{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "----\n",
    "\n",
    "Nama        : Badriah Nursakinah\n",
    "\n",
    "Batch       : BSD_005\n",
    "\n",
    "Dataset     : P1G5_Set_1_badriah_nursakinah.csv\n",
    "\n",
    "Studi Kasus : Memprediksi `default_payment_next_month` dengan model Classification pada dataset yang sudah di simpan pada format csv\n",
    "\n",
    "Link Hugging : https://huggingface.co/spaces/nursakinahbadriah/predict_credit_card_default/tree/main\n",
    "\n",
    "---\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 1. Perkenalan\n",
    "\n",
    "Problem Statement : Sebagai Data Scientiest saya akan mencoba memprediksi `default_payment_next_month`  dengan model Classification, dimana untuk model inference merupakan kesimpulan akhir yang menjawab proses pengolahan data dengan menggunakan model Classification\n",
    "\n",
    "\n",
    "Adapun poin-poin yang akan dianalisa dengan mengunakan metode `Explore Data Analysis` diantaranya sebagai berikut :\n",
    "\n",
    "   - Objective 1 : Memprediksi limit_balance untuk `Age`, `Count`, `Marital_Status`, `Education_Level`\n",
    "   - Objective 2 : Memprediksi usia yang paling banyak membayar\n",
    "   - Objective 3 : Memprediksi jumlah pengguna kartu kredit berdasarkan jenis kelamin\n",
    "   - Objective 4 : Memprediksi pengguna kartu kredit berdsarkan status pernikahan\n",
    "   - Objective 5 : Memprediksi pengguna kartu kredit berdasarkan usia\n",
    "   - Objective 6 : Memprediksi limit_limi_balance pada setiap individu\n",
    "   - Objective 7 : Memprediksi hubungan antara umur dengan limit_balance"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Query SQL\n",
    "\n",
    "Merupakan hasil proses penyimpanan data yang sudah diolah pada Query SQL dengan menggunaka google platform, dimana data yang sudah pada Query SQL akan disimpan pada format csv. Dimana data yang berformat csv ini nantinya akan digunakan sebagai dataset guna diperlukan pada proses selanjutnya.\n",
    "\n",
    "`'SELECT limit_balance,\n",
    "    CAST(sex AS INT) AS sex,\n",
    "    CAST(education_level AS INT) AS education_level,\n",
    "    CAST(marital_status AS INT) AS marital_status,\n",
    "    age,\n",
    "    pay_0,\n",
    "    pay_2,\n",
    "    pay_3,\n",
    "    pay_4,\n",
    "    CAST(pay_5 AS FLOAT) AS pay_5,\n",
    "    CAST(pay_6 AS FLOAT) AS pay_6,\n",
    "    bill_amt_1,\n",
    "    bill_amt_2,\n",
    "    bill_amt_3,\n",
    "    bill_amt_4,\n",
    "    bill_amt_5,\n",
    "    bill_amt_6,\n",
    "    pay_amt_1,\n",
    "    pay_amt_2,\n",
    "    pay_amt_3,\n",
    "    pay_amt_4,\n",
    "    pay_amt_5,\n",
    "    pay_amt_6,\n",
    "    CAST(default_payment_next_month AS INT) AS default_payment_next_month\n",
    "FROM\n",
    "    credit_card_default.ml_datasets\n",
    "LIMIT 9945`\n",
    "'''"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3. Import Libraries"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Berikut merupakan beberapa libraries yang digunakan sebagai alat pendukung dalam proses analisa ini dan machine learning framework yang digunakan adalah `Scikit-Learn`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from scipy.stats import skew\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "import phik\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report, accuracy_score\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from phik.report import plot_correlation_matrix\n",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.pipeline import make_pipeline, Pipeline\n",
    "from feature_engine.outliers import Winsorizer\n",
    "from sklearn.model_selection import cross_val_score, KFold, GridSearchCV\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.metrics import f1_score\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import roc_auc_score, ConfusionMatrixDisplay\n",
    "import pickle\n",
    "import json"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Loading Data\n",
    "\n",
    "Referensi data yang digunakan bersumber dari proses Query SQL dimana dataset ini akan diolah dan diproses sebagai bahan acuan guna memprediksi `default_payment_next_month` dengan model Classification pada dataset yang sudah di simpan pada format csv.\n",
    "\n",
    "Adapun tujuan dari proses ini adalah untuk mengimpor atau memuat data dari sumber eksternal ke dalam program atau lingkungan pemrograman tertentu, dimana proses ini merupakan langkah awal dalam analisis data dan pemrosesan data lebih lanjut"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>limit_balance</th>\n",
       "      <th>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>age</th>\n",
       "      <th>pay_0</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>...</th>\n",
       "      <th>bill_amt_4</th>\n",
       "      <th>bill_amt_5</th>\n",
       "      <th>bill_amt_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "      <th>default_payment_next_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>29296.0</td>\n",
       "      <td>26210.0</td>\n",
       "      <td>17643.0</td>\n",
       "      <td>2545.0</td>\n",
       "      <td>2208.0</td>\n",
       "      <td>1336.0</td>\n",
       "      <td>2232.0</td>\n",
       "      <td>542.0</td>\n",
       "      <td>348.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>200000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>50146.0</td>\n",
       "      <td>50235.0</td>\n",
       "      <td>48984.0</td>\n",
       "      <td>1689.0</td>\n",
       "      <td>2164.0</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>3480.0</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>3000.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1434.0</td>\n",
       "      <td>500.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4641.0</td>\n",
       "      <td>1019.0</td>\n",
       "      <td>900.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1500.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>260000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>33.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>27821.0</td>\n",
       "      <td>30767.0</td>\n",
       "      <td>29890.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>1137.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>1085.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>150000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>150464.0</td>\n",
       "      <td>143375.0</td>\n",
       "      <td>146411.0</td>\n",
       "      <td>4019.0</td>\n",
       "      <td>146896.0</td>\n",
       "      <td>157436.0</td>\n",
       "      <td>4600.0</td>\n",
       "      <td>4709.0</td>\n",
       "      <td>5600.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2960</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>28.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2800.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2961</th>\n",
       "      <td>50000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>51.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>300.0</td>\n",
       "      <td>5880.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2962</th>\n",
       "      <td>450000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>780.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2963</th>\n",
       "      <td>50000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>44.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>780.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2964</th>\n",
       "      <td>290000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>3184.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>800.0</td>\n",
       "      <td>3184.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>6617.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2965 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      limit_balance  sex  education_level  marital_status   age  pay_0  pay_2  \\\n",
       "0           80000.0    1                6               1  54.0    0.0    0.0   \n",
       "1          200000.0    1                4               1  49.0    0.0    0.0   \n",
       "2           20000.0    2                6               2  22.0    0.0    0.0   \n",
       "3          260000.0    2                4               2  33.0    0.0    0.0   \n",
       "4          150000.0    1                4               2  32.0    0.0    0.0   \n",
       "...             ...  ...              ...             ...   ...    ...    ...   \n",
       "2960        80000.0    2                3               2  28.0   -1.0   -1.0   \n",
       "2961        50000.0    2                3               1  51.0   -1.0   -1.0   \n",
       "2962       450000.0    2                2               1  38.0   -2.0   -2.0   \n",
       "2963        50000.0    2                2               1  44.0   -2.0   -2.0   \n",
       "2964       290000.0    2                2               1  39.0    1.0   -2.0   \n",
       "\n",
       "      pay_3  pay_4  pay_5  ...  bill_amt_4  bill_amt_5  bill_amt_6  pay_amt_1  \\\n",
       "0       0.0    0.0      0  ...     29296.0     26210.0     17643.0     2545.0   \n",
       "1       0.0    0.0      0  ...     50146.0     50235.0     48984.0     1689.0   \n",
       "2       0.0    0.0      0  ...      1434.0       500.0         0.0     4641.0   \n",
       "3       0.0    0.0      0  ...     27821.0     30767.0     29890.0     5000.0   \n",
       "4       0.0   -1.0      0  ...    150464.0    143375.0    146411.0     4019.0   \n",
       "...     ...    ...    ...  ...         ...         ...         ...        ...   \n",
       "2960   -1.0   -2.0     -2  ...         0.0         0.0         0.0     2800.0   \n",
       "2961   -1.0   -1.0     -2  ...         0.0         0.0         0.0      300.0   \n",
       "2962   -2.0   -2.0     -2  ...       390.0       390.0       390.0      390.0   \n",
       "2963   -2.0   -2.0     -2  ...       390.0       390.0         0.0      390.0   \n",
       "2964   -2.0   -2.0     -2  ...      3184.0       390.0       390.0    10000.0   \n",
       "\n",
       "      pay_amt_2  pay_amt_3  pay_amt_4  pay_amt_5  pay_amt_6  \\\n",
       "0        2208.0     1336.0     2232.0      542.0      348.0   \n",
       "1        2164.0     2500.0     3480.0     2500.0     3000.0   \n",
       "2        1019.0      900.0        0.0     1500.0        0.0   \n",
       "3        5000.0     1137.0     5000.0     1085.0     5000.0   \n",
       "4      146896.0   157436.0     4600.0     4709.0     5600.0   \n",
       "...         ...        ...        ...        ...        ...   \n",
       "2960        0.0        0.0        0.0        0.0        0.0   \n",
       "2961     5880.0        0.0        0.0        0.0        0.0   \n",
       "2962      780.0      390.0      390.0      390.0      390.0   \n",
       "2963      390.0      390.0      390.0        0.0      780.0   \n",
       "2964      800.0     3184.0      390.0      390.0     6617.0   \n",
       "\n",
       "      default_payment_next_month  \n",
       "0                              1  \n",
       "1                              0  \n",
       "2                              1  \n",
       "3                              0  \n",
       "4                              0  \n",
       "...                          ...  \n",
       "2960                           0  \n",
       "2961                           1  \n",
       "2962                           1  \n",
       "2963                           0  \n",
       "2964                           0  \n",
       "\n",
       "[2965 rows x 24 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# data loading\n",
    "data = pd.read_csv('P1G5_Set_1_badriah_nursakinah.csv')\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['limit_balance', 'sex', 'education_level', 'marital_status', 'age',\n",
       "       'pay_0', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6', 'bill_amt_1',\n",
       "       'bill_amt_2', 'bill_amt_3', 'bill_amt_4', 'bill_amt_5', 'bill_amt_6',\n",
       "       'pay_amt_1', 'pay_amt_2', 'pay_amt_3', 'pay_amt_4', 'pay_amt_5',\n",
       "       'pay_amt_6', 'default_payment_next_month'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "menampilkan data dengan bentuk array, dimana data dengan type ini akan lebih memudahkan saat melakukan proses handling outlier."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>limit_balance</th>\n",
       "      <th>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>age</th>\n",
       "      <th>pay_0</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>...</th>\n",
       "      <th>bill_amt_4</th>\n",
       "      <th>bill_amt_5</th>\n",
       "      <th>bill_amt_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "      <th>default_payment_next_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2.965000e+03</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "      <td>2965.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>163369.308600</td>\n",
       "      <td>1.607757</td>\n",
       "      <td>1.849578</td>\n",
       "      <td>1.559865</td>\n",
       "      <td>35.193255</td>\n",
       "      <td>0.005059</td>\n",
       "      <td>-0.122428</td>\n",
       "      <td>-0.141653</td>\n",
       "      <td>-0.185160</td>\n",
       "      <td>-0.225295</td>\n",
       "      <td>...</td>\n",
       "      <td>44089.683305</td>\n",
       "      <td>40956.080607</td>\n",
       "      <td>39773.072513</td>\n",
       "      <td>6348.902867</td>\n",
       "      <td>6.272494e+03</td>\n",
       "      <td>5150.497133</td>\n",
       "      <td>4561.376054</td>\n",
       "      <td>4913.286678</td>\n",
       "      <td>5382.701518</td>\n",
       "      <td>0.214165</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>125030.415472</td>\n",
       "      <td>0.488333</td>\n",
       "      <td>0.778184</td>\n",
       "      <td>0.522317</td>\n",
       "      <td>9.109439</td>\n",
       "      <td>1.114395</td>\n",
       "      <td>1.180784</td>\n",
       "      <td>1.183630</td>\n",
       "      <td>1.178322</td>\n",
       "      <td>1.159003</td>\n",
       "      <td>...</td>\n",
       "      <td>61907.454056</td>\n",
       "      <td>58271.904751</td>\n",
       "      <td>57303.488981</td>\n",
       "      <td>20885.735336</td>\n",
       "      <td>2.887967e+04</td>\n",
       "      <td>14287.079982</td>\n",
       "      <td>13281.499599</td>\n",
       "      <td>16734.340778</td>\n",
       "      <td>17275.953029</td>\n",
       "      <td>0.410311</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>-46627.000000</td>\n",
       "      <td>-46627.000000</td>\n",
       "      <td>-73895.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>50000.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2582.000000</td>\n",
       "      <td>1958.000000</td>\n",
       "      <td>1430.000000</td>\n",
       "      <td>1013.000000</td>\n",
       "      <td>9.900000e+02</td>\n",
       "      <td>477.000000</td>\n",
       "      <td>313.000000</td>\n",
       "      <td>323.000000</td>\n",
       "      <td>173.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>140000.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>34.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>19894.000000</td>\n",
       "      <td>18814.000000</td>\n",
       "      <td>18508.000000</td>\n",
       "      <td>2234.000000</td>\n",
       "      <td>2.175000e+03</td>\n",
       "      <td>1994.000000</td>\n",
       "      <td>1600.000000</td>\n",
       "      <td>1646.000000</td>\n",
       "      <td>1615.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>230000.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>58622.000000</td>\n",
       "      <td>53373.000000</td>\n",
       "      <td>52287.000000</td>\n",
       "      <td>5087.000000</td>\n",
       "      <td>5.000000e+03</td>\n",
       "      <td>4500.000000</td>\n",
       "      <td>4000.000000</td>\n",
       "      <td>4021.000000</td>\n",
       "      <td>4081.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>800000.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>69.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>488808.000000</td>\n",
       "      <td>441981.000000</td>\n",
       "      <td>436172.000000</td>\n",
       "      <td>493358.000000</td>\n",
       "      <td>1.227082e+06</td>\n",
       "      <td>199209.000000</td>\n",
       "      <td>202076.000000</td>\n",
       "      <td>388071.000000</td>\n",
       "      <td>403500.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       limit_balance          sex  education_level  marital_status  \\\n",
       "count    2965.000000  2965.000000      2965.000000     2965.000000   \n",
       "mean   163369.308600     1.607757         1.849578        1.559865   \n",
       "std    125030.415472     0.488333         0.778184        0.522317   \n",
       "min     10000.000000     1.000000         0.000000        0.000000   \n",
       "25%     50000.000000     1.000000         1.000000        1.000000   \n",
       "50%    140000.000000     2.000000         2.000000        2.000000   \n",
       "75%    230000.000000     2.000000         2.000000        2.000000   \n",
       "max    800000.000000     2.000000         6.000000        3.000000   \n",
       "\n",
       "               age        pay_0        pay_2        pay_3        pay_4  \\\n",
       "count  2965.000000  2965.000000  2965.000000  2965.000000  2965.000000   \n",
       "mean     35.193255     0.005059    -0.122428    -0.141653    -0.185160   \n",
       "std       9.109439     1.114395     1.180784     1.183630     1.178322   \n",
       "min      21.000000    -2.000000    -2.000000    -2.000000    -2.000000   \n",
       "25%      28.000000    -1.000000    -1.000000    -1.000000    -1.000000   \n",
       "50%      34.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "75%      41.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "max      69.000000     8.000000     7.000000     7.000000     8.000000   \n",
       "\n",
       "             pay_5  ...     bill_amt_4     bill_amt_5     bill_amt_6  \\\n",
       "count  2965.000000  ...    2965.000000    2965.000000    2965.000000   \n",
       "mean     -0.225295  ...   44089.683305   40956.080607   39773.072513   \n",
       "std       1.159003  ...   61907.454056   58271.904751   57303.488981   \n",
       "min      -2.000000  ...  -46627.000000  -46627.000000  -73895.000000   \n",
       "25%      -1.000000  ...    2582.000000    1958.000000    1430.000000   \n",
       "50%       0.000000  ...   19894.000000   18814.000000   18508.000000   \n",
       "75%       0.000000  ...   58622.000000   53373.000000   52287.000000   \n",
       "max       7.000000  ...  488808.000000  441981.000000  436172.000000   \n",
       "\n",
       "           pay_amt_1     pay_amt_2      pay_amt_3      pay_amt_4  \\\n",
       "count    2965.000000  2.965000e+03    2965.000000    2965.000000   \n",
       "mean     6348.902867  6.272494e+03    5150.497133    4561.376054   \n",
       "std     20885.735336  2.887967e+04   14287.079982   13281.499599   \n",
       "min         0.000000  0.000000e+00       0.000000       0.000000   \n",
       "25%      1013.000000  9.900000e+02     477.000000     313.000000   \n",
       "50%      2234.000000  2.175000e+03    1994.000000    1600.000000   \n",
       "75%      5087.000000  5.000000e+03    4500.000000    4000.000000   \n",
       "max    493358.000000  1.227082e+06  199209.000000  202076.000000   \n",
       "\n",
       "           pay_amt_5      pay_amt_6  default_payment_next_month  \n",
       "count    2965.000000    2965.000000                 2965.000000  \n",
       "mean     4913.286678    5382.701518                    0.214165  \n",
       "std     16734.340778   17275.953029                    0.410311  \n",
       "min         0.000000       0.000000                    0.000000  \n",
       "25%       323.000000     173.000000                    0.000000  \n",
       "50%      1646.000000    1615.000000                    0.000000  \n",
       "75%      4021.000000    4081.000000                    0.000000  \n",
       "max    388071.000000  403500.000000                    1.000000  \n",
       "\n",
       "[8 rows x 24 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dari hasil output diatas dapat disimpulkan bahwa jika diambil angka yang `75%` dimana angka ini merupakan angka yang paling besar nilai presentase penggunanya, maka untuk :\n",
    "- limit_balance terbesar                 : 230000\n",
    "- sex pengguna kartu kredit              : wanita (code 2)\n",
    "- education_level pengguna kartu kredit  : Mahasiswa/i (code 2)\n",
    "- marital_status pengguna kartu kredit   : lajang (code 2)\n",
    "- usia pengguna kartu kredit             : 41"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 2965 entries, 0 to 2964\n",
      "Data columns (total 24 columns):\n",
      " #   Column                      Non-Null Count  Dtype  \n",
      "---  ------                      --------------  -----  \n",
      " 0   limit_balance               2965 non-null   float64\n",
      " 1   sex                         2965 non-null   int64  \n",
      " 2   education_level             2965 non-null   int64  \n",
      " 3   marital_status              2965 non-null   int64  \n",
      " 4   age                         2965 non-null   float64\n",
      " 5   pay_0                       2965 non-null   float64\n",
      " 6   pay_2                       2965 non-null   float64\n",
      " 7   pay_3                       2965 non-null   float64\n",
      " 8   pay_4                       2965 non-null   float64\n",
      " 9   pay_5                       2965 non-null   int64  \n",
      " 10  pay_6                       2965 non-null   int64  \n",
      " 11  bill_amt_1                  2965 non-null   float64\n",
      " 12  bill_amt_2                  2965 non-null   float64\n",
      " 13  bill_amt_3                  2965 non-null   float64\n",
      " 14  bill_amt_4                  2965 non-null   float64\n",
      " 15  bill_amt_5                  2965 non-null   float64\n",
      " 16  bill_amt_6                  2965 non-null   float64\n",
      " 17  pay_amt_1                   2965 non-null   float64\n",
      " 18  pay_amt_2                   2965 non-null   float64\n",
      " 19  pay_amt_3                   2965 non-null   float64\n",
      " 20  pay_amt_4                   2965 non-null   float64\n",
      " 21  pay_amt_5                   2965 non-null   float64\n",
      " 22  pay_amt_6                   2965 non-null   float64\n",
      " 23  default_payment_next_month  2965 non-null   int64  \n",
      "dtypes: float64(18), int64(6)\n",
      "memory usage: 556.1 KB\n"
     ]
    }
   ],
   "source": [
    "#cek data info\n",
    "data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dari hasil output diatas maka data tidak mmeiliki missing value, artinya dari data diatas dengan `Dtype` sudah sesuai dan tidak perlu diubah lagi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>limit_balance</th>\n",
       "      <th>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>age</th>\n",
       "      <th>pay_0</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>...</th>\n",
       "      <th>bill_amt_4</th>\n",
       "      <th>bill_amt_5</th>\n",
       "      <th>bill_amt_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "      <th>default_payment_next_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>29296.0</td>\n",
       "      <td>26210.0</td>\n",
       "      <td>17643.0</td>\n",
       "      <td>2545.0</td>\n",
       "      <td>2208.0</td>\n",
       "      <td>1336.0</td>\n",
       "      <td>2232.0</td>\n",
       "      <td>542.0</td>\n",
       "      <td>348.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>200000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>50146.0</td>\n",
       "      <td>50235.0</td>\n",
       "      <td>48984.0</td>\n",
       "      <td>1689.0</td>\n",
       "      <td>2164.0</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>3480.0</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>3000.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1434.0</td>\n",
       "      <td>500.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4641.0</td>\n",
       "      <td>1019.0</td>\n",
       "      <td>900.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1500.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>260000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>33.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>27821.0</td>\n",
       "      <td>30767.0</td>\n",
       "      <td>29890.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>1137.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>1085.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>150000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>150464.0</td>\n",
       "      <td>143375.0</td>\n",
       "      <td>146411.0</td>\n",
       "      <td>4019.0</td>\n",
       "      <td>146896.0</td>\n",
       "      <td>157436.0</td>\n",
       "      <td>4600.0</td>\n",
       "      <td>4709.0</td>\n",
       "      <td>5600.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   limit_balance  sex  education_level  marital_status   age  pay_0  pay_2  \\\n",
       "0        80000.0    1                6               1  54.0    0.0    0.0   \n",
