Clustering_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Importando as Bibliotecas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.preprocessing import Normalizer\n",
    "from sklearn import metrics\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import math\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "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>BALANCE</th>\n",
       "      <th>BALANCE_FREQUENCY</th>\n",
       "      <th>PURCHASES</th>\n",
       "      <th>ONEOFF_PURCHASES</th>\n",
       "      <th>INSTALLMENTS_PURCHASES</th>\n",
       "      <th>CASH_ADVANCE</th>\n",
       "      <th>PURCHASES_FREQUENCY</th>\n",
       "      <th>ONEOFF_PURCHASES_FREQUENCY</th>\n",
       "      <th>PURCHASES_INSTALLMENTS_FREQUENCY</th>\n",
       "      <th>CASH_ADVANCE_FREQUENCY</th>\n",
       "      <th>CASH_ADVANCE_TRX</th>\n",
       "      <th>PURCHASES_TRX</th>\n",
       "      <th>CREDIT_LIMIT</th>\n",
       "      <th>PAYMENTS</th>\n",
       "      <th>MINIMUM_PAYMENTS</th>\n",
       "      <th>PRC_FULL_PAYMENT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>40.900749</td>\n",
       "      <td>0.818182</td>\n",
       "      <td>95.40</td>\n",
       "      <td>0.00</td>\n",
       "      <td>95.4</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1000.0</td>\n",
       "      <td>201.802084</td>\n",
       "      <td>139.509787</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3202.467416</td>\n",
       "      <td>0.909091</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6442.945483</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.250000</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>7000.0</td>\n",
       "      <td>4103.032597</td>\n",
       "      <td>1072.340217</td>\n",
       "      <td>0.222222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2495.148862</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>773.17</td>\n",
       "      <td>773.17</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>7500.0</td>\n",
       "      <td>622.066742</td>\n",
       "      <td>627.284787</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1666.670542</td>\n",
       "      <td>0.636364</td>\n",
       "      <td>1499.00</td>\n",
       "      <td>1499.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>205.788017</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7500.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>817.714335</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>16.00</td>\n",
       "      <td>16.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1200.0</td>\n",
       "      <td>678.334763</td>\n",
       "      <td>244.791237</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       BALANCE  BALANCE_FREQUENCY  PURCHASES  ONEOFF_PURCHASES  \\\n",
       "0    40.900749           0.818182      95.40              0.00   \n",
       "1  3202.467416           0.909091       0.00              0.00   \n",
       "2  2495.148862           1.000000     773.17            773.17   \n",
       "3  1666.670542           0.636364    1499.00           1499.00   \n",
       "4   817.714335           1.000000      16.00             16.00   \n",
       "\n",
       "   INSTALLMENTS_PURCHASES  CASH_ADVANCE  PURCHASES_FREQUENCY  \\\n",
       "0                    95.4      0.000000             0.166667   \n",
       "1                     0.0   6442.945483             0.000000   \n",
       "2                     0.0      0.000000             1.000000   \n",
       "3                     0.0    205.788017             0.083333   \n",
       "4                     0.0      0.000000             0.083333   \n",
       "\n",
       "   ONEOFF_PURCHASES_FREQUENCY  PURCHASES_INSTALLMENTS_FREQUENCY  \\\n",
       "0                    0.000000                          0.083333   \n",
       "1                    0.000000                          0.000000   \n",
       "2                    1.000000                          0.000000   \n",
       "3                    0.083333                          0.000000   \n",
       "4                    0.083333                          0.000000   \n",
       "\n",
       "   CASH_ADVANCE_FREQUENCY  CASH_ADVANCE_TRX  PURCHASES_TRX  CREDIT_LIMIT  \\\n",
       "0                0.000000                 0              2        1000.0   \n",
       "1                0.250000                 4              0        7000.0   \n",
       "2                0.000000                 0             12        7500.0   \n",
       "3                0.083333                 1              1        7500.0   \n",
       "4                0.000000                 0              1        1200.0   \n",
       "\n",
       "      PAYMENTS  MINIMUM_PAYMENTS  PRC_FULL_PAYMENT  \n",
