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..f093a47
--- /dev/null
+++ b/.ipynb_checkpoints/lab-dw-data-structuring-and-combining-checkpoint.ipynb
@@ -0,0 +1,1442 @@
+{
+ "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": 2,
+   "id": "492d06e3-92c7-4105-ac72-536db98d3244",
+   "metadata": {
+    "id": "492d06e3-92c7-4105-ac72-536db98d3244"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(4008, 11) (996, 11) (7070, 11)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df1 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file1.csv\")\n",
+    "df2 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file2.csv\")\n",
+    "df3 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file3.csv\")\n",
+    "\n",
+    "print(df1.shape, df2.shape, df3.shape)\n",
+    "#df1.head()\n",
+    "#df2.head()\n",
+    "#df3.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d669a282-5584-49aa-9db6-39f49e0c9139",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(12074, 13)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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",
+       "      <th>State</th>\n",
+       "      <th>Gender</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  Customer          ST GENDER             Education Customer Lifetime Value  \\\n",
+       "0  RB50392  Washington    NaN                Master                     NaN   \n",
+       "1  QZ44356     Arizona      F              Bachelor              697953.59%   \n",
+       "2  AI49188      Nevada      F              Bachelor             1288743.17%   \n",
+       "3  WW63253  California      M              Bachelor              764586.18%   \n",
+       "4  GA49547  Washington      M  High School or Below              536307.65%   \n",
+       "\n",
+       "    Income  Monthly Premium Auto Number of Open Complaints     Policy Type  \\\n",
+       "0      0.0                1000.0                    1/0/00   Personal Auto   \n",
+       "1      0.0                  94.0                    1/0/00   Personal Auto   \n",
+       "2  48767.0                 108.0                    1/0/00   Personal Auto   \n",
+       "3      0.0                 106.0                    1/0/00  Corporate Auto   \n",
+       "4  36357.0                  68.0                    1/0/00   Personal Auto   \n",
+       "\n",
+       "   Vehicle Class  Total Claim Amount State Gender  \n",
+       "0  Four-Door Car            2.704934   NaN    NaN  \n",
+       "1  Four-Door Car         1131.464935   NaN    NaN  \n",
+       "2   Two-Door Car          566.472247   NaN    NaN  \n",
+       "3            SUV          529.881344   NaN    NaN  \n",
+       "4  Four-Door Car           17.269323   NaN    NaN  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.concat([df1, df2, df3], ignore_index=True)\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7ec71551-1d1e-42e7-857d-f6182c4de520",
+   "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', 'state',\n",
+       "       'gender'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns = (\n",
+    "    df.columns\n",
+    "    .str.replace(\"ST\", \"state\", regex=False)\n",
+    "    .str.lower()\n",
+    "    .str.strip()\n",
+    "    .str.replace(\" \", \"_\")\n",
+    ")\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "54754960-f4af-4415-bf02-f7934dc2b64e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['gender'] = df['gender'].replace({\n",
+    "    'F': 'F', 'Femal': 'F', 'Female': 'F', 'female': 'F',\n",
+    "    'M': 'M', 'Male': 'M', 'male': 'M'\n",
+    "})\n",
+    "\n",
+    "df['state'] = df['state'].replace({\n",
+    "    'AZ': 'Arizona',\n",
+    "    'Cali': 'California',\n",
+    "    'WA': 'Washington'\n",
+    "})\n",
+    "\n",
+    "df['education'] = df['education'].replace({'Bachelors': 'Bachelor'})\n",
+    "\n",
+    "df['customer_lifetime_value'] = (\n",
+    "    df['customer_lifetime_value']\n",
+    "    .astype(str)\n",
+    "    .str.replace('%', '', regex=False)\n",
+    "    .astype(float)\n",
+    ")\n",
+    "\n",
+    "df['vehicle_class'] = df['vehicle_class'].replace({\n",
+    "    'Sports Car': 'Luxury',\n",
+    "    'Luxury SUV': 'Luxury',\n",
+    "    'Luxury Car': 'Luxury'\n",
+    "})\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "5f348734-53b9-46c1-b1f5-90be4b327f48",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['number_of_open_complaints'] = (\n",
+    "    df['number_of_open_complaints']\n",
+    "    .astype(str)\n",
+    "    .str.split('/')\n",
+    "    .str[1]\n",
+    "    .astype(float)\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "8b5cee0d-fa6c-47aa-8df5-4a9ff3120651",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                      2937\n",
+       "state                        10007\n",
+       "gender                       10129\n",
+       "education                     2937\n",
+       "customer_lifetime_value       2944\n",
+       "income                        2937\n",
+       "monthly_premium_auto          2937\n",
+       "number_of_open_complaints    10007\n",
+       "policy_type                   2937\n",
+       "vehicle_class                 2937\n",
+       "total_claim_amount            2937\n",
+       "state                         5004\n",
+       "gender                        5004\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7aa802df-5ef5-4794-885a-ec3cb29c3aff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['number_of_open_complaints'] = df['number_of_open_complaints'].fillna(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d68dca87-ef24-4d10-85d3-d577d5bd9c11",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                      2937\n",
+       "state                        10007\n",
