K Prototype Algorithm Implementation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## K - Prototype Clustring Algorithm Implementation "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We use K-Means clustering algorithm if we have numeric data and K-Modes algorithm for Categorical data but what if we have mixed data i.e numeric and categorical both. We use K-Prototype in this case. It has been designed to use K-Means for numeric columns and K-Modes for categorical columns."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load Libraries "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from kmodes.kprototypes import KPrototypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load Data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "marketing_data = pd.read_csv(\"marketing.csv\",sep=\",\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>CLV</th>\n",
       "      <th>Coverage</th>\n",
       "      <th>Income</th>\n",
       "      <th>loc_type</th>\n",
       "      <th>monthly_premium</th>\n",
       "      <th>months_last_claim</th>\n",
       "      <th>Months_Since_Policy_Inception</th>\n",
       "      <th>Total_Claim_Amount</th>\n",
       "      <th>Vehicle_Class</th>\n",
       "      <th>avg_vehicle_age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BU79786</td>\n",
       "      <td>Washington</td>\n",
       "      <td>2763.519279</td>\n",
       "      <td>Basic</td>\n",
       "      <td>56274</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>69</td>\n",
       "      <td>32</td>\n",
       "      <td>5</td>\n",
       "      <td>384.811147</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>40.696695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>AI49188</td>\n",
       "      <td>Nevada</td>\n",
       "      <td>12887.431650</td>\n",
       "      <td>Premium</td>\n",
       "      <td>48767</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>108</td>\n",
       "      <td>18</td>\n",
       "      <td>38</td>\n",
       "      <td>566.472247</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>48.755298</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>HB64268</td>\n",
       "      <td>Washington</td>\n",
       "      <td>2813.692575</td>\n",
       "      <td>Basic</td>\n",
       "      <td>43836</td>\n",
       "      <td>Rural</td>\n",
       "      <td>73</td>\n",
       "      <td>12</td>\n",
       "      <td>44</td>\n",
       "      <td>138.130879</td>\n",
       "      <td>Four-Door Car</td>\n",
       "      <td>70.394474</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>OC83172</td>\n",
       "      <td>Oregon</td>\n",
       "      <td>8256.297800</td>\n",
       "      <td>Basic</td>\n",
       "      <td>62902</td>\n",
       "      <td>Rural</td>\n",
       "      <td>69</td>\n",
       "      <td>14</td>\n",
       "      <td>94</td>\n",
       "      <td>159.383042</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>53.460212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>XZ87318</td>\n",
       "      <td>Oregon</td>\n",
       "      <td>5380.898636</td>\n",
       "      <td>Basic</td>\n",
       "      <td>55350</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>321.600000</td>\n",
       "      <td>Four-Door Car</td>\n",
       "      <td>32.811507</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Customer       State           CLV Coverage  Income  loc_type  \\\n",
       "0  BU79786  Washington   2763.519279    Basic   56274  Suburban   \n",
       "1  AI49188      Nevada  12887.431650  Premium   48767  Suburban   \n",
       "2  HB64268  Washington   2813.692575    Basic   43836     Rural   \n",
       "3  OC83172      Oregon   8256.297800    Basic   62902     Rural   \n",
       "4  XZ87318      Oregon   5380.898636    Basic   55350  Suburban   \n",
       "\n",
       "   monthly_premium  months_last_claim  Months_Since_Policy_Inception  \\\n",
       "0               69                 32                              5   \n",
       "1              108                 18                             38   \n",
       "2               73                 12                             44   \n",
       "3               69                 14                             94   \n",
       "4               67                  0                             13   \n",
       "\n",