       "0   201.802084        139.509787          0.000000  \n",
       "1  4103.032597       1072.340217          0.222222  \n",
       "2   622.066742        627.284787          0.000000  \n",
       "3     0.000000               NaN          0.000000  \n",
       "4   678.334763        244.791237          0.000000  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"CC GENERAL.csv\")\n",
    "df.drop(columns=[\"CUST_ID\", \"TENURE\"], inplace=True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "O dado possui 8950 amostras e 16 atributos\n"
     ]
    }
   ],
   "source": [
    "print(\"O dado possui\",df.shape[0], \"amostras e\", df.shape[1], \"atributos\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BALANCE                               0\n",
      "BALANCE_FREQUENCY                     0\n",
      "PURCHASES                             0\n",
      "ONEOFF_PURCHASES                      0\n",
      "INSTALLMENTS_PURCHASES                0\n",
      "CASH_ADVANCE                          0\n",
      "PURCHASES_FREQUENCY                   0\n",
      "ONEOFF_PURCHASES_FREQUENCY            0\n",
      "PURCHASES_INSTALLMENTS_FREQUENCY      0\n",
      "CASH_ADVANCE_FREQUENCY                0\n",
      "CASH_ADVANCE_TRX                      0\n",
      "PURCHASES_TRX                         0\n",
      "CREDIT_LIMIT                          1\n",
      "PAYMENTS                              0\n",
      "MINIMUM_PAYMENTS                    313\n",
      "PRC_FULL_PAYMENT                      0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "missing = df.isna().sum()\n",
    "print(missing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BALANCE                             0\n",
      "BALANCE_FREQUENCY                   0\n",
      "PURCHASES                           0\n",
      "ONEOFF_PURCHASES                    0\n",
      "INSTALLMENTS_PURCHASES              0\n",
      "CASH_ADVANCE                        0\n",
      "PURCHASES_FREQUENCY                 0\n",
      "ONEOFF_PURCHASES_FREQUENCY          0\n",
      "PURCHASES_INSTALLMENTS_FREQUENCY    0\n",
      "CASH_ADVANCE_FREQUENCY              0\n",
      "CASH_ADVANCE_TRX                    0\n",
      "PURCHASES_TRX                       0\n",
      "CREDIT_LIMIT                        0\n",
      "PAYMENTS                            0\n",
      "MINIMUM_PAYMENTS                    0\n",
      "PRC_FULL_PAYMENT                    0\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "df.fillna(df.median(), inplace=True)\n",
    "missing = df.isna().sum()\n",
    "print(missing)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Feature Engineering - 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1224x1080 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "matriz_correlacao =df.corr()\n",
    "plt.figure(figsize = (17, 15))\n",
    "sns.heatmap(matriz_correlacao, annot = True, fmt = \".1f\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead 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>BALANCE</th>\n",
       "      <th>BALANCE_FREQUENCY</th>\n",
       "      <th>PURCHASES</th>\n",
       "      <th>ONEOFF_PURCHASES</th>\n",
       "      <th>INSTALLMENTS_PURCHASES</th>\n",
       "      <th>CASH_ADVANCE</th>\n",
       "      <th>PURCHASES_FREQUENCY</th>\n",
       "      <th>ONEOFF_PURCHASES_FREQUENCY</th>\n",
       "      <th>PURCHASES_INSTALLMENTS_FREQUENCY</th>\n",
       "      <th>CASH_ADVANCE_FREQUENCY</th>\n",
       "      <th>CASH_ADVANCE_TRX</th>\n",
       "      <th>PURCHASES_TRX</th>\n",
       "      <th>CREDIT_LIMIT</th>\n",
       "      <th>PAYMENTS</th>\n",
       "      <th>MINIMUM_PAYMENTS</th>\n",
       "      <th>PRC_FULL_PAYMENT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>BALANCE</th>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BALANCE_FREQUENCY</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PURCHASES</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.916845</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ONEOFF_PURCHASES</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.916845</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>INSTALLMENTS_PURCHASES</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CASH_ADVANCE</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PURCHASES_FREQUENCY</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.862934</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ONEOFF_PURCHASES_FREQUENCY</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PURCHASES_INSTALLMENTS_FREQUENCY</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.862934</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CASH_ADVANCE_FREQUENCY</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CASH_ADVANCE_TRX</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PURCHASES_TRX</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CREDIT_LIMIT</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PAYMENTS</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MINIMUM_PAYMENTS</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PRC_FULL_PAYMENT</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  BALANCE  BALANCE_FREQUENCY  PURCHASES  \\\n",
