08</th>\n",
+       "      <th>city08U</th>\n",
+       "      <th>cityA08</th>\n",
+       "      <th>cityA08U</th>\n",
+       "      <th>cityCD</th>\n",
+       "      <th>cityE</th>\n",
+       "      <th>...</th>\n",
+       "      <th>UCity</th>\n",
+       "      <th>UCityA</th>\n",
+       "      <th>UHighway</th>\n",
+       "      <th>UHighwayA</th>\n",
+       "      <th>year</th>\n",
+       "      <th>youSaveSpend</th>\n",
+       "      <th>charge240b</th>\n",
+       "      <th>phevCity</th>\n",
+       "      <th>phevHwy</th>\n",
+       "      <th>phevComb</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.0</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "      <td>37843.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>17.532506</td>\n",
+       "      <td>0.216169</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.023531</td>\n",
+       "      <td>17.941389</td>\n",
+       "      <td>4.042737</td>\n",
+       "      <td>0.520149</td>\n",
+       "      <td>0.327163</td>\n",
+       "      <td>0.000406</td>\n",
+       "      <td>0.184790</td>\n",
+       "      <td>...</td>\n",
+       "      <td>22.587229</td>\n",
+       "      <td>0.652380</td>\n",
+       "      <td>33.619221</td>\n",
+       "      <td>0.933845</td>\n",
+       "      <td>2000.064398</td>\n",
+       "      <td>-2658.999022</td>\n",
+       "      <td>0.004360</td>\n",
+       "      <td>0.069313</td>\n",
+       "      <td>0.068203</td>\n",
+       "      <td>0.068573</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>4.575950</td>\n",
+       "      <td>1.141527</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.427647</td>\n",
+       "      <td>6.660360</td>\n",
+       "      <td>9.645820</td>\n",
+       "      <td>3.837874</td>\n",
+       "      <td>3.542596</td>\n",
+       "      <td>0.039918</td>\n",
+       "      <td>2.904558</td>\n",
+       "      <td>...</td>\n",
+       "      <td>9.350163</td>\n",
+       "      <td>5.284547</td>\n",
+       "      <td>10.048326</td>\n",
+       "      <td>6.059456</td>\n",
+       "      <td>10.390588</td>\n",
+       "      <td>2553.098329</td>\n",
+       "      <td>0.142776</td>\n",
+       "      <td>1.966806</td>\n",
+       "      <td>1.871986</td>\n",
+       "      <td>1.913647</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>0.060000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>6.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>1984.000000</td>\n",
+       "      <td>-22250.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>14.330870</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>15.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>18.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>27.100000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>1990.000000</td>\n",
+       "      <td>-4250.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>17.347895</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>17.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>21.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>33.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>2001.000000</td>\n",
+       "      <td>-2500.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>20.600625</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>20.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>25.139300</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>38.109600</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>2009.000000</td>\n",
+       "      <td>-750.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>47.087143</td>\n",
+       "      <td>18.311667</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>12.000000</td>\n",
+       "      <td>138.000000</td>\n",
+       "      <td>138.304000</td>\n",
+       "      <td>127.000000</td>\n",
+       "      <td>127.093000</td>\n",
+       "      <td>5.350000</td>\n",
+       "      <td>122.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>197.577100</td>\n",
+       "      <td>181.560900</td>\n",
+       "      <td>159.100000</td>\n",
+       "      <td>152.187800</td>\n",
+       "      <td>2017.000000</td>\n",
+       "      <td>4000.000000</td>\n",
+       "      <td>7.000000</td>\n",
+       "      <td>97.000000</td>\n",
+       "      <td>79.000000</td>\n",
+       "      <td>88.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>8 rows × 59 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          barrels08    barrelsA08  charge120     charge240        city08  \\\n",
+       "count  37843.000000  37843.000000    37843.0  37843.000000  37843.000000   \n",
+       "mean      17.532506      0.216169        0.0      0.023531     17.941389   \n",
+       "std        4.575950      1.141527        0.0      0.427647      6.660360   \n",
+       "min        0.060000      0.000000        0.0      0.000000      6.000000   \n",
+       "25%       14.330870      0.000000        0.0      0.000000     15.000000   \n",
+       "50%       17.347895      0.000000        0.0      0.000000     17.000000   \n",