       "   Total_Claim_Amount  Vehicle_Class  avg_vehicle_age  \n",
       "0          384.811147   Two-Door Car        40.696695  \n",
       "1          566.472247   Two-Door Car        48.755298  \n",
       "2          138.130879  Four-Door Car        70.394474  \n",
       "3          159.383042   Two-Door Car        53.460212  \n",
       "4          321.600000  Four-Door Car        32.811507  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "marketing_data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see we have mixed data type so we can't just use either K-Means or K-Modes. We will have to use combination of both these algorithm which is nothing but K-Prototype clustering algorithm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Cleaning "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets drop 'Customer' column as this has no use."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "marketing_data.drop('Customer',axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Let's  Scale Numeric Columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "Numeric_Cols = ['CLV','Income','monthly_premium','months_last_claim','Months_Since_Policy_Inception','Total_Claim_Amount','avg_vehicle_age']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>State</th>\n",
       "      <th>Coverage</th>\n",
       "      <th>loc_type</th>\n",
       "      <th>Vehicle_Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Washington</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>Two-Door Car</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>Premium</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>Two-Door Car</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Washington</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Four-Door Car</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Oregon</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Two-Door Car</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Oregon</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>Four-Door Car</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        State Coverage  loc_type  Vehicle_Class\n",
       "0  Washington    Basic  Suburban   Two-Door Car\n",
       "1      Nevada  Premium  Suburban   Two-Door Car\n",
       "2  Washington    Basic     Rural  Four-Door Car\n",
       "3      Oregon    Basic     Rural   Two-Door Car\n",
       "4      Oregon    Basic  Suburban  Four-Door Car"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cat_data = marketing_data.drop(Numeric_Cols,axis=1)\n",
    "cat_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>CLV</th>\n",
       "      <th>Income</th>\n",
       "      <th>monthly_premium</th>\n",
       "      <th>months_last_claim</th>\n",
       "      <th>Months_Since_Policy_Inception</th>\n",
       "      <th>Total_Claim_Amount</th>\n",
       "      <th>avg_vehicle_age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2763.519279</td>\n",
       "      <td>56274</td>\n",
       "      <td>69</td>\n",
       "      <td>32</td>\n",
       "      <td>5</td>\n",
       "      <td>384.811147</td>\n",
       "      <td>40.696695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12887.431650</td>\n",
       "      <td>48767</td>\n",
       "      <td>108</td>\n",
       "      <td>18</td>\n",
       "      <td>38</td>\n",
       "      <td>566.472247</td>\n",
       "      <td>48.755298</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2813.692575</td>\n",
       "      <td>43836</td>\n",
       "      <td>73</td>\n",
       "      <td>12</td>\n",
       "      <td>44</td>\n",
       "      <td>138.130879</td>\n",
       "      <td>70.394474</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8256.297800</td>\n",
       "      <td>62902</td>\n",
       "      <td>69</td>\n",
       "      <td>14</td>\n",
       "      <td>94</td>\n",
       "      <td>159.383042</td>\n",
       "      <td>53.460212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5380.898636</td>\n",
       "      <td>55350</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>321.600000</td>\n",
       "      <td>32.811507</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            CLV  Income  monthly_premium  months_last_claim  \\\n",
       "0   2763.519279   56274               69                 32   \n",
