diff --git a/.ipynb_checkpoints/lab-dw-data-structuring-and-combining-checkpoint.ipynb b/.ipynb_checkpoints/lab-dw-data-structuring-and-combining-checkpoint.ipynb
new file mode 100644
index 0000000..6eb7a60
--- /dev/null
+++ b/.ipynb_checkpoints/lab-dw-data-structuring-and-combining-checkpoint.ipynb
@@ -0,0 +1,1286 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "25d7736c-ba17-4aff-b6bb-66eba20fbf4e",
+   "metadata": {
+    "id": "25d7736c-ba17-4aff-b6bb-66eba20fbf4e"
+   },
+   "source": [
+    "# Lab | Data Structuring and Combining Data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a2cdfc70-44c8-478c-81e7-2bc43fdf4986",
+   "metadata": {
+    "id": "a2cdfc70-44c8-478c-81e7-2bc43fdf4986"
+   },
+   "source": [
+    "## Challenge 1: Combining & Cleaning Data\n",
+    "\n",
+    "In this challenge, we will be working with the customer data from an insurance company, as we did in the two previous labs. The data can be found here:\n",
+    "- https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file1.csv\n",
+    "\n",
+    "But this time, we got new data, which can be found in the following 2 CSV files located at the links below.\n",
+    "\n",
+    "- https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file2.csv\n",
+    "- https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file3.csv\n",
+    "\n",
+    "Note that you'll need to clean and format the new data.\n",
+    "\n",
+    "Observation:\n",
+    "- One option is to first combine the three datasets and then apply the cleaning function to the new combined dataset\n",
+    "- Another option would be to read the clean file you saved in the previous lab, and just clean the two new files and concatenate the three clean datasets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "492d06e3-92c7-4105-ac72-536db98d3244",
+   "metadata": {
+    "id": "492d06e3-92c7-4105-ac72-536db98d3244"
+   },
+   "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>Customer</th>\n",
+       "      <th>ST</th>\n",
+       "      <th>GENDER</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>Monthly Premium Auto</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1000.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>2.704934</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>697953.59%</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>1131.464935</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1288743.17%</td>\n",
+       "      <td>48767.0</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>566.472247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>764586.18%</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>529.881344</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>M</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>536307.65%</td>\n",
+       "      <td>36357.0</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>17.269323</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4003</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4004</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4005</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4006</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4007</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>4008 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     Customer          ST GENDER             Education  \\\n",
+       "0     RB50392  Washington    NaN                Master   \n",
+       "1     QZ44356     Arizona      F              Bachelor   \n",
+       "2     AI49188      Nevada      F              Bachelor   \n",
+       "3     WW63253  California      M              Bachelor   \n",
+       "4     GA49547  Washington      M  High School or Below   \n",
+       "...       ...         ...    ...                   ...   \n",
+       "4003      NaN         NaN    NaN                   NaN   \n",
+       "4004      NaN         NaN    NaN                   NaN   \n",
+       "4005      NaN         NaN    NaN                   NaN   \n",
+       "4006      NaN         NaN    NaN                   NaN   \n",
+       "4007      NaN         NaN    NaN                   NaN   \n",
+       "\n",
+       "     Customer Lifetime Value   Income  Monthly Premium Auto  \\\n",
+       "0                        NaN      0.0                1000.0   \n",
+       "1                 697953.59%      0.0                  94.0   \n",
+       "2                1288743.17%  48767.0                 108.0   \n",
+       "3                 764586.18%      0.0                 106.0   \n",
+       "4                 536307.65%  36357.0                  68.0   \n",
+       "...                      ...      ...                   ...   \n",
+       "4003                     NaN      NaN                   NaN   \n",
+       "4004                     NaN      NaN                   NaN   \n",
+       "4005                     NaN      NaN                   NaN   \n",
+       "4006                     NaN      NaN                   NaN   \n",
+       "4007                     NaN      NaN                   NaN   \n",
+       "\n",
+       "     Number of Open Complaints     Policy Type  Vehicle Class  \\\n",
+       "0                       1/0/00   Personal Auto  Four-Door Car   \n",
+       "1                       1/0/00   Personal Auto  Four-Door Car   \n",
+       "2                       1/0/00   Personal Auto   Two-Door Car   \n",
+       "3                       1/0/00  Corporate Auto            SUV   \n",
+       "4                       1/0/00   Personal Auto  Four-Door Car   \n",
+       "...                        ...             ...            ...   \n",
+       "4003                       NaN             NaN            NaN   \n",
+       "4004                       NaN             NaN            NaN   \n",
+       "4005                       NaN             NaN            NaN   \n",
+       "4006                       NaN             NaN            NaN   \n",
+       "4007                       NaN             NaN            NaN   \n",
+       "\n",
+       "      Total Claim Amount  \n",
+       "0               2.704934  \n",
+       "1            1131.464935  \n",
+       "2             566.472247  \n",
+       "3             529.881344  \n",
+       "4              17.269323  \n",
+       "...                  ...  \n",
+       "4003                 NaN  \n",
+       "4004                 NaN  \n",
+       "4005                 NaN  \n",
+       "4006                 NaN  \n",
+       "4007                 NaN  \n",
+       "\n",
+       "[4008 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "df1 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file1.csv\")\n",
+    "df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f4d09544",
+   "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>Customer</th>\n",
+       "      <th>ST</th>\n",
+       "      <th>GENDER</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>Monthly Premium Auto</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>GS98873</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>323912.47%</td>\n",
+       "      <td>16061</td>\n",
+       "      <td>88</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>633.600000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>CW49887</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>462680.11%</td>\n",
+       "      <td>79487</td>\n",
+       "      <td>114</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>547.200000</td>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>MY31220</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>899704.02%</td>\n",
+       "      <td>54230</td>\n",
+       "      <td>112</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>537.600000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>UH35128</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2580706.30%</td>\n",
+       "      <td>71210</td>\n",
+       "      <td>214</td>\n",
+       "      <td>1/1/00</td>\n",
+       "      <td>1027.200000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Luxury Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>WH52799</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>380812.21%</td>\n",
+       "      <td>94903</td>\n",
+       "      <td>94</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>451.200000</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>991</th>\n",
+       "      <td>HV85198</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>847141.75%</td>\n",
+       "      <td>63513</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>185.667213</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>992</th>\n",
+       "      <td>BS91566</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>543121.91%</td>\n",
+       "      <td>58161</td>\n",
+       "      <td>68</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>140.747286</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>993</th>\n",
+       "      <td>IL40123</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>568964.41%</td>\n",
+       "      <td>83640</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>471.050488</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>994</th>\n",
+       "      <td>MY32149</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>368672.38%</td>\n",
+       "      <td>0</td>\n",
+       "      <td>96</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>28.460568</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>995</th>\n",
+       "      <td>SA91515</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>399258.39%</td>\n",
+       "      <td>0</td>\n",
+       "      <td>111</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>700.349052</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>996 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Customer          ST GENDER Education Customer Lifetime Value  Income  \\\n",
+       "0    GS98873     Arizona      F  Bachelor              323912.47%   16061   \n",
+       "1    CW49887  California      F    Master              462680.11%   79487   \n",
+       "2    MY31220  California      F   College              899704.02%   54230   \n",
+       "3    UH35128      Oregon      F   College             2580706.30%   71210   \n",
+       "4    WH52799     Arizona      F   College              380812.21%   94903   \n",
+       "..       ...         ...    ...       ...                     ...     ...   \n",
+       "991  HV85198     Arizona      M    Master              847141.75%   63513   \n",
+       "992  BS91566     Arizona      F   College              543121.91%   58161   \n",
+       "993  IL40123      Nevada      F   College              568964.41%   83640   \n",
+       "994  MY32149  California      F    Master              368672.38%       0   \n",
+       "995  SA91515  California      M  Bachelor              399258.39%       0   \n",
+       "\n",
+       "     Monthly Premium Auto Number of Open Complaints  Total Claim Amount  \\\n",
+       "0                      88                    1/0/00          633.600000   \n",
+       "1                     114                    1/0/00          547.200000   \n",
+       "2                     112                    1/0/00          537.600000   \n",
+       "3                     214                    1/1/00         1027.200000   \n",
+       "4                      94                    1/0/00          451.200000   \n",
+       "..                    ...                       ...                 ...   \n",
+       "991                    70                    1/0/00          185.667213   \n",
+       "992                    68                    1/0/00          140.747286   \n",
+       "993                    70                    1/0/00          471.050488   \n",
+       "994                    96                    1/0/00           28.460568   \n",
+       "995                   111                    1/0/00          700.349052   \n",
+       "\n",
+       "        Policy Type  Vehicle Class  \n",
+       "0     Personal Auto  Four-Door Car  \n",
+       "1      Special Auto            SUV  \n",
+       "2     Personal Auto   Two-Door Car  \n",
+       "3     Personal Auto     Luxury Car  \n",
+       "4    Corporate Auto   Two-Door Car  \n",
+       "..              ...            ...  \n",
+       "991   Personal Auto  Four-Door Car  \n",
+       "992  Corporate Auto  Four-Door Car  \n",
+       "993  Corporate Auto   Two-Door Car  \n",
+       "994   Personal Auto   Two-Door Car  \n",
+       "995   Personal Auto            SUV  \n",
+       "\n",
+       "[996 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file2.csv\")\n",
+    "df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b48e9b60",
+   "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>Customer</th>\n",
+       "      <th>State</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>Monthly Premium Auto</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>SA25987</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>3479.137523</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>104</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>499.200000</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>TB86706</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>2502.637401</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>66</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>3.468912</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ZL73902</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>3265.156348</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>F</td>\n",
+       "      <td>25820</td>\n",
+       "      <td>82</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>393.600000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>KX23516</td>\n",
+       "      <td>California</td>\n",
+       "      <td>4455.843406</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>F</td>\n",
