{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# xi. Model Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#load model scaler dan model knn yang sudah disimpen dalam bentuk pkl\n",
    "with open('scaler.pkl', 'rb') as file_1:\n",
    "  scaler = pickle.load(file_1)\n",
    "\n",
    "with open('model_knn.pkl', 'rb') as file_2:\n",
    "  model_knn = pickle.load(file_2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Membuat data dummy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Atur seed di sini\n",
    "seed_value = 777\n",
    "random.seed(seed_value)\n",
    "np.random.seed(seed_value)\n",
    "\n",
    "# Jumlah data point yang ingin dibuat\n",
    "n = 100\n",
    "\n",
    "# Membuat data untuk kolom 'distance'\n",
    "limit_balance = np.round(np.random.uniform(10000, 800000, n), 2)\n",
    "\n",
    "# Membuat data untuk kolom 'surge_multiplier'\n",
    "pay_1 = [-2.0,-1.0,0.0,1.0,2.0,3.0,4.0,5.0,6.0,7.0,8.0]\n",
    "pay_1 = random.choices(pay_1, k=n)\n",
    "\n",
    "pay_2 = [-2.0,-1.0,0.0,1.0,2.0,3.0,4.0,5.0,6.0,7.0]\n",
    "pay_2 = random.choices(pay_2, k=n)\n",
    "\n",
    "pay_3 = [-2.0,-1.0,0.0,2.0,3.0,4.0,5.0,6.0,7.0]\n",
    "pay_3 = random.choices(pay_3, k=n)\n",
    "\n",
    "pay_4 = [-2.0,-1.0,0.0,2.0,3.0,4.0,5.0,6.0,7.0,8.0]\n",
    "pay_4 = random.choices(pay_4, k=n)\n",
    "\n",
    "pay_5 = [-2.0,-1.0,0.0,2.0,3.0,4.0,5.0,6.0,7.0]\n",
    "pay_5 = random.choices(pay_5, k=n)\n",
    "\n",
    "pay_6 = [-2.0,-1.0,0.0,2.0,3.0,4.0,6.0,7.0]\n",
    "pay_6 = random.choices(pay_6, k=n)\n",
    "\n",
    "# Membuat DataFrame\n",
    "df_inf = pd.DataFrame({\n",
    "    'limit_balance': limit_balance,\n",
    "    'pay_1': pay_1,\n",
    "    'pay_2': pay_2,\n",
    "    'pay_3': pay_3,\n",
    "    'pay_4': pay_4,\n",
    "    'pay_5': pay_5,\n",
    "    'pay_6': pay_6,\n",
    "    \n",
    "})"
   ]
  },
  {
   "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>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>0</th>\n",
       "      <td>130604.35</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>248861.72</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>59008.77</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>373289.67</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>669850.17</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>7.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>772548.37</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>780417.84</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>-2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>169988.27</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>547083.91</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>377622.60</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    limit_balance  pay_1  pay_2  pay_3  pay_4  pay_5  pay_6\n",
       "0       130604.35    0.0    7.0    5.0    5.0    2.0    6.0\n",
       "1       248861.72    2.0   -2.0    3.0    0.0   -2.0    6.0\n",
       "2        59008.77    2.0   -2.0    3.0    5.0    2.0    7.0\n",
       "3       373289.67    0.0    7.0    2.0    2.0   -2.0    0.0\n",
       "4       669850.17    1.0    4.0   -1.0    0.0    7.0    7.0\n",
       "..            ...    ...    ...    ...    ...    ...    ...\n",
       "95      772548.37    2.0   -2.0    0.0    0.0    6.0    3.0\n",
       "96      780417.84    7.0    6.0    7.0    5.0    3.0   -2.0\n",
       "97      169988.27    4.0    2.0    3.0   -2.0   -1.0    4.0\n",
       "98      547083.91    4.0    1.0    4.0   -1.0    5.0    2.0\n",
       "99      377622.60   -2.0    5.0    3.0    7.0    3.0    7.0\n",
       "\n",
       "[100 rows x 7 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_inf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    pay_1  pay_2  pay_3  pay_4  pay_5  pay_6\n",
      "0     0.0    7.0    5.0    5.0    2.0    6.0\n",
