{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "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>employee_id</th>\n",
       "      <th>domisili</th>\n",
       "      <th>jenis_kelamin</th>\n",
       "      <th>date_of_birth</th>\n",
       "      <th>join_date</th>\n",
       "      <th>resign_date</th>\n",
       "      <th>marriage_stat</th>\n",
       "      <th>dependant</th>\n",
       "      <th>education</th>\n",
       "      <th>absent_90D</th>\n",
       "      <th>...</th>\n",
       "      <th>total_income_work</th>\n",
       "      <th>income_dependant_ratio</th>\n",
       "      <th>work_efficiency</th>\n",
       "      <th>active_work_category</th>\n",
       "      <th>work_stability_score</th>\n",
       "      <th>position_score</th>\n",
       "      <th>job_income_position_score</th>\n",
       "      <th>education_score</th>\n",
       "      <th>education_income_ratio</th>\n",
       "      <th>weighted_satisfaction_performance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>EM13274</td>\n",
       "      <td>Kota Jakarta Timur</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>1999-01-23</td>\n",
       "      <td>2021-11-30</td>\n",
       "      <td>2023-02-02</td>\n",
       "      <td>Single</td>\n",
       "      <td>0</td>\n",
       "      <td>D2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>4.341320e+07</td>\n",
       "      <td>3.100943e+06</td>\n",
       "      <td>1.12750</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>2.800000</td>\n",
       "      <td>1</td>\n",
       "      <td>3.100943e+06</td>\n",
       "      <td>3</td>\n",
       "      <td>1.033648e+06</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>EM10730</td>\n",
       "      <td>Tangerang</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1998-04-12</td>\n",
       "      <td>2023-01-31</td>\n",
       "      <td>2024-03-16</td>\n",
       "      <td>Single</td>\n",
       "      <td>0</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.489849e+07</td>\n",
       "      <td>1.146038e+06</td>\n",
       "      <td>1.22500</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>4.333333</td>\n",
       "      <td>1</td>\n",
       "      <td>1.146038e+06</td>\n",
       "      <td>1</td>\n",
       "      <td>1.146038e+06</td>\n",
       "      <td>2.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>EM4510</td>\n",
       "      <td>Kabupaten Bekasi</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1981-06-10</td>\n",
       "      <td>2021-10-30</td>\n",
       "      <td>2023-12-15</td>\n",
       "      <td>Married</td>\n",
       "      <td>2</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.003449e+08</td>\n",
       "      <td>2.671265e+06</td>\n",
       "      <td>1.18125</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>4</td>\n",
       "      <td>2.003449e+06</td>\n",
       "      <td>1</td>\n",
       "      <td>8.013796e+06</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>EM2622</td>\n",
       "      <td>Kabupaten Bekasi</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1981-07-26</td>\n",
       "      <td>2021-09-13</td>\n",
       "      <td>2023-10-31</td>\n",
       "      <td>Married</td>\n",
       "      <td>3</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.537505e+08</td>\n",
       "      <td>2.537505e+06</td>\n",
       "      <td>1.22000</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>4</td>\n",
       "      <td>2.537505e+06</td>\n",
       "      <td>1</td>\n",
       "      <td>1.015002e+07</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>EM0633</td>\n",
       "      <td>Kota Jakarta Pusat</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1988-07-07</td>\n",
       "      <td>2022-08-22</td>\n",
       "      <td>2023-10-01</td>\n",
       "      <td>Married</td>\n",
       "      <td>1</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>8.0</td>\n",
       "      <td>...</td>\n",
       "      <td>3.312456e+07</td>\n",
       "      <td>1.274022e+06</td>\n",
       "      <td>1.18250</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>1.444444</td>\n",
       "      <td>1</td>\n",
       "      <td>2.548043e+06</td>\n",
       "      <td>1</td>\n",
       "      <td>2.548043e+06</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  employee_id            domisili jenis_kelamin date_of_birth   join_date  \\\n",
       "0     EM13274  Kota Jakarta Timur     Perempuan    1999-01-23  2021-11-30   \n",
       "1     EM10730           Tangerang     Laki-laki    1998-04-12  2023-01-31   \n",
       "2      EM4510    Kabupaten Bekasi     Laki-laki    1981-06-10  2021-10-30   \n",
       "3      EM2622    Kabupaten Bekasi     Laki-laki    1981-07-26  2021-09-13   \n",
       "4      EM0633  Kota Jakarta Pusat     Laki-laki    1988-07-07  2022-08-22   \n",
       "\n",
       "  resign_date marriage_stat  dependant education  absent_90D  ...  \\\n",
       "0  2023-02-02        Single          0        D2         4.0  ...   \n",
       "1  2024-03-16        Single          0      SLTA         2.0  ...   \n",
       "2  2023-12-15       Married          2      SLTA         0.0  ...   \n",
       "3  2023-10-31       Married          3      SLTA         0.0  ...   \n",
       "4  2023-10-01       Married          1      SLTA         8.0  ...   \n",
       "\n",
       "   total_income_work income_dependant_ratio work_efficiency  \\\n",
       "0       4.341320e+07           3.100943e+06         1.12750   \n",
       "1       1.489849e+07           1.146038e+06         1.22500   \n",
       "2       2.003449e+08           2.671265e+06         1.18125   \n",
       "3       2.537505e+08           2.537505e+06         1.22000   \n",
       "4       3.312456e+07           1.274022e+06         1.18250   \n",
       "\n",
       "   active_work_category  work_stability_score position_score  \\\n",
       "0              Mid-term              2.800000              1   \n",
       "1              Mid-term              4.333333              1   \n",
       "2              Mid-term             25.000000              4   \n",
       "3              Mid-term             25.000000              4   \n",
       "4              Mid-term              1.444444              1   \n",
       "\n",
       "  job_income_position_score  education_score  education_income_ratio  \\\n",
       "0              3.100943e+06                3            1.033648e+06   \n",
       "1              1.146038e+06                1            1.146038e+06   \n",
       "2              2.003449e+06                1            8.013796e+06   \n",
       "3              2.537505e+06                1            1.015002e+07   \n",
       "4              2.548043e+06                1            2.548043e+06   \n",
       "\n",
       "   weighted_satisfaction_performance  \n",
       "0                                1.8  \n",
       "1                                2.6  \n",
       "2                                3.0  \n",
       "3                                4.0  \n",
       "4                                1.8  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df = pd.read_csv(\"D:/Tugas Akhir/Codingan/Development/App/data/df_train_YESUSFIX.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop(columns=['active_work_category', 'work_stability_score', \n",
    "                      'position_score', 'job_income_position_score',\n",
    "                      'education_score', 'education_income_ratio',\n",
    "                      'weighted_satisfaction_performance'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12288"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>churn_status</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>9265</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>3023</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   churn_status  Count\n",
       "0             0   9265\n",
       "1             1   3023"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "churn = df['churn_status']\n",
    "exploded_churn = churn.explode()\n",
    "\n",
    "churn_count = exploded_churn.value_counts().reset_index()\n",
    "churn_count.columns = ['churn_status', 'Count']\n",
    "churn_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "cat_feature = ['departemen', 'position', 'domisili', 'marriage_stat', 'job_satisfaction', 'performance_rating',\n",
    "               'education', 'jenis_kelamin']\n",
    "\n",
    "X = df.drop(columns=['churn_status', 'employee_id', 'date_of_birth', 'join_date', 'resign_date', 'active_work_months'])\n",
    "y = df['churn_status']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9830"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2458"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "churn_status\n",
       "0    7412\n",
       "1    2418\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting imblearn\n",
      "  Using cached imblearn-0.0-py2.py3-none-any.whl.metadata (355 bytes)\n",
      "Collecting imbalanced-learn (from imblearn)\n",
      "  Using cached imbalanced_learn-0.13.0-py3-none-any.whl.metadata (8.8 kB)\n",
      "Requirement already satisfied: numpy<3,>=1.24.3 in d:\\tugas akhir\\codingan\\development\\app\\.venv\\lib\\site-packages (from imbalanced-learn->imblearn) (1.26.4)\n",
      "Requirement already satisfied: scipy<2,>=1.10.1 in d:\\tugas akhir\\codingan\\development\\app\\.venv\\lib\\site-packages (from imbalanced-learn->imblearn) (1.13.1)\n",
      "Requirement already satisfied: scikit-learn<2,>=1.3.2 in d:\\tugas akhir\\codingan\\development\\app\\.venv\\lib\\site-packages (from imbalanced-learn->imblearn) (1.6.1)\n",
      "Collecting sklearn-compat<1,>=0.1 (from imbalanced-learn->imblearn)\n",
      "  Using cached sklearn_compat-0.1.3-py3-none-any.whl.metadata (18 kB)\n",
      "Requirement already satisfied: joblib<2,>=1.1.1 in d:\\tugas akhir\\codingan\\development\\app\\.venv\\lib\\site-packages (from imbalanced-learn->imblearn) (1.4.2)\n",
      "Requirement already satisfied: threadpoolctl<4,>=2.0.0 in d:\\tugas akhir\\codingan\\development\\app\\.venv\\lib\\site-packages (from imbalanced-learn->imblearn) (3.5.0)\n",
      "Using cached imblearn-0.0-py2.py3-none-any.whl (1.9 kB)\n",
      "Using cached imbalanced_learn-0.13.0-py3-none-any.whl (238 kB)\n",
      "Using cached sklearn_compat-0.1.3-py3-none-any.whl (18 kB)\n",
      "Installing collected packages: sklearn-compat, imbalanced-learn, imblearn\n",
      "Successfully installed imbalanced-learn-0.13.0 imblearn-0.0 sklearn-compat-0.1.3\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "%pip install imblearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "After SMOTE class distribution:\n",
      "churn_status\n",
      "1    7412\n",
      "0    7412\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "from imblearn.over_sampling import SMOTENC\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "cat_indices = [X.columns.get_loc(col) for col in cat_feature]\n",
    "\n",
    "# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n",
    "\n",
    "sm = SMOTENC(categorical_features=cat_indices, random_state=42)\n",
    "X_train_res, y_train_res = sm.fit_resample(X_train, y_train)\n",
    "\n",
    "print(\"\\nAfter SMOTE class distribution:\")\n",
    "print(y_train_res.value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training:  churn_status\n",
      "1    7412\n",
      "0    7412\n",
      "Name: count, dtype: int64\n",
      "Testing:  churn_status\n",
      "0    1853\n",
      "1     605\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(\"Training: \", y_train_res.value_counts())\n",
    "print(\"Testing: \", y_test.value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "churn_status\n",
       "1    7412\n",
       "0    7412\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train_res.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(14824, 23)\n",
      "(2458, 23)\n"
     ]
    }
   ],
   "source": [
    "print(X_train_res.shape)\n",
    "print(X_test.shape)"
   ]
  },
  {
   "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>domisili</th>\n",
       "      <th>jenis_kelamin</th>\n",
       "      <th>marriage_stat</th>\n",
       "      <th>dependant</th>\n",
       "      <th>education</th>\n",
       "      <th>absent_90D</th>\n",
       "      <th>avg_time_work</th>\n",
       "      <th>departemen</th>\n",
       "      <th>position</th>\n",
       "      <th>income</th>\n",
       "      <th>total_komp</th>\n",
       "      <th>job_satisfaction</th>\n",
       "      <th>performance_rating</th>\n",
       "      <th>age_years</th>\n",
       "      <th>active_work</th>\n",
       "      <th>income_3_months</th>\n",
       "      <th>income_6_months</th>\n",
       "      <th>total_income_work</th>\n",
       "      <th>income_dependant_ratio</th>\n",
       "      <th>work_efficiency</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Kota Jakarta Timur</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>Single</td>\n",
       "      <td>0</td>\n",
       "      <td>D2</td>\n",
       "      <td>4.0</td>\n",
       "      <td>9.02</td>\n",
       "      <td>Corporate Strategy &amp; Communications</td>\n",
       "      <td>Staff</td>\n",
       "      <td>3.100943e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Low</td>\n",
       "      <td>Excellent</td>\n",
       "      <td>25</td>\n",
       "      <td>429</td>\n",
       "      <td>9.302829e+06</td>\n",
       "      <td>1.860566e+07</td>\n",
       "      <td>4.341320e+07</td>\n",
       "      <td>3.100943e+06</td>\n",
       "      <td>1.12750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Tangerang</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>Single</td>\n",
       "      <td>0</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9.80</td>\n",
       "      <td>Engineering &amp; IT</td>\n",
       "      <td>Staff</td>\n",
       "      <td>1.146038e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>High</td>\n",
       "      <td>Good</td>\n",
       "      <td>26</td>\n",
       "      <td>410</td>\n",
       "      <td>3.438114e+06</td>\n",
       "      <td>6.876228e+06</td>\n",
       "      <td>1.489849e+07</td>\n",
       "      <td>1.146038e+06</td>\n",
       "      <td>1.22500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Kabupaten Bekasi</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>Married</td>\n",
       "      <td>2</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.45</td>\n",
       "      <td>Creative &amp; Design</td>\n",
       "      <td>Manager</td>\n",
       "      <td>8.013796e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>High</td>\n",
       "      <td>Excellent</td>\n",
       "      <td>43</td>\n",
       "      <td>776</td>\n",
       "      <td>2.404139e+07</td>\n",
       "      <td>4.808278e+07</td>\n",
       "      <td>2.003449e+08</td>\n",
       "      <td>2.671265e+06</td>\n",
       "      <td>1.18125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Kabupaten Bekasi</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>Married</td>\n",
       "      <td>3</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.76</td>\n",
       "      <td>Marketing</td>\n",
       "      <td>Manager</td>\n",
       "      <td>1.015002e+07</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Very High</td>\n",
       "      <td>Outstanding</td>\n",
       "      <td>43</td>\n",
       "      <td>778</td>\n",
       "      <td>3.045007e+07</td>\n",
       "      <td>6.090013e+07</td>\n",
       "      <td>2.537505e+08</td>\n",
       "      <td>2.537505e+06</td>\n",
       "      <td>1.22000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Kota Jakarta Pusat</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>Married</td>\n",
       "      <td>1</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>8.0</td>\n",
       "      <td>9.46</td>\n",
       "      <td>Operations</td>\n",
       "      <td>Staff</td>\n",
       "      <td>2.548043e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Low</td>\n",
       "      <td>Excellent</td>\n",
       "      <td>36</td>\n",
       "      <td>405</td>\n",
       "      <td>7.644129e+06</td>\n",
       "      <td>1.528826e+07</td>\n",
       "      <td>3.312456e+07</td>\n",
       "      <td>1.274022e+06</td>\n",
       "      <td>1.18250</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12283</th>\n",
       "      <td>Kabupaten Bogor</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>Married</td>\n",
       "      <td>0</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>4.0</td>\n",
       "      <td>9.40</td>\n",
       "      <td>HR</td>\n",
       "      <td>Staff</td>\n",
       "      <td>1.092339e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>High</td>\n",
       "      <td>Excellent</td>\n",
       "      <td>40</td>\n",
       "      <td>832</td>\n",
       "      <td>3.277017e+06</td>\n",
       "      <td>6.554034e+06</td>\n",
       "      <td>2.949315e+07</td>\n",
       "      <td>1.092339e+06</td>\n",
       "      <td>1.17500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12284</th>\n",
       "      <td>Kota Jakarta Barat</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>Married</td>\n",
       "      <td>2</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>3.0</td>\n",
       "      <td>9.11</td>\n",
       "      <td>Corporate Strategy &amp; Communications</td>\n",
       "      <td>Staff</td>\n",
       "      <td>1.175199e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Medium</td>\n",
       "      <td>Good</td>\n",
       "      <td>32</td>\n",
       "      <td>408</td>\n",
       "      <td>3.525597e+06</td>\n",
       "      <td>7.051194e+06</td>\n",
       "      <td>1.527759e+07</td>\n",
       "      <td>3.917330e+05</td>\n",
       "      <td>1.13875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12285</th>\n",
       "      <td>Tangerang</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>Single</td>\n",
       "      <td>0</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.82</td>\n",
       "      <td>HR</td>\n",
