{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import library\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import pickle\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load all files\n",
    "\n",
    "with open('list_num_cols.txt', 'r') as file_1:\n",
    "  list_num_cols = json.load(file_1)\n",
    "\n",
    "with open('model_scaler.pkl', 'rb') as file_2:\n",
    "  scaler = pickle.load(file_2)\n",
    "\n",
    "with open('model_rfc.pkl', 'rb') as file_3:\n",
    "  model_rfc = pickle.load(file_3)\n",
    "  \n",
    "with open('model_gbc.pkl', 'rb') as file_4:\n",
    "  model_gbc = pickle.load(file_4)"
   ]
  },
  {
   "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>age</th>\n",
       "      <th>anaemia</th>\n",
       "      <th>creatinine_phosphokinase</th>\n",
       "      <th>diabetes</th>\n",
       "      <th>ejection_fraction</th>\n",
       "      <th>high_blood_pressure</th>\n",
       "      <th>platelets</th>\n",
       "      <th>serum_creatinine</th>\n",
       "      <th>serum_sodium</th>\n",
       "      <th>sex</th>\n",
       "      <th>smoking</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20</td>\n",
       "      <td>1</td>\n",
       "      <td>300</td>\n",
       "      <td>1</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>150000</td>\n",
       "      <td>2.5</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  anaemia  creatinine_phosphokinase  diabetes  ejection_fraction  \\\n",
       "0   20        1                       300         1                 50   \n",
       "\n",
       "   high_blood_pressure  platelets  serum_creatinine  serum_sodium  sex  \\\n",
       "0                    1     150000               2.5           150    0   \n",
       "\n",
       "   smoking  time  \n",
       "0        1     2  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Create new data\n",
    "\n",
    "data_inf = pd.DataFrame({\n",
    "    'age'                       : [20],\n",
    "    'anaemia'                   : [1],\n",
    "    'creatinine_phosphokinase'  : [300],\n",
    "    'diabetes'                  : [1],\n",
    "    'ejection_fraction'         : [50],\n",
    "    'high_blood_pressure'       : [1],\n",
    "    'platelets'                 : [150000],\n",
    "    'serum_creatinine'          : [2.5],\n",
    "    'serum_sodium'              : [150],\n",
    "    'sex'                       : [0],\n",
    "    'smoking'                   : [1],\n",
    "    'time'                      : [2],\n",
    "})\n",
    "\n",
    "data_inf"
   ]
  },
  {
   "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>age</th>\n",
       "      <th>ejection_fraction</th>\n",
       "      <th>serum_creatinine</th>\n",
       "      <th>serum_sodium</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20</td>\n",
       "      <td>50</td>\n",
       "      <td>2.5</td>\n",
       "      <td>150</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  ejection_fraction  serum_creatinine  serum_sodium  time\n",
       "0   20                 50               2.5           150     2"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Split between numerical columns and categorical columns\n",
    "\n",
    "data_inf_num = data_inf[list_num_cols]\n",
    "data_inf_num"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Feature scaling and feature encoding\n",
    "\n",
    "data_inf_num_scaled  = scaler.transform(data_inf_num)\n",
    "data_inf_final = data_inf_num_scaled"
   ]
  },
  {
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   0\n",
       "0  1"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Predict using Random Forest Classification Model\n",
    "\n",
    "y_pred_inf_rfc = pd.DataFrame(model_rfc.predict(data_inf_final))\n",
    "y_pred_inf_rfc"
   ]
  },
  {
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   0\n",
       "0  1"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Predict using GradientBoost Classification - Hyperparameter\n",
    "\n",
    "y_pred_inf_gbc = pd.DataFrame(model_gbc.predict(data_inf_final))\n",
    "y_pred_inf_gbc"
   ]
  }
 ],
 "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": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}