+       "75%       20.600625      0.000000        0.0      0.000000     20.000000   \n",
+       "max       47.087143     18.311667        0.0     12.000000    138.000000   \n",
+       "\n",
+       "            city08U       cityA08      cityA08U        cityCD         cityE  \\\n",
+       "count  37843.000000  37843.000000  37843.000000  37843.000000  37843.000000   \n",
+       "mean       4.042737      0.520149      0.327163      0.000406      0.184790   \n",
+       "std        9.645820      3.837874      3.542596      0.039918      2.904558   \n",
+       "min        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
+       "25%        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
+       "50%        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
+       "75%        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
+       "max      138.304000    127.000000    127.093000      5.350000    122.000000   \n",
+       "\n",
+       "       ...         UCity        UCityA      UHighway     UHighwayA  \\\n",
+       "count  ...  37843.000000  37843.000000  37843.000000  37843.000000   \n",
+       "mean   ...     22.587229      0.652380     33.619221      0.933845   \n",
+       "std    ...      9.350163      5.284547     10.048326      6.059456   \n",
+       "min    ...      0.000000      0.000000      0.000000      0.000000   \n",
+       "25%    ...     18.000000      0.000000     27.100000      0.000000   \n",
+       "50%    ...     21.000000      0.000000     33.000000      0.000000   \n",
+       "75%    ...     25.139300      0.000000     38.109600      0.000000   \n",
+       "max    ...    197.577100    181.560900    159.100000    152.187800   \n",
+       "\n",
+       "               year  youSaveSpend    charge240b      phevCity       phevHwy  \\\n",
+       "count  37843.000000  37843.000000  37843.000000  37843.000000  37843.000000   \n",
+       "mean    2000.064398  -2658.999022      0.004360      0.069313      0.068203   \n",
+       "std       10.390588   2553.098329      0.142776      1.966806      1.871986   \n",
+       "min     1984.000000 -22250.000000      0.000000      0.000000      0.000000   \n",
+       "25%     1990.000000  -4250.000000      0.000000      0.000000      0.000000   \n",
+       "50%     2001.000000  -2500.000000      0.000000      0.000000      0.000000   \n",
+       "75%     2009.000000   -750.000000      0.000000      0.000000      0.000000   \n",
+       "max     2017.000000   4000.000000      7.000000     97.000000     79.000000   \n",
+       "\n",
+       "           phevComb  \n",
+       "count  37843.000000  \n",
+       "mean       0.068573  \n",
+       "std        1.913647  \n",
+       "min        0.000000  \n",
+       "25%        0.000000  \n",
+       "50%        0.000000  \n",
+       "75%        0.000000  \n",
+       "max       88.000000  \n",
+       "\n",
+       "[8 rows x 59 columns]"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds.describe() # exploring the data "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "barrels08         0\n",
+       "barrelsA08        0\n",
+       "charge120         0\n",
+       "charge240         0\n",
+       "city08            0\n",
+       "              ...  \n",
+       "modifiedOn        0\n",
+       "startStop     31705\n",
+       "phevCity          0\n",
+       "phevHwy           0\n",
+       "phevComb          0\n",
+       "Length: 83, dtype: int64"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds.isnull()   ##  checking missing null is looking nan \n",
+    "ds.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "cylinders       123\n",
+       "displ           120\n",
+       "drive          1189\n",
+       "eng_dscr      15403\n",
+       "trany            11\n",
+       "guzzler       35562\n",
+       "trans_dscr    22796\n",
+       "tCharger      32657\n",
+       "sCharger      37177\n",
+       "atvType       34771\n",
+       "fuelType2     36435\n",
+       "rangeA        36440\n",
+       "evMotor       37281\n",
+       "mfrCode       30818\n",
+       "c240Dscr      37806\n",
+       "c240bDscr     37807\n",
+       "startStop     31705\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds_null = ds.isnull().sum()\n",
+    "ds_null[ds_null>0]     ## looking for what to drop in the dataset \n",
+    "## trying to explore the missing data that is greater than zero "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "barrels08         0\n",
+       "barrelsA08    36435\n",
+       "charge120     37843\n",
+       "charge240     37691\n",
+       "city08            0\n",
+       "              ...  \n",
+       "modifiedOn        0\n",
+       "startStop         0\n",
+       "phevCity      37788\n",
+       "phevHwy       37788\n",
+       "phevComb      37788\n",
+       "Length: 83, dtype: int64"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# check the zeros \n",
+    "ds_zeros = ds[ds == 0.0].count()\n",
+    "ds_zeros"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "barrelsA08         36435\n",
+       "charge120          37843\n",