       "      <td>Staff</td>\n",
       "      <td>1.479552e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Medium</td>\n",
       "      <td>Good</td>\n",
       "      <td>24</td>\n",
       "      <td>539</td>\n",
       "      <td>4.438656e+06</td>\n",
       "      <td>8.877312e+06</td>\n",
       "      <td>2.515238e+07</td>\n",
       "      <td>1.479552e+06</td>\n",
       "      <td>1.22750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12286</th>\n",
       "      <td>Tangerang</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>Married</td>\n",
       "      <td>1</td>\n",
       "      <td>D1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>9.17</td>\n",
       "      <td>Finance &amp; Accounting</td>\n",
       "      <td>Staff</td>\n",
       "      <td>4.655009e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Low</td>\n",
       "      <td>Low</td>\n",
       "      <td>26</td>\n",
       "      <td>918</td>\n",
       "      <td>1.396503e+07</td>\n",
       "      <td>2.793005e+07</td>\n",
       "      <td>1.396503e+08</td>\n",
       "      <td>2.327504e+06</td>\n",
       "      <td>1.14625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12287</th>\n",
       "      <td>Tangerang</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>Married</td>\n",
       "      <td>2</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>7.0</td>\n",
       "      <td>9.37</td>\n",
       "      <td>Creative &amp; Design</td>\n",
       "      <td>Senior</td>\n",
       "      <td>6.400201e+06</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Very High</td>\n",
       "      <td>Excellent</td>\n",
       "      <td>47</td>\n",
       "      <td>559</td>\n",
       "      <td>1.920060e+07</td>\n",
       "      <td>3.840121e+07</td>\n",
       "      <td>1.152036e+08</td>\n",
       "      <td>2.133400e+06</td>\n",
       "      <td>1.17125</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>12288 rows × 20 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 domisili jenis_kelamin marriage_stat  dependant education  \\\n",
       "0      Kota Jakarta Timur     Perempuan        Single          0        D2   \n",
       "1               Tangerang     Laki-laki        Single          0      SLTA   \n",
       "2        Kabupaten Bekasi     Laki-laki       Married          2      SLTA   \n",
       "3        Kabupaten Bekasi     Laki-laki       Married          3      SLTA   \n",
       "4      Kota Jakarta Pusat     Laki-laki       Married          1      SLTA   \n",
       "...                   ...           ...           ...        ...       ...   \n",
       "12283     Kabupaten Bogor     Perempuan       Married          0      SLTA   \n",
       "12284  Kota Jakarta Barat     Laki-laki       Married          2      SLTA   \n",
       "12285           Tangerang     Laki-laki        Single          0      SLTA   \n",
       "12286           Tangerang     Perempuan       Married          1        D1   \n",
       "12287           Tangerang     Perempuan       Married          2      SLTA   \n",
       "\n",
       "       absent_90D  avg_time_work                           departemen  \\\n",
       "0             4.0           9.02  Corporate Strategy & Communications   \n",
       "1             2.0           9.80                     Engineering & IT   \n",
       "2             0.0           9.45                    Creative & Design   \n",
       "3             0.0           9.76                            Marketing   \n",
       "4             8.0           9.46                           Operations   \n",
       "...           ...            ...                                  ...   \n",
       "12283         4.0           9.40                                   HR   \n",
       "12284         3.0           9.11  Corporate Strategy & Communications   \n",
       "12285         0.0           9.82                                   HR   \n",
       "12286         5.0           9.17                 Finance & Accounting   \n",
       "12287         7.0           9.37                    Creative & Design   \n",
       "\n",
       "      position        income  total_komp job_satisfaction performance_rating  \\\n",
       "0        Staff  3.100943e+06         0.0              Low          Excellent   \n",
       "1        Staff  1.146038e+06         0.0             High               Good   \n",
       "2      Manager  8.013796e+06         0.0             High          Excellent   \n",
       "3      Manager  1.015002e+07         0.0        Very High        Outstanding   \n",
       "4        Staff  2.548043e+06         0.0              Low          Excellent   \n",
       "...        ...           ...         ...              ...                ...   \n",
       "12283    Staff  1.092339e+06         0.0             High          Excellent   \n",
       "12284    Staff  1.175199e+06         0.0           Medium               Good   \n",
       "12285    Staff  1.479552e+06         0.0           Medium               Good   \n",
       "12286    Staff  4.655009e+06         0.0              Low                Low   \n",
       "12287   Senior  6.400201e+06         0.0        Very High          Excellent   \n",
       "\n",
       "       age_years  active_work  income_3_months  income_6_months  \\\n",
       "0             25          429     9.302829e+06     1.860566e+07   \n",
       "1             26          410     3.438114e+06     6.876228e+06   \n",
       "2             43          776     2.404139e+07     4.808278e+07   \n",
       "3             43          778     3.045007e+07     6.090013e+07   \n",
       "4             36          405     7.644129e+06     1.528826e+07   \n",
       "...          ...          ...              ...              ...   \n",
       "12283         40          832     3.277017e+06     6.554034e+06   \n",
       "12284         32          408     3.525597e+06     7.051194e+06   \n",
       "12285         24          539     4.438656e+06     8.877312e+06   \n",
       "12286         26          918     1.396503e+07     2.793005e+07   \n",
       "12287         47          559     1.920060e+07     3.840121e+07   \n",
       "\n",
       "       total_income_work  income_dependant_ratio  work_efficiency  \n",
       "0           4.341320e+07            3.100943e+06          1.12750  \n",
       "1           1.489849e+07            1.146038e+06          1.22500  \n",
       "2           2.003449e+08            2.671265e+06          1.18125  \n",
       "3           2.537505e+08            2.537505e+06          1.22000  \n",
       "4           3.312456e+07            1.274022e+06          1.18250  \n",
       "...                  ...                     ...              ...  \n",
       "12283       2.949315e+07            1.092339e+06          1.17500  \n",
       "12284       1.527759e+07            3.917330e+05          1.13875  \n",
       "12285       2.515238e+07            1.479552e+06          1.22750  \n",
       "12286       1.396503e+08            2.327504e+06          1.14625  \n",
       "12287       1.152036e+08            2.133400e+06          1.17125  \n",
       "\n",
       "[12288 rows x 20 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0:\ttest: 0.9522383\tbest: 0.9522383 (0)\ttotal: 371ms\tremaining: 6m 10s\n",
      "200:\ttest: 0.9749033\tbest: 0.9749426 (188)\ttotal: 15.7s\tremaining: 1m 2s\n",
      "400:\ttest: 0.9751700\tbest: 0.9753029 (270)\ttotal: 32.3s\tremaining: 48.2s\n",
      "600:\ttest: 0.9757035\tbest: 0.9757052 (599)\ttotal: 47.2s\tremaining: 31.3s\n",
      "800:\ttest: 0.9760228\tbest: 0.9760585 (762)\ttotal: 1m 2s\tremaining: 15.5s\n",
      "999:\ttest: 0.9761958\tbest: 0.9762119 (990)\ttotal: 1m 17s\tremaining: 0us\n",
      "\n",
      "bestTest = 0.9762119056\n",
      "bestIteration = 990\n",
      "\n",
      "Shrink model to first 991 iterations.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<catboost.core.CatBoostClassifier at 0x1cb3665ba30>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from catboost import CatBoostClassifier\n",
    "import pandas as pd\n",
    "\n",
    "model = CatBoostClassifier(\n",
    "    iterations=1000,\n",
    "    learning_rate=0.01,\n",
    "    depth=6,\n",
    "    cat_features= cat_feature,\n",
    "    loss_function='Logloss',\n",
    "    eval_metric='AUC',\n",
    "    scale_pos_weight=len(y_train_res[y_train_res == 0]) / len(y_train_res[y_train_res == 1]),\n",
    "    verbose=200\n",
    ")\n",
    "\n",
    "# Melatih model\n",
    "model.fit(X_train_res, y_train_res, eval_set=(X_test, y_test), use_best_model=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\Tugas Akhir\\Codingan\\Development\\App\\.venv\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import optuna\n",
    "from catboost import CatBoostClassifier\n",
    "from sklearn.metrics import roc_auc_score\n",
    "\n",
    "# Fungsi objective untuk Optuna\n",
    "def objective(trial):\n",
    "    # Definisikan parameter yang akan dioptimasi\n",
    "    params = {\n",
    "        'iterations': trial.suggest_int('iterations', 500, 1000),\n",
    "        'learning_rate': trial.suggest_float('learning_rate', 0.001, 0.1, log=True),\n",
    "        'depth': trial.suggest_int('depth', 4, 6),\n",
    "        'subsample': trial.suggest_float('subsample', 0.5, 0.8),\n",
    "        'colsample_bylevel': trial.suggest_float('colsample_bylevel', 0.5, 0.8),\n",
    "        'l2_leaf_reg': trial.suggest_float('l2_leaf_reg', 5, 20),\n",
    "        'random_strength': trial.suggest_float('random_strength', 5, 10),\n",
    "        'cat_features': cat_feature,\n",
    "        'loss_function': 'Logloss',\n",
    "        'random_state': 42,\n",
    "        'verbose': 0\n",
    "    }\n",
    "\n",
    "    # Inisialisasi model dengan parameter yang dioptimasi\n",
    "    model = CatBoostClassifier(**params)\n",
    "\n",
    "    # Melatih model dengan validasi\n",
    "    model.fit(X_train_res, y_train_res, eval_set=(X_test, y_test), use_best_model=True)\n",
    "\n",
    "    # Prediksi probabilitas untuk menghitung AUC\n",
    "    y_pred = model.predict_proba(X_test)[:, 1]\n",
    "    auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "    return auc  # Mengembalikan AUC sebagai skor yang ingin dimaksimalkan"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[I 2025-04-15 14:46:04,525] A new study created in memory with name: no-name-a82f1532-93fd-444e-a2a9-e64f1ab1581d\n",
      "[I 2025-04-15 14:46:47,591] Trial 0 finished with value: 0.9760700762221638 and parameters: {'iterations': 879, 'learning_rate': 0.03194622545083888, 'depth': 4, 'subsample': 0.6984770397557132, 'colsample_bylevel': 0.6107784129933028, 'l2_leaf_reg': 19.31004315136751, 'random_strength': 8.538025613654153}. Best is trial 0 with value: 0.9760700762221638.\n",
      "[I 2025-04-15 14:47:49,613] Trial 1 finished with value: 0.968974145120934 and parameters: {'iterations': 987, 'learning_rate': 0.00497466285240473, 'depth': 6, 'subsample': 0.7324064062513642, 'colsample_bylevel': 0.5860390386187008, 'l2_leaf_reg': 13.6700598295073, 'random_strength': 8.68535276828941}. Best is trial 0 with value: 0.9760700762221638.\n",
      "[I 2025-04-15 14:48:52,501] Trial 2 finished with value: 0.9771271068136104 and parameters: {'iterations': 958, 'learning_rate': 0.029644496717173407, 'depth': 5, 'subsample': 0.7324841402342017, 'colsample_bylevel': 0.7540959396418829, 'l2_leaf_reg': 7.126960456494959, 'random_strength': 7.4284219069859745}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:49:44,391] Trial 3 finished with value: 0.9687270586451275 and parameters: {'iterations': 778, 'learning_rate': 0.002458862957591489, 'depth': 6, 'subsample': 0.5532293644121917, 'colsample_bylevel': 0.5854134727534657, 'l2_leaf_reg': 16.679333851474986, 'random_strength': 7.393624819420116}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:50:18,713] Trial 4 finished with value: 0.9763555190823012 and parameters: {'iterations': 562, 'learning_rate': 0.036725493598596365, 'depth': 5, 'subsample': 0.7722133171879484, 'colsample_bylevel': 0.6532823306754292, 'l2_leaf_reg': 12.030754990066507, 'random_strength': 8.877550003001012}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:51:17,350] Trial 5 finished with value: 0.968570065072052 and parameters: {'iterations': 962, 'learning_rate': 0.0011370325299877532, 'depth': 5, 'subsample': 0.6728515618578689, 'colsample_bylevel': 0.6826782056061581, 'l2_leaf_reg': 13.623633572161166, 'random_strength': 6.601819735133423}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:51:57,207] Trial 6 finished with value: 0.9687047584216792 and parameters: {'iterations': 617, 'learning_rate': 0.0015432741560526652, 'depth': 5, 'subsample': 0.7499204041791451, 'colsample_bylevel': 0.7446512678837157, 'l2_leaf_reg': 10.072108741396685, 'random_strength': 7.00923150345308}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:52:37,654] Trial 7 finished with value: 0.976307350599653 and parameters: {'iterations': 619, 'learning_rate': 0.09249177862479464, 'depth': 5, 'subsample': 0.5961272939306226, 'colsample_bylevel': 0.6454652012357972, 'l2_leaf_reg': 13.952857635588412, 'random_strength': 5.3135323404658195}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:53:16,002] Trial 8 finished with value: 0.9680910562723839 and parameters: {'iterations': 668, 'learning_rate': 0.0017846267770558202, 'depth': 5, 'subsample': 0.6091299857459994, 'colsample_bylevel': 0.5146530801783137, 'l2_leaf_reg': 6.463177992505614, 'random_strength': 9.83403822639651}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:54:07,117] Trial 9 finished with value: 0.9701837092407667 and parameters: {'iterations': 899, 'learning_rate': 0.009675766544107381, 'depth': 5, 'subsample': 0.7887519851916923, 'colsample_bylevel': 0.7583643579850647, 'l2_leaf_reg': 12.884965304659517, 'random_strength': 7.548006066067643}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:54:49,239] Trial 10 finished with value: 0.9754644021533097 and parameters: {'iterations': 777, 'learning_rate': 0.024122661029117063, 'depth': 4, 'subsample': 0.5013447329900989, 'colsample_bylevel': 0.7800307305883676, 'l2_leaf_reg': 5.638932266363305, 'random_strength': 5.942927125428197}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:55:16,702] Trial 11 finished with value: 0.9764081476096389 and parameters: {'iterations': 508, 'learning_rate': 0.04726537771631546, 'depth': 4, 'subsample': 0.7937595144792454, 'colsample_bylevel': 0.6888257437132431, 'l2_leaf_reg': 9.252398775691933, 'random_strength': 8.42482116769386}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:55:43,712] Trial 12 finished with value: 0.9769504890439002 and parameters: {'iterations': 520, 'learning_rate': 0.07517500503326581, 'depth': 4, 'subsample': 0.7116563324529114, 'colsample_bylevel': 0.7144947743480992, 'l2_leaf_reg': 8.350160243659916, 'random_strength': 8.168242005926878}. Best is trial 2 with value: 0.9771271068136104.\n",
      "[I 2025-04-15 14:56:21,069] Trial 13 finished with value: 0.9774294978435685 and parameters: {'iterations': 703, 'learning_rate': 0.06983698579391724, 'depth': 4, 'subsample': 0.7065367059268508, 'colsample_bylevel': 0.724103178768751, 'l2_leaf_reg': 8.023903029922751, 'random_strength': 7.928311734643061}. Best is trial 13 with value: 0.9774294978435685.\n",
      "[I 2025-04-15 14:57:09,353] Trial 14 finished with value: 0.9731246627091203 and parameters: {'iterations': 724, 'learning_rate': 0.015490359934301434, 'depth': 6, 'subsample': 0.6446878985673278, 'colsample_bylevel': 0.7920667146800474, 'l2_leaf_reg': 7.371821145261041, 'random_strength': 6.451885650217026}. Best is trial 13 with value: 0.9774294978435685.\n",
      "[I 2025-04-15 14:57:52,357] Trial 15 finished with value: 0.9738400538773399 and parameters: {'iterations': 859, 'learning_rate': 0.014795165553926048, 'depth': 4, 'subsample': 0.665044880376952, 'colsample_bylevel': 0.7290363615996102, 'l2_leaf_reg': 5.2279489954943, 'random_strength': 9.524780688568056}. Best is trial 13 with value: 0.9774294978435685.\n",
      "[I 2025-04-15 14:58:30,199] Trial 16 finished with value: 0.9766686142195145 and parameters: {'iterations': 722, 'learning_rate': 0.058843073710673745, 'depth': 4, 'subsample': 0.7070259824991089, 'colsample_bylevel': 0.7046723312898295, 'l2_leaf_reg': 9.886755559850055, 'random_strength': 7.515414918520503}. Best is trial 13 with value: 0.9774294978435685.\n",
      "[I 2025-04-15 14:59:29,101] Trial 17 finished with value: 0.9759648191674881 and parameters: {'iterations': 836, 'learning_rate': 0.0201164375942546, 'depth': 6, 'subsample': 0.7464329768357236, 'colsample_bylevel': 0.751756591889216, 'l2_leaf_reg': 11.194529638284472, 'random_strength': 7.890747626459661}. Best is trial 13 with value: 0.9774294978435685.\n",
      "[I 2025-04-15 15:00:13,792] Trial 18 finished with value: 0.9691284626671959 and parameters: {'iterations': 941, 'learning_rate': 0.008139386305286263, 'depth': 4, 'subsample': 0.6324467522547773, 'colsample_bylevel': 0.6640606522826965, 'l2_leaf_reg': 7.637155074182216, 'random_strength': 9.118659113863696}. Best is trial 13 with value: 0.9774294978435685.\n",
      "[I 2025-04-15 15:01:04,807] Trial 19 finished with value: 0.9772921284671273 and parameters: {'iterations': 812, 'learning_rate': 0.047376913098252045, 'depth': 5, 'subsample': 0.6838122071503733, 'colsample_bylevel': 0.7976712282377681, 'l2_leaf_reg': 15.51559416611185, 'random_strength': 6.860978796602465}. Best is trial 13 with value: 0.9774294978435685.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Trial:\n",
      "AUC: 0.9774294978435685\n",
      "Params:\n",
      "  iterations: 703\n",
      "  learning_rate: 0.06983698579391724\n",
      "  depth: 4\n",
      "  subsample: 0.7065367059268508\n",
      "  colsample_bylevel: 0.724103178768751\n",
      "  l2_leaf_reg: 8.023903029922751\n",
      "  random_strength: 7.928311734643061\n"
     ]
    }
   ],
   "source": [
    "# Buat studi Optuna untuk memaksimalkan AUC\n",
    "study = optuna.create_study(direction='maximize')\n",
    "study.optimize(objective, n_trials=20)  # Lakukan 20 percobaan\n",
    "\n",