       "BALANCE                               1.0                NaN        NaN   \n",
       "BALANCE_FREQUENCY                     NaN                1.0        NaN   \n",
       "PURCHASES                             NaN                NaN   1.000000   \n",
       "ONEOFF_PURCHASES                      NaN                NaN   0.916845   \n",
       "INSTALLMENTS_PURCHASES                NaN                NaN        NaN   \n",
       "CASH_ADVANCE                          NaN                NaN        NaN   \n",
       "PURCHASES_FREQUENCY                   NaN                NaN        NaN   \n",
       "ONEOFF_PURCHASES_FREQUENCY            NaN                NaN        NaN   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY      NaN                NaN        NaN   \n",
       "CASH_ADVANCE_FREQUENCY                NaN                NaN        NaN   \n",
       "CASH_ADVANCE_TRX                      NaN                NaN        NaN   \n",
       "PURCHASES_TRX                         NaN                NaN        NaN   \n",
       "CREDIT_LIMIT                          NaN                NaN        NaN   \n",
       "PAYMENTS                              NaN                NaN        NaN   \n",
       "MINIMUM_PAYMENTS                      NaN                NaN        NaN   \n",
       "PRC_FULL_PAYMENT                      NaN                NaN        NaN   \n",
       "\n",
       "                                  ONEOFF_PURCHASES  INSTALLMENTS_PURCHASES  \\\n",
       "BALANCE                                        NaN                     NaN   \n",
       "BALANCE_FREQUENCY                              NaN                     NaN   \n",
       "PURCHASES                                 0.916845                     NaN   \n",
       "ONEOFF_PURCHASES                          1.000000                     NaN   \n",
       "INSTALLMENTS_PURCHASES                         NaN                     1.0   \n",
       "CASH_ADVANCE                                   NaN                     NaN   \n",
       "PURCHASES_FREQUENCY                            NaN                     NaN   \n",
       "ONEOFF_PURCHASES_FREQUENCY                     NaN                     NaN   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY               NaN                     NaN   \n",
       "CASH_ADVANCE_FREQUENCY                         NaN                     NaN   \n",
       "CASH_ADVANCE_TRX                               NaN                     NaN   \n",
       "PURCHASES_TRX                                  NaN                     NaN   \n",
       "CREDIT_LIMIT                                   NaN                     NaN   \n",
       "PAYMENTS                                       NaN                     NaN   \n",
       "MINIMUM_PAYMENTS                               NaN                     NaN   \n",
       "PRC_FULL_PAYMENT                               NaN                     NaN   \n",
       "\n",
       "                                  CASH_ADVANCE  PURCHASES_FREQUENCY  \\\n",
       "BALANCE                                    NaN                  NaN   \n",
       "BALANCE_FREQUENCY                          NaN                  NaN   \n",
       "PURCHASES                                  NaN                  NaN   \n",
       "ONEOFF_PURCHASES                           NaN                  NaN   \n",
       "INSTALLMENTS_PURCHASES                     NaN                  NaN   \n",
       "CASH_ADVANCE                               1.0                  NaN   \n",
       "PURCHASES_FREQUENCY                        NaN             1.000000   \n",
       "ONEOFF_PURCHASES_FREQUENCY                 NaN                  NaN   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY           NaN             0.862934   \n",
       "CASH_ADVANCE_FREQUENCY                     NaN                  NaN   \n",
       "CASH_ADVANCE_TRX                           NaN                  NaN   \n",
       "PURCHASES_TRX                              NaN                  NaN   \n",
       "CREDIT_LIMIT                               NaN                  NaN   \n",
       "PAYMENTS                                   NaN                  NaN   \n",
       "MINIMUM_PAYMENTS                           NaN                  NaN   \n",
       "PRC_FULL_PAYMENT                           NaN                  NaN   \n",
       "\n",
       "                                  ONEOFF_PURCHASES_FREQUENCY  \\\n",