+       "charge240          37691\n",
+       "city08U            30544\n",
+       "cityA08            36435\n",
+       "cityA08U           37103\n",
+       "cityCD             37831\n",
+       "cityE              37668\n",
+       "cityUF             37788\n",
+       "co2                  120\n",
+       "co2A                  15\n",
+       "co2TailpipeAGpm    36490\n",
+       "co2TailpipeGpm       120\n",
+       "comb08U            30544\n",
+       "combA08            36435\n",
+       "combA08U           37103\n",
+       "combE              37668\n",
+       "combinedCD         37828\n",
+       "combinedUF         37788\n",
+       "displ                  2\n",
+       "engId              12600\n",
+       "fuelCostA08        36471\n",
+       "ghgScoreA              9\n",
+       "highway08U         30544\n",
+       "highwayA08         36435\n",
+       "highwayA08U        37103\n",
+       "highwayCD          37833\n",
+       "highwayE           37668\n",
+       "highwayUF          37788\n",
+       "hlv                33228\n",
+       "hpv                33229\n",
+       "lv2                31593\n",
+       "lv4                24449\n",
+       "phevBlended        37807\n",
+       "pv2                31604\n",
+       "pv4                24449\n",
+       "range              37723\n",
+       "rangeCity          37750\n",
+       "rangeCityA         37788\n",
+       "rangeHwy           37750\n",
+       "rangeHwyA          37788\n",
+       "UCity                 25\n",
+       "UCityA             36481\n",
+       "UHighway              25\n",
+       "UHighwayA          36481\n",
+       "youSaveSpend        1234\n",
+       "charge240b         37807\n",
+       "phevCity           37788\n",
+       "phevHwy            37788\n",
+       "phevComb           37788\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds_zeros[ds_zeros>0] ## all column greater than zero"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "eng_dscr      15403\n",
+       "guzzler       35562\n",
+       "trans_dscr    22796\n",
+       "tCharger      32657\n",
+       "sCharger      37177\n",
+       "atvType       34771\n",
+       "fuelType2     36435\n",
+       "rangeA        36440\n",
+       "evMotor       37281\n",
+       "mfrCode       30818\n",
+       "c240Dscr      37806\n",
+       "c240bDscr     37807\n",
+       "startStop     31705\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## list to drop the null \n",
+    "ds_null = ds.isnull().sum()\n",
+    "ds_null[ds_null>10000]\n",
+    "#list(ds_null>1000].index)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "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>barrels08</th>\n",
+       "      <th>barrelsA08</th>\n",
+       "      <th>charge120</th>\n",
+       "      <th>charge240</th>\n",
+       "      <th>city08</th>\n",
+       "      <th>city08U</th>\n",
+       "      <th>cityA08</th>\n",
+       "      <th>cityA08U</th>\n",
+       "      <th>cityCD</th>\n",
+       "      <th>cityE</th>\n",
+       "      <th>...</th>\n",
+       "      <th>UHighwayA</th>\n",
+       "      <th>VClass</th>\n",
+       "      <th>year</th>\n",
+       "      <th>youSaveSpend</th>\n",
+       "      <th>charge240b</th>\n",
+       "      <th>createdOn</th>\n",
+       "      <th>modifiedOn</th>\n",
+       "      <th>phevCity</th>\n",
+       "      <th>phevHwy</th>\n",
+       "      <th>phevComb</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>15.695714</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>-1250</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>29.964545</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Two Seaters</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>-8500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>12.207778</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Subcompact Cars</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>29.964545</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Vans</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>-8500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>17.347895</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>17</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Compact Cars</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-4000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>Tue Jan 01 00:00:00 EST 2013</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 69 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   barrels08  barrelsA08  charge120  charge240  city08  city08U  cityA08  \\\n",
+       "0  15.695714         0.0        0.0        0.0      19      0.0        0   \n",
+       "1  29.964545         0.0        0.0        0.0       9      0.0        0   \n",
+       "2  12.207778         0.0        0.0        0.0      23      0.0        0   \n",
+       "3  29.964545         0.0        0.0        0.0      10      0.0        0   \n",
+       "4  17.347895         0.0        0.0        0.0      17      0.0        0   \n",
+       "\n",