+       "gender                       10129\n",
+       "education                     2937\n",
+       "customer_lifetime_value       2944\n",
+       "income                        2937\n",
+       "monthly_premium_auto          2937\n",
+       "number_of_open_complaints        0\n",
+       "policy_type                   2937\n",
+       "vehicle_class                 2937\n",
+       "total_claim_amount            2937\n",
+       "state                         5004\n",
+       "gender                        5004\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "87a9b5cd-2464-4818-87e4-6e5ee153e91b",
+   "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",
+       "      <th>state</th>\n",
+       "      <th>gender</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>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>2.704934</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>6.979536e+05</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>1131.464935</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>1.288743e+06</td>\n",
+       "      <td>48767.0</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>566.472247</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>7.645862e+05</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>529.881344</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>5.363077e+05</td>\n",
+       "      <td>36357.0</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>17.269323</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2.340599e+04</td>\n",
+       "      <td>71941.0</td>\n",
+       "      <td>73.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>College</td>\n",
+       "      <td>3.096511e+03</td>\n",
+       "      <td>21604.0</td>\n",
+       "      <td>79.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>8.163890e+03</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>85.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>College</td>\n",
+       "      <td>7.524442e+03</td>\n",
+       "      <td>21941.0</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9134</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2.611837e+03</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>77.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9135 rows × 13 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state 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",
+       "9130  LA72316         NaN    NaN              Bachelor   \n",
+       "9131  PK87824         NaN    NaN               College   \n",
+       "9132  TD14365         NaN    NaN              Bachelor   \n",
+       "9133  UP19263         NaN    NaN               College   \n",
+       "9134  Y167826         NaN    NaN               College   \n",
+       "\n",
+       "      customer_lifetime_value   income  monthly_premium_auto  \\\n",
+       "0                         NaN      0.0                1000.0   \n",
+       "1                6.979536e+05      0.0                  94.0   \n",
+       "2                1.288743e+06  48767.0                 108.0   \n",
+       "3                7.645862e+05      0.0                 106.0   \n",
+       "4                5.363077e+05  36357.0                  68.0   \n",
+       "...                       ...      ...                   ...   \n",
+       "9130             2.340599e+04  71941.0                  73.0   \n",
+       "9131             3.096511e+03  21604.0                  79.0   \n",
+       "9132             8.163890e+03      0.0                  85.0   \n",
+       "9133             7.524442e+03  21941.0                  96.0   \n",
+       "9134             2.611837e+03      0.0                  77.0   \n",
+       "\n",
+       "      number_of_open_complaints     policy_type  vehicle_class  \\\n",
+       "0                           0.0   Personal Auto  Four-Door Car   \n",
+       "1                           0.0   Personal Auto  Four-Door Car   \n",
+       "2                           0.0   Personal Auto   Two-Door Car   \n",
+       "3                           0.0  Corporate Auto            SUV   \n",
+       "4                           0.0   Personal Auto  Four-Door Car   \n",
+       "...                         ...             ...            ...   \n",
+       "9130                        0.0   Personal Auto  Four-Door Car   \n",
+       "9131                        0.0  Corporate Auto  Four-Door Car   \n",
+       "9132                        0.0  Corporate Auto  Four-Door Car   \n",
+       "9133                        0.0   Personal Auto  Four-Door Car   \n",
+       "9134                        0.0  Corporate Auto   Two-Door Car   \n",
+       "\n",
+       "      total_claim_amount       state gender  \n",
+       "0               2.704934         NaN    NaN  \n",
+       "1            1131.464935         NaN    NaN  \n",
+       "2             566.472247         NaN    NaN  \n",
+       "3             529.881344         NaN    NaN  \n",
+       "4              17.269323         NaN    NaN  \n",
+       "...                  ...         ...    ...  \n",
+       "9130          198.234764  California      M  \n",
+       "9131          379.200000  California      F  \n",
+       "9132          790.784983  California      M  \n",
+       "9133          691.200000  California      M  \n",
+       "9134          369.600000  California      M  \n",
+       "\n",
+       "[9135 rows x 13 columns]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df.drop_duplicates().reset_index(drop=True)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ac898103-cfef-4501-b55b-9d3c16433401",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "67ffbb9c-8393-45f0-9547-a6526ec9774a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_cols = df.select_dtypes(include=['float64', 'int64']).columns\n",