      "1     2.0   -2.0    3.0    0.0   -2.0    6.0\n",
      "2     2.0   -2.0    3.0    5.0    2.0    7.0\n",
      "3     0.0    7.0    2.0    2.0   -2.0    0.0\n",
      "4     1.0    4.0   -1.0    0.0    7.0    7.0\n",
      "..    ...    ...    ...    ...    ...    ...\n",
      "95    2.0   -2.0    0.0    0.0    6.0    3.0\n",
      "96    7.0    6.0    7.0    5.0    3.0   -2.0\n",
      "97    4.0    2.0    3.0   -2.0   -1.0    4.0\n",
      "98    4.0    1.0    4.0   -1.0    5.0    2.0\n",
      "99   -2.0    5.0    3.0    7.0    3.0    7.0\n",
      "\n",
      "[100 rows x 6 columns]\n",
      "    limit_balance\n",
      "0       130604.35\n",
      "1       248861.72\n",
      "2        59008.77\n",
      "3       373289.67\n",
      "4       669850.17\n",
      "..            ...\n",
      "95      772548.37\n",
      "96      780417.84\n",
      "97      169988.27\n",
      "98      547083.91\n",
      "99      377622.60\n",
      "\n",
      "[100 rows x 1 columns]\n"
     ]
    }
   ],
   "source": [
    "#membagi 2 kolom numerical dan kategorical\n",
    "df_inf_num = df_inf[['limit_balance']]\n",
    "df_inf_cat= df_inf[['pay_1', 'pay_2', 'pay_3', 'pay_4','pay_5','pay_6']]\n",
    "\n",
    "print(df_inf_cat)\n",
    "print(df_inf_num)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Scaling"
   ]
  },
  {
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.241209</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.477723</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.098018</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.726579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.319700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>1.525097</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>1.540836</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>0.319977</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>1.074168</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>0.735245</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           0\n",
       "0   0.241209\n",
       "1   0.477723\n",
       "2   0.098018\n",
       "3   0.726579\n",
       "4   1.319700\n",
       "..       ...\n",
       "95  1.525097\n",
       "96  1.540836\n",
       "97  0.319977\n",
       "98  1.074168\n",
       "99  0.735245\n",
       "\n",
       "[100 rows x 1 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_inf_num_scaled = scaler.transform(df_inf_num)\n",
    "df_inf_num_scaled=pd.DataFrame(df_inf_num_scaled)\n",
    "df_inf_num_scaled\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Menggabungkan 2 kolom numerikal yang sudah di scaling dan kolom kategorical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.2412087 ,  0.        ,  7.        ,  5.        ,  5.        ,\n",
       "         2.        ,  6.        ],\n",
       "       [ 0.47772344,  2.        , -2.        ,  3.        ,  0.        ,\n",
       "        -2.        ,  6.        ],\n",
       "       [ 0.09801754,  2.        , -2.        ,  3.        ,  5.        ,\n",
       "         2.        ,  7.        ],\n",
       "       [ 0.72657934,  0.        ,  7.        ,  2.        ,  2.        ,\n",
       "        -2.        ,  0.        ],\n",
       "       [ 1.31970034,  1.        ,  4.        , -1.        ,  0.        ,\n",
       "         7.        ,  7.        ],\n",
       "       [ 1.46465534,  6.        ,  0.        ,  7.        ,  6.        ,\n",
       "         4.        ,  3.        ],\n",
       "       [ 1.1486426 ,  8.        , -1.        , -2.        ,  5.        ,\n",
       "         5.        ,  3.        ],\n",
       "       [ 1.21422404,  8.        ,  6.        ,  5.        ,  4.        ,\n",
       "         4.        ,  3.        ],\n",
       "       [ 0.425344  ,  4.        ,  4.        ,  5.        ,  2.        ,\n",
       "         0.        ,  3.        ],\n",