+       "      <td>0</td>\n",
+       "      <td>121</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>699.615192</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>FN77294</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7704.958480</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>M</td>\n",
+       "      <td>30366</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>484.800000</td>\n",
+       "      <td>SUV</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7065</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>California</td>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>M</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>73</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7066</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>College</td>\n",
+       "      <td>F</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>79</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7067</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>California</td>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>85</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7068</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>College</td>\n",
+       "      <td>M</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>96</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7069</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>College</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>7070 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     Customer       State  Customer Lifetime Value             Education  \\\n",
+       "0     SA25987  Washington              3479.137523  High School or Below   \n",
+       "1     TB86706     Arizona              2502.637401                Master   \n",
+       "2     ZL73902      Nevada              3265.156348              Bachelor   \n",
+       "3     KX23516  California              4455.843406  High School or Below   \n",
+       "4     FN77294  California              7704.958480  High School or Below   \n",
+       "...       ...         ...                      ...                   ...   \n",
+       "7065  LA72316  California             23405.987980              Bachelor   \n",
+       "7066  PK87824  California              3096.511217               College   \n",
+       "7067  TD14365  California              8163.890428              Bachelor   \n",
+       "7068  UP19263  California              7524.442436               College   \n",
+       "7069  Y167826  California              2611.836866               College   \n",
+       "\n",
+       "     Gender  Income  Monthly Premium Auto  Number of Open Complaints  \\\n",
+       "0         M       0                   104                          0   \n",
+       "1         M       0                    66                          0   \n",
+       "2         F   25820                    82                          0   \n",
+       "3         F       0                   121                          0   \n",
+       "4         M   30366                   101                          2   \n",
+       "...     ...     ...                   ...                        ...   \n",
+       "7065      M   71941                    73                          0   \n",
+       "7066      F   21604                    79                          0   \n",
+       "7067      M       0                    85                          3   \n",
+       "7068      M   21941                    96                          0   \n",
+       "7069      M       0                    77                          0   \n",
+       "\n",
+       "         Policy Type  Total Claim Amount  Vehicle Class  \n",
+       "0      Personal Auto          499.200000   Two-Door Car  \n",
+       "1      Personal Auto            3.468912   Two-Door Car  \n",
+       "2      Personal Auto          393.600000  Four-Door Car  \n",
+       "3      Personal Auto          699.615192            SUV  \n",
+       "4      Personal Auto          484.800000            SUV  \n",
+       "...              ...                 ...            ...  \n",
+       "7065   Personal Auto          198.234764  Four-Door Car  \n",
+       "7066  Corporate Auto          379.200000  Four-Door Car  \n",
+       "7067  Corporate Auto          790.784983  Four-Door Car  \n",
+       "7068   Personal Auto          691.200000  Four-Door Car  \n",
+       "7069  Corporate Auto          369.600000   Two-Door Car  \n",
+       "\n",
+       "[7070 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file3.csv\")\n",
+    "df3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "35090aa7",
+   "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>Customer</th>\n",
+       "      <th>ST</th>\n",
+       "      <th>GENDER</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>Monthly Premium Auto</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1000.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>2.704934</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>697953.59%</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>1131.464935</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1288743.17%</td>\n",
+       "      <td>48767.0</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>566.472247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>764586.18%</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>529.881344</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>M</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>536307.65%</td>\n",
+       "      <td>36357.0</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>17.269323</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4003</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4004</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4005</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4006</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4007</th>\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",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>4008 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     Customer          ST GENDER             Education  \\\n",
+       "0     RB50392  Washington    NaN                Master   \n",
+       "1     QZ44356     Arizona      F              Bachelor   \n",
+       "2     AI49188      Nevada      F              Bachelor   \n",
+       "3     WW63253  California      M              Bachelor   \n",
+       "4     GA49547  Washington      M  High School or Below   \n",
+       "...       ...         ...    ...                   ...   \n",
+       "4003      NaN         NaN    NaN                   NaN   \n",
+       "4004      NaN         NaN    NaN                   NaN   \n",
+       "4005      NaN         NaN    NaN                   NaN   \n",
+       "4006      NaN         NaN    NaN                   NaN   \n",
+       "4007      NaN         NaN    NaN                   NaN   \n",
+       "\n",
+       "     Customer Lifetime Value   Income  Monthly Premium Auto  \\\n",
+       "0                        NaN      0.0                1000.0   \n",
+       "1                 697953.59%      0.0                  94.0   \n",
+       "2                1288743.17%  48767.0                 108.0   \n",
+       "3                 764586.18%      0.0                 106.0   \n",
+       "4                 536307.65%  36357.0                  68.0   \n",
+       "...                      ...      ...                   ...   \n",
+       "4003                     NaN      NaN                   NaN   \n",
+       "4004                     NaN      NaN                   NaN   \n",
+       "4005                     NaN      NaN                   NaN   \n",
+       "4006                     NaN      NaN                   NaN   \n",
+       "4007                     NaN      NaN                   NaN   \n",
+       "\n",
+       "     Number of Open Complaints     Policy Type  Vehicle Class  \\\n",
+       "0                       1/0/00   Personal Auto  Four-Door Car   \n",
+       "1                       1/0/00   Personal Auto  Four-Door Car   \n",
+       "2                       1/0/00   Personal Auto   Two-Door Car   \n",
+       "3                       1/0/00  Corporate Auto            SUV   \n",
+       "4                       1/0/00   Personal Auto  Four-Door Car   \n",
+       "...                        ...             ...            ...   \n",
+       "4003                       NaN             NaN            NaN   \n",
+       "4004                       NaN             NaN            NaN   \n",
+       "4005                       NaN             NaN            NaN   \n",
+       "4006                       NaN             NaN            NaN   \n",
+       "4007                       NaN             NaN            NaN   \n",
+       "\n",
+       "      Total Claim Amount  \n",
+       "0               2.704934  \n",
+       "1            1131.464935  \n",
+       "2             566.472247  \n",
+       "3             529.881344  \n",
+       "4              17.269323  \n",
+       "...                  ...  \n",
+       "4003                 NaN  \n",
+       "4004                 NaN  \n",
+       "4005                 NaN  \n",
+       "4006                 NaN  \n",
+       "4007                 NaN  \n",
+       "\n",
+       "[4008 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a795af02",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Customer', 'ST', 'GENDER', 'Education', 'Customer Lifetime Value',\n",
+       "       'Income', 'Monthly Premium Auto', 'Number of Open Complaints',\n",
+       "       'Policy Type', 'Vehicle Class', 'Total Claim Amount'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "0c4059ef",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'st', 'gender', 'education', 'customer lifetime value',\n",
+       "       'income', 'monthly premium auto', 'number of open complaints',\n",
+       "       'policy type', 'vehicle class', 'total claim amount'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1.columns.str.lower()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "43746587",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1.rename(columns={\"old_column_name1\": \"new_column_name1\", \"old_column_name2\": \"new_column_name2\",...}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "afd9cbe0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3cb5ce7a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "488ffb2e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0517cc02",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "31b8a9e7-7db9-4604-991b-ef6771603e57",
+   "metadata": {
+    "id": "31b8a9e7-7db9-4604-991b-ef6771603e57"
+   },
+   "source": [
+    "# Challenge 2: Structuring Data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a877fd6d-7a0c-46d2-9657-f25036e4ca4b",
+   "metadata": {
+    "id": "a877fd6d-7a0c-46d2-9657-f25036e4ca4b"
+   },
+   "source": [
+    "In this challenge, we will continue to work with customer data from an insurance company, but we will use a dataset with more columns, called marketing_customer_analysis.csv, which can be found at the following link:\n",
+    "\n",
+    "https://raw.githubusercontent.com/data-bootcamp-v4/data/main/marketing_customer_analysis_clean.csv\n",
+    "\n",
+    "This dataset contains information such as customer demographics, policy details, vehicle information, and the customer's response to the last marketing campaign. Our goal is to explore and analyze this data by performing data cleaning, formatting, and structuring."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26",
+   "metadata": {
+    "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26"
+   },
+   "outputs": [],
+   "source": [
+    "# Your code goes here"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "df35fd0d-513e-4e77-867e-429da10a9cc7",
+   "metadata": {
+    "id": "df35fd0d-513e-4e77-867e-429da10a9cc7"
+   },
+   "source": [
+    "1. You work at the marketing department and you want to know which sales channel brought the most sales in terms of total revenue. Using pivot, create a summary table showing the total revenue for each sales channel (branch, call center, web, and mail).\n",
+    "Round the total revenue to 2 decimal points.  Analyze the resulting table to draw insights."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "640993b2-a291-436c-a34d-a551144f8196",
+   "metadata": {
+    "id": "640993b2-a291-436c-a34d-a551144f8196"
+   },
+   "source": [
+    "2. Create a pivot table that shows the average customer lifetime value per gender and education level. Analyze the resulting table to draw insights."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "32c7f2e5-3d90-43e5-be33-9781b6069198",
+   "metadata": {
+    "id": "32c7f2e5-3d90-43e5-be33-9781b6069198"
+   },
+   "source": [
+    "## Bonus\n",
+    "\n",
+    "You work at the customer service department and you want to know which months had the highest number of complaints by policy type category. Create a summary table showing the number of complaints by policy type and month.\n",
+    "Show it in a long format table."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3d09a8f-953c-448a-a5f8-2e5a8cca7291",
+   "metadata": {
+    "id": "e3d09a8f-953c-448a-a5f8-2e5a8cca7291"
+   },
+   "source": [
+    "*In data analysis, a long format table is a way of structuring data in which each observation or measurement is stored in a separate row of the table. The key characteristic of a long format table is that each column represents a single variable, and each row represents a single observation of that variable.*\n",
+    "\n",
+    "*More information about long and wide format tables here: https://www.statology.org/long-vs-wide-data/*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a069e0b-b400-470e-904d-d17582191be4",
+   "metadata": {