    "# Tampilkan hasil terbaik\n",
    "print(\"Best Trial:\")\n",
    "print(f\"AUC: {study.best_trial.value}\")\n",
    "print(\"Params:\")\n",
    "for key, value in study.best_trial.params.items():\n",
    "    print(f\"  {key}: {value}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0:\ttest: 0.8633242\tbest: 0.8633242 (0)\ttotal: 105ms\tremaining: 1m 13s\n",
      "100:\ttest: 0.9693666\tbest: 0.9696128 (84)\ttotal: 4.78s\tremaining: 28.5s\n",
      "Stopped by overfitting detector  (50 iterations wait)\n",
      "\n",
      "bestTest = 0.9696128235\n",
      "bestIteration = 84\n",
      "\n",
      "Shrink model to first 85 iterations.\n",
      "Learn AUC: 0.9742 | Test AUC: 0.9696\n"
     ]
    }
   ],
   "source": [
    "from catboost import CatBoostClassifier\n",
    "from sklearn.metrics import roc_auc_score\n",
    "\n",
    "# Ambil parameter terbaik dari Optuna\n",
    "best_params = study.best_trial.params\n",
    "\n",
    "# Tambahkan parameter tetap (yang tidak dioptimasi)\n",
    "best_params.update({\n",
    "    'loss_function': 'Logloss',  # Masih pakai Logloss untuk training\n",
    "    'eval_metric': 'AUC',        # Pakai AUC untuk evaluasi\n",
    "    'cat_features': cat_feature,\n",
    "    'random_state': 42,\n",
    "    'verbose': 100,  # Set verbose ke 100 agar terlihat AUC setiap 100 iterasi\n",
    "    'od_type': 'Iter',\n",
    "    'od_wait': 50\n",
    "})\n",
    "\n",
    "# Latih model dengan parameter terbaik\n",
    "final_model = CatBoostClassifier(**best_params)\n",
    "\n",
    "final_model.fit(\n",
    "    X_train_res, y_train_res,\n",
    "    eval_set=(X_test, y_test),\n",
    "    use_best_model=True, \n",
    "    verbose=100  # AUC akan ditampilkan setiap 100 iterasi\n",
    ")\n",
    "\n",
    "# Dapatkan prediksi probabilitas\n",
    "y_pred_train = final_model.predict_proba(X_train_res)[:, 1]  # Untuk training set\n",
    "y_pred_test = final_model.predict_proba(X_test)[:, 1]  # Untuk testing set\n",
    "\n",
    "# Hitung AUC untuk training dan testing\n",
    "train_auc = roc_auc_score(y_train_res, y_pred_train)\n",
    "test_auc = roc_auc_score(y_test, y_pred_test)\n",
    "\n",
    "# Cetak skor AUC setelah training selesai\n",
    "print(f\"Learn AUC: {train_auc:.4f} | Test AUC: {test_auc:.4f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "with open('D:/Tugas Akhir/Codingan/Development/App/model/clasification_final_model_smote.sav', 'wb') as f:\n",
    "    pickle.dump(final_model, f)\n",
    "\n",
    "with open('D:/Tugas Akhir/Codingan/Development/App/model/clasification_model_smote.sav', 'wb') as f:\n",
    "    pickle.dump(model, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Final Training Logloss: 0.1081012015241318\n",
      "Final Validation Logloss: 0.1696693209926746\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA04AAAIjCAYAAAA0vUuxAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8ekN5oAAAACXBIWXMAAA9hAAAPYQGoP6dpAACIJElEQVR4nOzdd3xV9f3H8de5M7nZiyRA2HsrCOJArSxRnK1orQJaOizWlmot9VdFreKqUnfrom7ctYoL3IiCIAjI3isDstfdvz9OckkgQICQe2/yfj4e55F7zz33nM/NN8G8/Y5jBIPBICIiIiIiInJQlnAXICIiIiIiEukUnERERERERA5DwUlEREREROQwFJxEREREREQOQ8FJRERERETkMBScREREREREDkPBSURERERE5DAUnERERERERA5DwUlEREREROQwFJxERCSqderUiUmTJoW7DBERaeEUnEREhNmzZ2MYBt999124S4k61dXVPPjggwwbNoykpCRiYmLo0aMHU6dOZd26deEuT0REmogt3AWIiIgci7Vr12KxhOf/A+7Zs4exY8eyZMkSzjvvPH7+858THx/P2rVreeWVV/j3v/+Nx+MJS20iItK0FJxERCRi+Hw+AoEADoej0e9xOp3HsaJDmzRpEt9//z2vv/46l1xySb3X7rjjDm6++eYmuc7RfF9ERKRpaaieiIg02s6dO7n66qvJzMzE6XTSt29fnnnmmXrHeDwebrnlFgYPHkxSUhJxcXGcfvrpfPrpp/WO27JlC4ZhcP/99zNr1iy6du2K0+nkxx9/ZMaMGRiGwYYNG5g0aRLJyckkJSUxefJkKisr651n/zlOtcMOFyxYwLRp08jIyCAuLo6LLrqIgoKCeu8NBALMmDGDtm3b4nK5OOuss/jxxx8bNW/q22+/5b333uOaa645IDSBGejuv//+0PMzzzyTM88884DjJk2aRKdOnQ77ffn++++x2WzcdtttB5xj7dq1GIbBI488EtpXXFzMH/7wB3JycnA6nXTr1o177rmHQCBwyM8lIiINU4+TiIg0Sl5eHieffDKGYTB16lQyMjJ4//33ueaaaygtLeUPf/gDAKWlpTz11FNcfvnlTJkyhbKyMp5++mnGjBnDokWLGDRoUL3zPvvss1RXV/OrX/0Kp9NJampq6LVLL72Uzp07M3PmTJYuXcpTTz1FmzZtuOeeew5b73XXXUdKSgq33norW7ZsYdasWUydOpU5c+aEjpk+fTr33nsv48ePZ8yYMSxfvpwxY8ZQXV192PO/8847AFx55ZWN+O4duf2/L9nZ2Zxxxhm8+uqr3HrrrfWOnTNnDlarlZ/97GcAVFZWcsYZZ7Bz505+/etf06FDB77++mumT5/O7t27mTVr1nGpWUSkJVNwEhGRRrn55pvx+/2sWLGCtLQ0AH7zm99w+eWXM2PGDH79618TGxtLSkoKW7ZsqTesbMqUKfTq1YuHH36Yp59+ut55d+zYwYYNG8jIyDjgmieccEK94/fu3cvTTz/dqOCUlpbGRx99hGEYgNm79NBDD1FSUkJSUhJ5eXk88MADXHjhhbz11luh9912223MmDHjsOdfvXo1AP379z/ssUejoe/LhAkT+PWvf83KlSvp169faP+cOXM444wzyMzMBOCBBx5g48aNfP/993Tv3h2AX//617Rt25b77ruPP/3pT+Tk5ByXukVEWioN1RMRkcMKBoO88cYbjB8/nmAwyJ49e0LbmDFjKCkpYenSpQBYrdZQaAoEAhQWFuLz+RgyZEjomLouueSSBkMTmMGsrtNPP529e/dSWlp62Jp/9atfhUJT7Xv9fj9bt24FYP78+fh8Pq699tp677vuuusOe24gVENCQkKjjj9SDX1fLr74Ymw2W71es5UrV/Ljjz8yYcKE0L7XXnuN008/nZSUlHptNXLkSPx+P1988cVxqVlEpCVTj5OIiBxWQUEBxcXF/Pvf/+bf//53g8fk5+eHHv/nP//hH//4B2vWrMHr9Yb2d+7c+YD3NbSvVocOHeo9T0lJAaCoqIjExMRD1nyo9wKhANWtW7d6x6WmpoaOPZTa65eVlZGcnHzY449UQ9+X9PR0zj77bF599VXuuOMOwOxtstlsXHzxxaHj1q9fzw8//HDQQFq3rUREpHEUnERE5LBqFxT4xS9+wcSJExs8ZsCAAQC88MILTJo0iQsvvJAbb7yRNm3aYLVamTlzJhs3bjzgfbGxsQe9rtVqbXB/MBg8bM3H8t7G6NWrFwArVqzg9NNPP+zxhmE0eG2/39/g8Qf7vlx22WVMnjyZZcuWMWjQIF599VXOPvts0tPTQ8cEAgFGjRrFn//85wbP0aNHj8PWKyIi9Sk4iYjIYWVkZJCQkIDf72fkyJGHPPb111+nS5cuvPnmm/WGyu2/oEG4dezYEYANGzbU693Zu3dvqFfqUMaPH8/MmTN54YUXGhWcUlJS2LRp0wH7a3u+GuvCCy/k17/+dWi43rp165g+fXq9Y7p27Up5eflh20pERBpPc5xEROSwrFYrl1xyCW+88QYrV6484PW6y3zX9vTU7V359ttvWbhw4fEv9AicffbZ2Gw2Hn/88Xr76y7pfSjDhw9n7NixPPXUU7z99tsHvO7xeLjhhhtCz7t27cqaNWvqfa+WL1/OggULjqju5ORkxowZw6uvvsorr7yCw+HgwgsvrHfMpZdeysKFC/nwww8PeH9xcTE+n++IrikiIupxEhGROp555hk++OCDA/Zff/313H333Xz66acMGzaMKVOm0KdPHwoLC1m6dCnz5s2jsLAQgPPOO48333yTiy66iHPPPZfNmzfzxBNP0KdPH8rLy5v7Ix1UZmYm119/Pf/4xz84//zzGTt2LMuXL+f9998nPT29Xm/ZwTz33HOMHj2aiy++mPHjx3P22WcTFxfH+vXreeWVV9i9e3foXk5XX301DzzwAGPGjOGaa64hPz+fJ554gr59+zZqsYu6JkyYwC9+8Qsee+wxxowZc8AcqxtvvJF33nmH8847j0mTJjF48GAqKipYsWIFr7/+Olu2bKk3tE9ERA5PwUlEREL2732pNWnSJNq3b8+iRYu4/fbbefPNN3nsscdIS0ujb9++9ZYHnzRpErm5ufzrX//iww8/pE+fPrzwwgu89tprfPbZZ830SRrnnnvuweVy8eSTTzJv3jyGDx/ORx99xGmnnUZMTMxh35+RkcHXX3/NY489xpw5c7j55pvxeDx07NiR888/n+uvvz50bO/evXnuuee45ZZbmDZtGn369OH555/npZdeOuLvy/nnn09sbCxlZWX1VtOr5XK5+Pzzz7nrrrt47bXXeO6550hMTKRHjx7cdtttJCUlHdH1REQEjGBTzZIVERFpAYqLi0lJSeHvf/87N998c7jLERGRCKE5TiIi0mpVVVUdsG/WrFkAnHnmmc1bjIiIRDQN1RMRkVZrzpw5zJ49m3HjxhEfH89XX33Fyy+/zOjRozn11FPDXZ6IiEQQBScREWm1BgwYgM1m495776W0tDS0YMTf//73cJcmIiIRRnOcREREREREDkNznERERERERA5DwUlEREREROQwWt0cp0AgwK5du0hISGjUzQ1FRERERKRlCgaDlJWV0bZtWyyWQ/cptbrgtGvXLnJycsJdhoiIiIiIRIjt27fTvn37Qx7T6oJTQkICYH5zEhMTw1wNeL1ePvroI0aPHo3dbg93OXIQaqfooHaKHmqr6KB2ih5qq+igdoo8paWl5OTkhDLCobS64FQ7PC8xMTFigpPL5SIxMVG/QBFM7RQd1E7RQ20VHdRO0UNtFR3UTpGrMVN4tDiEiIiIiIjIYSg4iYiIiIiIHIaCk4iIiIiIyGG0ujlOIiIiInJs/H4/Xq833GVEHa/Xi81mo7q6Gr/fH+5yWg273Y7Vaj3m8yg4iYiIiEijlZeXs2PHDoLBYLhLiTrBYJCsrCy2b9+u+4k2I8MwaN++PfHx8cd0HgUnEREREWkUv9/Pjh07cLlcZGRk6I//IxQIBCgvLyc+Pv6wN1uVphEMBikoKGDHjh107979mHqeFJxEREREpFG8Xi/BYJCMjAxiY2PDXU7UCQQCeDweYmJiFJyaUUZGBlu2bMHr9R5TcFKLiYiIiMgRUU+TRJOm+nlVcBIRERERETkMBScREREREZHDUHASERERETlCnTp1YtasWY0+/rPPPsNqtVJSUnL8imomM2bMYNCgQeEuo9kpOImIiIhIi2UYxiG3GTNmHNV5Fy9ezK9+9atGH3/KKaewc+dOEhMTj+p6jfXZZ59hGAbFxcXH9TqtkVbVExEREZEWa/fu3aHHc+bM4ZZbbmHt2rWhfXXv7RMMBvH7/dhsh/8TOSMj44jqcDgcZGVlUVpaekTvk8ihHicREREROSrBYJBKjy8sW2NvwJuVlRXakpKSMAwj9HzNmjUkJCTw/vvvM3jwYJxOJ1999RUbN27kggsuIDMzk/j4eE466STmzZtX77z7D9UzDIOnnnqKiy66CJfLRffu3XnnnXdCr+8/VG/27NkkJyfz4Ycf0rt3b+Lj4xk7dmy9oOfz+fj9739PcnIyaWlp3HTTTUycOJELL7zwqNusqKiIq666ipSUFFwuF+eccw7r16+vd8yTTz5JTk4OLpeLiy66iAceeIDk5OSDnjMQCHD77bfTvn17nE4ngwYN4oMPPgi97vF4mDp1KtnZ2cTExNCxY0dmzpwJmD9DM2bMoEOHDjidTtq2bcvvf//7o/58x5N6nERERETkqFR5/fS55cOwXPvH28fgcjTNn7J/+ctfuP/+++nSpQspKSls376dcePGceedd+J0OnnuuecYP348a9eupUOHDgc9z2233ca9997Lfffdx8MPP8wVV1zB1q1bSU1NbfD4yspK7r//fp5//nksFgu/+MUvuOGGG3jxxRcBuOeee3jxxRd59tln6d27N//85z95++23Oeuss476s06aNIn169fzzjvvkJiYyE033cS4ceP48ccfsdvtLFiwgN/85jfcc889nH/++cybN4+//e1vhzznP//5T/7xj3/wr3/9ixNOOIFnnnmG888/n1WrVtG9e3ceeugh3nnnHV599VU6dOjA9u3b2b59OwBvvPEGDz74IK+88gp9+/YlNzeX5cuXH/XnO54UnERERESkVbv99tsZNWpU6HlqaioDBw4MPb/jjjt46623eOedd5g6depBzzNp0iQuv/xyAO666y4eeughFi1axNixYxs83uv18sQTT9C1a1cApk6dyu233x56/eGHH2b69OlcdNFFADzyyCPMnTv3qD9nbWBasGABp5xyCgAvvvgiOTk5vP322/zsZz/j4Ycf5pxzzuGGG24AoEePHnz99de8++67Bz3v/fffz0033cRll10GmIHv008/ZdasWTz66KNs27aN7t27c9ppp2EYBh07dgy9d9u2bWRlZTFy5EjsdjsdOnRg6NChR/0ZjycFpzBam1vG+twSdlaEuxIRERGRIxdrt/Lj7WPCdu2mMmTIkHrPy8vLmTFjBu+99x67d+/G5/NRVVXFtm3bDnmeAQMGhB7HxcWRmJhIfn7+QY93uVyh0ASQnZ0dOr6kpIS8vLx6IcJqtTJ48GACgcARfb5aq1evxmazMWzYsNC+tLQ0evbsyerVqwFYu3ZtKKjVGjp06EGDU2lpKbt27eLUU0+tt//UU08N9RxNmjSJUaNG0bNnT8aOHct5553H6NGjAfjZz37GrFmz6NKlC2PHjmXcuHGMHz++UfPMmpvmOIXR60u2M/WV5Xy3R80gIiIi0ccwDFwOW1g2wzCa7HPExcXVe37DDTfw1ltvcdddd/Hll1+ybNky+vfvj8fjOeR57Hb7Ad+fQ4Wcho5v7NytaHLiiSeyefNm7rjjDqqqqrj00kv56U9/CkBOTg5r167lscceIzY2lmuvvZYRI0bg9XrDXPWB9Bd7GDls5rffd3T/00BEREREjoMFCxYwadIkLrroIvr3709WVhZbtmxp1hqSkpLIzMxk8eLFoX1+v5+lS5ce9Tl79+6Nz+fj22+/De3bu3cva9eupU+fPgD07Nmz3jWBA57XlZiYSNu2bVmwYEG9/QsWLAids/a4CRMm8OSTTzJnzhzeeOMNCgsLAYiNjWX8+PE89NBDfPbZZyxcuJAVK1Yc9ec8XiKvD6wVsVvN4ORvef9jQURERCRqde/enTfffJPx48djGAZ/+9vfjnp43LG47rrrmDlzJt26daNXr148/PDDFBUVNaq3bcWKFSQkJISeG4bBwIEDueCCC5gyZQr/+te/SEhI4C9/+Qvt2rXjggsuCF1zxIgRPPDAA4wfP55PPvmE999//5DXvPHGG7n11lvp2rUrgwYN4tlnn2XZsmWhRS4eeOABsrOzOeGEE7BYLLz22mtkZWWRnJzM7Nmz8fv9DBs2DJfLxQsvvEBsbGy9eVCRQsEpjNTjJCIiIhJ5HnjgAa6++mpOOeUU0tPTuemmm8Jy/6WbbrqJ3NxcrrrqKqxWK7/61a8YM2YMVuvh53eNGDGi3nOr1YrP5+PZZ5/l+uuv57zzzsPj8TBixAjmzp0bGjZ46qmn8sQTT3Dbbbfxf//3f4wZM4Y//vGPPPLIIwe91u9//3tKSkr405/+RH5+Pn369OGdd96he/fuACQkJHDvvfeyfv16rFYrJ510EnPnzsVisZCcnMzdd9/NtGnT8Pv99O/fn//973+kpaUdw3fu+DCCLXEg5SGUlpaSlJRESUnJcb9z8+E89eUm/v7eaganB3jl+rEHjHOVyOH1epk7dy7jxo1TO0UwtVP0UFtFB7VT9Giutqqurmbz5s107tyZmJiY43adlioQCFBaWkpiYiIWy5HPmAkEAvTu3ZtLL72UO+644zhU2LApU6awZs0avvzyy2a7ZlM61M/tkWQD9TiFUW2Pk189TiIiIiKyn61bt/LRRx9xxhln4Ha7eeSRR9i8eTM///nPj+t177//fkaNGkVcXBzvv/8+//nPf3jssceO6zWjgYJTGNXOcfK1qj4/EREREWkMi8XC7NmzueGGGwgGg/Tr14958+bRu3fv43rdRYsWce+991JWVkaXLl146KGH+OUvf3lcrxkNFJzCyKHFIURERETkIHJycg5Yra45vPrqq81+zWig5cjDyK7FIUREREREooKCUxg5QkP1mu4GbiIiIiIi0vQUnMLIYTMDk3qcREREREQim4JTGDlq1uDXHCcRERERkcim4BRGdqt6nEREREREooGCUxjVLg6hHicRERERkcim4BRGocUh1OMkIiIiEtHOPPNM/vCHP4Sed+rUiVmzZh3yPYZh8Pbbbx/ztZvqPOE2adIkLrzwwnCXcdQUnMLIYdMNcEVERESOp/HjxzN27NgGX/vyyy8xDIMffvjhiM+7ePFifvWrXx1refXMmDGDQYMGHbB/9+7dnHPOOU16rf3Nnj2b5OTk43qNaKfgFEb7liMPcyEiIiIiLdQ111zDxx9/zI4dOw547dlnn2XIkCEMGDDgiM+bkZGBy+VqihIPKysrC6fT2SzXkoNTcAqjuN0L+Y31HU4Krgp3KSIiIiJHLhgET0V4tmDj/s/zeeedR0ZGBrNnz663v7y8nNdee41rrrmGvXv3cvnll9OuXTtcLhf9+/fn5ZdfPuR59x+qt379ekaMGEFMTAx9+vTh448/PuA9f/nLXxgyZAjx8fF06dKFv/3tb3i9XsDs8bnttttYvnw5hmFgGEao5v2H6q1YsYKf/OQnxMbGkpaWxq9+9SvKy8tDr9cOibv//vvJzs4mLS2N3/3ud6FrHY1t27ZxwQUXEB8fT2JiIpdeeil5eXn1jvn73/9OmzZtSEhI4Je//CV/+ctfGuxBq+V2u/n9739PmzZtiImJ4bTTTmPx4sWh14uKirjiiivIyMggNjaW7t278+yzzwLg8XiYOnUq2dnZxMTE0LFjR2bOnHnUn68xbMf17HJIcVvn8xf7K/zLdy7BRv7yi4iIiEQMbyXc1TY81/7rLnDEHfYwm83GVVddxezZs7n55psxDHNV49deew2/38/ll19OeXk5gwcP5qabbiIxMZH33nuPK6+8kq5duzJ06NDDXiMQCHDxxReTmZnJt99+S0lJSb35ULUSEhJ49NFH6d69O6tWrWLKlCkkJCTw5z//mQkTJrBy5Uo++OAD5s2bB0BSUtIB56ioqGDMmDEMHz6cxYsXk5+fzy9/+UumTp1aLxx++umnZGdn8+mnn7JhwwYmTJjAoEGDmDJlymE/T0OfrzY0ff755/h8Pn73u98xYcIEPvvsMwBefPFF7rzzTh577DFOPfVUXnnlFf7xj3/QuXPng573z3/+M2+88Qb/+c9/6NixI/feey9jxoxhw4YNpKam8re//Y0ff/yR999/n/T0dDZs2EBVVRUADz30EO+88w6vvvoqHTp0YPv27Wzfvv2IP9uRUHAKI4vN7HJ14MMXCOIIcz0iIiIiLdHVV1/Nfffdx+eff86ZZ54JmMP0LrnkEpKSkkhKSuKGG24IHX/dddfx4Ycf8uqrrzYqOM2bN481a9bw4Ycf0ratGSTvuuuuA+Yl3XzzzZSWlpKYmEiXLl244YYbeOWVV/jzn/9MbGws8fHx2Gw2srKyDnqtl156ierqap577jni4szg+MgjjzB+/HjuueceMjMzAUhJSeGRRx7BarXSq1cvzj33XObPn39UwWn+/PmsWLGCzZs3k5OTA8Bzzz1H3759Wbx4MSeddBIPP/ww11xzDZMnTwbglltu4aOPPqrXE1ZXRUUFjz/+OLNnzw59n5588kk+/vhjnn76aW688Ua2bdvGCSecwJAhQwCzl6/Wtm3b6N69O6eddhqGYdCxY8cj/lxHSsEpjKx2MzjZ8eHxBWieUbIiIiIiTcTuMnt+wnXtRurVqxennHIKzzzzDGeeeSYbNmzgyy+/5PbbbwfA7/dz11138eqrr7Jz5048Hg9ut7vRc5hWr15NTk5OKDQBDB8+/IDj5syZw6xZs9i6dSvl5eX4fD4SExMb/TlqrzVw4MBQaAI49dRTCQQCrF27NhSc+vbti9VqDR2TnZ3NihUrjuhada+Zk5MTCk0Affr0ITk5mdWrV3PSSSexdu1arr322nrvGzp0KJ988kmD59y4cSNer5dTTz01tM9utzN06FBWr14NwG9/+1suueQSli5dyujRo7nwwgs55ZRTAHM44qhRo+jZsydjx47lvPPOY/To0Uf1+RpLc5zCyGI3+5gc+PDqZk4iIiISbQzDHC4Xjq1myF1jXXPNNbzxxhuUlZXx7LPP0rVrV8444wwA7rvvPv75z39y00038emnn7Js2TLGjBmDx+Npsm/VwoULufLKKxk1ahTvvPMO33//PTfffHOTXqMuu91e77lhGAQC0XUPnHPOOYetW7fyxz/+kV27dnH22WeHegZPPPFENm/ezB133EFVVRWXXnopP/3pT49rPQpOYWStGapnN3x4/NH1gywiIiISTS699FIsFgsvvfQSzz33HFdffXVovtOCBQu44IIL+MUvfsHAgQPp0qUL69ata/S5e/fuzfbt29m9e3do3zfffFPvmK+//pqOHTtyww03MGTIELp3787WrVvrHeNwOPD7/Ye91vLly6moqAjtW7BgARaLhZ49eza65iNR+/nqziH68ccfKS4upk+fPgD07Nmz3sIOwAHP6+ratSsOh4MFCxaE9nm9XhYvXhw6J5irF06cOJEXXniBWbNm8e9//zv0WmJiIhMmTODJJ59kzpw5vPHGGxQWFh7z5z0YDdULJ6vZ42THh1fBSUREROS4iY+PZ8KECUyfPp3S0lImTZoUeq179+68/vrrfP3116SkpPDAAw+Ql5dX7w/4Qxk5ciQ9evRg4sSJ3HfffZSWlnLzzTfXO6Z79+5s27aNN954gxEjRvD+++/z1ltv1TumU6dObN68mWXLltG+fXsSEhIOWIb8iiuu4NZbb2XixInMmDGDgoICrrvuOq688srQML2j5ff7WbZsWb19TqeTkSNH0r9/f6644gpmzZqFz+fj2muv5YwzzgjNP7ruuuuYMmUKQ4YM4ZRTTmHOnDn88MMPdOnSpcFrxcXF8dvf/pYbb7yR1NRUOnTowL333ktlZSXXXHMNYM6TGjx4MH379sXtdvPuu+/Su3dvAB544AGys7M54YQTsFgsvPbaa2RlZR3Xe1GpxymcbHWH6ik4iYiIiBxP11xzDUVFRYwZM6befKT/+7//48QTT2TMmDGceeaZZGVlceGFFzb6vBaLhbfeeouqqiqGDh3KL3/5S+688856x5x//vn84Q9/4M9//jMnnngiX3/9NX/729/qHXPJJZcwduxYzjrrLDIyMhpcEt3lcvHhhx9SWFjISSedxE9/+lPOPvtsHnnkkSP7ZjSgvLycE044od42fvx4DMPgv//9LykpKYwYMYKRI0fSpUsX5syZE3rvFVdcwfTp07nhhhtCw+gmTZpETEzMQa939913c8kll3DllVdy4oknsmHDBj788ENSUlIAswdu+vTpDBgwgBEjRmC1WnnllVcAc4XCe++9lyFDhnDSSSexZcsW5s6di8Vy/OKNEWxl62CXlpaSlJRESUnJEU/Ga3LLXoK3f8tn/oFk/Ppt+rZPDW89clBer5e5c+cybty4A8YMS+RQO0UPtVV0UDtFj+Zqq+rqajZv3kznzp0P+QexNCwQCIRW1Tuef+BHilGjRpGVlcXzzz8f1joO9XN7JNlAQ/XCqd5QvVaVX0VERESkBamsrOSJJ55gzJgxWK1WXn75ZebNm9fgjYCjlYJTOFnN/yNkN8zlyEVEREREopFhGMydO5c777yT6upqevbsyRtvvMHIkSPDXVqTUXAKJ+u+G+CWa46TiIiIiESp2NhY5s2bF+4yjquWP7gyktX0ODnQcuQiIiIiIpFMwSmcNMdJREREolArW1tMolxT/bwqOIVTneCkOU4iIiIS6axWKwAejyfMlYg0Xu3Pa+3P79HSHKdwqrmPk93QfZxEREQk8tlsNlwuFwUFBdjt9laxpHZTCgQCeDweqqur9b1rJoFAgIKCAlwuFzbbsUUfBadwstbeANerHicRERGJeIZhkJ2dzebNm9m6dWu4y4k6wWCQqqoqYmNjMQwj3OW0GhaLhQ4dOhzz91zBKZxCwUlznERERCQ6OBwOunfvruF6R8Hr9fLFF18wYsQI3VS6GTkcjibp4VNwCqfa+zjh16p6IiIiEjUsFgsxMTHhLiPqWK1WfD4fMTExCk5RSIMrw6nmPk7mqnoKTiIiIiIikUrBKZxqV9Uz/Hi8vjAXIyIiIiIiB6PgFE7WfV20AZ87jIWIiIiIiMihKDiFU02PE0DA5w1jISIiIiIicigKTuFUJzj5vepxEhERERGJVApO4WSx4DfMOxgHNVRPRERERCRiKTiFWcAw5zkFfLoXgoiIiIhIpFJwCjO/RcFJRERERCTSKTiFWcBiznMKKjiJiIiIiEQsBacwC9T0OOHXHCcRERERkUil4BRmwZrgpB4nEREREZHIpeAUZsFQj5Pu4yQiIiIiEqkUnMIsWHMvp6BfPU4iIiIiIpFKwSnManucLApOIiIiIiIRS8Ep3Gp6nFBwEhERERGJWApOYRa0mj1ORkBznEREREREIpWCU7hZneZXLQ4hIiIiIhKxFJzCzKjpcbIGNFRPRERERCRSRURwevTRR+nUqRMxMTEMGzaMRYsWHfTY2bNnYxhGvS0mJqYZq21iNnOOk4bqiYiIiIhErrAHpzlz5jBt2jRuvfVWli5dysCBAxkzZgz5+fkHfU9iYiK7d+8ObVu3bm3GipuWUbM4hEXBSUREREQkYoU9OD3wwANMmTKFyZMn06dPH5544glcLhfPPPPMQd9jGAZZWVmhLTMzsxkrblqGzZzjpOAkIiIiIhK5bOG8uMfjYcmSJUyfPj20z2KxMHLkSBYuXHjQ95WXl9OxY0cCgQAnnngid911F3379m3wWLfbjdvtDj0vLS0FwOv14vVGQFixmE1gDXgiox5pUG3bqI0im9opeqitooPaKXqoraKD2inyHElbhDU47dmzB7/ff0CPUWZmJmvWrGnwPT179uSZZ55hwIABlJSUcP/993PKKaewatUq2rdvf8DxM2fO5Lbbbjtg/0cffYTL5WqaD3IMeuYVkAhY8fHue3OxGOGuSA7l448/DncJ0ghqp+ihtooOaqfoobaKDmqnyFFZWdnoY8ManI7G8OHDGT58eOj5KaecQu/evfnXv/7FHXfcccDx06dPZ9q0aaHnpaWl5OTkMHr0aBITE5ul5kPxvL8A9oIdH6NGj8Fpt4a7JGmA1+vl448/ZtSoUdjt9nCXIwehdooeaqvooHaKHmqr6KB2ijy1o9EaI6zBKT09HavVSl5eXr39eXl5ZGVlNeocdrudE044gQ0bNjT4utPpxOl0Nvi+SPiBDTpjAXDgI2ixRkRNcnCR8nMjh6Z2ih5qq+igdooeaqvooHaKHEfSDmFdHMLhcDB48GDmz58f2hcIBJg/f369XqVD8fv9rFixguzs7ONV5nFlqVkcwoEPjy8Q5mpERERERKQhYR+qN23aNCZOnMiQIUMYOnQos2bNoqKigsmTJwNw1VVX0a5dO2bOnAnA7bffzsknn0y3bt0oLi7mvvvuY+vWrfzyl78M58c4akbNfZzs+PD6g2GuRkREREREGhL24DRhwgQKCgq45ZZbyM3NZdCgQXzwwQehBSO2bduGxbKvY6yoqIgpU6aQm5tLSkoKgwcP5uuvv6ZPnz7h+gjHxmp2D9oN9TiJiIiIiESqsAcngKlTpzJ16tQGX/vss8/qPX/wwQd58MEHm6GqZmI1h+rZ8eHxKziJiIiIiESisN8At7UL1vQ4OTXHSUREREQkYik4hZu17hwnBScRERERkUik4BRutXOcNFRPRERERCRiKTiFW+0cJ8OHV0P1REREREQikoJTuNX0ODnw4laPk4iIiIhIRFJwCreaOU4O/OpxEhERERGJUApO4VZnjpNugCsiIiIiEpkUnMKt3n2c/GEuRkREREREGqLgFGa193FyGF68PvU4iYiIiIhEIgWncKtzHyctDiEiIiIiEpkUnMIttKqeliMXEREREYlUCk7hFprj5NcNcEVEREREIpSCU7jVuY+TepxERERERCKTglO41cxxshkBvD5vmIsREREREZGGKDiFW01wAvD5PGEsREREREREDkbBKdzqBCe/V8FJRERERCQSKTiFW80cJ4CgrzqMhYiIiIiIyMEoOIWbYcGPFYCAepxERERERCKSglME8NUEp6AWhxARERERiUgKThHAb5jD9QI+d5grERERERGRhig4RQC/YQMgqOAkIiIiIhKRFJwiQG1wCmg5chERERGRiKTgFAEChjnHye9Vj5OIiIiISCRScIoAtXOcgupxEhERERGJSApOESCgOU4iIiIiIhFNwSkCBI3a5cjV4yQiIiIiEokUnCJAwGKreaDgJCIiIiISiRScIsC+oXq6Aa6IiIiISCRScIoAwZrgZPg1x0lEREREJBIpOEWCmqF6RsBLMBgMczEiIiIiIrI/BacIEKwJTnZ8uH2BMFcjIiIiIiL7U3CKAPWCk1fBSUREREQk0ig4RYKaOU5OfLh9/jAXIyIiIiIi+1NwigCBOj1O1epxEhERERGJOApOEaB2OXK74aNaPU4iIiIiIhFHwSkChIKT5jiJiIiIiEQkBacIUBucHKjHSUREREQkEik4RYB6wcmr4CQiIiIiEmkUnCJA0LACGqonIiIiIhKpFJwigN9iB7Q4hIiIiIhIpFJwigDB0FA9r5YjFxERERGJQApOEcBfZ46TboArIiIiIhJ5FJwiQMDiAMCpHicRERERkYik4BQBauc4xRgeraonIiIiIhKBFJwiQMAwg5MTL26fepxERERERCKNglME8NcZqudWj5OIiIiISMRRcIoA/poepxg0VE9EREREJBIpOEWAQM0cJ6ehoXoiIiIiIpFIwSkC7JvjpB4nEREREZFIpOAUAWrnOMVoOXIRERERkYik4BQBapcjd+LB7fWFuRoREREREdmfglMEqB2qZzWCeL3eMFcjIiIiIiL7U3CKALU9TgB+b1UYKxERERERkYYoOEWA2h4nALzV4StEREREREQapOAUCQyDQM0CEUGfgpOIiIiISKRRcIoQAavTfKAeJxERERGRiKPgFCGCthgADL+Ck4iIiIhIpFFwihQ1wQmfO7x1iIiIiIjIARScIoXNHKpnaI6TiIiIiEjEUXCKFHazx8kW9ODzB8JcjIiIiIiI1KXgFCGMmqF6MXhw+xScREREREQiiYJThLDU9Dg58VLt9Ye5GhERERERqUvBKVLU9Dg5Da96nEREREREIoyCU6SoM1RPPU4iIiIiIpFFwSlS1KyqZw7VU4+TiIiIiEgkUXCKFLZ9c5zcPvU4iYiIiIhEEgWnCBEMzXHyqMdJRERERCTCKDhFirpD9dTjJCIiIiISURScIkXdoXrqcRIRERERiSgKTpEiFJw8muMkIiIiIhJhFJwiRc1QvRhDN8AVEREREYk0Ck6Rok6PkxaHEBERERGJLApOESJYZ3EIDdUTEREREYksCk6RoqbHKUY9TiIiIiIiEUfBKVKE7uOkOU4iIiIiIpFGwSlS1Buqpx4nEREREZFIouAUKercx0k9TiIiIiIikUXBKVJojpOIiIiISMRScIoQoVX1DK2qJyIiIiISaRScIkW9oXrqcRIRERERiSQKTpGizlA99TiJiIiIiEQWBadIUXdVPY+Ck4iIiIhIJImI4PToo4/SqVMnYmJiGDZsGIsWLWrU+1555RUMw+DCCy88vgU2h5oeJ4sRxOdzh7kYERERERGpK+zBac6cOUybNo1bb72VpUuXMnDgQMaMGUN+fv4h37dlyxZuuOEGTj/99Gaq9DirCU4Afk9VGAsREREREZH92cJdwAMPPMCUKVOYPHkyAE888QTvvfcezzzzDH/5y18afI/f7+eKK67gtttu48svv6S4uPig53e73bjd+3pwSktLAfB6vXi93qb7IEeptgZvwMBeu89dFRG1yT6hdlK7RDS1U/RQW0UHtVP0UFtFB7VT5DmStjCCwWDwONZySB6PB5fLxeuvv15vuN3EiRMpLi7mv//9b4Pvu/XWW/nhhx946623mDRpEsXFxbz99tsNHjtjxgxuu+22A/a/9NJLuFyupvgYTebcZddgC3oZ6Z3FdUNTw12OiIiIiEiLVllZyc9//nNKSkpITEw85LFh7XHas2cPfr+fzMzMevszMzNZs2ZNg+/56quvePrpp1m2bFmjrjF9+nSmTZsWel5aWkpOTg6jR48+7DenOXi9Xj7++GNGjRqF5UcXuEuw4GfcuHHhLk3qqNtOdrv98G+QsFA7RQ+1VXRQO0UPtVV0UDtFntrRaI0R9qF6