+    "df[num_cols] = df[num_cols].fillna(0)\n",
+    "#df[num_cols].isnull().sum()\n",
+    "df[num_cols] = df[num_cols].astype(int)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "43505402-b509-4ecf-b2da-90bd98790547",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 9135 entries, 0 to 9134\n",
+      "Data columns (total 13 columns):\n",
+      " #   Column                     Non-Null Count  Dtype \n",
+      "---  ------                     --------------  ----- \n",
+      " 0   customer                   9134 non-null   object\n",
+      " 1   state                      2064 non-null   object\n",
+      " 2   gender                     1942 non-null   object\n",
+      " 3   education                  9134 non-null   object\n",
+      " 4   customer_lifetime_value    9135 non-null   int64 \n",
+      " 5   income                     9135 non-null   int64 \n",
+      " 6   monthly_premium_auto       9135 non-null   int64 \n",
+      " 7   number_of_open_complaints  9135 non-null   int64 \n",
+      " 8   policy_type                9134 non-null   object\n",
+      " 9   vehicle_class              9134 non-null   object\n",
+      " 10  total_claim_amount         9135 non-null   int64 \n",
+      " 11  state                      7070 non-null   object\n",
+      " 12  gender                     7070 non-null   object\n",
+      "dtypes: int64(5), object(8)\n",
+      "memory usage: 927.9+ KB\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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",
+       "      <th>state</th>\n",
+       "      <th>gender</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>0</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  customer       state gender             education  customer_lifetime_value  \\\n",
+       "0  RB50392  Washington    NaN                Master                        0   \n",
+       "1  QZ44356     Arizona      F              Bachelor                   697953   \n",
+       "2  AI49188      Nevada      F              Bachelor                  1288743   \n",
+       "3  WW63253  California      M              Bachelor                   764586   \n",
+       "4  GA49547  Washington      M  High School or Below                   536307   \n",
+       "\n",
+       "   income  monthly_premium_auto  number_of_open_complaints     policy_type  \\\n",
+       "0       0                  1000                          0   Personal Auto   \n",
+       "1       0                    94                          0   Personal Auto   \n",
+       "2   48767                   108                          0   Personal Auto   \n",
+       "3       0                   106                          0  Corporate Auto   \n",
+       "4   36357                    68                          0   Personal Auto   \n",
+       "\n",
+       "   vehicle_class  total_claim_amount state gender  \n",
+       "0  Four-Door Car                   2   NaN    NaN  \n",
+       "1  Four-Door Car                1131   NaN    NaN  \n",
+       "2   Two-Door Car                 566   NaN    NaN  \n",
+       "3            SUV                 529   NaN    NaN  \n",
+       "4  Four-Door Car                  17   NaN    NaN  "
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.info()\n",
+    "df.head()"
+   ]
+  },
+  {
+   "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": 13,
+   "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26",
+   "metadata": {
+    "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(10910, 27)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 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",
+       "   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",
+       "   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",
+       "   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",
+       "  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",
+       "[5 rows x 27 columns]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('https://raw.githubusercontent.com/data-bootcamp-v4/data/main/marketing_customer_analysis_clean.csv')\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "743f1e66-d458-4747-ba43-c7b6d031722c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 10910 entries, 0 to 10909\n",
+      "Data columns (total 27 columns):\n",
+      " #   Column                         Non-Null Count  Dtype  \n",
+      "---  ------                         --------------  -----  \n",
+      " 0   unnamed:_0                     10910 non-null  int64  \n",
+      " 1   customer                       10910 non-null  object \n",
+      " 2   state                          10910 non-null  object \n",
+      " 3   customer_lifetime_value        10910 non-null  float64\n",
+      " 4   response                       10910 non-null  object \n",
+      " 5   coverage                       10910 non-null  object \n",
+      " 6   education                      10910 non-null  object \n",
+      " 7   effective_to_date              10910 non-null  object \n",
+      " 8   employmentstatus               10910 non-null  object \n",
+      " 9   gender                         10910 non-null  object \n",
+      " 10  income                         10910 non-null  int64  \n",
+      " 11  location_code                  10910 non-null  object \n",
+      " 12  marital_status                 10910 non-null  object \n",
+      " 13  monthly_premium_auto           10910 non-null  int64  \n",
+      " 14  months_since_last_claim        10910 non-null  float64\n",
+      " 15  months_since_policy_inception  10910 non-null  int64  \n",
+      " 16  number_of_open_complaints      10910 non-null  float64\n",