+    "id": "3a069e0b-b400-470e-904d-d17582191be4"
+   },
+   "outputs": [],
+   "source": [
+    "# Your code goes here"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/lab-dw-data-structuring-and-combining.ipynb b/lab-dw-data-structuring-and-combining.ipynb
index ec4e3f9..9c9112d 100644
--- a/lab-dw-data-structuring-and-combining.ipynb
+++ b/lab-dw-data-structuring-and-combining.ipynb
@@ -36,16 +36,3208 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "492d06e3-92c7-4105-ac72-536db98d3244",
    "metadata": {
     "id": "492d06e3-92c7-4105-ac72-536db98d3244"
    },
    "outputs": [],
    "source": [
-    "# Your code goes here"
+    "import pandas as pd\n",
+    "df1 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file1.csv\")\n",
+    "#df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "94b17acc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file2.csv\")\n",
+    "#df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "86a0178e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df3 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file3.csv\")\n",
+    "#df3"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d4abcb8f",
+   "metadata": {},
+   "source": [
+    "# Cleaning df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "38a86441",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1.columns = df1.columns.str.lower()\n",
+    "df1.columns = df1.columns.str.replace(\" \", \"_\")\n",
+    "df1.rename(columns={\"st\":\"state\"}, inplace=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ff7995dc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                     2937\n",
+       "state                        2937\n",
+       "gender                       3054\n",
+       "education                    2937\n",
+       "customer_lifetime_value      2940\n",
+       "income                       2937\n",
+       "monthly_premium_auto         2937\n",
+       "number_of_open_complaints    2937\n",
+       "policy_type                  2937\n",
+       "vehicle_class                2937\n",
+       "total_claim_amount           2937\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1[\"customer_lifetime_value\"] = df1[\"customer_lifetime_value\"].str.strip(\"%\")\n",
+    "df1[\"customer_lifetime_value\"] = pd.to_numeric(df1[\"customer_lifetime_value\"], errors=\"coerce\")\n",
+    "df1.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "17a4ff8c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1[\"number_of_open_complaints\"] = df1[\"number_of_open_complaints\"].str.split(\"/\", expand=True)[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "fb710d08",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                       0\n",
+       "state                          0\n",
+       "gender                       117\n",
+       "education                      0\n",
+       "customer_lifetime_value        3\n",
+       "income                         0\n",
+       "monthly_premium_auto           0\n",
+       "number_of_open_complaints      0\n",
+       "policy_type                    0\n",
+       "vehicle_class                  0\n",
+       "total_claim_amount             0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1 = df1.dropna(how=\"all\")\n",
+    "df1.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "0315ffe2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                     0\n",
+       "state                        0\n",
+       "gender                       0\n",
+       "education                    0\n",
+       "customer_lifetime_value      0\n",
+       "income                       0\n",
+       "monthly_premium_auto         0\n",
+       "number_of_open_complaints    0\n",
+       "policy_type                  0\n",
+       "vehicle_class                0\n",
+       "total_claim_amount           0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1[\"gender\"] = df1[\"gender\"].fillna(\"unknown\")\n",
+    "df1[\"customer_lifetime_value\"] = df1[\"customer_lifetime_value\"].fillna(0)\n",
+    "df1.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "6773cc52",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>unknown</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1000.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>2.704934</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>1131.464935</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>48767.0</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>566.472247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>529.881344</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>M</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>36357.0</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>17.269323</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1066</th>\n",
+       "      <td>TM65736</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>305955.03</td>\n",
+       "      <td>38644.0</td>\n",
+       "      <td>78.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>361.455219</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1067</th>\n",
+       "      <td>VJ51327</td>\n",
+       "      <td>Cali</td>\n",
+       "      <td>F</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>2031499.76</td>\n",
+       "      <td>63209.0</td>\n",
+       "      <td>102.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>207.320041</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1068</th>\n",
+       "      <td>GS98873</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>323912.47</td>\n",
+       "      <td>16061.0</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>633.600000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1069</th>\n",
+       "      <td>CW49887</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>462680.11</td>\n",
+       "      <td>79487.0</td>\n",
+       "      <td>114.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>547.200000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1070</th>\n",
+       "      <td>MY31220</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>899704.02</td>\n",
+       "      <td>54230.0</td>\n",
+       "      <td>112.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>537.600000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1071 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state   gender             education  \\\n",
+       "0     RB50392  Washington  unknown                Master   \n",
+       "1     QZ44356     Arizona        F              Bachelor   \n",
+       "2     AI49188      Nevada        F              Bachelor   \n",
+       "3     WW63253  California        M              Bachelor   \n",
+       "4     GA49547  Washington        M  High School or Below   \n",
+       "...       ...         ...      ...                   ...   \n",
+       "1066  TM65736      Oregon        M                Master   \n",
+       "1067  VJ51327        Cali        F  High School or Below   \n",
+       "1068  GS98873     Arizona        F              Bachelor   \n",
+       "1069  CW49887  California        F                Master   \n",
+       "1070  MY31220  California        F               College   \n",
+       "\n",
+       "      customer_lifetime_value   income  monthly_premium_auto  \\\n",
+       "0                        0.00      0.0                1000.0   \n",
+       "1                   697953.59      0.0                  94.0   \n",
+       "2                  1288743.17  48767.0                 108.0   \n",
+       "3                   764586.18      0.0                 106.0   \n",
+       "4                   536307.65  36357.0                  68.0   \n",
+       "...                       ...      ...                   ...   \n",
+       "1066                305955.03  38644.0                  78.0   \n",
+       "1067               2031499.76  63209.0                 102.0   \n",
+       "1068                323912.47  16061.0                  88.0   \n",
+       "1069                462680.11  79487.0                 114.0   \n",
+       "1070                899704.02  54230.0                 112.0   \n",
+       "\n",
+       "     number_of_open_complaints     policy_type  vehicle_class  \\\n",
+       "0                            0   Personal Auto  Four-Door Car   \n",
+       "1                            0   Personal Auto  Four-Door Car   \n",
+       "2                            0   Personal Auto   Two-Door Car   \n",
+       "3                            0  Corporate Auto            SUV   \n",
+       "4                            0   Personal Auto  Four-Door Car   \n",
+       "...                        ...             ...            ...   \n",
+       "1066                         1   Personal Auto  Four-Door Car   \n",
+       "1067                         2   Personal Auto            SUV   \n",
+       "1068                         0   Personal Auto  Four-Door Car   \n",
+       "1069                         0    Special Auto            SUV   \n",
+       "1070                         0   Personal Auto   Two-Door Car   \n",
+       "\n",
+       "      total_claim_amount  \n",
+       "0               2.704934  \n",
+       "1            1131.464935  \n",
+       "2             566.472247  \n",
+       "3             529.881344  \n",
+       "4              17.269323  \n",
+       "...                  ...  \n",
+       "1066          361.455219  \n",
+       "1067          207.320041  \n",
+       "1068          633.600000  \n",
+       "1069          547.200000  \n",
+       "1070          537.600000  \n",
+       "\n",
+       "[1071 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "94604f47",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_columns = [\"gender\", \"education\", \"policy_type\", \"vehicle_class\", \"state\"]\n",
+    "for column in text_columns:\n",
+    "    df1[column] = df1[column].str.lower().str.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "49420406",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>unknown</td>\n",
+       "      <td>master</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1000.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>2.704934</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>f</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>1131.464935</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>nevada</td>\n",
+       "      <td>f</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>48767.0</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "      <td>566.472247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>california</td>\n",
+       "      <td>m</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>suv</td>\n",
+       "      <td>529.881344</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>m</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>36357.0</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>17.269323</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1066</th>\n",
+       "      <td>TM65736</td>\n",
+       "      <td>oregon</td>\n",
+       "      <td>m</td>\n",
+       "      <td>master</td>\n",
+       "      <td>305955.03</td>\n",
+       "      <td>38644.0</td>\n",
+       "      <td>78.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>361.455219</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1067</th>\n",
+       "      <td>VJ51327</td>\n",
+       "      <td>cali</td>\n",
+       "      <td>f</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>2031499.76</td>\n",
+       "      <td>63209.0</td>\n",
+       "      <td>102.0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>suv</td>\n",
+       "      <td>207.320041</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1068</th>\n",
+       "      <td>GS98873</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>f</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>323912.47</td>\n",
+       "      <td>16061.0</td>\n",
+       "      <td>88.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>633.600000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1069</th>\n",
+       "      <td>CW49887</td>\n",
+       "      <td>california</td>\n",
+       "      <td>f</td>\n",
+       "      <td>master</td>\n",
+       "      <td>462680.11</td>\n",
+       "      <td>79487.0</td>\n",
+       "      <td>114.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>special auto</td>\n",
+       "      <td>suv</td>\n",
+       "      <td>547.200000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1070</th>\n",
+       "      <td>MY31220</td>\n",
+       "      <td>california</td>\n",
+       "      <td>f</td>\n",
+       "      <td>college</td>\n",
+       "      <td>899704.02</td>\n",
+       "      <td>54230.0</td>\n",
+       "      <td>112.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "      <td>537.600000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1071 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state   gender             education  \\\n",
+       "0     RB50392  washington  unknown                master   \n",
+       "1     QZ44356     arizona        f              bachelor   \n",
+       "2     AI49188      nevada        f              bachelor   \n",
+       "3     WW63253  california        m              bachelor   \n",
+       "4     GA49547  washington        m  high school or below   \n",
+       "...       ...         ...      ...                   ...   \n",
+       "1066  TM65736      oregon        m                master   \n",
+       "1067  VJ51327        cali        f  high school or below   \n",
+       "1068  GS98873     arizona        f              bachelor   \n",
+       "1069  CW49887  california        f                master   \n",
+       "1070  MY31220  california        f               college   \n",
+       "\n",
+       "      customer_lifetime_value   income  monthly_premium_auto  \\\n",
+       "0                        0.00      0.0                1000.0   \n",