       "       [ 1.01756628,  2.        ,  2.        ,  3.        ,  2.        ,\n",
       "         2.        ,  7.        ],\n",
       "       [ 0.14752974,  1.        ,  3.        ,  7.        ,  5.        ,\n",
       "         2.        ,  3.        ],\n",
       "       [ 0.1259037 ,  8.        ,  3.        ,  0.        ,  3.        ,\n",
       "         3.        ,  0.        ],\n",
       "       [ 0.93158974,  8.        ,  5.        ,  5.        ,  8.        ,\n",
       "         4.        ,  2.        ],\n",
       "       [ 0.54247806,  5.        ,  1.        ,  4.        ,  3.        ,\n",
       "         7.        ,  6.        ],\n",
       "       [ 1.56242432,  7.        , -2.        ,  3.        ,  6.        ,\n",
       "         0.        , -2.        ],\n",
       "       [ 0.98982766, -1.        ,  7.        ,  4.        ,  0.        ,\n",
       "         5.        , -1.        ],\n",
       "       [ 1.07721126,  6.        , -1.        ,  5.        ,  4.        ,\n",
       "         4.        ,  6.        ],\n",
       "       [ 0.87256576,  8.        , -1.        ,  4.        ,  5.        ,\n",
       "        -2.        ,  2.        ],\n",
       "       [ 0.4247989 , -2.        ,  2.        ,  3.        ,  8.        ,\n",
       "         7.        , -1.        ],\n",
       "       [ 0.58974984,  5.        ,  1.        ,  0.        ,  5.        ,\n",
       "         6.        ,  3.        ],\n",
       "       [ 0.3522264 ,  1.        ,  0.        ,  4.        ,  5.        ,\n",
       "         3.        , -1.        ],\n",
       "       [ 0.2945793 ,  4.        ,  5.        ,  5.        , -2.        ,\n",
       "         7.        ,  3.        ],\n",
       "       [ 0.61722398, -1.        ,  6.        ,  5.        , -1.        ,\n",
       "        -1.        ,  3.        ],\n",
       "       [ 0.3051966 ,  5.        ,  4.        ,  5.        ,  0.        ,\n",
       "         3.        ,  2.        ],\n",
       "       [ 0.96523928,  0.        ,  2.        , -2.        ,  6.        ,\n",
       "         3.        ,  4.        ],\n",
       "       [ 1.39483734,  3.        , -2.        ,  4.        ,  2.        ,\n",
       "         4.        ,  4.        ],\n",
       "       [ 0.98329534,  6.        , -2.        ,  7.        ,  5.        ,\n",
       "         4.        ,  7.        ],\n",
       "       [ 0.39992794,  7.        ,  0.        , -2.        ,  7.        ,\n",
       "         5.        , -1.        ],\n",
       "       [ 0.28428988,  4.        ,  6.        ,  3.        , -2.        ,\n",
       "         6.        ,  7.        ],\n",
       "       [ 1.28991906, -2.        , -2.        ,  2.        ,  8.        ,\n",
       "         6.        ,  2.        ],\n",
       "       [ 0.35608716,  4.        ,  4.        ,  4.        ,  6.        ,\n",
       "        -1.        ,  6.        ],\n",
       "       [ 0.81663428,  4.        , -2.        ,  6.        , -1.        ,\n",
       "         0.        , -1.        ],\n",
       "       [ 0.8192234 , -2.        , -2.        ,  6.        ,  5.        ,\n",
       "         2.        ,  0.        ],\n",
       "       [ 0.9485924 ,  4.        ,  3.        ,  7.        ,  3.        ,\n",
       "        -2.        ,  7.        ],\n",
       "       [ 0.84154036,  1.        ,  4.        , -1.        , -1.        ,\n",
       "         0.        ,  4.        ],\n",
       "       [ 0.02102988,  6.        ,  7.        ,  4.        , -1.        ,\n",
       "         0.        ,  7.        ],\n",
       "       [ 0.82807368,  3.        ,  2.        , -1.        ,  6.        ,\n",
       "         2.        ,  3.        ],\n",
       "       [ 1.41549784,  4.        , -1.        ,  3.        ,  8.        ,\n",
       "         0.        , -1.        ],\n",
       "       [ 1.21644404, -1.        ,  2.        , -1.        ,  6.        ,\n",