       "BALANCE                                                  NaN   \n",
       "BALANCE_FREQUENCY                                        NaN   \n",
       "PURCHASES                                                NaN   \n",
       "ONEOFF_PURCHASES                                         NaN   \n",
       "INSTALLMENTS_PURCHASES                                   NaN   \n",
       "CASH_ADVANCE                                             NaN   \n",
       "PURCHASES_FREQUENCY                                      NaN   \n",
       "ONEOFF_PURCHASES_FREQUENCY                               1.0   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY                         NaN   \n",
       "CASH_ADVANCE_FREQUENCY                                   NaN   \n",
       "CASH_ADVANCE_TRX                                         NaN   \n",
       "PURCHASES_TRX                                            NaN   \n",
       "CREDIT_LIMIT                                             NaN   \n",
       "PAYMENTS                                                 NaN   \n",
       "MINIMUM_PAYMENTS                                         NaN   \n",
       "PRC_FULL_PAYMENT                                         NaN   \n",
       "\n",
       "                                  PURCHASES_INSTALLMENTS_FREQUENCY  \\\n",
       "BALANCE                                                        NaN   \n",
       "BALANCE_FREQUENCY                                              NaN   \n",
       "PURCHASES                                                      NaN   \n",
       "ONEOFF_PURCHASES                                               NaN   \n",
       "INSTALLMENTS_PURCHASES                                         NaN   \n",
       "CASH_ADVANCE                                                   NaN   \n",
       "PURCHASES_FREQUENCY                                       0.862934   \n",
       "ONEOFF_PURCHASES_FREQUENCY                                     NaN   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY                          1.000000   \n",
       "CASH_ADVANCE_FREQUENCY                                         NaN   \n",
       "CASH_ADVANCE_TRX                                               NaN   \n",
       "PURCHASES_TRX                                                  NaN   \n",
       "CREDIT_LIMIT                                                   NaN   \n",
       "PAYMENTS                                                       NaN   \n",
       "MINIMUM_PAYMENTS                                               NaN   \n",
       "PRC_FULL_PAYMENT                                               NaN   \n",
       "\n",
       "                                  CASH_ADVANCE_FREQUENCY  CASH_ADVANCE_TRX  \\\n",
       "BALANCE                                              NaN               NaN   \n",
       "BALANCE_FREQUENCY                                    NaN               NaN   \n",
       "PURCHASES                                            NaN               NaN   \n",
       "ONEOFF_PURCHASES                                     NaN               NaN   \n",
       "INSTALLMENTS_PURCHASES                               NaN               NaN   \n",
       "CASH_ADVANCE                                         NaN               NaN   \n",
       "PURCHASES_FREQUENCY                                  NaN               NaN   \n",
       "ONEOFF_PURCHASES_FREQUENCY                           NaN               NaN   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY                     NaN               NaN   \n",
       "CASH_ADVANCE_FREQUENCY                               1.0               NaN   \n",
       "CASH_ADVANCE_TRX                                     NaN               1.0   \n",
       "PURCHASES_TRX                                        NaN               NaN   \n",
       "CREDIT_LIMIT                                         NaN               NaN   \n",
       "PAYMENTS                                             NaN               NaN   \n",
       "MINIMUM_PAYMENTS                                     NaN               NaN   \n",
       "PRC_FULL_PAYMENT                                     NaN               NaN   \n",
       "\n",
       "                                  PURCHASES_TRX  CREDIT_LIMIT  PAYMENTS  \\\n",
       "BALANCE                                     NaN           NaN       NaN   \n",
       "BALANCE_FREQUENCY                           NaN           NaN       NaN   \n",
       "PURCHASES                                   NaN           NaN       NaN   \n",
       "ONEOFF_PURCHASES                            NaN           NaN       NaN   \n",
       "INSTALLMENTS_PURCHASES                      NaN           NaN       NaN   \n",
       "CASH_ADVANCE                                NaN           NaN       NaN   \n",