+       "   cityA08U  cityCD  cityE  ...  UHighwayA           VClass  year  \\\n",
+       "0       0.0     0.0    0.0  ...        0.0      Two Seaters  1985   \n",
+       "1       0.0     0.0    0.0  ...        0.0      Two Seaters  1985   \n",
+       "2       0.0     0.0    0.0  ...        0.0  Subcompact Cars  1985   \n",
+       "3       0.0     0.0    0.0  ...        0.0             Vans  1985   \n",
+       "4       0.0     0.0    0.0  ...        0.0     Compact Cars  1993   \n",
+       "\n",
+       "   youSaveSpend  charge240b                     createdOn  \\\n",
+       "0         -1250         0.0  Tue Jan 01 00:00:00 EST 2013   \n",
+       "1         -8500         0.0  Tue Jan 01 00:00:00 EST 2013   \n",
+       "2           500         0.0  Tue Jan 01 00:00:00 EST 2013   \n",
+       "3         -8500         0.0  Tue Jan 01 00:00:00 EST 2013   \n",
+       "4         -4000         0.0  Tue Jan 01 00:00:00 EST 2013   \n",
+       "\n",
+       "                     modifiedOn  phevCity  phevHwy  phevComb  \n",
+       "0  Tue Jan 01 00:00:00 EST 2013         0        0         0  \n",
+       "1  Tue Jan 01 00:00:00 EST 2013         0        0         0  \n",
+       "2  Tue Jan 01 00:00:00 EST 2013         0        0         0  \n",
+       "3  Tue Jan 01 00:00:00 EST 2013         0        0         0  \n",
+       "4  Tue Jan 01 00:00:00 EST 2013         0        0         0  \n",
+       "\n",
+       "[5 rows x 69 columns]"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## list to drop the null \n",
+    "ds_null = ds.isnull().sum()\n",
+    "ds_null[ds_null>10000]\n",
+    "li_to_drop = list(ds_null[ds_null>1000].index)\n",
+    "\n",
+    "ds_dropped = ds.drop(columns=li_to_drop)\n",
+    "ds_dropped.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "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>barrels08</th>\n",
+       "      <th>barrelsA08</th>\n",
+       "      <th>charge120</th>\n",
+       "      <th>charge240</th>\n",
+       "      <th>city08</th>\n",
+       "      <th>city08U</th>\n",
+       "      <th>cityA08</th>\n",
+       "      <th>cityA08U</th>\n",
+       "      <th>cityCD</th>\n",
+       "      <th>cityE</th>\n",
+       "      <th>...</th>\n",
+       "      <th>UCity</th>\n",
+       "      <th>UCityA</th>\n",
+       "      <th>UHighway</th>\n",
+       "      <th>UHighwayA</th>\n",
+       "      <th>year</th>\n",
+       "      <th>youSaveSpend</th>\n",
+       "      <th>charge240b</th>\n",
+       "      <th>phevCity</th>\n",
+       "      <th>phevHwy</th>\n",
+       "      <th>phevComb</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>15.695714</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>23.3333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>35.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>-1250</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>29.964545</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>11.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>19.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>-8500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>12.207778</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>29.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>47.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>29.964545</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>12.2222</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>16.6667</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1985</td>\n",
+       "      <td>-8500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>17.347895</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>17</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>21.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>32.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-4000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</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>37838</th>\n",
+       "      <td>14.982273</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>24.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>37.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-750</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37839</th>\n",
+       "      <td>14.330870</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>25.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>39.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37840</th>\n",
+       "      <td>15.695714</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>18</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>23.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>34.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-1250</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37841</th>\n",
+       "      <td>15.695714</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>18</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>23.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>34.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-1250</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37842</th>\n",