+       "1                   697953.59      0.0                  94.0   \n",
+       "2                  1288743.17  48767.0                 108.0   \n",
+       "3                   764586.18      0.0                 106.0   \n",
+       "4                   536307.65  36357.0                  68.0   \n",
+       "...                       ...      ...                   ...   \n",
+       "1066                305955.03  38644.0                  78.0   \n",
+       "1067               2031499.76  63209.0                 102.0   \n",
+       "1068                323912.47  16061.0                  88.0   \n",
+       "1069                462680.11  79487.0                 114.0   \n",
+       "1070                899704.02  54230.0                 112.0   \n",
+       "\n",
+       "     number_of_open_complaints     policy_type  vehicle_class  \\\n",
+       "0                            0   personal auto  four-door car   \n",
+       "1                            0   personal auto  four-door car   \n",
+       "2                            0   personal auto   two-door car   \n",
+       "3                            0  corporate auto            suv   \n",
+       "4                            0   personal auto  four-door car   \n",
+       "...                        ...             ...            ...   \n",
+       "1066                         1   personal auto  four-door car   \n",
+       "1067                         2   personal auto            suv   \n",
+       "1068                         0   personal auto  four-door car   \n",
+       "1069                         0    special auto            suv   \n",
+       "1070                         0   personal auto   two-door car   \n",
+       "\n",
+       "      total_claim_amount  \n",
+       "0               2.704934  \n",
+       "1            1131.464935  \n",
+       "2             566.472247  \n",
+       "3             529.881344  \n",
+       "4              17.269323  \n",
+       "...                  ...  \n",
+       "1066          361.455219  \n",
+       "1067          207.320041  \n",
+       "1068          633.600000  \n",
+       "1069          547.200000  \n",
+       "1070          537.600000  \n",
+       "\n",
+       "[1071 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "688c5dbc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['unknown', 'female', 'male'], dtype=object)"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1[\"gender\"] = df1[\"gender\"].replace({\"m\": \"male\", \"f\": \"female\", \"femal\": \"female\"})\n",
+    "df1[\"gender\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "e8d2c1e0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['four-door car', 'two-door car', 'suv', 'luxury'], dtype=object)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1[\"vehicle_class\"] = df1[\"vehicle_class\"].replace({\"luxury suv\": \"luxury\", \"luxury car\": \"luxury\", \"sports car\": \"luxury\", \"luxery\": \"luxury\" })\n",
+    "df1[\"vehicle_class\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "e9c343c2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['washington', 'arizona', 'nevada', 'california', 'oregon'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1[\"state\"] = df1[\"state\"].replace({\"cali\": \"california\", \"az\": \"arizona\", \"wa\": \"washington\"})\n",
+    "df1[\"state\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "bae40876",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['master', 'bachelor', 'high school or below', 'college', 'doctor'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#df1[\"education\"].unique()\n",
+    "df1[\"education\"] = df1[\"education\"].replace({\"bachelors\": \"bachelor\"})\n",
+    "df1[\"education\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "3ce9d3ac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['personal auto', 'corporate auto', 'special auto'], dtype=object)"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1[\"policy_type\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "8f1cc493",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df1[\"income\"] = df1[\"income\"].astype(int)\n",
+    "df1[\"monthly_premium_auto\"] = df1[\"monthly_premium_auto\"].astype(int)\n",
+    "df1[\"number_of_open_complaints\"] = df1[\"number_of_open_complaints\"].astype(int)\n",
+    "df1[\"customer_lifetime_value\"] = df1[\"customer_lifetime_value\"].round(2)\n",
+    "df1[\"total_claim_amount\"] = df1[\"total_claim_amount\"].round(2)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "9d7e96f8",
+   "metadata": {},
+   "source": [
+    "# Cleaning df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "7d38baae",
+   "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>Customer</th>\n",
+       "      <th>ST</th>\n",
+       "      <th>GENDER</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>Monthly Premium Auto</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>GS98873</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>323912.47%</td>\n",
+       "      <td>16061</td>\n",
+       "      <td>88</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>633.600000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>CW49887</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>462680.11%</td>\n",
+       "      <td>79487</td>\n",
+       "      <td>114</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>547.200000</td>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>MY31220</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>899704.02%</td>\n",
+       "      <td>54230</td>\n",
+       "      <td>112</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>537.600000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>UH35128</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2580706.30%</td>\n",
+       "      <td>71210</td>\n",
+       "      <td>214</td>\n",
+       "      <td>1/1/00</td>\n",
+       "      <td>1027.200000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Luxury Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>WH52799</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>380812.21%</td>\n",
+       "      <td>94903</td>\n",
+       "      <td>94</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>451.200000</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>991</th>\n",
+       "      <td>HV85198</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>847141.75%</td>\n",
+       "      <td>63513</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>185.667213</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>992</th>\n",
+       "      <td>BS91566</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>543121.91%</td>\n",
+       "      <td>58161</td>\n",
+       "      <td>68</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>140.747286</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>993</th>\n",
+       "      <td>IL40123</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>568964.41%</td>\n",
+       "      <td>83640</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>471.050488</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>994</th>\n",
+       "      <td>MY32149</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>368672.38%</td>\n",
+       "      <td>0</td>\n",
+       "      <td>96</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>28.460568</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>995</th>\n",
+       "      <td>SA91515</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>399258.39%</td>\n",
+       "      <td>0</td>\n",
+       "      <td>111</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>700.349052</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>996 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Customer          ST GENDER Education Customer Lifetime Value  Income  \\\n",
+       "0    GS98873     Arizona      F  Bachelor              323912.47%   16061   \n",
+       "1    CW49887  California      F    Master              462680.11%   79487   \n",
+       "2    MY31220  California      F   College              899704.02%   54230   \n",
+       "3    UH35128      Oregon      F   College             2580706.30%   71210   \n",
+       "4    WH52799     Arizona      F   College              380812.21%   94903   \n",
+       "..       ...         ...    ...       ...                     ...     ...   \n",
+       "991  HV85198     Arizona      M    Master              847141.75%   63513   \n",
+       "992  BS91566     Arizona      F   College              543121.91%   58161   \n",
+       "993  IL40123      Nevada      F   College              568964.41%   83640   \n",
+       "994  MY32149  California      F    Master              368672.38%       0   \n",
+       "995  SA91515  California      M  Bachelor              399258.39%       0   \n",
+       "\n",
+       "     Monthly Premium Auto Number of Open Complaints  Total Claim Amount  \\\n",
+       "0                      88                    1/0/00          633.600000   \n",
+       "1                     114                    1/0/00          547.200000   \n",
+       "2                     112                    1/0/00          537.600000   \n",
+       "3                     214                    1/1/00         1027.200000   \n",
+       "4                      94                    1/0/00          451.200000   \n",
+       "..                    ...                       ...                 ...   \n",
+       "991                    70                    1/0/00          185.667213   \n",
+       "992                    68                    1/0/00          140.747286   \n",
+       "993                    70                    1/0/00          471.050488   \n",
+       "994                    96                    1/0/00           28.460568   \n",
+       "995                   111                    1/0/00          700.349052   \n",
+       "\n",
+       "        Policy Type  Vehicle Class  \n",
+       "0     Personal Auto  Four-Door Car  \n",
+       "1      Special Auto            SUV  \n",
+       "2     Personal Auto   Two-Door Car  \n",
+       "3     Personal Auto     Luxury Car  \n",
+       "4    Corporate Auto   Two-Door Car  \n",
+       "..              ...            ...  \n",
+       "991   Personal Auto  Four-Door Car  \n",
+       "992  Corporate Auto  Four-Door Car  \n",
+       "993  Corporate Auto   Two-Door Car  \n",
+       "994   Personal Auto   Two-Door Car  \n",
+       "995   Personal Auto            SUV  \n",
+       "\n",
+       "[996 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "096441e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2.columns = df2.columns.str.lower()\n",
+    "df2.columns = df2.columns.str.replace(\" \", \"_\")\n",
+    "df2.rename(columns={\"st\":\"state\"}, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "2a6d8955",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                     0\n",
+       "state                        0\n",
+       "gender                       5\n",
+       "education                    0\n",
+       "customer_lifetime_value      0\n",
+       "income                       0\n",
+       "monthly_premium_auto         0\n",
+       "number_of_open_complaints    0\n",
+       "total_claim_amount           0\n",
+       "policy_type                  0\n",
+       "vehicle_class                0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"customer_lifetime_value\"] = df2[\"customer_lifetime_value\"].str.strip(\"%\")\n",
+    "df2[\"customer_lifetime_value\"] = pd.to_numeric(df1[\"customer_lifetime_value\"], errors=\"coerce\")\n",
+    "df2.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "0ddeb913",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2[\"gender\"] = df2[\"gender\"].fillna(\"unknown\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "5167588d",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>GS98873</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>16061</td>\n",
+       "      <td>88</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>633.600000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>CW49887</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>79487</td>\n",
+       "      <td>114</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>547.200000</td>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>MY31220</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>54230</td>\n",
+       "      <td>112</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>537.600000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>UH35128</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>71210</td>\n",
+       "      <td>214</td>\n",
+       "      <td>1/1/00</td>\n",
+       "      <td>1027.200000</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Luxury Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>WH52799</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>94903</td>\n",
+       "      <td>94</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>451.200000</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>991</th>\n",
+       "      <td>HV85198</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>2153133.28</td>\n",
+       "      <td>63513</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>185.667213</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>992</th>\n",
+       "      <td>BS91566</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>1262283.27</td>\n",
+       "      <td>58161</td>\n",
+       "      <td>68</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>140.747286</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>993</th>\n",
+       "      <td>IL40123</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>F</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2017196.15</td>\n",
+       "      <td>83640</td>\n",