R6KsrIwrr7ySJ598kvT09Ea9x+l04nQ6D9hvt9sj6gfWbreDPQbcJdgCboKGFYct7FPQZD+R9nMjDVM7RQ+1VXRQO0UPtVV0UDtFjiNph7AGp/T0dKxWK3l5efX25+XlkZWVdcDxGzduZMuWLYwfPz60LxAwbxZrs9lYu3YtXbt2Pb5FH0dGnZvgVnp8OGyOMFckIiIiIiIQ5lX1HA4HgwcPZv78+aF9gUCA+fPnM3z48AOO79WrFytWrGDZsmWh7fzzz+ess85i2bJl5OTkNGf5TS4UnAwv5W5fmKsREREREZFaYR+qN23aNCZOnMiQIUMYOnQos2bNoqKiIrTK3lVXXUW7du2YOXMmMTEx9OvXr977k5OTAQ7YH5XsZnCKwUOlboIrIiIiIhIxwh6cJkyYQEFBAbfccgu5ubkMGjSIDz74ILRgxLZt27BYWslcnzpD9SrU4yQiIiIiEjHCHpwApk6dytSpUxt87bPPPjvke2fPnt30BYWLzVzEwpzjpB4nEREREZFI0Uq6cqKELRYAp+FRj5OIiIiISARRcIok6nESEREREYlICk6RJDTHyUOFRz1OIiIiIiKRQsEpktTpcdJQPRERERGRyKHgFEns5hynGMNDhVtD9UREREREIoWCUySpN8dJPU4iIiIiIpFCwSmS1L2PkxaHEBERERGJGApOkaQmOMXgoVJznEREREREIoaCUySp7XEy1OMkIiIiIhJJFJwiieY4iYiIiIhEJAWnSFJnjlO5VtUTEREREYkYCk6RpHY5cs1xEhERERGJKApOkaR2qJ7hpVJznEREREREIoaCUySps6peheY4iYiIiIhEDAWnSOKIAyAWN5Wa4yQiIiIiEjEUnCJJTXCKM6rx+AN4fIEwFyQiIiIiIqDgFFkc8QDEUQ2gJclFRERERCKEglMkqRecgroJroiIiIhIhFBwiiQ1Q/UsRlBLkouIiIiIRBAFp0hid4UexlGtHicRERERkQih4BRJLBawm71OLqNaPU4iIiIiIhFCwSnS1K6sh1s9TiIiIiIiEULBKdLUBCcX1VpVT0REREQkQig4RZralfWMaso1VE9EREREJCIoOEUa574lySvdGqonIiIiIhIJFJwiTWiOUzUVGqonIiIiIhIRFJwijaPOqnpaHEJEREREJCIoOEUax76hehWa4yQiIiIiEhEUnCKNepxERERERCKOglOkqXsfJ/U4iYiIiIhEBAWnSFPnPk5aHEJEREREJDIcVXD64IMP+Oqrr0LPH330UQYNGsTPf/5zioqKmqy4VsmRAEC8UUWFliMXEREREYkIRxWcbrzxRkpLSwFYsWIFf/rTnxg3bhybN29m2rRpTVpgqxPqcXJTqR4nEREREZGIYDuaN23evJk+ffoA8MYbb3Deeedx1113sXTpUsaNG9ekBbY6tXOcjGr1OImIiIiIRIij6nFyOBxUVlYCMG/ePEaPHg1AampqqCdKjlLNcuSa4yQiIiIiEjmOqsfptNNOY9q0aZx66qksWrSIOXPmALBu3Trat2/fpAW2OqFV9aopq/YRDAYxDCPMRYmIiIiItG5H1eP0yCOPYLPZeP3113n88cdp164dAO+//z5jx45t0gJbndB9nNz4A0HKtSS5iIiIiEjYHVWPU4cOHXj33XcP2P/ggw8ec0GtXs1QvTiqASip8pIQYw9nRSIiIiIird5R9TgtXbqUFStWhJ7/97//5cILL+Svf/0rHo+nyYprlZw1wcmoBoKUVHnDW4+IiIiIiBxdcPr1r3/NunXrANi0aROXXXYZLpeL1157jT//+c9NWmCrUzNUz0oAJ14FJxERERGRCHBUwWndunUMGjQIgNdee40RI0bw0ksvMXv2bN54442mrK/1sbtCD+OoplTBSUREREQk7I4qOAWDQQKBAGAuR15776acnBz27NnTdNW1RhZrKDy5jGr1OImIiIiIRICjCk5Dhgzh73//O88//zyff/455557LmDeGDczM7NJC2yV6ixJruAkIiIiIhJ+RxWcZs2axdKlS5k6dSo333wz3bp1A+D111/nlFNOadICWyUFJxERERGRiHJUy5EPGDCg3qp6te677z6sVusxF9XqORIA815OCk4iIiIiIuF3VMGp1pIlS1i9ejUAffr04cQTT2ySolq9ej1OugGuiIiIiEi4HVVwys/PZ8KECXz++eckJycDUFxczFlnncUrr7xCRkZGU9bY+oSCUxV71OMkIiIiIhJ2RzXH6brrrqO8vJxVq1ZRWFhIYWEhK1eupLS0lN///vdNXWPrUxOcNFRPRERERCQyHFWP0wcffMC8efPo3bt3aF+fPn149NFHGT16dJMV12o54gHdx0lEREREJFIcVY9TIBDAbrcfsN9ut4fu7yTHINTjpFX1REREREQiwVEFp5/85Cdcf/317Nq1K7Rv586d/PGPf+Tss89usuJarf2WIw8Gg2EuSERERESkdTuq4PTII49QWlpKp06d6Nq1K127dqVz586Ulpby8MMPN3WNrY/THKrnohp/IEiFxx/mgkREREREWrejmuOUk5PD0qVLmTdvHmvWrAGgd+/ejBw5skmLa7Vq5jglWNwAlFR5iXce08rxIiIiIiJyDI76r3HDMBg1ahSjRo1qynoEQkP1kqw1wanSS7vk2HBWJCIiIiLSqjU6OD300EONPqmWJD9GNcEpsU6Pk4iIiIiIhE+jg9ODDz7YqOMMw1BwOlY1Q/XiDQUnEREREZFI0OjgtHnz5uNZh9RVuxw51QC6l5OIiIiISJgd1ap6cpzVBKfYmuCkHicRERERkfA6qsUhpk2b1uB+wzCIiYmhW7duXHDBBaSmph5Tca2WIwGA2EAloOAkIiIiIhJuRxWcvv/+e5YuXYrf76dnz54ArFu3DqvVSq9evXjsscf405/+xFdffUWfPn2atOBWITYFgJhABTZ8Ck4iIiIiImF2VEP1LrjgAkaOHMmuXbtYsmQJS5YsYceOHYwaNYrLL7+cnTt3MmLECP74xz82db2tQ2wyYACQTIWCk4iIiIhImB1VcLrvvvu44447SExMDO1LSkpixowZ3HvvvbhcLm655RaWLFnSZIW2KhYrxCQBkGyUKTiJiIiIiITZUQWnkpIS8vPzD9hfUFBAaWkpAMnJyXg8nmOrrjVzmfPDUihXcBIRERERCbOjHqp39dVX89Zbb7Fjxw527NjBW2+9xTXXXMOFF14IwKJFi+jRo0dT1tq6xNYEJ6NMy5GLiIiIiITZUS0O8a9//Ys//vGPXHbZZfh8PvNENhsTJ04M3Si3V69ePPXUU01XaWtT0+OUbKjHSUREREQk3I4qOMXHx/Pkk0/y4IMPsmnTJgC6dOlCfHx86JhBgwY1SYGtVmz9oXrBYBDDMMJclIiIiIhI63RUwalWfHx86F5NdUOTNIHaOU5GOT5/kAqPn3jnMTWXiIiIiIgcpaOa4xQIBLj99ttJSkqiY8eOdOzYkeTkZO644w4CgUBT19g61fQ4pVvLAdhT5g5nNSIiIiIirdpRdWHcfPPNPP3009x9992ceuqpAHz11VfMmDGD6upq7rzzziYtslVymTfBbWOrAjfklVbTKT0uzEWJiIiIiLRORxWc/vOf//DUU09x/vnnh/YNGDCAdu3ace211yo4NYVQj1MFAPnqcRIRERERCZujGqpXWFhIr169Dtjfq1cvCgsLj7koYd+qepQBZo+TiIiIiIiEx1EFp4EDB/LII48csP+RRx5hwIABx1yUEOpxSgiawalAPU4iIiIiImFzVEP17r33Xs4991zmzZvH8OHDAVi4cCHbt29n7ty5TVpgq1XT4+TylQBB9TiJiIiIiITRUfU4nXHGGaxbt46LLrqI4uJiiouLufjii1m1ahXPP/98U9fYOtX0OFmDPuKo1hwnEREREZEwOuobA7Vt2/aARSCWL1/O008/zb///e9jLqzVc7jAFgO+alKMcvU4iYiIiIiE0VH1OEkzid23QIR6nEREREREwkfBKZLVzHNKMcopq/ZR6fGFuSARERERkdZJwSmSxdbeBLcSgPxS9TqJiIiIiITDEc1xuvjiiw/5enFx8bHUIvur6XHKiakCj3kT3E7pcWEuSkRERESk9Tmi4JSUlHTY16+66qpjKkjqqJnj1NZRBegmuCIiIiIi4XJEwenZZ589XnVIQ2p6nNrYKgC0QISIiIiISJhExBynRx99lE6dOhETE8OwYcNYtGjRQY998803GTJkCMnJycTFxTFo0KCWe++omh6nNEtNcFKPk4iIiIhIWIQ9OM2ZM4dp06Zx6623snTpUgYOHMiYMWPIz89v8PjU1FRuvvlmFi5cyA8//MDkyZOZPHkyH374YTNX3gxc+5YjB/U4iYiIiIiES9iD0wMPPMCUKVOYPHkyffr04YknnsDlcvHMM880ePyZZ57JRRddRO/evenatSvXX389AwYM4KuvvmrmyptBzap68YFSQHOcRERERETC5YjmODU1j8fDkiVLmD59emifxWJh5MiRLFy48LDvDwaDfPLJJ6xdu5Z77rmnwWPcbjdu976emtJSM4R4vV68Xu8xfoJjV1tDQ7UYjkRsQIy3BDCDUyTU3Bodqp0kcqidoofaKjqonaKH2io6qJ0iz5G0RViD0549e/D7/WRmZtbbn5mZyZo1aw76vpKSEtq1a4fb7cZqtfLYY48xatSoBo+dOXMmt9122wH7P/roI1wu17F9gCb08ccfH7Avvno3ZwOWqr0A7CosZ+7cuc1cmdTVUDtJ5FE7RQ+1VXRQO0UPtVV0UDtFjsrKykYfG9bgdLQSEhJYtmwZ5eXlzJ8/n2nTptGlSxfOPPPMA46dPn0606ZNCz0vLS0lJyeH0aNHk5iY2IxVN8zr9fLxxx8zatQo7HZ7/Rcr98Lqm3AGqrDho8pv46yRY4h1WMNTbCt2yHaSiKF2ih5qq+igdooeaqvooHaKPLWj0RojrMEpPT0dq9VKXl5evf15eXlkZWUd9H0Wi4Vu3boBMGjQIFavXs3MmTMbDE5OpxOn03nAfrvdHlE/sA3Wk5ABFhsEfLS3l7LFm0pRtZ/EuJjwFCkR93MjDVM7RQ+1VXRQO0UPtVV0UDtFjiNph7AuDuFwOBg8eDDz588P7QsEAsyfP5/hw4c3+jyBQKDePKYWw2KFxHYA9I83V9bbXaIFIkREREREmlvYh+pNmzaNiRMnMmTIEIYOHcqsWbOoqKhg8uTJAFx11VW0a9eOmTNnAuacpSFDhtC1a1fcbjdz587l+eef5/HHHw/nxzh+kjtA8Vb6xBbzv6KO7CiqCndFIiIiIiKtTtiD04QJEygoKOCWW24hNzeXQYMG8cEHH4QWjNi2bRsWy76OsYqKCq699lp27NhBbGwsvXr14oUXXmDChAnh+gjHV3IHALrYCwHYUdT4CWwiIiIiItI0wh6cAKZOncrUqVMbfO2zzz6r9/zvf/87f//735uhqgiRlANAe8seAPU4iYiIiIiEQdhvgCuHkWwGpwx/PqAeJxERERGRcFBwinQ1PU6J7t2AepxERERERMJBwSnS1fQ4Oct3AUF2l1Tj8wfCW5OIiIiISCuj4BTpEtsDBoa/mmxrGf5AkNxSLUkuIiIiItKcFJwinc0BCdkADEo07+Wk4XoiIiIiIs1LwSka1AzX6+MqARScRERERESam4JTNKhZIKKrQ/dyEhEREREJBwWnaFDT49Te2Auox0lEREREpLkpOEWD5A4AtPHnAepxEhERERFpbgpO0SDJDE6JHt3LSUREREQkHBScokHNUL2Yil0AupeTiIiIiEgzU3CKBkntAbB4ykizVuleTiIiIiIizUzBKRo44sCVDsCJiaUAbC/UcD0RERERkeai4BQt0rsDMCg2H4BthRXhrEZEREREpFVRcIoW6T0A6OcwF4jYVKDgJCIiIiLSXBScokVGLwA6BXcAsFHBSURERESk2Sg4RYsMs8cpo2oLAJv2lIexGBERERGR1kXBKVqk9wQgtnwLNnxs21uJV0uSi4iIiIg0CwWnaJHUHhzxGAEfPe0F+AJBthdWhrsqEREREZFWQcEpWhhGaGW94Yl7AS0QISIiIiLSXBScoknNAhEDY3IBzXMSEREREWkuCk7RpGZJ8m7GTkA9TiIiIiIizUXBKZrU9Dhle7cCCk4iIiIiIs1FwSmaZJgr6yWWb8ZCQEP1RERERESaiYJTNEnuCFYnFr+bdkYBe8o9lFR6w12ViIiIiEiLp+AUTaw2SOsGwLC4fAA2qtdJREREROS4U3CKNln9ARgWuwPQPCcRERERkeag4BRt2g4CoL+xCYC1uaVhLEZEREREpHVQcIo2bU8AoIN7PQArdyo4iYiIiIgcb7ZwFyBHKKs/GBZc7nwyKGLVLhvBYBDDMMJdmYiIiIhIi6Uep2jjiIN0c1nyE2xbKK32saOoKsxFiYiIiIi0bApO0ahmntOZCTsBWLmzJIzFiIiIiIi0fApO0Sh7EGD2OAGs3KXgJCIiIiJyPCk4RaOaBSI6etYBsGqXFogQERERETmetDhENAotELGHNhSxcqdDC0SIiIiIiBxH6nGKRg4XZPQCYJB1E3vKPeSXucNclIiIiIhIy6XgFK3aDQbgnDhzuJ4WiBAREREROX4UnKJVr3MBOCvwDQYBVig4iYiIiIgcNwpO0arrT8CRQLKvgBOMDSzYsCfcFYmIiIiItFgKTtHK5oSe5wBwrvVblmwtorDCE+aiRERERERaJgWnaNb3QgDOty8mGAzw6Zr88NYjIiIiItJCKThFs65ngyOBjOAeTjA2MG91XrgrEhERERFpkRScopk9BnqOBWCy7QO+WFeA2+cPc1EiIiIiIi2PglO0O/m3BA0r463fcJbvK77ZVBjuikREREREWhwFp2jXbjDGiBsAuNP+NIuWrwxzQSIiIiIiLY+CU0sw4kZKUvuTZFRyypo7w12NiIiIiEiLo+DUEljt2C7+F96glVP9i8lf9kG4KxIRERERaVEUnFqIuPZ9+ch1HgD2+f8HAS0SISIiIiLSVBScWpBtA66jOBhHStl6WPpcuMsREREREWkxFJxakKF9uvJP38UABOfNgJKd4S1IRERERKSFUHBqQQa2T+Zt2zksC3TBqC6Gt38LgUC4yxIRERERiXoKTi2IzWphSNdM/uj9HV5LDGz+HL5+KNxliYiIiIhEPQWnFub07ulsDmYzO2GKuWPerfDWb6G6JLyFiYiIiIhEMQWnFubMHm0AmJl/MpXD/gAYsPwleOgE+GA67P7hyE7o94Lf1+R1ioiIiIhEE1u4C5Cm1SHNRf92SazYWcKbKVfzi6vPMec6FW6Cbx4zt8x+0O8SaNMbktqDLQYsNnOz2sHvgaoi+P4Fc7Pa4YQrocuZULYbAj5oNwTSu0PhZijdCYltzXNV7oXyAsjqB464cH87RERERESahIJTC3TegGxW7CzhvR9284uTT4bfLYaN82HZS7B2LuStNLfG8gILHzG3xkrKgUufg3YnHnH9IiIiIiKRRsGpBRrXP5uZ76/h2817yS+rpk1CDPQYY26VhbDqTdj0ORRvhdJdZg+T32f2JAW8YHWYvVA5Q+Hka83heoufgpLtkNgOgn7Y8R24S8GZaPY0le4051HZYsDqNI99Zgx0G2nut8dCek+zF6pos3mD3r4XQo9zoKrQ7MlK6wbOhAM/kN8Hvuqac+tHVkRERESan/4KbYFyUl0Myklm2fZiPliZy1XDO+170ZUKJ/3S3I5Ej9H1nwf8UFVsns8wzH3ucjMYVZfA29fC2vfMHq5aG+bVP8eqN8GwmkEMwLDUhCsX+DxQXQwVBWZoAjOQZfUzg5q7zDwmNrlmSwFXGqR1h4xe+4YJxqWbQw1FRERERI6BglMLdd6AbJZtL+bd5bvrB6emYrFCXFr9fc5482tsMkx4wQxOZblmuHKXQcFa8FZBamez52v5y1CeZwam2BRzflTB6oNf0++GnUvMrbGszjpzuZxmj1ZcBsQkAUad4xyQ1R/aDjJ7x0RERERE6lBwaqHG9c/mrrmrWbSlkBU7SujfPql5C7BYoPf4Qx/zk79B6Q5IyDZDTVmuuepf0A8Wuxmm4tLM4YC1r+/63gxYMUlmT1JVsbmQRVURlOdDwRrYs94cfkjQDFu7l5lboxg1QwJrrh+fCfFtsLjS6bWrEMs3myAx2xxWmNjODH0WG8QkqmdLREREpAVTcGqh2ibHcsGgdrz1/U7+OX8dT008KdwlHchqg5RO+54nZJnbwaR1NbfGCgSgeAvkrjDDlrfanJdVUWD2gNXlLjN7ssrzwFdlbu5Scx4YYAV6AuS9c/Dr2ePM3raYZHO4ob1mc7jMXix7nPnVEWf2wmX0guQOZvAyrDUhzGoOfawdwhjwm6HRHmeG0VrBoPnVMBqqRERERESamIJTC3bdT7rx32U7mbc6nx92FDOgfXK4S2peFgukdjG3xggGzVDlrTIXxKjcCxX5UJ6Hv2Q3W9cso1N2Kpay3WavVnle7RvNL94KcyvdeRw+jGEGq2Bg3/UMq9krlpgNOcPMJeIdcWbPl8VuBlOLrc7jml60hGwtsiEiIiJyhPTXUwvWJSOeCwe1483vdzJr3nqemRSBvU6RxDAgvk2dHd1CjwJeLysq5pIzbhwW+35D8vw+s3eqqshc0KK6BDyVZgDzVtR8ray/ryzXHFZYutvsWQoGakLRwQT3LaIR2uWHyj3mlrvCXPmwUZ/TAskdIbMvdBgOJ12jeV0iIiIih6Hg1MJdd3Z3/rt8F5+syefTtfmc1bPN4d8kR8ZqM4feuVKP7TzBYM1WE6Rqh+/5qsFTbg7bMyz7Nr/bDGt7N8K2hea9uXwec0l5v9dcXr72a8BnzvuqLDRfL9psbmvehe+ehnPug65nmUMFRUREROQACk4tXOf0OCad0omnv9rMX99cwYd/HEFijBYxiEiGUTNnyVJ/v6NmnlRDEtuaPUd9zm/cNQIBc4jh3vWwezksfBQKN8GLl5gLbrQ/CeKzzMd+jxnaLFZz1UGrwxwGWPvYmWD20MWmmvOwYpIho6fmXYmIiEiLpODUCtwwuifzVuexdW8lM+euYebF/cNdkoSLxWLOiUrMhs4j4MSJ8Omd8P2L5hDD/e+1daRSOkHv8yGlo3lfrdhU815a6T01r0pERESimv6SaQViHVbuuWQAl/37G15etI3zBmRzarf0cJclkSAmEc65B0bfCbnLzV6oqiIzRFkdZk9SMGj2Pvk95tA/vwd8bnNeV1meOa/L74XSXVC0Bb5+6MDrJLSFIVebYS0m0eytciaAI17DA0VERCQqKDi1Eid3SePKkzvy/DdbuemNH/jwDyOIc6r5pYbVBu0Gm9vR8lTAug9h8+dQscecT1VVaAaqsl3w6d/h0wbe54jfF6TqbYnma/YY895aNqf5NTbV7DFzJprDApNyzF4tERERkeNIfzm3Ijed04tP1uSzo6iK+z5cy4zz+4a7JGlJHHHQ72Jzq8vnhh//C0ufg5Lt5j2zqkvNRSrAXPjCUw5lu4/uulYH/OT/YPjUY6tfRERE5BAUnFqReKeNuy/pz5VPL2L211s4q1cbzuiREe6ypKWzOWHApeZWl89thih3ac3XuludfT63uUiFr9p8XFFgLuPuqTCHDVbkw8e3wMo3sOQMp1NBFcZqHyS3h/ZDNBRQREREmoSCUytzevcMLh/agZcXbWPqi0t5/ben0DMrIdxlSWtkc5rbsQyzCwbh+xfgg+mweznW3csZCLDjP+br7QbD+Y9AZp+mqFhERERaMQWnVmjG+X3YWFDOos2FXD17MW9eewqZiTHhLkvkyBkGnHgldDsb1n2AP38N+WsXkZngwJL/I+xcAv863Vy23XyD+R5bjDm00BFvbqmdYdivIblDWD+OiIiIRC4Fp1bIabPyr18M5qLHFrBlbyUXPbqApyedRO/sxHCXJnJ0Es1V+wJeL4u8cxk3bhyWqgJ470+wdi4Ubzv8Ob59AvpcYC424Uo1l1DP6AmxyWCPA5vjuH8MERERiVwKTq1USpyD568ZxsRnF7GpoIKfPv41D//8BH7SKzPcpYk0jcS2cNlLsGe9OVeKoDm0j6A5X8pTAe5ycz7Vj/81VwNc+cbBz5fRCzqfAT3GmF91XyoREZFWRf/lb8VyUl289dtT+e2LS/h6415++Z/vuPncPlx9aicMwwh3eSLHzjAgo8fhjzvpGtj2LWz8xLyHVUU+5K+BvevNBSgACtaY26J/QVwG5Awz52eldoEuZ0FWf/N6IiIi0iIpOLVySS47/7l6KLf8dyUvL9rOHe/+yNrcUmac3xeXQz8e0op0GGZu+/N7zXtSbf/GDFY/vmOu7Lfm3frHWWsWu4hJgi5nQLeREJ9lPk/rar4mIiIiUUt/GQt2q4W7LupP14x47py7mle/28HSbcX8/uzuZCfF0LdtokKUtF5WOyRkmvOf+lwA4+6HLV/C3o3mjX53fW8+91aC320O/fv+BXMLncMBWQNg2G9gwM/C91lERETkqOmvYQHAMAx+eXoX+rRN5A+vLGNDfjm/f/l7ANokOHlpyjC6tdGy5SJY7dD1J+ZWy+cxb+Ab8EHxVlj3IWz/1rzRb+Uec/jfzu/gzV/C+o9gzF0Qr3uoiYiIRBMFJ6nnlK7pvH/96Tzw8TrW5paxeU8F+WVuLvv3t7zyK4UnkQbZHJDS0Xyc1rV+qAoGoWgzLJ8DX9wHK141t/gs6D4Szvo/SMwOT90iIiLSaJZwFyCRJy3eyZ0X9ef1357CvGln0Ds7kT3lbi569GtmvLOKDfll4S5RJHoYhrmAxFnTYfL7kNnP3F+eaw7ne3gwfHqXOfRPREREIpaCkxxSSpyDl345jIHtkyhz+5j99RZGPfgFf3t7JSVV3nCXJxJdOgyD3y6A6Tvgqv9C+6HgrYDP74GHT4RHh8Gbv4IF/4QN86A8P9wVi4iISA0N1ZPDSolz8Na1p/LF+gJe+GYb81bn8fw3W5m7Yjfn9M/i7F6ZnN49HZtVOVykUZwJ0OVM835Qq940e542fb5vyfO6Bk+CUXdAjG5QLSIiEk4R8Zfuo48+SqdOnYiJiWHYsGEsWrTooMc++eSTnH766aSkpJCSksLIkSMPebw0DYvF4MyebXhq4hBemjKMLhlx7K3w8MI325g8ezFn3v8ZsxdsZkN+OR5fINzlikQHw4B+l8CVb8EN6+Gyl805T30uhLTu5jFLZsNjJ8Nbv4X3/wLfPA4b5psr+omIiEizCXuP05w5c5g2bRpPPPEEw4YNY9asWYwZM4a1a9fSpk2bA47/7LPPuPzyyznllFOIiYnhnnvuYfTo0axatYp27dqF4RO0Pqd0TeeD60fw1YYCPlmTz9wVuewoqmLG/34EwGoxuHRIe2ac3xenzRrmakWiRFwa9BpnbrU2fwnvTIWiLbD8pQPfk9oVOp8OPcdB5xFgj222ckVERFqbsAenBx54gClTpjB58mQAnnjiCd577z2eeeYZ/vKXvxxw/Isvvljv+VNPPcUbb7zB/Pnzueqqq5qlZgGHzcJPemXyk16Z3DyuD68v2c5rS3awIb+cSo+flxdtZ2NBBU/8YjCpcY5wlysSnTqfDr/92rzpbnkeVBWai0gUrIW966Fwo7ktmQ2GBVI6QdsT4My/Qnq3cFcvIiLSooQ1OHk8HpYsWcL06dND+ywWCyNHjmThwoWNOkdlZSVer5fU1NQGX3e73bjd7tDz0tJSALxeL15v+Bc3qK0hEmo5WjYDLhvSjsuGtCMYDPLF+j384dUVLNpcyMkz53NSxxTG9G3DRYPaEmOPzh6oltBOrUGLbCfDAX1/euD+qmKMHYswNs7Dsu4DjLJdULgJCjcRXP0/AsOvI9D/UkjpYg4JjDAtsq1aILVT9FBbRQe1U+Q5krYwgsFg8DjWcki7du2iXbt2fP311wwfPjy0/89//jOff/4533777WHPce211/Lhhx+yatUqYmJiDnh9xowZ3HbbbQfsf+mll3C5XMf2AeSgdlXCf9ZZya3a9wdbvD3I4LQgCY4g6TEwMDWIJfL+nhOJPsEgTl8JCdU76ZY3l8yyFaGXKu2pbEsbwZb0s3Hbk8JYpIiISOSprKzk5z//OSUlJSQmHnohprAP1TsWd999N6+88gqfffZZg6EJYPr06UybNi30vLS0lJycHEaPHn3Yb05z8Hq9fPzxx4waNQq73R7ucprUNcEgm/ZU8snafF78djs7i6v5PHdfUjq5cwr3/7Q/mYkNt10kacnt1JKonYDgDfhW/xfLkqcxdi7B5S2kV+7b9CyYSzCzP7TpTaDHOQS7jQ5rT5TaKjqonaKH2io6qJ0iT+1otMYIa3BKT0/HarWSl5dXb39eXh5ZWVmHfO/999/P3Xffzbx58xgwYMBBj3M6nTidzgP22+32iPqBjbR6mkqvtg56tU1myohuzF2xm+XbSyip8vL+yt18s7mIMf9cQFq8E6fNwhk9MrhkcHt6Z4c/0B5MS22nlqbVt9PAn5mbpxLWvQ/fPI6xYzHGriWwawmWZS9Amz4w7DfQ53yITQlbqa2+raKE2il6qK2ig9opchxJO4Q1ODkcDgYPHsz8+fO58MILAQgEAsyfP5+pU6ce9H333nsvd955Jx9++CFDhgxppmrlWNitFi4Y1I4LBpkrH157Vleue+l7ftxdSkVhJQDr88t56qvN9G2byCUntmdo51TaJseS4rJjROAcDZGI53CZy533uwT2bIDcH2D7IvO+Ufk/wv9+D+/9CbqdbR7Tcxw448NdtYiISEQK+1C9adOmMXHiRIYMGcLQoUOZNWsWFRUVoVX2rrrqKtq1a8fMmTMBuOeee7jlllt46aWX6NSpE7m5uQDEx8cTH6//4EeLrhnxvDP1VNbkluH2BcgvrebtZTv5ZE0+q3aVsmrXj6FjY+wWspNiOblLGv93bm/inGH/sRWJPundzK3fxXDmX8yV+Fa8BnkrYd0H5uaIhxMnwsm/heSccFcsIiISUcL+F+iECRMoKCjglltuITc3l0GDBvHBBx+QmZkJwLZt27BY9t2n9/HHH8fj8fDTn9ZfZerWW29lxowZzVm6HCOb1UK/dvsmq5/TP5vCCg//W76Ld3/YxeY9lewpd1PtDbB5TwWb91SwdGsRj15xIllJMTisFhy2iLiHs0h0iU2G0/5gbvlrYNWbsOJ1c2nzbx6Fbx6D9kOg20hI7QJJ7aHdELDp1gIiItJ6hT04AUydOvWgQ/M+++yzes+3bNly/AuSsEmNczDxlE5MPKUTAG6fn7wSN6tzS/m/t1eyNq+MkQ98DoDNYtC3bSIndEghOymGNolOBndIpUOaVksUabQ2vaDNX+HM6bBhHiz4J2z5EnYsNrdarnQYeBl0PgPa9DbDlIbQiohIKxIRwUnkYJw2Kx3SXHRIczGgfRK/f/l7Fm8pAsAXCLJ8RwnLd5TUe0/HNBdtEpxYLQYdUl0MaJ/MSZ1S6ZEZr7lSIgdjGNB9lLmV7oJ1H8K2b6B0J+Svhso9sPARcwNwJpkBqk1vyOwLad0gsS0kdwB7bHg/i4iIyHGg4CRRIzspltd+cwrVXj8Ae8rdLNlaxKpdpRSUudlWWMny7cVs3VvJ1r3mghPfbCrk1e92AJCVGMNJnVPpnB5HmwQnljohymY16JjqolubeFLjHApY0roltoUhk80NwO81e6NWvgm5K2DvenCXwPZvzK0uW6w5j+rEq6D9ULBoOK2IiLQMCk4SdWLsVgDap7hon+IKrdQHUFbtZem2YirdPjz+AOvzylm2vZjFWwrJLa3mf8t3Hfb8yS47XTPi6ZoRR9eMeHpkJdAtPZbw3SpaJMysduh5jrkB+DxmeMpfDXmrzBX6iraavVPuUlj2orm50qHLmZDUDuIyoMNwaHsCWKxh/TgiIiJHQ8FJWpSEGDtn9Mg4YH+118+izYWs3l3Klr0V7Cn3HPD6lr0V7CiqorjSy5KtRSzZWlTvGLth5f41X5CeEEN6vJOMBCcZ8Q4yEpykxztJT3CS4rKT7HKQFGvHbtX/aZcWyuYwh+dl9oX+dRbqCQbNeVHfPQtr3jWH9618vf57XWnQbjCW9J7k7HXD7naQ3VfD+0REJOIpOEmrEGO3MqJHBiMaCFV1VXn8bN5TwcaCcjYWlLMhv5y1uWVs2lOBNwA7iqvZUVzdqGsmOG1kJDhpk+gkNc4MU4kxdhJj7aS4HKTFO8wAFu8kOc6Ow2rBbrVgtWiYoEQpw4Ccoebmf8icI7X9W6jcC8XbYPMX5uP1H2Fd/xEnAjzzb8CA1M7mCn5xbSAmyQxnhgW81RD0m6+l94DkjmYPloKWiIg0MwUnkTpiHVb6tE2kT9vEevvLK6t59X8f0m/IKRRV+ykoc7On3F3v694KD0UVHkqrfQCUuX2UuX1s2lNxRDVYDHOpdrvFwGGz0CHVRd92SeaCF4ZBnNNGWryDrMQYOtXM19KcLIk4Vjt0Pt3cavm9sHMp5K3En7uKorULSPPnY1QVQuEmc2us2FRzZb+0bpDVzxwCmHOyedNfERGR40DBSaQRnHYraTFwQodk7Hb7IY/1B4KUVnkprPSwp8xNbmk1xZVeSqq8lFaZX4sqPRSUe9hb7g7dq6pWIAgeXwAPUOHxU1R54MqBdcU7bfRvl0TftomkxDlIjLWTGGMjIcZGjM2K027BabPisFlIi3No8QsJH6sdOgyDDsMIeL0sCMxl3DnnYPcUm/OkSnZARQFUl5ghK+Cv6VkKwt4NULDOPMZbAVWF5pb7g3kfKgCL3QxSNoc5v6rb2dD1bPNmvo64cH5yERFpARScRJqY1WKQEucgJc5B14z4wx4fDAZx+wJ4/QG8/iA+fwBvIIjXF6Da52djfgUrd5VQWuXFHwhS5vaxp8zN7pJqdhRVUu72sXDTXhZu2tuo+hJibHRKi6Njmove2YmcP7AtOan6v/QSJoYB8W3MrTGCQTNYle6E4u1QsNpc6a926fSC1fuO3Th/32NHvLlARUKW2TvVYTikdDKHBcYkgTNRKwCKiMghKTiJhJlhGMTYraHVAvfXKyuRcwdkN/iaxxdgY0E5P+woZl1eOaVVXkqrvZRV+yir9lHt9ePxB/D4AlR7/RRVmq+t2FnCip0lvPvDbu77cC3DOqdydu82nN49g25t4rWwhUQuw4DYZHPL7As9x5r7g0FzqF/JdvD7YM86WPc+bF8MvirwlJtb0WbYthC+eWz/E0NM4r4gFZNsLmSR2gXSukJqV3MelivN7DkTEZFWR8FJJIo5bBZ6ZyfSOzvx8Adjrh64vbCSLXsr2bKngs/W5fP1xr18u7mQbzcXAmuwW80bB2cnxZIe78DltOG0WeiRmcAZPTJom6xJ+RKBDMMMOGldzefdR8Lwa81A5S4zhwCW55m9VNu/he2LoCLf7L3yVQM1PVnVBx8WG+KIN4NVbIp5z6vUzpDS2fyakAX2OHOulSPOPFbLr4uItAgKTiKtSIzdSvfMBLpnJgAwZUQXdhRV8vGPeXy+roBFmwup9PjZWFDBxoKGF7VIj3eQFmeuFJgW76iZN+WkW5t4xvbL0qqAElmM2p6kRDNUdQQGTqh/jLfavP9UVfG+8FRdbAatvRuhcCPsrenNIriv96p0B+StOFwBZi9VXDrYa8JUSidzLpYjzgxVie2hTS9IyjHrFRGRiKTgJNLKtU9xMfnUzkw+tTOBQJDdpdVsKignv9TN3go3VZ4AFR4fS7YW8f22IvaUew64D1atCUNyuPuS/lp8QqKLPcbcDjfPyu+rCVhFZrCqLIKSbVC42RwCWLjFvHeVp9IMVkE/EDT3Ve7Zd54tXzZ8fkdCTYBqD7YYc8hgahdzmGBaF0jqAFb9Z1tEJFz0L7CIhFgsBu2SY2l3kOF4JVVedhZVsbfCTWGFh73lHvZWuMkrdfPm0h3M+W47ibE2Jp/aGZvFMJdVtxrEO20KUxL9rDZwpZrb4QSD4PeYvVfl+eb9q7xVZvDau9Gcj+WrMsNY0RbYux48ZeYNhHcsbvicFhskdzB7rGq3tO6Q0bMmbDmb7rOKiMgBFJxEpNGSYu0kxTY8MX5op1T+/MYPPPnlZp78cnO913JSYzmzRxs6p8dhsxpYLQY2i4HVYsFmMRfHyEx0kpkYQ0aCU4tTSPQzDDPINHbFQJ/HHBKY/yOUF4DfbYat2pBVuMmci3Wo+13FpppDEq0Oc25V7bXjM80bC9c+jm9jrjDoiNdKgiIiR0DBSUSaxKUn5eD2+Xlw3nrK3T58/gCBoPna9sIqnv9ma6POYxiQ6nIQH2PD5bAR77TictiIq/ka77ThcliJq/naMyuBU7qmH8dPJtIMbA5o09vcGhIIQNkus3eqaMu+4YF71sGeDWbvVe29rY7ourHmvbIccWaPlmHZt1ntWG0xnFJSifXVF81j7C7zeHtsnccuczGM/ffZY80Qh2EOhUxsp4UyRCSqKTiJSJO5cngnrhzeKfQ8EAhS4fHx7aZCvlxfQFGlF18ggM8fxB8I4guYX8vdPgrK3OSVVuMLBNlb4WFvRcPzqBpy8YntuP2Cfjj1P8+lpbJYzOF4Se2h02n1XwsGzXlXZbvBU2EOEXSXmUMEy/PNRS7K8+o/9laa7/VV7QtdDV0WyABY/+OxfwZbjLkAhtUOGHUWwjDAYN8+RwLEZ5hBLRg0A1hyR3MFQ0eceR57bM1XlxnKbLH7vmoemIgcJ/rXRUSOG4vFICHGzsg+mYzsk3nY4wOBIIWVHgrK3FR6fJS7/VS6fVR4/DXPfVS6/VR4zK9FlR7mrc7jzaU7WbylkN+O6Iwj0AwfTCSSGEbj517V8lSYi1h4K8y5V55KCPggGNi3+T34qstZtnghg/r1xBbwmO/zVpnBy1u13+P991WaIS4YNN/nqzbnch1vFnudYBV74GNHXP0l42sfW+xmT5vFan5PQ71v1pp9NV/rPgbz85kPGn7eqGNqbgSd2A6cCTV12GquZ6vTG6i5oiLhpOAkIhHDYjFIj3eSHt/4Se6LtxTyh1eWsb2wir++/SOxVitPbvmajIQYxg/M5sIT2uG0aXiQSD2OOHMz+5MOKuj1snMjDBw0DuzHcONfv89cgbBkR00wC1I/RARrntbcT6uioKZXzDB7z4q3QllNT5mv2gxntV+9VeacsFoBL7i95kIcLY3FZobA2FSITTKHQlpsYLFjNSycvLcY65wXakJhfE071wmI9pj6wzEP2Azzfc4EcNYs42+r857a0Fj3cW3QFGkFFJxEJKqd1CmVD/84gpe/3cYzCzazu6SatXnlrM0r56sNe/jHR+vo1y6JxBgbibF2EmPsJMbaar6ai110SHWRk+oK90cRabmstpql1bscn/MHAmaQ8lXX9HZVm0MQQ1/rbjW9bZ6Kmsc1z4N+CPjr97oFgzU9cbWv+c1r1e6jJjDUHXbY0PNDHoN5rbLdULKzfgg84HP69t1HbL97NVuATICyH47wm9cUjAbClOUg+6zm0NMDAthBevgOGtr232czh4HanGB11nnsMJf2j8/ct3iKxW7+TFrs5nEWm7nfat/32v7XqhsupdVScBKRqBfvtDFlRBeuGNqOZ9/8gD4nDGNNXgWzv95MXqmbT9bkH/YcQzuncvEJ7eiZlUDn9DiSXY5mqFxEmoTFUtOz4gKOYMhiJAoGzZAW8NUPbbXPvVXmnLaqYrN3LeADvxef180P3y9lQP8++4ZVhrbyfYGS4H7hsM4W8JvHu8vMHrvq0kMHuX1Fm3X6/cf5mxMhjP3D1H7ByjAIhUnDqGkjH/g92PweLiBIcLlt3zDMukMyLQ3srztMdP/nhrXOsVYzAMa1gYSsmsVZgmZ7VhWbbdTg9fZ7blhCP1fmz1jN/ySw1Am2DdZRt546x9b+bNV+NeoE7R5jzSG0UULBSURaDLvVQvs4OK1bGmf1zuKa0zqzYMMeCsrclFZ7KanyUlrlpbTaF3pcUuVlY0E5izYXsmjzvgnybZNi6NM2iS4ZcXRMczG0Uyrd2sTrflQicnwZhtnjcYSLXAS9XrZvc9H/WIdVNnjyYJ0et5qv+/8xHNzvcSDQwD6/ea56PXi1vXx13lNv337X2r/3L7TPDCb4POZXvwd8bjP4VRWbi6K4y80g4PfWDwZ+777HwUZMlA3WXP8ohPoda4Nwa/endQpOIiKRwGGzcFavw99DZ3dJFa99t4OvNuxh295Kckur2VVibqzed1zHNBeXD+3A5FM7ad6UiLQetWGuNfzZGAjsC1ANDd0M