+       "      <td>18.311667</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>16</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>29.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1993</td>\n",
+       "      <td>-4500</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>37843 rows × 60 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       barrels08  barrelsA08  charge120  charge240  city08  city08U  cityA08  \\\n",
+       "0      15.695714         0.0        0.0        0.0      19      0.0        0   \n",
+       "1      29.964545         0.0        0.0        0.0       9      0.0        0   \n",
+       "2      12.207778         0.0        0.0        0.0      23      0.0        0   \n",
+       "3      29.964545         0.0        0.0        0.0      10      0.0        0   \n",
+       "4      17.347895         0.0        0.0        0.0      17      0.0        0   \n",
+       "...          ...         ...        ...        ...     ...      ...      ...   \n",
+       "37838  14.982273         0.0        0.0        0.0      19      0.0        0   \n",
+       "37839  14.330870         0.0        0.0        0.0      20      0.0        0   \n",
+       "37840  15.695714         0.0        0.0        0.0      18      0.0        0   \n",
+       "37841  15.695714         0.0        0.0        0.0      18      0.0        0   \n",
+       "37842  18.311667         0.0        0.0        0.0      16      0.0        0   \n",
+       "\n",
+       "       cityA08U  cityCD  cityE  ...    UCity  UCityA  UHighway  UHighwayA  \\\n",
+       "0           0.0     0.0    0.0  ...  23.3333     0.0   35.0000        0.0   \n",
+       "1           0.0     0.0    0.0  ...  11.0000     0.0   19.0000        0.0   \n",
+       "2           0.0     0.0    0.0  ...  29.0000     0.0   47.0000        0.0   \n",
+       "3           0.0     0.0    0.0  ...  12.2222     0.0   16.6667        0.0   \n",
+       "4           0.0     0.0    0.0  ...  21.0000     0.0   32.0000        0.0   \n",
+       "...         ...     ...    ...  ...      ...     ...       ...        ...   \n",
+       "37838       0.0     0.0    0.0  ...  24.0000     0.0   37.0000        0.0   \n",
+       "37839       0.0     0.0    0.0  ...  25.0000     0.0   39.0000        0.0   \n",
+       "37840       0.0     0.0    0.0  ...  23.0000     0.0   34.0000        0.0   \n",
+       "37841       0.0     0.0    0.0  ...  23.0000     0.0   34.0000        0.0   \n",
+       "37842       0.0     0.0    0.0  ...  20.0000     0.0   29.0000        0.0   \n",
+       "\n",
+       "       year  youSaveSpend  charge240b  phevCity  phevHwy  phevComb  \n",
+       "0      1985         -1250         0.0         0        0         0  \n",
+       "1      1985         -8500         0.0         0        0         0  \n",
+       "2      1985           500         0.0         0        0         0  \n",
+       "3      1985         -8500         0.0         0        0         0  \n",
+       "4      1993         -4000         0.0         0        0         0  \n",
+       "...     ...           ...         ...       ...      ...       ...  \n",
+       "37838  1993          -750         0.0         0        0         0  \n",
+       "37839  1993          -500         0.0         0        0         0  \n",
+       "37840  1993         -1250         0.0         0        0         0  \n",
+       "37841  1993         -1250         0.0         0        0         0  \n",
+       "37842  1993         -4500         0.0         0        0         0  \n",
+       "\n",
+       "[37843 rows x 60 columns]"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## how to check the negatives\n",
+    "## numeric ()\n",
+    "## or select_type()\n",
+    "\n",
+    "numeric = ds.select_dtypes(exclude=object)\n",
+    "numeric\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "barrels08              0\n",
+       "barrelsA08             0\n",
+       "charge120              0\n",
+       "charge240              0\n",
+       "city08                 0\n",
+       "city08U                0\n",
+       "cityA08                0\n",
+       "cityA08U               0\n",
+       "cityCD                 0\n",
+       "cityE                  0\n",
+       "cityUF                 0\n",
+       "co2                31989\n",
+       "co2A               37318\n",
+       "co2TailpipeAGpm        0\n",
+       "co2TailpipeGpm         0\n",
+       "comb08                 0\n",
+       "comb08U                0\n",
+       "combA08                0\n",
+       "combA08U               0\n",
+       "combE                  0\n",
+       "combinedCD             0\n",
+       "combinedUF             0\n",
+       "cylinders              0\n",
+       "displ                  0\n",
+       "engId                  0\n",
+       "feScore            32028\n",
+       "fuelCost08             0\n",
+       "fuelCostA08            0\n",
+       "ghgScore           32028\n",
+       "ghgScoreA          37325\n",
+       "highway08              0\n",
+       "highway08U             0\n",