+       "      <td>70</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>471.050488</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>994</th>\n",
+       "      <td>MY32149</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>1646436.59</td>\n",
+       "      <td>0</td>\n",
+       "      <td>96</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>28.460568</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>995</th>\n",
+       "      <td>SA91515</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>559538.99</td>\n",
+       "      <td>0</td>\n",
+       "      <td>111</td>\n",
+       "      <td>1/0/00</td>\n",
+       "      <td>700.349052</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>996 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    customer       state gender education  customer_lifetime_value  income  \\\n",
+       "0    GS98873     Arizona      F  Bachelor                     0.00   16061   \n",
+       "1    CW49887  California      F    Master                697953.59   79487   \n",
+       "2    MY31220  California      F   College               1288743.17   54230   \n",
+       "3    UH35128      Oregon      F   College                764586.18   71210   \n",
+       "4    WH52799     Arizona      F   College                536307.65   94903   \n",
+       "..       ...         ...    ...       ...                      ...     ...   \n",
+       "991  HV85198     Arizona      M    Master               2153133.28   63513   \n",
+       "992  BS91566     Arizona      F   College               1262283.27   58161   \n",
+       "993  IL40123      Nevada      F   College               2017196.15   83640   \n",
+       "994  MY32149  California      F    Master               1646436.59       0   \n",
+       "995  SA91515  California      M  Bachelor                559538.99       0   \n",
+       "\n",
+       "     monthly_premium_auto number_of_open_complaints  total_claim_amount  \\\n",
+       "0                      88                    1/0/00          633.600000   \n",
+       "1                     114                    1/0/00          547.200000   \n",
+       "2                     112                    1/0/00          537.600000   \n",
+       "3                     214                    1/1/00         1027.200000   \n",
+       "4                      94                    1/0/00          451.200000   \n",
+       "..                    ...                       ...                 ...   \n",
+       "991                    70                    1/0/00          185.667213   \n",
+       "992                    68                    1/0/00          140.747286   \n",
+       "993                    70                    1/0/00          471.050488   \n",
+       "994                    96                    1/0/00           28.460568   \n",
+       "995                   111                    1/0/00          700.349052   \n",
+       "\n",
+       "        policy_type  vehicle_class  \n",
+       "0     Personal Auto  Four-Door Car  \n",
+       "1      Special Auto            SUV  \n",
+       "2     Personal Auto   Two-Door Car  \n",
+       "3     Personal Auto     Luxury Car  \n",
+       "4    Corporate Auto   Two-Door Car  \n",
+       "..              ...            ...  \n",
+       "991   Personal Auto  Four-Door Car  \n",
+       "992  Corporate Auto  Four-Door Car  \n",
+       "993  Corporate Auto   Two-Door Car  \n",
+       "994   Personal Auto   Two-Door Car  \n",
+       "995   Personal Auto            SUV  \n",
+       "\n",
+       "[996 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "daa64953",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_columns = [\"gender\", \"education\", \"policy_type\", \"vehicle_class\", \"state\"]\n",
+    "for column in text_columns:\n",
+    "    df2[column] = df1[column].str.lower().str.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "c3394711",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['washington', 'arizona', 'nevada', 'california', 'oregon'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"state\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "3198eaaa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['unknown', 'female', 'male'], dtype=object)"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"gender\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "301f87ce",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['master', 'bachelor', 'high school or below', 'college', 'doctor'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"education\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "26e27e09",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['personal auto', 'corporate auto', 'special auto'], dtype=object)"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"policy_type\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "88857119",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['four-door car', 'two-door car', 'suv', 'luxury'], dtype=object)"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"vehicle_class\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "30f064b1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['1/0/00', '1/1/00', '1/3/00', '1/5/00', '1/2/00', '1/4/00'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"number_of_open_complaints\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "845e7522",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2[\"number_of_open_complaints\"] = df2[\"number_of_open_complaints\"].str.split(\"/\", expand=True)[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "7af46c3d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['0', '1', '3', '5', '2', '4'], dtype=object)"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2[\"number_of_open_complaints\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "8c40edf7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2[\"number_of_open_complaints\"] = df2[\"number_of_open_complaints\"].astype(int)\n",
+    "df2[\"customer_lifetime_value\"] = df2[\"customer_lifetime_value\"].round(2)\n",
+    "df2[\"total_claim_amount\"] = df2[\"total_claim_amount\"].round(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "e2174417",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>GS98873</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>unknown</td>\n",
+       "      <td>master</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>16061</td>\n",
+       "      <td>88</td>\n",
+       "      <td>0</td>\n",
+       "      <td>633.60</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>CW49887</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>79487</td>\n",
+       "      <td>114</td>\n",
+       "      <td>0</td>\n",
+       "      <td>547.20</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>MY31220</td>\n",
+       "      <td>nevada</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>54230</td>\n",
+       "      <td>112</td>\n",
+       "      <td>0</td>\n",
+       "      <td>537.60</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>UH35128</td>\n",
+       "      <td>california</td>\n",
+       "      <td>male</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>71210</td>\n",
+       "      <td>214</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1027.20</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>suv</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>WH52799</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>male</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>94903</td>\n",
+       "      <td>94</td>\n",
+       "      <td>0</td>\n",
+       "      <td>451.20</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>991</th>\n",
+       "      <td>HV85198</td>\n",
+       "      <td>oregon</td>\n",
+       "      <td>female</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>2153133.28</td>\n",
+       "      <td>63513</td>\n",
+       "      <td>70</td>\n",
+       "      <td>0</td>\n",
+       "      <td>185.67</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>992</th>\n",
+       "      <td>BS91566</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>male</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>1262283.27</td>\n",
+       "      <td>58161</td>\n",
+       "      <td>68</td>\n",
+       "      <td>0</td>\n",
+       "      <td>140.75</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>luxury</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>993</th>\n",
+       "      <td>IL40123</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>male</td>\n",
+       "      <td>doctor</td>\n",
+       "      <td>2017196.15</td>\n",
+       "      <td>83640</td>\n",
+       "      <td>70</td>\n",
+       "      <td>0</td>\n",
+       "      <td>471.05</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>994</th>\n",
+       "      <td>MY32149</td>\n",
+       "      <td>california</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>1646436.59</td>\n",
+       "      <td>0</td>\n",
+       "      <td>96</td>\n",
+       "      <td>0</td>\n",
+       "      <td>28.46</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>suv</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>995</th>\n",
+       "      <td>SA91515</td>\n",
+       "      <td>oregon</td>\n",
+       "      <td>female</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>559538.99</td>\n",
+       "      <td>0</td>\n",
+       "      <td>111</td>\n",
+       "      <td>0</td>\n",
+       "      <td>700.35</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>996 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    customer       state   gender             education  \\\n",
+       "0    GS98873  washington  unknown                master   \n",
+       "1    CW49887     arizona   female              bachelor   \n",
+       "2    MY31220      nevada   female              bachelor   \n",
+       "3    UH35128  california     male              bachelor   \n",
+       "4    WH52799  washington     male  high school or below   \n",
+       "..       ...         ...      ...                   ...   \n",
+       "991  HV85198      oregon   female  high school or below   \n",
+       "992  BS91566     arizona     male              bachelor   \n",
+       "993  IL40123     arizona     male                doctor   \n",
+       "994  MY32149  california   female              bachelor   \n",
+       "995  SA91515      oregon   female  high school or below   \n",
+       "\n",
+       "     customer_lifetime_value  income  monthly_premium_auto  \\\n",
+       "0                       0.00   16061                    88   \n",
+       "1                  697953.59   79487                   114   \n",
+       "2                 1288743.17   54230                   112   \n",
+       "3                  764586.18   71210                   214   \n",
+       "4                  536307.65   94903                    94   \n",
+       "..                       ...     ...                   ...   \n",
+       "991               2153133.28   63513                    70   \n",
+       "992               1262283.27   58161                    68   \n",
+       "993               2017196.15   83640                    70   \n",
+       "994               1646436.59       0                    96   \n",
+       "995                559538.99       0                   111   \n",
+       "\n",
+       "     number_of_open_complaints  total_claim_amount     policy_type  \\\n",
+       "0                            0              633.60   personal auto   \n",
+       "1                            0              547.20   personal auto   \n",
+       "2                            0              537.60   personal auto   \n",
+       "3                            1             1027.20  corporate auto   \n",
+       "4                            0              451.20   personal auto   \n",
+       "..                         ...                 ...             ...   \n",
+       "991                          0              185.67   personal auto   \n",
+       "992                          0              140.75   personal auto   \n",
+       "993                          0              471.05   personal auto   \n",
+       "994                          0               28.46   personal auto   \n",
+       "995                          0              700.35   personal auto   \n",
+       "\n",
+       "     vehicle_class  \n",
+       "0    four-door car  \n",
+       "1    four-door car  \n",
+       "2     two-door car  \n",
+       "3              suv  \n",
+       "4    four-door car  \n",
+       "..             ...  \n",
+       "991  four-door car  \n",
+       "992         luxury  \n",
+       "993   two-door car  \n",
+       "994            suv  \n",
+       "995  four-door car  \n",
+       "\n",
+       "[996 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "54b16d91",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                     0\n",
+       "state                        0\n",
+       "gender                       0\n",
+       "education                    0\n",
+       "customer_lifetime_value      0\n",
+       "income                       0\n",
+       "monthly_premium_auto         0\n",
+       "number_of_open_complaints    0\n",
+       "total_claim_amount           0\n",
+       "policy_type                  0\n",
+       "vehicle_class                0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a7fab3b",
+   "metadata": {},
+   "source": [
+    "# Cleaning df3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "377f69cb",
+   "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>Customer</th>\n",