7r9v/6Gdfvb16tXM3zOs5jBAqwNv0GD+/E84+ydnYrdQ05NYp0ex9nnd3p79h4jWHh8M7Du+Njz6PFCea66iWRvMHPEQm2wOQ6x7jf2vWbeX01I7lLGmF4raWusE1brht24N9Z77DxxeCfu+t1F24+5W8BsgInJo2Umx/P7s7vz+7O4AlFV7Wb27jB93lbBlbyUb8s0eqa17K7n7/TXMWbydq0/rTPc28fTOTjzoTYFFRCTKWCxgOY5/zHu9uO1JkJDd9D2DctwpOImI7Cchxs7QzqkM7bxvrkSF28d7K3Zz34dr2byngr+9vRIAh9XCqL6ZjB+QTef0eHJSY3E59E+riIhIS6P/uouINEKc08alQ3I4p18Wz3y1haXbitiQX87O4ire+2E37/2wGwCrxWBop1TO7JlBdnIs6fEOTuqUit2qu/OKiIhEMwUnEZEjkBBj5/qR3UPPV+4s4dXvtrN4SxE7iyoprfaxcNNeFm7aGzqmV1YC9/9sIP3aJYWjZBEREWkCCk4iIsegX7ukeoFo694K5q3O57sthRRVeli9u4w1uWVc8OgCLj6hHT8d3J6TOqVisWh1PhERkWii4CQi0oQ6psVxzWmduea0zgDsKXdz639X8d6K3by2ZAevLdlBpzQXvzi5Iz8d3F73ixIREYkSGnQvInIcpcc7efSKE3ntN8OZMCSHeKeNLXsr+ft7qxl213xufG05y7YXEwwGw12qiIiIHIJ6nEREmsFJnVI5qVMqt4zvw3+X7eL5b7ayendpqBeqR2Y8lw7J4dKTckiM0RK1IiIikUbBSUSkGcU5bfx8WAcuH5rD0m3FvPDNVuau2M26vHL+/t5qZs1bz8+GtGdQTjLd2yTQOzsBw9B8KBERkXBTcBIRCQPDMBjcMYXBHVOYcX5f3v1hF7MXbGF9fjnPLtgSOm5g+ySm/qQ7gzumkBRrx6pFJURERMJCwUlEJMySYu1cMawjl5/Ugc/W5fPRqjw2FpSzYmcJy3eUMOW57wCwGDCkYyoXntCO8wZma0ifiIhIM1JwEhGJEBaLwU96ZfKTXpmAuSLfU19u5rXvtrO3wkMgCIu2FLJoSyH3fbiGG8f0YsJJOeqFEhERaQYKTiIiESo93slfzunFX87phdcfILekmrkrdjNn8XY27angr2+tYPbXm7nmtM5cMKgdMXZruEsWERFpsRScRESigN1qISfVxa/P6MrVp3XmhW+28sDH61iXV85Nb6zgb2+voktGHP3aJXHV8I4MaJ8c7pJFRERaFAUnEZEoY7damHxqZy4+sT2vLt7O7K+3sLO4ijW5ZazJLeP1JTsY3iWN35zZlRHd07Uqn4iISBNQcBIRiVJJsXamjOjCNad1ZmdxFevyynjvh928s3wXCzftZeGmvfTKSmB0n0yGdEplWJdUnDYN5xMRETkaCk4iIlHOYjHISXWRk+ri7N6Z/GlMT57+cjOvLN4W6oUCSI1z8LMh7fnZ4By6tYkPc9UiIiLRRcFJRKSFaZccyy3j+/D7s7sxd0Uu320pZMHGPeSVuvnX55v41+eb6JmZwMg+bTi5SxpDOqYS61BPlIiIyKEoOImItFDJLgc/H9aBnw/rgM8f4JM1+byyeDtfrCtgbV4Za/PKePTTjbgcVsb2y+LiE9ozvGualjcXERFpgIKTiEgrYLNaGN03i9F9syip9DJvdR4LNu5h4ca97C6p5s2lO3lz6U6yEmM4f1BbRvXJ5IScZGxWS7hLFxERiQgKTiIirUySy84lg9tzyeD2BINBlm4r5s2lO/jf8l3kllbz7y828e8vNpEYY6N3diI9sxIY3DGFYZ3TyEqKCXf5IiIiYaHgJCLSihmGweCOKQzumMIt4/vw6Zp83l+Zy2drCyip8vLt5kK+3VzIcwu3AjAoJ5nLTsrhvIFtiXfqPyEiItJ66L96IiICgNNmZWy/bMb2y8bnD7Amt4x1eWWs2lXKos2FrNpVwrLtxSzbXszt7/7Iuf2zGTcgm0Htk0mJc4S7fBERkeNKwUlERA5gs1ro1y6Jfu2SuPhEc19BmZs3l+5gzuLtbNpTwWtLdvDakh0AdEpzMTAnmSEdUzi7dyZtk2PDWL2IiEjTU3ASEZFGyUhw8uszuvKrEV34bmsRr3+3g0VbCtm8p4IteyvZsreS/y7bxd/+u4p+7RIZ1jmNEzokk5kYQ3q8kw6pLq3YJyIiUUvBSUREjohhGJzUKZWTOqUCUFzpYfmOEpZtK+bL9QUs2VbEyp2lrNxZWu99LoeV/u2S6JGZQE5KDAWFBt3zy+melYRdq/eJiEiEU3ASEZFjkuxycEaPDM7okcH1I7tTUObm6417WLylkFW7Sims8JBf6qbS4w8tNmGy8uTar0mMsTGmbxZn9mxD98x4OqS6iLHrhrwiIhJZFJxERKRJZSQ4uWBQOy4Y1C60zx8IsrGgnOXbi9myt4LNBeX8sDmXIp+N0mpfvflSACkuO5mJMbRJjKFdcgxj+2VzWrd0DfUTEZGwUXASEZHjzmox6JGZQI/MBAC8Xi9z5+5kzNjRLNtZxtwVu1m+vZiNBRWUu30UVXopqvSyJrcMgJcXbadtUgwnd0mjT9tETuyYQv92GuInIiLNR8FJRETCxmoxOLlLGid3SQMgGAxSXOklv8xNXmk1eaXVrNxZwtvLdrGrpJo3v9/Jm9/vBMw5U93bxNM2OZaeWQmc1i2dAe2TcdgUpkREpOkpOImISMQwDIOUOAcpcQ56Zpm9Uz8bksP0cb1ZsGEPK3eWsmJnCd9tLaS40svyHSUs31HC+ytzmTVvPQBJsXYyE510axNPtwwzWLVNjmVgTjJJsfZwfjwREYliCk4iIhLxYuxWzu6dydm9MwEIBIJsKChny54KthdVsXRbEV9v2ENRpZeSKnNbl1de7xwWA/q1S6JXVgId0+LonB5HxzQXiTH20DVSXHZsGv4nIiINUHASEZGoY9lvztQ1dCYQCFJU6aGwwsOO4io25JWzaU8FuSVVbNpTwda9lfywo4QfdpQc8typcQ7ap8TSPiWWnBQXndLj+EmvNmQmxjTHRxMRkQil4CQiIi2CxWKQFu8kLd5J98wEzurZpt7ru0uqWLyliM0FFWzZa25b91ZS5fETJEi1NwBAYYUZvuoGLMOAYZ1TGT+wLeP6ZZMS52jWzyYiIuGn4CQiIq1CdlIs5w+MPejrPn+A4iov+aVudhRVsqOoiu1FlSzbXsz324r5ZlMh32wq5Jb/riI93kFyrINkl50Ul4POGXEM7pBCn7aJtElwarifiEgLpOAkIiIC2KwW0uOdpMc76dM2sd5r2wsreW/Fbt5Ztosfd5eSV+omr9Td4HksBmQmxtA2OZZOaXGM7ZfFiB7pOG26qa+ISDRTcBIRETmMnFQXvzmjK785oyu5JdXsKXdTVOmhuNJLYYWH1btLWbK1iM17KvAFguwuqWZ3STVLthbxxtIdOG0W4pw2HFYLHVJddG0TR2KsHafVQpLLQUaCk4x4JxkJThJjbFgsBokxdi2tLiISQRScREREjkBWUgxZSQ0vFBEIBNlT7mZXSTW7iqtYsrWI/y3fRX6ZG7fPA0BuaTWLthQe9jrJLjv3XDKAMX2zmrR+ERE5OgpOIiIiTcRiMWiTGEObxBgG5SQzrn82fx3Xm22FlXj9ASo9frbsqWDzngoqPT6qvQGKKj0UlLkpKHdTUOamwu0jEITiSi+/fn4Jk0/txIjuGWQnx5CdFEtijA3DMML9UUVEWh0FJxERkePIajHonB4Xej4oJ/mw7/H6A9z9/hqe/mozzy7YwrMLtoReS3DaGN41jTF9s+jWJp7EWDtJsXYSY2xalEJE5DhScBIREYkwdquFv53Xh6GdU3ntux3sKq5id0kVRZVeytw+Pvoxj49+zDvgfQ6rBavFIDXOwYD2SQxon8zA9kn0a58UutGviIgcHQUnERGRCDWmb1a9OU6VHh8b8yv4eHUen6/Np6DMTWm1j3K3DwCPPwB+2Flcxc7iKt5fmRt6b5eMOPq2TSLeacVps9I2OYaOaXHEOcw/BWIdVpJibSTG2EmMtRNj1yqAIiJ1KTiJiIhECZfDRv/2SfRvn8S0UT1C+33+AKXVPtw+Pz5/kO1Flfywo4QfdhSzfHsJO4ur2FRQwaaCikZfy2GzmPOpfFYe3/Q1TocNp80S2uxWC446Xx2h5wYOqxW7zQjti3PYyEl10S4llhhbzfE179F8LRGJFgpOIiIiUc5mtZAa5wg9z0l1cUrX9NDzPeVuVuwoYX1+GW5vgEqvn+2FlWwrrMTjCxAMQqXXR2mVj9JqL8EgeHwB9pR7AIOC6vLjVnttuKobvuo+bpccy8+GtGdE9wwsFoUsEQkfBScREZEWLj3eyVm92nBWrzaHPTYQCFLu8VFa5aWwrJp5n3/JCUOG4Q8auH0B3D4/Hl8Arz+Axx/c97jmq3u/515/kOIqD9sKK8krcZvDCevw+APmvobvJ8yy7cW8t2I36fEOEmLsOG3mvbA6prlw2qwYBqTFOWiX4iLFZQ4xzEqKIT3e2RTfOhGREAUnERERCam9+W5ijJ3MeDubE+G0bmnY7U2zuEQgEAyFJY/P3Ny+fY89fn/oudsX4JtNe3l9yQ72lHtqesBgTW7ZYa+THu8gKykGAwOHzUJanPm8R2YCvbMT6ZWVQJxTfwaJSOPpXwwRERFpNhaLQYzF2ujFJ8b0zeLGMT1Zl1eOzx+g3O1j695KthdW4gsECQSD5Je62VlcRVm1lwqPnz3l7npBqyGGATkpLlwOK1aLgdViYDHMr1bDwGIhtM883sCoeZ8ROoeBxYB4p42kWDt2qwWLxag5xnzNMMBqsRwwP6zu1C4Dg4wEJ22TY3E5rFgsBunxDpw2LdAhEkkUnERERCSiuRy2Rt3/qlalx8f6vHIKK83gVO3xs6fCw46iStbsLmP17lLyy9xsK6w8ThUfO4fNQr+2iXRMizODWk0Yc9otZCfG0CbRGQp1AIGAn01FBl1zy8hJT9CNkkWOAwUnERERaVFcDhsDDxO09pa72VhQgdvnx1/Tc+UPgD8QML8GgwRq9geDEASCwSDB2hMEIYj5nnK3l9IqH96AudBGMBgkECT0Xl+g/rBE737zvHyBIHmlbnaXVFHtNevx+AIs3VbM0m3FR/DJrfxrzUJgXy+Y027BabMSY7dgt1jAAKfNQsc0Fx1T44ixW7BaLNisBnargdViwW4xQot0OG1WnDbz9dreOMOo+5hQj51hgNWofVy/985i1D5WmJPopeAkIiIirU5avJO0CF1AIhgMsnVvJUu3FbGn3F0nuEGVx8fukmr2VngIBkMxDp8/wKZde6gIOiiu8lLu3nd/r4Z8ub4ZPshBWIx9wyBrh0daDHMYZ224stSEMItlv2NqHsc5bfTIjKdrRjwOm3nj5xSXg/R4J72yE3TDZzkuFJxEREREIohhGHRKj6NTelyj3+P1epk7dy7jxp2FN2iwu6Sasmofbq+fal8At9eP128GrQqPj817KthZVBVa+dAfCOALBPH6A/j8wdAKiXV7yQI1PWn+gNkb5w+aPXKB2h66mh62wwkEIeAPAo04+BCWbC1qcL/FgF5ZiWQlxWC1GHRMdXFq93R6ZiZgGBBjs5IUa1fvlxwxBScRERGRFsTlsNE1Iz4s1w4GgzVDH6kZ/nhguKoNXf6AGbT8Nc+DoeGSNccd4lxFlR7W5paxtbAytFJjUYWH3SXV7Cyu4sfdpfy4uzRU11Nfba5Xp81ikBhrx2KY9xLrlplAr6wEYu3WUI9WQowNh9VS730Om4WkWDtJsebKk/ExNmxWA1vNcEW7xaJA1oIpOImIiIhIkzAMA5u1eYLD+IEN788rrWbp1iKzx80fYOWOEr7asIf8smoAvP4gvkCQwop9qy7uKqnmi3UFTVKXYRAKUjaLpearEZoL5qm28uC6r7BZLXWO2/d6Q++z1cw/q30eY7eQ6jLvbWYYZqDrlZVI37aJWmb/ONJ3VkRERERajMzEGM7pn33Q1z2+AIUVHkqqvAQJUuH2sSa3jA355Xj9AfyBIOVuP6VVXvyB+sMJ3T4/JVXe0FbtDRxw/mDQDGfm0MgDXweDve7jt6JjapyDNglOnDaztyzWYa3XS5aR4KRDqos2ic5QQKsX0iwWrDW9aDE2KzEOCw6rRas0ouAkIiIiIq2Iw2YhKymGrKSY0L7BHVOP6lw+fyA07NAXCOKv6c0yn5vzxUKv+4O4PV6++Oorhp08HCzWfe+rPTZQ9/375p7562y+gBn2iio9lFebC4CUVftYtauU3NJqCis89XrTmoLVYhBrtxLrsBJrt+JymPdii7FbcNisOKzmPcocNjNkmas57luZ0RG6j1ndxxZG9Mho9D3dIoGCk4iIiIjIUbBZLUf0x7TX62VbAgzumILd3vQr/xVXmvO88kqrQ3PIKjw+Sqt9lNb0kuWWVLO1sJKiCk+9MGYuxb/veW1gA2p64Q69UuPRWPTXsxWcRERERESkeSW7HCS7HPTOTmyS83n9ASo9fqq9fqo8fio9fqpqHld5zc3rC+Dx77tXmcdvruLo9gdwe+uuzuiv99jjCxDjiJ7QBApOIiIiIiLSALvVQlKsuZKggOXwh4iIiIiIiLRuYQ9Ojz76KJ06dSImJoZhw4axaNGigx67atUqLrnkEjp16oRhGMyaNav5ChURERERkVYrrMFpzpw5TJs2jVtvvZWlS5cycOBAxowZQ35+foPHV1ZW0qVLF+6++26ysrKauVoREREREWmtwhqcHnjgAaZMmcLkyZPp06cPTzzxBC6Xi2eeeabB40866STuu+8+LrvsMpxOZzNXKyIiIiIirVXYFofweDwsWbKE6dOnh/ZZLBZGjhzJwoULm+w6brcbt9sdel5aWgqYy0F6vd4mu87Rqq0hEmqRg1M7RQe1U/RQW0UHtVP0UFtFB7VT5DmStghbcNqzZw9+v5/MzMx6+zMzM1mzZk2TXWfmzJncdtttB+z/6KOPcLlcTXadY/Xxxx+HuwRpBLVTdFA7RQ+1VXRQO0UPtVV0UDtFjsrKykYf2+KXI58+fTrTpk0LPS8tLSUnJ4fRo0eTmNg0a9wfC6/Xy8cff8yoUaOOy43QpGmonaKD2il6qK2ig9opeqitooPaKfLUjkZrjLAFp/T0dKxWK3l5efX25+XlNenCD06ns8H5UHa7PaJ+YCOtHmmY2ik6qJ2ih9oqOqidoofaKjqonSLHkbRD2BaHcDgcDB48mPnz54f2BQIB5s+fz/Dhw8NVloiIiIiIyAHCOlRv2rRpTJw4kSFDhjB06FBmzZpFRUUFkydPBuCqq66iXbt2zJw5EzAXlPjxxx9Dj3fu3MmyZcuIj4+nW7duYfscIiIiIiLSsoU1OE2YMIGCggJuueUWcnNzGTRoEB988EFowYht27ZhsezrFNu1axcnnHBC6Pn999/P/fffzxlnnMFnn33W3OWLiIiIiEgrEfbFIaZOncrUqVMbfG3/MNSpUyeCwWAzVCUiIiIiIrJPWG+AKyIiIiIiEg0UnERERERERA5DwUlEREREROQwFJxEREREREQOQ8FJRERERETkMBScREREREREDiPsy5E3t9rlzEtLS8Ncicnr9VJZWUlpaSl2uz3c5chBqJ2ig9opeqitooPaKXqoraKD2iny1GaCxtzyqNUFp7KyMgBycnLCXImIiIiIiESCsrIykpKSDnmMEWxld5QNBALs2rWLhIQEDMMIdzmUlpaSk5PD9u3bSUxMDHc5chBqp+igdooeaqvooHaKHmqr6KB2ijzBYJCysjLatm2LxXLoWUytrsfJYrHQvn37cJdxgMTERP0CRQG1U3RQO0UPtVV0UDtFD7VVdFA7RZbD9TTV0uIQIiIiIiIih6HgJCIiIiIichgKTmHmdDq59dZbcTqd4S5FDkHtFB3UTtFDbRUd1E7RQ20VHdRO0a3VLQ4hIiIiIiJypNTjJCIiIiIichgKTiIiIiIiIoeh4CQiIiIiInIYCk4iIiIiIiKHoeAURo8++iidOnUiJiaGYcOGsWjRonCX1KrNmDEDwzDqbb169Qq9Xl1dze9+9zvS0tKIj4/nkksuIS8vL4wVtx5ffPEF48ePp23bthiGwdtvv13v9WAwyC233EJ2djaxsbGMHDmS9evX1zumsLCQK664gsTERJKTk7nmmmsoLy9vxk/R8h2unSZNmnTA79jYsWPrHaN2Ov5mzpzJSSedREJCAm3atOHCCy9k7dq19Y5pzL9327Zt49xzz8XlctGmTRtuvPFGfD5fc36UFq8xbXXmmWce8Hv1m9/8pt4xaqvj6/HHH2fAgAGhm9oOHz6c999/P/S6fp9aDgWnMJkzZw7Tpk3j1ltvZenSpQwcOJAxY8aQn58f7tJatb59+7J79+7Q9tVXX4Ve++Mf/8j//vc/XnvtNT7//HN27drFxRdfHMZqW4+KigoGDhzIo48+2uDr9957Lw899BBPPPEE3377LXFxcYwZM4bq6urQMVdccQWrVq3i448/5t133+WLL77gV7/6VXN9hFbhcO0EMHbs2Hq/Yy+//HK919VOx9/nn3/O7373O7755hs+/vhjvF4vo0ePpqKiInTM4f698/v9nHvuuXg8Hr7++mv+85//MHv2bG655ZZwfKQWqzFtBTBlypR6v1f33ntv6DW11fHXvn177r77bpYsWcJ3333HT37yEy644AJWrVoF6PepRQlKWAwdOjT4u9/9LvTc7/cH27ZtG5w5c2YYq2rdbr311uDAgQMbfK24uDhot9uDr732Wmjf6tWrg0Bw4cKFzVShBIPBIBB86623Qs8DgUAwKysreN9994X2FRcXB51OZ/Dll18OBoPB4I8//hgEgosXLw4d8/777wcNwwju3Lmz2WpvTfZvp2AwGJw4cWLwggsuOOh71E7hkZ+fHwSCn3/+eTAYbNy/d3Pnzg1aLJZgbm5u6JjHH388mJiYGHS73c37AVqR/dsqGAwGzzjjjOD1119/0PeorcIjJSUl+NRTT+n3qYVRj1MYeDwelixZwsiRI0P7LBYLI0eOZOHChWGsTNavX0/btm3p0qULV1xxBdu2bQNgyZIleL3eem3Wq1cvOnTooDYLs82bN5Obm1uvbZKSkhg2bFiobRYuXEhycjJDhgwJHTNy5EgsFgvffvtts9fcmn322We0adOGnj178tvf/pa9e/eGXlM7hUdJSQkAqampQOP+vVu4cCH9+/cnMzMzdMyYMWMoLS0N/V92aXr7t1WtF198kfT0dPr168f06dOprKwMvaa2al5+v59XXnmFiooKhg8frt+nFsYW7gJaoz179uD3++v9ggBkZmayZs2aMFUlw4YNY/bs2fTs2ZPdu3dz2223cfrpp7Ny5Upyc3NxOBwkJyfXe09mZia5ubnhKVgAQt//hn6fal/Lzc2lTZs29V632Wykpqaq/ZrR2LFjufjii+ncuTMbN27kr3/9K+eccw4LFy7EarWqncIgEAjwhz/8gVNPPZV+/foBNOrfu9zc3AZ/52pfk6bXUFsB/PznP6djx460bduWH374gZtuuom1a9fy5ptvAmqr5rJixQqGDx9OdXU18fHxvPXWW/Tp04dly5bp96kFUXASqXHOOeeEHg8YMIBhw4bRsWNHXn31VWJjY8NYmUjLcNlll4Ue9+/fnwEDBtC1a1c+++wzzj777DBW1nr97ne/Y+XKlfXmc0pkOlhb1Z0D2L9/f7Kzszn77LPZuHEjXbt2be4yW62ePXuybNkySkpKeP3115k4cSKff/55uMuSJqahemGQnp6O1Wo9YEWVvLw8srKywlSV7C85OZkePXqwYcMGsrKy8Hg8FBcX1ztGbRZ+td//Q/0+ZWVlHbDwis/no7CwUO0XRl26dCE9PZ0NGzYAaqfmNnXqVN59910+/fRT2rdvH9rfmH/vsrKyGvydq31NmtbB2qohw4YNA6j3e6W2Ov4cDgfdunVj8ODBzJw5k4EDB/LPf/5Tv08tjIJTGDgcDgYPHsz8+fND+wKBAPPnz2f48OFhrEzqKi8vZ+PGjWRnZzN48GDsdnu9Nlu7di3btm1Tm4VZ586dycrKqtc2paWlfPvtt6G2GT58OMXFxSxZsiR0zCeffEIgEAj9kSHNb8eOHezdu5fs7GxA7dRcgsEgU6dO5a233uKTTz6hc+fO9V5vzL93w4cP5//bubOQKNs+juO/aRnJTKdwMIupKTLKkrIN7MAixQoK60STsLIobDkQtKiDIKIdkjaio7IiqCBI6KAesxSUFi3bo6jG7EASi0LR1vk/B/EOzzxG0/u+6Zh9P3CD3su13Bf3yM/rmvv+/ftBQbesrEzR0dFKTEzsmo78AUKN1ffcuXNHkoKeK8aq6/n9fn38+JHnqacJ99sp/lSnT5+2iIgIKykpsUePHtmqVavM5XIFvVEFXauwsNAqKirM5/NZdXW1paenW2xsrDU1NZmZWX5+vg0bNsyuXLlitbW1lpKSYikpKWFu9Z+hpaXF6urqrK6uziRZcXGx1dXV2cuXL83MbNeuXeZyuay0tNTu3btnmZmZNmLECGtvbw+UMWfOHEtOTrYbN25YVVWVJSQkWE5OTri61CP9aJxaWlqsqKjIrl27Zj6fzy5fvmyTJk2yhIQE+/DhQ6AMxqnzrV692mJiYqyiosIaGxsDW1tbW+CcUJ93X758sfHjx1tGRobduXPHLl68aG632zZt2hSOLvVYocbq2bNntnXrVqutrTWfz2elpaU2cuRIS01NDZTBWHW+jRs3WmVlpfl8Prt3755t3LjRHA6H/fXXX2bG89STEJzC6ODBgzZs2DBzOp02bdo0u379erib9EfLzs62+Ph4czqdNnToUMvOzrZnz54Fjre3t9uaNWts4MCBFhkZaQsXLrTGxsYwtvjPcfXqVZPUYVu6dKmZfXsl+ebNmy0uLs4iIiIsLS3Nnjx5ElTGmzdvLCcnx6Kioiw6Otry8vKspaUlDL3puX40Tm1tbZaRkWFut9v69u1rw4cPt5UrV3b4ZxHj1Pm+N0aS7NixY4Fzfubzrr6+3ubOnWv9+vWz2NhYKywstM+fP3dxb3q2UGPV0NBgqampNmjQIIuIiLBRo0bZ+vXr7f3790HlMFada/ny5TZ8+HBzOp3mdrstLS0tEJrMeJ56EoeZWdfNbwEAAADA74fvOAEAAABACAQnAAAAAAiB4AQAAAAAIRCcAAAAACAEghMAAAAAhEBwAgAAAIAQCE4AAAAAEALBCQAAAABCIDgBAPADXq9X+/btC3czAABhRnACAHQby5Yt04IFCyRJM2fOVEFBQZfVXVJSIpfL1WF/TU2NVq1a1WXtAAB0T33C3QAAADrTp0+f5HQ6/+fr3W73L2wNAOB3xYwTAKDbWbZsmSorK7V//345HA45HA7V19dLkh48eKC5c+cqKipKcXFxys3NVXNzc+DamTNnat26dSooKFBsbKxmz54tSSouLlZSUpL69+8vj8ejNWvWqLW1VZJUUVGhvLw8vX//PlDfli1bJHVcqtfQ0KDMzExFRUUpOjpaWVlZev36deD4li1bNHHiRJ08eVJer1cxMTFatGiRWlpaOvemAQA6FcEJANDt7N+/XykpKVq5cqUaGxvV2Ngoj8ejd+/eadasWUpOTlZtba0uXryo169fKysrK+j648ePy+l0qrq6WkeOHJEk9erVSwcOHNDDhw91/PhxXblyRRs2bJAkTZ8+Xfv27VN0dHSgvqKiog7t8vv9yszM1Nu3b1VZWamysjK9ePFC2dnZQec9f/5c58+f14ULF3ThwgVVVlZq165dnXS3AABdgaV6AIBuJyYmRk6nU5GRkRo8eHBg/6FDh5ScnKwdO3YE9h09elQej0dPnz7V6NGjJUkJCQnas2dPUJn//L6U1+vVtm3blJ+fr8OHD8vpdComJkYOhyOovn8rLy/X/fv35fP55PF4JEknTpzQuHHjVFNTo6lTp0r6FrBKSko0YMAASVJubq7Ky8u1ffv2/+/GAADChhknAMBv4+7du7p69aqioqIC25gxYyR9m+X5j8mTJ3e49vLly0pLS9PQoUM1YMAA5ebm6s2bN2pra/vp+h8/fiyPxxMITZKUmJgol8ulx48fB/Z5vd5AaJKk+Ph4NTU1/Vd9BQB0L8w4AQB+G62trZo/f752797d4Vh8fHzg5/79+wcdq6+v17x587R69Wpt375dgwYNUlVVlVasWKFPnz4pMjLyl7azb9++Qb87HA75/f5fWgcAoGsRnAAA3ZLT6dTXr1+D9k2aNEnnzp2T1+tVnz4//yfs1q1b8vv92rt3r3r1+rbY4uzZsyHr+7exY8fq1atXevXqVWDW6dGjR3r37p0SExN/uj0AgN8PS/UAAN2S1+vVjRs3VF9fr+bmZvn9fq1du1Zv375VTk6Oampq9Pz5c126dEl5eXk/DD2jRo3S58+fdfDgQb148UInT54MvDTin/W1traqvLxczc3N313Cl56erqSkJC1evFi3b9/WzZs3tWTJEs2YMUNTpkz55fcAANB9EJwAAN1SUVGRevfurcTERLndbjU0NGjIkCGqrq7W169flZGRoaSkJBUUFMjlcgVmkr5nwoQJKi4u1u7duzV+/HidOnVKO3fuDDpn+vTpys/PV3Z2ttxud4eXS0jfltyVlpZq4MCBSk1NVXp6ukaOHKkzZ8788v4DALoXh5lZuBsBAAAAAN0ZM04AAAAAEALBCQAAAABCIDgBAAAAQAgEJwAAAAAIgeAEAAAAACEQnAAAAAAgBIITAAAAAIRAcAIAAACAEAhOAAAAABACwQkAAAAAQiA4AQAAAEAIfwNKvOR9TujAmAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evals_result = final_model.get_evals_result()\n",
    "\n",
    "# Menampilkan skor terakhir\n",
    "train_score = evals_result['learn']['Logloss'][-1]\n",
    "val_score = evals_result['validation']['Logloss'][-1]\n",
    "\n",
    "print(f\"Final Training Logloss: {train_score}\")\n",
    "print(f\"Final Validation Logloss: {val_score}\")\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Ambil skor training dan validation dari evals_result\n",
    "train_logloss = evals_result['learn']['Logloss']\n",
    "val_logloss = evals_result['validation']['Logloss']\n",
    "\n",
    "# Plot learning curve\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(train_logloss, label='Training Logloss')\n",
    "plt.plot(val_logloss, label='Validation Logloss')\n",
    "plt.xlabel('Iteration')\n",
    "plt.ylabel('Logloss')\n",
    "plt.title('Learning Curve')\n",
    "plt.legend()\n",
    "plt.grid()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Final Training Logloss: 0.11638732557293754\n",
      "Final Validation Logloss: 0.1740072208615152\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "evals_result = model.get_evals_result()\n",
    "\n",
    "# Menampilkan skor terakhir\n",
    "train_score = evals_result['learn']['Logloss'][-1]\n",
    "val_score = evals_result['validation']['Logloss'][-1]\n",
    "\n",
    "print(f\"Final Training Logloss: {train_score}\")\n",
    "print(f\"Final Validation Logloss: {val_score}\")\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Ambil skor training dan validation dari evals_result\n",
    "train_logloss = evals_result['learn']['Logloss']\n",
    "val_logloss = evals_result['validation']['Logloss']\n",
    "\n",
    "# Plot learning curve\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(train_logloss, label='Training Logloss')\n",
    "plt.plot(val_logloss, label='Validation Logloss')\n",
    "plt.xlabel('Iteration')\n",
    "plt.ylabel('Logloss')\n",
    "plt.title('Learning Curve')\n",
    "plt.legend()\n",
    "plt.grid()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0:\ttotal: 115ms\tremaining: 1m 54s\n",
      "200:\ttotal: 19s\tremaining: 1m 15s\n",
      "400:\ttotal: 39s\tremaining: 58.2s\n",
      "600:\ttotal: 59.1s\tremaining: 39.2s\n",
      "800:\ttotal: 1m 18s\tremaining: 19.5s\n",
      "999:\ttotal: 1m 39s\tremaining: 0us\n",
      "0:\ttotal: 151ms\tremaining: 2m 30s\n",
      "200:\ttotal: 19.3s\tremaining: 1m 16s\n",
      "400:\ttotal: 38.8s\tremaining: 57.9s\n",
      "600:\ttotal: 58.1s\tremaining: 38.6s\n",
      "800:\ttotal: 1m 17s\tremaining: 19.4s\n",
      "999:\ttotal: 1m 38s\tremaining: 0us\n",
      "0:\ttotal: 120ms\tremaining: 2m\n",
      "200:\ttotal: 18.3s\tremaining: 1m 12s\n",
      "400:\ttotal: 38.7s\tremaining: 57.9s\n",
      "600:\ttotal: 1m 2s\tremaining: 41.3s\n",
      "800:\ttotal: 1m 23s\tremaining: 20.7s\n",
      "999:\ttotal: 1m 45s\tremaining: 0us\n",
      "0:\ttotal: 149ms\tremaining: 2m 28s\n",
      "200:\ttotal: 22s\tremaining: 1m 27s\n",
      "400:\ttotal: 44.4s\tremaining: 1m 6s\n",
      "600:\ttotal: 1m 5s\tremaining: 43.3s\n",
      "800:\ttotal: 1m 25s\tremaining: 21.3s\n",
      "999:\ttotal: 1m 47s\tremaining: 0us\n",
      "0:\ttotal: 117ms\tremaining: 1m 56s\n",
      "200:\ttotal: 21.8s\tremaining: 1m 26s\n",
      "400:\ttotal: 43.6s\tremaining: 1m 5s\n",
      "600:\ttotal: 1m 4s\tremaining: 42.8s\n",
      "800:\ttotal: 1m 24s\tremaining: 21s\n",
      "999:\ttotal: 1m 45s\tremaining: 0us\n",
      "0:\ttotal: 144ms\tremaining: 2m 23s\n",
      "200:\ttotal: 21.3s\tremaining: 1m 24s\n",
      "400:\ttotal: 41.6s\tremaining: 1m 2s\n",
      "600:\ttotal: 1m 2s\tremaining: 41.2s\n",
      "800:\ttotal: 1m 22s\tremaining: 20.4s\n",
      "999:\ttotal: 1m 43s\tremaining: 0us\n",
      "0:\ttotal: 152ms\tremaining: 2m 31s\n",
      "200:\ttotal: 20.5s\tremaining: 1m 21s\n",
      "400:\ttotal: 40.8s\tremaining: 1m\n",
      "600:\ttotal: 1m 1s\tremaining: 40.9s\n",
      "800:\ttotal: 1m 22s\tremaining: 20.5s\n",
      "999:\ttotal: 1m 43s\tremaining: 0us\n",
      "0:\ttotal: 75.4ms\tremaining: 1m 15s\n",
      "200:\ttotal: 20.8s\tremaining: 1m 22s\n",
      "400:\ttotal: 42.3s\tremaining: 1m 3s\n",
      "600:\ttotal: 1m 1s\tremaining: 40.6s\n",
      "800:\ttotal: 1m 19s\tremaining: 19.7s\n",
      "999:\ttotal: 1m 40s\tremaining: 0us\n",
      "0:\ttotal: 67.7ms\tremaining: 1m 7s\n",
      "200:\ttotal: 21.3s\tremaining: 1m 24s\n",
      "400:\ttotal: 42s\tremaining: 1m 2s\n",
      "600:\ttotal: 1m 2s\tremaining: 41.2s\n",
      "800:\ttotal: 1m 21s\tremaining: 20.3s\n",
      "999:\ttotal: 1m 41s\tremaining: 0us\n",
      "0:\ttotal: 122ms\tremaining: 2m 1s\n",
      "200:\ttotal: 20.9s\tremaining: 1m 23s\n",
      "400:\ttotal: 41.3s\tremaining: 1m 1s\n",
      "600:\ttotal: 1m 2s\tremaining: 41.4s\n",
      "800:\ttotal: 1m 22s\tremaining: 20.6s\n",
      "999:\ttotal: 1m 43s\tremaining: 0us\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Scores for each fold: [0.93327909 0.9275834  0.93490643 0.93327909 0.94141579 0.92676973\n",
      " 0.93083808 0.92595606 0.93241042 0.9267101 ]\n",
      "Mean Accuracy: 0.93\n",
      "Standard Deviation: 0.00\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score, StratifiedKFold\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "# Fungsi untuk menghitung skor cross-validation dan visualisasi\n",