+       "highwayA08             0\n",
+       "highwayA08U            0\n",
+       "highwayCD              0\n",
+       "highwayE               0\n",
+       "highwayUF              0\n",
+       "hlv                    0\n",
+       "hpv                    0\n",
+       "id                     0\n",
+       "lv2                    0\n",
+       "lv4                    0\n",
+       "phevBlended            0\n",
+       "pv2                    0\n",
+       "pv4                    0\n",
+       "range                  0\n",
+       "rangeCity              0\n",
+       "rangeCityA             0\n",
+       "rangeHwy               0\n",
+       "rangeHwyA              0\n",
+       "UCity                  0\n",
+       "UCityA                 0\n",
+       "UHighway               0\n",
+       "UHighwayA              0\n",
+       "year                   0\n",
+       "youSaveSpend       32526\n",
+       "charge240b             0\n",
+       "phevCity               0\n",
+       "phevHwy                0\n",
+       "phevComb               0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "numeric[numeric <0].count() # counts all numeric less than zero\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "co2             31989\n",
+       "co2A            37318\n",
+       "feScore         32028\n",
+       "ghgScore        32028\n",
+       "ghgScoreA       37325\n",
+       "youSaveSpend    32526\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds_nagatives = numeric[numeric <0].count()\n",
+    "ds_nagatives[ds_nagatives >0]    # counts cloumn that have more zero negative."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "condition = ds['displ'].isnull()\n",
+    "null_displ = ds[condition]\n",
+    "null_displ = null_displ[['year', 'make', 'model', 'trany', 'fuelType', 'cylinders', 'displ']]"
+   ]
+  },
+  {
+   "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>year</th>\n",
+       "      <th>make</th>\n",
+       "      <th>model</th>\n",
+       "      <th>trany</th>\n",
+       "      <th>fuelType</th>\n",
+       "      <th>cylinders</th>\n",
+       "      <th>displ</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>7138</th>\n",
+       "      <td>2000</td>\n",
+       "      <td>Nissan</td>\n",
+       "      <td>Altra EV</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7139</th>\n",
+       "      <td>2000</td>\n",
+       "      <td>Toyota</td>\n",
+       "      <td>RAV4 EV</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8143</th>\n",
+       "      <td>2001</td>\n",
+       "      <td>Toyota</td>\n",
+       "      <td>RAV4 EV</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8144</th>\n",
+       "      <td>2001</td>\n",
+       "      <td>Ford</td>\n",
+       "      <td>Th!nk</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8146</th>\n",
+       "      <td>2001</td>\n",
+       "      <td>Ford</td>\n",
+       "      <td>Explorer USPS Electric</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Electricity</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30969</th>\n",
+       "      <td>2017</td>\n",
+       "      <td>Kia</td>\n",
+       "      <td>Soul Electric</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30972</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Tesla</td>\n",
+       "      <td>Model S (60 kW-hr battery pack)</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30973</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Tesla</td>\n",
+       "      <td>Model S AWD - 60D</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30974</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Tesla</td>\n",
+       "      <td>Model S AWD - P100D</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30975</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Tesla</td>\n",
+       "      <td>Model X AWD - 60D</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>120 rows × 7 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       year    make                            model           trany  \\\n",
+       "7138   2000  Nissan                         Altra EV             NaN   \n",
+       "7139   2000  Toyota                          RAV4 EV             NaN   \n",
+       "8143   2001  Toyota                          RAV4 EV             NaN   \n",
+       "8144   2001    Ford                            Th!nk             NaN   \n",
+       "8146   2001    Ford           Explorer USPS Electric             NaN   \n",
+       "...     ...     ...                              ...             ...   \n",
+       "30969  2017     Kia                    Soul Electric  Automatic (A1)   \n",
+       "30972  2016   Tesla  Model S (60 kW-hr battery pack)  Automatic (A1)   \n",
+       "30973  2016   Tesla                Model S AWD - 60D  Automatic (A1)   \n",
+       "30974  2016   Tesla              Model S AWD - P100D  Automatic (A1)   \n",
+       "30975  2016   Tesla                Model X AWD - 60D  Automatic (A1)   \n",
+       "\n",
+       "          fuelType  cylinders  displ  \n",
+       "7138   Electricity        NaN    NaN  \n",