       "         6.        , -2.        ],\n",
       "       [ 0.19410568,  2.        ,  6.        ,  5.        ,  4.        ,\n",
       "         3.        ,  3.        ],\n",
       "       [ 0.46747886,  0.        ,  3.        , -2.        ,  5.        ,\n",
       "         4.        ,  0.        ],\n",
       "       [ 0.96699726,  4.        ,  1.        ,  7.        ,  5.        ,\n",
       "         0.        , -2.        ],\n",
       "       [ 1.14729824, -2.        ,  0.        ,  4.        ,  6.        ,\n",
       "         2.        ,  2.        ],\n",
       "       [ 0.732326  , -1.        ,  6.        , -1.        ,  3.        ,\n",
       "         5.        ,  0.        ],\n",
       "       [ 1.21519438,  8.        ,  7.        ,  6.        ,  0.        ,\n",
       "         6.        ,  4.        ],\n",
       "       [ 0.30277702,  6.        ,  6.        ,  5.        ,  2.        ,\n",
       "         0.        ,  3.        ],\n",
       "       [ 0.88142942,  3.        ,  0.        , -1.        , -1.        ,\n",
       "         6.        ,  6.        ],\n",
       "       [ 0.87022948,  7.        ,  6.        , -1.        ,  8.        ,\n",
       "         2.        ,  6.        ],\n",
       "       [ 0.74611628,  8.        ,  1.        ,  4.        ,  5.        ,\n",
       "         7.        ,  7.        ],\n",
       "       [ 1.25117824,  1.        ,  4.        ,  2.        ,  6.        ,\n",
       "         0.        ,  3.        ],\n",
       "       [ 0.1820945 ,  8.        ,  0.        ,  3.        ,  6.        ,\n",
       "         5.        ,  4.        ],\n",
       "       [ 1.07646016,  8.        ,  6.        ,  3.        ,  2.        ,\n",
       "         5.        ,  0.        ],\n",
       "       [ 0.5724871 , -1.        ,  1.        ,  5.        ,  7.        ,\n",
       "         2.        ,  6.        ],\n",
       "       [ 0.54385006,  7.        ,  7.        ,  4.        ,  7.        ,\n",
       "         2.        ,  2.        ],\n",
       "       [ 0.71023962, -2.        ,  2.        ,  4.        , -1.        ,\n",
       "         2.        ,  6.        ],\n",
       "       [ 0.04256878,  8.        ,  0.        ,  7.        ,  7.        ,\n",
       "         0.        ,  2.        ],\n",
       "       [ 0.65609134,  4.        ,  0.        ,  7.        , -2.        ,\n",
       "         4.        ,  4.        ],\n",
       "       [ 1.4571261 ,  0.        , -2.        ,  4.        ,  2.        ,\n",
       "        -2.        ,  2.        ],\n",
       "       [ 0.1441048 ,  0.        ,  0.        ,  2.        ,  4.        ,\n",
       "         4.        , -2.        ],\n",
       "       [ 0.49789242, -2.        ,  3.        ,  6.        ,  6.        ,\n",
       "         7.        ,  0.        ],\n",
       "       [ 0.83427514,  5.        , -1.        , -2.        ,  0.        ,\n",
       "         7.        ,  0.        ],\n",
       "       [ 0.518338  ,  6.        ,  2.        ,  3.        ,  8.        ,\n",
       "         3.        ,  0.        ],\n",
       "       [ 0.70928656,  5.        ,  1.        ,  3.        , -1.        ,\n",
       "         6.        , -2.        ],\n",
       "       [ 0.02580838,  2.        ,  2.        ,  0.        , -1.        ,\n",
       "         7.        ,  3.        ],\n",
       "       [ 0.1533025 ,  5.        ,  1.        ,  7.        ,  5.        ,\n",
       "         7.        ,  6.        ],\n",
       "       [ 1.09428994,  3.        ,  5.        ,  4.        , -2.        ,\n",
       "        -1.        ,  4.        ],\n",
       "       [ 1.32079058,  2.        ,  0.        ,  3.        ,  2.        ,\n",
       "         5.        ,  2.        ],\n",
       "       [ 0.67042874,  2.        ,  2.        , -1.        ,  8.        ,\n",
       "        -1.        , -1.        ],\n",