       "1       200000.0    1                4               1  49.0    0.0    0.0   \n",
       "2        20000.0    2                6               2  22.0    0.0    0.0   \n",
       "3       260000.0    2                4               2  33.0    0.0    0.0   \n",
       "4       150000.0    1                4               2  32.0    0.0    0.0   \n",
       "\n",
       "   pay_3  pay_4  pay_5  ...  bill_amt_4  bill_amt_5  bill_amt_6  pay_amt_1  \\\n",
       "0    0.0    0.0      0  ...     29296.0     26210.0     17643.0     2545.0   \n",
       "1    0.0    0.0      0  ...     50146.0     50235.0     48984.0     1689.0   \n",
       "2    0.0    0.0      0  ...      1434.0       500.0         0.0     4641.0   \n",
       "3    0.0    0.0      0  ...     27821.0     30767.0     29890.0     5000.0   \n",
       "4    0.0   -1.0      0  ...    150464.0    143375.0    146411.0     4019.0   \n",
       "\n",
       "   pay_amt_2  pay_amt_3  pay_amt_4  pay_amt_5  pay_amt_6  \\\n",
       "0     2208.0     1336.0     2232.0      542.0      348.0   \n",
       "1     2164.0     2500.0     3480.0     2500.0     3000.0   \n",
       "2     1019.0      900.0        0.0     1500.0        0.0   \n",
       "3     5000.0     1137.0     5000.0     1085.0     5000.0   \n",
       "4   146896.0   157436.0     4600.0     4709.0     5600.0   \n",
       "\n",
       "   default_payment_next_month  \n",
       "0                           1  \n",
       "1                           0  \n",
       "2                           1  \n",
       "3                           0  \n",
       "4                           0  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# menampilkan 5 data awal\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>limit_balance</th>\n",
       "      <th>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>age</th>\n",
       "      <th>pay_0</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>...</th>\n",
       "      <th>bill_amt_4</th>\n",
       "      <th>bill_amt_5</th>\n",
       "      <th>bill_amt_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "      <th>default_payment_next_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2960</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>28.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2800.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2961</th>\n",
       "      <td>50000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>51.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>300.0</td>\n",
       "      <td>5880.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2962</th>\n",
       "      <td>450000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>780.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2963</th>\n",
       "      <td>50000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>44.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>780.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2964</th>\n",
       "      <td>290000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>3184.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>800.0</td>\n",
       "      <td>3184.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>6617.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      limit_balance  sex  education_level  marital_status   age  pay_0  pay_2  \\\n",
       "2960        80000.0    2                3               2  28.0   -1.0   -1.0   \n",
       "2961        50000.0    2                3               1  51.0   -1.0   -1.0   \n",
       "2962       450000.0    2                2               1  38.0   -2.0   -2.0   \n",
       "2963        50000.0    2                2               1  44.0   -2.0   -2.0   \n",
       "2964       290000.0    2                2               1  39.0    1.0   -2.0   \n",
       "\n",
       "      pay_3  pay_4  pay_5  ...  bill_amt_4  bill_amt_5  bill_amt_6  pay_amt_1  \\\n",
       "2960   -1.0   -2.0     -2  ...         0.0         0.0         0.0     2800.0   \n",
       "2961   -1.0   -1.0     -2  ...         0.0         0.0         0.0      300.0   \n",
       "2962   -2.0   -2.0     -2  ...       390.0       390.0       390.0      390.0   \n",
       "2963   -2.0   -2.0     -2  ...       390.0       390.0         0.0      390.0   \n",
       "2964   -2.0   -2.0     -2  ...      3184.0       390.0       390.0    10000.0   \n",
       "\n",
       "      pay_amt_2  pay_amt_3  pay_amt_4  pay_amt_5  pay_amt_6  \\\n",
       "2960        0.0        0.0        0.0        0.0        0.0   \n",
       "2961     5880.0        0.0        0.0        0.0        0.0   \n",
       "2962      780.0      390.0      390.0      390.0      390.0   \n",
       "2963      390.0      390.0      390.0        0.0      780.0   \n",
       "2964      800.0     3184.0      390.0      390.0     6617.0   \n",
       "\n",
       "      default_payment_next_month  \n",
       "2960                           0  \n",
       "2961                           1  \n",
       "2962                           1  \n",
       "2963                           0  \n",
       "2964                           0  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# menampilkan 5 data akhir\n",
    "data.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dari output diatas menampilkan data untuk 5 data paling awal dan 5 data yang paling akhir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# mengganti nama column\n",
    "data.rename(columns={'pay_0': 'pay_1'},inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cek duplikat data\n",
    "data.duplicated().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output ini memberikan kesimpulan bahwa adanya data yang duplikat, maka untuk tidak terjadi bias pada saat pengolahan data diproses `Future Engineer` maka data ini akna di lakukan `drop_duplicate`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# drop duplikat data\n",
    "data.drop_duplicates(inplace=True)\n",
    "data.duplicated().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Proses ini menghilangkan data yang duplikat, dan terlihat dari hasil outputnya bahwa data sudah tidak ada yang duplikat maka dapat dilakukan proses selanjutnya"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "limit_balance                 0\n",
       "sex                           0\n",
       "education_level               0\n",
       "marital_status                0\n",
       "age                           0\n",
       "pay_1                         0\n",
       "pay_2                         0\n",
       "pay_3                         0\n",
       "pay_4                         0\n",
       "pay_5                         0\n",
       "pay_6                         0\n",
       "bill_amt_1                    0\n",
       "bill_amt_2                    0\n",
       "bill_amt_3                    0\n",
       "bill_amt_4                    0\n",
       "bill_amt_5                    0\n",
       "bill_amt_6                    0\n",
       "pay_amt_1                     0\n",
       "pay_amt_2                     0\n",
       "pay_amt_3                     0\n",
       "pay_amt_4                     0\n",
       "pay_amt_5                     0\n",
       "pay_amt_6                     0\n",
       "default_payment_next_month    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cek missing value\n",
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Perlu melakukan double check `missing value` dilakukan setelah proses `drop_duplicate`, untuk memastikan apakah data memiliki kondisi yang sama atau ada perubahan terutama pada bagian `missing value`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>limit_balance</th>\n",
       "      <th>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>age</th>\n",
       "      <th>pay_1</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>...</th>\n",
       "      <th>bill_amt_4</th>\n",
       "      <th>bill_amt_5</th>\n",
       "      <th>bill_amt_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "      <th>default_payment_next_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2.964000e+03</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "      <td>2964.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>163356.950067</td>\n",
       "      <td>1.607625</td>\n",
       "      <td>1.849865</td>\n",
       "      <td>1.560054</td>\n",
       "      <td>35.193657</td>\n",
       "      <td>0.004723</td>\n",
       "      <td>-0.121795</td>\n",
       "      <td>-0.141026</td>\n",
       "      <td>-0.184548</td>\n",
       "      <td>-0.224696</td>\n",
       "      <td>...</td>\n",
       "      <td>44104.558367</td>\n",
       "      <td>40969.898448</td>\n",
       "      <td>39786.491228</td>\n",
       "      <td>6351.044872</td>\n",
       "      <td>6.274611e+03</td>\n",
       "      <td>5152.234818</td>\n",
       "      <td>4562.914980</td>\n",
       "      <td>4914.944332</td>\n",
       "      <td>5384.517544</td>\n",
       "      <td>0.214238</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>125049.701016</td>\n",
       "      <td>0.488362</td>\n",
       "      <td>0.778159</td>\n",
       "      <td>0.522304</td>\n",
       "      <td>9.110949</td>\n",
       "      <td>1.114434</td>\n",
       "      <td>1.180479</td>\n",
       "      <td>1.183337</td>\n",
       "      <td>1.178049</td>\n",
       "      <td>1.158739</td>\n",
       "      <td>...</td>\n",
       "      <td>61912.600106</td>\n",
       "      <td>58276.878626</td>\n",
       "      <td>57308.498646</td>\n",
       "      <td>20888.933729</td>\n",
       "      <td>2.888432e+04</td>\n",
       "      <td>14289.177313</td>\n",
       "      <td>13283.476236</td>\n",
       "      <td>16736.920951</td>\n",
       "      <td>17278.585006</td>\n",
       "      <td>0.410362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10000.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>-2.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>-46627.000000</td>\n",
       "      <td>-46627.000000</td>\n",
       "      <td>-73895.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>50000.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2585.000000</td>\n",
       "      <td>1974.500000</td>\n",
       "      <td>1433.000000</td>\n",
       "      <td>1013.000000</td>\n",
       "      <td>9.975000e+02</td>\n",
       "      <td>479.250000</td>\n",
       "      <td>313.750000</td>\n",
       "      <td>325.250000</td>\n",
       "      <td>175.250000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>140000.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>34.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>19895.000000</td>\n",
       "      <td>18819.500000</td>\n",
       "      <td>18511.500000</td>\n",
       "      <td>2238.000000</td>\n",
       "      <td>2.182500e+03</td>\n",
       "      <td>1997.000000</td>\n",
       "      <td>1600.000000</td>\n",
       "      <td>1646.500000</td>\n",
       "      <td>1626.500000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>230000.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>58638.500000</td>\n",
       "      <td>53414.500000</td>\n",
       "      <td>52297.000000</td>\n",
       "      <td>5089.500000</td>\n",
       "      <td>5.000000e+03</td>\n",
       "      <td>4500.000000</td>\n",
       "      <td>4000.250000</td>\n",
       "      <td>4021.000000</td>\n",
       "      <td>4081.750000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>800000.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>69.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>488808.000000</td>\n",
       "      <td>441981.000000</td>\n",
       "      <td>436172.000000</td>\n",
       "      <td>493358.000000</td>\n",
       "      <td>1.227082e+06</td>\n",
       "      <td>199209.000000</td>\n",
       "      <td>202076.000000</td>\n",
       "      <td>388071.000000</td>\n",
       "      <td>403500.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       limit_balance          sex  education_level  marital_status  \\\n",
       "count    2964.000000  2964.000000      2964.000000     2964.000000   \n",
       "mean   163356.950067     1.607625         1.849865        1.560054   \n",
       "std    125049.701016     0.488362         0.778159        0.522304   \n",
       "min     10000.000000     1.000000         0.000000        0.000000   \n",
       "25%     50000.000000     1.000000         1.000000        1.000000   \n",
       "50%    140000.000000     2.000000         2.000000        2.000000   \n",
       "75%    230000.000000     2.000000         2.000000        2.000000   \n",
       "max    800000.000000     2.000000         6.000000        3.000000   \n",
       "\n",
       "               age        pay_1        pay_2        pay_3        pay_4  \\\n",
       "count  2964.000000  2964.000000  2964.000000  2964.000000  2964.000000   \n",
       "mean     35.193657     0.004723    -0.121795    -0.141026    -0.184548   \n",
       "std       9.110949     1.114434     1.180479     1.183337     1.178049   \n",
       "min      21.000000    -2.000000    -2.000000    -2.000000    -2.000000   \n",
       "25%      28.000000    -1.000000    -1.000000    -1.000000    -1.000000   \n",
       "50%      34.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "75%      41.000000     0.000000     0.000000     0.000000     0.000000   \n",
       "max      69.000000     8.000000     7.000000     7.000000     8.000000   \n",
       "\n",
       "             pay_5  ...     bill_amt_4     bill_amt_5     bill_amt_6  \\\n",
       "count  2964.000000  ...    2964.000000    2964.000000    2964.000000   \n",
       "mean     -0.224696  ...   44104.558367   40969.898448   39786.491228   \n",
       "std       1.158739  ...   61912.600106   58276.878626   57308.498646   \n",
       "min      -2.000000  ...  -46627.000000  -46627.000000  -73895.000000   \n",
       "25%      -1.000000  ...    2585.000000    1974.500000    1433.000000   \n",
       "50%       0.000000  ...   19895.000000   18819.500000   18511.500000   \n",
       "75%       0.000000  ...   58638.500000   53414.500000   52297.000000   \n",
       "max       7.000000  ...  488808.000000  441981.000000  436172.000000   \n",
       "\n",
       "           pay_amt_1     pay_amt_2      pay_amt_3      pay_amt_4  \\\n",
       "count    2964.000000  2.964000e+03    2964.000000    2964.000000   \n",
       "mean     6351.044872  6.274611e+03    5152.234818    4562.914980   \n",
       "std     20888.933729  2.888432e+04   14289.177313   13283.476236   \n",
       "min         0.000000  0.000000e+00       0.000000       0.000000   \n",
       "25%      1013.000000  9.975000e+02     479.250000     313.750000   \n",
       "50%      2238.000000  2.182500e+03    1997.000000    1600.000000   \n",
       "75%      5089.500000  5.000000e+03    4500.000000    4000.250000   \n",
       "max    493358.000000  1.227082e+06  199209.000000  202076.000000   \n",
       "\n",
       "           pay_amt_5      pay_amt_6  default_payment_next_month  \n",
       "count    2964.000000    2964.000000                 2964.000000  \n",
       "mean     4914.944332    5384.517544                    0.214238  \n",
       "std     16736.920951   17278.585006                    0.410362  \n",
       "min         0.000000       0.000000                    0.000000  \n",
       "25%       325.250000     175.250000                    0.000000  \n",
       "50%      1646.500000    1626.500000                    0.000000  \n",
       "75%      4021.000000    4081.750000                    0.000000  \n",
       "max    388071.000000  403500.000000                    1.000000  \n",
       "\n",
       "[8 rows x 24 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cek statistik deskriptif data\n",
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Karena dilakukan proses `drop_duplicate` maka perlu dilakukan double check pada proses `cek statistik deskriptif` data .Dan untuk penjelsan untuk hasil output masih sama dengan hasil output yang diatas dimana jika diambil angka yang `75%` dimana angka ini merupakan angka yang paling besar nilai presentase penggunanya, maka untuk :\n",
    "- limit_balance terbesar                 : 230000\n",
    "- sex pengguna kartu kredit              : wanita (code 2)\n",
    "- education_level pengguna kartu kredit  : Mahasiswa/i (code 2)\n",
    "- marital_status pengguna kartu kredit   : lajang (code 2)\n",
    "- usia pengguna kartu kredit             : 41"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 5. Exploratory Data Analysis (EDA)\n",
    "\n",
    "Pada bagian `Exploratory Data Analysis (EDA)` ini akan lebih memfokuskan pada eksplorasi data dari dataset yang digunakan. Eksplorasi ini dilakukan dengan menggunakan berbagai teknik, seperti query, grouping, visualisasi sederhana, dan lainnya.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>limit_balance</th>\n",
       "      <th>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>age</th>\n",
       "      <th>pay_1</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>...</th>\n",
       "      <th>bill_amt_5</th>\n",
       "      <th>bill_amt_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "      <th>default_payment_next_month</th>\n",
       "      <th>Klasifikasi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>26210.0</td>\n",
       "      <td>17643.0</td>\n",
       "      <td>2545.0</td>\n",
       "      <td>2208.0</td>\n",
       "      <td>1336.0</td>\n",
       "      <td>2232.0</td>\n",
       "      <td>542.0</td>\n",
       "      <td>348.0</td>\n",
       "      <td>1</td>\n",
       "      <td>Lansia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>200000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>50235.0</td>\n",
       "      <td>48984.0</td>\n",
       "      <td>1689.0</td>\n",
       "      <td>2164.0</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>3480.0</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>3000.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Lansia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>20000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>22.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>500.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4641.0</td>\n",
       "      <td>1019.0</td>\n",
       "      <td>900.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1500.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>Remaja</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>260000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>33.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>30767.0</td>\n",
       "      <td>29890.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>1137.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>1085.0</td>\n",
       "      <td>5000.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Dewasa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>150000.0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>32.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>143375.0</td>\n",
       "      <td>146411.0</td>\n",
       "      <td>4019.0</td>\n",
       "      <td>146896.0</td>\n",
       "      <td>157436.0</td>\n",
       "      <td>4600.0</td>\n",
       "      <td>4709.0</td>\n",
       "      <td>5600.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Dewasa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2960</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>28.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2800.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Dewasa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2961</th>\n",
       "      <td>50000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>51.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>300.0</td>\n",
       "      <td>5880.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>Lansia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2962</th>\n",
       "      <td>450000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>38.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>780.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>1</td>\n",
       "      <td>Dewasa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2963</th>\n",
       "      <td>50000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>44.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>780.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Dewasa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2964</th>\n",
       "      <td>290000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>...</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>10000.0</td>\n",
       "      <td>800.0</td>\n",
       "      <td>3184.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>390.0</td>\n",
       "      <td>6617.0</td>\n",
       "      <td>0</td>\n",
       "      <td>Dewasa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2964 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      limit_balance  sex  education_level  marital_status   age  pay_1  pay_2  \\\n",
       "0           80000.0    1                6               1  54.0    0.0    0.0   \n",
       "1          200000.0    1                4               1  49.0    0.0    0.0   \n",
       "2           20000.0    2                6               2  22.0    0.0    0.0   \n",
       "3          260000.0    2                4               2  33.0    0.0    0.0   \n",
       "4          150000.0    1                4               2  32.0    0.0    0.0   \n",
       "...             ...  ...              ...             ...   ...    ...    ...   \n",
       "2960        80000.0    2                3               2  28.0   -1.0   -1.0   \n",
       "2961        50000.0    2                3               1  51.0   -1.0   -1.0   \n",
       "2962       450000.0    2                2               1  38.0   -2.0   -2.0   \n",
       "2963        50000.0    2                2               1  44.0   -2.0   -2.0   \n",
       "2964       290000.0    2                2               1  39.0    1.0   -2.0   \n",
       "\n",
       "      pay_3  pay_4  pay_5  ...  bill_amt_5  bill_amt_6  pay_amt_1  pay_amt_2  \\\n",
       "0       0.0    0.0      0  ...     26210.0     17643.0     2545.0     2208.0   \n",
       "1       0.0    0.0      0  ...     50235.0     48984.0     1689.0     2164.0   \n",
       "2       0.0    0.0      0  ...       500.0         0.0     4641.0     1019.0   \n",
       "3       0.0    0.0      0  ...     30767.0     29890.0     5000.0     5000.0   \n",
       "4       0.0   -1.0      0  ...    143375.0    146411.0     4019.0   146896.0   \n",
       "...     ...    ...    ...  ...         ...         ...        ...        ...   \n",
       "2960   -1.0   -2.0     -2  ...         0.0         0.0     2800.0        0.0   \n",
       "2961   -1.0   -1.0     -2  ...         0.0         0.0      300.0     5880.0   \n",
       "2962   -2.0   -2.0     -2  ...       390.0       390.0      390.0      780.0   \n",
       "2963   -2.0   -2.0     -2  ...       390.0         0.0      390.0      390.0   \n",
       "2964   -2.0   -2.0     -2  ...       390.0       390.0    10000.0      800.0   \n",
       "\n",
       "      pay_amt_3  pay_amt_4  pay_amt_5  pay_amt_6  default_payment_next_month  \\\n",
       "0        1336.0     2232.0      542.0      348.0                           1   \n",
       "1        2500.0     3480.0     2500.0     3000.0                           0   \n",
       "2         900.0        0.0     1500.0        0.0                           1   \n",
       "3        1137.0     5000.0     1085.0     5000.0                           0   \n",
       "4      157436.0     4600.0     4709.0     5600.0                           0   \n",
       "...         ...        ...        ...        ...                         ...   \n",
       "2960        0.0        0.0        0.0        0.0                           0   \n",
       "2961        0.0        0.0        0.0        0.0                           1   \n",
       "2962      390.0      390.0      390.0      390.0                           1   \n",
       "2963      390.0      390.0        0.0      780.0                           0   \n",
       "2964     3184.0      390.0      390.0     6617.0                           0   \n",
       "\n",
       "      Klasifikasi  \n",
       "0          Lansia  \n",
       "1          Lansia  \n",
       "2          Remaja  \n",
       "3          Dewasa  \n",
       "4          Dewasa  \n",
       "...           ...  \n",
       "2960       Dewasa  \n",
       "2961       Lansia  \n",
       "2962       Dewasa  \n",
       "2963       Dewasa  \n",
       "2964       Dewasa  \n",
       "\n",
       "[2964 rows x 25 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Membuat kolom baru bernama chol2\n",
    "penampung = []\n",
    "for i in data['age']:\n",
    "  if i > 45:\n",
    "    penampung.append('Lansia')\n",
    "  elif i > 25:\n",
    "    penampung.append('Dewasa')\n",
    "  elif i < 25:\n",
    "    penampung.append('Remaja')\n",
    "  else:\n",
    "    penampung.append('Kanak-Kanak')\n",
    "  \n",
    "data['Klasifikasi'] = penampung\n",
    "\n",
    "data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Tujuan dari proses diatas adalah untuk membuat kolom baru bernama 'chol2' (dari hasil menampilkan data set pada columns 5 awal dan akhir)yang digabungkan, berdasarkan klasifikasi usia yang diberikan dalam kolom 'age' pada suatu dataset."