       "PURCHASES_FREQUENCY                         NaN           NaN       NaN   \n",
       "ONEOFF_PURCHASES_FREQUENCY                  NaN           NaN       NaN   \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY            NaN           NaN       NaN   \n",
       "CASH_ADVANCE_FREQUENCY                      NaN           NaN       NaN   \n",
       "CASH_ADVANCE_TRX                            NaN           NaN       NaN   \n",
       "PURCHASES_TRX                               1.0           NaN       NaN   \n",
       "CREDIT_LIMIT                                NaN           1.0       NaN   \n",
       "PAYMENTS                                    NaN           NaN       1.0   \n",
       "MINIMUM_PAYMENTS                            NaN           NaN       NaN   \n",
       "PRC_FULL_PAYMENT                            NaN           NaN       NaN   \n",
       "\n",
       "                                  MINIMUM_PAYMENTS  PRC_FULL_PAYMENT  \n",
       "BALANCE                                        NaN               NaN  \n",
       "BALANCE_FREQUENCY                              NaN               NaN  \n",
       "PURCHASES                                      NaN               NaN  \n",
       "ONEOFF_PURCHASES                               NaN               NaN  \n",
       "INSTALLMENTS_PURCHASES                         NaN               NaN  \n",
       "CASH_ADVANCE                                   NaN               NaN  \n",
       "PURCHASES_FREQUENCY                            NaN               NaN  \n",
       "ONEOFF_PURCHASES_FREQUENCY                     NaN               NaN  \n",
       "PURCHASES_INSTALLMENTS_FREQUENCY               NaN               NaN  \n",
       "CASH_ADVANCE_FREQUENCY                         NaN               NaN  \n",
       "CASH_ADVANCE_TRX                               NaN               NaN  \n",
       "PURCHASES_TRX                                  NaN               NaN  \n",
       "CREDIT_LIMIT                                   NaN               NaN  \n",
       "PAYMENTS                                       NaN               NaN  \n",
       "MINIMUM_PAYMENTS                               1.0               NaN  \n",
       "PRC_FULL_PAYMENT                               NaN               1.0  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "matriz_correlacao_v1 = matriz_correlacao[matriz_correlacao>0.85]\n",
    "matriz_correlacao_v1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = df.drop(columns=[\"ONEOFF_PURCHASES\", \"PURCHASES_INSTALLMENTS_FREQUENCY\"]) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Rodando os Modelos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def calcular_wcss(data):\n",
    "    wcss = []\n",
    "    for k in range(1,10):\n",
    "        kmeans = KMeans(n_clusters = k)\n",
    "        kmeans.fit(X=data)\n",
    "        data['Clusters']=kmeans.labels_\n",
    "        wcss.append(kmeans.inertia_)\n",
    "    return wcss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n",
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/3053334412.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  data['Clusters']=kmeans.labels_\n"
     ]
    }
   ],
   "source": [
    "df_balance = df[['BALANCE']]\n",
    "df_balance.head()\n",
    "soma_quadrados = calcular_wcss(df_balance)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,5))\n",
    "plt.plot(soma_quadrados)\n",
    "plt.xlabel('Número de clusters')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "x1, y1 = 2,soma_quadrados[0]\n",
    "x2, y2 = 10,soma_quadrados[len(soma_quadrados)-1]\n",
    "    \n",
    "new = []\n",
    "for i in range(len(soma_quadrados)):\n",
    "    x0 = i+2\n",
    "    y0 = soma_quadrados[i]\n",
    "    numerador = abs((y2 - y1)*x0 - (x2 - x1)*y0 + x2*y1 - y2*x1)\n",
    "    denominador = math.sqrt((y2 - y1)**2 + (x2 - x1)**2)\n",
    "    new.append(numerador/denominador)\n",
    "\n",
    "melhor_cluster = new.index(max(new)) + 2\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "values = Normalizer().fit_transform(df.values)\n",
    "kmeans = KMeans(n_clusters=melhor_cluster, n_init=10, max_iter=300)\n",
    "y_pred = kmeans.fit_predict(values)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Validação com o Silhouette, Davies Bouldin, Calinski"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def clustering_algorithm(n_clusters, dataset):\n",
    "    kmeans = KMeans(n_clusters=melhor_cluster, n_init=10, max_iter=300)\n",
    "    labels = kmeans.fit_predict(dataset)\n",
    "    s = metrics.silhouette_score(dataset, labels, metric='euclidean')\n",
    "    dbs = metrics.davies_bouldin_score(dataset, labels)\n",
    "    calinski = metrics.calinski_harabasz_score(dataset, labels)\n",