       "1  12887.431650   48767              108                 18   \n",
       "2   2813.692575   43836               73                 12   \n",
       "3   8256.297800   62902               69                 14   \n",
       "4   5380.898636   55350               67                  0   \n",
       "\n",
       "   Months_Since_Policy_Inception  Total_Claim_Amount  avg_vehicle_age  \n",
       "0                              5          384.811147        40.696695  \n",
       "1                             38          566.472247        48.755298  \n",
       "2                             44          138.130879        70.394474  \n",
       "3                             94          159.383042        53.460212  \n",
       "4                             13          321.600000        32.811507  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numeric_data = marketing_data[Numeric_Cols]\n",
    "numeric_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Lets do scaling of numeric columns\n",
    "\n",
    "scaler = StandardScaler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "numeric_data_scaled = scaler.fit_transform(numeric_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "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>CLV</th>\n",
       "      <th>Income</th>\n",
       "      <th>monthly_premium</th>\n",
       "      <th>months_last_claim</th>\n",
       "      <th>Months_Since_Policy_Inception</th>\n",
       "      <th>Total_Claim_Amount</th>\n",
       "      <th>avg_vehicle_age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.772349</td>\n",
       "      <td>0.239359</td>\n",
       "      <td>-0.692321</td>\n",
       "      <td>1.684521</td>\n",
       "      <td>-1.535588</td>\n",
       "      <td>0.027591</td>\n",
       "      <td>-0.950653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.684632</td>\n",
       "      <td>-0.069518</td>\n",
       "      <td>0.434436</td>\n",
       "      <td>0.293427</td>\n",
       "      <td>-0.352508</td>\n",
       "      <td>0.746670</td>\n",
       "      <td>-0.138215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.765128</td>\n",
       "      <td>-0.272405</td>\n",
       "      <td>-0.576756</td>\n",
       "      <td>-0.302756</td>\n",
       "      <td>-0.137403</td>\n",
       "      <td>-0.948856</td>\n",
       "      <td>2.043365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.018143</td>\n",
       "      <td>0.512069</td>\n",
       "      <td>-0.692321</td>\n",
       "      <td>-0.104028</td>\n",
       "      <td>1.655142</td>\n",
       "      <td>-0.864733</td>\n",
       "      <td>0.336117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.395669</td>\n",
       "      <td>0.201341</td>\n",
       "      <td>-0.750103</td>\n",
       "      <td>-1.495122</td>\n",
       "      <td>-1.248781</td>\n",
       "      <td>-0.222621</td>\n",
       "      <td>-1.745608</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        CLV    Income  monthly_premium  months_last_claim  \\\n",
       "0 -0.772349  0.239359        -0.692321           1.684521   \n",
       "1  0.684632 -0.069518         0.434436           0.293427   \n",
       "2 -0.765128 -0.272405        -0.576756          -0.302756   \n",
       "3  0.018143  0.512069        -0.692321          -0.104028   \n",
       "4 -0.395669  0.201341        -0.750103          -1.495122   \n",
       "\n",
       "   Months_Since_Policy_Inception  Total_Claim_Amount  avg_vehicle_age  \n",
       "0                      -1.535588            0.027591        -0.950653  \n",
       "1                      -0.352508            0.746670        -0.138215  \n",
       "2                      -0.137403           -0.948856         2.043365  \n",
       "3                       1.655142           -0.864733         0.336117  \n",
       "4                      -1.248781           -0.222621        -1.745608  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numeric_data_scaled_df = pd.DataFrame(data=numeric_data_scaled,columns=Numeric_Cols)\n",
    "numeric_data_scaled_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now lets combine both categorical and scaled numeric data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>State</th>\n",
       "      <th>Coverage</th>\n",
       "      <th>loc_type</th>\n",
       "      <th>Vehicle_Class</th>\n",