+       "7139   Electricity        NaN    NaN  \n",
+       "8143   Electricity        NaN    NaN  \n",
+       "8144   Electricity        NaN    NaN  \n",
+       "8146   Electricity        NaN    NaN  \n",
+       "...            ...        ...    ...  \n",
+       "30969  Electricity        NaN    NaN  \n",
+       "30972  Electricity        NaN    NaN  \n",
+       "30973  Electricity        NaN    NaN  \n",
+       "30974  Electricity        NaN    NaN  \n",
+       "30975  Electricity        NaN    NaN  \n",
+       "\n",
+       "[120 rows x 7 columns]"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "null_displ"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ds[['displ','cylinders']] = ds[['displ','cylinders']].fillna(0)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "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>year</th>\n",
+       "      <th>make</th>\n",
+       "      <th>model</th>\n",
+       "      <th>trany</th>\n",
+       "      <th>drive</th>\n",
+       "      <th>fuelType</th>\n",
+       "      <th>cylinders</th>\n",
+       "      <th>displ</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>29670</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Volvo</td>\n",
+       "      <td>XC90 AWD</td>\n",
+       "      <td>Automatic (S8)</td>\n",
+       "      <td>All-Wheel Drive</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29671</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Chevrolet</td>\n",
+       "      <td>Spark EV</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Front-Wheel Drive</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29672</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Mercedes-Benz</td>\n",
+       "      <td>B250e</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Front-Wheel Drive</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29673</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Hyundai</td>\n",
+       "      <td>Sonata Plug-in Hybrid</td>\n",
+       "      <td>Auto(AM6)</td>\n",
+       "      <td>Front-Wheel Drive</td>\n",
+       "      <td>Regular Gas and Electricity</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29674</th>\n",
+       "      <td>2016</td>\n",
+       "      <td>Jaguar</td>\n",
+       "      <td>XF AWD</td>\n",
+       "      <td>Automatic (S8)</td>\n",
+       "      <td>All-Wheel Drive</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>3.0</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29995</th>\n",
+       "      <td>1987</td>\n",
+       "      <td>GMC</td>\n",
+       "      <td>R15 Pickup 2WD</td>\n",
+       "      <td>Automatic 3-spd</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>4.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29996</th>\n",
+       "      <td>2017</td>\n",
+       "      <td>Mitsubishi</td>\n",
+       "      <td>Mirage</td>\n",
+       "      <td>Manual 5-spd</td>\n",
+       "      <td>Front-Wheel Drive</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>1.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29997</th>\n",
+       "      <td>2017</td>\n",
+       "      <td>Mitsubishi</td>\n",
+       "      <td>Mirage</td>\n",
+       "      <td>Automatic (variable gear ratios)</td>\n",
+       "      <td>Front-Wheel Drive</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>1.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29998</th>\n",
+       "      <td>2017</td>\n",
+       "      <td>Chrysler</td>\n",
+       "      <td>Pacifica</td>\n",
+       "      <td>Automatic 9-spd</td>\n",
+       "      <td>Front-Wheel Drive</td>\n",
+       "      <td>Regular</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>3.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29999</th>\n",
+       "      <td>2017</td>\n",
+       "      <td>Mitsubishi</td>\n",
+       "      <td>i-MiEV</td>\n",
+       "      <td>Automatic (A1)</td>\n",
+       "      <td>Rear-Wheel Drive</td>\n",
+       "      <td>Electricity</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>330 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       year           make                  model  \\\n",
+       "29670  2016          Volvo               XC90 AWD   \n",
+       "29671  2016      Chevrolet               Spark EV   \n",
+       "29672  2016  Mercedes-Benz                  B250e   \n",
+       "29673  2016        Hyundai  Sonata Plug-in Hybrid   \n",
+       "29674  2016         Jaguar                 XF AWD   \n",
+       "...     ...            ...                    ...   \n",
+       "29995  1987            GMC         R15 Pickup 2WD   \n",
+       "29996  2017     Mitsubishi                 Mirage   \n",
+       "29997  2017     Mitsubishi                 Mirage   \n",
+       "29998  2017       Chrysler               Pacifica   \n",
+       "29999  2017     Mitsubishi                 i-MiEV   \n",
+       "\n",
+       "                                  trany              drive  \\\n",
+       "29670                    Automatic (S8)    All-Wheel Drive   \n",