    "    return s, dbs, calinski"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.34825743673945714 1.2212897290249243 3528.7176223195843\n",
      "0.040008075044657365 3.8619621663882 332.40937002647536\n"
     ]
    }
   ],
   "source": [
    "random_data = np.random.rand(8950, 16)\n",
    "\n",
    "s1, dbs1, calinski1 = clustering_algorithm(5, values)\n",
    "s, dbs, calinski = clustering_algorithm(melhor_cluster, random_data)\n",
    "print(s1, dbs1, calinski1)\n",
    "print(s, dbs, calinski)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.3539365567789984 1.1600500216962613 1205.0962308393632\n",
      "0.3579918892235798 1.1481051277562329 1212.520678199777\n",
      "0.35748343068042765 1.2647292659421105 1177.0044108806744\n"
     ]
    }
   ],
   "source": [
    "set1, set2, set3 = np.array_split(values, 3) \n",
    "s1, dbs1, calinski1 = clustering_algorithm(melhor_cluster, set1)\n",
    "s2, dbs2, calinski2 = clustering_algorithm(melhor_cluster, set2)\n",
    "s3, dbs3, calinski3 = clustering_algorithm(melhor_cluster, set3)\n",
    "print(s1, dbs1, calinski1)\n",
    "print(s2, dbs2, calinski2)\n",
    "print(s3, dbs3, calinski3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# EDA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "labels = kmeans.labels_\n",
    "df[\"cluster\"] = labels\n",
    "\n",
    "plt.scatter(df['PURCHASES'], df['PAYMENTS'], c= labels, s=5, cmap='rainbow')\n",
    "plt.xlabel(\"Valor total pago\")\n",
    "plt.ylabel(\"Valor total gasto\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Feature Engineering - 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">BALANCE</th>\n",
       "      <th colspan=\"2\" halign=\"left\">BALANCE_FREQUENCY</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">MINIMUM_PAYMENTS</th>\n",
       "      <th colspan=\"8\" halign=\"left\">PRC_FULL_PAYMENT</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cluster</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2214.0</td>\n",
       "      <td>3135.603247</td>\n",
       "      <td>2575.447077</td>\n",
       "      <td>114.523682</td>\n",
       "      <td>1287.939171</td>\n",
       "      <td>2109.140702</td>\n",
       "      <td>4394.912690</td>\n",
       "      <td>18495.558550</td>\n",
       "      <td>2214.0</td>\n",
       "      <td>0.996246</td>\n",
       "      <td>...</td>\n",
       "      <td>1852.325655</td>\n",
       "      <td>76406.207520</td>\n",
       "      <td>2214.0</td>\n",
       "      <td>0.001476</td>\n",
       "      <td>0.012044</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.181818</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3366.0</td>\n",
       "      <td>494.425578</td>\n",
       "      <td>911.098284</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>24.689935</td>\n",
       "      <td>88.864667</td>\n",
       "      <td>477.056467</td>\n",
       "      <td>7533.854422</td>\n",
       "      <td>3366.0</td>\n",
       "      <td>0.782325</td>\n",
       "      <td>...</td>\n",
       "      <td>266.655387</td>\n",
       "      <td>3933.230932</td>\n",
       "      <td>3366.0</td>\n",
       "      <td>0.241182</td>\n",
       "      <td>0.344302</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.416667</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1657.0</td>\n",
       "      <td>1112.504042</td>\n",
       "      <td>1630.639904</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>208.581872</td>\n",
       "      <td>544.879717</td>\n",
       "      <td>1296.922119</td>\n",
       "      <td>19043.138560</td>\n",
       "      <td>1657.0</td>\n",
       "      <td>0.911103</td>\n",
       "      <td>...</td>\n",
       "      <td>574.771719</td>\n",
       "      <td>18621.013310</td>\n",
       "      <td>1657.0</td>\n",
       "      <td>0.272632</td>\n",
       "      <td>0.361402</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1713.0</td>\n",
       "      <td>2073.653488</td>\n",
       "      <td>1992.529303</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>722.404832</td>\n",
       "      <td>1396.385805</td>\n",
       "      <td>2784.030599</td>\n",
       "      <td>14581.459140</td>\n",
       "      <td>1713.0</td>\n",
       "      <td>0.877338</td>\n",
       "      <td>...</td>\n",
       "      <td>936.940012</td>\n",
       "      <td>21235.065300</td>\n",
       "      <td>1713.0</td>\n",
       "      <td>0.063577</td>\n",
       "      <td>0.144426</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4 rows × 128 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        BALANCE                                                     \\\n",
       "          count         mean          std         min          25%   \n",