       "      <th>CLV</th>\n",
       "      <th>Income</th>\n",
       "      <th>monthly_premium</th>\n",
       "      <th>months_last_claim</th>\n",
       "      <th>Months_Since_Policy_Inception</th>\n",
       "      <th>Total_Claim_Amount</th>\n",
       "      <th>avg_vehicle_age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Washington</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>-0.772349</td>\n",
       "      <td>0.239359</td>\n",
       "      <td>-0.692321</td>\n",
       "      <td>1.684521</td>\n",
       "      <td>-1.535588</td>\n",
       "      <td>0.027591</td>\n",
       "      <td>-0.950653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>Premium</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>0.684632</td>\n",
       "      <td>-0.069518</td>\n",
       "      <td>0.434436</td>\n",
       "      <td>0.293427</td>\n",
       "      <td>-0.352508</td>\n",
       "      <td>0.746670</td>\n",
       "      <td>-0.138215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Washington</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Four-Door Car</td>\n",
       "      <td>-0.765128</td>\n",
       "      <td>-0.272405</td>\n",
       "      <td>-0.576756</td>\n",
       "      <td>-0.302756</td>\n",
       "      <td>-0.137403</td>\n",
       "      <td>-0.948856</td>\n",
       "      <td>2.043365</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Oregon</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>0.018143</td>\n",
       "      <td>0.512069</td>\n",
       "      <td>-0.692321</td>\n",
       "      <td>-0.104028</td>\n",
       "      <td>1.655142</td>\n",
       "      <td>-0.864733</td>\n",
       "      <td>0.336117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Oregon</td>\n",
       "      <td>Basic</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>Four-Door Car</td>\n",
       "      <td>-0.395669</td>\n",
       "      <td>0.201341</td>\n",
       "      <td>-0.750103</td>\n",
       "      <td>-1.495122</td>\n",
       "      <td>-1.248781</td>\n",
       "      <td>-0.222621</td>\n",
       "      <td>-1.745608</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        State Coverage  loc_type  Vehicle_Class       CLV    Income  \\\n",
       "0  Washington    Basic  Suburban   Two-Door Car -0.772349  0.239359   \n",
       "1      Nevada  Premium  Suburban   Two-Door Car  0.684632 -0.069518   \n",
       "2  Washington    Basic     Rural  Four-Door Car -0.765128 -0.272405   \n",
       "3      Oregon    Basic     Rural   Two-Door Car  0.018143  0.512069   \n",
       "4      Oregon    Basic  Suburban  Four-Door Car -0.395669  0.201341   \n",
       "\n",
       "   monthly_premium  months_last_claim  Months_Since_Policy_Inception  \\\n",
       "0        -0.692321           1.684521                      -1.535588   \n",
       "1         0.434436           0.293427                      -0.352508   \n",
       "2        -0.576756          -0.302756                      -0.137403   \n",
       "3        -0.692321          -0.104028                       1.655142   \n",
       "4        -0.750103          -1.495122                      -1.248781   \n",
       "\n",
       "   Total_Claim_Amount  avg_vehicle_age  \n",
       "0            0.027591        -0.950653  \n",
       "1            0.746670        -0.138215  \n",
       "2           -0.948856         2.043365  \n",
       "3           -0.864733         0.336117  \n",
       "4           -0.222621        -1.745608  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_data = pd.concat([cat_data,numeric_data_scaled_df],axis=1)\n",
    "final_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert the dataframe to Numpy array before training the model\n",
    "\n",
    "final_data_array = final_data.values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train the Model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "kproto = KPrototypes(n_clusters=3,verbose=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 1, iteration: 1/100, moves: 1684, ncost: 43961.88599677503\n",
      "Run: 1, iteration: 2/100, moves: 1044, ncost: 42727.25320856664\n",
      "Run: 1, iteration: 3/100, moves: 491, ncost: 42513.888709012106\n",
      "Run: 1, iteration: 4/100, moves: 213, ncost: 42474.6955836033\n",
      "Run: 1, iteration: 5/100, moves: 138, ncost: 42455.958910534646\n",