   ]
  },
  {
   "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>count</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Klasifikasi</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Dewasa</th>\n",
       "      <td>2136</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kanak-Kanak</th>\n",
       "      <td>119</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Lansia</th>\n",
       "      <td>438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Remaja</th>\n",
       "      <td>271</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             count\n",
       "Klasifikasi       \n",
       "Dewasa        2136\n",
       "Kanak-Kanak    119\n",
       "Lansia         438\n",
       "Remaja         271"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# grouping data dan dibuat dalam dataframe\n",
    "\n",
    "data_age = pd.DataFrame(data.groupby('Klasifikasi')['Klasifikasi'].value_counts())\n",
    "\n",
    "data_age"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas menjelaskan banyaknya pengguna kartu kredit berdasarkan usia"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data yang akan dipakai untuk plot\n",
    "data_sorted = data_age.sort_values(by='count', ascending = False).reset_index()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 1 : Analisa Limit Balance Untuk 'Age', 'Count', 'Marital Status', 'Education Level'**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x500 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Membuat subplots dengan 1 baris dan 4 kolom\n",
    "fig, axs = plt.subplots(1, 4, figsize=(20, 5))\n",
    "\n",
    "# Grafik 1: Histogram\n",
    "data['age'].plot(kind='hist', bins=20, ax=axs[0], color='blue')\n",
    "axs[0].set_xlabel('Age')\n",
    "axs[0].set_ylabel('Count')\n",
    "axs[0].set_title('Distribution of Age')\n",
    "\n",
    "# Grafik 2: Pie Chart\n",
    "marital_status_counts = data['marital_status'].value_counts()\n",
    "marital_status_counts.plot(kind='pie', autopct='%1.1f%%', ax=axs[1], colors=['orange', 'green', 'blue', 'red'])\n",
    "axs[1].set_title('Marital Status Distribution')\n",
    "axs[1].set_ylabel('')\n",
    "\n",
    "# Grafik 3: Bar Chart\n",
    "education_counts = data['education_level'].value_counts()\n",
    "education_counts.plot(kind='bar', ax=axs[2], color='purple')\n",
    "axs[2].set_xlabel('Education Level')\n",
    "axs[2].set_ylabel('Count')\n",
    "axs[2].set_title('Education Level Distribution')\n",
    "\n",
    "# Grafik 4: Line Chart\n",
    "limit_balance_sorted = data['limit_balance'].sort_values()\n",
    "axs[3].plot(limit_balance_sorted, color='green')\n",
    "axs[3].set_xlabel('Index')\n",
    "axs[3].set_ylabel('Limit Balance')\n",
    "axs[3].set_title('Change in Limit Balance')\n",
    "\n",
    "# Menampilkan grafik\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "kesimpulan untuk ke grafik diatas ini untuk \n",
    "- Grafik Distribusi Usia              : Dari tren grafik histogram dapat disimpulkan untuk ditribusi usia rata-rata pengguna kartu kredit diatas usia 30 tahun\n",
    "\n",
    "- Grafik Distribusi Status Perkawinan : Dari tren grafik phie chart dapat disimpulkan pengguna kartu kredit dengan jumlah presentase mencapai 53.8% berstatus masih lajang\n",
    "\n",
    "- Grafik Distribusi Pendidikan        : Tren grafik batang  ini menunjukkan hampir 1400 menggunakan kartu kredit jika ditinjau dari segi level pendidikan yaitu Mahasiswa/\n",
    "\n",
    "- Grafik Distribusi Saldo Limit       : Tren grafik menunjukkan perubahan saldo limit dari waktu ke waktu. Dimana garis hijau menunjukkan peningkatan saldo limit, sedangkan garis merah menunjukkan penurunan saldo limit."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 2 : Memprediksi Usia Yang Paling Banyak Membayar**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1800x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Set ukuran figure\n",
    "plt.figure(figsize=(18, 10))\n",
    "\n",
    "# Plot bar graph untuk jenis liga\n",
    "ax = sns.barplot(x='Klasifikasi', y='count', hue='Klasifikasi', data=data_sorted)\n",
    "\n",
    "# Set font size for axis labels\n",
    "ax.tick_params(axis='x', labelsize=16)\n",
    "ax.tick_params(axis='y', labelsize=16)\n",
    "\n",
    "# Labelling the graph\n",
    "plt.title('Tingkat Umur Yang Paling Banyak membayar', fontsize = 20)\n",
    "plt.xlabel('Klasifikasi Umur', fontsize = 18)\n",
    "plt.ylabel('Jumlah', fontsize = 18)\n",
    "\n",
    "# Show final plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Grafik tersebut menunjukkan bahwa kelompok umur yang membayar paling tinggi adalah `Dewasa`. Kelompok ini mungkin membayar paling banyak karena mereka mempunyai pendapatan lebih tinggi dibandingkan kelompok umur lainnya. Kelompok `Lansia` mungkin membayar paling banyak kedua karena mereka mungkin memiliki biaya pengobatan yang lebih banyak. Kelompok `Remaja` mungkin membayar paling banyak ketiga karena mereka mungkin membeli lebih banyak produk dan jasa dibandingkan kelompok `Kanak-Kanak`. Kelompok `Kanak-Kanak`mungkin membayar paling banyak keempat karena mereka mungkin membeli lebih sedikit produk dan jasa dibandingkan kelompok usia lainnya. Kelompok `Klasifikasi Umur` mungkin membayar paling sedikit karena mereka mungkin tidak mampu membayar barang dan jasa."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 3: Analisa Jumlah Pengguna Berdasarkan Jenis Kelamin**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Menghitung jumlah pengguna berdasarkan sex\n",
    "jumlah_pengguna = data['sex'].value_counts()\n",
    "\n",
    "# Membuat diagram batang\n",
    "colors = ['blue', 'pink']  # Daftar warna yang akan digunakan\n",
    "jumlah_pengguna.plot(kind='bar', color=colors)\n",
    "\n",
    "# Menambahkan keterangan jenis kelamin\n",
    "plt.xlabel('Jenis Kelamin')\n",
    "plt.ylabel('Jumlah Pengguna')\n",
    "plt.title('Jumlah Pengguna Berdasarkan Jenis Kelamin')\n",
    "\n",
    "\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Berdasarkan tren yang ada, diprediksikan gender wanita lebih banyak menggunakan kartu kredit"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 4: Analisa Jumlah Pengguna Berdasarkan Status Pernikahan**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Menghitung jumlah pengguna berdasarkan marital_status\n",
    "jumlah_pengguna = data['marital_status'].value_counts()\n",
    "\n",
    "# Membuat diagram batang\n",
    "colors = ['blue', 'green', 'orange', 'red']  # Daftar warna yang akan digunakan\n",
    "jumlah_pengguna.plot(kind='bar', color=colors)\n",
    "\n",
    "# Menambahkan keterangan status pernikahan\n",
    "plt.xlabel('Status Pernikahan')\n",
    "plt.ylabel('Jumlah Pengguna')\n",
    "plt.title('Jumlah Pengguna Berdasarkan Status Pernikahan')\n",
    "\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Berdasarkan tren diatas, diprediksikan bahwa jumlah banyaknya pengguna kartu kredit lebih cenderung yang masih lajang"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 5 : Analisa Jumlah Kartu Kredit Berdasarkan Usia**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1800x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Set ukuran figure\n",
    "plt.figure(figsize=(18, 10))\n",
    "\n",
    "# Menghitung jumlah pengguna berdasarkan usia\n",
    "education_counts = data['age'].value_counts()\n",
    "\n",
    "# Membuat diagram batang\n",
    "colors = sns.color_palette('pastel')  # Menggunakan palet warna 'pastel'\n",
    "sns.barplot(x=education_counts.index, y=education_counts.values, palette=colors)\n",
    "\n",
    "plt.title('Jumlah Pengguna Kartu Kredit Berdasarkan Usia')\n",
    "plt.xticks(rotation=360)  # Ubah rotasi label x-axis sesuai kebutuhan\n",
    "plt.xlabel('Usia')\n",
    "plt.ylabel('Jumlah')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dari tren grafik diagram batang secara spesifik, kelompok usia pengguna kartu kredit terbanyak adalah antara 45 hingga 64 tahun. Diikuti oleh kelompok umur antara 25 dan 44 tahun.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 6 : Analisa Prediksi Limit Balance**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# Mengambil kolom \"limit_balance\"\n",
    "limit_balance = data['limit_balance']\n",
    "\n",
    "# Membuat histogram\n",
    "plt.hist(limit_balance, bins=20, color='pink')\n",
    "plt.xlabel('Limit Balance')\n",
    "plt.ylabel('Jumlah')\n",
    "plt.title('Distribusi Limit Balance')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil tren histogram menunjukkan bahwa kebanyakan orang memiliki batas saldo antara $100.000 dan $300.000. Batang di sisi kiri dan kanan grafik menunjukkan bahwa lebih sedikit orang yang memiliki saldo batas sangat rendah atau sangat tinggi."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Objective 7 : Analisa Hubungan Antara Umur Dengan Limit Balance**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='sex', ylabel='count'>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x='sex', data=data,hue=\"default_payment_next_month\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 6. Feature Engineering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Karena akan melakukan model `Classification` pada dataset, maka data akan dibagi menjadi feature X dan label/target y. Lalu kedua dataset tersebut juga akan dibagi menjadi train-set dan test-set. Sebelum split data, maka langkah awal akan membuat variable baru `data_inf` yang bertujuan untuk train data inference sehingga tidak perlu untuk menginput secara manual di inference dan tujuan dari proses ini adalah untuk mengubah atau membuat fitur-fitur baru yang lebih informatif atau lebih sesuai dengan masalah yang ingin diselesaikan."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# menyimpan 1 data random dari data asli untuk digunakan sebagai data inference ke dalam variabel data_inf\n",
    "data_inf = data.sample(1, random_state=0)\n",
    "\n",
    "# menghapus data inference dari df\n",
    "data.drop(data_inf.index, inplace=True)\n",
    "\n",
    "# melakukan reset index untuk data_inf dan df\n",
    "data.reset_index(drop=True, inplace=True)\n",
    "data_inf.reset_index(drop=True, inplace=True)\n",
    "\n",
    "#simpan ke csv\n",
    "data_inf.to_csv('data_inf')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Model Missing Value**\n",
    "\n",
    "Proses ini memiliki cara kerja untuk menangani nilai yang hilang (missing value) yang ada di dalamnya. Dimana proses missing value ini lebih bertujuan untuk mencegah bias dalam proses analisis selanjutnya."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "limit_balance                 0\n",
       "sex                           0\n",
       "education_level               0\n",
       "marital_status                0\n",
       "age                           0\n",
       "pay_1                         0\n",
       "pay_2                         0\n",
       "pay_3                         0\n",
       "pay_4                         0\n",
       "pay_5                         0\n",
       "pay_6                         0\n",
       "bill_amt_1                    0\n",
       "bill_amt_2                    0\n",
       "bill_amt_3                    0\n",
       "bill_amt_4                    0\n",
       "bill_amt_5                    0\n",
       "bill_amt_6                    0\n",
       "pay_amt_1                     0\n",
       "pay_amt_2                     0\n",
       "pay_amt_3                     0\n",
       "pay_amt_4                     0\n",
       "pay_amt_5                     0\n",
       "pay_amt_6                     0\n",
       "default_payment_next_month    0\n",
       "Klasifikasi                   0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Cek data yang kolomnya memiliki nilai\n",
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Split Feature `X` dan Target `y`**\n",
    "\n",
    " Proses ini yaitu melakukan pemisahan antara label dengan fitur dimana secara keseluruhan, pemisahan fitur (X) dan variabel target (y) merupakan langkah penting dalam machine learning sehingga dapat menggeneralisasi dengan baik terhadap contoh-contoh yang tidak terlihat. Adapun tujuan dari proses ini adalah untuk  mempersiapkan data yang akan digunakan dalam pemodelan atau analisis prediktif. Yang pada umumnya, pemisahan fitur X (variabel independen) yang digunakan sebagai input untuk memprediksi target y (variabel dependen)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Splitting dataset X (feature) dan y (target)\n",
    "\n",
    "X = data.drop(['default_payment_next_month'], axis = 1)\n",
    "y = data['default_payment_next_month']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X,\n",
    "                                                    y,\n",
    "                                                    test_size = 0.2,\n",
    "                                                    stratify=y,\n",
    "                                                    random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Split Numerical Columns and Categorical Columns**\n",
    "\n",
    "Proses split numerical columns dan Categorical columns ini bertujuan untuk memisahkan kolom-kolom berdasarkan jenis data Dengan memisahkan kolom numerik dan kolom kategorikal, dimana hal ini dapat mengoptimalkan pemrosesan, analisis, dan visualisasi data dengan memperlakukan setiap jenis data secara terpisah\n",
    "\n",
    "Adapun tujuan dari proses Split Numerical Columns and Categorical Columns pada data adalah untuk memisahkan variabel numerik (numerical) dan variabel kategorikal (categorical) dalam dataset. Dimana pemisahan ini merupakan langkah yang begitu penting, dikarenakan variabel numerik dan kategorikal sering kali memerlukan perlakuan yang berbeda dalam analisis atau pemodelan data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "# proses melakukan split kolom numerik dan kategori\n",
    "cat_cols = X_train.select_dtypes(include='object').columns.tolist()\n",
    "num_cols = X_train.select_dtypes(exclude='object').columns.tolist()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Feature Selection**\n",
    "\n",
    "*Feature selection* merupakan dalam bagian proses dimana fitur yang akan dimasukkan ke model akan diseleksi berdasarkan adanya korelasi dengan target. Dikarenakan pada bagian ini, fitur-fitur yang tidak memiliki pengaruh terhadap target akan dihapus (drop) dengan cara memeriksa korelasinya . Adapun Tujuan dari feature selection (pemilihan fitur) adalah untuk mengidentifikasi dan memilih subset fitur yang paling relevan atau informatif dari suatu dataset. Dalam proses ini, fitur-fitur yang tidak memberikan kontribusi signifikan terhadap pemodelan atau analisis dapat dieliminasi, sementara fitur-fitur yang penting dipertahankan."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "limit_balance        58\n",
       "sex                   2\n",
       "education_level       7\n",
       "marital_status        4\n",
       "age                  47\n",
       "pay_1                11\n",
       "pay_2                10\n",
       "pay_3                 9\n",
       "pay_4                10\n",
       "pay_5                 9\n",
       "pay_6                 8\n",
       "bill_amt_1         2125\n",
       "bill_amt_2         2107\n",
       "bill_amt_3         2071\n",
       "bill_amt_4         2036\n",
       "bill_amt_5         2009\n",
       "bill_amt_6         1986\n",
       "pay_amt_1          1186\n",
       "pay_amt_2          1138\n",
       "pay_amt_3          1086\n",
       "pay_amt_4          1011\n",
       "pay_amt_5           988\n",
       "pay_amt_6           989\n",
       "dtype: int64"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cek total unik data\n",
    "X_train[num_cols].nunique()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pada kondisi dengan data diatas, saya akan membuat kondisi di mana data yang dimiliki memang berbentuk numerik. Namun, terdapat pula data kategorikal di dalamnya. Oleh karena itu, data akan dipisahkan dengan membuat parameter > 11 yang termasuk data kategorikal. Dimana nantinya hasil ouput pada data memiliki kondisi numerical yang berisi kolom-kolom dengan jumlah nilai unik lebih dari 11, dan categorical_num yang berisi kolom-kolom dengan jumlah nilai unik 11 atau kurang"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['limit_balance', 'age', 'bill_amt_1', 'bill_amt_2', 'bill_amt_3', 'bill_amt_4', 'bill_amt_5', 'bill_amt_6', 'pay_amt_1', 'pay_amt_2', 'pay_amt_3', 'pay_amt_4', 'pay_amt_5', 'pay_amt_6']\n",
      "['sex', 'education_level', 'marital_status', 'pay_1', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6']\n"
     ]
    }
   ],
   "source": [
    "numerical = []\n",
    "categorical_num = []\n",
    "for i in num_cols:\n",
    "    if X_train[i].nunique()>11:\n",
    "        numerical.append(i)\n",
    "    else:\n",
    "        categorical_num.append(i)\n",
    "print(numerical)\n",
    "print(categorical_num)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dapat disimpulkan bahwa dari hasil ouput pada data memiliki kondisi numerical yang berisi kolom-kolom dengan jumlah nilai unik lebih dari 11, dan categorical_num yang berisi kolom-kolom dengan jumlah nilai unik 11 atau kurang"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>sex</th>\n",
       "      <th>education_level</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>pay_1</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>pay_6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1968</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2</td>\n",