       "cluster                                                              \n",
       "0        2214.0  3135.603247  2575.447077  114.523682  1287.939171   \n",
       "1        3366.0   494.425578   911.098284    0.000000    24.689935   \n",
       "2        1657.0  1112.504042  1630.639904    0.000000   208.581872   \n",
       "3        1713.0  2073.653488  1992.529303    0.000000   722.404832   \n",
       "\n",
       "                                                BALANCE_FREQUENCY            \\\n",
       "                 50%          75%           max             count      mean   \n",
       "cluster                                                                       \n",
       "0        2109.140702  4394.912690  18495.558550            2214.0  0.996246   \n",
       "1          88.864667   477.056467   7533.854422            3366.0  0.782325   \n",
       "2         544.879717  1296.922119  19043.138560            1657.0  0.911103   \n",
       "3        1396.385805  2784.030599  14581.459140            1713.0  0.877338   \n",
       "\n",
       "         ... MINIMUM_PAYMENTS               PRC_FULL_PAYMENT            \\\n",
       "         ...              75%           max            count      mean   \n",
       "cluster  ...                                                             \n",
       "0        ...      1852.325655  76406.207520           2214.0  0.001476   \n",
       "1        ...       266.655387   3933.230932           3366.0  0.241182   \n",
       "2        ...       574.771719  18621.013310           1657.0  0.272632   \n",
       "3        ...       936.940012  21235.065300           1713.0  0.063577   \n",
       "\n",
       "                                                           \n",
       "              std  min  25%       50%       75%       max  \n",
       "cluster                                                    \n",
       "0        0.012044  0.0  0.0  0.000000  0.000000  0.181818  \n",
       "1        0.344302  0.0  0.0  0.000000  0.416667  1.000000  \n",
       "2        0.361402  0.0  0.0  0.083333  0.500000  1.000000  \n",
       "3        0.144426  0.0  0.0  0.000000  0.083333  1.000000  \n",
       "\n",
       "[4 rows x 128 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"cluster\").describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[5.28987034e-01 2.88650584e-04 8.55725867e-02 4.24377039e-02\n",
      "  4.32299306e-02 1.18679409e-01 9.23415704e-05 2.96846643e-05\n",
      "  6.81379545e-05 4.18384713e-05 7.73094730e-04 1.98084797e-03\n",
      "  6.63315961e-01 1.96171274e-01 2.83563247e-01 4.11163583e-07]\n",
      " [7.56762644e-02 2.29872695e-04 1.22931772e-01 4.99541404e-02\n",
      "  7.30767015e-02 2.48419116e-02 1.70838317e-04 3.41839200e-05\n",
      "  1.38191155e-04 8.27756382e-06 1.30236659e-04 2.85628436e-03\n",
      "  9.41926347e-01 1.53223035e-01 5.72492681e-02 7.40359697e-05]\n",
      " [1.55943825e-01 2.41722117e-04 4.15911123e-01 2.39890351e-01\n",
      "  1.76177597e-01 3.48987276e-02 1.97215850e-04 8.45428702e-05\n",
      "  1.45452886e-04 1.11934483e-05 2.14789401e-04 5.89638957e-03\n",
      "  5.81981930e-01 4.41084482e-01 9.95348919e-02 7.07000013e-05]\n",
      " [2.99782071e-01 2.24374000e-04 4.29997757e-02 2.37095105e-02\n",
      "  1.92962590e-02 4.88897968e-01 4.57117049e-05 1.59833073e-05\n",
      "  3.05868491e-05 7.68310609e-05 1.80110502e-03 8.37488044e-04\n",
      "  6.15346508e-01 3.66115545e-01 1.16169613e-01 1.51920662e-05]]\n"
     ]
    }
   ],
   "source": [
    "centroids = kmeans.cluster_centers_\n",
    "print(centroids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BALANCE \n",
      "0.0297\n",
      "BALANCE_FREQUENCY \n",
      "0.0000\n",
      "PURCHASES \n",
      "0.0215\n",
      "ONEOFF_PURCHASES \n",
      "0.0077\n",
      "INSTALLMENTS_PURCHASES \n",
      "0.0036\n",
      "CASH_ADVANCE \n",
      "0.0359\n",
      "PURCHASES_FREQUENCY \n",
      "0.0000\n",
      "ONEOFF_PURCHASES_FREQUENCY \n",
      "0.0000\n",
      "PURCHASES_INSTALLMENTS_FREQUENCY \n",
      "0.0000\n",
      "CASH_ADVANCE_FREQUENCY \n",
      "0.0000\n",
      "CASH_ADVANCE_TRX \n",
      "0.0000\n",
      "PURCHASES_TRX \n",
      "0.0000\n",
      "CREDIT_LIMIT \n",
      "0.0202\n",
      "PAYMENTS \n",
      "0.0140\n",
      "MINIMUM_PAYMENTS \n",
      "0.0074\n",
      "PRC_FULL_PAYMENT \n",
      "0.0000\n"
     ]
    }
   ],
   "source": [
    "max = len(centroids[0])\n",
    "for i in range(max):\n",
    "    print(df.columns.values[i],\"\\n{:.4f}\".format(centroids[:, i].var()))\n",
    "# df.columns.values[i] pega cada coluna do df\n",
    "# \"\\n{:.4f}\" até 4 casas depois da virgula para o resultado\n",