      "Run: 1, iteration: 6/100, moves: 156, ncost: 42402.820714246474\n",
      "Run: 1, iteration: 7/100, moves: 105, ncost: 42379.19358381165\n",
      "Run: 1, iteration: 8/100, moves: 58, ncost: 42372.9477994903\n",
      "Run: 1, iteration: 9/100, moves: 19, ncost: 42372.36140413257\n",
      "Run: 1, iteration: 10/100, moves: 8, ncost: 42372.19091052687\n",
      "Run: 1, iteration: 11/100, moves: 5, ncost: 42372.116424505504\n",
      "Run: 1, iteration: 12/100, moves: 2, ncost: 42372.10264999943\n",
      "Run: 1, iteration: 13/100, moves: 1, ncost: 42372.1000756721\n",
      "Run: 1, iteration: 14/100, moves: 0, ncost: 42372.1000756721\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 2, iteration: 1/100, moves: 1519, ncost: 42924.58793858539\n",
      "Run: 2, iteration: 2/100, moves: 784, ncost: 42454.11105299574\n",
      "Run: 2, iteration: 3/100, moves: 548, ncost: 42174.75484529926\n",
      "Run: 2, iteration: 4/100, moves: 357, ncost: 42030.34480623709\n",
      "Run: 2, iteration: 5/100, moves: 219, ncost: 42002.00757840315\n",
      "Run: 2, iteration: 6/100, moves: 110, ncost: 41991.1200738527\n",
      "Run: 2, iteration: 7/100, moves: 44, ncost: 41989.20144468097\n",
      "Run: 2, iteration: 8/100, moves: 24, ncost: 41987.681756036014\n",
      "Run: 2, iteration: 9/100, moves: 20, ncost: 41985.876819269906\n",
      "Run: 2, iteration: 10/100, moves: 19, ncost: 41985.342800677376\n",
      "Run: 2, iteration: 11/100, moves: 6, ncost: 41985.251513463205\n",
      "Run: 2, iteration: 12/100, moves: 4, ncost: 41985.12184450256\n",
      "Run: 2, iteration: 13/100, moves: 4, ncost: 41985.045903069724\n",
      "Run: 2, iteration: 14/100, moves: 0, ncost: 41985.045903069724\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 3, iteration: 1/100, moves: 1993, ncost: 43373.4985134895\n",
      "Run: 3, iteration: 2/100, moves: 984, ncost: 42800.34330236661\n",
      "Run: 3, iteration: 3/100, moves: 602, ncost: 42541.19049341338\n",
      "Run: 3, iteration: 4/100, moves: 394, ncost: 42330.24406053535\n",
      "Run: 3, iteration: 5/100, moves: 461, ncost: 42150.74394137565\n",
      "Run: 3, iteration: 6/100, moves: 324, ncost: 42048.1112961439\n",
      "Run: 3, iteration: 7/100, moves: 210, ncost: 42010.60355873247\n",
      "Run: 3, iteration: 8/100, moves: 91, ncost: 42000.48588846171\n",
      "Run: 3, iteration: 9/100, moves: 67, ncost: 41992.50364897872\n",
      "Run: 3, iteration: 10/100, moves: 45, ncost: 41989.2052518789\n",
      "Run: 3, iteration: 11/100, moves: 23, ncost: 41987.38283281441\n",
      "Run: 3, iteration: 12/100, moves: 15, ncost: 41985.947403270795\n",
      "Run: 3, iteration: 13/100, moves: 13, ncost: 41985.66987788473\n",
      "Run: 3, iteration: 14/100, moves: 17, ncost: 41985.21467575552\n",
      "Run: 3, iteration: 15/100, moves: 10, ncost: 41985.055122065714\n",
      "Run: 3, iteration: 16/100, moves: 1, ncost: 41985.04590306973\n",
      "Run: 3, iteration: 17/100, moves: 0, ncost: 41985.04590306973\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 4, iteration: 1/100, moves: 1347, ncost: 43041.881045937305\n",
      "Run: 4, iteration: 2/100, moves: 553, ncost: 42839.255248011774\n",
      "Run: 4, iteration: 3/100, moves: 339, ncost: 42743.09498601547\n",
      "Run: 4, iteration: 4/100, moves: 255, ncost: 42670.30342130563\n",
      "Run: 4, iteration: 5/100, moves: 225, ncost: 42610.7974189982\n",
      "Run: 4, iteration: 6/100, moves: 243, ncost: 42547.09462792039\n",
      "Run: 4, iteration: 7/100, moves: 237, ncost: 42482.74872565146\n",
      "Run: 4, iteration: 8/100, moves: 198, ncost: 42433.624154011435\n",
      "Run: 4, iteration: 9/100, moves: 165, ncost: 42405.181341728305\n",
      "Run: 4, iteration: 10/100, moves: 119, ncost: 42388.748923972234\n",
      "Run: 4, iteration: 11/100, moves: 55, ncost: 42385.735129990346\n",
      "Run: 4, iteration: 12/100, moves: 37, ncost: 42384.21013035425\n",
      "Run: 4, iteration: 13/100, moves: 20, ncost: 42383.79783589886\n",
      "Run: 4, iteration: 14/100, moves: 3, ncost: 42383.78226272755\n",
      "Run: 4, iteration: 15/100, moves: 4, ncost: 42383.74963142211\n",
      "Run: 4, iteration: 16/100, moves: 9, ncost: 42383.68101282645\n",
      "Run: 4, iteration: 17/100, moves: 5, ncost: 42383.64637345116\n",