       "      <td>-2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2725</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>-2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>443</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>825</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>664</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2604</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>-2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1478</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>617</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1993</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1897</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2370 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      sex  education_level  marital_status  pay_1  pay_2  pay_3  pay_4  pay_5  \\\n",
       "1968    2                2               1   -2.0   -2.0   -1.0    2.0      2   \n",
       "2725    1                2               2    0.0    0.0    0.0   -2.0     -2   \n",
       "443     1                2               1    0.0    0.0    0.0    0.0      0   \n",
       "825     2                2               1    0.0    0.0    0.0    0.0      0   \n",
       "664     2                2               1    0.0    0.0    0.0    0.0      0   \n",
       "...   ...              ...             ...    ...    ...    ...    ...    ...   \n",
       "2604    2                1               2   -2.0   -2.0   -2.0   -2.0     -2   \n",
       "1478    2                3               1    2.0    2.0    2.0    0.0      0   \n",
       "617     2                2               1    0.0    0.0    0.0    0.0      0   \n",
       "1993    2                3               1    2.0    2.0    2.0    2.0      3   \n",
       "1897    2                2               1    1.0    3.0    2.0    2.0      2   \n",
       "\n",
       "      pay_6  \n",
       "1968     -2  \n",
       "2725     -2  \n",
       "443       0  \n",
       "825       0  \n",
       "664       0  \n",
       "...     ...  \n",
       "2604     -2  \n",
       "1478      0  \n",
       "617       0  \n",
       "1993      2  \n",
       "1897      0  \n",
       "\n",
       "[2370 rows x 9 columns]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# memanggil data kategorikal\n",
    "X_train[categorical_num]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas menampilkan semua data yang memiliki kondisi katgorikal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# memisahkan data nominal dan ordinal\n",
    "nominal = ['sex','marital_status']\n",
    "ordinal =['education_level',  'pay_1', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dengan memisahkan data nominal dan ordinal, maka saya dapat menerapkan metode atau teknik analisis yang sesuai untuk setiap jenis data, karena karakteristik dan sifat data nominal dan ordinal berbeda."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Handling Outlier**\n",
    "\n",
    "Proses handling outlier pada `Feature Engineer` ini saya memilih proses `capping skew Winsorizer` dikarenakan jumlah `outlier` tidak banyak untuk handling. Esensi dari proses `capping skew Winsorizer` dimana proses ini cenderung lebih sederhana dan memerlukan sedikit komputasi dibandingkan dengan melatih model pembelajaran mesin untuk menangani outlier jika ditinjau dari ketersediaan data dan komputasi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "skew ['limit_balance', 'age', 'bill_amt_1', 'bill_amt_2', 'bill_amt_3', 'bill_amt_4', 'bill_amt_5', 'bill_amt_6', 'pay_amt_1', 'pay_amt_2', 'pay_amt_3', 'pay_amt_4', 'pay_amt_5', 'pay_amt_6']\n",
      "not skew []\n"
     ]
    }
   ],
   "source": [
    "# penampungan data\n",
    "skew = []\n",
    "not_skew =[]\n",
    "\n",
    "#membuat kondisi pengecekan skew data.\n",
    "for i in numerical:\n",
    "    if X_train[i].skew() > -0.5 and X_train[i].skew() < 0.5:\n",
    "        not_skew.append(i)\n",
    "    else:\n",
    "        skew.append(i)\n",
    "print('skew',skew)\n",
    "print('not skew',not_skew)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas merupakan hasil dari proses pengecekan data apakah memiliki sifat `skew distribution` atau `tidak`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Proses capping skewed\n",
    "winsoriser_skewed = Winsorizer(capping_method='iqr',\n",
    "                             tail='both',\n",
    "                             fold=1.5,# memilih nilai 1,5 karena skew tidak extreme \n",
    "                             variables=skew)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Tujuan dengan menggunakan ` capping skew` dilakukan untuk mengurangi pengaruh outlier dan mengatasi masalah distribusi data yang tidak simetris."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_cap = winsoriser_skewed.fit_transform(X_train)\n",
    "X_test_cap = winsoriser_skewed.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Langkah awal dalam proses seleksi fitur saya akan melakukan pengecekan korelasi menggunakan `phik`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "interval columns not set, guessing: ['limit_balance', 'sex', 'education_level', 'marital_status', 'age', 'pay_1', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6', 'bill_amt_1', 'bill_amt_2', 'bill_amt_3', 'bill_amt_4', 'bill_amt_5', 'bill_amt_6', 'pay_amt_1', 'pay_amt_2', 'pay_amt_3', 'pay_amt_4', 'pay_amt_5', 'pay_amt_6', 'default_payment_next_month']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "limit_balance                 0.237051\n",
       "sex                           0.030504\n",
       "education_level               0.072756\n",
       "marital_status                0.000000\n",
       "age                           0.056337\n",
       "pay_1                         0.624816\n",
       "pay_2                         0.491306\n",
       "pay_3                         0.337561\n",
       "pay_4                         0.317012\n",
       "pay_5                         0.310919\n",
       "pay_6                         0.385757\n",
       "bill_amt_1                    0.050579\n",
       "bill_amt_2                    0.047317\n",
       "bill_amt_3                    0.039870\n",
       "bill_amt_4                    0.062772\n",
       "bill_amt_5                    0.046389\n",
       "bill_amt_6                    0.033454\n",
       "pay_amt_1                     0.204781\n",
       "pay_amt_2                     0.197974\n",
       "pay_amt_3                     0.199761\n",
       "pay_amt_4                     0.156310\n",
       "pay_amt_5                     0.111837\n",
       "pay_amt_6                     0.198784\n",
       "Klasifikasi                   0.089455\n",
       "default_payment_next_month    1.000000\n",
       "Name: default_payment_next_month, dtype: float64"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#menghitung nilai korelasi menggunakan fitur phik\n",
    "\n",
    "combined_train_data = pd.concat([X_train_cap,y_train],axis=1)\n",
    "phik_overview = combined_train_data.phik_matrix()\n",
    "phik_overview['default_payment_next_month']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas menjelaskan bahwa beberapa 'columns' yang memiliki atau tidak memiliki korelasi dengan variabel `default_payment_next_month`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['limit_balance',\n",
       " 'pay_1',\n",
       " 'pay_2',\n",
       " 'pay_3',\n",
       " 'pay_4',\n",
       " 'pay_5',\n",
       " 'pay_6',\n",
       " 'pay_amt_1',\n",
       " 'pay_amt_2',\n",
       " 'pay_amt_3',\n",
       " 'pay_amt_4',\n",
       " 'pay_amt_5',\n",
       " 'pay_amt_6']"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# menggambil korelasi\n",
    "phik_overview['default_payment_next_month']\n",
    "features =[]\n",
    "for i in X_train.columns.tolist():\n",
    "    if phik_overview['default_payment_next_month'][i]> 0.1:# mengambil nilai korelasi diatas 0,1\n",
    "        features.append(i)\n",
    "features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas memberikan gambaran terkait variabel yang memiliki korelasi dengan  `default_payment_next_month` "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_cols =['limit_balance','pay_amt_1','pay_amt_2','pay_amt_3','pay_amt_4','pay_amt_5','pay_amt_6']\n",
    "\n",
    "cat_ord = ['pay_1','pay_2','pay_3','pay_4','pay_5','pay_6']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas memberikan gambaran terkait variabel yang sudah dipisahkan dengan numerik dan kategorikal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "# membuat variable untuk pengujian\n",
    "X_train_features = X_train_cap[features]\n",
    "X_test_features = X_test_cap[features]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>limit_balance</th>\n",
       "      <th>pay_1</th>\n",
       "      <th>pay_2</th>\n",
       "      <th>pay_3</th>\n",
       "      <th>pay_4</th>\n",
       "      <th>pay_5</th>\n",
       "      <th>pay_6</th>\n",
       "      <th>pay_amt_1</th>\n",
       "      <th>pay_amt_2</th>\n",
       "      <th>pay_amt_3</th>\n",
       "      <th>pay_amt_4</th>\n",
       "      <th>pay_amt_5</th>\n",
       "      <th>pay_amt_6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1968</th>\n",
       "      <td>80000.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2</td>\n",
       "      <td>-2</td>\n",
       "      <td>0.000</td>\n",
       "      <td>11049.375</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2725</th>\n",
       "      <td>180000.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>-2</td>\n",
       "      <td>1110.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>443</th>\n",
       "      <td>310000.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11171.625</td>\n",
       "      <td>11049.375</td>\n",
       "      <td>2500.0</td>\n",
       "      <td>9527.875</td>\n",
       "      <td>3000.0</td>\n",
       "      <td>4377.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>825</th>\n",
       "      <td>270000.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2500.000</td>\n",
       "      <td>2000.000</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2000.000</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>2000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>664</th>\n",
       "      <td>380000.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9000.000</td>\n",
       "      <td>9000.000</td>\n",
       "      <td>10068.0</td>\n",
       "      <td>8768.000</td>\n",
       "      <td>9087.0</td>\n",
       "      <td>9133.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2604</th>\n",
       "      <td>270000.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2</td>\n",
       "      <td>-2</td>\n",
       "      <td>592.000</td>\n",
       "      <td>1593.000</td>\n",
       "      <td>913.0</td>\n",
       "      <td>1471.000</td>\n",
       "      <td>1302.0</td>\n",
       "      <td>7107.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1478</th>\n",
       "      <td>30000.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3280.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1511.0</td>\n",
       "      <td>609.000</td>\n",
       "      <td>500.0</td>\n",
       "      <td>800.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>617</th>\n",
       "      <td>160000.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8450.000</td>\n",
       "      <td>5289.000</td>\n",
       "      <td>4022.0</td>\n",
       "      <td>4195.000</td>\n",
       "      <td>3986.0</td>\n",
       "      <td>3958.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1993</th>\n",
       "      <td>30000.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1700.000</td>\n",
       "      <td>1200.000</td>\n",
       "      <td>1600.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1500.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1897</th>\n",
       "      <td>10000.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>3000.0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>500.0</td>\n",
       "      <td>1000.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2370 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      limit_balance  pay_1  pay_2  pay_3  pay_4  pay_5  pay_6  pay_amt_1  \\\n",
       "1968        80000.0   -2.0   -2.0   -1.0    2.0      2     -2      0.000   \n",
       "2725       180000.0    0.0    0.0    0.0   -2.0     -2     -2   1110.000   \n",
       "443        310000.0    0.0    0.0    0.0    0.0      0      0  11171.625   \n",
       "825        270000.0    0.0    0.0    0.0    0.0      0      0   2500.000   \n",
       "664        380000.0    0.0    0.0    0.0    0.0      0      0   9000.000   \n",
       "...             ...    ...    ...    ...    ...    ...    ...        ...   \n",
       "2604       270000.0   -2.0   -2.0   -2.0   -2.0     -2     -2    592.000   \n",
       "1478        30000.0    2.0    2.0    2.0    0.0      0      0   3280.000   \n",
       "617        160000.0    0.0    0.0    0.0    0.0      0      0   8450.000   \n",
       "1993        30000.0    2.0    2.0    2.0    2.0      3      2   1700.000   \n",
       "1897        10000.0    1.0    3.0    2.0    2.0      2      0      0.000   \n",
       "\n",
       "      pay_amt_2  pay_amt_3  pay_amt_4  pay_amt_5  pay_amt_6  \n",
       "1968  11049.375        0.0      0.000        0.0        0.0  \n",
       "2725      0.000        0.0      0.000        0.0        0.0  \n",
       "443   11049.375     2500.0   9527.875     3000.0     4377.0  \n",
       "825    2000.000     2000.0   2000.000     2000.0     2000.0  \n",
       "664    9000.000    10068.0   8768.000     9087.0     9133.0  \n",
       "...         ...        ...        ...        ...        ...  \n",
       "2604   1593.000      913.0   1471.000     1302.0     7107.0  \n",
       "1478      0.000     1511.0    609.000      500.0      800.0  \n",
       "617    5289.000     4022.0   4195.000     3986.0     3958.0  \n",
       "1993   1200.000     1600.0      0.000     1500.0        0.0  \n",
       "1897      0.000     3000.0      0.000      500.0     1000.0  \n",
       "\n",
       "[2370 rows x 13 columns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# cek data baru\n",
    "X_train_features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hasil output diatas merupakan variable untuk pengujian. Dengan membuat variabel X_train_features dan X_test_features, saya dapat mempersiapkan data yang akan digunakan untuk menguji model. Dimana variabel-variabel ini terdiri dari fitur-fitur yang telah melalui proses capping dan telah dipilih berdasarkan daftar features yang relevan. Dalam proses pengujian, saya akan menggunakan variabel ini sebagai input untuk model yang telah dilatih sebelumnya"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Model Pipeline**\n",
    "\n",
    "Pipline berfungsi untuk menggabungkan proses `encoding` dan proses `scaling`. Dimana menggunakan pipeline dalam proses feature engineering dapat mencegah terjadinya kebocoran informasi (data leakage)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "# membuat scaler\n",
    "scaler = StandardScaler()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                 [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;,\n",
       "                                  &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                  &#x27;pay_amt_6&#x27;])])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label  sk-toggleable__label-arrow \">&nbsp;&nbsp;ColumnTransformer<a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for ColumnTransformer</span></a><span class=\"sk-estimator-doc-link \">i<span>Not fitted</span></span></label><div class=\"sk-toggleable__content \"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                 [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;,\n",
       "                                  &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                  &#x27;pay_amt_6&#x27;])])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label  sk-toggleable__label-arrow \">scaling</label><div class=\"sk-toggleable__content \"><pre>[&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;, &#x27;pay_amt_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label  sk-toggleable__label-arrow \">&nbsp;StandardScaler<a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content \"><pre>StandardScaler()</pre></div> </div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label  sk-toggleable__label-arrow \">remainder</label><div class=\"sk-toggleable__content \"><pre></pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label  sk-toggleable__label-arrow \">passthrough</label><div class=\"sk-toggleable__content \"><pre>passthrough</pre></div> </div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "ColumnTransformer(remainder='passthrough',\n",
       "                  transformers=[('scaling', StandardScaler(),\n",
       "                                 ['limit_balance', 'pay_amt_1', 'pay_amt_2',\n",
       "                                  'pay_amt_3', 'pay_amt_4', 'pay_amt_5',\n",
       "                                  'pay_amt_6'])])"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# transform berdasarkan scallar\n",
    "preprocessor = ColumnTransformer([('scaling',scaler,num_cols)],remainder = 'passthrough')\n",
    "preprocessor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>scaling__limit_balance</th>\n",
       "      <th>scaling__pay_amt_1</th>\n",
       "      <th>scaling__pay_amt_2</th>\n",