+       "29671                    Automatic (A1)  Front-Wheel Drive   \n",
+       "29672                    Automatic (A1)  Front-Wheel Drive   \n",
+       "29673                         Auto(AM6)  Front-Wheel Drive   \n",
+       "29674                    Automatic (S8)    All-Wheel Drive   \n",
+       "...                                 ...                ...   \n",
+       "29995                   Automatic 3-spd   Rear-Wheel Drive   \n",
+       "29996                      Manual 5-spd  Front-Wheel Drive   \n",
+       "29997  Automatic (variable gear ratios)  Front-Wheel Drive   \n",
+       "29998                   Automatic 9-spd  Front-Wheel Drive   \n",
+       "29999                    Automatic (A1)   Rear-Wheel Drive   \n",
+       "\n",
+       "                          fuelType  cylinders  displ  \n",
+       "29670                      Premium        4.0    2.0  \n",
+       "29671                  Electricity        0.0    0.0  \n",
+       "29672                  Electricity        0.0    0.0  \n",
+       "29673  Regular Gas and Electricity        4.0    2.0  \n",
+       "29674                      Premium        6.0    3.0  \n",
+       "...                            ...        ...    ...  \n",
+       "29995                      Regular        6.0    4.3  \n",
+       "29996                      Regular        3.0    1.2  \n",
+       "29997                      Regular        3.0    1.2  \n",
+       "29998                      Regular        6.0    3.6  \n",
+       "29999                  Electricity        0.0    0.0  \n",
+       "\n",
+       "[330 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds[['year', 'make', 'model', 'trany', 'drive','fuelType','cylinders', 'displ']][29670:30000]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dtype('float64')"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## datatype corrections \n",
+    "\n",
+    "ds['cylinders'].dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "barrels08     float64\n",
+       "barrelsA08    float64\n",
+       "charge120     float64\n",
+       "charge240     float64\n",
+       "city08          int64\n",
+       "               ...   \n",
+       "modifiedOn     object\n",
+       "startStop      object\n",
+       "phevCity        int64\n",
+       "phevHwy         int64\n",
+       "phevComb        int64\n",
+       "Length: 83, dtype: object"
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dtype('int64')"
+      ]
+     },
+     "execution_count": 68,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds['cylinders'] = ds['cylinders'].astype('int64')\n",
+    "ds['cylinders'].dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{nan, 'Auto(AV-S6)', 'Manual(M7)', 'Automatic (S7)', 'Auto(AM-S9)', 'Automatic 9-spd', 'Automatic (A6)', 'Auto(AM7)', 'Automatic (AM6)', 'Auto(AV-S8)', 'Automatic (AV-S6)', 'Auto(AM-S6)', 'Automatic 3-spd', 'Automatic (variable gear ratios)', 'Automatic (A1)', 'Auto (AV-S8)', 'Manual 7-spd', 'Auto(AM-S8)', 'Automatic 7-spd', 'Manual 4-spd Doubled', 'Automatic 6spd', 'Automatic 5-spd', 'Automatic (S5)', 'Auto (AV)', 'Auto(L4)', 'Manual 3-spd', 'Automatic (S8)', 'Automatic 4-spd', 'Automatic 8-spd', 'Manual 6-spd', 'Automatic (AV)', 'Auto (AV-S6)', 'Auto(L3)', 'Auto(AM-S7)', 'Manual 5 spd', 'Auto(AM5)', 'Auto(A1)', 'Auto(AM6)', 'Automatic (S9)', 'Manual 4-spd', 'Manual 5-spd', 'Automatic (S6)', 'Auto(AM8)', 'Automatic (S4)', 'Auto(AV-S7)', 'Automatic (AM5)', 'Automatic 6-spd'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "## cleaning gtext and removing special symbols \n",
+    "print (set(ds['trany']))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Manual 5-spd', 'Automatic 3-spd', 'Automatic 4-spd',\n",
+       "       'Automatic 5-spd', 'Manual 4-spd', 'Manual 3-spd', 'Manual 6-spd',\n",
+       "       'Automatic (S5)', 'Automatic (variable gear ratios)',\n",
+       "       'Automatic 6-spd', 'Automatic (S6)', nan, 'Automatic (S4)',\n",
+       "       'Automatic 7-spd', 'Automatic (S7)', 'Automatic (S8)',\n",
+       "       'Automatic (AM5)', 'Auto(AM6)', 'Auto(AV-S7)', 'Automatic (A6)',\n",
+       "       'Automatic (AV-S6)', 'Auto(AM7)', 'Manual 4-spd Doubled',\n",
+       "       'Manual 5 spd', 'Automatic (AM6)', 'Manual 7-spd', 'Auto(L4)',\n",
+       "       'Auto(L3)', 'Automatic (AV)', 'Auto (AV-S6)', 'Auto(AM5)',\n",
+       "       'Auto(AV-S6)', 'Auto (AV-S8)', 'Automatic 8-spd', 'Auto(AV-S8)',\n",
+       "       'Automatic (A1)', 'Auto (AV)', 'Auto(AM-S6)', 'Auto(AM-S7)',\n",
+       "       'Automatic 6spd', 'Automatic 9-spd', 'Automatic (S9)',\n",
+       "       'Auto(AM-S8)', 'Auto(A1)', 'Auto(AM8)', 'Manual(M7)',\n",
+       "       'Auto(AM-S9)'], dtype=object)"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ds['trany'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ds['trany'] = ds['trany']"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "ade50332f43eeb97f8e1fbc4c7d493d3589b4263fef63cb9cf9d26d524eaa4f1"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.9.7 ('base')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}