       "       [ 1.3410634 ,  1.        ,  6.        ,  7.        ,  8.        ,\n",
       "         6.        , -1.        ],\n",
       "       [ 0.86393012,  5.        ,  5.        , -2.        ,  7.        ,\n",
       "         0.        ,  4.        ],\n",
       "       [ 0.55948346,  4.        ,  5.        ,  6.        ,  6.        ,\n",
       "        -2.        ,  6.        ],\n",
       "       [ 1.1490545 ,  1.        ,  2.        ,  5.        ,  4.        ,\n",
       "         6.        , -2.        ],\n",
       "       [ 0.14828566,  3.        , -2.        ,  5.        ,  0.        ,\n",
       "         0.        ,  4.        ],\n",
       "       [ 1.4107169 ,  3.        ,  4.        , -2.        ,  8.        ,\n",
       "         0.        ,  0.        ],\n",
       "       [ 0.53128808,  4.        ,  4.        ,  4.        , -2.        ,\n",
       "         7.        ,  4.        ],\n",
       "       [ 1.40909564, -2.        ,  0.        ,  7.        , -2.        ,\n",
       "         7.        ,  3.        ],\n",
       "       [ 0.46902142,  7.        ,  5.        ,  6.        ,  6.        ,\n",
       "         5.        ,  2.        ],\n",
       "       [ 0.4766043 ,  1.        ,  7.        ,  5.        ,  5.        ,\n",
       "         4.        ,  3.        ],\n",
       "       [ 1.27386016,  4.        ,  1.        ,  6.        , -2.        ,\n",
       "         7.        , -1.        ],\n",
       "       [ 1.32342374,  8.        ,  5.        ,  7.        , -2.        ,\n",
       "         6.        ,  2.        ],\n",
       "       [ 1.0021645 ,  5.        ,  1.        , -1.        ,  4.        ,\n",
       "         5.        ,  4.        ],\n",
       "       [ 0.49189714, -1.        , -1.        ,  3.        ,  3.        ,\n",
       "         2.        ,  7.        ],\n",
       "       [ 0.04652876,  1.        , -2.        ,  7.        ,  7.        ,\n",
       "         5.        ,  0.        ],\n",
       "       [ 0.63164816,  5.        ,  1.        , -2.        ,  3.        ,\n",
       "        -1.        , -2.        ],\n",
       "       [ 0.81871406,  5.        ,  6.        ,  7.        ,  2.        ,\n",
       "        -1.        ,  7.        ],\n",
       "       [ 0.01167376,  7.        ,  1.        , -2.        ,  4.        ,\n",
       "         0.        ,  4.        ],\n",
       "       [ 1.22441748,  8.        , -1.        , -2.        ,  8.        ,\n",
       "         0.        ,  6.        ],\n",
       "       [ 1.35006448, -2.        ,  2.        ,  5.        ,  3.        ,\n",
       "         7.        , -2.        ],\n",
       "       [ 0.20782186,  1.        ,  6.        ,  2.        ,  8.        ,\n",
       "         6.        ,  4.        ],\n",
       "       [ 0.45452436,  1.        ,  5.        ,  3.        ,  8.        ,\n",
       "         3.        , -1.        ],\n",
       "       [ 0.51601032,  5.        ,  7.        , -1.        ,  7.        ,\n",
       "         7.        , -1.        ],\n",
       "       [ 1.4323641 , -1.        ,  6.        , -2.        , -2.        ,\n",
       "         2.        ,  7.        ],\n",
       "       [ 1.57930408,  1.        , -1.        ,  5.        ,  6.        ,\n",
       "         2.        , -1.        ],\n",
       "       [ 1.21799718,  8.        ,  6.        ,  6.        ,  2.        ,\n",
       "         4.        ,  3.        ],\n",
       "       [ 0.06769908,  0.        ,  2.        ,  7.        ,  7.        ,\n",
       "         3.        ,  3.        ],\n",
       "       [ 1.52509674,  2.        , -2.        ,  0.        ,  0.        ,\n",
       "         6.        ,  3.        ],\n",
       "       [ 1.54083568,  7.        ,  6.        ,  7.        ,  5.        ,\n",
       "         3.        , -2.        ],\n",
       "       [ 0.31997654,  4.        ,  2.        ,  3.        , -2.        ,\n",