+      " 17  number_of_policies             10910 non-null  int64  \n",
+      " 18  policy_type                    10910 non-null  object \n",
+      " 19  policy                         10910 non-null  object \n",
+      " 20  renew_offer_type               10910 non-null  object \n",
+      " 21  sales_channel                  10910 non-null  object \n",
+      " 22  total_claim_amount             10910 non-null  float64\n",
+      " 23  vehicle_class                  10910 non-null  object \n",
+      " 24  vehicle_size                   10910 non-null  object \n",
+      " 25  vehicle_type                   10910 non-null  object \n",
+      " 26  month                          10910 non-null  int64  \n",
+      "dtypes: float64(4), int64(6), object(17)\n",
+      "memory usage: 2.2+ MB\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "unnamed:_0                       0\n",
+       "customer                         0\n",
+       "state                            0\n",
+       "customer_lifetime_value          0\n",
+       "response                         0\n",
+       "coverage                         0\n",
+       "education                        0\n",
+       "effective_to_date                0\n",
+       "employmentstatus                 0\n",
+       "gender                           0\n",
+       "income                           0\n",
+       "location_code                    0\n",
+       "marital_status                   0\n",
+       "monthly_premium_auto             0\n",
+       "months_since_last_claim          0\n",
+       "months_since_policy_inception    0\n",
+       "number_of_open_complaints        0\n",
+       "number_of_policies               0\n",
+       "policy_type                      0\n",
+       "policy                           0\n",
+       "renew_offer_type                 0\n",
+       "sales_channel                    0\n",
+       "total_claim_amount               0\n",
+       "vehicle_class                    0\n",
+       "vehicle_size                     0\n",
+       "vehicle_type                     0\n",
+       "month                            0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.info()\n",
+    "df.describe()\n",
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "28a56e42-3a6e-4f75-b978-dc495e29a452",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "demographics = df[['customer', 'gender', 'education', 'marital_status', 'income']]\n",
+    "\n",
+    "policy_info = df[['policy_type', 'policy', 'vehicle_class']]\n",
+    "\n",
+    "marketing = df[['response', 'coverage', 'sales_channel']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d1830e4-e285-4855-960f-15c4aaf79de5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "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": 17,
+   "id": "1d47d409-38ca-4884-b081-4c10340eb3f1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "               total_claim_amount\n",
+      "sales_channel                    \n",
+      "Agent                  1810226.82\n",
+      "Branch                 1301204.00\n",
+      "Call Center             926600.82\n",
+      "Web                     706600.04\n"
+     ]
+    }
+   ],
+   "source": [
+    "pivot_revenue = pd.pivot_table(\n",
+    "    df,\n",
+    "    values='total_claim_amount',\n",
+    "    index='sales_channel',\n",
+    "    aggfunc='sum'\n",
+    ").round(2)\n",
+    "\n",
+    "print(pivot_revenue)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "f65a657b-0a7e-4fc9-9a35-457d8e2060c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "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\n"
+     ]
+    }
+   ],
+   "source": [
+    "pivot_clv = pd.pivot_table(\n",
+    "    df,\n",
+    "    values='customer_lifetime_value',\n",
+    "    index='gender',\n",
+    "    columns='education',\n",
+    "    aggfunc='mean'\n",
+    ").round(2)\n",
+    "\n",
+    "print(pivot_clv)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "675082f1-2dd0-4096-9e77-99716730b4db",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "      policy_type     month  number_of_open_complaints\n",
+      "0  Corporate Auto  February                       1089\n",
+      "1  Corporate Auto   January                       1252\n",
+      "2   Personal Auto  February                       3799\n",
+      "3   Personal Auto   January                       4329\n",
+      "4    Special Auto  February                        204\n"
+     ]
+    }
+   ],
+   "source": [
+    "df['month'] = pd.to_datetime(df['effective_to_date']).dt.month_name()\n",
+    "\n",
+    "pivot_complaints = pd.pivot_table(\n",
+    "    df,\n",
+    "    values='number_of_open_complaints',\n",
+    "    index=['policy_type', 'month'],\n",
+    "    aggfunc='count'\n",
+    ").reset_index()\n",
+    "\n",
+    "print(pivot_complaints.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9727d1a-797c-4eb5-9ec3-004765f1bded",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Shows which months there are more complaints per policy category.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "737a4b0f-db95-4357-8e3d-fb7aab35125c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "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..f093a47 100644
--- a/lab-dw-data-structuring-and-combining.ipynb
+++ b/lab-dw-data-structuring-and-combining.ipynb
@@ -36,14 +36,856 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "492d06e3-92c7-4105-ac72-536db98d3244",
    "metadata": {
     "id": "492d06e3-92c7-4105-ac72-536db98d3244"
    },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(4008, 11) (996, 11) (7070, 11)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df1 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file1.csv\")\n",