       "      <th>scaling__pay_amt_3</th>\n",
       "      <th>scaling__pay_amt_4</th>\n",
       "      <th>scaling__pay_amt_5</th>\n",
       "      <th>scaling__pay_amt_6</th>\n",
       "      <th>remainder__pay_1</th>\n",
       "      <th>remainder__pay_2</th>\n",
       "      <th>remainder__pay_3</th>\n",
       "      <th>remainder__pay_4</th>\n",
       "      <th>remainder__pay_5</th>\n",
       "      <th>remainder__pay_6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.686097</td>\n",
       "      <td>-1.028015</td>\n",
       "      <td>2.133638</td>\n",
       "      <td>-0.917534</td>\n",
       "      <td>-0.907005</td>\n",
       "      <td>-0.908620</td>\n",
       "      <td>-0.881127</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.138932</td>\n",
       "      <td>-0.713036</td>\n",
       "      <td>-1.007524</td>\n",
       "      <td>-0.917534</td>\n",
       "      <td>-0.907005</td>\n",
       "      <td>-0.908620</td>\n",
       "      <td>-0.881127</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.211471</td>\n",
       "      <td>2.142103</td>\n",
       "      <td>2.133638</td>\n",
       "      <td>-0.184365</td>\n",
       "      <td>2.288891</td>\n",
       "      <td>0.103903</td>\n",
       "      <td>0.504560</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.881459</td>\n",
       "      <td>-0.318602</td>\n",
       "      <td>-0.438955</td>\n",
       "      <td>-0.330999</td>\n",
       "      <td>-0.236153</td>\n",
       "      <td>-0.233605</td>\n",
       "      <td>-0.247959</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.788992</td>\n",
       "      <td>1.525872</td>\n",
       "      <td>1.551033</td>\n",
       "      <td>2.035084</td>\n",
       "      <td>2.034009</td>\n",
       "      <td>2.158312</td>\n",
       "      <td>2.010233</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2365</th>\n",
       "      <td>0.881459</td>\n",
       "      <td>-0.860026</td>\n",
       "      <td>-0.554659</td>\n",
       "      <td>-0.649781</td>\n",
       "      <td>-0.413593</td>\n",
       "      <td>-0.469185</td>\n",
       "      <td>1.368834</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2366</th>\n",
       "      <td>-1.098612</td>\n",
       "      <td>-0.097265</td>\n",
       "      <td>-1.007524</td>\n",
       "      <td>-0.474407</td>\n",
       "      <td>-0.702730</td>\n",
       "      <td>-0.739866</td>\n",
       "      <td>-0.627860</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2367</th>\n",
       "      <td>-0.026074</td>\n",
       "      <td>1.369801</td>\n",
       "      <td>0.496055</td>\n",
       "      <td>0.261988</td>\n",
       "      <td>0.500107</td>\n",
       "      <td>0.436685</td>\n",
       "      <td>0.371912</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2368</th>\n",
       "      <td>-1.098612</td>\n",
       "      <td>-0.545614</td>\n",
       "      <td>-0.666383</td>\n",
       "      <td>-0.448306</td>\n",
       "      <td>-0.907005</td>\n",
       "      <td>-0.402359</td>\n",
       "      <td>-0.881127</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2369</th>\n",
       "      <td>-1.263618</td>\n",
       "      <td>-1.028015</td>\n",
       "      <td>-1.007524</td>\n",
       "      <td>-0.037732</td>\n",
       "      <td>-0.907005</td>\n",
       "      <td>-0.739866</td>\n",
       "      <td>-0.564543</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2370 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      scaling__limit_balance  scaling__pay_amt_1  scaling__pay_amt_2  \\\n",
       "0                  -0.686097           -1.028015            2.133638   \n",
       "1                   0.138932           -0.713036           -1.007524   \n",
       "2                   1.211471            2.142103            2.133638   \n",
       "3                   0.881459           -0.318602           -0.438955   \n",
       "4                   1.788992            1.525872            1.551033   \n",
       "...                      ...                 ...                 ...   \n",
       "2365                0.881459           -0.860026           -0.554659   \n",
       "2366               -1.098612           -0.097265           -1.007524   \n",
       "2367               -0.026074            1.369801            0.496055   \n",
       "2368               -1.098612           -0.545614           -0.666383   \n",
       "2369               -1.263618           -1.028015           -1.007524   \n",
       "\n",
       "      scaling__pay_amt_3  scaling__pay_amt_4  scaling__pay_amt_5  \\\n",
       "0              -0.917534           -0.907005           -0.908620   \n",
       "1              -0.917534           -0.907005           -0.908620   \n",
       "2              -0.184365            2.288891            0.103903   \n",
       "3              -0.330999           -0.236153           -0.233605   \n",
       "4               2.035084            2.034009            2.158312   \n",
       "...                  ...                 ...                 ...   \n",
       "2365           -0.649781           -0.413593           -0.469185   \n",
       "2366           -0.474407           -0.702730           -0.739866   \n",
       "2367            0.261988            0.500107            0.436685   \n",
       "2368           -0.448306           -0.907005           -0.402359   \n",
       "2369           -0.037732           -0.907005           -0.739866   \n",
       "\n",
       "      scaling__pay_amt_6  remainder__pay_1  remainder__pay_2  \\\n",
       "0              -0.881127              -2.0              -2.0   \n",
       "1              -0.881127               0.0               0.0   \n",
       "2               0.504560               0.0               0.0   \n",
       "3              -0.247959               0.0               0.0   \n",
       "4               2.010233               0.0               0.0   \n",
       "...                  ...               ...               ...   \n",
       "2365            1.368834              -2.0              -2.0   \n",
       "2366           -0.627860               2.0               2.0   \n",
       "2367            0.371912               0.0               0.0   \n",
       "2368           -0.881127               2.0               2.0   \n",
       "2369           -0.564543               1.0               3.0   \n",
       "\n",
       "      remainder__pay_3  remainder__pay_4  remainder__pay_5  remainder__pay_6  \n",
       "0                 -1.0               2.0               2.0              -2.0  \n",
       "1                  0.0              -2.0              -2.0              -2.0  \n",
       "2                  0.0               0.0               0.0               0.0  \n",
       "3                  0.0               0.0               0.0               0.0  \n",
       "4                  0.0               0.0               0.0               0.0  \n",
       "...                ...               ...               ...               ...  \n",
       "2365              -2.0              -2.0              -2.0              -2.0  \n",
       "2366               2.0               0.0               0.0               0.0  \n",
       "2367               0.0               0.0               0.0               0.0  \n",
       "2368               2.0               2.0               3.0               2.0  \n",
       "2369               2.0               2.0               2.0               0.0  \n",
       "\n",
       "[2370 rows x 13 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# proses transformasi\n",
    "X_train_final = preprocessor.fit_transform(X_train_features)\n",
    "X_train_final_data = pd.DataFrame(X_train_final, columns= list(preprocessor.get_feature_names_out()))\n",
    "X_train_final_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 7. Model Definition"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pada model definitioan saya akan menggunakan model  `logistic regression`, `SVM`, dan `KNN` dimana ketiga model ini akan diuji dengan proses `hyperparameter tuning` untuk dapat menghasilkan nilai F-1 score. Hasil F-1 score yang didapat ini nantinya akan dibandingkan dari ketiga model tersebut dan diambil nilai mana yang lebih besar guna dapat mengetahui model mana yang paling baik digunakan pada proses `Model Evaluation`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "kasih penjelsan mengapa memilih metoide F-1 score, Crossvall dan kenapa menggunakan capping outlier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "logreg_pipe = Pipeline([('preprocessing', preprocessor), \n",
    "                        ('logreg', LogisticRegression(random_state=42))])\n",
    "\n",
    "svm_pipe = Pipeline([('preprocessing', preprocessor), \n",
    "                        ('SVM', SVC())])\n",
    "\n",
    "knn_pipe = Pipeline([('preprocessing', preprocessor), \n",
    "                        ('KNN', KNeighborsClassifier())])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pada bagian `Model Definotion` ini saya akan memilih  model `F1 score ` dalam `cross validation` karena ada beberapa keuntungan yang bakan saya dapatkan jika saya menggunakan model `F1 score ` dalam `cross validation` pada proses `Model Training` berikutnya, adapun kelebihan dari `cross validation` :\n",
    "\n",
    "- Menangani ketidakseimbangan kelas: F1-score sangat berguna ketika terdapat ketidakseimbangan antara jumlah sampel dari kelas positif dan negatif dalam dataset. Dalam kasus seperti itu, menggunakan metrik evaluasi seperti akurasi saja mungkin tidak memberikan gambaran yang akurat tentang kinerja model. F1-score mempertimbangkan baik presisi (proporsi prediksi positif yang benar) maupun recall (proporsi kasus positif yang terdeteksi dengan benar), sehingga memberikan informasi yang lebih baik tentang kemampuan model dalam mengklasifikasikan kelas-kelas yang tidak seimbang\n",
    "\n",
    "- Mengurangi variabilitas estimasi: Cross-validation membantu mengurangi variabilitas estimasi kinerja model dengan menguji model pada subset yang berbeda dari data pelatihan dan pengujian. Dalam setiap iterasi cross-validation, F1-score dihitung untuk mengevaluasi kinerja model. Dengan menggabungkan skor F1-score ini, saya dapat mendapatkan estimasi yang lebih stabil dan akurat tentang sejauh mana model dapat melakukan klasifikasi dengan benar\n",
    "\n",
    "- Menghindari overfitting: Cross-validation membantu menghindari overfitting dengan memvalidasi model pada subset pengujian yang tidak digunakan dalam pelatihan. Dengan menggunakan F1-score sebagai metrik evaluasi dalam cross-validation, saya dapat memastikan bahwa model tidak hanya mempelajari pola yang spesifik terhadap data pelatihan, tetapi juga mampu menggeneralisasi dengan baik pada data yang belum pernah dilihat sebelumnya."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 8. Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Model Cross Validation**\n",
    "\n",
    "Pada model `cross validation`saya akan melakukan pengecekan silang dengan menggunakan data baru sebagai model yang sudah dibua. Adapun tujuan dari melakukan pengecekan silang (cross-validation) dengan menggunakan data baru pada model yang sudah dibuat adalah untuk menguji kinerja model secara objektif dan mengukur sejauh mana model dapat menggeneralisasi pada data yang belum pernah dilihat sebelumnya. Dengan menggunakan data baru sebagai pengujian, saya mendapatkan perkiraan yang lebih akurat tentang kinerja model dan memvalidasi apakah model yang telah dilatih mampu mengklasifikasikan data yang tidak digunakan selama pelatihan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# menyimpan hasil cross validation\n",
    "cv_logreq = cross_val_score(logreg_pipe,X_train_features,y_train, cv =5,scoring='f1')\n",
    "cv_svm = cross_val_score(svm_pipe,X_train_features,y_train, cv =5,scoring='f1')\n",
    "cv_knn = cross_val_score(knn_pipe,X_train_features,y_train, cv =5,scoring='f1')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Proses Menemukan Model Berdasarkan Nilai F1 Score**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logistic\n",
      "f1score - All - Cross Validataion : [0.38518519 0.57324841 0.50331126 0.41958042 0.32394366]\n",
      "f1score - mean - Cross Validataion : 0.4410537865317787\n",
      "f1score - std - Cross Validataion : 0.08791882394364739\n",
      "f1score - Range of Test Set : 0.35313496258813126-0.5289726104754261\n",
      "--------------------------------------------------\n",
      "SVM_model\n",
      "f1score - All - Cross Validataion : [0.49350649 0.63030303 0.55345912 0.49350649 0.43312102]\n",
      "f1score - mean - Cross Validataion : 0.5207792311842305\n",
      "f1score - std - Cross Validataion : 0.06668583696523635\n",
      "f1score - Range of Test Set : 0.4540933942189942-0.5874650681494669\n",
      "--------------------------------------------------\n",
      "KNN_model\n",
      "f1score - All - Cross Validataion : [0.46060606 0.57303371 0.49425287 0.41025641 0.43209877]\n",
      "f1score - mean - Cross Validataion : 0.47404956354459127\n",
      "f1score - std - Cross Validataion : 0.05694944811421507\n",
      "f1score - Range of Test Set : 0.4171001154303762-0.5309990116588064\n",
      "--------------------------------------------------\n",
      "Best Model : SVM_model\n",
      "Cross validation mean from best model : 0.5207792311842305\n"
     ]
    }
   ],
   "source": [
    "# menemukan model terbaik berdasarkan skor cross val (mean) dengan for looping\n",
    "\n",
    "name_model = []\n",
    "cv_scores = 0\n",
    "\n",
    "for cv,name in zip([cv_logreq,cv_svm,cv_knn], \n",
    "                   ['Logistic','SVM_model', 'KNN_model']) : \n",
    "    print(name)\n",
    "    print(f'f1score - All - Cross Validataion : {cv}')\n",
    "    print(f'f1score - mean - Cross Validataion : {cv.mean()}')\n",
    "    print(f'f1score - std - Cross Validataion : {cv.std()}')\n",
    "    print(f'f1score - Range of Test Set : {cv.mean()-cv.std()}-{cv.mean()+cv.std()}')\n",
    "    print('-' * 50)\n",
    "\n",
    "    if cv.mean() > cv_scores :\n",
    "        cv_scores = cv.mean()\n",
    "        name_model = name\n",
    "    else:\n",
    "        pass\n",
    "print(f'Best Model : {name_model}')\n",
    "print(f'Cross validation mean from best model : {cv_scores}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dapat disimpulkan dari hasil output diatas berdasarkan nilai `mean` yang tertinggi pada nilai F1 Score bahwa `model erbaik : SVM_model`\n",
    "dengan nilai rata-rata validasi silang dari model terbaik : 0.5207792311842305"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Proses Looping Data**\n",
    "\n",
    "Pada bagian ini proses yang umumnya dilakukan dalam cross-validation untuk membandingkan kinerja beberapa model yang berbeda dan menentukan model mana yang paling baik untuk data yang saya miliki. Dimana tujuan utama dari proses ini adalah untuk memilih model yang dapat memberikan hasil yang lebih baik dalam memprediksi atau mengklasifikasikan data yang tidak terlihat sebelumnya"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-2 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-2 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-2 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-2 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-2 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-2 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-2 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                                  [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;,\n",
       "                                                   &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;,\n",
       "                                                   &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                                   &#x27;pay_amt_6&#x27;])])),\n",
       "                (&#x27;SVM&#x27;, SVC())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;Pipeline<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                                  [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;,\n",
       "                                                   &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;,\n",
       "                                                   &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                                   &#x27;pay_amt_6&#x27;])])),\n",
       "                (&#x27;SVM&#x27;, SVC())])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;preprocessing: ColumnTransformer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for preprocessing: ColumnTransformer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                 [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;,\n",
       "                                  &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                  &#x27;pay_amt_6&#x27;])])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">scaling</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;, &#x27;pay_amt_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;StandardScaler<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>StandardScaler()</pre></div> </div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">remainder</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;pay_1&#x27;, &#x27;pay_2&#x27;, &#x27;pay_3&#x27;, &#x27;pay_4&#x27;, &#x27;pay_5&#x27;, &#x27;pay_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">passthrough</label><div class=\"sk-toggleable__content fitted\"><pre>passthrough</pre></div> </div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('preprocessing',\n",