      "Run: 4, iteration: 18/100, moves: 3, ncost: 42383.62705072495\n",
      "Run: 4, iteration: 19/100, moves: 1, ncost: 42383.62452205959\n",
      "Run: 4, iteration: 20/100, moves: 0, ncost: 42383.62452205959\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 5, iteration: 1/100, moves: 1045, ncost: 45741.11150117688\n",
      "Run: 5, iteration: 2/100, moves: 836, ncost: 44802.95285739556\n",
      "Run: 5, iteration: 3/100, moves: 1094, ncost: 43378.26131230203\n",
      "Run: 5, iteration: 4/100, moves: 814, ncost: 42919.66048764934\n",
      "Run: 5, iteration: 5/100, moves: 489, ncost: 42694.285762021835\n",
      "Run: 5, iteration: 6/100, moves: 380, ncost: 42566.69778768824\n",
      "Run: 5, iteration: 7/100, moves: 263, ncost: 42506.74453654206\n",
      "Run: 5, iteration: 8/100, moves: 167, ncost: 42478.497703108274\n",
      "Run: 5, iteration: 9/100, moves: 197, ncost: 42420.922722889045\n",
      "Run: 5, iteration: 10/100, moves: 153, ncost: 42390.68815144908\n",
      "Run: 5, iteration: 11/100, moves: 107, ncost: 42373.85156501508\n",
      "Run: 5, iteration: 12/100, moves: 40, ncost: 42372.46853731938\n",
      "Run: 5, iteration: 13/100, moves: 16, ncost: 42372.187731007565\n",
      "Run: 5, iteration: 14/100, moves: 7, ncost: 42372.11642450552\n",
      "Run: 5, iteration: 15/100, moves: 2, ncost: 42372.10264999941\n",
      "Run: 5, iteration: 16/100, moves: 1, ncost: 42372.100075672104\n",
      "Run: 5, iteration: 17/100, moves: 0, ncost: 42372.100075672104\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 6, iteration: 1/100, moves: 1516, ncost: 45803.652125980516\n",
      "Run: 6, iteration: 2/100, moves: 1191, ncost: 43899.92963250347\n",
      "Run: 6, iteration: 3/100, moves: 976, ncost: 42887.09371503335\n",
      "Run: 6, iteration: 4/100, moves: 763, ncost: 42353.787425479255\n",
      "Run: 6, iteration: 5/100, moves: 588, ncost: 42093.12112434008\n",
      "Run: 6, iteration: 6/100, moves: 335, ncost: 42011.62973295488\n",
      "Run: 6, iteration: 7/100, moves: 139, ncost: 41997.817157580335\n",
      "Run: 6, iteration: 8/100, moves: 69, ncost: 41990.32129931787\n",
      "Run: 6, iteration: 9/100, moves: 21, ncost: 41989.06275525609\n",
      "Run: 6, iteration: 10/100, moves: 14, ncost: 41988.22045907584\n",
      "Run: 6, iteration: 11/100, moves: 28, ncost: 41985.84517858905\n",
      "Run: 6, iteration: 12/100, moves: 18, ncost: 41985.334342315415\n",
      "Run: 6, iteration: 13/100, moves: 10, ncost: 41985.12223193957\n",
      "Run: 6, iteration: 14/100, moves: 4, ncost: 41985.043971616906\n",
      "Run: 6, iteration: 15/100, moves: 0, ncost: 41985.043971616906\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 7, iteration: 1/100, moves: 1606, ncost: 43423.61821177372\n",
      "Run: 7, iteration: 2/100, moves: 916, ncost: 42879.072051106894\n",
      "Run: 7, iteration: 3/100, moves: 572, ncost: 42555.45646950056\n",
      "Run: 7, iteration: 4/100, moves: 516, ncost: 42256.72513681975\n",
      "Run: 7, iteration: 5/100, moves: 446, ncost: 42079.717921132615\n",
      "Run: 7, iteration: 6/100, moves: 269, ncost: 42017.92417050355\n",
      "Run: 7, iteration: 7/100, moves: 133, ncost: 42001.86742772359\n",
      "Run: 7, iteration: 8/100, moves: 80, ncost: 41993.55497829179\n",
      "Run: 7, iteration: 9/100, moves: 54, ncost: 41989.31377746734\n",
      "Run: 7, iteration: 10/100, moves: 28, ncost: 41987.382832814415\n",
      "Run: 7, iteration: 11/100, moves: 15, ncost: 41985.94740327078\n",
      "Run: 7, iteration: 12/100, moves: 13, ncost: 41985.669877884735\n",
      "Run: 7, iteration: 13/100, moves: 17, ncost: 41985.214675755524\n",
      "Run: 7, iteration: 14/100, moves: 10, ncost: 41985.05512206572\n",
      "Run: 7, iteration: 15/100, moves: 1, ncost: 41985.045903069724\n",
      "Run: 7, iteration: 16/100, moves: 0, ncost: 41985.045903069724\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 8, iteration: 1/100, moves: 1378, ncost: 44785.41498336305\n",
      "Run: 8, iteration: 2/100, moves: 1038, ncost: 43542.98302097722\n",
      "Run: 8, iteration: 3/100, moves: 924, ncost: 42881.24033775151\n",
      "Run: 8, iteration: 4/100, moves: 631, ncost: 42491.31788691923\n",
      "Run: 8, iteration: 5/100, moves: 509, ncost: 42203.22675480116\n",
      "Run: 8, iteration: 6/100, moves: 412, ncost: 42058.24785651465\n",