+    "df2 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file2.csv\")\n",
+    "df3 = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file3.csv\")\n",
+    "\n",
+    "print(df1.shape, df2.shape, df3.shape)\n",
+    "#df1.head()\n",
+    "#df2.head()\n",
+    "#df3.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d669a282-5584-49aa-9db6-39f49e0c9139",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(12074, 13)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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",
+       "      <th>State</th>\n",
+       "      <th>Gender</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  Customer          ST GENDER             Education Customer Lifetime Value  \\\n",
+       "0  RB50392  Washington    NaN                Master                     NaN   \n",
+       "1  QZ44356     Arizona      F              Bachelor              697953.59%   \n",
+       "2  AI49188      Nevada      F              Bachelor             1288743.17%   \n",
+       "3  WW63253  California      M              Bachelor              764586.18%   \n",
+       "4  GA49547  Washington      M  High School or Below              536307.65%   \n",
+       "\n",
+       "    Income  Monthly Premium Auto Number of Open Complaints     Policy Type  \\\n",
+       "0      0.0                1000.0                    1/0/00   Personal Auto   \n",
+       "1      0.0                  94.0                    1/0/00   Personal Auto   \n",
+       "2  48767.0                 108.0                    1/0/00   Personal Auto   \n",
+       "3      0.0                 106.0                    1/0/00  Corporate Auto   \n",
+       "4  36357.0                  68.0                    1/0/00   Personal Auto   \n",
+       "\n",
+       "   Vehicle Class  Total Claim Amount State Gender  \n",
+       "0  Four-Door Car            2.704934   NaN    NaN  \n",
+       "1  Four-Door Car         1131.464935   NaN    NaN  \n",
+       "2   Two-Door Car          566.472247   NaN    NaN  \n",
+       "3            SUV          529.881344   NaN    NaN  \n",
+       "4  Four-Door Car           17.269323   NaN    NaN  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.concat([df1, df2, df3], ignore_index=True)\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7ec71551-1d1e-42e7-857d-f6182c4de520",
+   "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', 'state',\n",
+       "       'gender'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns = (\n",
+    "    df.columns\n",
+    "    .str.replace(\"ST\", \"state\", regex=False)\n",
+    "    .str.lower()\n",
+    "    .str.strip()\n",
+    "    .str.replace(\" \", \"_\")\n",
+    ")\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "54754960-f4af-4415-bf02-f7934dc2b64e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['gender'] = df['gender'].replace({\n",
+    "    'F': 'F', 'Femal': 'F', 'Female': 'F', 'female': 'F',\n",
+    "    'M': 'M', 'Male': 'M', 'male': 'M'\n",
+    "})\n",
+    "\n",
+    "df['state'] = df['state'].replace({\n",
+    "    'AZ': 'Arizona',\n",
+    "    'Cali': 'California',\n",
+    "    'WA': 'Washington'\n",
+    "})\n",
+    "\n",
+    "df['education'] = df['education'].replace({'Bachelors': 'Bachelor'})\n",
+    "\n",
+    "df['customer_lifetime_value'] = (\n",
+    "    df['customer_lifetime_value']\n",
+    "    .astype(str)\n",
+    "    .str.replace('%', '', regex=False)\n",
+    "    .astype(float)\n",
+    ")\n",
+    "\n",
+    "df['vehicle_class'] = df['vehicle_class'].replace({\n",
+    "    'Sports Car': 'Luxury',\n",
+    "    'Luxury SUV': 'Luxury',\n",
+    "    'Luxury Car': 'Luxury'\n",
+    "})\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "5f348734-53b9-46c1-b1f5-90be4b327f48",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# Your code goes here"
+    "df['number_of_open_complaints'] = (\n",
+    "    df['number_of_open_complaints']\n",
+    "    .astype(str)\n",
+    "    .str.split('/')\n",
+    "    .str[1]\n",
+    "    .astype(float)\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "8b5cee0d-fa6c-47aa-8df5-4a9ff3120651",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                      2937\n",
+       "state                        10007\n",
+       "gender                       10129\n",
+       "education                     2937\n",
+       "customer_lifetime_value       2944\n",
+       "income                        2937\n",
+       "monthly_premium_auto          2937\n",
+       "number_of_open_complaints    10007\n",
+       "policy_type                   2937\n",
+       "vehicle_class                 2937\n",
+       "total_claim_amount            2937\n",
+       "state                         5004\n",
+       "gender                        5004\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7aa802df-5ef5-4794-885a-ec3cb29c3aff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['number_of_open_complaints'] = df['number_of_open_complaints'].fillna(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d68dca87-ef24-4d10-85d3-d577d5bd9c11",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                      2937\n",
+       "state                        10007\n",
+       "gender                       10129\n",
+       "education                     2937\n",
+       "customer_lifetime_value       2944\n",
+       "income                        2937\n",
+       "monthly_premium_auto          2937\n",
+       "number_of_open_complaints        0\n",
+       "policy_type                   2937\n",
+       "vehicle_class                 2937\n",
+       "total_claim_amount            2937\n",
+       "state                         5004\n",