       "                 ColumnTransformer(remainder='passthrough',\n",
       "                                   transformers=[('scaling', StandardScaler(),\n",
       "                                                  ['limit_balance', 'pay_amt_1',\n",
       "                                                   'pay_amt_2', 'pay_amt_3',\n",
       "                                                   'pay_amt_4', 'pay_amt_5',\n",
       "                                                   'pay_amt_6'])])),\n",
       "                ('SVM', SVC())])"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm_pipe.fit(X_train_features,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Melakukan prediksi sebelum di tunning\n",
    "y_pred_train = svm_pipe.predict(X_train_features)\n",
    "y_pred_test = svm_pipe.predict(X_test_features)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report : \n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.87      0.97      0.91      1862\n",
      "           1       0.78      0.45      0.57       508\n",
      "\n",
      "    accuracy                           0.86      2370\n",
      "   macro avg       0.82      0.71      0.74      2370\n",
      "weighted avg       0.85      0.86      0.84      2370\n",
      " \n",
      "\n"
     ]
    }
   ],
   "source": [
    "#cek hasil model \n",
    "print('Classification Report : \\n', classification_report(y_train, y_pred_train), '\\n')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dari data model diatas didapat bahwa model memiliki akurasi keseluruhan sebesar 91%, yang menunjukkan bahwa sebagian besar prediksi yang dilakukan oleh model adalah benar. Namun, perlu diperhatikan bahwa kinerja model lebih rendah dibandingkan dengan kelas non-default (0) dengan nilai F1score 57%. Ini menunjukkan bahwa model cenderung lebih baik dalam memprediksi kelas non-default (0) daripada kelas default (1) ."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Hyperparameter Tuning**\n",
    "\n",
    "Metode yang digunakan pada proses `Hyperparameter Tuning` menggunakan metode `gird`. Dimana tujuan dari metode `hyperparameter tuning` menggunakan `metode grid` adalah untuk mencari kombinasi hyperparameter yang optimal untuk model yang saya gunakan. Dalam `hyperparameter tuning`, saya mencoba berbagai kombinasi nilai hyperparameter yang berbeda untuk menemukan kombinasi yang memberikan kinerja terbaik untuk model yang saya gunakan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-3 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-3 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-3 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-3 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-3 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-3 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                        ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                                          transformers=[(&#x27;scaling&#x27;,\n",
       "                                                                         StandardScaler(),\n",
       "                                                                         [&#x27;limit_balance&#x27;,\n",
       "                                                                          &#x27;pay_amt_1&#x27;,\n",
       "                                                                          &#x27;pay_amt_2&#x27;,\n",
       "                                                                          &#x27;pay_amt_3&#x27;,\n",
       "                                                                          &#x27;pay_amt_4&#x27;,\n",
       "                                                                          &#x27;pay_amt_5&#x27;,\n",
       "                                                                          &#x27;pay_amt_6&#x27;])])),\n",
       "                                       (&#x27;SVM&#x27;, SVC())]),\n",
       "             param_grid={&#x27;SVM__C&#x27;: [0.001, 0.01, 0.1, 1, 10, 500],\n",
       "                         &#x27;SVM__gamma&#x27;: [0.001, 0.01, 0.1, 1, 10, 500, &#x27;auto&#x27;]},\n",
       "             scoring=&#x27;f1&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;GridSearchCV<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.model_selection.GridSearchCV.html\">?<span>Documentation for GridSearchCV</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                        ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                                          transformers=[(&#x27;scaling&#x27;,\n",
       "                                                                         StandardScaler(),\n",
       "                                                                         [&#x27;limit_balance&#x27;,\n",
       "                                                                          &#x27;pay_amt_1&#x27;,\n",
       "                                                                          &#x27;pay_amt_2&#x27;,\n",
       "                                                                          &#x27;pay_amt_3&#x27;,\n",
       "                                                                          &#x27;pay_amt_4&#x27;,\n",
       "                                                                          &#x27;pay_amt_5&#x27;,\n",
       "                                                                          &#x27;pay_amt_6&#x27;])])),\n",
       "                                       (&#x27;SVM&#x27;, SVC())]),\n",
       "             param_grid={&#x27;SVM__C&#x27;: [0.001, 0.01, 0.1, 1, 10, 500],\n",
       "                         &#x27;SVM__gamma&#x27;: [0.001, 0.01, 0.1, 1, 10, 500, &#x27;auto&#x27;]},\n",
       "             scoring=&#x27;f1&#x27;)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: Pipeline</label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                                  [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;,\n",
       "                                                   &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;,\n",
       "                                                   &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                                   &#x27;pay_amt_6&#x27;])])),\n",
       "                (&#x27;SVM&#x27;, SVC())])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" ><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;preprocessing: ColumnTransformer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for preprocessing: ColumnTransformer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                 [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;,\n",
       "                                  &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                  &#x27;pay_amt_6&#x27;])])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-16\" type=\"checkbox\" ><label for=\"sk-estimator-id-16\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">scaling</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;, &#x27;pay_amt_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-17\" type=\"checkbox\" ><label for=\"sk-estimator-id-17\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;StandardScaler<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>StandardScaler()</pre></div> </div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-18\" type=\"checkbox\" ><label for=\"sk-estimator-id-18\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">remainder</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;pay_1&#x27;, &#x27;pay_2&#x27;, &#x27;pay_3&#x27;, &#x27;pay_4&#x27;, &#x27;pay_5&#x27;, &#x27;pay_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-19\" type=\"checkbox\" ><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">passthrough</label><div class=\"sk-toggleable__content fitted\"><pre>passthrough</pre></div> </div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-20\" type=\"checkbox\" ><label for=\"sk-estimator-id-20\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[('preprocessing',\n",
       "                                        ColumnTransformer(remainder='passthrough',\n",
       "                                                          transformers=[('scaling',\n",
       "                                                                         StandardScaler(),\n",
       "                                                                         ['limit_balance',\n",
       "                                                                          'pay_amt_1',\n",
       "                                                                          'pay_amt_2',\n",
       "                                                                          'pay_amt_3',\n",
       "                                                                          'pay_amt_4',\n",
       "                                                                          'pay_amt_5',\n",
       "                                                                          'pay_amt_6'])])),\n",
       "                                       ('SVM', SVC())]),\n",
       "             param_grid={'SVM__C': [0.001, 0.01, 0.1, 1, 10, 500],\n",
       "                         'SVM__gamma': [0.001, 0.01, 0.1, 1, 10, 500, 'auto']},\n",
       "             scoring='f1')"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "\n",
    "# Define parameter grid\n",
    "param_grid = {'SVM__C': [0.001, 0.01, 0.1, 1, 10, 500],# nilai parameter 'gamma' yang optimal\n",
    "              'SVM__gamma': [0.001, 0.01, 0.1, 1, 10, 500, 'auto']}#nilai  parameter 'C' yang optimal (auto untuk meningkatkan nilai hasil setelah tuning)\n",
    "\n",
    "# Initialize GridSearchCV with SVM classifier and parameter grid\n",
    "svm_grid = GridSearchCV(estimator=svm_pipe, param_grid=param_grid, cv=5, scoring='f1')\n",
    "\n",
    "# Fit GridSearchCV to the training data\n",
    "svm_grid.fit(X_train_features, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Akses model terbaik yang ditemukan\n",
    "best_svm = svm_grid.best_estimator_\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-4 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-4 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-4 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-4 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-4 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-4 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-4 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-4 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-4 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-4 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-4 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                                  [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;,\n",
       "                                                   &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;,\n",
       "                                                   &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                                   &#x27;pay_amt_6&#x27;])])),\n",
       "                (&#x27;SVM&#x27;, SVC(C=1, gamma=&#x27;auto&#x27;))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-21\" type=\"checkbox\" ><label for=\"sk-estimator-id-21\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;Pipeline<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                                   transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                                  [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;,\n",
       "                                                   &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;,\n",
       "                                                   &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                                   &#x27;pay_amt_6&#x27;])])),\n",
       "                (&#x27;SVM&#x27;, SVC(C=1, gamma=&#x27;auto&#x27;))])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-22\" type=\"checkbox\" ><label for=\"sk-estimator-id-22\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;preprocessing: ColumnTransformer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for preprocessing: ColumnTransformer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
       "                  transformers=[(&#x27;scaling&#x27;, StandardScaler(),\n",
       "                                 [&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;,\n",
       "                                  &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;,\n",
       "                                  &#x27;pay_amt_6&#x27;])])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-23\" type=\"checkbox\" ><label for=\"sk-estimator-id-23\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">scaling</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;limit_balance&#x27;, &#x27;pay_amt_1&#x27;, &#x27;pay_amt_2&#x27;, &#x27;pay_amt_3&#x27;, &#x27;pay_amt_4&#x27;, &#x27;pay_amt_5&#x27;, &#x27;pay_amt_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-24\" type=\"checkbox\" ><label for=\"sk-estimator-id-24\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;StandardScaler<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>StandardScaler()</pre></div> </div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-25\" type=\"checkbox\" ><label for=\"sk-estimator-id-25\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">remainder</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;pay_1&#x27;, &#x27;pay_2&#x27;, &#x27;pay_3&#x27;, &#x27;pay_4&#x27;, &#x27;pay_5&#x27;, &#x27;pay_6&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-26\" type=\"checkbox\" ><label for=\"sk-estimator-id-26\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">passthrough</label><div class=\"sk-toggleable__content fitted\"><pre>passthrough</pre></div> </div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-27\" type=\"checkbox\" ><label for=\"sk-estimator-id-27\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC(C=1, gamma=&#x27;auto&#x27;)</pre></div> </div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('preprocessing',\n",
       "                 ColumnTransformer(remainder='passthrough',\n",
       "                                   transformers=[('scaling', StandardScaler(),\n",
       "                                                  ['limit_balance', 'pay_amt_1',\n",
       "                                                   'pay_amt_2', 'pay_amt_3',\n",
       "                                                   'pay_amt_4', 'pay_amt_5',\n",
       "                                                   'pay_amt_6'])])),\n",
       "                ('SVM', SVC(C=1, gamma='auto'))])"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "best_svm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 9. Model Evaluation\n",
    "\n",
    "Proses `Model Evaluation` pada bagian ini yaitu untuk mengetahui nilai `Prediksi F1score Sebelum Tuning` dengan `Prediksi F1score Setelah Tuning` dari data yang telah diolah, dan dari hasil nilai inilah maka dapat disimpulkan apakah data ini masih dikatakan `Goodfitting`, `Overfitting` atau `Underfitting`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Melakukan prediksi pada data uji menggunakan model terbaik\n",
    "y_pred_train_best = best_svm.predict(X_train_features)\n",
    "y_pred_test_best = best_svm.predict(X_test_features)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report : \n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.87      0.97      0.91      1862\n",
      "           1       0.78      0.46      0.58       508\n",
      "\n",
      "    accuracy                           0.86      2370\n",
      "   macro avg       0.83      0.71      0.75      2370\n",
      "weighted avg       0.85      0.86      0.84      2370\n",
      " \n",
      "\n",
      "Confusion Matrix      : \n",