+       "      <th>State</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>Monthly Premium Auto</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>SA25987</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>3479.137523</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>104</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>499.200000</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>TB86706</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>2502.637401</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>66</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>3.468912</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ZL73902</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>3265.156348</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>F</td>\n",
+       "      <td>25820</td>\n",
+       "      <td>82</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>393.600000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>KX23516</td>\n",
+       "      <td>California</td>\n",
+       "      <td>4455.843406</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>F</td>\n",
+       "      <td>0</td>\n",
+       "      <td>121</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>699.615192</td>\n",
+       "      <td>SUV</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>FN77294</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7704.958480</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>M</td>\n",
+       "      <td>30366</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>484.800000</td>\n",
+       "      <td>SUV</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7065</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>California</td>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>M</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>73</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7066</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>College</td>\n",
+       "      <td>F</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>79</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7067</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>California</td>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>85</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7068</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>College</td>\n",
+       "      <td>M</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>96</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7069</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>College</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>7070 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     Customer       State  Customer Lifetime Value             Education  \\\n",
+       "0     SA25987  Washington              3479.137523  High School or Below   \n",
+       "1     TB86706     Arizona              2502.637401                Master   \n",
+       "2     ZL73902      Nevada              3265.156348              Bachelor   \n",
+       "3     KX23516  California              4455.843406  High School or Below   \n",
+       "4     FN77294  California              7704.958480  High School or Below   \n",
+       "...       ...         ...                      ...                   ...   \n",
+       "7065  LA72316  California             23405.987980              Bachelor   \n",
+       "7066  PK87824  California              3096.511217               College   \n",
+       "7067  TD14365  California              8163.890428              Bachelor   \n",
+       "7068  UP19263  California              7524.442436               College   \n",
+       "7069  Y167826  California              2611.836866               College   \n",
+       "\n",
+       "     Gender  Income  Monthly Premium Auto  Number of Open Complaints  \\\n",
+       "0         M       0                   104                          0   \n",
+       "1         M       0                    66                          0   \n",
+       "2         F   25820                    82                          0   \n",
+       "3         F       0                   121                          0   \n",
+       "4         M   30366                   101                          2   \n",
+       "...     ...     ...                   ...                        ...   \n",
+       "7065      M   71941                    73                          0   \n",
+       "7066      F   21604                    79                          0   \n",
+       "7067      M       0                    85                          3   \n",
+       "7068      M   21941                    96                          0   \n",
+       "7069      M       0                    77                          0   \n",
+       "\n",
+       "         Policy Type  Total Claim Amount  Vehicle Class  \n",
+       "0      Personal Auto          499.200000   Two-Door Car  \n",
+       "1      Personal Auto            3.468912   Two-Door Car  \n",
+       "2      Personal Auto          393.600000  Four-Door Car  \n",
+       "3      Personal Auto          699.615192            SUV  \n",
+       "4      Personal Auto          484.800000            SUV  \n",
+       "...              ...                 ...            ...  \n",
+       "7065   Personal Auto          198.234764  Four-Door Car  \n",
+       "7066  Corporate Auto          379.200000  Four-Door Car  \n",
+       "7067  Corporate Auto          790.784983  Four-Door Car  \n",
+       "7068   Personal Auto          691.200000  Four-Door Car  \n",
+       "7069  Corporate Auto          369.600000   Two-Door Car  \n",
+       "\n",
+       "[7070 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "17283368",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Customer', 'State', 'Customer Lifetime Value', 'Education', 'Gender',\n",
+       "       'Income', 'Monthly Premium Auto', 'Number of Open Complaints',\n",
+       "       'Policy Type', 'Total Claim Amount', 'Vehicle Class'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "c964a69b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'customer_lifetime_value', 'education', 'gender',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'policy_type', 'total_claim_amount', 'vehicle_class'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3.columns = (df3.columns.str.strip().str.lower().str.replace(\" \", \"_\"))\n",
+    "df3 = df3.rename(columns={\"st\": \"state\"})\n",
+    "df3.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "eefd8d37",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_columns = [\"gender\", \"education\", \"policy_type\", \"vehicle_class\", \"state\"]\n",
+    "for column in text_columns:\n",
+    "    df3[column] = df3[column].str.lower().str.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "d1005163",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>education</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>SA25987</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>3479.137523</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>m</td>\n",
+       "      <td>0</td>\n",
+       "      <td>104</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>499.200000</td>\n",
+       "      <td>two-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>TB86706</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>2502.637401</td>\n",
+       "      <td>master</td>\n",
+       "      <td>m</td>\n",
+       "      <td>0</td>\n",
+       "      <td>66</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>3.468912</td>\n",
+       "      <td>two-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ZL73902</td>\n",
+       "      <td>nevada</td>\n",
+       "      <td>3265.156348</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>f</td>\n",
+       "      <td>25820</td>\n",
+       "      <td>82</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>393.600000</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>KX23516</td>\n",
+       "      <td>california</td>\n",
+       "      <td>4455.843406</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>f</td>\n",
+       "      <td>0</td>\n",
+       "      <td>121</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>699.615192</td>\n",
+       "      <td>suv</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>FN77294</td>\n",
+       "      <td>california</td>\n",
+       "      <td>7704.958480</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>m</td>\n",
+       "      <td>30366</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>484.800000</td>\n",
+       "      <td>suv</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7065</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>california</td>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>73</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7066</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>california</td>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>college</td>\n",
+       "      <td>f</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>79</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7067</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>california</td>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>0</td>\n",
+       "      <td>85</td>\n",
+       "      <td>3</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7068</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>california</td>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>college</td>\n",
+       "      <td>m</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>96</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>four-door car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7069</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>california</td>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>college</td>\n",
+       "      <td>m</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>two-door car</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>7070 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state  customer_lifetime_value             education  \\\n",
+       "0     SA25987  washington              3479.137523  high school or below   \n",
+       "1     TB86706     arizona              2502.637401                master   \n",
+       "2     ZL73902      nevada              3265.156348              bachelor   \n",
+       "3     KX23516  california              4455.843406  high school or below   \n",
+       "4     FN77294  california              7704.958480  high school or below   \n",
+       "...       ...         ...                      ...                   ...   \n",
+       "7065  LA72316  california             23405.987980              bachelor   \n",
+       "7066  PK87824  california              3096.511217               college   \n",
+       "7067  TD14365  california              8163.890428              bachelor   \n",
+       "7068  UP19263  california              7524.442436               college   \n",
+       "7069  Y167826  california              2611.836866               college   \n",
+       "\n",
+       "     gender  income  monthly_premium_auto  number_of_open_complaints  \\\n",
+       "0         m       0                   104                          0   \n",
+       "1         m       0                    66                          0   \n",
+       "2         f   25820                    82                          0   \n",
+       "3         f       0                   121                          0   \n",
+       "4         m   30366                   101                          2   \n",
+       "...     ...     ...                   ...                        ...   \n",
+       "7065      m   71941                    73                          0   \n",
+       "7066      f   21604                    79                          0   \n",
+       "7067      m       0                    85                          3   \n",
+       "7068      m   21941                    96                          0   \n",
+       "7069      m       0                    77                          0   \n",
+       "\n",
+       "         policy_type  total_claim_amount  vehicle_class  \n",
+       "0      personal auto          499.200000   two-door car  \n",
+       "1      personal auto            3.468912   two-door car  \n",
+       "2      personal auto          393.600000  four-door car  \n",
+       "3      personal auto          699.615192            suv  \n",
+       "4      personal auto          484.800000            suv  \n",
+       "...              ...                 ...            ...  \n",
+       "7065   personal auto          198.234764  four-door car  \n",
+       "7066  corporate auto          379.200000  four-door car  \n",
+       "7067  corporate auto          790.784983  four-door car  \n",
+       "7068   personal auto          691.200000  four-door car  \n",
+       "7069  corporate auto          369.600000   two-door car  \n",
+       "\n",
+       "[7070 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "48018657",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([3479.137523, 2502.637401, 3265.156348, ..., 8163.890428,\n",
+       "       7524.442436, 2611.836866])"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3[\"vehicle_class\"] = df3[\"vehicle_class\"].replace({\"luxury suv\": \"luxury\", \"luxury car\": \"luxury\", \"sports car\": \"luxury\", \"luxery\": \"luxury\" })\n",
+    "df3[\"customer_lifetime_value\"].unique()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "17ba33fe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df3[\"number_of_open_complaints\"] = df3[\"number_of_open_complaints\"].astype(int)\n",
+    "df3[\"customer_lifetime_value\"] = df3[\"customer_lifetime_value\"].round(2)\n",
+    "df3[\"total_claim_amount\"] = df3[\"total_claim_amount\"].round(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "6e6b8ca0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                     0\n",
+       "state                        0\n",
+       "customer_lifetime_value      0\n",
+       "education                    0\n",
+       "gender                       0\n",