       "        -1.        ,  4.        ],\n",
       "       [ 1.07416782,  4.        ,  1.        ,  4.        , -1.        ,\n",
       "         5.        ,  2.        ],\n",
       "       [ 0.7352452 , -2.        ,  5.        ,  3.        ,  7.        ,\n",
       "         3.        ,  7.        ]])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_inf_final = np.concatenate([df_inf_num_scaled,df_inf_cat],axis = 1)\n",
    "df_inf_final"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1,\n",
       "       0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0,\n",
       "       1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1], dtype=int64)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#membuat kolom predict \n",
    "y_pred_inf = model_knn.predict(df_inf_final)\n",
    "y_pred_inf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Def_payment - Prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Def_payment - Prediction\n",
       "0                          0\n",
       "1                          1\n",
       "2                          0\n",
       "3                          1\n",
       "4                          1\n",
       "..                       ...\n",
       "95                         1\n",
       "96                         1\n",
       "97                         1\n",
       "98                         1\n",
       "99                         1\n",
       "\n",
       "[100 rows x 1 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#membuat kolom predict kedalam data frame dan memberi nama kolomnya dengan 'Def_payment - Prediction'\n",
    "y_pred_inf_df = pd.DataFrame(y_pred_inf, columns=['Def_payment - Prediction'])\n",
    "y_pred_inf_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>Def_payment - Prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>130604.35</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>248861.72</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>59008.77</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>373289.67</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>669850.17</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>772548.37</td>\n",
       "      <td>2.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>780417.84</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>169988.27</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>547083.91</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>377622.60</td>\n",
       "      <td>-2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    limit_balance  pay_1  pay_2  pay_3  pay_4  pay_5  pay_6  \\\n",
       "0       130604.35    0.0    7.0    5.0    5.0    2.0    6.0   \n",
       "1       248861.72    2.0   -2.0    3.0    0.0   -2.0    6.0   \n",
       "2        59008.77    2.0   -2.0    3.0    5.0    2.0    7.0   \n",
       "3       373289.67    0.0    7.0    2.0    2.0   -2.0    0.0   \n",
       "4       669850.17    1.0    4.0   -1.0    0.0    7.0    7.0   \n",
       "..            ...    ...    ...    ...    ...    ...    ...   \n",
       "95      772548.37    2.0   -2.0    0.0    0.0    6.0    3.0   \n",
       "96      780417.84    7.0    6.0    7.0    5.0    3.0   -2.0   \n",
       "97      169988.27    4.0    2.0    3.0   -2.0   -1.0    4.0   \n",
       "98      547083.91    4.0    1.0    4.0   -1.0    5.0    2.0   \n",
       "99      377622.60   -2.0    5.0    3.0    7.0    3.0    7.0   \n",
       "\n",
       "    Def_payment - Prediction  \n",
       "0                          0  \n",
       "1                          1  \n",
       "2                          0  \n",
       "3                          1  \n",
       "4                          1  \n",
       "..                       ...  \n",
       "95                         1  \n",
       "96                         1  \n",
       "97                         1  \n",