      " <sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay object at 0x14f520f70>\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAgQAAAGwCAYAAADWsX1oAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAABCtUlEQVR4nO3de1gU9f4H8PcssIDILqLBuglqWQqlaGhIeT2SeMk0LbPIyEhPBt4oUyvJS0ZiecFI0kryhEftIimdKFITS0LFKDMkbwmKC3YQVvBw3f39QcyvDdx22YWFnffrPPM87cx3Zj+zh8f97Od7GUGv1+tBREREkiazdQBERERke0wIiIiIiAkBERERMSEgIiIiMCEgIiIiMCEgIiIiMCEgIiIiAI62DsASOp0OhYWFcHd3hyAItg6HiIjMpNfrce3aNajVashkLfcbtbKyEtXV1RZfRy6Xw8XFxQoRtT3tOiEoLCyEj4+PrcMgIiILFRQUoFu3bi1y7crKSnR27YDrsHwdPpVKhfPnz9tlUtCuEwJ3d3cAQBg6QA5WCMg+rb+ca+sQiFqM9to1+Nx+h/jveUuorq7GdegRBjeLviuqoUeyRoPq6momBG1NQzeBHAITArJbCoXC1iEQtbjW6PZ1sfC7wt4H3bXrhICIiMhUMgiQWZB4yOz8yT9MCIiISBJksOxXvr1XCOz9/oiIiMgErBAQEZEkCAIgs2CoggDAChMV2iwmBEREJAnsMjDO3u+PiIiITMAKARERSYJMsHCWAcAuAyIiovaOXQbG2fv9ERERkQlYISAiIkmQWTjLwN5/QTMhICIiSWCXgXH2fn9ERERkAlYIiIhIEgRBsOghSvb+CD0mBEREJAnsMjCOCQEREUkCBxUaZ+/3R0RERCZghYCIiCRBgGW/gjmGgIiIyA5YZeliO2bv90dEREQmYIWAiIgkgbMMjGNCQEREksBZBsbZ+/0RERGRCVghICIiSWCXgXFMCIiISBJkECCzYPKgvScE9n5/REREZAJWCIiISBI4qNA4JgRERCQJHENgHBMCIiKSBFYIjLP3+yMiIiITsEJARESSUP9wo+aXCATorRdMG8SEgIiIJIFdBsbZ+/0RERGRCVghICIiSeAsA+OYEBARkSSwy8A4e78/IiIiMgErBEREJAmWP8vAgvJCO8AKARERSUJDl4ElmzkyMjIwYcIEqNVqCIKAlJSURm1yc3PxwAMPQKlUws3NDYMGDUJ+fr54vLKyEpGRkejcuTM6duyIKVOmoKioyOAa+fn5GD9+PDp06AAvLy8sXLgQtbW15n8+Zp9BREREf6uiogIBAQFISEho8vjZs2cxZMgQ9OnTB9988w1++uknLF26FC4uLmKbBQsWYO/evfjoo49w8OBBFBYWYvLkyeLxuro6jB8/HtXV1Th8+DA++OADJCUlISYmxux4Bb1e325XWtBqtVAqlZgBN8jtvJRD0pVYcdHWIRC1GK1WC2VXX5SVlUGhULTceyiVeKujJ1yF5v8O/p9eh6jyEhQUFBjE6uzsDGdnZ6PnCoKA3bt3Y9KkSeK+adOmwcnJCf/617+aPKesrAw33XQTtm/fjoceeggAcOrUKfj5+SEzMxODBw/GF198gfvvvx+FhYXw9vYGACQmJmLRokW4cuUK5HK5yffHCgEREUmCtboMfHx8oFQqxS02NtbsWHQ6HT7//HPcfvvtCA0NhZeXF4KCggy6FbKzs1FTU4OQkBBxX58+feDr64vMzEwAQGZmJvr27SsmAwAQGhoKrVaLkydPmhUTBxUSEZEkWGtQYVMVAnMVFxejvLwcr7/+Ol599VWsXr0aaWlpmDx5Mg4cOIDhw4dDo9FALpfDw8PD4Fxvb29oNBoAgEajMUgGGo43HDMHEwIiIiIzKBQKi7s3dDodAGDixIlYsGABAKB///44fPgwEhMTMXz4cIvjNBe7DIiISBJae5aBMV26dIGjoyP8/f0N9vv5+YmzDFQqFaqrq1FaWmrQpqioCCqVSmzz11kHDa8b2piKCQEREUlC/dMOm79Zc+i6XC7HoEGDkJeXZ7D/119/Rffu3QEAgYGBcHJywr59+8TjeXl5yM/PR3BwMAAgODgYJ06cQHFxsdgmPT0dCoWiUbLxd9hlQERE1ALKy8tx5swZ8fX58+eRk5MDT09P+Pr6YuHChXjkkUcwbNgwjBw5Emlpadi7dy+++eYbAIBSqURERASio6Ph6ekJhUKBOXPmIDg4GIMHDwYAjB49Gv7+/pg+fTri4uKg0Wjw8ssvIzIy0uyxDUwIiIhIEgRY9ivf3HOPHTuGkSNHiq+jo6MBAOHh4UhKSsKDDz6IxMRExMbGYu7cuejduzc++eQTDBkyRDxn3bp1kMlkmDJlCqqqqhAaGoq3335bPO7g4IDU1FTMnj0bwcHBcHNzQ3h4OFasWGH+/XEdAqK2jesQkD1rzXUI3ld2QQcL1iG4rtfhqbLfWzRWW+IYAiIiImKXARERSUNrdxm0N0wIiIhIEpgQGMcuAyIiImKFgIiIpIEVAuOYEBARkSQIggBBaP7XumDnKQETAiIikgRWCIzjGAIiIiJihYCIiKSh4ZkElpxvz5gQEBGRJAhC/dbs860XSptk7wkPERERmYAVAiIikgThj/9Zcr49Y0JARESSwFkGxrHLgIiIiFghICIiaWCFwDgmBEREJAkyADILvtVlequF0iaxy4CIiIhYISAiImngLAPjmBAQEZFk2PdXumWYEBARkSRYvFKhnWcTHENARERErBAQEZE0cNqhcUwIiIhIEmQQILPga92Sc9sDdhkQERERKwRERCQN7DIwjgkBERFJAmcZGMcuAyIiImKFgIiIpIFdBsYxISAiIkng0sXGscuAiIiIWCEgIiJpkAkWPv7YvgsErBAQEZE0CFbYzJGRkYEJEyZArVZDEASkpKTcsO0zzzwDQRCwfv16g/0lJSUICwuDQqGAh4cHIiIiUF5ebtDmp59+wtChQ+Hi4gIfHx/ExcWZGWk9JgRERCQJrZ0QVFRUICAgAAkJCUbb7d69G99//z3UanWjY2FhYTh58iTS09ORmpqKjIwMzJo1Szyu1WoxevRodO/eHdnZ2VizZg2WLVuGzZs3mxktuwyIiIhaxNixYzF27FijbS5duoQ5c+bgyy+/xPjx4w2O5ebmIi0tDUePHsXAgQMBABs3bsS4cePwxhtvQK1WIzk5GdXV1Xj//fchl8txxx13ICcnB2vXrjVIHEzBCgEREUmCYIX/AfW/yv+8VVVVNSsenU6H6dOnY+HChbjjjjsaHc/MzISHh4eYDABASEgIZDIZsrKyxDbDhg2DXC4X24SGhiIvLw9Xr141Kx4mBEREJAkNKxVasgGAj48PlEqluMXGxjYrntWrV8PR0RFz585t8rhGo4GXl5fBPkdHR3h6ekKj0YhtvL29Ddo0vG5oYyp2GRAREZmhoKAACoVCfO3s7Gz2NbKzs7FhwwYcP34cQhtZE5kVAonpdW8Qnv1oK14/cwyJFRcRcH+owfHEiotNbvfNf0Zs49P/Tszbux1rL53EG/knELZxNZzdOhhcp/tdAZj/+Q6svXQSb178GXM++xA39/VrlXskMsXVwst4/6m5eM6nL+Z07oUVg0Jw4fiPTbZNnrsEz7j5YN9b77ZylGRNMitsAKBQKAy25iQEhw4dQnFxMXx9feHo6AhHR0dcuHABzz33HHr06AEAUKlUKC4uNjivtrYWJSUlUKlUYpuioiKDNg2vG9qYigmBxDi7dcDFE79gx4KXmzz+wi0DDLYPnomGTqfDDyn/AQAoVd6Yv3cHis/+htUjJmDjpMeh9rsd4e+sM3iPOSkfoqTgElaPmIA37puMqmsVmPtZMmSOLEqR7VVcLcWaUZPh4OSIqN3b8Er2fjwUuxQdPJSN2v6w5wucP3Icyq7eTVyJ2pPWnmVgzPTp0/HTTz8hJydH3NRqNRYuXIgvv/wSABAcHIzS0lJkZ2eL5+3fvx86nQ5BQUFim4yMDNTU1Iht0tPT0bt3b3Tq1MmsmNrEv84JCQlYs2YNNBoNAgICsHHjRtx99922DssunfzqAE5+deCGx7VFVwxeB4wfjV8zDuP33/IBAH3HhqCutgY7FrwEvV4PAEietwQxR77GTbf0wJVzv8H79l7o2LkT9q58A1cvXQYApMauQ8yRr9HZtxuunPutZW6OyERfrd0Ez25dEf7OWnFflx6+jdpdLbyMnc/FYO5nH+KtKU+2YoRkD8rLy3HmzBnx9fnz55GTkwNPT0/4+vqic+fOBu2dnJygUqnQu3dvAICfnx/GjBmDmTNnIjExETU1NYiKisK0adPEKYqPPfYYli9fjoiICCxatAg///wzNmzYgHXr1sFcNq8Q7Ny5E9HR0XjllVdw/PhxBAQEIDQ0tFGZhFqfu1cX9B0zCt99sEPc5+gsR211jZgMAEDN/yoBAL3uGQQAKDp9FuW/l+De8Efh4OQEJxcX3Bs+DZdzf8V/LxS07k0QNeHH/6TDd0A/bH78GSzs3h+rgsfg0NbtBm10Oh2SIubjvvnPQO3f20aRklUJAgQLNnOff3zs2DEMGDAAAwYMAABER0djwIABiImJMfkaycnJ6NOnD0aNGoVx48ZhyJAhBmsMKJVKfPXVVzh//jwCAwPx3HPPISYmxuwph0AbqBCsXbsWM2fOxIwZMwAAiYmJ+Pzzz/H+++9j8eLFNo5O2oLDHkbltQr88NkX4r68g9/h4ddjcN/8Z7A/4T04u3XAgyuWAAAUqvrRsFXlFVg79mE8s+M9jFs8DwBQfOY84ieGQVdX1/o3QvQXv5/PR8a7HyJkztMY83wULhz/Ebuej4GjkxOCH38YAPDVm29D5uiAfzz7lI2jJWtp7acdjhgxwuDH09/57bffGu3z9PTE9u3bGzf+k379+uHQoUNmRteYTSsE1dXVyM7ORkhIiLhPJpMhJCQEmZmZjdpXVVU1mv9JLeee6Y/gyM7dqP3THNvLub8iadYChMydhfjfT2P1ueP4/UIByoqKodfV/+E7ubhg+ttv4Oz3R7F6xANYM+pBFP6Sh8hPP4CTi4utbodIpNfp4Nv/Tkxavhi+/e/E0KfCMGTGY8h470MAwIUffsL+t99H+Oa1bWYEOFFLs2mF4Pfff0ddXV2TcyhPnTrVqH1sbCyWL1/eWuFJWq977oaqdy9sCZ/d6NjRXSk4uisF7l5dUF1xHXq9HiFzZuL38xcAAIOmTkLn7t0QN/IBMTt+b0YU1l46iYD7R+PYx3ta9V6I/kqp8kLXPrcZ7FP17oXjfwyePfPdEVy78jte7D1YPK6rq8PHS1ZiX8J7eC238Q8Wavtau0LQ3ti8y8AcS5YsQXR0tPhaq9XCx8fHhhHZr3vDp+HC8R9x6UTuDdtcK/4dAHDPE4+gprIKufvrS1byDq7Q63QGpbKG14LM5sNWiHDr4IEoOn3WYF/R6XPo7NsNABD06BT0GTnE4Hj8xMcx+NEpCJ4+tdXiJOsSxwJYcL49s2lC0KVLFzg4ODQ5h7Kp+ZPOzs7Nmu9J/8/ZrQNuurWH+LpLDx906+ePipJSXL1YCABwce+Iux68Hx8vWdHkNUb880mczTqGqvIK+P1jGKasehm7Y2Lxv7L6Lpzc/RmYsuolPLpuFQ4kboUgkyH0uUjoamuRl3G4xe+R6O+MmvM04v7xIL5YsxGBk+/Hb8dy8O3W7QjbuBoA0LFzJ3TsbDhly8HJCQrvm6C6/VZbhExWwMcfG2fThEAulyMwMBD79u3DpEmTANSP7N23bx+ioqJsGZrd6n5XAKLTPhJfP7x6GQAg88Nd+OCf9dWXgQ9NhCAIOPrRZ01eo8fA/rj/pefg3LEDin49i+S5i5H170/E40W/nsXbD8/A+CUL8ML+z6DX6VHw08/YOGk6tBrOHiHb6xHYH8/s2IKUmNfxeewGdOnhg4fjliFo2oO2Do3IZgS9OUMgW8DOnTsRHh6Od955B3fffTfWr1+PXbt24dSpU43GFvyVVquFUqnEDLhBbve9OyRViRUXbR0CUYvRarVQdvVFWVmZwXLAVn8PpRKH1D7oaEG3ZblOh6GFBS0aqy3ZfAzBI488gitXriAmJgYajQb9+/dHWlra3yYDRERE5mjGUgKNzrdnNk8IACAqKopdBERERDbUJhICIiKilsYKgXFMCIiISBI47dA4TgonIiIiVgiIiEga2GVgHBMCIiKSBHYZGMcuAyIiImKFgIiIpIFdBsYxISAiIkmQCQJkFnyrW3Jue8CEgIiIJIEVAuM4hoCIiIhYISAiImkQYOEsAzt/iB4TAiIikgRBVr81+3ybPhu45bHLgIiIiFghICIiibBwYSJ7H1XIhICIiCSBswyMY5cBERERsUJARETSUF8hsORZBlYMpg1iQkBERJLALgPj2GVARERErBAQEZE08FkGxjEhICIiSWCXgXFMCIiISBIEC9chsGgNg3aAYwiIiIiIFQIiIpIGdhkYxwoBERFJQkNCYMlmjoyMDEyYMAFqtRqCICAlJUU8VlNTg0WLFqFv375wc3ODWq3GE088gcLCQoNrlJSUICwsDAqFAh4eHoiIiEB5eblBm59++glDhw6Fi4sLfHx8EBcX16zPhwkBERFRC6ioqEBAQAASEhIaHbt+/TqOHz+OpUuX4vjx4/j000+Rl5eHBx54wKBdWFgYTp48ifT0dKSmpiIjIwOzZs0Sj2u1WowePRrdu3dHdnY21qxZg2XLlmHz5s1mx8suAyIikgRBJkCQWTCoUG/euWPHjsXYsWObPKZUKpGenm6w76233sLdd9+N/Px8+Pr6Ijc3F2lpaTh69CgGDhwIANi4cSPGjRuHN954A2q1GsnJyaiursb7778PuVyOO+64Azk5OVi7dq1B4mAKVgiIiEgSrNVloNVqDbaqqiqrxFdWVgZBEODh4QEAyMzMhIeHh5gMAEBISAhkMhmysrLENsOGDYNcLhfbhIaGIi8vD1evXjXr/ZkQEBERmcHHxwdKpVLcYmNjLb5mZWUlFi1ahEcffRQKhQIAoNFo4OXlZdDO0dERnp6e0Gg0Yhtvb2+DNg2vG9qYil0GREQkCdZaqbCgoED80gYAZ2dni+KqqanB1KlTodfrsWnTJouuZQkmBEREJAnWmnaoUCgMEgJLNCQDFy5cwP79+w2uq1KpUFxcbNC+trYWJSUlUKlUYpuioiKDNg2vG9qYil0GRERENtCQDJw+fRpff/01OnfubHA8ODgYpaWlyM7OFvft378fOp0OQUFBYpuMjAzU1NSIbdLT09G7d2906tTJrHiYEBARkSQ0LF1syWaO8vJy5OTkICcnBwBw/vx55OTkID8/HzU1NXjooYdw7NgxJCcno66uDhqNBhqNBtXV1QAAPz8/jBkzBjNnzsSRI0fw3XffISoqCtOmTYNarQYAPPbYY5DL5YiIiMDJkyexc+dObNiwAdHR0WZ/PuwyICIiSRBgYZeBme2PHTuGkSNHiq8bvqTDw8OxbNky7NmzBwDQv39/g/MOHDiAESNGAACSk5MRFRWFUaNGQSaTYcqUKYiPjxfbKpVKfPXVV4iMjERgYCC6dOmCmJgYs6ccAkwIiIhIIlr74UYjRoyAXq+/4XFjxxp4enpi+/btRtv069cPhw4dMiu2prDLgIiIiFghICIiibBwloHZfQbtDBMCIiKShNbuMmhv2GVARERErBAQEZE0CLL6zZLz7RkTAiIikgR2GRhn5/kOERERmYIVAiIikgaZUL9Zcr4dY0JARETSYK2nG9kpJgRERCQJHENgHMcQEBERESsEREQkERxDYBQTAiIikgaOITCKXQZERETECgEREUmDIBMgWFD2t+Tc9oAJARERSQO7DIxilwERERGxQkBERNIgCBZ2Gdh5hYAJARERSQO7DIwyKSHYs2ePyRd84IEHmh0MERER2YZJCcGkSZNMupggCKirq7MkHiIiopYhg4ULE1ktkjbJpIRAp9O1dBxEREQtis8yMM6iMQSVlZVwcXGxVixEREQth0sXG2V2AaSurg4rV67EzTffjI4dO+LcuXMAgKVLl+K9996zeoBERETU8sxOCFatWoWkpCTExcVBLpeL+++88068++67Vg2OiIjIahpmGViy2TGzE4Jt27Zh8+bNCAsLg4ODg7g/ICAAp06dsmpwRERE1iLILN/smdm3d+nSJfTq1avRfp1Oh5qaGqsERURERK3L7ITA398fhw4darT/448/xoABA6wSFBERkdWxy8Aos2cZxMTEIDw8HJcuXYJOp8Onn36KvLw8bNu2DampqS0RIxERkcX4tEPjzK4QTJw4EXv37sXXX38NNzc3xMTEIDc3F3v37sV9993XEjESERFRC2vWOgRDhw5Fenq6tWMhIiJqOXyWgVHNXpjo2LFjyM3NBVA/riAwMNBqQREREVkdFyYyyuwug4sXL2Lo0KG4++67MW/ePMybNw+DBg3CkCFDcPHixZaIkYiIqN3JyMjAhAkToFarIQgCUlJSDI7r9XrExMSga9eucHV1RUhICE6fPm3QpqSkBGFhYVAoFPDw8EBERATKy8sN2vz0008YOnQoXFxc4OPjg7i4uGbFa3ZC8PTTT6Ompga5ubkoKSlBSUkJcnNzodPp8PTTTzcrCCIiopbW8CwDSzZzVFRUICAgAAkJCU0ej4uLQ3x8PBITE5GVlQU3NzeEhoaisrJSbBMWFoaTJ08iPT0dqampyMjIwKxZs8TjWq0Wo0ePRvfu3ZGdnY01a9Zg2bJl2Lx5s/mfj16v15tzgqurKw4fPtxoimF2djaGDh2K69evmx1Ec2m1WiiVSsyAG+Sw71IOSVdiBStvZL+0Wi2UXX1RVlYGhULRcu+hVKJo6hAonJr/CB9tTS28d32LgoICg1idnZ3h7Oxs9FxBELB7927x6cF6vR5qtRrPPfccnn/+eQBAWVkZvL29kZSUhGnTpiE3Nxf+/v44evQoBg4cCABIS0vDuHHjcPHiRajVamzatAkvvfQSNBqNuHrw4sWLkZKSYvZigWZXCHx8fJpcgKiurg5qtdrcyxEREbUSS9cgqP/h6ePjA6VSKW6xsbFmR3L+/HloNBqEhISI+5RKJYKCgpCZmQkAyMzMhIeHh5gMAEBISAhkMhmysrLENsOGDTN4lEBoaCjy8vJw9epVs2IyO1Vas2YN5syZg4SEBDHIY8eOYd68eXjjjTfMvRwREVG70lSFwFwajQYA4O3tbbDf29tbPKbRaODl5WVw3NHREZ6engZtevbs2egaDcc6depkckwmJQSdOnUy6DupqKhAUFAQHB3rT6+trYWjoyOeeuopsRxCRETUljRnHMBfzwcAhULRYt0btmRSQrB+/foWDoOIiKiFtaFphyqVCgBQVFSErl27ivuLiorQv39/sU1xcbHBebW1tSgpKRHPV6lUKCoqMmjT8LqhjalMSgjCw8PNuigRERHdWM+ePaFSqbBv3z4xAdBqtcjKysLs2bMBAMHBwSgtLUV2dra41s/+/fuh0+kQFBQktnnppZdQU1MDJycnAEB6ejp69+5tVncB0IxBhX9WWVkJrVZrsBEREbVFrT3tsLy8HDk5OcjJyQFQP5AwJycH+fn5EAQB8+fPx6uvvoo9e/bgxIkTeOKJJ6BWq8Wudz8/P4wZMwYzZ87EkSNH8N133yEqKgrTpk0TB/E/9thjkMvliIiIwMmTJ7Fz505s2LAB0dHRZn8+Zg8qrKiowKJFi7Br1y7897//bXS8rq7O7CCIiIhaXCt3GRw7dgwjR44UXzd8SYeHhyMpKQkvvPACKioqMGvWLJSWlmLIkCFIS0uDi4uLeE5ycjKioqIwatQoyGQyTJkyBfHx8eJxpVKJr776CpGRkQgMDESXLl0QExNjsFaBqcxehyAyMhIHDhzAypUrMX36dCQkJODSpUt455138PrrryMsLMzsIJqL6xCQFHAdArJnrbkOwZXHR0Iht2Adgupa3PThgRaN1ZbM/mT27t2Lbdu2YcSIEZgxYwaGDh2KXr16oXv37khOTm7VhICIiMhkfLiRUWaPISgpKcEtt9wCoH7qRUlJCQBgyJAhyMjIsG50REREViLIBIs3e2Z2QnDLLbfg/PnzAIA+ffpg165dAOorBx4eHlYNjoiIiFqH2QnBjBkz8OOPPwKoXy85ISEBLi4uWLBgARYuXGj1AImIiKzCkmWLLe1uaAfMHkOwYMEC8b9DQkJw6tQpZGdno1evXujXr59VgyMiIrIaGSycZWC1SNqk5g+3/EP37t3RvXt3a8RCRETUYqy1dLG9Mikh+POcx78zd+7cZgdDREREtmFSQrBu3TqTLiYIgk0SgnUn0qFw79jq70vUGvSlRX/fiKid0l8rb703a0PPMmiLTEoIGmYVEBERtVtch8AoOx8iQURERKaweFAhERFRu8AKgVFMCIiISCIsXUvAvhMCdhkQERERKwRERCQRMln9Zsn5dqxZd3fo0CE8/vjjCA4OxqVLlwAA//rXv/Dtt99aNTgiIiKr4dLFRpmdEHzyyScIDQ2Fq6srfvjhB1RVVQEAysrK8Nprr1k9QCIiImp5ZicEr776KhITE7FlyxY4OTmJ+++9914cP37cqsERERFZDSsERpk9hiAvLw/Dhg1rtF+pVKK0tNQaMREREVkfpx0aZXaFQKVS4cyZM432f/vtt7jlllusEhQREZHVNQwqtGSzY2bf3cyZMzFv3jxkZWVBEAQUFhYiOTkZzz//PGbPnt0SMRIREVELM7vLYPHixdDpdBg1ahSuX7+OYcOGwdnZGc8//zzmzJnTEjESERFZjl0GRpmdEAiCgJdeegkLFy7EmTNnUF5eDn9/f3TsyKcNEhFRG8aEwKhmL0wkl8vh7+9vzViIiIjIRsxOCEaOHAnBSJa0f/9+iwIiIiJqEawQGGV2QtC/f3+D1zU1NcjJycHPP/+M8PBwa8VFRERkXVy62CizE4J169Y1uX/ZsmUoLy+3OCAiIiJqfVZLdx5//HG8//771rocERGRdXGlQqOs9rTDzMxMuLi4WOtyRERE1iXAwjEEVoukTTI7IZg8ebLBa71ej8uXL+PYsWNYunSp1QIjIiKi1mN2QqBUKg1ey2Qy9O7dGytWrMDo0aOtFhgREZFVcZaBUWYlBHV1dZgxYwb69u2LTp06tVRMREREVifIZBAsmClgybntgVl35+DggNGjR/OphkRE1A5ZOqDQvApBXV0dli5dip49e8LV1RW33norVq5cCb1eL7bR6/WIiYlB165d4erqipCQEJw+fdrgOiUlJQgLC4NCoYCHhwciIiJaZFaf2enOnXfeiXPnzlk9ECIiInuyevVqbNq0CW+99RZyc3OxevVqxMXFYePGjWKbuLg4xMfHIzExEVlZWXBzc0NoaCgqKyvFNmFhYTh58iTS09ORmpqKjIwMzJo1y+rxmp0QvPrqq3j++eeRmpqKy5cvQ6vVGmxERERtUitPOzx8+DAmTpyI8ePHo0ePHnjooYcwevRoHDlyBEB9dWD9+vV4+eWXMXHiRPTr1w/btm1DYWEhUlJSAAC5ublIS0vDu+++i6CgIAwZMgQbN27Ejh07UFhYaNWPx+SEYMWKFaioqMC4cePw448/4oEHHkC3bt3QqVMndOrUCR4eHhxXQEREbZeVEoK//hCuqqpq8u3uuece7Nu3D7/++isA4Mcff8S3336LsWPHAgDOnz8PjUaDkJAQ8RylUomgoCBkZmYCqJ/S7+HhgYEDB4ptQkJCIJPJkJWVZdWPx+RBhcuXL8czzzyDAwcOWDUAIiKi9sTHx8fg9SuvvIJly5Y1ard48WJotVr06dMHDg4OqKurw6pVqxAWFgYA0Gg0AABvb2+D87y9vcVjGo0GXl5eBscdHR3h6ekptrEWkxOChkEQw4cPt2oARERErcJKzzIoKCiAQqEQdzs7OzfZfNeuXUhOTsb27dtxxx13ICcnB/Pnz4darW6Tz/4xa9qhsaccEhERtWlWWodAoVAYJAQ3snDhQixevBjTpk0DAPTt2xcXLlxAbGwswsPDoVKpAABFRUXo2rWreF5RUZH4IEGVSoXi4mKD69bW1qKkpEQ831rMSpVuv/12eHp6Gt2IiIgIuH79OmR/qUg4ODhAp9MBAHr27AmVSoV9+/aJx7VaLbKyshAcHAwACA4ORmlpKbKzs8U2+/fvh06nQ1BQkFXjNatCsHz58kYrFRIREbULrbxS4YQJE7Bq1Sr4+vrijjvuwA8//IC1a9fiqaee+uNyAubPn49XX30Vt912G3r27ImlS5dCrVZj0qRJAAA/Pz+MGTMGM2fORGJiImpqahAVFYVp06ZBrVY3/16aYFZCMG3atEaDG4iIiNqFVk4INm7ciKVLl+LZZ59FcXEx1Go1/vnPfyImJkZs88ILL6CiogKzZs1CaWkphgwZgrS0NIOHBSYnJyMqKgqjRo2CTCbDlClTEB8f3/z7uAFB/+clk4xwcHDA5cuX21RCoNVqoVQqUXriMBTuHW0dDlHLcGp6wBKRPdBeK4dHn0CUlZWZ1C/frPf447ui5JUZULjIm3+dymp4Lt/aorHaktmzDIiIiNolK80ysFcmJwQNgyCIiIjaJT7t0CizH39MRETULjEhMMq+6x9ERERkElYIiIhIGjiGwCgmBEREJA0CLOwysFokbZJ9pztERERkElYIiIhIGjio0CgmBEREJA1MCIxilwERERGxQkBERBIhWDjLQLDv39BMCIiISBrYZWCUfac7REREZBJWCIiISBpYITCKCQEREUmDILNsHADHEBAREdkBmVC/WXK+HbPvdIeIiIhMwgoBERFJA7sMjGJCQERE0sBBhUbZd7pDREREJmGFgIiIpEFm4UqFlpzbDjAhICIiaWCXgVH2ne4QERGRSVghICIiaeAsA6OYEBARkTQIsLDLwGqRtEn2ne4QERGRSVghICIiaeAsA6OYEBARkTRwloFRTAiIiEgaOKjQKPu+OyIiIjIJKwRERCQNgoWPP2aXARERkR1gl4FR9n13RERENnTp0iU8/vjj6Ny5M1xdXdG3b18cO3ZMPK7X6xETE4OuXbvC1dUVISEhOH36tME1SkpKEBYWBoVCAQ8PD0RERKC8vNzqsTIhICIiaWiYZWDJZoarV6/i3nvvhZOTE7744gv88ssvePPNN9GpUyexTVxcHOLj45GYmIisrCy4ubkhNDQUlZWVYpuwsDCcPHkS6enpSE1NRUZGBmbNmmW1j6UBuwyIiEgarNRloNVqDXY7OzvD2dm5UfPVq1fDx8cHW7duFff17NlT/G+9Xo/169fj5ZdfxsSJEwEA27Ztg7e3N1JSUjBt2jTk5uYiLS0NR48excCBAwEAGzduxLhx4/DGG29ArVY3/37+ghUCIiIiM/j4+ECpVIpbbGxsk+327NmDgQMH4uGHH4aXlxcGDBiALVu2iMfPnz8PjUaDkJAQcZ9SqURQUBAyMzMBAJmZmfDw8BCTAQAICQmBTCZDVlaWVe+LFQIiIpIGmYWzDP44t6CgAAqFQtzdVHUAAM6dO4dNmzYhOjoaL774Io4ePYq5c+dCLpcjPDwcGo0GAODt7W1wnre3t3hMo9HAy8vL4LijoyM8PT3FNtbChICIiKTBSisVKhQKg4TgRnQ6HQYOHIjXXnsNADBgwAD8/PPPSExMRHh4ePPjaCHsMiAiImoBXbt2hb+/v8E+Pz8/5OfnAwBUKhUAoKioyKBNUVGReEylUqG4uNjgeG1tLUpKSsQ21sKEgIiIpKFhUKElmxnuvfde5OXlGez79ddf0b17dwD1AwxVKhX27dsnHtdqtcjKykJwcDAAIDg4GKWlpcjOzhbb7N+/HzqdDkFBQc39JJrELgMiIpIGK40hMNWCBQtwzz334LXXXsPUqVNx5MgRbN68GZs3bwYACIKA+fPn49VXX8Vtt92Gnj17YunSpVCr1Zg0aRKA+orCmDFjMHPmTCQmJqKmpgZRUVGYNm2aVWcYAEwIiIhIKgTBwmmH5iUEgwYNwu7du7FkyRKsWLECPXv2xPr16xEWFia2eeGFF1BRUYFZs2ahtLQUQ4YMQVpaGlxcXMQ2ycnJiIqKwqhRoyCTyTBlyhTEx8c3/z5uQNDr9XqrX7WVaLVaKJVKlJ44DIV7R1uHQ9QynJoewUxkD7TXyuHRJxBlZWUmDdRr1nv88V1R8uFqKDq4Nv861/8Hz8cXtWistsQKARERSYOVZhnYKyYEREQkDXy4kVH2fXdERERkElYIiIhIGlp5lkF7w4SAiIikgV0GRtn33REREZFJWCEgIiJp4CwDo5gQEBGRNMhk9Zsl59sx+747IiIiMgkrBBKXlrANOV8ehObsBTi5OOPWu/pi0uLZUN1a//CN/xZcxstDH2ry3KcTViJw/D/E15kffY597+1E0bkCuLh3wF3j/oFHVz7XKvdBdCNpG7ci54sD0Jz5rf5vfGA/THpxDlS9eohtkl9YhVPfHkFZ0e9w7uCKWwb2w4MvzRXbXDz5K75MSMLZIz+i/GopOnfriqHTp+AfTz9qm5uiZrKwywDsMiA7djorB8OnT0b3AD/oauvw2Zp3sPGJBYhJT4ZzB1d0Unvh9SN7DM759t+fIX3zdtwxYrC47+t3d+DrLf/G5Bcj0bO/P6quV+K/Fy+39u0QNXL6++MYHv4wuvf3r/8bfz0BGx+LQsw3H8H5j2Vsffv54e7JY+F5swoVpVqkvvkO4h+NxKvf74HMwQH5J3Lh3sUTT25cgU5qb5w79hOSX1gFmYMMI2Y8YuM7JJNxloFRNn2WQUZGBtasWYPs7GxcvnwZu3fvFp/wZAo+y8D6rv33Kl4IvB/ROxNwW1D/JtusGvckfO/sjelxSwAAFWVaLAmahGffi0Ofewe2YrQSwWcZWNW1/17FC/3uQ/Qnm3Hb4LuabHPxl9NYdd+jWPFdCm7q0a3JNv9+cTU0p89jwUeJLRmu3WvVZxl8+jYUbhY8y6Dif/Cc/KzdPsvApulORUUFAgICkJCQYMsw6E/+d60CANDBo+k/9gsnTuHiL6dxzyP3i/tOHToKvU6PUs0VLB/1GJYMnoQtkUtRUljUKjETmeN/2nIAN/4br7r+P2Tu3IPOvjejk9r7htepvFYOtxtcg6g9smmXwdixYzF27FiT21dVVaGqqkp8rdVqWyIsydLpdPhoxQbcOrAfbu59S5NtDu9MhapXD9wa2Ffc93t+IfR6HdIStmHqK/Ph4u6GPW9uQfzj8/Fy2jY4yp1a6xaIjNLpdPjolTdx66AA3Nynl8Gxg0kfYfeqeFRd/x+8b+2Oef9OuOHf7tmjP+LYnq8QuW1Da4RN1sJZBka1q7uLjY2FUqkUNx8fH1uHZFd2LH0ThXnnELFxeZPHqyurcPSzdNz7p+oAAOj0OtTV1GLqsvnwHx6EW+66ExHxy1D820X8mnm8FSInMs2OF1ejMO8sIt5+rdGxuyePxYtfJiP6k83wusUXW55ZjJrKqkbtLp06g8SnnsP4BTPhP3xwo+PUhjWsQ2DJZsfaVUKwZMkSlJWViVtBQYGtQ7IbO2LexM/7D2PBjo3o1NWryTY//OcAqisrETR5jMF+5U1dAABdb+sp7nPv3AkdPZXsNqA2Y8dLq/Hz199iwUeJTXYFuCo6wusWX9w2+C7M2hyHojO/ISftgEGby7+ew4ZHnsWQsAcxbv7TrRU6UatoV7MMnJ2d4ezMAVbWpNfrsfOVtcj5MgPRO95CFx/1Ddt+tzMV/UKGwL1zJ4P9tw6s7z4oOpcvJhMVpVqUl5TB8+Yb98EStQa9Xo+dL8chJ+0bRH/0Drr43mzSOXq9HrVVNeK+wryzWD91NgY/PB4TF0e2ZMjUUgTBwlkG9l0haFcJAVnfjqVv4uhn6Xhmy+twduuAsuL/Aqj/tSR3+f/kq/i3izhzJAeRW99odA3vW3wRcN9Q7Fq+HmGxi+DS0Q2fxSVCdasvegcHttq9EDVlx4urcTQlDc+8/yacO3ZAWfHvAABX946Qu7rgyoWLyN6TDr/hg+HeuROuFhbhy4QkyF1ccMeoewHUdxOsnzob/sMHY9SsMPEaMgeHRgkytWFcutgoJgQSl/HhbgDAumlRBvufWPMigh8eL74+vCsVHl294Dfs7iavE752KT5eGY+EGQshkwm4Lag/oj5YCwcn/omRbWVs+xgAsO6hfxrsf2LtKwh+ZAKcnJ1x5sgP2P/uv3G9TAtFl87oNXgAnv/sPSi6eAIAfvh8H8r/exVHPv0CRz79QryGZ7euWJW1t/VuhqgF2XQdgvLycpw5cwYAMGDAAKxduxYjR46Ep6cnfH19//Z8rkNAksB1CMiOteo6BKnvQeHWofnXqbgOz/sj7HYdApv+fDt27BhGjhwpvo6OjgYAhIeHIykpyUZRERGRXZIJ9Zsl59sxmyYEI0aMgA0LFERERPQHdvASEZE08FkGRjEhICIiaeAsA6OYEBARkTSwQmCUfd8dERERmYQVAiIikgRBECBYUPa35Nz2gAkBERFJA7sMjLLvuyMiIiKTsEJARETSwAqBUUwIiIhIGgQLVyq08zEE9p3uEBERtQGvv/46BEHA/PnzxX2VlZWIjIxE586d0bFjR0yZMgVFRUUG5+Xn52P8+PHo0KEDvLy8sHDhQtTW1rZIjEwIiIhIGhq6DCzZmuHo0aN455130K9fP4P9CxYswN69e/HRRx/h4MGDKCwsxOTJk8XjdXV1GD9+PKqrq3H48GF88MEHSEpKQkxMjEUfw40wISAiImloWKnQks1M5eXlCAsLw5YtW9CpUydxf1lZGd577z2sXbsW//jHPxAYGIitW7fi8OHD+P777wEAX331FX755Rd8+OGH6N+/P8aOHYuVK1ciISEB1dXVVvtYGjAhICIiMoNWqzXYqqqqbtg2MjIS48ePR0hIiMH+7Oxs1NTUGOzv06cPfH19kZmZCQDIzMxE37594e3tLbYJDQ2FVqvFyZMnrXxXTAiIiEgqBMHCLoP6CoGPjw+USqW4xcbGNvl2O3bswPHjx5s8rtFoIJfL4eHhYbDf29sbGo1GbPPnZKDheMMxa+MsAyIikgYrPdyooKAACoVC3O3s7NyoaUFBAebNm4f09HS4uLg0/z1bESsEREQkDVYaVKhQKAy2phKC7OxsFBcX46677oKjoyMcHR1x8OBBxMfHw9HREd7e3qiurkZpaanBeUVFRVCpVAAAlUrVaNZBw+uGNtbEhICIiMjKRo0ahRMnTiAnJ0fcBg4ciLCwMPG/nZycsG/fPvGcvLw85OfnIzg4GAAQHByMEydOoLi4WGyTnp4OhUIBf39/q8fMLgMiIpIGmYULE5lxrru7O+68806DfW5ubujcubO4PyIiAtHR0fD09IRCocCcOXMQHByMwYMHAwBGjx4Nf39/TJ8+HXFxcdBoNHj55ZcRGRnZZFXCUkwIiIhIGtrY0sXr1q2DTCbDlClTUFVVhdDQULz99tvicQcHB6SmpmL27NkIDg6Gm5sbwsPDsWLFCqvG0UDQ6/X6FrlyK9BqtVAqlSg9cRgK9462DoeoZThZ/5cAUVuhvVYOjz6BKCsrMxioZ9X3+OO74up3e6Ho6Nb865RXoNO9E1o0VltihYCIiKTBSrMM7BUTAiIikoY21mXQ1tj33REREZFJWCEgIiJpYJeBUUwIiIhIGthlYJR93x0RERGZhBUCIiKSBpmsfrPkfDvGhICIiCRBEAQIFowDsOTc9oAJARERSUPD448tOd+O2Xf9g4iIiEzCCgEREUkDpx0axYSAiIgkwsJph3ZeVLfvuyMiIiKTsEJARETSwC4Do5gQEBGRNHAdAqPs++6IiIjIJKwQEBGRNLDLwCgmBEREJA18uJFR9n13REREZBJWCIiISBrYZWAUEwIiIpII4Y/NkvPtFxMCIiKSBlYIjOIYAiIiImKFgIiIJIIVAqOYEBARkURwDIEx7DIgIiIiVgiIiEgi2GVgFBMCIiKSBvYYGMUuAyIiImKFgIiIpIIlAmOYEBARkTRwDIFR7DIgIiIiJgRERCQRAv6/StCszby3i42NxaBBg+Du7g4vLy9MmjQJeXl5Bm0qKysRGRmJzp07o2PHjpgyZQqKiooM2uTn52P8+PHo0KEDvLy8sHDhQtTW1lr4YTTGhICIiCRCsMJmuoMHDyIyMhLff/890tPTUVNTg9GjR6OiokJss2DBAuzduxcfffQRDh48iMLCQkyePFk8XldXh/Hjx6O6uhqHDx/GBx98gKSkJMTExDT7U7gRQa/X661+1Vai1WqhVCpReuIwFO4dbR0OUctwcrZ1BEQtRnutHB59AlFWVgaFQtEy79HwXXE6Bwp39+Zf59o1eNzWv9mxXrlyBV5eXjh48CCGDRuGsrIy3HTTTdi+fTseeughAMCpU6fg5+eHzMxMDB48GF988QXuv/9+FBYWwtvbGwCQmJiIRYsW4cqVK5DL5c2+n79ihYCIiMgMWq3WYKuqqjLpvLKyMgCAp6cnACA7Oxs1NTUICQkR2/Tp0we+vr7IzMwEAGRmZqJv375iMgAAoaGh0Gq1OHnypLVuCQATAiIikgzrdBn4+PhAqVSKW2xs7N++s06nw/z583HvvffizjvvBABoNBrI5XJ4eHgYtPX29oZGoxHb/DkZaDjecMyaOO2QiIikwUrTDgsKCgy6DJyd/75bLzIyEj///DO+/fbb5r9/C2OFgIiIyAwKhcJg+7uEICoqCqmpqThw4AC6desm7lepVKiurkZpaalB+6KiIqhUKrHNX2cdNLxuaGMtTAiIiEgaLJpyaH51Qa/XIyoqCrt378b+/fvRs2dPg+OBgYFwcnLCvn37xH15eXnIz89HcHAwACA4OBgnTpxAcXGx2CY9PR0KhQL+/v4WfBiNscuAiIgkonWXLo6MjMT27dvx2Wefwd3dXezzVyqVcHV1hVKpREREBKKjo+Hp6QmFQoE5c+YgODgYgwcPBgCMHj0a/v7+mD59OuLi4qDRaPDyyy8jMjLSpK4KczAhICIiagGbNm0CAIwYMcJg/9atW/Hkk08CANatWweZTIYpU6agqqoKoaGhePvtt8W2Dg4