+       "income                       0\n",
+       "monthly_premium_auto         0\n",
+       "number_of_open_complaints    0\n",
+       "policy_type                  0\n",
+       "total_claim_amount           0\n",
+       "vehicle_class                0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "95d6e7fa",
+   "metadata": {},
+   "source": [
+    "## Last checks before merging"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "41b9ddbc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'gender', 'education', 'customer_lifetime_value',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'policy_type', 'vehicle_class', 'total_claim_amount'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "8d871ec0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'gender', 'education', 'customer_lifetime_value',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'total_claim_amount', 'policy_type', 'vehicle_class'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "217fcbfa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'customer_lifetime_value', 'education', 'gender',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'policy_type', 'total_claim_amount', 'vehicle_class'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "af4e7429",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols = df1.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "2a68032b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = df2[cols]\n",
+    "df3 = df3[cols]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "c4afa62d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'gender', 'education', 'customer_lifetime_value',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'policy_type', 'vehicle_class', 'total_claim_amount'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "884587cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'gender', 'education', 'customer_lifetime_value',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'policy_type', 'vehicle_class', 'total_claim_amount'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "1473ee10",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'gender', 'education', 'customer_lifetime_value',\n",
+       "       'income', 'monthly_premium_auto', 'number_of_open_complaints',\n",
+       "       'policy_type', 'vehicle_class', 'total_claim_amount'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df3.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "c09a78a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "comb_df = pd.concat([df1, df2, df3], axis=0).reset_index(drop=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "6f49d6b9",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>unknown</td>\n",
+       "      <td>master</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>2.70</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>0</td>\n",
+       "      <td>94</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>1131.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>nevada</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>108</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "      <td>566.47</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>california</td>\n",
+       "      <td>male</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>0</td>\n",
+       "      <td>106</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>suv</td>\n",
+       "      <td>529.88</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>male</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>36357</td>\n",
+       "      <td>68</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>17.27</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>california</td>\n",
+       "      <td>m</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>23405.99</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>73</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>198.23</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>california</td>\n",
+       "      <td>f</td>\n",
+       "      <td>college</td>\n",
+       "      <td>3096.51</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>79</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>379.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9134</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>california</td>\n",
+       "      <td>m</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>8163.89</td>\n",
+       "      <td>0</td>\n",
+       "      <td>85</td>\n",
+       "      <td>3</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>790.78</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9135</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>california</td>\n",
+       "      <td>m</td>\n",
+       "      <td>college</td>\n",
+       "      <td>7524.44</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>96</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>691.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9136</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>california</td>\n",
+       "      <td>m</td>\n",
+       "      <td>college</td>\n",
+       "      <td>2611.84</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "      <td>369.60</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9137 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state   gender             education  \\\n",
+       "0     RB50392  washington  unknown                master   \n",
+       "1     QZ44356     arizona   female              bachelor   \n",
+       "2     AI49188      nevada   female              bachelor   \n",
+       "3     WW63253  california     male              bachelor   \n",
+       "4     GA49547  washington     male  high school or below   \n",
+       "...       ...         ...      ...                   ...   \n",
+       "9132  LA72316  california        m              bachelor   \n",
+       "9133  PK87824  california        f               college   \n",
+       "9134  TD14365  california        m              bachelor   \n",
+       "9135  UP19263  california        m               college   \n",
+       "9136  Y167826  california        m               college   \n",
+       "\n",
+       "      customer_lifetime_value  income  monthly_premium_auto  \\\n",
+       "0                        0.00       0                  1000   \n",
+       "1                   697953.59       0                    94   \n",
+       "2                  1288743.17   48767                   108   \n",
+       "3                   764586.18       0                   106   \n",
+       "4                   536307.65   36357                    68   \n",
+       "...                       ...     ...                   ...   \n",
+       "9132                 23405.99   71941                    73   \n",
+       "9133                  3096.51   21604                    79   \n",
+       "9134                  8163.89       0                    85   \n",
+       "9135                  7524.44   21941                    96   \n",
+       "9136                  2611.84       0                    77   \n",
+       "\n",
+       "      number_of_open_complaints     policy_type  vehicle_class  \\\n",
+       "0                             0   personal auto  four-door car   \n",
+       "1                             0   personal auto  four-door car   \n",
+       "2                             0   personal auto   two-door car   \n",
+       "3                             0  corporate auto            suv   \n",
+       "4                             0   personal auto  four-door car   \n",
+       "...                         ...             ...            ...   \n",
+       "9132                          0   personal auto  four-door car   \n",
+       "9133                          0  corporate auto  four-door car   \n",
+       "9134                          3  corporate auto  four-door car   \n",
+       "9135                          0   personal auto  four-door car   \n",
+       "9136                          0  corporate auto   two-door car   \n",
+       "\n",
+       "      total_claim_amount  \n",
+       "0                   2.70  \n",
+       "1                1131.46  \n",
+       "2                 566.47  \n",
+       "3                 529.88  \n",
+       "4                  17.27  \n",
+       "...                  ...  \n",
+       "9132              198.23  \n",
+       "9133              379.20  \n",
+       "9134              790.78  \n",
+       "9135              691.20  \n",
+       "9136              369.60  \n",
+       "\n",
+       "[9137 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 52,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "comb_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "f111a761",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(9137, 11)"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "comb_df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "0d8ddfd4",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>unknown</td>\n",
+       "      <td>master</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>2.70</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>arizona</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>0</td>\n",
+       "      <td>94</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>1131.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>nevada</td>\n",
+       "      <td>female</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>108</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>two-door car</td>\n",
+       "      <td>566.47</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>california</td>\n",
+       "      <td>male</td>\n",
+       "      <td>bachelor</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>0</td>\n",
+       "      <td>106</td>\n",
+       "      <td>0</td>\n",
+       "      <td>corporate auto</td>\n",
+       "      <td>suv</td>\n",
+       "      <td>529.88</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>washington</td>\n",
+       "      <td>male</td>\n",
+       "      <td>high school or below</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>36357</td>\n",
+       "      <td>68</td>\n",
+       "      <td>0</td>\n",
+       "      <td>personal auto</td>\n",
+       "      <td>four-door car</td>\n",
+       "      <td>17.27</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  customer       state   gender             education  \\\n",
+       "0  RB50392  washington  unknown                master   \n",
+       "1  QZ44356     arizona   female              bachelor   \n",
+       "2  AI49188      nevada   female              bachelor   \n",
+       "3  WW63253  california     male              bachelor   \n",
+       "4  GA49547  washington     male  high school or below   \n",
+       "\n",
+       "   customer_lifetime_value  income  monthly_premium_auto  \\\n",
+       "0                     0.00       0                  1000   \n",
+       "1                697953.59       0                    94   \n",
+       "2               1288743.17   48767                   108   \n",
+       "3                764586.18       0                   106   \n",
+       "4                536307.65   36357                    68   \n",
+       "\n",
+       "   number_of_open_complaints     policy_type  vehicle_class  \\\n",
+       "0                          0   personal auto  four-door car   \n",
+       "1                          0   personal auto  four-door car   \n",
+       "2                          0   personal auto   two-door car   \n",
+       "3                          0  corporate auto            suv   \n",
+       "4                          0   personal auto  four-door car   \n",
+       "\n",
+       "   total_claim_amount  \n",
+       "0                2.70  \n",
+       "1             1131.46  \n",
+       "2              566.47  \n",
+       "3              529.88  \n",
+       "4               17.27  "
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "comb_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "cb0dd902",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                      object\n",
+       "state                         object\n",
+       "gender                        object\n",
+       "education                     object\n",
+       "customer_lifetime_value      float64\n",
+       "income                         int64\n",
+       "monthly_premium_auto           int64\n",
+       "number_of_open_complaints      int64\n",
+       "policy_type                   object\n",
+       "vehicle_class                 object\n",
+       "total_claim_amount           float64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "comb_df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d4a003cd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d89b38da",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17742cba",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "31b8a9e7-7db9-4604-991b-ef6771603e57",
@@ -72,14 +3264,505 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 56,
    "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26",
    "metadata": {
     "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26"
    },
    "outputs": [],
    "source": [
-    "# Your code goes here"
+    "import pandas as pd\n",
+    "url = \"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/marketing_customer_analysis_clean.csv\"\n",
+    "df = pd.read_csv(url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "ffacfc9f",
+   "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>unnamed:_0</th>\n",
+       "      <th>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>response</th>\n",
+       "      <th>coverage</th>\n",
+       "      <th>education</th>\n",
+       "      <th>effective_to_date</th>\n",
+       "      <th>employmentstatus</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>...</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>policy</th>\n",