+       "gender                        5004\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "87a9b5cd-2464-4818-87e4-6e5ee153e91b",
+   "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",
+       "      <th>state</th>\n",
+       "      <th>gender</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>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>2.704934</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>6.979536e+05</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>1131.464935</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>1.288743e+06</td>\n",
+       "      <td>48767.0</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>566.472247</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>7.645862e+05</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>529.881344</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>5.363077e+05</td>\n",
+       "      <td>36357.0</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>17.269323</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2.340599e+04</td>\n",
+       "      <td>71941.0</td>\n",
+       "      <td>73.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>College</td>\n",
+       "      <td>3.096511e+03</td>\n",
+       "      <td>21604.0</td>\n",
+       "      <td>79.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>California</td>\n",
+       "      <td>F</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>8.163890e+03</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>85.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>College</td>\n",
+       "      <td>7.524442e+03</td>\n",
+       "      <td>21941.0</td>\n",
+       "      <td>96.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9134</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2.611837e+03</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>77.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>California</td>\n",
+       "      <td>M</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9135 rows × 13 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state 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",
+       "9130  LA72316         NaN    NaN              Bachelor   \n",
+       "9131  PK87824         NaN    NaN               College   \n",
+       "9132  TD14365         NaN    NaN              Bachelor   \n",
+       "9133  UP19263         NaN    NaN               College   \n",
+       "9134  Y167826         NaN    NaN               College   \n",
+       "\n",
+       "      customer_lifetime_value   income  monthly_premium_auto  \\\n",
+       "0                         NaN      0.0                1000.0   \n",
+       "1                6.979536e+05      0.0                  94.0   \n",
+       "2                1.288743e+06  48767.0                 108.0   \n",
+       "3                7.645862e+05      0.0                 106.0   \n",
+       "4                5.363077e+05  36357.0                  68.0   \n",
+       "...                       ...      ...                   ...   \n",
+       "9130             2.340599e+04  71941.0                  73.0   \n",
+       "9131             3.096511e+03  21604.0                  79.0   \n",
+       "9132             8.163890e+03      0.0                  85.0   \n",
+       "9133             7.524442e+03  21941.0                  96.0   \n",
+       "9134             2.611837e+03      0.0                  77.0   \n",
+       "\n",
+       "      number_of_open_complaints     policy_type  vehicle_class  \\\n",
+       "0                           0.0   Personal Auto  Four-Door Car   \n",
+       "1                           0.0   Personal Auto  Four-Door Car   \n",
+       "2                           0.0   Personal Auto   Two-Door Car   \n",
+       "3                           0.0  Corporate Auto            SUV   \n",
+       "4                           0.0   Personal Auto  Four-Door Car   \n",
+       "...                         ...             ...            ...   \n",
+       "9130                        0.0   Personal Auto  Four-Door Car   \n",
+       "9131                        0.0  Corporate Auto  Four-Door Car   \n",
+       "9132                        0.0  Corporate Auto  Four-Door Car   \n",
+       "9133                        0.0   Personal Auto  Four-Door Car   \n",
+       "9134                        0.0  Corporate Auto   Two-Door Car   \n",
+       "\n",
+       "      total_claim_amount       state gender  \n",
+       "0               2.704934         NaN    NaN  \n",
+       "1            1131.464935         NaN    NaN  \n",
+       "2             566.472247         NaN    NaN  \n",
+       "3             529.881344         NaN    NaN  \n",
+       "4              17.269323         NaN    NaN  \n",
+       "...                  ...         ...    ...  \n",
+       "9130          198.234764  California      M  \n",
+       "9131          379.200000  California      F  \n",
+       "9132          790.784983  California      M  \n",
+       "9133          691.200000  California      M  \n",
+       "9134          369.600000  California      M  \n",
+       "\n",
+       "[9135 rows x 13 columns]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df.drop_duplicates().reset_index(drop=True)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ac898103-cfef-4501-b55b-9d3c16433401",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "67ffbb9c-8393-45f0-9547-a6526ec9774a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_cols = df.select_dtypes(include=['float64', 'int64']).columns\n",
+    "df[num_cols] = df[num_cols].fillna(0)\n",
+    "#df[num_cols].isnull().sum()\n",