      "Run: 8, iteration: 7/100, moves: 226, ncost: 42012.593754262096\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Run: 8, iteration: 8/100, moves: 114, ncost: 42000.60539527798\n",
      "Run: 8, iteration: 9/100, moves: 92, ncost: 41990.77458475859\n",
      "Run: 8, iteration: 10/100, moves: 39, ncost: 41988.42789926502\n",
      "Run: 8, iteration: 11/100, moves: 37, ncost: 41985.97249469417\n",
      "Run: 8, iteration: 12/100, moves: 15, ncost: 41985.66987788474\n",
      "Run: 8, iteration: 13/100, moves: 17, ncost: 41985.21467575553\n",
      "Run: 8, iteration: 14/100, moves: 10, ncost: 41985.05512206572\n",
      "Run: 8, iteration: 15/100, moves: 1, ncost: 41985.045903069724\n",
      "Run: 8, iteration: 16/100, moves: 0, ncost: 41985.045903069724\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 9, iteration: 1/100, moves: 1572, ncost: 45250.2468638323\n",
      "Run: 9, iteration: 2/100, moves: 1187, ncost: 43306.023793413246\n",
      "Run: 9, iteration: 3/100, moves: 712, ncost: 42688.35717897862\n",
      "Run: 9, iteration: 4/100, moves: 540, ncost: 42524.88917206295\n",
      "Run: 9, iteration: 5/100, moves: 257, ncost: 42436.692081033456\n",
      "Run: 9, iteration: 6/100, moves: 173, ncost: 42408.580317104694\n",
      "Run: 9, iteration: 7/100, moves: 102, ncost: 42395.11967296615\n",
      "Run: 9, iteration: 8/100, moves: 64, ncost: 42389.9074194054\n",
      "Run: 9, iteration: 9/100, moves: 36, ncost: 42388.57197978771\n",
      "Run: 9, iteration: 10/100, moves: 19, ncost: 42387.85518102076\n",
      "Run: 9, iteration: 11/100, moves: 14, ncost: 42386.70317621285\n",
      "Run: 9, iteration: 12/100, moves: 8, ncost: 42386.54495428694\n",
      "Run: 9, iteration: 13/100, moves: 2, ncost: 42386.52418975031\n",
      "Run: 9, iteration: 14/100, moves: 3, ncost: 42386.493266319034\n",
      "Run: 9, iteration: 15/100, moves: 0, ncost: 42386.493266319034\n",
      "Init: initializing centroids\n",
      "Init: initializing clusters\n",
      "Starting iterations...\n",
      "Run: 10, iteration: 1/100, moves: 1202, ncost: 45584.36540100236\n",
      "Run: 10, iteration: 2/100, moves: 967, ncost: 44612.72993497613\n",
      "Run: 10, iteration: 3/100, moves: 903, ncost: 43320.11295116219\n",
      "Run: 10, iteration: 4/100, moves: 683, ncost: 42658.218120261336\n",
      "Run: 10, iteration: 5/100, moves: 416, ncost: 42524.855948544886\n",
      "Run: 10, iteration: 6/100, moves: 177, ncost: 42495.303053526826\n",
      "Run: 10, iteration: 7/100, moves: 142, ncost: 42463.30809571498\n",
      "Run: 10, iteration: 8/100, moves: 160, ncost: 42402.60555389769\n",
      "Run: 10, iteration: 9/100, moves: 70, ncost: 42392.56260121595\n",
      "Run: 10, iteration: 10/100, moves: 37, ncost: 42389.24522732779\n",
      "Run: 10, iteration: 11/100, moves: 16, ncost: 42388.236795555684\n",
      "Run: 10, iteration: 12/100, moves: 8, ncost: 42387.73745175293\n",
      "Run: 10, iteration: 13/100, moves: 16, ncost: 42386.492763851675\n",
      "Run: 10, iteration: 14/100, moves: 2, ncost: 42386.46816528233\n",
      "Run: 10, iteration: 15/100, moves: 0, ncost: 42386.46816528233\n",
      "Best run was number 6\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([2, 2, 2, ..., 1, 2, 2], dtype=uint16)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kproto.fit_predict(final_data_array,categorical=[0,1,2,3])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([['1.4892479757271928', '-0.17866403872290276',\n",
       "        '1.8528232498282782', '0.022514279683447786',\n",
       "        '-0.0044803090434404995', '1.5534283318919457',\n",
       "        '0.05841242762031066', 'California', 'Extended', 'Suburban',\n",
       "        'SUV'],\n",
       "       ['-0.14719282878528323', '0.964370037557572',\n",
       "        '-0.24110631112290754', '-0.06802247735658976',\n",
       "        '0.0794618380306117', '-0.5022677261053352',\n",
       "        '-0.022226919467376642', 'California', 'Basic', 'Rural',\n",
       "        'Four-Door Car'],\n",
       "       ['-0.23807796696267414', '-0.7465400492202009',\n",
       "        '-0.24873173020243483', '0.05027100686665932',\n",
       "        '-0.06397908602880217', '0.03717920157933059',\n",
       "        '0.004133005118793087', 'California', 'Basic', 'Suburban',\n",