+       "      <th>renew_offer_type</th>\n",
+       "      <th>sales_channel</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>vehicle_size</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>month</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>DK49336</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>4809.216960</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-18</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>292.800000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>KX64629</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2228.525238</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-01-18</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>744.924331</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>LZ68649</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>14947.917300</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-10</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>480.000000</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>XL78013</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>22332.439460</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-01-11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>484.013411</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>QA50777</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>9025.067525</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-17</td>\n",
+       "      <td>Medical Leave</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>707.925645</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</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>10905</th>\n",
+       "      <td>10905</td>\n",
+       "      <td>FE99816</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>15563.369440</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-19</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>1214.400000</td>\n",
+       "      <td>Luxury Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10906</th>\n",
+       "      <td>10906</td>\n",
+       "      <td>KX53892</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>5259.444853</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-01-06</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>273.018929</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10907</th>\n",
+       "      <td>10907</td>\n",
+       "      <td>TL39050</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>23893.304100</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-06</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>381.306996</td>\n",
+       "      <td>Luxury SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10908</th>\n",
+       "      <td>10908</td>\n",
+       "      <td>WA60547</td>\n",
+       "      <td>California</td>\n",
+       "      <td>11971.977650</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-13</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>618.288849</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10909</th>\n",
+       "      <td>10909</td>\n",
+       "      <td>IV32877</td>\n",
+       "      <td>California</td>\n",
+       "      <td>6857.519928</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-08</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>1021.719397</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>10910 rows × 27 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       unnamed:_0 customer       state  customer_lifetime_value response  \\\n",
+       "0               0  DK49336     Arizona              4809.216960       No   \n",
+       "1               1  KX64629  California              2228.525238       No   \n",
+       "2               2  LZ68649  Washington             14947.917300       No   \n",
+       "3               3  XL78013      Oregon             22332.439460      Yes   \n",
+       "4               4  QA50777      Oregon              9025.067525       No   \n",
+       "...           ...      ...         ...                      ...      ...   \n",
+       "10905       10905  FE99816      Nevada             15563.369440       No   \n",
+       "10906       10906  KX53892      Oregon              5259.444853       No   \n",
+       "10907       10907  TL39050     Arizona             23893.304100       No   \n",
+       "10908       10908  WA60547  California             11971.977650       No   \n",
+       "10909       10909  IV32877  California              6857.519928       No   \n",
+       "\n",
+       "       coverage education effective_to_date employmentstatus gender  ...  \\\n",
+       "0         Basic   College        2011-02-18         Employed      M  ...   \n",
+       "1         Basic   College        2011-01-18       Unemployed      F  ...   \n",
+       "2         Basic  Bachelor        2011-02-10         Employed      M  ...   \n",
+       "3      Extended   College        2011-01-11         Employed      M  ...   \n",
+       "4       Premium  Bachelor        2011-01-17    Medical Leave      F  ...   \n",
+       "...         ...       ...               ...              ...    ...  ...   \n",
+       "10905   Premium  Bachelor        2011-01-19       Unemployed      F  ...   \n",
+       "10906     Basic   College        2011-01-06         Employed      F  ...   \n",
+       "10907  Extended  Bachelor        2011-02-06         Employed      F  ...   \n",
+       "10908   Premium   College        2011-02-13         Employed      F  ...   \n",
+       "10909     Basic  Bachelor        2011-01-08       Unemployed      M  ...   \n",
+       "\n",
+       "       number_of_policies     policy_type        policy  renew_offer_type  \\\n",
+       "0                       9  Corporate Auto  Corporate L3            Offer3   \n",
+       "1                       1   Personal Auto   Personal L3            Offer4   \n",
+       "2                       2   Personal Auto   Personal L3            Offer3   \n",
+       "3                       2  Corporate Auto  Corporate L3            Offer2   \n",
+       "4                       7   Personal Auto   Personal L2            Offer1   \n",
+       "...                   ...             ...           ...               ...   \n",
+       "10905                   7   Personal Auto   Personal L1            Offer3   \n",
+       "10906                   6   Personal Auto   Personal L3            Offer2   \n",
+       "10907                   2  Corporate Auto  Corporate L3            Offer1   \n",
+       "10908                   6   Personal Auto   Personal L1            Offer1   \n",
+       "10909                   3   Personal Auto   Personal L1            Offer4   \n",
+       "\n",
+       "       sales_channel  total_claim_amount  vehicle_class  vehicle_size  \\\n",
+       "0              Agent          292.800000  Four-Door Car       Medsize   \n",
+       "1        Call Center          744.924331  Four-Door Car       Medsize   \n",
+       "2        Call Center          480.000000            SUV       Medsize   \n",
+       "3             Branch          484.013411  Four-Door Car       Medsize   \n",
+       "4             Branch          707.925645  Four-Door Car       Medsize   \n",
+       "...              ...                 ...            ...           ...   \n",
+       "10905            Web         1214.400000     Luxury Car       Medsize   \n",
+       "10906         Branch          273.018929  Four-Door Car       Medsize   \n",
+       "10907            Web          381.306996     Luxury SUV       Medsize   \n",
+       "10908         Branch          618.288849            SUV       Medsize   \n",
+       "10909            Web         1021.719397            SUV       Medsize   \n",
+       "\n",
+       "      vehicle_type month  \n",
+       "0                A     2  \n",
+       "1                A     1  \n",
+       "2                A     2  \n",
+       "3                A     1  \n",
+       "4                A     1  \n",
+       "...            ...   ...  \n",
+       "10905            A     1  \n",
+       "10906            A     1  \n",
+       "10907            A     2  \n",
+       "10908            A     2  \n",
+       "10909            A     1  \n",
+       "\n",
+       "[10910 rows x 27 columns]"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "3f630515",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Arizona', 'California', 'Washington', 'Oregon', 'Nevada'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"state\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "7bfdd4f3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "unnamed:_0                         int64\n",
+       "customer                          object\n",
+       "state                             object\n",
+       "customer_lifetime_value          float64\n",
+       "response                          object\n",
+       "coverage                          object\n",
+       "education                         object\n",
+       "effective_to_date                 object\n",
+       "employmentstatus                  object\n",
+       "gender                            object\n",
+       "income                             int64\n",
+       "location_code                     object\n",
+       "marital_status                    object\n",
+       "monthly_premium_auto               int64\n",
+       "months_since_last_claim          float64\n",
+       "months_since_policy_inception      int64\n",
+       "number_of_open_complaints        float64\n",
+       "number_of_policies                 int64\n",
+       "policy_type                       object\n",
+       "policy                            object\n",
+       "renew_offer_type                  object\n",
+       "sales_channel                     object\n",
+       "total_claim_amount               float64\n",
+       "vehicle_class                     object\n",
+       "vehicle_size                      object\n",
+       "vehicle_type                      object\n",
+       "month                              int64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "a8cccc6e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Agent', 'Call Center', 'Branch', 'Web'], dtype=object)"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[\"sales_channel\"].unique()"
    ]
   },
   {
@@ -93,6 +3776,89 @@
     "Round the total revenue to 2 decimal points.  Analyze the resulting table to draw insights."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "68f9b972",
+   "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>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>sales_channel</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Agent</th>\n",
+       "      <td>1810226.82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Branch</th>\n",
+       "      <td>1301204.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Call Center</th>\n",
+       "      <td>926600.82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Web</th>\n",
+       "      <td>706600.04</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               total_claim_amount\n",
+       "sales_channel                    \n",
+       "Agent                  1810226.82\n",
+       "Branch                 1301204.00\n",
+       "Call Center             926600.82\n",
+       "Web                     706600.04"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pivot_sales_channel = df.pivot_table(index=\"sales_channel\", values=\"total_claim_amount\", aggfunc='sum')\n",
+    "pivot_sales_channel = pivot_sales_channel.round(2)\n",
+    "pivot_sales_channel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "900557e2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "640993b2-a291-436c-a34d-a551144f8196",
@@ -103,6 +3869,103 @@
     "2. Create a pivot table that shows the average customer lifetime value per gender and education level. Analyze the resulting table to draw insights."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "803a15bb",
+   "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>education</th>\n",
+       "      <th>Bachelor</th>\n",
+       "      <th>College</th>\n",
+       "      <th>Doctor</th>\n",
+       "      <th>High School or Below</th>\n",
+       "      <th>Master</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>gender</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>F</th>\n",
+       "      <td>7874.27</td>\n",
+       "      <td>7748.82</td>\n",
+       "      <td>7328.51</td>\n",
+       "      <td>8675.22</td>\n",
+       "      <td>8157.05</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>M</th>\n",
+       "      <td>7703.60</td>\n",
+       "      <td>8052.46</td>\n",
+       "      <td>7415.33</td>\n",
+       "      <td>8149.69</td>\n",
+       "      <td>8168.83</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "education  Bachelor  College   Doctor  High School or Below   Master\n",
+       "gender                                                              \n",
+       "F           7874.27  7748.82  7328.51               8675.22  8157.05\n",
+       "M           7703.60  8052.46  7415.33               8149.69  8168.83"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pivot_lifetime_value = df.pivot_table(index=\"gender\", columns=\"education\", values=\"customer_lifetime_value\",aggfunc=\"mean\")\n",
+    "pivot_lifetime_value = pivot_lifetime_value.round(2)\n",
+    "pivot_lifetime_value"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2a7cef6e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d64c57dc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "32c7f2e5-3d90-43e5-be33-9781b6069198",
@@ -130,7 +3993,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 63,
    "id": "3a069e0b-b400-470e-904d-d17582191be4",
    "metadata": {
     "id": "3a069e0b-b400-470e-904d-d17582191be4"
@@ -160,7 +4023,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,