+    "df[num_cols] = df[num_cols].astype(int)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "43505402-b509-4ecf-b2da-90bd98790547",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 9135 entries, 0 to 9134\n",
+      "Data columns (total 13 columns):\n",
+      " #   Column                     Non-Null Count  Dtype \n",
+      "---  ------                     --------------  ----- \n",
+      " 0   customer                   9134 non-null   object\n",
+      " 1   state                      2064 non-null   object\n",
+      " 2   gender                     1942 non-null   object\n",
+      " 3   education                  9134 non-null   object\n",
+      " 4   customer_lifetime_value    9135 non-null   int64 \n",
+      " 5   income                     9135 non-null   int64 \n",
+      " 6   monthly_premium_auto       9135 non-null   int64 \n",
+      " 7   number_of_open_complaints  9135 non-null   int64 \n",
+      " 8   policy_type                9134 non-null   object\n",
+      " 9   vehicle_class              9134 non-null   object\n",
+      " 10  total_claim_amount         9135 non-null   int64 \n",
+      " 11  state                      7070 non-null   object\n",
+      " 12  gender                     7070 non-null   object\n",
+      "dtypes: int64(5), object(8)\n",
+      "memory usage: 927.9+ KB\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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",
+       "      <th>state</th>\n",
+       "      <th>gender</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>0</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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</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</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  customer       state gender             education  customer_lifetime_value  \\\n",
+       "0  RB50392  Washington    NaN                Master                        0   \n",
+       "1  QZ44356     Arizona      F              Bachelor                   697953   \n",
+       "2  AI49188      Nevada      F              Bachelor                  1288743   \n",
+       "3  WW63253  California      M              Bachelor                   764586   \n",
+       "4  GA49547  Washington      M  High School or Below                   536307   \n",
+       "\n",
+       "   income  monthly_premium_auto  number_of_open_complaints     policy_type  \\\n",
+       "0       0                  1000                          0   Personal Auto   \n",
+       "1       0                    94                          0   Personal Auto   \n",
+       "2   48767                   108                          0   Personal Auto   \n",
+       "3       0                   106                          0  Corporate Auto   \n",
+       "4   36357                    68                          0   Personal Auto   \n",
+       "\n",
+       "   vehicle_class  total_claim_amount state gender  \n",
+       "0  Four-Door Car                   2   NaN    NaN  \n",
+       "1  Four-Door Car                1131   NaN    NaN  \n",
+       "2   Two-Door Car                 566   NaN    NaN  \n",
+       "3            SUV                 529   NaN    NaN  \n",
+       "4  Four-Door Car                  17   NaN    NaN  "
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.info()\n",
+    "df.head()"
    ]
   },
   {
@@ -72,16 +914,351 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26",
    "metadata": {
     "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26"
    },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(10910, 27)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>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",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 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",
+       "   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",
+       "   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",
+       "   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",
+       "  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",
+       "[5 rows x 27 columns]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('https://raw.githubusercontent.com/data-bootcamp-v4/data/main/marketing_customer_analysis_clean.csv')\n",
+    "print(df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "743f1e66-d458-4747-ba43-c7b6d031722c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 10910 entries, 0 to 10909\n",
+      "Data columns (total 27 columns):\n",
+      " #   Column                         Non-Null Count  Dtype  \n",
+      "---  ------                         --------------  -----  \n",
+      " 0   unnamed:_0                     10910 non-null  int64  \n",
+      " 1   customer                       10910 non-null  object \n",
+      " 2   state                          10910 non-null  object \n",
+      " 3   customer_lifetime_value        10910 non-null  float64\n",
+      " 4   response                       10910 non-null  object \n",
+      " 5   coverage                       10910 non-null  object \n",
+      " 6   education                      10910 non-null  object \n",
+      " 7   effective_to_date              10910 non-null  object \n",
+      " 8   employmentstatus               10910 non-null  object \n",
+      " 9   gender                         10910 non-null  object \n",
+      " 10  income                         10910 non-null  int64  \n",
+      " 11  location_code                  10910 non-null  object \n",
+      " 12  marital_status                 10910 non-null  object \n",
+      " 13  monthly_premium_auto           10910 non-null  int64  \n",
+      " 14  months_since_last_claim        10910 non-null  float64\n",
+      " 15  months_since_policy_inception  10910 non-null  int64  \n",