       "98                         1  \n",
       "99                         1  \n",
       "\n",
       "[100 rows x 8 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#membuat variabel baru dengan menggabungkan 2 tabel yaitu df_inf dan y _preditc inf\n",
    "tabel_inference = pd.concat([df_inf, y_pred_inf_df], axis=1)\n",
    "tabel_inference"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# xii. Kesimpulan "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- Saya memilih f1 score sebagai parameter score karena menurut saya untuk meminimalisir false postive dan false negative penting .\n",
    "\n",
    "- Dari hasil std yang mendekati 0 dan berada di bawah mean berarti model KNN yang default nilai STD 0.03 sehingga modelnya best fit . Jadi bisa dikatakan bahwa model knn default memiliki konsistensi yang bagus akan tetapi validasi hasil predictnya kurang bagus dikarenakan hanya sekitar 48%. Dari sisi bisnis model ini belum bisa digunakan karena hasil predictnya yang masih kurang bagus kurang dari 50% sehingga bisa menimbulkan hasil predict yang salah dimana bisa menyebabkan perusahaan rugi.\n",
    "\n",
    "- Untuk Meningkatkan jumlah user yang bisa bayar ada baiknya untuk penagihan bisa dilakukan ditanggal gajian sekitar 25-31 pada saat gajian karena pada saat tanggal tersebut uang mereka jumlahnya banyak jadi bisa membayar \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conceptual Problems :"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Apakah yang dimaksud dengan coeficient pada logistic regression?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Yang dimaksud dengan coeficient pada logistic regression adalah nilai bobot atau parameter yang digunakan untuk mengukur hubungan antara variabel independen (fitur) dengan variabel dependen (kelas atau target)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2. Apakah fungsi parameter kernel pada SVM? Jelaskan salah satu kernel yang kalian pahami!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Kernel adalah fungsi matematis yang digunakan untuk mengukur kesamaan antara pasangan data dalam ruang fitur\n",
    "Salah satu kernelnya adalah linear yang digunakan untuk pemisahan data yang dapat dipisahkan dengan garis lurus."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3. Bagaimana cara memilih K yang optimal pada KNN ?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Cara memilih K yang optimal pada KNN adalah dengan membagi data set menjadi 2 yaitu train dan test lalu mendefine model knn. Lalu diolah dengan menggunakan cross validation untuk menentukan parameter mana yang terbaik dan memvariasikan nilai K dan mengamati performa validasi silang, kita bisa menemukan K yang optimal"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "4. Apa yang dimaksud dengan metrics-metrics berikut : Accuracy, Precision, Recall, F1 Score, dan kapan waktu yang tepat untuk menggunakannya ?\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Accuracy: Merupakan rasio dari jumlah prediksi yang benar (positif dan negatif) dibandingkan dengan jumlah total sampel. Berguna ketika distribusi kelas seimbang. Namun, bisa menjadi bias jika kelas tidak seimbang.\n",
    "\n",
    "Precision: Merupakan rasio dari jumlah prediksi positif yang benar dibandingkan dengan total prediksi positif. Berguna ketika penting untuk menghindari false positive.\n",
    "\n",
    "Recall: Merupakan rasio dari jumlah prediksi positif yang benar dibandingkan dengan total jumlah sampel positif yang sebenarnya. Berguna ketika penting untuk menghindari false negative.\n",
    "\n",
    "F1 Score: Merupakan ukuran yang mengkombinasikan precision dan recall. Berguna ketika Anda ingin mencari keseimbangan antara precision dan recall."
   ]
  }
 ],
 "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": "3.9.17"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}