       "        'Four-Door Car']], dtype='<U32')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cluster centroid\n",
    "\n",
    "kproto.cluster_centroids_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Assign cluster labels to original dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "marketing_data['cluster'] = kproto.labels_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>State</th>\n",
       "      <th>CLV</th>\n",
       "      <th>Coverage</th>\n",
       "      <th>Income</th>\n",
       "      <th>loc_type</th>\n",
       "      <th>monthly_premium</th>\n",
       "      <th>months_last_claim</th>\n",
       "      <th>Months_Since_Policy_Inception</th>\n",
       "      <th>Total_Claim_Amount</th>\n",
       "      <th>Vehicle_Class</th>\n",
       "      <th>avg_vehicle_age</th>\n",
       "      <th>cluster</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Washington</td>\n",
       "      <td>2763.519279</td>\n",
       "      <td>Basic</td>\n",
       "      <td>56274</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>69</td>\n",
       "      <td>32</td>\n",
       "      <td>5</td>\n",
       "      <td>384.811147</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>40.696695</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Nevada</td>\n",
       "      <td>12887.431650</td>\n",
       "      <td>Premium</td>\n",
       "      <td>48767</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>108</td>\n",
       "      <td>18</td>\n",
       "      <td>38</td>\n",
       "      <td>566.472247</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>48.755298</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Washington</td>\n",
       "      <td>2813.692575</td>\n",
       "      <td>Basic</td>\n",
       "      <td>43836</td>\n",
       "      <td>Rural</td>\n",
       "      <td>73</td>\n",
       "      <td>12</td>\n",
       "      <td>44</td>\n",
       "      <td>138.130879</td>\n",
       "      <td>Four-Door Car</td>\n",
       "      <td>70.394474</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Oregon</td>\n",
       "      <td>8256.297800</td>\n",
       "      <td>Basic</td>\n",
       "      <td>62902</td>\n",
       "      <td>Rural</td>\n",
       "      <td>69</td>\n",
       "      <td>14</td>\n",
       "      <td>94</td>\n",
       "      <td>159.383042</td>\n",
       "      <td>Two-Door Car</td>\n",
       "      <td>53.460212</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Oregon</td>\n",
       "      <td>5380.898636</td>\n",
       "      <td>Basic</td>\n",
       "      <td>55350</td>\n",
       "      <td>Suburban</td>\n",
       "      <td>67</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>321.600000</td>\n",
       "      <td>Four-Door Car</td>\n",
       "      <td>32.811507</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        State           CLV Coverage  Income  loc_type  monthly_premium  \\\n",
       "0  Washington   2763.519279    Basic   56274  Suburban               69   \n",
       "1      Nevada  12887.431650  Premium   48767  Suburban              108   \n",
       "2  Washington   2813.692575    Basic   43836     Rural               73   \n",
       "3      Oregon   8256.297800    Basic   62902     Rural               69   \n",
       "4      Oregon   5380.898636    Basic   55350  Suburban               67   \n",
       "\n",
       "   months_last_claim  Months_Since_Policy_Inception  Total_Claim_Amount  \\\n",
       "0                 32                              5          384.811147   \n",
       "1                 18                             38          566.472247   \n",
       "2                 12                             44          138.130879   \n",
       "3                 14                             94          159.383042   \n",
       "4                  0                             13          321.600000   \n",
       "\n",
       "   Vehicle_Class  avg_vehicle_age  cluster  \n",
       "0   Two-Door Car        40.696695        2  \n",
       "1   Two-Door Car        48.755298        2  \n",
       "2  Four-Door Car        70.394474        2  \n",
       "3   Two-Door Car        53.460212        1  \n",
       "4  Four-Door Car        32.811507        2  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "marketing_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}