+      " 16  number_of_open_complaints      10910 non-null  float64\n",
+      " 17  number_of_policies             10910 non-null  int64  \n",
+      " 18  policy_type                    10910 non-null  object \n",
+      " 19  policy                         10910 non-null  object \n",
+      " 20  renew_offer_type               10910 non-null  object \n",
+      " 21  sales_channel                  10910 non-null  object \n",
+      " 22  total_claim_amount             10910 non-null  float64\n",
+      " 23  vehicle_class                  10910 non-null  object \n",
+      " 24  vehicle_size                   10910 non-null  object \n",
+      " 25  vehicle_type                   10910 non-null  object \n",
+      " 26  month                          10910 non-null  int64  \n",
+      "dtypes: float64(4), int64(6), object(17)\n",
+      "memory usage: 2.2+ MB\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "unnamed:_0                       0\n",
+       "customer                         0\n",
+       "state                            0\n",
+       "customer_lifetime_value          0\n",
+       "response                         0\n",
+       "coverage                         0\n",
+       "education                        0\n",
+       "effective_to_date                0\n",
+       "employmentstatus                 0\n",
+       "gender                           0\n",
+       "income                           0\n",
+       "location_code                    0\n",
+       "marital_status                   0\n",
+       "monthly_premium_auto             0\n",
+       "months_since_last_claim          0\n",
+       "months_since_policy_inception    0\n",
+       "number_of_open_complaints        0\n",
+       "number_of_policies               0\n",
+       "policy_type                      0\n",
+       "policy                           0\n",
+       "renew_offer_type                 0\n",
+       "sales_channel                    0\n",
+       "total_claim_amount               0\n",
+       "vehicle_class                    0\n",
+       "vehicle_size                     0\n",
+       "vehicle_type                     0\n",
+       "month                            0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.info()\n",
+    "df.describe()\n",
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "28a56e42-3a6e-4f75-b978-dc495e29a452",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# Your code goes here"
+    "demographics = df[['customer', 'gender', 'education', 'marital_status', 'income']]\n",
+    "\n",
+    "policy_info = df[['policy_type', 'policy', 'vehicle_class']]\n",
+    "\n",
+    "marketing = df[['response', 'coverage', 'sales_channel']]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d1830e4-e285-4855-960f-15c4aaf79de5",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "df35fd0d-513e-4e77-867e-429da10a9cc7",
@@ -128,17 +1305,114 @@
     "*More information about long and wide format tables here: https://www.statology.org/long-vs-wide-data/*"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1d47d409-38ca-4884-b081-4c10340eb3f1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "               total_claim_amount\n",
+      "sales_channel                    \n",
+      "Agent                  1810226.82\n",
+      "Branch                 1301204.00\n",
+      "Call Center             926600.82\n",
+      "Web                     706600.04\n"
+     ]
+    }
+   ],
+   "source": [
+    "pivot_revenue = pd.pivot_table(\n",
+    "    df,\n",
+    "    values='total_claim_amount',\n",
+    "    index='sales_channel',\n",
+    "    aggfunc='sum'\n",
+    ").round(2)\n",
+    "\n",
+    "print(pivot_revenue)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "f65a657b-0a7e-4fc9-9a35-457d8e2060c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "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\n"
+     ]
+    }
+   ],
+   "source": [
+    "pivot_clv = pd.pivot_table(\n",
+    "    df,\n",
+    "    values='customer_lifetime_value',\n",
+    "    index='gender',\n",
+    "    columns='education',\n",
+    "    aggfunc='mean'\n",
+    ").round(2)\n",
+    "\n",
+    "print(pivot_clv)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "675082f1-2dd0-4096-9e77-99716730b4db",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "      policy_type     month  number_of_open_complaints\n",
+      "0  Corporate Auto  February                       1089\n",
+      "1  Corporate Auto   January                       1252\n",
+      "2   Personal Auto  February                       3799\n",
+      "3   Personal Auto   January                       4329\n",
+      "4    Special Auto  February                        204\n"
+     ]
+    }
+   ],
+   "source": [
+    "df['month'] = pd.to_datetime(df['effective_to_date']).dt.month_name()\n",
+    "\n",
+    "pivot_complaints = pd.pivot_table(\n",
+    "    df,\n",
+    "    values='number_of_open_complaints',\n",
+    "    index=['policy_type', 'month'],\n",
+    "    aggfunc='count'\n",
+    ").reset_index()\n",
+    "\n",
+    "print(pivot_complaints.head())"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3a069e0b-b400-470e-904d-d17582191be4",
-   "metadata": {
-    "id": "3a069e0b-b400-470e-904d-d17582191be4"
-   },
+   "id": "a9727d1a-797c-4eb5-9ec3-004765f1bded",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# Your code goes here"
+    "Shows which months there are more complaints per policy category.\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "737a4b0f-db95-4357-8e3d-fb7aab35125c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -146,7 +1420,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -160,7 +1434,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,