    "# format(centroids[:, i].var()) pega todos os centroides (:) com base em todos para o atributo representado por i\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "             BALANCE    PURCHASES  CASH_ADVANCE  CREDIT_LIMIT     PAYMENTS  \\\n",
      "cluster                                                                      \n",
      "0        3135.603247   520.790989    873.709081   4119.557362  1085.707366   \n",
      "1         494.425578   641.730856    154.870275   5174.713505   821.004877   \n",
      "2        1112.504042  3108.849662    260.502413   3976.053870  3349.882383   \n",
      "3        2073.653488   300.188009   3428.814190   4142.861186  2798.379358   \n",
      "\n",
      "         MINIMUM_PAYMENTS  n_clients  \n",
      "cluster                               \n",
      "0             2007.279167       2214  \n",
      "1              237.191607       3366  \n",
      "2              623.344050       1657  \n",
      "3              751.039957       1713  \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/63/r6q02qh978b2cq3rygjg3n1m0000gn/T/ipykernel_19612/1440892446.py:2: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.\n",
      "  description = df.groupby(\"cluster\")[\"BALANCE\", \"PURCHASES\", \"CASH_ADVANCE\", \"CREDIT_LIMIT\", \"PAYMENTS\", \"MINIMUM_PAYMENTS\"]\n"
     ]
    }
   ],
   "source": [
    "#com base na celula anterior, selecionarei as variaveis diferentes de zero: BALANCE 0.0224, PURCHASES 0.0197, CASH_ADVANCE 0.0225, CREDIT_LIMIT 0.0360, PAYMENTS 0.0279, MINIMUM_PAYMENTS 0.0543\n",
    "description = df.groupby(\"cluster\")[\"BALANCE\", \"PURCHASES\", \"CASH_ADVANCE\", \"CREDIT_LIMIT\", \"PAYMENTS\", \"MINIMUM_PAYMENTS\"]\n",
    "n_clients = description.size()\n",
    "description = description.mean()\n",
    "description['n_clients'] = n_clients \n",
    "print(description)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Resultados"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**CLUSTER 0**: Clientes que gastam bem. Clientes com bom limite. Pagadores Razoáveis. Boa quantidade de clientes.\n",
    "\n",
    "**CLUSTER 1**: Clientes que gastam bem. Clientes com o maior limite. Piores pagadores. Boa quantidade de clientes.\n",
    "\n",
    "**CLUSTER 2**: Clientes que gastam bastante. Clientes com o menor limite. Melhores pagadores. Poucos Clientes\n",
    "\n",
    "**CLUSTER 3**: Clientes que gastam pouco. Clientes com bom limite. Pagadores Razoáveis. Poucos Clientes\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cluster</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2214.0</td>\n",
       "      <td>0.001476</td>\n",
       "      <td>0.012044</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.181818</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3366.0</td>\n",
       "      <td>0.241182</td>\n",
       "      <td>0.344302</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.416667</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1657.0</td>\n",
       "      <td>0.272632</td>\n",
       "      <td>0.361402</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1713.0</td>\n",
       "      <td>0.063577</td>\n",
       "      <td>0.144426</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          count      mean       std  min  25%       50%       75%       max\n",
       "cluster                                                                    \n",
       "0        2214.0  0.001476  0.012044  0.0  0.0  0.000000  0.000000  0.181818\n",
       "1        3366.0  0.241182  0.344302  0.0  0.0  0.000000  0.416667  1.000000\n",
       "2        1657.0  0.272632  0.361402  0.0  0.0  0.083333  0.500000  1.000000\n",
       "3        1713.0  0.063577  0.144426  0.0  0.0  0.000000  0.083333  1.000000"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby(\"cluster\")[\"PRC_FULL_PAYMENT\"].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Uma ideia, utilizando esses dados, é montar uma estratégia de negócio em um dos grupos com o objetivo de aumentar o arrecadamento de dinheiro. O grupo mais adequado para isso seria o cluster 0, pois ele possui um bom número de clientes e são bons pagadores, bom limite de crédito. Fazer com que eles utilizem mais o cartão de crédito.\n",
    "\n",
    "O cluster 2 gasta muito com compras e são os melhores pagadores. Eles não possuem um limite de crédito alto, mas podemos incentivá-los a usarem o cartão de crédito aumentando o limite desse grupo.\n",
    "\n",
    "Os piores pagadores devem ter uma estratégia melhor definida para evitar inadimplência.\n",
    "\n",
    "\n",
    "Em análises futuras, podemos aplicar os modelos DBScan e MeanShift."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "500f7f10694b2893afae1da788732c6ac22dc35f0e9089c2212b15742643ccce"
  },
  "kernelspec": {
   "display_name": "Python 3.6.3 64-bit ('base': conda)",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}