OSE1NxezZsxEcHAw3NzeEh4djxYoVVo+X6xAQtXVch4DsWGuuQ1B27qTF6xAob7mjRWO1JVYIiIhIGvhwI6M4qJCIiIhYISAiIqlo3UGF7Q0TAiIikggLuwyYEBAREdkBjiEwimMIiIiIiBUCIiKSCo4hMIYJARERSQO7DIxilwERERGxQkBERBLBHgOjmBAQEZFEMCMwhl0GRERExAoBERFJBAcVGsWEgIiIpIEJgVHsMiAiIiJWCIiISCo4qNAYJgRERCQNAizsMrBaJG0SEwIiIpIGjiEwimMIiIiIiBUCIiKSCo4hMIYJARERSQO7DIxq1wmBXq8HAGjLK2wcCVELcqqxdQRELUZbXg7g//89b9H3unbNpue3de06Ibj2x/85vsH32TgSIiKyxLVr16BUKlvk2nK5HCqVCj6332HxtVQqFeRyuRWiansEfWukZS1Ep9OhsLAQ7u7uEOy8lNNWaLVa+Pj4oKCgAAqFwtbhEFkV/75bn16vx7Vr16BWqyGTtdw498rKSlRXV1t8HblcDhcXFytE1Pa06wqBTCZDt27dbB2GJCkUCv6DSXaLf9+tq6UqA3/m4uJit1/k1sJph0RERMSEgIiIiJgQkJmcnZ3xyiuvwNnZ2dahEFkd/75Jytr1oEIiIiKyDlYIiIiIiAkBERERMSEgIiIiMCEgIiIiMCEgMyQkJKBHjx5wcXFBUFAQjhw5YuuQiKwiIyMDEyZMgFqthiAISElJsXVIRK2OCQGZZOfOnYiOjsYrr7yC48ePIyAgAKGhoSguLrZ1aEQWq6ioQEBAABISEmwdCpHNcNohmSQoKAiDBg3CW2+9BaD+ORI+Pj6YM2cOFi9ebOPoiKxHEATs3r0bkyZNsnUoRK2KFQL6W9XV1cjOzkZISIi4TyaTISQkBJmZmTaMjIiIrIUJAf2t33//HXV1dfD29jbY7+3tDY1GY6OoiIjImpgQEBERERMC+ntdunSBg4MDioqKDPYXFRVBpVLZKCoiIrImJgT0t+RyOQIDA7Fv3z5xn06nw759+xAcHGzDyIiIyFocbR0AtQ/R0dEIDw/HwIEDcffdd2P9+vWoqKjAjBkzbB0akcXKy8tx5swZ8fX58+eRk5MDT09P+Pr62jAyotbDaYdksrfeegtr1qyBRqNB//79ER8fj6CgIFuHRWSxb775BiNHjmy0Pzw8HElJSa0fEJENMCEgIiIijiEgIiIiJgREREQEJgREREQEJgREREQEJgREREQEJgREREQEJgREREQEJgREREQEJgREFnvyyScxadIk8fWIESMwf/78Vo/jm2++gSAIKC0tvWEbQRCQkpJi8jWXLVuG/v37WxTXb7/9BkEQkJOTY9F1iKhlMSEgu/Tkk09CEAQIggC5XI5evXphxYoVqK2tbfH3/vTTT7Fy5UqT2pryJU5E1Br4cCOyW2PGjMHWrVtRVVWF//znP4iMjISTkxOWLFnSqG11dTXkcrlV3tfT09Mq1yEiak2sEJDdcnZ2hkqlQvfu3TF79myEhIRgz549AP6/zL9q1Sqo1Wr07t0bAFBQUICpU6fCw8MDnp6emDhxIn777TfxmnV1dYiOjoaHhwc6d+6MF154AX99HMhfuwyqqqqwaNEi+Pj4wNnZGb169cJ7772H3377TXygTqdOnSAIAp588kkA9Y+Xjo2NRc+ePeHq6oqAgAB8/PHHBu/zn//8B7fffjtcXV0xcuRIgzhNtWjRItx+++3o0KEDbrnlFixduhQ1NTWN2r3zzjvw8fFBhw4dMHXqVJSVlRkcf/fdd+Hn5wcXFxf06dMHb7/9ttmxEJFtMSEgyXB1dUV1dbX4et++fcjLy0N6ejpSU1NRU1OD0NBQuLu749ChQ/juu+/QsWNHjBkzRjzvzTffRFJSEt5//318++23KCkpwe7du42+7xNPPIF///vfiI+PR25uLt555x107NgRPj4++OSTTwAAeXl5uHz5MjZs2AAAiI2NxbZt25CYmIiTJ09iwYIFePzxx3Hw4EEA9YnL5MmTMWHCBOTk5ODpp5/G4sWLzf5M3N3dkZSUhF9++QUbNmzAli1bsG7dOoM2Z86cwa5du7B3716kpaXhhx9+wLPPPiseT05ORkxMDFatWoXc3Fy89tprWLp0KT744AOz4yEiG9IT2aHw8HD9xIkT9Xq9Xq/T6fTp6el6Z2dn/fPPPy8e9/b21ldVVYnn/Otf/9L37t1br9PpxH1VVVV6V1dX/ZdffqnX6/X6rl276uPi4sTjNTU1+m7duonvpdfr9cOHD9fPmzdPr9fr9Xl5eXoA+vT09CbjPHDggB6A/urVq+K+yspKfYcOHfSHDx82aBsREaF/9NFH9Xq9Xr9kyRK9v7+/wfFFixY1utZfAdDv3r37hsfXrFmjDwwMFF+/8soregcHB/3FixfFfV988YVeJpPpL1++rNfr9fpbb71Vv337doPrrFy5Uh8cHKzX6/X68+fP6wHof/jhhxu+LxHZHscQkN1KTU1Fx44dUVNTA51Oh8ceewzLli0Tj/ft29dg3MCPP/6IM2fOwN3d3eA6lZWVOHv2LMrKynD58mUEBQWJxxwdHTFw4MBG3QYNcnJy4ODggOHDh5sc95kzZ3D9+nXcd999Bvurq6sxYMAAAEBubq5BHAAQHBxs8ns02LlzJ+Lj43H27FmUl5ejtrYWCoXCoI2vry9uvvlmg/fR6XTIy8uDu7s7zp49i4iICMycOVNsU1tbC6VSaXY8RGQ7TAjIbo0cORKbNm2CXC6HWq2Go6Phn7ubm5vB6/LycgQGBiI5ObnRtW666aZmxeDq6mr2OeXl5QCAzz//3OCLGKgfF2EtmZmZCAsLw/LlyxEaGgqlUokdO3bgzTffNDvWLVu2NEpQHBwcrBYrEbU8JgRkt9zc3NCrVy+T2991113YuXMnvLy8Gv1KbtC1a1dkZWVh2LBhAOp/CWdnZ+Ouu+5qsn3fvn2h0+lw8OBBhISENDreUKGoq6sT9/n7+8PZ2Rn5+fk3rCz4+fmJAyQbfP/9939/k39y+PBhdO/eHS+99JK478KFC43a5efno7CwEGq1WnwfmUyG3r17w9vbG2q1GufOnUNYWJhZ709EbQsHFRL9ISwsDF26dMHEiRNx6NAhnD9/Ht988w3mzp2LixcvAgDmzZuH119/HSkpKTh16hSeffZZo2sI9OjRA+Hh4XjqqaeQkpIiXnPXrl0AgO7du0MQBKSmpuLKlSsoLy+Hu7s7nn/+eSxYsAAffPABzp49i+PHj2Pjxo3iQL1nnnkGp0+fxsKFC5GXl4ft27cjKSnJrPu97bbbkJ+fjx07duDs2bOIj49vcoCki4sLwsPD8eOPP+LQoUOYO3cupk6dCpVKBQBYvnw5YmNjER8fj19//RUnTpzA1q1bsXbtWrPiISLbYkJA9IcOHTogIyMDvr6+mDx5Mvz8/BAREYHKykqxYvDcc89h+vTpCA8PR3BwMNzd3fHggw8ave6mTZvw0EMP4dlnn0WfPn0wc+ZMVFRUAABuvvlmLF++HIsXL4a3tzeioqIAACtXrsTSpUsRGxsLPz8/jBkzBp9//jl69uwJoL5f/5NPPkFKSgoCAgKQmJiI1157zaz7feCBB7BgwQJERUWhf//+OHz4MJYuXdqoXa9evTB58mSMGzcOo0ePRr9+/QymFT799NN49913sXXrVvTt2xfDhw9HUlKSGCsRtQ+C/kajoYiIiEgyWCEgIiIiJgRERETEhICIiIjAhICIiIjAhICIiIjAhICIiIjAhICIiIjAhICIiIjAhICIiIjAhICIiIjAhICIiIgA/B/FXroYzv2AvAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print('Classification Report : \\n', classification_report(y_train, y_pred_train_best), '\\n')\n",
    "print('Confusion Matrix      : \\n', ConfusionMatrixDisplay.from_estimator(best_svm, X_train_features, y_train, cmap='Reds'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Untuk hasil output dari nilai `Classification Report` dapat disimpulkan bahwa bahwa model memiliki akurasi keseluruhan sebesar 91%, yang menunjukkan bahwa sebagian besar prediksi yang dilakukan oleh model adalah benar. Namun, perlu diperhatikan bahwa kinerja model lebih rendah dibandingkan dengan kelas non-default (0) dengan nilai F1score 58%. Ini menunjukkan bahwa model cenderung lebih baik dalam memprediksi kelas non-default (0) daripada kelas default (1)\n",
    "\n",
    "\n",
    "\n",
    "Dan Untuk hasil output `Matrix Accuray` dapat diismpulkan bahwa : \n",
    "\n",
    "- pada kolom yang bernilai angka 495 memiliki pengertian `True Positif` artinya jumlah data yang secara benar diprediksi sebagai positif oleh model\n",
    "- pada kolom yang bernilai 1858 artinya `True Negatif` artinya jumlah data yang secara benar diprediksi sebagai negatif oleh model\n",
    "- Pada kolom yang bernilai 5 artinya `False Posiitif` artinya jumlah data yang salah diprediksi sebagai positif oleh model\n",
    "- Pada kolom yang bernilai 13 adalah `False Negatif` artinya jumlah data yang salah diprediksi sebagai negatif oleh model\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Analisa Hasil Prediksi Train**\n",
    "\n",
    "Adapun tujuan dari analisis hasil prediksi train adalah untuk memahami kinerja model pada data pelatihan. Analisis ini membantu dalam evaluasi dan pemahaman tentang bagaimana model ini dapat mempelajari pola-pola dalam data pelatihan dan sejauh mana model dapat menggeneralisasi pada data yang telah dilihat sebelumnya"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Melakukan prediksi pada data uji\n",
    "y_pred_test = best_svm.predict(X_test_features)\n",
    "\n",
    "# Membuat confusion matrix\n",
    "conf_matrix = confusion_matrix(y_test, y_pred_test)\n",
    "\n",
    "# Visualisasi confusion matrix\n",
    "plt.figure(figsize=(8, 6))\n",
    "sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=['Not Default', 'Default'], yticklabels=['Not Default', 'Default'])\n",
    "plt.xlabel('Predicted Label')\n",
    "plt.ylabel('True Label')\n",
    "plt.title('Confusion Matrix')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pada proses ini jika ditinjau dari hasil diatas maka saya akan membandingkan hasil sebelum dan sesudah di tuning, berikut cara dalam melakukan prediksi pada data uji menggunakan model `SVM` untuk menampilkan hasil nilai sebelum tuning dan setelah tuning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification Report Sebelum Penyetelan (Tuning) Model:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.85      0.95      0.89       466\n",
      "           1       0.66      0.37      0.47       127\n",
      "\n",
      "    accuracy                           0.82       593\n",
      "   macro avg       0.75      0.66      0.68       593\n",
      "weighted avg       0.81      0.82      0.80       593\n",
      "\n",
      "\n",
      "Classification Report Setelah Penyetelan (Tuning) Model:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.85      0.95      0.90       466\n",
      "           1       0.66      0.39      0.49       127\n",
      "\n",
      "    accuracy                           0.83       593\n",
      "   macro avg       0.76      0.67      0.69       593\n",
      "weighted avg       0.81      0.83      0.81       593\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Melakukan prediksi pada data uji menggunakan model SVM sebelum tuning\n",
    "y_pred_test_before_tuning = svm_pipe.predict(X_test_features)\n",
    "\n",
    "# Melakukan prediksi pada data uji menggunakan model terbaik setelah tuning\n",
    "y_pred_test_after_tuning = best_svm.predict(X_test_features)\n",
    "\n",
    "# Laporan klasifikasi sebelum penyetelan (tuning) model\n",
    "print(\"Classification Report Sebelum Penyetelan (Tuning) Model:\")\n",
    "print(classification_report(y_test, y_pred_test_before_tuning))\n",
    "\n",
    "# Laporan klasifikasi setelah penyetelan (tuning) model\n",
    "print(\"\\nClassification Report Setelah Penyetelan (Tuning) Model:\")\n",
    "print(classification_report(y_test, y_pred_test_after_tuning))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dari hasil output diatas dapat ditarik kesimpulan bahwa: \n",
    "\n",
    "- Setelah penyetelan (tuning) model, terjadi sedikit perbaikan dalam kinerja model pada kelas 1, dengan peningkatan dalam precision, recall, dan F1-score.\n",
    "- Namun, kelas 1 masih memiliki kinerja yang lebih rendah dibandingkan dengan kelas 0, dengan presisi, recall, dan F1-score yang lebih rendah.\n",
    "- Perlu dilakukan penyesuaian lebih lanjut atau peningkatan model untuk meningkatkan kinerja pada kelas 1 agar lebih seimbang dengan kelas 0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 10. Model Saving\n",
    "\n",
    "Pada bagian `Model Saving` ini merupakan proses penyimpanan model dan file-file lain yang terkait dengan hasil proses pembuatan model, diaman hasil `Model Saving` ini akan digunakan pada proses `Model Inference`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Save the files\n",
    "with open('best_svm_model.pkl', 'wb') as file_1:\n",
    "  pickle.dump(best_svm, file_1)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 11. Model Inference\n",
    "\n",
    "Model yang sudah dilatih akan dicoba pada data yang bukan termasuk ke dalam train-set ataupun test-set. Data ini harus dalam format yang asli, bukan data yang sudah di-scaled. Gunakan model terbaik berdasarkan hasil `Model Evaluation`. Hasil ini ada pada `Notebook` yang berbeda"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 11. Conceptual Problems\n",
    "\n",
    "Pada bagian ini saya akan menjelaskan dan menganalisa informasi dari model yang telah dibuat\n",
    "\n",
    "\n",
    "1. **Parameter dalam regresi logistik(Coefisien pada logistic regression):**\n",
    "   yang dikenal sebagai koefisien, menggambarkan pengaruh relatif dari setiap fitur terhadap probabilitas klasifikasi yang dihasilkan. Koefisien positif menunjukkan bahwa peningkatan nilai fitur tersebut akan meningkatkan probabilitas klasifikasi yang diinginkan, sedangkan koefisien negatif menunjukkan hubungan sebaliknya. Dengan kata lain, koefisien pada regresi logistik memberikan informasi tentang sejauh mana setiap fitur berkontribusi terhadap hasil prediksi yang akurat\n",
    "\n",
    "2. **Parameter Kernel pada Support Vector Machine (SVM):**\n",
    "   salah satu parameter penting yang digunakan untuk menentukan jenis fungsi kernel yang akan digunakan dalam memetakan data ke dalam ruang dimensi yang lebih tinggi. Parameter ini memungkinkan SVM untuk mengatasi masalah klasifikasi yang tidak linier dengan menciptakan hiperplane pemisah yang lebih kompleks dalam dimensi yang lebih tinggi. Salah satu contoh kernel yang sering digunakan adalah kernel RBF (Radial Basis Function), yang efektif dalam memetakan data ke dalam ruang dimensi tak terhingga. Pemilihan parameter kernel yang sesuai sangat penting karena akan mempengaruhi kinerja SVM dalam memisahkan dan mengklasifikasikan data. Setiap fungsi kernel memiliki karakteristik dan kegunaan yang berbeda tergantung pada bentuk data dan masalah klasifikasi yang dihadap\n",
    "\n",
    "3. **Cara Memilih K yang Optimal pada K-Nearest Neighbors (KNN):**\n",
    "   Untuk memilih nilai K yang optimal pada algoritma KNN, saya menggunakan teknik validasi silang (cross-validation) dimana pada `Cross-Validation`untuk membagi data menjadi subset pelatihan dan subset validasi. Uji performa KNN dengan berbagai nilai K pada subset validasi dan pilih nilai K yang memberikan kinerja terbaik secara keseluruhan.\n",
    "\n",
    "4. **Metrics-Metrics pada Evaluasi Klasifikasi:**\n",
    "   - **Akurasi (Accuracy):** Mengukur sejauh mana model klasifikasi dapat memprediksi dengan benar. Akurasi dihitung dengan membagi jumlah prediksi yang benar dengan total jumlah prediksi. Namun, akurasi mungkin tidak dapat memberikan gambaran yang akurat jika terdapat ketidakseimbangan kelas dalam dataset\n",
    "   - **Presisi (Precision):** Mengukur sejauh mana prediksi positif yang dihasilkan oleh model adalah benar. Presisi dihitung dengan membagi jumlah prediksi positif yang benar dengan total jumlah prediksi positif.\n",
    "   - **Recall (Recall) atau Sensitivitas:** Mengukur sejauh mana model dapat menemukan dan mengklasifikasikan dengan benar semua instance positif. Recall dihitung dengan membagi jumlah prediksi positif yang benar dengan total jumlah instance positif yang sebenarnya.\n",
    "   - **F1-Score:** F1-score adalah ukuran gabungan dari presisi dan recall. Ini memberikan keseimbangan antara presisi dan recall. F1-score dihitung dengan menggunakan rata-rata harmonis antara presisi dan recall.\n",
    "   \n",
    "    Kapan menggunakan:\n",
    "   - **Accuracy**: Digunakan ketika distribusi kelas dalam dataset seimbang dan kita ingin mengetahui kinerja keseluruhan model.\n",
    "   - **Precision dan Recall**: Digunakan ketika ada ketidakseimbangan dalam distribusi kelas dan penting untuk memperhitungkan false positives (precision) atau false negatives (recall).\n",
    "   - **F1 Score**: Digunakan ketika Anda menginginkan perpaduan yang baik antara presisi dan recall dan Anda tidak ingin terlalu fokus pada salah satu dari keduanya secara berlebihan.\n",
    "   \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 12. Overall Analysis\n",
    "\n",
    "Dengan mengacu pada perbandingan laporan klasifikasi sebelum dan setelah penyetelan (tuning) model, serta evaluasi kinerja model sebelumnya, saya dapat menyusun analisis keseluruhan mengenai model yang digunakan untuk klasifikasi data ini:\n",
    "\n",
    "1. **Kinerja Model Sebelum Penyetelan**:\n",
    "   - Sebelum penyetelan model, kinerja model SVM cukup baik dengan F1-score rata-rata sebesar 0.89 pada proses cross-validation.\n",
    "   - Meskipun memiliki akurasi yang lumayan baik, model cenderung lebih baik dalam memprediksi kelas non-default (0) daripada kelas default (1). Hal ini terlihat dari perbedaan yang signifikan dalam recall,precission, F1-score dan support antara kedua kelas.\n",
    "   - Kinerja model pada kelas default (1) cenderung lebih rendah, yang mungkin mengindikasikan adanya kesulitan dalam mengidentifikasi instance (data yang akan diklasifikasikan oleh model) yang sebenarnya termasuk dalam kelas default\n",
    "\n",
    "2. **Penyetelan (Tuning) Model**:\n",
    "   - Setelah penyetelan (tuning) model, kinerja model mengalami penaikan angka namun tidak siginifikan perubahannya, terutama dalam model recall dan F1-score terutama jika dilihat dari kelas default (1).\n",
    "   - Penaikan kinerja ini bisa disebabkan oleh berbagai faktor, bisa disebabkan oleh pengaruh dari proses tuning yang tidak diharapkan namun hal yang paling utama adalah pemilihan paarmeter pada `c` dan `gamma` pada model `grid`\n",
    "\n",
    "3. **Kesimpulan dan Rekomendasi**:\n",
    "   - Evaluasi dan penyesuaian parameter: Perhatikan pemilihan parameter yang digunakan dalam model SVM. Parameter C dan gamma pada model grid dapat memiliki pengaruh signifikan terhadap kinerja model. Lakukan evaluasi lebih lanjut terhadap parameter tersebut dengan mengubah nilai-nilai yang berbeda untuk mencari kombinasi parameter yang optimal.\n",
    "\n",
    "   - Data preprocessing: Coba eksplorasi penggunaan teknik preprocessing data untuk meningkatkan kinerja model. Misalnya, lakukan normalisasi atau penskalaan pada fitur-fitur data, atau terapkan teknik seleksi fitur untuk mengurangi dimensi data dan meningkatkan relevansi fitur terhadap klasifikasi.\n",
    "\n",
    "   - Penggunaan metode klasifikasi lain: Selain SVM, perlu dipertimbangkan penggunaan metode klasifikasi lain yang mungkin lebih cocok untuk kasus ini. Cobalah metode klasifikasi seperti Decision Tree, Random Forest, Naive Bayes, atau Neural Networks untuk melihat apakah terdapat peningkatan kinerja pada kelas default (1).\n",
    "\n",
    "   - Penanganan ketidakseimbangan kelas: Jika perbedaan kinerja antara kelas non-default (0) dan default (1) masih signifikan, pertimbangkan strategi penanganan ketidakseimbangan kelas. Misalnya, Anda dapat menggunakan teknik oversampling atau undersampling untuk mengatasi ketidakseimbangan tersebut dan meningkatkan kemampuan model dalam mengklasifikasikan kelas default dengan lebih baik.\n",
    "\n",
    "   - Cross-validation yang lebih komprehensif: Selain F1-score rata-rata, perlu juga memperhatikan hasil evaluasi lainnya seperti precision, recall, dan support untuk masing-masing kelas. Lakukan cross-validation yang lebih komprehensif dengan memeriksa variasi kinerja model pada setiap lipatan data (fold) untuk mendapatkan pemahaman yang lebih baik tentang kinerja model secara keseluruhan.\n",
    "\n",
    "   - Analisis lebih lanjut: Lakukan analisis lebih lanjut terhadap data yang digunakan, termasuk pemahaman yang lebih mendalam tentang karakteristik kelas default (1) dan faktor-faktor yang mempengaruhi prediksi yang salah. Ini dapat membantu dalam mengidentifikasi fitur-fitur penting, kekurangan data, atau pola-pola yang perlu diperhatikan dalam pemodelan.\n",
    "\n",
    "Dengan menganalisis kinerja model secara menyeluruh sebelum dan setelah penyetelan, serta dengan mempertimbangkan rekomendasi-rekomendasi yang telah disebutkan, diharapkan dapat membantu dalam memperbaiki kinerja model klasifikasi untuk kasus ini.\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}