    "def cross_validate_and_visualize_accuracy(model, X, y, cv=10):\n",
    "    # Stratified K-Fold untuk mempertahankan distribusi label\n",
    "    skf = StratifiedKFold(n_splits=cv, shuffle=True, random_state=42)\n",
    "\n",
    "    # Hitung skor cross-validation dengan metrik akurasi\n",
    "    scores = cross_val_score(model, X, y, scoring='accuracy', cv=skf)\n",
    "\n",
    "    # Rata-rata dan standar deviasi\n",
    "    mean_score = np.mean(scores)\n",
    "    std_score = np.std(scores)\n",
    "\n",
    "    # Visualisasi hasil cross-validation\n",
    "    plt.figure(figsize=(8, 5))\n",
    "    plt.plot(range(1, cv + 1), scores, marker='o', linestyle='-', color='b', label='Fold Score')\n",
    "    plt.axhline(y=mean_score, color='r', linestyle='--', label=f'Mean Accuracy: {mean_score:.2f}')\n",
    "    plt.fill_between(range(1, cv + 1), mean_score - std_score, mean_score + std_score, color='r', alpha=0.2, label='±1 Std Dev')\n",
    "    plt.title('Cross-Validation Scores (Accuracy)')\n",
    "    plt.xlabel('Fold')\n",
    "    plt.ylabel('Accuracy')\n",
    "    plt.legend()\n",
    "    plt.grid()\n",
    "    plt.show()\n",
    "\n",
    "    # Cetak hasil skor\n",
    "    print(f'Accuracy Scores for each fold: {scores}')\n",
    "    print(f'Mean Accuracy: {mean_score:.2f}')\n",
    "    print(f'Standard Deviation: {std_score:.2f}')\n",
    "\n",
    "# Contoh penggunaan\n",
    "# Ganti model dengan model Anda, misalnya `model`\n",
    "cross_validate_and_visualize_accuracy(model, X, y, cv=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0:\ttotal: 91.9ms\tremaining: 1m 17s\n",
      "100:\ttotal: 6.52s\tremaining: 47.9s\n",
      "200:\ttotal: 13.6s\tremaining: 43.3s\n",
      "300:\ttotal: 20.2s\tremaining: 36.5s\n",
      "400:\ttotal: 27.4s\tremaining: 30.2s\n",
      "500:\ttotal: 34.9s\tremaining: 23.8s\n",
      "600:\ttotal: 43s\tremaining: 17.3s\n",
      "700:\ttotal: 51.9s\tremaining: 10.5s\n",
      "800:\ttotal: 59.6s\tremaining: 3.12s\n",
      "842:\ttotal: 1m 2s\tremaining: 0us\n",
      "0:\ttotal: 67.1ms\tremaining: 56.5s\n",
      "100:\ttotal: 6.46s\tremaining: 47.4s\n",
      "200:\ttotal: 13.8s\tremaining: 44.1s\n",
      "300:\ttotal: 20.8s\tremaining: 37.5s\n",
      "400:\ttotal: 28s\tremaining: 30.9s\n",
      "500:\ttotal: 35.7s\tremaining: 24.4s\n",
      "600:\ttotal: 43.2s\tremaining: 17.4s\n",
      "700:\ttotal: 50.6s\tremaining: 10.3s\n",
      "800:\ttotal: 57.9s\tremaining: 3.04s\n",
      "842:\ttotal: 1m 1s\tremaining: 0us\n",
      "0:\ttotal: 119ms\tremaining: 1m 39s\n",
      "100:\ttotal: 6.62s\tremaining: 48.6s\n",
      "200:\ttotal: 14.1s\tremaining: 44.9s\n",
      "300:\ttotal: 21.3s\tremaining: 38.4s\n",
      "400:\ttotal: 29.4s\tremaining: 32.4s\n",
      "500:\ttotal: 37.3s\tremaining: 25.4s\n",
      "600:\ttotal: 46.3s\tremaining: 18.6s\n",
      "700:\ttotal: 53.2s\tremaining: 10.8s\n",
      "800:\ttotal: 57.6s\tremaining: 3.02s\n",
      "842:\ttotal: 59.2s\tremaining: 0us\n",
      "0:\ttotal: 38.5ms\tremaining: 32.4s\n",
      "100:\ttotal: 3.24s\tremaining: 23.8s\n",
      "200:\ttotal: 9.09s\tremaining: 29s\n",
      "300:\ttotal: 15.5s\tremaining: 27.8s\n",
      "400:\ttotal: 23.5s\tremaining: 25.9s\n",
      "500:\ttotal: 29.2s\tremaining: 19.9s\n",
      "600:\ttotal: 34.1s\tremaining: 13.7s\n",
      "700:\ttotal: 39.6s\tremaining: 8.01s\n",
      "800:\ttotal: 47.6s\tremaining: 2.49s\n",
      "842:\ttotal: 50.8s\tremaining: 0us\n",
      "0:\ttotal: 53.8ms\tremaining: 45.3s\n",
      "100:\ttotal: 8.28s\tremaining: 1m\n",
      "200:\ttotal: 17.5s\tremaining: 55.9s\n",
      "300:\ttotal: 27.1s\tremaining: 48.9s\n",
      "400:\ttotal: 36.4s\tremaining: 40.1s\n",
      "500:\ttotal: 45.7s\tremaining: 31.2s\n",
      "600:\ttotal: 56s\tremaining: 22.6s\n",
      "700:\ttotal: 1m 3s\tremaining: 12.8s\n",
      "800:\ttotal: 1m 11s\tremaining: 3.77s\n",
      "842:\ttotal: 1m 20s\tremaining: 0us\n",
      "0:\ttotal: 55.7ms\tremaining: 46.9s\n",
      "100:\ttotal: 7.81s\tremaining: 57.4s\n",
      "200:\ttotal: 13.5s\tremaining: 43.1s\n",
      "300:\ttotal: 20.5s\tremaining: 36.8s\n",
      "400:\ttotal: 26.3s\tremaining: 29s\n",
      "500:\ttotal: 32.3s\tremaining: 22.1s\n",
      "600:\ttotal: 37.1s\tremaining: 14.9s\n",
      "700:\ttotal: 42s\tremaining: 8.51s\n",
      "800:\ttotal: 46.5s\tremaining: 2.44s\n",
      "842:\ttotal: 48.7s\tremaining: 0us\n",
      "0:\ttotal: 36.6ms\tremaining: 30.8s\n",
      "100:\ttotal: 3.52s\tremaining: 25.8s\n",
      "200:\ttotal: 7.5s\tremaining: 24s\n",
      "300:\ttotal: 11.5s\tremaining: 20.7s\n",
      "400:\ttotal: 15.6s\tremaining: 17.2s\n",
      "500:\ttotal: 20.1s\tremaining: 13.8s\n",
      "600:\ttotal: 24.9s\tremaining: 10s\n",
      "700:\ttotal: 29.6s\tremaining: 5.99s\n",
      "800:\ttotal: 35.1s\tremaining: 1.84s\n",
      "842:\ttotal: 37.2s\tremaining: 0us\n",
      "0:\ttotal: 37.4ms\tremaining: 31.5s\n",
      "100:\ttotal: 4.17s\tremaining: 30.7s\n",
      "200:\ttotal: 9.52s\tremaining: 30.4s\n",
      "300:\ttotal: 14.1s\tremaining: 25.4s\n",
      "400:\ttotal: 18.7s\tremaining: 20.6s\n",
      "500:\ttotal: 24.7s\tremaining: 16.9s\n",
      "600:\ttotal: 33.1s\tremaining: 13.3s\n",
      "700:\ttotal: 40.1s\tremaining: 8.13s\n",
      "800:\ttotal: 45.3s\tremaining: 2.38s\n",
      "842:\ttotal: 47.3s\tremaining: 0us\n",
      "0:\ttotal: 53ms\tremaining: 44.6s\n",
      "100:\ttotal: 3.52s\tremaining: 25.8s\n",
      "200:\ttotal: 8.93s\tremaining: 28.5s\n",
      "300:\ttotal: 13.2s\tremaining: 23.8s\n",
      "400:\ttotal: 17.8s\tremaining: 19.6s\n",
      "500:\ttotal: 22.3s\tremaining: 15.2s\n",
      "600:\ttotal: 27.7s\tremaining: 11.2s\n",
      "700:\ttotal: 32.4s\tremaining: 6.55s\n",
      "800:\ttotal: 36.9s\tremaining: 1.94s\n",
      "842:\ttotal: 39.1s\tremaining: 0us\n",
      "0:\ttotal: 45.1ms\tremaining: 38s\n",
      "100:\ttotal: 5.7s\tremaining: 41.9s\n",
      "200:\ttotal: 15s\tremaining: 47.8s\n",
      "300:\ttotal: 25.4s\tremaining: 45.7s\n",
      "400:\ttotal: 32s\tremaining: 35.3s\n",
      "500:\ttotal: 37.6s\tremaining: 25.7s\n",
      "600:\ttotal: 43.2s\tremaining: 17.4s\n",
      "700:\ttotal: 48.1s\tremaining: 9.73s\n",
      "800:\ttotal: 53.5s\tremaining: 2.8s\n",
      "842:\ttotal: 55.6s\tremaining: 0us\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsQAAAHWCAYAAABwo5+OAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8ekN5oAAAACXBIWXMAAA9hAAAPYQGoP6dpAACwvklEQVR4nOzdd3hTZfvA8W+apk13GYW2rNICLWVTpsqQVakiGwfKUlzgAP2hOMDB+4K+iOKEVwV5BZUhIijDsqeMMmVP2ZQCbelMm5zfH+GkDR20JWna5v5cVy/oyZNznuQk6Z3n3M/9aBRFURBCCCGEEMJJuTi6A0IIIYQQQjiSBMRCCCGEEMKpSUAshBBCCCGcmgTEQgghhBDCqUlALIQQQgghnJoExEIIIYQQwqlJQCyEEEIIIZyaBMRCCCGEEMKpSUAshBBCCCGcmgTEQginMmzYMEJCQqy2aTQa3n333Tve991330Wj0di0P+vXr0ej0bB+/Xqb7lcUbMGCBVSuXJmUlBRHd6VcunbtGl5eXixfvtzRXRHCZiQgFqICO3nyJM8++yyhoaHo9Xp8fX259957mT59Ounp6Y7uXqF2796NRqPh7bffLrDN8ePH0Wg0jB07thR7VjJfffUV33//vaO7YcVkMvG///2Ptm3bUrlyZXx8fGjQoAFDhgzhr7/+cnT37MJoNDJx4kRefPFFvL298709ODgYjUbDihUrHNDDsq9KlSo8/fTTvPPOO47uihA24+roDggh7OOPP/5g4MCBuLu7M2TIEBo3bozBYGDz5s383//9HwcPHuS///2vo7tZoJYtWxIREcFPP/3EpEmT8m3z448/AvDEE0/c1bHS09NxdbXvx+FXX31F1apVGTZsmNX2jh07kp6ejpubm12Pn5+XXnqJL7/8kt69ezN48GBcXV05evQoK1asIDQ0lHbt2pV6n+xt2bJlHD16lGeeeSbf29euXculS5cICQlh3rx59OzZs5R7WD4899xzfPbZZ6xdu5YuXbo4ujtC3DUJiIWogE6fPs2jjz5KnTp1WLt2LUFBQZbbRo0axYkTJ/jjjz8KvL/JZMJgMKDX60ujuwUaPHgw77zzDn/99Ve+wdlPP/1EREQELVu2vKvjOPJxuri4OOT4V65c4auvvmLkyJF5vhh9+umnXL16tdT6kp2djclkKpUvBbNnz+bee++lRo0a+d4+d+5cWrZsydChQ3nzzTdJTU3Fy8vL7v0qrtJ8zvLTsGFDGjduzPfffy8BsagQJGVCiAroo48+IiUlhe+++84qGFbVq1ePl19+2fK7RqNh9OjRzJs3j0aNGuHu7s7KlSsB2LNnDz179sTX1xdvb2+6du2a53J6VlYW7733HvXr10ev11OlShXuu+8+YmNjLW0uX77M8OHDqVmzJu7u7gQFBdG7d2/OnDlT4OMYPHgwkDMSnFtcXBxHjx61tPntt9948MEHCQ4Oxt3dnbCwMD744AOMRuMdn6/8cog3b95M69at0ev1hIWFMXPmzHzvO3v2bLp06UK1atVwd3cnMjKSr7/+2qpNSEgIBw8eZMOGDWg0GjQaDZ07dwYKziFeuHAhUVFReHh4ULVqVZ544gkuXLhg1WbYsGF4e3tz4cIF+vTpg7e3NwEBAbz22mt3fNynT59GURTuvffefJ+PatWqWW1LTExkzJgxhISE4O7uTs2aNRkyZAgJCQmWNvHx8Tz11FNUr14dvV5Ps2bNmDNnjtV+zpw5g0ajYerUqXz66aeEhYXh7u7OoUOHADhy5AgDBgygcuXK6PV6WrVqxdKlS632UZTXW34yMjJYuXIl3bp1y/f29PR0fv31Vx599FEGDRpEeno6v/32W75tV6xYQadOnfDx8cHX15fWrVvneZ1u376dmJgYKlWqhJeXF02bNmX69OmW2zt37mx5HeR2e557Yc+ZwWBgwoQJREVF4efnh5eXFx06dGDdunV59msymZg+fTpNmjRBr9cTEBDAAw88wK5duwDo1KkTzZo1y/fxhoeHEx0dbbWte/fuLFu2DEVR8r2PEOWJjBALUQEtW7aM0NBQ7rnnniLfZ+3atSxYsIDRo0dTtWpVSxDXoUMHfH19GTduHDqdjpkzZ9K5c2c2bNhA27ZtAfNks8mTJ/P000/Tpk0bkpOT2bVrF7t376Z79+4A9O/fn4MHD/Liiy8SEhJCfHw8sbGxnD17Ns8kN1XdunW55557WLBgAZ988glardZymxp8PP744wB8//33eHt7M3bsWLy9vVm7di0TJkwgOTmZ//znP8V6/g4cOECPHj0ICAjg3XffJTs7m4kTJ1K9evU8bb/++msaNWrEww8/jKurK8uWLeOFF17AZDIxatQowDziquasvvXWWwD57kv1/fffM3z4cFq3bs3kyZO5cuUK06dPZ8uWLezZswd/f39LW6PRSHR0NG3btmXq1KmsXr2ajz/+mLCwMJ5//vkCj1GnTh3AHHgPHDgQT0/PAtumpKTQoUMHDh8+zIgRI2jZsiUJCQksXbqU8+fPU7VqVdLT0+ncuTMnTpxg9OjR1K1bl4ULFzJs2DASExOtvoCB+YtERkYGzzzzDO7u7lSuXJmDBw9aRm/feOMNvLy8WLBgAX369OGXX36hb9++QNFeb/mJi4vDYDAUeEVh6dKlpKSk8OijjxIYGEjnzp2ZN2+e5TWW+/yMGDGCRo0aMX78ePz9/dmzZw8rV660tI2NjeWhhx4iKCiIl19+mcDAQA4fPszvv/+e57koqvyes+TkZL799lsee+wxRo4cyc2bN/nuu++Ijo5mx44dNG/e3HL/p556iu+//56ePXvy9NNPk52dzaZNm/jrr79o1aoVTz75JCNHjuTvv/+mcePGlvvt3LmTY8eO5cnnj4qK4pNPPuHgwYNW7YUolxQhRIWSlJSkAErv3r2LfB9AcXFxUQ4ePGi1vU+fPoqbm5ty8uRJy7aLFy8qPj4+SseOHS3bmjVrpjz44IMF7v/GjRsKoPznP/8p+gO55csvv1QAZdWqVZZtRqNRqVGjhtK+fXvLtrS0tDz3ffbZZxVPT08lIyPDsm3o0KFKnTp1rNoBysSJEy2/9+nTR9Hr9co///xj2Xbo0CFFq9Uqt39s5nfc6OhoJTQ01Gpbo0aNlE6dOuVpu27dOgVQ1q1bpyiKohgMBqVatWpK48aNlfT0dEu733//XQGUCRMmWD0WQHn//fet9tmiRQslKioqz7FuN2TIEAVQKlWqpPTt21eZOnWqcvjw4TztJkyYoADK4sWL89xmMpkURVGUTz/9VAGUuXPnWm4zGAxK+/btFW9vbyU5OVlRFEU5ffq0Aii+vr5KfHy81b66du2qNGnSxOp8mUwm5Z577lHq169v2Xan11tBvv32WwVQDhw4kO/tDz30kHLvvfdafv/vf/+ruLq6WvUzMTFR8fHxUdq2bWt1ftS+KoqiZGdnK3Xr1lXq1Kmj3LhxI982iqIonTp1yvc1cftrtLDnLDs7W8nMzLTaduPGDaV69erKiBEjLNvWrl2rAMpLL72U53hqnxITExW9Xq+8/vrrVre/9NJLipeXl5KSkmK1fevWrQqgzJ8/P88+hShvJGVCiAomOTkZAB8fn2Ldr1OnTkRGRlp+NxqN/Pnnn/Tp04fQ0FDL9qCgIB5//HE2b95sOZa/vz8HDx7k+PHj+e7bw8MDNzc31q9fz40bN4rVr0ceeQSdTmd1OXrDhg1cuHDBki6hHkN18+ZNEhIS6NChA2lpaRw5cqTIxzMajaxatYo+ffpQu3Zty/aGDRvmuWR8+3GTkpJISEigU6dOnDp1iqSkpCIfV7Vr1y7i4+N54YUXrHKLH3zwQSIiIvLN/X7uueesfu/QoQOnTp2647Fmz57NF198Qd26dfn111957bXXaNiwIV27drVKz/jll19o1qyZZYQ2N7UM3fLlywkMDOSxxx6z3KbT6XjppZdISUlhw4YNVvfr378/AQEBlt+vX7/O2rVrGTRokOX8JSQkcO3aNaKjozl+/LilT3d6vRXk2rVrAFSqVCnf21atWmXV//79+6PRaFiwYIFlW2xsLDdv3uSNN97Ik/utPhd79uzh9OnTvPLKK1aj+bnblMTtzxmAVqu15BGbTCauX79OdnY2rVq1Yvfu3ZZ2v/zyCxqNhokTJ+bZr9onPz8/evfuzU8//WRJgzAajcyfP58+ffrkyaVWn8fcaTNClFcSEAtRwfj6+gLmoLA46tata/X71atXSUtLIzw8PE/bhg0bYjKZOHfuHADvv/8+iYmJNGjQgCZNmvB///d/7N+/39Le3d2dDz/8kBUrVlC9enU6duzIRx99xOXLly1tkpKSuHz5suXn+vXrgLnEU3R0NL/++isZGRmAOV3C1dWVQYMGWe5/8OBB+vbti5+fH76+vgQEBFiqTxQnML169Srp6enUr18/z235PRdbtmyhW7dueHl54e/vT0BAAG+++Waxj6v6559/CjxWRESE5XaVmguaW6VKlYr0xcPFxYVRo0YRFxdHQkICv/32Gz179mTt2rU8+uijlnYnT5684yXxf/75h/r16+PiYv1npWHDhlaPS3X76+3EiRMoisI777xDQECA1Y8axMXHxwN3fr3diZJPzuv8+fPJysqiRYsWnDhxghMnTnD9+nXatm3LvHnzLO1OnjwJUOjzUZQ2JXH7c6aaM2cOTZs2teRTBwQE8Mcff1i9/k6ePElwcDCVK1cu9BhDhgzh7NmzbNq0CYDVq1dz5coVnnzyyTxt1efR1rW5hXAECYiFqGB8fX0JDg7m77//Ltb9co90FlfHjh05efIks2bNonHjxnz77be0bNmSb7/91tLmlVde4dixY0yePBm9Xs8777xDw4YN2bNnDwAvv/wyQUFBlp9+/fpZ7vvEE0+QnJzM77//jsFg4JdffrHk+IJ5wlenTp3Yt28f77//PsuWLSM2NpYPP/wQMI+c2cPJkyfp2rUrCQkJTJs2jT/++IPY2FjGjBlj1+Pmljuv+m5UqVKFhx9+mOXLl9OpUyc2b96cJ4i1pdtfb+pz9dprrxEbG5vvT7169YCivd7yU6VKFYB8vyyoQe+9995L/fr1LT+bN29m27ZtRRpxL66CAsmCJkTm9x6dO3cuw4YNIywsjO+++46VK1cSGxtLly5dSvT6i46Opnr16sydO9ey/8DAwHwnIqrPY9WqVYt9HCHKGplUJ0QF9NBDD/Hf//6Xbdu20b59+xLtIyAgAE9PT44ePZrntiNHjuDi4kKtWrUs2ypXrszw4cMZPnw4KSkpdOzYkXfffZenn37a0iYsLIxXX32VV199lePHj9O8eXM+/vhj5s6dy7hx46zqCee+rP3www/j4+PDjz/+iE6n48aNG1bpEuvXr+fatWssXryYjh07WrafPn26RI/bw8Mj38vxtz8Xy5YtIzMzk6VLl1qlV+Q3w7+oo2jqZLejR4/mKWd19OhRy+321KpVKzZs2MClS5eoU6cOYWFhd/yCVadOHfbv34/JZLIaJVbTVe7UbzUtR6fTFVgFIreivN5uFxERAZhfF02aNLFsP336NFu3bmX06NF06tTJ6j4mk4knn3ySH3/8kbfffpuwsDAA/v77b0uAfrvcbQp7LJUqVco30C7OF5FFixYRGhrK4sWLrV5jt6dGhIWFsWrVKq5fv17oKLFWq+Xxxx/n+++/58MPP2TJkiWMHDky3y9e6vtLvQogRHkmI8RCVEDjxo3Dy8uLp59+mitXruS5/eTJk1bln/Kj1Wrp0aMHv/32m1VptCtXrvDjjz9y3333WdIz1NxMlbe3N/Xq1SMzMxOAtLQ0S7qDKiwsDB8fH0ubyMhIunXrZvmJioqytPXw8KBv374sX76cr7/+Gi8vL3r37m3VV7C+FG4wGPjqq68KfYwFPe7o6GiWLFnC2bNnLdsPHz7MqlWr8rS9/bhJSUnMnj07z369vLxITEy84/FbtWpFtWrVmDFjhuW5AXOZr8OHD/Pggw8W9yHl6/Lly5ZSZ7kZDAbWrFmDi4uLJeDr378/+/bt49dff83TXn3sMTExXL58mfnz51tuy87O5vPPP8fb2ztPoHm7atWq0blzZ2bOnMmlS5fy3J67LvKdXm8FiYqKws3NzVJmTKWODo8bN44BAwZY/QwaNIhOnTpZ2vTo0QMfHx8mT56c5zWtPhctW7akbt26fPrpp3nOee7XSlhYGEeOHLF6bPv27WPLli2FPo7c8nsNbt++nW3btlm169+/P4qi8N577+XZx+0pJE8++SQ3btzg2WefJSUlpcCFb+Li4vDz86NRo0ZF7q8QZZWMEAtRAYWFhfHjjz/yyCOP0LBhQ6uV6rZu3Woph3UnkyZNIjY2lvvuu48XXngBV1dXZs6cSWZmJh999JGlXWRkJJ07dyYqKorKlSuza9cuFi1axOjRowE4duwYXbt2ZdCgQURGRuLq6sqvv/7KlStXrHJVC/PEE0/wv//9j1WrVjF48GCrCT733HMPlSpVYujQobz00ktoNBp++OGHEtdHfe+991i5ciUdOnTghRdesAR2jRo1sspV7dGjB25ubvTq1csSPHzzzTdUq1YtT1AXFRXF119/zaRJk6hXrx7VqlXLd0EDnU7Hhx9+yPDhw+nUqROPPfaYpexaSEiIJR3jbp0/f542bdrQpUsXunbtSmBgIPHx8fz000/s27ePV155xXIp/P/+7/9YtGgRAwcOZMSIEURFRXH9+nWWLl3KjBkzaNasGc888wwzZ85k2LBhxMXFERISwqJFi9iyZQuffvppkSZ5fvnll9x33300adKEkSNHEhoaypUrV9i2bRvnz59n3759wJ1fbwXR6/X06NGD1atX8/7771u2z5s3j+bNm1td8cjt4Ycf5sUXX2T37t20bNmSTz75hKeffprWrVvz+OOPU6lSJfbt20daWhpz5szBxcWFr7/+ml69etG8eXOGDx9OUFAQR44c4eDBg5YvViNGjGDatGlER0fz1FNPER8fz4wZM2jUqJFlwuqdPPTQQyxevJi+ffvy4IMPcvr0aWbMmEFkZCQpKSmWdvfffz9PPvkkn332GcePH+eBBx7AZDKxadMm7r//fqvnrkWLFjRu3JiFCxfSsGHDAsvUxcbG0qtXL8khFhWDQ2pbCCFKxbFjx5SRI0cqISEhipubm+Lj46Pce++9yueff25V2gpQRo0ale8+du/erURHRyve3t6Kp6encv/99ytbt261ajNp0iSlTZs2ir+/v+Lh4aFEREQo//rXvxSDwaAoiqIkJCQoo0aNUiIiIhQvLy/Fz89Padu2rbJgwYIiP5bs7GwlKChIAZTly5fnuX3Lli1Ku3btFA8PDyU4OFgZN26csmrVKquSZopStLJriqIoGzZsUKKiohQ3NzclNDRUmTFjhjJx4sQ8ZdeWLl2qNG3aVNHr9UpISIjy4YcfKrNmzVIA5fTp05Z2ly9fVh588EHFx8dHASzltm4vu6aaP3++0qJFC8Xd3V2pXLmyMnjwYOX8+fNWbYYOHap4eXnleS7y6+ftkpOTlenTpyvR0dFKzZo1FZ1Op/j4+Cjt27dXvvnmG6vyYIqiKNeuXVNGjx6t1KhRQ3Fzc1Nq1qypDB06VElISLC0uXLlijJ8+HClatWqipubm9KkSRNl9uzZVvtRS4gVVILv5MmTypAhQ5TAwEBFp9MpNWrUUB566CFl0aJFljZ3er0VZvHixYpGo1HOnj2rKIqixMXFKYDyzjvvFHifM2fOKIAyZswYy7alS5cq99xzj+Lh4aH4+voqbdq0UX766Ser+23evFnp3r274uPjo3h5eSlNmzZVPv/8c6s2c+fOVUJDQxU3NzelefPmyqpVqwosu5bfc2YymZR///vfSp06dRR3d3elRYsWyu+//57v6zw7O1v5z3/+o0RERChubm5KQECA0rNnTyUuLi7Pfj/66CMFUP7973/n+5wcPnxYAZTVq1cX+LwJUZ5oFEWWmBFCCOEcjEYjkZGRDBo0iA8++MDR3Smzpk+fzpgxYzhz5oxVfrzqlVdeYePGjcTFxckIsagQJCAWQgjhVObPn8/zzz/P2bNn8fb2dnR3yhxFUWjWrBlVqlTJd4LotWvXqFOnDgsWLCAmJsYBPRTC9iQgFkIIIQSpqaksXbqUdevW8c033/Dbb7/x8MMPO7pbQpQKCYiFEEIIwZkzZ6hbty7+/v688MIL/Otf/3J0l4QoNRIQCyGEEEIIpyZ1iIUQQgghhFOTgFgIIYQQQjg1WZijhEwmExcvXsTHx0dKzgghhBBClEGKonDz5k2Cg4OtlpW/nQTEJXTx4sUCVzUSQgghhBBlx7lz56hZs2aBt0tAXELqMqTnzp3D19fXwb2p2LKysvjzzz/p0aMHOp3O0d0RpUDOufORc+585Jw7p9I+78nJydSqVeuOy8dLQFxCapqEr6+vBMR2lpWVhaenJ76+vvKh6STknDsfOefOR865c3LUeb9TeqtMqhNCCCGEEE5NAmIhhBBCCOHUJCAWQgghhBBOTXKIhRBCiHJMURSys7MxGo2O7kqxZGVl4erqSkZGRrnruyg5W593rVaLq6vrXZfAlYBYCCGEKKcMBgOXLl0iLS3N0V0pNkVRCAwM5Ny5c1LP34nY47x7enoSFBSEm5tbifchAbEQQghRDplMJk6fPo1WqyU4OBg3N7dyFViaTCZSUlLw9vYudMEEUbHY8rwrioLBYODq1aucPn2a+vXrl3ifEhALIYQQ5ZDBYMBkMlGrVi08PT0d3Z1iM5lMGAwG9Hq9BMROxNbn3cPDA51Oxz///GPZb0nIK1AIIYQoxySYFM7OFu8BeRcJIYQQQginJikTQghRBhiNsGkTXLoEQUHQoQNotY7ulRBCOAcZIRZCCAdbvBhCQuD+++Hxx83/hoSYtwtRGoxGWL8efvrJ/G9Zr4LWuXNnXnnllULbhISE8Omnn5ZKf0T5JwGxEEI40OLFMGAAnD9vvf3CBfN2CYqFvTniC9mwYcPQarVUqlQJrVaLRqNBo9Fw4sQJ+x30NmlpaYwfP56wsDD0ej0BAQF06tSJ3377rdT6IMoOSZkQQggHMRrh5ZdBUfLepiig0cArr0Dv3pI+IexD/UJ2+2tQ/UK2aBH062efY0dHRzN9+nR8fHwsk6ICAgLsc7B8PPfcc2zfvp3PP/+cyMhIrl27xtatW7l27ZrdjmkwGO6qVq6wHxkhFkIIB9m0Ke/IcG6KAufOmdsJURSKAqmpRftJToaXXir4CxmYv7AlJxdtf/ntpzDu7u5Ur16dwMBAy4/21je/DRs20KZNG9zd3QkKCuKNN94gOzu7wH3Fx8fTq1cvPDw8qFu3LvPmzbvj8ZcuXcqbb75JTEwMISEhREVF8eKLLzJixAhLm8zMTF5//XVq1aqFu7s79erV47vvvrPcfqd+du7cmdGjR/PKK69QtWpVoqOjAfj777/p2bMn3t7eVK9enSeffJKEhITiPYHCpiQgFkIIB7l0ybbthEhLA2/vov34+ZlHgguiKOYvbH5+RdufrRbLu3DhAjExMbRu3Zp9+/bx9ddf89133zFp0qQC7zNs2DDOnTvHunXrWLRoEV999RXx8fGFHicwMJDly5dz8+bNAtsMGTKEn376ic8++4zDhw8zc+ZMvL29i9XPOXPm4ObmxpYtW5gxYwaJiYl06dKFFi1asGvXLlauXMmVK1cYNGhQMZ4lYWuSMiGEEA4SFGTbdkKUJ3/88Qc1a9a0/N6zZ08WLlzIV199Ra1atfjiiy/QaDRERERw8eJFXn/9dSZMmJCn5uyxY8dYsWIFO3bsoHXr1gB89913NGzYsNDj//e//2Xw4MFUqVKFZs2acd999zFgwADuvfdey34XLFhAbGws3bp1AyA0NNRy/6L2s379+nz00UeW+02aNIkWLVrw73//27Jt1qxZ1KpVi2PHjtGgQYOSPJ3iLskIsRBCOEiHDlCzpjlXOD8aDdSqZW4nRFF4ekJKStF+li8v2j6XLy/a/oq7WF7nzp3ZuHEju3fvZu/evXz22WcAHD58mPbt21stQ33vvfeSkpLC+XxyjA4fPoyrqytRUVGWbREREfj7+xd6/I4dO3Lq1CnWrFnDgAEDOHjwIB06dOCDDz4AYO/evWi1Wjp16pTv/Yvaz9z9Ati3bx/r1q3D29vb8hMREQHAyZMnC+2zsB8ZIRZCCAfRamH6dPPkpdupf2M//VQm1Imi02jAy6tobXv0MH8hu3Ah//xfjcZ8e48e9nkNenl5ERoaiq+vr8NW29PpdHTo0IEOHTrw+uuvM2nSJN5//31ef/11PDw8bHIMr9tOSEpKCr169eLDDz/M0zZILgc5jIwQCyGEA/XrZ57J7+dnvb1SJfvO8BdC/UIGea9SOPILWcOGDdm2bRtKrih9y5Yt+Pj4WKVYqCIiIsjOziYuLs6y7ejRoyQmJhb72JGRkWRnZ5ORkUGTJk0wmUxs2LDBJv1UtWzZkoMHDxISEkK9evWsfm4PnkXpkYBYCCEcrF8/6N7d/H81+Bg6VIJhYX/qF7IaNay316zpuC9kL7zwAufOnePFF1/kyJEj/Pbbb0ycOJGxY8fmO5IcHh7OAw88wLPPPsv27duJi4vj6aefvuMIb+fOnZk5cyZxcXGcOXOG5cuX8+abb3L//ffj6+tLSEgIQ4cOZcSIESxZsoTTp0+zfv16FixYUKJ+qkaNGsX169d57LHH2LlzJydPnmTVqlUMHz4cY1lfEaUCk4BYCCHKgD17zP+qE8337XNcX4Rz6dcPzpyBdevgxx/N/54+7bgvZDVq1GD58uXs2LGDZs2a8dxzz/HUU0/x9ttvF3if2bNnExwcTKdOnejXrx/PPPMM1apVK/Q40dHRzJkzhx49etCwYUNefPFFoqOjLQEvwNdff82AAQN44YUXiIiIYOTIkaSmppa4nwDBwcFs2bIFo9FIjx49aNKkCa+88gr+/v4OSx0RoFGU4lYOFADJycn4+fmRlJSEr6+vo7tToWVlZbF8+XJiYmLQ6XSO7o4oBc52zm/cgMqVzf9fvRq6dQN/f7h+veAJdxWNs51zW8jIyOD06dPUrVsXvV7v6O4Um8lkIjk52aE5xKL02eO8F/ZeKGq8Jq9AIYRwsN27zf+GhporSuh0kJgI//zj0G4JIYTTkIBYCCEcbNcu879RUeDmBo0bm39XA2UhhBD2JQGxEEI4mDo5vlUr878tWpj/VfOKhRBC2JcExEII4WC5R4gBWrY0/ysBsRBClA4JiIUQwoGuXzfP6IecQFgdIZaUCSGEKB0SEAshhAOpQW9YmHkxDoBmzczVJS5dgsuXHdc3IYRwFhIQCyGEA6npEmr+MJiX3g0PN/9f0iaEEML+JCAWQggHUifUqfnDKplYJ4QQpUcCYiGEcKDbJ9Sp1HxiySMWQgj7k4BYCCEc5No185K5kBMAq2SEWAghSo8ExEII4SBqukS9eualmnNTA+JTp8yr1glRkQwbNgytVsuYMWPy3DZq1Cg0Gg3Dhg0r/Y4VID09ncqVK1O1alUyMzMd3Z0yIyMjg1GjRlGlShW8vb3p378/V65cKfQ+V65c4YUXXqBmzZp4enrywAMPcPz4cas2zz77LGFhYXh4eBAQEEDv3r05cuSIPR+KBMRCCOEoty/IkVvlylCnjvn/e/eWWpeEKDW1atVi8eLFpKenW7ZlZGTw448/Urt2bQf2LK9ffvmFRo0aERERwZIlSxzaF0VRyM7OdmgfVGPGjGHZsmUsXLiQDRs2cPHiRfr161dge0VR6NevH2fOnOHXX39lz5491KlTh27dupGammppFxUVxezZszl8+DCrVq1CURR69OiB0Wi022ORgFgIIRykoPxhleQRixJLTS34JyOj6G1zBauFti2BFi1aUKNGDRYvXmzZtnjxYmrXrk0L9RLJLSaTicmTJ1O3bl08PDxo1qwZixYtstxuNBp56qmnLLeHh4czffp0q30MGzaMPn36MHXqVIKCgqhSpQqjRo0iKyvrjn397rvveOKJJ3jiiSf47rvv8tx+8OBBHnroIXx9ffHx8aFDhw6cPHnScvusWbNo1KgR7u7uBAUFMXr0aADOnDmDRqNhb65vvYmJiWg0GtavXw/A+vXr0Wg0rFixgqioKNzd3dm8eTMnT56kd+/eVK9eHW9vb1q3bs3q1aut+pWZmcnrr79OrVq1cHd3p169enz33XcoikK9evWYOnWqVfu9e/ei0Wg4ceLEHZ+TpKQkvvvuO6ZNm0aXLl0sQezWrVv566+/8r3P8ePH+euvv/j4449p3bo14eHhfP3116Snp/PTTz9Z2j3zzDN07NiRkJAQWrZsyaRJkzh37hxn1BwzO5CAWAghHKSwEWKQPGJxF7y9C/7p39+6bbVqBbft2dO6bUhI/u1K6IknnmDOnDmW32fNmsXw4cPztJs8eTL/+9//mDFjBgcPHmTMmDE88cQTbNiwATAHzDVr1mThwoUcOnSICRMm8Oabb7JgwQKr/axbt46TJ0+ybt065syZw/fff8/3339faB9PnjzJtm3bGDRoEIMGDWLTpk38888/ltsvXLhAx44dcXd3Z+3atcTFxTFixAjLKO7XX3/NqFGjeOaZZzhw4ABLly6lXr16xX6u3njjDaZMmcLhw4dp2rQpKSkpxMTEsGbNGvbs2cMDDzxAr169OHv2rOU+Q4YM4aeffuKzzz7j8OHDzJw5E29vbzQaDSNGjGD27NlWx5g9ezYdO3akXr16DBs2jM6dOxfYn7i4OLKysujWrZtlW0REBLVr12bbtm353kdNN9Hr9ZZtLi4uliA/P6mpqcyePZu6detSq1atOz5PJaaIEklKSlIAJSkpydFdqfAMBoOyZMkSxWAwOLoropQ4wzm/elVRwPyTmJh/m99/N98eGVm6fXMEZzjntpaenq4cOnRISU9Pz3uj+uLK7ycmxrqtp2fBbTt1sm5btWr+7Ypp6NChysMPP6wcP35ccXd3V86cOaOcOXNG0ev1ytWrV5XevXsrQ4cOVRRFUTIyMhRPT09l69atVvt46qmnlMcee6zAY4waNUrp37+/1THr1KmjZGdnW7YNHDhQeeSRRwrt65tvvqn06dPH8nvv3r2ViRMnWn4fP368Urdu3QJfu8HBwcpbb72V722nT59WAGXPnj2WbTdu3FAAZd26dYqiKMq6desUQFmyZEmh/VQURWnUqJHy+eefK4qiKEePHlUAJTY2Nt+2Fy5cULRarbJ9+3ZFUczvwapVqyrff/+9oiiK8sYbbyhPPvlkgceaN2+e4ubmlmd769atlXHjxuV7H4PBoNSuXVvp06ePkpCQoGRmZipTpkxRAKVHjx5Wbb/88kvFy8tLAZTw8HDlxIkTBfalsPdCUeM1V/uF2kIIIQqijg43aAB+fvm3UUeIjxyBtDTw9CydvokKICWl4Nu0Wuvf4+MLbuty24VkG1+yrlq1KjExMXz//fcoisKDDz5I1apVrdqcOHGCtLQ0unfvbrXdYDBYpVZ8+eWXzJo1i7Nnz5Keno7BYKB58+ZW92nUqBHaXI8/KCiIAwcOFNg/o9HInDlzrNIvnnjiCV577TUmTJiAi4sLe/fupUOHDuh0ujz3j4+P5+LFi3Tt2rVIz0dhWt12KSklJYV3332XP/74g0uXLpGdnU16erplhHjv3r1otVo6deqU7/6Cg4N58MEHmTVrFm3atGHZsmVkZmYycOBAwDwqb2s6nY5FixYxYsQIqlatilarpVu3bvTs2RNFUazaDh48mO7du3Pp0iWmTp3KoEGD2LJli9Xosi1JQCyEEA5Q0IIcuQUFQfXqcOUKHDgAbduWTt9EBeDl5fi2RTR8+HBeeuklwBzU3i7lVnD/xx9/UKNGDavb3N3dAfj555957bXX+Pjjj2nfvj0+Pj785z//Yfv27Vbtbw9aNRoNJpOpwL6tWrWKCxcu8Mgjj1htNxqNrFmzhu7du+Ph4VHg/Qu7DczpAoBVMFhQTrPXbc/9a6+9RmxsLFOnTqVevXp4eHgwYMAADAZDkY4N8PTTT/Pkk0/yySefMHv2bB555BE8i/jNOzAwEIPBQGJiIv65yuRcuXKFwMDAAu8XFRXFpk2bLJMDAwICaNu2bZ6A38/PDz8/P+rXr0+7du2oVKkSv/76K4899liR+ldckkMshBAOcKcJdQAaTc4osUysExXVAw88gMFgICsri+jo6Dy3R0ZG4u7uztmzZ6lXr57Vj5pTumXLFu655x5eeOEFWrRoQb169awmtZXUd999x6OPPsrevXutfh599FHL5LqmTZuyadOmfANZHx8fQkJCWLNmTb77DwgIAODSpUuWbXuLWFZmy5YtDBs2jL59+9KkSRMCAwOtJp01adIEk8lkybPOT0xMDF5eXnz99desXLmSESNGFOnYYA5sdTqd1WM7evQoZ8+epX379ne8v5+fHwEBARw/fpxdu3bRu3fvAtsqioKiKHYteScjxEII4QB3mlCnatkSVq6UiXWi4tJqtRw+fNjy/9v5+Pjw2muvMWbMGEwmE/fddx9JSUls2bIFX19fhg4dSv369fnf//7HqlWrqFu3Lj/88AM7d+6kbt26Je7X1atXWbZsGUuXLqVx48ZWtw0ZMoS+ffty/fp1Ro8ezeeff86jjz7K+PHj8fPz46+//qJNmzaEh4fz7rvv8txzz1GtWjV69uzJzZs32bJlCy+++CIeHh60a9eOKVOmULduXeLj43n77beL1L/69euzePFievXqhUaj4Z133rEa7Q4JCWHo0KGMGDGCzz77jGbNmvHPP/8QHx/PoEGDLM/3sGHDGD9+PPXr17cKZMePH8+FCxf43//+l+/x/fz8eOqppxg7diyVK1fG19eXF198kfbt29OuXTtLu4iICCZPnkzfvn0BWLhwIV5eXkRERHDw4EFefvll+vTpQ48ePQA4deoU8+fPp0ePHgQEBHD+/HmmTJmCh4cHMTExRXpuSkJGiIUQopRdvQrqRPDbqkvlISPEwhn4+vri6+tb4O0ffPAB77zzDpMnT6Zhw4Y88MAD/PHHH5aA99lnn6Vfv3488sgjtG3blmvXrvHCCy/cVZ/+97//4eXllW/+b9euXfHw8GDu3LlUqVKFtWvXkpKSQqdOnYiKiuKbb76xpGcMHTqUTz/9lK+++opGjRrx0EMPWS1EMWvWLLKzs4mKiuKVV15h0qRJRerftGnTqFSpEvfccw+9evUiOjqalrctefn1118zYMAAXnjhBSIiIhg5cqRVvV+Ap556CoPBkKe6x6VLl6wqVuTnk08+4aGHHqJ///507NiRwMBAqzJ6YB41TkpKsvx++fJlnn32WSIjI3nppZd48sknrUqu6fV6Nm3aRExMDPXq1eORRx7Bx8eHrVu3Uq1atSI9NyWhUW7PYhZFkpycjJ+fH0lJSYW+icXdy8rKYvny5cTExOQ7aUFUPBX9nK9caa5mFR5unjBXmJMnzSvZubmZ50lVwKcDqPjn3B4yMjI4ffo0devWtdtEI3symUwkJyfj6+tryaUVpW/Tpk107dqVc+fOUb16dbsfzx7nvbD3QlHjNYe/Ar/88ktCQkLQ6/W0bduWHTt2FNg2KyuL999/n7CwMPR6Pc2aNWPlypUFtp8yZQoajYZXXnnFanvnzp3RaDRWP88995ytHpIQQhSqKPnDqtBQcxUKgwEOHbJvv4QQziMzM5Pz58/z7rvvMnDgwFIJhssyhwbE8+fPZ+zYsUycOJHdu3fTrFkzoqOjiS+gBMzbb7/NzJkz+fzzzzl06BDPPfccffv2ZU8+yXU7d+5k5syZNG3aNN99jRw5kkuXLll+PvroI5s+NiGEKEhR84fBPLFOrRwlecRCCFv56aefqFOnDomJiRID4eCAeNq0aYwcOZLhw4cTGRnJjBkz8PT0ZNasWfm2/+GHH3jzzTeJiYkhNDSU559/npiYGD7++GOrdikpKQwePJhvvvmGSpUq5bsvT09PAgMDLT+S9iCEKC1FKbmWmyzhLISwtWHDhmE0GomLi8tTzs4ZOazKhMFgIC4ujvHjx1u2ubi40K1bt0KX/Ls9N8TDwyPPcn+jRo3iwQcfpFu3bgUmp8+bN4+5c+cSGBhIr169eOeddwqtvZeZmWlV7iM5ORkwp3EUZR10UXLq8yvPs/OoyOc8Ph7OndOh0Sg0bpxNUR5ikyYawJXdu01kZRnt3kdHqMjn3F6ysrJQFAWTyVRoLd2ySp3CpD4G4Rzscd5NJhOKopCVlZWnUklRP1McFhAnJCRgNBrz5KxUr16dIwXMMomOjmbatGl07NiRsLAw1qxZw+LFizEac/5A/Pzzz+zevZudO3cWeOzHH3+cOnXqEBwczP79+3n99dc5evRonpmRuU2ePJn33nsvz/Y///yzyEWsxd2JjY11dBdEKauI5zwurhrQnho1Uti0aW2R7pOS4gN0IS7OxO+/L8+zeFhFUhHPub24uroSGBhISkqKZTGG8ujmzZuO7oJwAFued4PBQHp6Ohs3biQ7O9vqtrS0tCLto1zVIZ4+fTojR44kIiICjUZDWFgYw4cPt6RYnDt3jpdffpnY2NhCZ9w+88wzlv83adKEoKAgunbtysmTJwkLC8v3PuPHj2fs2LGW35OTk6lVqxY9evSQdAs7y8rKIjY2lu7du8vscydRkc/5nj3maLZDB68i19TMzoZx4xQyMlxp0CCGBg3s2UPHqMjn3F4yMjI4d+4c3t7e5bLKhKIo3Lx5Ex8fHzQajaO7I0qJPc57RkYGHh4edOzYMd8qE0XhsIBYXcP6ypUrVtsLW/IvICCAJUuWkJGRwbVr1wgODuaNN94gNDQUgLi4OOLj463q8BmNRjZu3MgXX3xBZmZmvkW/295aD/XEiRMFBsTu7u6WJSJz0+l08uFdSuS5dj4V8Zyri1C1aeOCTle0oV6dDpo1g+3b4cABHY0a2a9/jlYRz7m9GI1GNBoNLi4u5bJsmXq5XH0MwjnY47y7uLig0Wjy/fwo6ueJw16Bbm5uREVFWS35ZzKZWLNmzR2X/NPr9dSoUYPs7Gx++eUXy3J/Xbt25cCBA1bLK7Zq1YrBgwezd+/efINhyFkmMSgoyDYPTgghClCckmu5qQt0SKUJIYSwPYemTIwdO5ahQ4fSqlUr2rRpw6effkpqaqpltZQhQ4ZQo0YNJk+eDMD27du5cOECzZs358KFC7z77ruYTCbGjRsHmJd3vH15RS8vL6pUqWLZfvLkSX788UdiYmKoUqUK+/fvZ8yYMXTs2LHAEm1CCGELly/DhQvmUmp3WqHudlJpQhSLwWDOtSktrq7m1WOEKKccGhA/8sgjXL16lQkTJnD58mWaN2/OypUrLRPtzp49azWcnpGRwdtvv82pU6fw9vYmJiaGH374AX9//yIf083NjdWrV1uC71q1atG/f/8irx0uhBAlpZZbi4gAb+/i3Tf3CLGimINqIfJlMMCOHealDUuLtze0aVNhg+Jhw4aRmJjIkiVLHN0VYScOn1Q3evRoRo8ene9t69evt/q9U6dOHCrmUk2376NWrVps2LChWPsQQghbKM6CHLdr3Ng8CHftGpw/D7Vq2bZvogLJzjYHw25ukM/cF5vLzDQfLzvbbgHxv/71L/744w/27t2Lm5sbiYmJd7zP6dOneeutt1i/fj3Xr1+natWqREVF8eGHHxIREcGZM2eoW7cue/bsobm6+k0JrV+/nvvvvx8w58b6+PgQGhpK9+7dGTNmjKRklgOSxS6EEKWkuAty5KbXQ2Sk+f+SNiGKxN3d/MKx948Ngu7OnTvz/fffF3i7wWBg4MCBPP/880XaX1ZWFt27dycpKYnFixdz9OhR5s+fT5MmTYoUTJfU0aNHuXjxIjt37uT1119n9erVNG7cmAMHDtjtmMI2JCAWQohSok6oK8kIMcjEOuG83nvvPcaMGUOTJk2K1P7gwYOcPHmSr776inbt2lGnTh3uvfdeJk2aRLt27QCoW7cuAC1atECj0dC5c2fAXL1j7Nix+Pv7U6VKFcaNG2dZTOJOqlWrRmBgIA0aNODRRx9ly5YtBAQE5Ankv/32Wxo2bIheryciIoKvvvrKcts999zD66+/btX+6tWr6HQ6Nm7cWKR+iOKTgFgIIUrBpUtw8SK4uEBJr87KxDohiiYgIAAXFxcWLVpktXhXbjt27ABg9erVXLp0ybI418cff8z333/PrFmz2Lx5M9evX+fXX38tUT88PDx47rnn2LJlC/Hx8YB5pdwJEybwr3/9i8OHD/Pvf/+bd955hzlz5gAwePBgfv75Z6sgfP78+QQHB9OhQ4cS9UPcmQTEQghRCnJPqPPyKtk+ZIRYVBT//ve/8fX1pWbNmvj6+rJp0yaee+45vL29LT9nz54t8f5r1KjBZ599xoQJE6hUqRJdunThgw8+4NSpU5Y2AQEBAFSpUoXAwEAqV64MwKeffsr48ePp168fDRs2ZMaMGfj5+ZW4LxEREQCcOXMGgIkTJ/Lxxx/Tr18/6tatS79+/RgzZgwzZ84EYNCgQVy8eJHNmzdb9vHjjz/y2GOPyQImdiQBsRBClIK7mVCnUkeWz5+Hq1fvuktCOMxzzz3H7t272bhxI7t376ZVq1a8//77VusIBAcH39UxRo0axeXLl5k3bx7t27dn4cKFNGrUqNDlwZOSkrh06ZJlwS4wL5Hd6i7euOpIr0ajITU1lZMnT/LUU09ZBf+TJk3i5MmTgDlQ79GjB/PmzQPMkwO3bdvG4MGDS9wHcWcOrzIhhBDOoKQLcuTm4wP168Px4+ZR4h49bNM3IUpb5cqV8ff3Jzk5GV9fXzw8PKhWrRr16tWz6XF8fHzo1asXvXr1YtKkSURHRzNp0iS6d+9u0+MU5vDhwwCEhISQcqsU3jfffGMVdANWi4cNHjyYl156ic8//5wff/yRJk2aFDl/WpSMjBALIUQpsMUIMUgesRAlpdFoiIiIIDU1FTCvSwBY5Rj7+fkRFBTE9u3bLduys7OJU9/AxZSens5///tfOnbsSEBAANWrVyc4OJhTp05Rr149qx91kh9A7969ycjIYOXKlfz4448yOlwKZIRYCCHs7OJF86S6u5lQp2rRAubPlzxiUQSZmWX2OCkpKSQnJ3Pz5k3S0tL4+eefAbh8+bKlTUBAgGXU9OzZs1y/fp2zZ89iNBrZu3cvAPXq1cM7n1Vu9u7dy8SJE3nyySeJjIzEzc2NDRs2MGvWLEsFh2rVquHh4cHKlSupWbMmer0ePz8/Xn75ZaZMmUL9+vWJiIhg2rRpRS7VFh8fT0ZGBjdv3iQuLo6PPvqIhIQEy4Q9MFfMeOmll/Dz8+OBBx4gMzOTXbt2cePGDcaOHQuYV9nt06cP77zzDocPH+axxx4r9nMsikcCYiGEsDN1cCkyEjw9725fMkIs7sjV1bxyXEqKedW60uDtbT5uEU2dOpX33nuv0DanT58mJCQEgAkTJliqMIC5VBrAunXrLOXScqtZsyYhISG89957nDlzBo1GY/l9zJgxgDk3+LPPPuP9999nwoQJdOjQgfXr1/Pqq69y6dIlhg4diouLCyNGjKBv374kJSXd8XGFh4ej0Wjw9vYmNDSUHj16MHbsWAIDAy1tnn76aTw9PfnPf/7D//3f/+Hl5UWTJk145ZVXrPY1ePBgYmJi6NixI7Vr177jscXd0ShFLa4nrCQnJ+Pn50dSUhK+vr6O7k6FlpWVxfLly4mJiUGn0zm6O6IUVLRz/u678N57MHQoFLL2QJEkJMCtyfEkJUFF+fipaOe8NGRkZHD69Gnq1q2LXq+3vtFgMK8cV1pcXYu9Sp3JZLLkELu4SAans7DHeS/svVDUeE1GiIUQws7udkGO3KpWNS/bfO4c7N0LHTve/T5FBeTmZrdllIWoiOQrmRBC2JGi3N2SzfmResRCCGFbEhALIYQdXbwIly+bJ9Q1a2abfap5xBIQCyGEbUhALIQQdqSODjdqdPcT6lTqCLFMrBNCCNuQgFgIIezIFgty3E4NiA8dgowM2+1XlE8yN144O1u8ByQgFkIIO7LVghy51axpnlxnNMKBA7bbryhf1GocaWlpDu6JEI6lvgfupkKNVJkQQgg7URT7jBBrNOZR4thYcx5x69a227coP7RaLf7+/sTHxwPg6emJRqNxcK+KzmQyYTAYyMjIkLJrTsSW511RFNLS0oiPj8ff399q+evikoBYCCHs5MIFiI8HrdZ2E+pULVuaA2LJI3Zu6oIPalBcniiKQnp6Oh4eHuUqkBd3xx7n3d/f32rxk5KQgFgIIewk94Q6Dw/b7ltKrwkAjUZDUFAQ1apVIysry9HdKZasrCw2btxIx44dZTEWJ2Lr867T6e5qZFglAbEQQtiJLRfkuJ1aem3/fvOCZMVYNVdUQFqt1iZBQWnSarVkZ2ej1+slIHYiZfW8S9KOEELYia0X5MgtLAx8fMxVJo4csf3+hRDCmUhALIQQdmCvCXUqFxdo3tz8f8kjFkKIuyMBsRBC2MH583D1qjmVoWlT+xxD8oiFEMI2JCAWQgg7UEeH7TGhTqXmEcsIsRBC3B0JiIUQwg7ssSDH7dQR4r17wWSy33GEEKKik4BYCCHswJ75w6qGDcHdHZKT4fRp+x1HCCEqOgmIhRDCxhSldEaIdTpo0sT8f0mbEEKIkpOAWAghbOzcOUhIME+oUwNWe5GJdUIIcfckIBZCCBtT0yUaNwa93r7Hkol1Qghx9yQgFkIIGyuNdAmVOkK8e7c5VUMIIUTxSUAshBA2VhoT6lRNm4JWa655fPGi/Y8nhBAVkQTEQghhQ6U1oU7l4QEREeb/Sx6xEEKUjATEQghhQ//8A9euWVeAsDfJIxZCiLsjAbEQQtiQOjrcpIm5RnBpkEoTQghxdyQgFkIIGyrN/GGVjBALIcTdkYBYCCFsqDTzh1XNm5v/PXvWnK4hhBCieCQgFkIIG8k9oa40R4j9/CAszPx/SZsQQojik4BYCCFs5MwZuH7dPKGucePSPbbkEQshRMlJQCyEEDaijg43bVp6E+pUkkcshBAlJwGxEELYiCMm1KlkhFgIIUpOAmIhhLARR0yoU6kB8bFjkJJS+scXQojyTAJiIYSwAUdNqFNVrw7BweZ+7NtX+scXQojyTAJiIYSwgdOn4cYNcHMr/Ql1KkmbEEKIkpGAWAghbCD3hDo3N8f0QSbWCSFEyUhALIQQNqBOqHNE/rBKRoiFEKJkJCAWQggbcGT+sEodIf77b8jMdFw/hBCivJGAWAgh7pKjJ9SpateGSpUgOxsOHnRcP4QQoryRgFgIIe7SqVOQmGhejKNRI8f1Q6ORPGIhhCgJCYiFEOIuqfnDjpxQp5I8YiGEKD4JiIUQ4i45ckGO28kIsRBCFJ8ExEIIcZccuWTz7dQR4n37wGh0bF+EEKK8kIBYCCHugqLkjMaWhRHi+vXBywvS0+HoUUf3RgghygcJiIUQ4i6cPAlJSeYJdZGRju4NaLXQrJn5/5JHLIQQRSMBsRBC3AU1XaJ5c9DpHNoVC5lYJ4QQxSMBsRBC3IWyUH/4djKxTgghikcCYiGEuAtlaUKdKvcIsaI4ti9CCFEeSEAshBAlZDKVrQl1qkaNzOkbiYlw5oyjeyOEEGWfBMRCCFFCJ05AcjLo9WVjQp3KzQ0aNzb/X/KIhRDiziQgFkKIElLzh5s3B1dXh3YlD8kjFkKIopOAWAghSqgs5g+rpNKEEEIUnQTEQghRQmVpyebbyQixEEIUnQTEQghRArkn1JXFEeKmTUGjgcuX4dIlR/dGCCHKNgmIhRCiBI4fh5s3wcMDGjZ0dG/y8vKCiAjz/yVtQgghCicBsRBClEBZnlCnkjxiIYQoGgmIhRCiBMryhDqV5BELIUTRODwg/vLLLwkJCUGv19O2bVt27NhRYNusrCzef/99wsLC0Ov1NGvWjJUrVxbYfsqUKWg0Gl555RWr7RkZGYwaNYoqVarg7e1N//79uXLliq0ekhDCCZTlCXUqGSEWQoiicWhAPH/+fMaOHcvEiRPZvXs3zZo1Izo6mvj4+Hzbv/3228ycOZPPP/+cQ4cO8dxzz9G3b1/25PNpv3PnTmbOnEnTpk3z3DZmzBiWLVvGwoUL2bBhAxcvXqRfv342f3xCiIqprE+oUzVvbv739Gm4ccOhXRFCiDLNoQHxtGnTGDlyJMOHDycyMpIZM2bg6enJrFmz8m3/ww8/8OabbxITE0NoaCjPP/88MTExfPzxx1btUlJSGDx4MN988w2VKlWyui0pKYnvvvuOadOm0aVLF6Kiopg9ezZbt27lr7/+sttjFUJUHMeOQUoKeHrmTFwriypXhpAQ8//37nVkT4QQomxz2FQQg8FAXFwc48ePt2xzcXGhW7dubNu2Ld/7ZGZmotfrrbZ5eHiwefNmq22jRo3iwQcfpFu3bkyaNMnqtri4OLKysujWrZtlW0REBLVr12bbtm20a9euwGNnZmZafk9OTgbMaRxZWVlFeMSipNTnV55n51HWz/lff2kAV5o1M6EoRspoNwFo1kzLmTMu7Npl5L77TI7uToHK+jkXtifn3DmV9nkv6nEcFhAnJCRgNBqpXr261fbq1atz5MiRfO8THR3NtGnT6NixI2FhYaxZs4bFixdjNBotbX7++Wd2797Nzp07893H5cuXcXNzw9/fP89xL1++XGB/J0+ezHvvvZdn+59//omnp2eB9xO2Exsb6+guiFJWVs/54sWNgTCqVDnN8uV/O7o7hfLyagA05I8/LtKgQdmfXVdWz7mwHznnzqm0zntaWlqR2pXRYkH5mz59OiNHjiQiIgKNRkNYWBjDhw+3pFicO3eOl19+mdjY2DwjyXdr/PjxjB071vJ7cnIytWrVokePHvj6+tr0WMJaVlYWsbGxdO/eHZ1O5+juiFJQ1s/51KlaAPr2rUNMTG0H9+ZONPz4I8TH1yQmJtDRnSlQWT/nwvbknDun0j7v6hX9O3FYQFy1alW0Wm2e6g5XrlwhMDD/D+2AgACWLFlCRkYG165dIzg4mDfeeIPQ0FDAnA4RHx9PS7XWEGA0Gtm4cSNffPEFmZmZBAYGYjAYSExMtBolLuy4AO7u7ri7u+fZrtPp5I1cSuS5dj5l8ZwbjTlVG9q1c6WMdS+PNm3M/x49qiErS0dZv6BVFs+5sC85586ptM57UY/hsEl1bm5uREVFsWbNGss2k8nEmjVraN++faH31ev11KhRg+zsbH755Rd69+4NQNeuXTlw4AB79+61/LRq1YrBgwezd+9etFotUVFR6HQ6q+MePXqUs2fP3vG4Qghx7BikpppXggsPd3Rv7iwoCKpXN1fG2L/f0b0RQoiyyaEpE2PHjmXo0KG0atWKNm3a8Omnn5Kamsrw4cMBGDJkCDVq1GDy5MkAbN++nQsXLtC8eXMuXLjAu+++i8lkYty4cQD4+PjQuHFjq2N4eXlRpUoVy3Y/Pz+eeuopxo4dS+XKlfH19eXFF1+kffv2BU6oE0IIlbogR/PmoNU6tCtF1rIlrFhhLhUnH3NCCJGXQwPiRx55hKtXrzJhwgQuX75M8+bNWblypWWi3dmzZ3FxyRnEzsjI4O233+bUqVN4e3sTExPDDz/8kGeC3J188sknuLi40L9/fzIzM4mOjuarr76y5UMTQlRQ5WFBjtu1aGEOiGWBDiGEyJ/DJ9WNHj2a0aNH53vb+vXrrX7v1KkThw4dKtb+b98HmFMuvvzyS7788sti7UsIIcrDks23kyWchRCicA5fulkIIcqL3BPqytsIMcDff4PB4Ni+CCFEWSQBsRBCFNGRI5CWZp5Q16CBo3tTdHXrgp+fORgu5kU2IYRwChIQCyFEEan5wy1blp8JdQAaTc4oseQRCyFEXhIQCyFEEakBcXnKH1apAbHkEQshRF4SEAshRBGpE+rKU/6wSp1YJyPEQgiRl8OrTIhiyMw0z+pxNtnZ5n/T0yEry7F9EaWjDJ7z7GzYu9cD0BAVmQ5piqO7VCwtIjSAB3v3KphS0nEpa8MhZfCcCzuTc+6c1PNexkhAXF5kZsL27eYZPc5GuRV4bNliToYUFV8ZPOdHzniTlnYf3h7ZNLi0Aa7c+T5lSbhRg4d7N1JTtRz/OY7wmqmO7pK1MnjOhZ3JOXdO6nk3GKAMLdktAXF5YTSag2E3N3B3d3RvSpfJBNevg7c3ZW9YS9hFGTzncecDAGgZnoqLn4+De1N8rkDTsDS2H/Jhz4VqhDdMcHSXrJXBcy7sTM65c8rIMAfDZeyKtwTE5Y27O+j1ju5F6TKZzP/q9fKh6SzK4DnfddwfgKjIjHL7HmwZmc72Qz7sPunHow+lOLo71srgORd2JufcOannvYyRV6AQQhRB3BFPAFpFlrFUg2JoEZ4OwJ6jng7uiRBClC0SEAshxB1kZ8PeW0FkVET5zeNveavvu496WtL4hBBCSEAshBB3dPiMnvRMF3y8jNSvneno7pRY47B0XLUK15NcOXel7ExmEUIIR5OAWAgh7iDusBcALcPTynWqo7ubQqMwc9rE7iOSNiGEEKpy/NEuhBClY9ehW+kSDctvuoSqRbj5MUgesRBC5JCAWAgh7sAyoa5h+Z1Qp2p5KyCWEWIhhMghAbEQQhQiOxv2HqtAI8QRMkIshBC3kzrEQghRiEOnPcjIdMHXy0i9WuV3Qp2qWf10NBqFC/FuxF93pVrlsrmMqrMwGmHTHm8uJegIqppFhxYpaLWO7pUQzkcCYiGEKISaP9wyonxPqFP5eJmoXyuTY2f17DnqSXT7ZEd3yWktXuvPy1NrcT7ezbKtZjUD0187R78uiY7rmBBOqAJ8vAshhP1UhAU5bpczsc7DwT1xXovX+jNgXCjn463L312I1zFgXCiL1/o7pmNCOCkJiIUQohC7DplLrpXnBTluZ1mgQybWOYTRCC9PrYV5bRSN1W3Krd9f+bgWRmOpd00IpyUBsRBCFCArG/YdN4+itoqsOAGxlF5zrE17vG+lSWjyvV1Bw7krbmza4126HRPCiUlALIQQBTh0yoNMgwt+3tmE1Sz/E+pUaqWJE+f0JKXIn4HSdimhaKsEFrWdEOLuySehEEIUIPeEOk3+g3nlUlV/I7WqGwDYd0xGiUtbUNUsm7YTQtw9CYiFEKIAOQtyVJx0CZXkETtOhxYp1KxmQHMri/h2GhRqVTfQoUVKKfdMCOclAbEQQhTAMqGuAgbEkkfsOFotTH/tXL7hsBokf/rqOalHLEQpkoBYCCHyYcjSsP+EOqGu4pRcU8kIsWP165JIgzoZebZXq5zNoo9OSR1iIUqZBMRCCJGPgyf1ZBpc8PfJJrSGwdHdsTl1hPjwGT3pGRUoQbqcOHdZx7F/PACFhR+epF1jc3rEEz2vSTAshANIQCyEEPlQ84ejGlasCXWqGtWyCKiUhdGo4cAJWaCjtC1aUwkw5xMP6JrIa09eAeCXdZVQ8k8tFkLYkQTEQgiRj4q4IEduGo3kETvSgtXmgHhQtxsA9Lw3CS8PI2cuuluqmwghSo8ExEIIkY+KuGTz7VqEpwOSR1zazl7W8dcBbzQahf5dzQGxp16hV4ckICdYFkKUHgmIhRDiNoYsDftvrVBXUUeIIWdinYwQl65Fq3PSJYKqZlu2D7w1WrxwtaRNVGRGI6zf5c1PKyuxfpe3LNFdRrgW9w4hISGMGDGCYcOGUbt2bXv0SQghHOrvk3oMWS5U8s2mbgWcUKdSUyb2n/AgKxt0xf6LIEri9nQJVc97zGkT/1xyZ+dBT9o0rrhfxpzV4rX+vDy11q2lu81qVjMw/bVzMpnSwYo9QvzKK6+wePFiQkND6d69Oz///DOZmRVnSVMhhIg7nJM/XBEn1KnCambi42Uk0+DCkTN6R3fHKZy56Mb2v2+lS3SxDog99AoPd5S0iYpq8Vp/BowL5Xy89ZLcF+J1DBgXyuK1/o7pmABKGBDv3buXHTt20LBhQ1588UWCgoIYPXo0u3fvtkcfhRCiVKmTmirighy5ubhA8wa30iYkj7hUqNUlOrVMITBXuoRqUPfrgKRNVDRGI7w8tdatZVesv2Urt35/5eNakj7hQCXOIW7ZsiWfffYZFy9eZOLEiXz77be0bt2a5s2bM2vWLBR5JwshyqmcJZsr7oQ6lWWBDskjLhULb438DrwtXUIV3S4Zb08jZy+7s+OgnJOKYtMe71tpEvlfclLQcO6KG5v2eJdux4RFiQPirKwsFixYwMMPP8yrr75Kq1at+Pbbb+nfvz9vvvkmgwcPtmU/hRCiVGQack2oq+AjxCCl10rTmYtu7DjohYuLQr/78w+IzWkTiQAsiK1cir0T9nQpQXfnRsVoJ2yv2FModu/ezezZs/npp59wcXFhyJAhfPLJJ0RERFja9O3bl9atW9u0o0IIURr+PulBVrYLlf2yCQmuuBPqVLkrTZhM5jQKYR/q6HCnljfzTZdQDep2gx9XVmHh6kr85+Xzck4qgKCqWTZtJ2yv2G+z1q1bc/z4cb7++msuXLjA1KlTrYJhgLp16/Loo4/arJNCCFFaLPnDFXxCnSoiJAN3NxM3U7WcuuDu6O5UaAVVl7hddPtkfLyMnLvixva/vUqja8LOOrRIoWY1AxryTyfVoFCruoEOLVJKuWdCVeyA+NSpU6xcuZKBAwei0+U/tO/l5cXs2bPvunNCCFHanGFBjtx0rtC0nizQYW+nL7ix69CtdIk7lNfSu+ekTSyUahMVglYL0187V0A4bN766avn0GpLs1cit2IHxPHx8Wzfvj3P9u3bt7Nr1y6bdEoIIRwl7nDOCLGzyMkj9nBwTyouNbDtHHWTapULTpdQqaPIC9dUwmSya9dEKendKRF/n7zn3svDxKKPTkkdYgcrdkA8atQozp07l2f7hQsXGDVqlE06JYQQjpBp0HDghPNMqFNZKk3ICLHdFDVdQtWjXTK+XkbOX3HjrwOSNlERrN3pQ+JNHZV8s/nzy2O8MewSYA6I+3ROdGznRPED4kOHDtGyZcs821u0aMGhQ4ds0ikhhHCEAyfME+qq+GVTJ6jiT6hT5a40IRUzbe/UeTfiDhctXUKVO21CFumoGOauqALAI91v0L3tTd579hJ+3tnEX9fJl54yoNgBsbu7O1euXMmz/dKlS7i6yrqfQojyK2dBjlSnmFCnalIvHa1W4eoNHRfipeyTranpEve3uklApTunS6gGdTePJi+StIlyLzXdhcXr/AF4MuYaAG46hQfvM69MuGS9v4N6JlTFDoh79OjB+PHjSUpKsmxLTEzkzTffpHv37jbtnBBClKacBTmcJ10CzLVvG4ZkAFKP2B6Kmy6hUtMmLsS7sW2/jCCWZ79t8CMlTUvdGpm0b5ozYVdNlfh1vb9cnXGwYgfEU6dO5dy5c9SpU4f777+f+++/n7p163L58mU+/vhje/RRCCFKxa5D5qDDmfKHVWrahOQR29bJ827sPuKFVqvQ9/7EYt3X3U2xBEySNlG+zV1uTpd4ouc1q6tPD7RPxt3NxIlzeg6d0juodwJKEBDXqFGD/fv389FHHxEZGUlUVBTTp0/nwIED1KpVyx59FEIIu8vI1PD3SfOEOmcpuZZb7gU6hO2o6RJdipkuoVKXeJa0ifLryjVX/tzuC8ATPa9b3ebjZaJbm2RA0iYcrURJv15eXjzzzDO27osQQjjM/uMeZBs1VPXPolZ151stSkqv2Ye6/PLAYqZLqLq3TcbPO5uLV93Yut+L+5o735e18m5+bCWMRg1tGqXSoE5mntv7dE7kj83+LNngz1tPXXZADwWUMCAGc7WJs2fPYjBYz8R++OGH77pTQghR2nIW5HCOFepu1/xWQHz2sjvXErVU8Tc6uEfl3/Gz7uw56nkrXaJkAbGaNjHn96osiK0sAXE59EOudIn8PNwxiWc0CrsOeXHuso5agc73hbwsKHZAfOrUKfr27cuBAwfQaDQot7LANbf+ghiN8iEqhCh/4g7fyh92ogU5cvPzNhFWM4OT5/XsOepJt7Y3Hd2lck9Nl+jaOpmqd/EFY1C3G8z5vSqL1vjzyVhZzaw8OXLGnV2HzDnkj/TI/0tRtcrZ3Nsshc17ffhtgz+jH7layr0UUIIc4pdffpm6desSHx+Pp6cnBw8eZOPGjbRq1Yr169fboYtCCGF/u9QV6pxwQp1KFuiwrYUlrC5xu25tb+Lvk82lBDe27PO2RddEKZl3q/ZwdLvkQlcoVCdPLtngXwq9EvkpdkC8bds23n//fapWrYqLiwsuLi7cd999TJ48mZdeeskefRRCCLtKz9BwUJ1Q19B5L0m3CE8HZGKdLRz7x529x8zpEne7CpmbLmcfC6XaRLmhKDB3hTmHXK09XBD1/K6P8+F6klwCcIRiB8RGoxEfHx8AqlatysWLFwGoU6cOR48etW3vhBCiFOw/YZ5QF1Api5pOOKFOJSPEtqMGrt3aJNskH3tQrmoTkplYPmzZ58WZi+54exp5uFNioW3DahpoUi8No1HDH5v9SqeDwkqxA+LGjRuzb98+ANq2bctHH33Eli1beP/99wkNDbV5B4UQwt7U/OFWDZ1zQp1KrTRx/Jw7N1OL/edB5FLSxTgK0rXNTSr5ZnP5mo7NeyVtojxQaw/373IDT/2dV92wpE1I+TWHKPYn3ttvv43pVjHE999/n9OnT9OhQweWL1/OZ599ZvMOCiGEveUs2ey8+cNgntxTo5oBRdGw77iUXyupo2fc2X/cE1cbpEuo3HQKfW6NMkraRNmXadBYvhQ9GXP9Dq3N1NfKym2+pGc48TdzByl2QBwdHU2/fv0AqFevHkeOHCEhIYH4+Hi6dOli8w4KIYS95SzZ7Lz5wypLPWJJmygxS7pE22Qq+9kuv2FQ91tpE2slbaKsW77FjxvJrgQHGOgcVbSKLS3C06kdmElahpbYWwt5iNJTrIA4KysLV1dX/v77b6vtlStXtpRdE0KI8iQ9Q8PBU+bRUGcfIYZcSzjLxLoSs3W6hKprm2Qq+WZz5ZqOTXskbaIsm7vcPJnu8QeuF7lMnkYjaROOVKyAWKfTUbt2bak1LISoMPYd98Ro1FC9ShY1qjnvhDqVLOF8d46ccefACU90riabpUuodK7Q737zPhdI2kSZdSNZy++3JsbdvlTznaivmaUb/cku/krf4i4UO2Xirbfe4s033+T69eKdZCGEKIvi1PrDEc49oU6lll47eNKDTIM8IcWVU13iJpV8bT94pC4B/YukTZRZi9ZUwpDlQpN6aTRrkF6s+3ZonkJlv2yuJblKzelSVuyA+IsvvmDjxo0EBwcTHh5Oy5YtrX6EEKI8yVmQQ/KHAWoHGqjsl022UcPfJ2ViXXEtiDVfKlfzfW2tS+tkKvtlE39dx0ZJmyiTfriVLlHc0WEAV1fo1SERkLSJ0lbspZv79Oljh24IIYRjqCPErSR/GDDnMbYIT2PNDl92H/GUvOpiOHRKz98nPdC5muh9h7qzJWVOm7jBt0sCWBBbmftbpdjlOKJkzlx0Y9MeHzQahceiS3YlvU/nROb8XpUlG/yZNva8XLkqJcUOiCdOnGiPfgghRKlLkwl1+Wp5KyDec1RGiItDTZfo0S7ZLukSqoHdzAHxL2v9+fz/zuJa7L/kwl5+XGkeHe4cdZNagSWbk9CjXTIe7ibOXHRn3zEPmocXL+1ClIxUXhdCOK19xzwxmTQEVskiOEAm1KkspddkYl2xqAHxQBtXl7jd/a1uUsUvm6s3dGzc42PXY4miU5ScdImi1h7Oj6deIbp9EiBpE6Wp2AGxi4sLWq22wB8hhCgvchbkSJXLkrmolSb2HfOUiVtFdPCknoOn1HSJJLseS+cK/bqYg+4FsVJtoqzYfcSTI2c80LubLOenpCzl1zb4333HRJEU+0LLr7/+avV7VlYWe/bsYc6cObz33ns265gQQthbzoIcki6RW/3amXh5GElN13L0Hz2RoRmO7lKZp44OR7dPxt/H/t8iBnW7wTe/mtMmvhgnaRNlgVp7+OGOifh5m+5qXw/dl4RWq7DvmCenL7hRt4bBFl0UhSj2W6h37955tg0YMIBGjRoxf/58nnrqKZt0TAgh7G3XIS9A8odv5+ICzRuks2WfN7uPeEpAXAQL19hnMY6CdI66SVX/LBISdayP86Fb26KthibsIzsbfvrz7tMlVFX8jXRscZN1u3xZst6fMYPj73qfonA2yyFu164da9assdXuhBDCrlLTXTh8Rg9IQJwfySMuuoMn9Rw65YGbzsTDdqoucTvXXIt0LJRFOhxu9Q5frlzTUcUv25L/e7ckbaJ02SQgTk9P57PPPqNGjRrFvu+XX35JSEgIer2etm3bsmPHjgLbZmVl8f777xMWFoZer6dZs2asXLnSqs3XX39N06ZN8fX1xdfXl/bt27NixQqrNp07d0aj0Vj9PPfcc8Xue2kxGmH9Rhd+Wh/E+t2+ktMnhA3sO+aByaQhqKpBJtTlQ80j3n1EAuI7UVeNi26XfNeXyotDrXX8y9pKsqqZg81dYR4dfrTHdXQ2Sl9RA+LNe725ekNyYuyt2M9wpUqV0OSafaIoCjdv3sTT05O5c+cWa1/z589n7NixzJgxg7Zt2/Lpp58SHR3N0aNHqVatWp72b7/9NnPnzuWbb74hIiKCVatW0bdvX7Zu3UqLFi0AqFmzJlOmTKF+/fooisKcOXPo3bs3e/bsoVGjRpZ9jRw5kvfff9/yu6dn2fzQX7wYXn4Zzp/XA80AqFnNwPTXztGvS6JD+yZEeZazIIeMDucnZ4TYA0VBJh0WQFFyJrbZazGOgnRqeZOASllcvaFj3S4fureTtAlHSElz4dd1/gA8YYN0CVXtwCxaRqSy+4gXyzb6MaL3NZvtW+RV7ID4k08+sQqIXVxcCAgIoG3btlSqVLzLNtOmTWPkyJEMHz4cgBkzZvDHH38wa9Ys3njjjTztf/jhB9566y1iYmIAeP7551m9ejUff/yxJRjv1auX1X3+9a9/8fXXX/PXX39ZBcSenp4EBgYWq7+lbfFiGDDA/IGb24V4HQPGhbLoo1MSFAtRQnGHzfnDMqEuf5GhGehcTSSluHL6ghuhNWVST34OntRz5IwH7m4mHu6YWKrHVtMmZi4OYMHqShIQO8iS9f6kZWipVyuDto1tu+Jln86J7D7ixZL1/hIQ21mxA+Jhw4bZ5MAGg4G4uDjGjx9v2ebi4kK3bt3Ytm1bvvfJzMxEr9dbbfPw8GDz5s35tjcajSxcuJDU1FTat29vddu8efOYO3cugYGB9OrVi3feeafQUeLMzEwyMzMtvycnJwPmNI6sLNtfbjUa4aWXXG8Fw9ZDMwoaNCi8/HFNYjpcp6JXu8symaz+FRVfaZzznbdKrjULT5HXVj40WmhcL509R7zYecSDWsH2nVhXXt/nP8X6A9C9XRIentlklXL3+3W9xszFAfy6zp/p4/5B56rc+U5lRHk957f73x/mdInHHrhGtmICG56CBzveYMKMGvy53ZcbKeDtWb6fK4CsW6N8WdnZYIf4Kc/xiniMYgfEs2fPxtvbm4EDB1ptX7hwIWlpaQwdOrRI+0lISMBoNFK9enWr7dWrV+fIkSP53ic6Oppp06bRsWNHwsLCWLNmDYsXL8Z4W1LtgQMHaN++PRkZGXh7e/Prr78SGRlpuf3xxx+nTp06BAcHs3//fl5//XWOHj3K4sWLC+zv5MmT8y0r9+eff9ol3eLAgSpcuHBfgbcraDh/xZ2pqzNp0sQ5vjXGXr7s6C6IUmavc56eruXoP60AuFHpFMsvZt7hHs6pSs1qcMSLRbtM6CMulsoxy9P7XFFgzsoIAOpHnWL5xdJ5jnIzBmrw8wvhWpKej1YZaNHiaqn34W6Vp3N+u+vX3Vmz0xeA4JaHWX7RtiPEigcEBoZw+bI3U5YbueeeSzbdvyPFbtpUKsdJSyvaVcBiB8STJ09m5syZebZXq1aNZ555psgBcUlMnz6dkSNHEhERgUajISwsjOHDhzNr1iyrduHh4ezdu5ekpCQWLVrE0KFD2bBhgyUofuaZZyxtmzRpQlBQEF27duXkyZOEhYXle+zx48czduxYy+/JycnUqlWLHj164Ovra/PHmpxctIS9OgQRE+xu8+OXJVkmE7GXL9M9MBCdiyyu6Azsfc637PXGZNIQHGDgicZVbL7/iuJsS4XVqyHlYjVigu272ER5fJ/vP+7BhQs+uLuZeKsX+HoHO6Qfj3ZLZuYves7uqc9bD+oc0oeSKI/n/HbT11fHZNLQrkkKT0X5AX42P8ZjXVP4ZJ435w+EEjOg/CfzZ6WnE3vjBt07dEDnY/+VFtUr+ndS7ID47Nmz1K1bN8/2OnXqcPbs2SLvp2rVqmi1Wq5cuWK1/cqVKwXm9gYEBLBkyRIyMjK4du0awcHBvPHGG4SGhlq1c3Nzo169egBERUWxc+dOpk+fnm8gD9C2bVsATpw4UWBA7O7ujrt73sBTp9Oh09n+A6hWrSK2C8gutx8kxaVzcXGaxyrM7HXO9x31Bsz5w/KaKlirCHOaxJ6jXqX2PJWn9/mSteYvUz3vSaKKL9iwkmmxPNL9BjN/qcZvGyox882zNqtyUFrK0zm/3U8rza+BJ2Ou2+0x9Ls/kU/mBbJ8sz+YXMrd+c3j1jw0naurXeKn2xX1GMU+e9WqVWP//v15tu/bt48qVYo+0uLm5kZUVJRV7WKTycSaNWvy5PveTq/XU6NGDbKzs/nll1/yXSwkN5PJZJX/e7u9e/cCEBQUVOT+21uHDlCz5p1ndn/yY3VOX3ArnU4JUUHkLNksE+oK07R+Oi4uCleu6biUUN7/CttW7uoSA0tpMY6CdGyRQrXKWVxPcmXtTttfsRT5O3RKz+4jXrhqFQZ1t111idu1b5JKtcpZJN50ZUOc/UdUnVWxA+LHHnuMl156iXXr1mE0GjEajaxdu5aXX36ZRx99tFj7Gjt2LN988w1z5szh8OHDPP/886SmplqqTgwZMsRq0t327dtZvHgxp06dYtOmTTzwwAOYTCbGjRtnaTN+/Hg2btzImTNnOHDgAOPHj2f9+vUMHjwYgJMnT/LBBx8QFxfHmTNnWLp0KUOGDKFjx440bdq0uE+H3Wi1MH26+f+3B8UaFEDBxUVh6UZ/Igc14r3/BpGeUf4vpQhRGnKWbLZtvl9F4+VhIrzOrVFiqUdsZf9xD46d1ePuZqJXB/umk9yJVgsDupqDcjVIF/an1h7ueU8SVf3tt0CAVoulgsmS9f52O46zK3ZA/MEHH9C2bVu6du2Kh4cHHh4e9OjRgy5duvDvf/+7WPt65JFHmDp1KhMmTKB58+bs3buXlStXWibanT17lkuXchLIMzIyePvtt4mMjKRv377UqFGDzZs34+/vb2kTHx/PkCFDCA8Pp2vXruzcuZNVq1bRvXt3wDwyvXr1anr06EFERASvvvoq/fv3Z9myZcV9KuyuXz9YtAhuX++kZvUsfvnoFAd+PsT9rZLJyHTh3f8G0/iRRizbaPv8JSEqkpQ0F47ICnVFJgt05E8NPGPuTcLHy/Ez/wfeCoh/Xe9PlizSYXcmE8y7FRA/+aD9J7bnXrXu9lKswjaKfQ3Mzc2N+fPnM2nSJPbu3YuHhwdNmjShTp06JerA6NGjGT16dL63rV+/3ur3Tp06cejQoUL399133xV6e61atdiwYUOx+uhI/fpB796wKTaDS+uPElTDhQ5tDZZSa2u+Ps7C1ZUY+0lNTl1w5+Gx9XjwvkSmv3aOMKkbKkQee456oigaalQzUL2KRA530iI8jXkrqsgSzrkoCixcc2sxDgenS6g6tEihepUsrlzTsWaHLw/cU7SJRKJkNu3x5uxld3y9jDx0n/2vEHRtfRNvTyMX4t3YdciT1o3ky7ytlTgDvH79+gwcOJCHHnqoxMGwKBqtFjp3NPFY50t0bplsVXdYozGvjnRk0UFeH3oZnauJPzb702hQIybMCCJN0iiEsBJ3WE2XkD8oRWEZIZaA2GLfMQ+On9WjdzfxkIPTJVRaLQzoImkTpUVNlxjQ9QYeevsP2erdFXreY36tSdqEfRQ7IO7fvz8ffvhhnu0fffRRntrEovR4e5qY8uIFDvx8iO5tk8k0uPDBt8FEDmzEkvV+colFiFtylmyW/OGiaN4gHYAzF925kVzBVwEqogWrb6VL3JNUphZKUJeO/nW9P4YsGQyxl4xMDQtvvQaeiCm9dQByp00I2yt2QLxx40bL0sm59ezZk40bN9qkU6LkwkMyWfXFcRZ9eJJa1Q38c8mdvq/VI+blehz7p2LXKxaiKGSEuHgq+RqpW8NcpUfSJm6lS9wKhtQAtKy4t1kKgVXM1QhWb5dqBPbyx2Y/klJcqVndQKeWKaV23AfvS0LnauLQKQ/5e24HxQ6IU1JScHPLW+ZLp9MVufixsC+NBvp3TeTwooO8NeISbjoTK7f60eTRSN78MpjU9PJZ71GIu3Uz1YWj/8iEuuJq0cD8XO056uHgnjje3qMenDhnTpd4sBRyR4sjd7UJNcdZ2N4Py80lZgc/cJ3SLJ/s523i/lY3AUmbsIdin8omTZowf/78PNt//vlnq+WRheN5eZiY9MJF/p5/iJ73JGHIcmHy7CAaDmjEotUyU1U4H3VCXa3qBqpVlgl1RdUiXCpNqNR0iQfvLVvpEipL2sQ6SZuwh2uJWpZvMdd6fqJn6aVLqCRtwn6KXWXinXfeoV+/fpw8eZIuXboAsGbNGn788UcWLVpk8w6Ku1e/diZ/TD/B0g1+vDKtFmcuujPwjTC6tUnm83FniQgpeNESISqSOMkfLhF1Yp2zp0yYF+MwT6Yqa+kSqnubpRBU1cClBDdit/vw4H1y5daWFq6uRFa2C80bpNG4XkapH//hjkm8MAW27ffmUoIrQVXli72tFHuEuFevXixZsoQTJ07wwgsv8Oqrr3LhwgXWrl1rWS5ZlD0aDfTunMShBQeZMPIi7m4mVu/wpemjkbz+WQ1S0iSNQlR8lgl1EZIuURwtbj1fR87onTrlas9RD05dcMejDKZLqFxcYEDXRCAneBe2M3eFOV2iNCfT5VajWhZtG5vzlpfKKLFNleiT7cEHH2TLli2kpqZy6tQpBg0axGuvvUazZs1s3T9hYx56hfeevcTBBQfp1SGRrGwXPvpfIBEDGjH/z0qSRiEqtLjDXgC0ipSAuDiCqmYTWCULRdGw/7jz5hGrAeaD9yXh5VH20iVU6jLCv23wI9MgaRO2cuq8G1v2eaPRKDwW7bgrBJI2YR8l/qq/ceNGhg4dSnBwMB9//DFdunThr7/+smXfhB2F1TSw9JOT/P7pcUJrZHIh3o1H3wyl6/P1OXhS7+juCWFzySkyoe5uOHsesaLk5A+rAWdZdU/TVIIDDCSluBK73dfR3akw5q00fyHq2vomwQFZDuuHGhCv2eFDUorzXrGxtWI9k5cvX2bKlCmWRTl8fX3JzMxkyZIlTJkyhdatW9urn8JOHrwvmYMLDvL+cxfQu5tYt8uX5o9H8uonNUmWN5qoQNT819qBmQRUkry74nL2POK4w56cvuCOp95IzL1lOy/XxQUGdpNFOmxJUWDureoSTzooXUIVEZJJREg6WdkurNji59C+VCRFjnh69epFeHg4+/fv59NPP+XixYt8/vnn9uybKCV6d4V3nr7M4YUH6dP5BtlGDdPmVSe8f2PmragsaRSiQshZkENGh0tCHSF21tJrau3hhzqU7XQJ1cBb5dd+2+AvaRM2sPOgJ8fO6vFwN9H3/kRHdycnbULKr9lMkQPiFStW8NRTT/Hee+/x4IMPotXKikUVTUiwgV+nnmLFZ8epXzuDy9d0PPFOXTo/24ADJySNQpRvlvxhCYhLRB0hPnDCw+nKeeVOl1ADzbKufdNUalQzkJyq5c+/JG3ibqmT6fp0TsTHy/FfiNSAePlWyRO3lSIHxJs3b+bmzZtERUXRtm1bvvjiCxISEuzZN+EgD9yTzIGfD/HvURfw1BvZuNuHFoMjeXlqTRJvyhchUT7JCPHdCQk24O+TTVa2C4dOOdcX5F2HPDlz8Va6RBmtLnE7F5ec4F3SJu5OVjb8/OetpZodUHs4P60j0wgOMHAzVcvanbIqoS0UOSBu164d33zzDZcuXeLZZ5/l559/Jjg4GJPJRGxsLDdv3rRnP0Upc3dTGD/8MocXHWRA1xsYjRo++7k64f0bMef3ypgc/wVZiCJLSnHh+Fl1Qp3UIC4JjcZ5J9apo8O9OiThqS8/OWRqreTfNvqTkSmjiCUV+5cvV2/oCKiURY92ZSN/3MUFendKBCRtwlaKPWvKy8uLESNGsHnzZg4cOMCrr77KlClTqFatGg8//LA9+igcqHZgFgs/PMWfXxwjvE4G8dd1DHu3Lh2eDmevk+YSivJnz60Ark5QJlX9jQ7uTfnVIjwdcK6JdYqSkz9cVhfjKEjbxqnUrG4eRVy1TdImSkpdqvmx6Ou4Fns5M/tR0yZ+2+gvg1Q2cFdlBMLDw/noo484f/48P/30k636JMqg7u1usv/nQ3z44nm8PIxs3e9N1JMNGf1hLW4kSxqFKNt23coflgU57o6aR+xMI8Q7D3ryzyV3vDyM9LynfKRLqHKnTSxcI2kTJZGc4mKp9/tEz7JVbq9zVAp+3tlcuabjrwNeju5OuWeTulparZY+ffqwdOlSW+xOlFFuOoVxQ69wZNFBHul+HZNJw5cLq9GgXyNm/VZFvqGKMktdslkW5Lg7asrEvuMeGJ1koD13uoRHOUqXUFnSJjb4k54haRPF9et6fzIyXQivk1HmPj/cdIplxURJm7h7UmhWFFvN6ln8PPk0a2ccJTI0nYREHU99EMI9I8ItgYcQZUnOhDrJH74b4XUy8HA3kZqu5fg5d0d3x+7Kc7qEqm3jVGpVN5CSpmWVVJsoNjVd4ome19CUwe8TatrEr+v9pUTqXZKAWJTY/a1S2PvjIT5+5Rw+Xka2/+1N6yERPPfv2lxLlDQKUTYk3tRy4tytCXWSMnFXtFpo1uBWPWInSJvYcdCTs5fd8fY08kD78pUuodJochbpUIN7UTQX4nWWCg6PP1C20iVUD7RPxt3NxIlzeqer/mJrEhCLu6JzhbFPxHP0l78Z3PMaiqJh5uIAGvRvzH8XV3Way6qi7FLzXUOCM6kiE+rumqXShBNMrFsQa16qt7ymS6jUpaaXbpS0ieL4aVVlFEXDvc1SCK1pcHR38uXjZaJbG3PlC0mbuDsSEAubCKqazdwPzrDhv0dpUi+N60muPPvvOrQbHsGOvyv+H05Rdlnyh6X+sE04yxLOJlPudImyOTpYVG0apVE7MJOUNC0rt8lSv0U1d4X5C5Gjl2q+E8uqdbcm/4mSkYBY2FTHlinsnnuY6a+dxdfLyK5DXrQbHsHISbW5eqMM1asRTkPyh21LLb22+4hnhc5Z3HHQi3NX3G6lS5SN2rMllTttQhbpKJoDJ/TsO+aJztVkee7Kql4dktBoFHYd8uLcZZ2ju1NuSUAsbM7VFV569CrHFv/N0IcSUBQN3y4JILx/I75aGCBpFKJUyQixbTUOS8dVq3Aj2ZWzl90c3R27UQPH3p0S0buX/8h/0K2gbtkmP0mbKIK5tybTPXhfEpX9yvYfrepVsrm3WQpgriYiSkYCYmE31atk8/27/7D52yM0b5DGjWRXRn1Ym9ZDGrJtv9RMFPZ3I1nLyfPmiSYtZUKdTbi7KTQKyxklrohMppy6vWod3/KudaM06gRlkpquZcVWSZsojMkE81aa0yXKWu3hgkjaxN2TgFjY3b3NU9n1w2G+GHcWf59s9hz15J4REQx/rw7x1yWNQtiPGrDVrZFZ5kd5ypOW4WoeccVcrfKvA16cv+KGj5eR6HKeLqHSaHJGiSVtonAbdntzId4Nf59sS53fsk4NiNfH+XA9Sao8lYQExKJUaLUwatBVji0+yFO9EwD4fllVGvRrxOc/B5Cd7eAOigopJ11C8odtqUV4xZ5Yp06m692xYqRLqAbmSptIk7SJAv3whzldYmC3G+Xm/IfVNNCkXhpGo4Y/NssVgJKQgFiUqoBK2Xz7zj/89f1hohqmkpTiyktTaxP1ZEM275U0CmFblgl1ki5hUxV5Cefc6RLldTGOgrSKTCMkOJO0DC0rtkjQlJ/0DA2L1prPf3lJl1BZ0iak/FqJSEAsHKJt4zS2f3+EGeP/obJfNvuPe9Lh6QiefCeESwk5aRRGI2yI82HjxhpsiPORCXmiWOIOm79klbUlV8u7Zg3S0WgULl5148q1ipX2tG2/Fxfi3fD1MtKjXcVIl1BZpU3IIh35WrbJn5upWuoEZXJf8xRHd6dY1IB45TZfmThZAhIQC4fRauHZ/gkc++Vvnul7FY1GYe6KKoT3b8wn86qxINafkF5N6P58BNOmtaL78xGE9GrC4rX+ju66KAeuJ2k5dcG8vLBMqLMtb08TDWpnAhUvbUINFHt3SsTdrXxcLi8OddT7901+pKZLCHC7H5abJ9MNfuA6LuXs6WkRnk7tQPMVgNjtskx3cZWz0y0qoir+Rma+dZYdc47QplEqN1O1jP2kFo+MD+V8vHVNxQvxOgaMC5WgWNyRejk/rGYGlXzl0oKtVcQ8YpMJFlXQdAlVy4g06tYwB03Lt0jQlNvVG66svFWBY3A5S5cA8xUASZsoOQmIRZnRKjKNbbOPMPPNM7hoFEBz6yeHcuv3Vz6uJekTolA5C3LI6LA9WJZwrkB5xFv3e3HxqjldonvbipUuocqdNrFQ0iasLIitRLZRQ8uIVCJDMxzdnRJRA+KlG/1lsnoxVazkL0dITTVf+7+dVgt6vXW7gri4gIdH4W3T0iAjA9zcrPebkUGBy0VpNPZpC9b9LU7bzEzzMEwBXDw8aFA7E5OiwZ0MtOQf9V67Apt2e9G59a3nymCg0AhZrzc/xqK0dXfHcq0sK4tCP1WK09bNLee1Upy22dnm9gXR6cyroZSVtkaj+TkuiKuruX1hbU0mtBkZ5mO6u1u2kZlZtP2aTPz9N3iSSvt6CZCebt1WqzU/x2B+7WYU8sevOG1dXHL6C3mPW9K2t78/i9PWTp8RrUKv40kljhw25d+fu/mMKEwxPk+K9b7X61kQa75cPqDDFdyNaVDQ01zOPyMe7XCez+f4sHajjtTrmXh5mApsa9fPCPV9np6OVX5CUT4j8mtbzM+I29su+sMdT1IZ3v28+Zjl8DOiQ/MUKvtlk56UybYdLnRokU88UUqfEQW2TU83n/fbthX6XvbKNek+I6Pw9/LtbQuLv3JTRIkkJSUpgJJkPt15f2JirO/g6Zl/O1CUTp2s21atWnDbiAhF2bUr5ycoqOC2oaHWbUNDC24bFGTdNjKy4Lb+/tZtW7YsuK1eb9323nsLbguKsmuX8uOkkwooygIGFNr201FHcvb70EOF7zc2NqftwIGFt126NKftk08W3nb+/Jy2I0cW3nbOnJy2L71UeNsZM3LajhtXeNtPP81pO3Fi4W2nTMlpO2VK4W0nTsxp++mnhbcdNy6n7YwZhbd96aWctnPmFNo2++mnc9rOn1/4fp98Mqft0qWFtx04MKdtbGzhbR96KKftpk2Ft+3a1fr1Xljbe++1bqvXF9y2ZUvrtv7+BbeNjCyVz4isBrb9jDDs2KEsWbJEMRbhM8Ly07Vr4W03bSryZ4RxVawSVDVTAUU5fd/jhe9XPiPMP2XgM0IZOVI+I8DqM2LoQ1eVeAqJI0rpM6KwOCLD11cxJCXlxD2dOhW8X09P6xgpJqbw5y23AQOUJFAAJSn38fIhKROizAmqWsgoQy5vflmTTs80YN6KypI+IazcSJbC9PbmWsGuL+446MWlBDf8vLOpVa1on0FClEVq2oQoHo2iKIqjO1EeJScn4+fnR9LFi/j65jMxwR4pE1u2gK8v+PnlbK9gKRN4eGA0QkivJiTEG3Ehv7YKejeFGwYvlFtp8IG+qQyJvsKwXtdoWDefS2aSMlF6bW2QMpFlMrHq0iWia9VCV4KUiditXvR5qRZhNTLY//PhvG0lZcImbR95I4TfN/szZfR5XnzkqnX7Yn5GZJlMLL94kZgqVdAV3NJuKRMvflafLxZWZ+hDCXz/5vEK/xmx76iee55uiIebiTPLDuDtaSqwbXH2W6S2t973lvd5UBA6B6ZMKAo0fbQhpy7q+fbtMzwWfaNcf0akZWio3aU+6QYXtn13mKYNMgpsC5R6HJGVlsaqGzeI7tkTnRo/2TFlIvnGDfyCg0lKSso/Xrulgn3HdwAvL+snv7B2xdnn7dQXWu43B1i/+O6kLLS9vf/50Gph+mvnGDAuFMAykQ5Ag/nN9cOkU7RplMrsZVX4dklVzl724qOFoXy0MJT7mt/kmb4JDOh6Aw99Pm9c9YOrKHS6nA9QR7V1dS36cFxZaKvVWgctJWlrMmHU662fo9u/OBZi11Ef0vAiMjLzzvfRaIre3+K0hbLR1o7v+0aNNCzY7MXOU1XBo5CarcX9jChqvasifJ5YFPK+Nxph0Vpz/vCgbjec4jOiaTMIrqXlxDkv/ogL5JEeN2yy3yJR3/fq+9zDo+BzXpzPk2J8RuRuu/2AF39frIKXh5GHow1591HOPiM89Qod7slmyfpKLP4rmKbNLhV+h9KODRQF4+3BvT0/04oYf0nKhCiT+nVJZNFHp6hx26XLmtWzWPTRKfp1SaRm9Szeefoyp377m+XTj9On8w20WoXNe30YMrEuwT2b8vLUmvx9ohhvHlEhWJZslgU57KqiVJrYss+by9d0+Ptk063tTUd3p1RoNDlLOS+Ide5qE2rt4b6dE60nGJZjlvJrG/wd2o/yREaIRZnVr0sivTslsm63FyuOp9Czvjf3t0zNU9RDq4We9ybT895kLl7VMXtpFb79rSpnLrrz2c/V+ezn6rRvmsIzfRMY1P06nvmNGosKJafkWhFnF4sSURc8OfKPnvQMTf5XZMoBNSDs2zkRN135fAwlMajbDSbPDmL5Vj9S0lxy0iaciCFLw/w/zQHxEzHlr/ZwQR66LwmtVmHfMU9OX3Cjbo1C0k4EICPEoozTaqFT1E06drxAp6ib+Va4yy04IIu3nrrMySV/s+qLY/TvcgNXrcK2/d4Mfy+E4AeaMvrDWuw7VozLM6JcSUjU8s8lWaGuNAQHZBFQKQujUcOBE+XzPWVOlzAHxOqIqbNo1iCd+rUzyMh04fdNfne+QwW0apsv15JcCaySRdfWFaf2dBV/Ix1bmK92yCIdRSMBsaiQXFygR7ubLProFOf+2M/k0ecJrZFJUoorXy6sRvPHI2k3LJxZv1WR5UsrmLjD5nyx+rUz8PN2vhGv0qTR5HzpKK9pE5v2eHPlmo5Kvtl0beMc6RKq3It0LHDSRTrUdInHoq9XuMopkjZRPBIJiAovsGo2bwy7wvFf/yb2y2MM7HYdV63C9r+9eeqDEIIeaMrzk2uz50j5HOES1iz5w7JCXako70s4L1zjnOkSKnVUfPkWP26mOldIkJTiwtKN/gA8EXPNsZ2xg96dkgDYvNebqzcqWLRvB8716hdOzcUFurW9yYIppzm/fD8fvnieerUyuJmqZcYvAbR8IpLWQyL45teqTveHoSKJk/zhUmUZIS6HAbHRCItuBcSDujtXuoSqaf10GtTOINPgfGkTv6ypRKbBhYZ102kRXkhJs3KqTpCBlhGpmEwalm10rnNbEvJXXzil6lWyGTf0Ckd/Ociar4/xSPfr6FxN7DrkxTP/qkNwz6Y8+6/aluBKlB+WCXWSP1wq1EDiwAkPsgopm1sWbdzjTfx1HZX9sulSgfJHi0Ojyfky4GxpE3NXmNMlnoy5bilXXdFY0iYkj/iOJCAWTs3FBbq0vsnPk09zYcUBpr5yjga1M0hJ0/LfXwNo9WRDop6IYOYvVUlOkbdLWXf1hitnL8uEutIUWiMTHy8jmQYXDp8uX2lHC2Jzym3pnPiK8qDu5uoKK7b6Oc3n3LnLOtbH+QDw+AMVp7rE7dSA+M/tvqSkOce5LSl5doS4JaBSNq8+Ec+RXw6yfuZRHn/gGm46E7uPePHcZPOo8chJtdl50LPQRbeE46gj+g1qZ+ArE+pKhYtL7jzi8hMQZ2fD4nX+QE5A6Kwah2UQXsecNrFsk7+ju1MqflxZGUXR0LHlTeoEVdySZI3DMgiraT63q7YVvEqbkIBYiDw0GugUlcK8SWe4sGI/08acIyIkndR0Ld8uCaDN0Ia0GNyQrxYGkOQkoynlRc6CHJI/XJrK4wIdG/f4EH9dRxW/bO5v5VzVJW5nTpswfylY6ARpE4oCPyyvAsATPSv2lyGNRtImikr+mgtRiKr+RsYMjufQwkNs/OYoT/S8hrubiX3HPBn1YW2CH2jKiPfq8NcBLxk1LgMkf9gxWpbDShOWxTjuv+HU6RIqtfzaiq2+FT5tYv9xDw6e8sBNZ3KK2tNqQPz7Zr9yl+dfmir2q14IG9FooEOLFH744AwXV+zn01fPERmaTlqGltnLqtJ+eATNHmvIF/MDSLx5h9VDhN2oNYhlyebS1SIiJyA2lYNMlexs+GWtP5ATCDq7RmEZNKybjiErpxRZRaXWHu7VIQl/H6ODe2N/7ZukUq1yFok3XdlwK29a5CUBsRDFVNnPyMuPxfP3/ENs+e4IQx9KQO9u4sAJT178T22CHmjK0IkhbNkro8alKf66K+euuKHRKJZL+KJ0NAzJQO9uIiVNy8nz7o7uzh1t2O1DQqKkS+Sm0eTUJFZHzysio9GcPwwVs/ZwfrRaeLhjIiBpE4WRgFiIEtJo4J5mqXz/7j9cXLGfz//vLI3D0snIdOF/f1ThvqcjaPxIJNN/qsb1JBk1tjc1fzi8TgY+XuVgmLICcXWFJmHm8mvlIY9YDfj6d7lR4VYnuxvqaPmqv3wr7PyIdbt8uJTgRmW/bGLudZ5Se7lXrZOBmvxVzFe8EKWskq+R0Y9cZf/Ph9g2+wjDeyXg4W7i0CkPXvm4FsE9m/LkOyFs2uMtH0Z2krMgh4wOO0LLiPKRR2xOlzAHxM6QP1ocjcIyiAy9lTZRQZf7VSfTDep2w6lWJuza+ibenkYuxLux61DZfo86igTEQtiQRgPtmqQya+I/XFq1jy9fP0vT+mlkGlyYu6IKHUeGEzkwkk/mVeNaoowa29KuW/nDMqHOMcpLpYl1u3y4luRKVf8sOkdJusTtBnatuIt0pKa7WErtPdHTOdIlVHp3hZ73mJdylrSJ/ElALISd+HmbeGHgVfb+eJjt3x/mqd4JeOqNHDnjwdhPzKPGg98OYUNc3lFjoxHW7/Lmp5WVWL/LG2PFn/dx1+KOqCXXJCB2hJwRYo8yfRVk4Ro1XSJR0iXyoY6ar9rmW+EmCC/d4EdKmpa6NTK5p5nzlWbMnTYh8pKAWAg702igTeM0vn3nHy6t3M+M8f/QIjwNQ5YLP66sQudnw4no34ipP1Tn6g1XFq/1J6RXE+5/LpzH3w7l/ufCCenVhMW3ZsWLvK5cc+W8TKhzqCb10tFqFRISdVyI1zm6O/nKyobFt9Il1OWKhbVGYRk0Ck0nK9uFpRv8HN0dm5q7Qq09fK3CLtVcmJh7k3HVKhw65cGxf8r+5NfSJgGxEKXI19vEs/0T2D3vMLt+OMwzfa/i7Wnk2Fk9/ze9JkHRTeg/LpTztwUUF+J1DBgXKkFxAdT84YiQDLw9ZUKdI+jdFSLrlu2JdWq6REClLDq2kHSJgqhfFipS2sSVa66s+su8UtvgCrxUc2H8fYx0aW2eSChpE3lJQCyEg0Q1TGPmW2e5uGI//33rH6IapmI0uQCaWz85lFu/v/JxLUmfyIfkD5cNLcLNAXFZnVinrsIm6RKFU9Mm/vzLlxvJFSNtYn5sJYxGDa0jUwkPyXR0dxxG0iYKJgGxEA7m42ViZN8Epr58vtB2ChrOXXFj0x7vUupZ+ZGzZLMExI5UlifWZWXD4nVquoRzjhAWVcO6GTQOM6dN/FZBAqe56lLNTlJ7uCAPdzRPrNu235tLCfKtMDcJiIUoIy4lFC3vsqjtnIllyeaGzjdRpiwpy6XX1u705XqSK9UqZ9GxRYqju1PmqV8aFlaAtImjZ9zZecgLrVbh0R7OnTteo1oWbRubX/8VtbReSUlALEQZEVQ1y6btnMXlBFcuXnXDxUWheYN0R3fHqTVvYA6Iz11xI6GMlRXMvRiHtmx1rUyqSGkT6mS66HbJVKuc7eDeOJ6kTeRPAmIhyogOLVKoWc2AhoJrVnnqjbRvIqNbuanl1mRCneP5epuoVysDgD1lKG0iKxt+vTWJaJAsxlEkESGZNKmXRrZRU64nYCkKzF1xa6lmJ6s9XBA1IF6zw4fkCroiYUnIMyFEGaHVwvTXzgHkExQrgEJahpbh79clWwY5LHYdkgl1ZUlZzCNes8OXG8muVK+SRQdJlygy9ctDea42sXWfF2cuuuPtaaT3rUDQ2UWEZBIRYs4RX76lYpXWuxsSEAtRhvTrksiij05Ro5p1WkSt6lmMG3IFV63CT6sq8+QECYpVORPqJH+4LCiLecSSLlEyatrE6u2+XE8qn0+culRz/y438NSX4RVjSpklbaIcj/7bmkwxFKKM6dclkd6dEtm0x5tLCTqCqppHtbRaaN80hYGvh/Hzn+ZLgD+8f9rpy0dZJtTJCHGZoJZe211GAmJDlkbSJUooPCSTZg3S2HfMkyXr/RnRu3ylHGQaNJbR7Sd6SmWR3Pp0TmTK90Es3+pHpkGDu5t8WZARYiHKIK0WOrdK4bEHbtC5VYplVKtP5yQWfXgSnauJn/+szBPvOPdI8cWrOi4l3JpQFy4T6soCNWXi+Fl9mchPXLPDh8SbrgRWyeK+5pIuUVwDu5bftIkVW82pMsEBBu5vJQux5NY6Mo3gAAM3U7Ws3enj6O6UCY7/tBJCFEvvzkn88tEpdK4m5sdW5vG365LlpEGxmi7RMCQDLw+ZUFcWVKucTY1qBgD2HXf8KLEayA3oKukSJaGmTazZ4cu1MlY55E7U2sOPP3Bdzv1tXFygd6dEQNImVA4PiL/88ktCQkLQ6/W0bduWHTt2FNg2KyuL999/n7CwMPR6Pc2aNWPlypVWbb7++muaNm2Kr68vvr6+tG/fnhUrVli1ycjIYNSoUVSpUgVvb2/69+/PlStX7PL4hLCHXh1zguKFqyvz+FuhThkUS/5w2dQyXM0j9nBoPwxZGn5d5w/kBHaieBrUyaR5g/JXbeJGspZlm8wTxiRdIn9qHvFvG/0xyXiCYwPi+fPnM3bsWCZOnMju3btp1qwZ0dHRxMfH59v+7bffZubMmXz++eccOnSI5557jr59+7Jnzx5Lm5o1azJlyhTi4uLYtWsXXbp0oXfv3hw8eNDSZsyYMSxbtoyFCxeyYcMGLl68SL9+/ez+eIWwpV4dk1j8n1O46UwsWlOJx950vqBY8ofLphZlZGJd7HYfklJcCapq4N5mki5RUgPLYbWJRWsqYchyoXFYOk3rSzpVfjpHpeDnnc2Vazr+OuDl6O44nEMD4mnTpjFy5EiGDx9OZGQkM2bMwNPTk1mzZuXb/ocffuDNN98kJiaG0NBQnn/+eWJiYvj4448tbXr16kVMTAz169enQYMG/Otf/8Lb25u//voLgKSkJL777jumTZtGly5diIqKYvbs2WzdutXSRojy4qEOSSz+z0ncdCZ+Wet8QXHc4Vsl1xpKQFyWtCwjpdcWWtIlEuWS+V2wpE3s9C1zC64UJHftYY3GwZ0po9x0Cg/eZ17KuTyN/tuLw+anGwwG4uLiGD9+vGWbi4sL3bp1Y9u2bfneJzMzE71eb7XNw8ODzZs359veaDSycOFCUlNTad++PQBxcXFkZWXRrVs3S7uIiAhq167Ntm3baNeuXYHHzszMtPyenJwMmNM4srJKYeWw7GxzhXGTCWe7tpF16/FmOdnjLqoe9ySy8KMTDBxXj1/WVmLgG6HM+9dJ3HTld9ZwUc75xas6Ll/T4eKi0Kh+qrw+ypDGDcwpLIdO6bmZrqB3v/Nr0dbv80xDziX+fl2vyevjLoTUTKd5eCp7j3rxy1o/RvRJsMl+7fXZ/s8lNzbu9kGjURgYLee+MA91vMGPK6vw63p/Jo0+VypfHrIU8+dBVnY2lEL8VNQYzWEBcUJCAkajkerVq1ttr169OkeOHMn3PtHR0UybNo2OHTsSFhbGmjVrWLx4MUaj0ardgQMHaN++PRkZGXh7e/Prr78SGRkJwOXLl3Fzc8Pf3z/PcS9fvlxgfydPnsx7772XZ/uff/6Jp2cpjoJcd95cqNhCzo/Tq3uR19+4xpQpbfhtfSW6jq3Ba6/tRFeOg2Io/Jzv2BEIQM2aN1l//XxpdUkUgaKAj09Dbt5047/bU6lXL7HI97XV+3znzuokpbhSuXI6N6oeY/lFm+zWaTVp48Xeo5F8/YcXgW3223Tftv5sX7iwPgCNGydwwHiGA3LuC6SpG49OV5cT5/TM3H6T2rVLrxpH7KZNpXKctLSiXUEsVxVMp0+fzsiRI4mIiECj0RAWFsbw4cPzpFiEh4ezd+9ekpKSWLRoEUOHDmXDhg2WoLgkxo8fz9ixYy2/JycnU6tWLXr06IGvr2+J91tk6emwZQt4e8Nto+QVXZbJROzly3QPDETn4vB5oGVWTDC0qXqCAf9Xn+3bg/jf5x34aXL5HCkuyjnfGR8MQOemmcQEB5dm90QRtGmYzpodbnhdr01M8J0HDWz9Pl+0py4Aj3dP5qGa8vq4W+F9s/nhB/j77wBae9QmoNLd52bZ47NdUeD1LeZz/2LvFPlsKIIf2txk+RZ/bhxqwHPtLtn9eFnp6cTeuEH3Dh3Q+di/5Jt6Rf9OHBYQV61aFa1Wm6e6w5UrVwgMDMz3PgEBASxZsoSMjAyuXbtGcHAwb7zxBqGhoVbt3NzcqFevHgBRUVHs3LmT6dOnM3PmTAIDAzEYDCQmJlqNEhd2XAB3d3fc3d3zbNfpdOh0uqI+7JLLygKNxlwrxUmDQp2LiwTEd/DQvSn89vFJer8axrKNlRj8Zj0WTDlVLoNiKPyc7znsDUDrhunyuiiDWoans2aHH/uOeqNzKfqVLVu8zzMNGpZuMOcPP9r9hrw+bCCidhYtI1LZfcSL3zdU5pl+tkmbANt+tu8+4sHRMx7o3U0M6pYo574I+t6fyPIt/izbWIkJT5dCxa1beRk6V9dSiZ+KegyHvVLc3NyIiopizZo1lm0mk4k1a9ZY8n0LotfrqVGjBtnZ2fzyyy/07t270PYmk8mS/xsVFYVOp7M67tGjRzl79uwdjytEeRDdPpml006gdzfx2wZ/Br4eiiGrYs0qURSIO6KWXJMJdWVRzhLOpV967c+/fElO1VKjmoH2TaUkn62oK/0tLMPVJn74w1x7+OGOifh5S+5wUfTqkIRGo7DrkBfnLpfCAF8Z5dCvTmPHjuWbb75hzpw5HD58mOeff57U1FSGDx8OwJAhQ6wm3W3fvp3Fixdz6tQpNm3axAMPPIDJZGLcuHGWNuPHj2fjxo2cOXOGAwcOMH78eNavX8/gwYMB8PPz46mnnmLs2LGsW7eOuLg4hg8fTvv27QucUCdEedOj3U2WfmwOipdu9GfAuFAyDRUnKL4Qr+PKNR1arUKz+hIQl0XqinX7jnuW+mqKC2JzFuOQAULbUatNrN3lw9UbZS/jMjsbfvpTrS7hvPNtiqt6lWxLWcLfNvg7tjMO5NCPikceeYSpU6cyYcIEmjdvzt69e1m5cqVlot3Zs2e5dCknnyUjI4O3336byMhI+vbtS40aNdi8ebNV6kN8fDxDhgwhPDycrl27snPnTlatWkX37t0tbT755BMeeugh+vfvT8eOHQkMDGTx4sWl9riFKA3d291k2a2R4mWb/OlfgYJidUGORqHpeOjLZzpIRVe/dibenkYyMl04+k/pzXvIyNSwdKM/kDOiKWwjtKaBqIapmEwaFq/1d3R38liz05cr13RU8csmun3R8kaFmbpIxxInDogd/hVv9OjRjB49Ot/b1q9fb/V7p06dOHToUKH7++677+54TL1ez5dffsmXX35Z5H4KUR51a2sOinuNrccfm81B8S8fncLdrXwHkbvU+sOyIEeZ5eICzeqns2WfN7uPeNIoLKNUjqumS9SsbqBdE0mXsLVB3W4Qd9iLBasr8Wx/2+UR28Lc5ebR4Ud7XC+38yYcpU/nRF77tBbr43y4kaylkq/xzneqYORikhAVXLe2N/n9kxN4uJv4Y7M//f4vjIzM8j1SrI4Qy4IcZVtLB6xYp66mNlDSJexCTZtYH+dD/HWHj6lZpKS5sPjWMt1PxEi6RHGF1TTQpF4aRqOG328tee1s5ONCCCfQtc1Nfv/UHBQv3+JXroNi6wl1MgJYlrUo5RXrcqdLDJR0CbuoW8NA68iylzaxZL0/aRlawmpm0LaxfC6UhCVtwklXrZOAWAgn0aX1Tf6YfhwPdxMrtvrRt5wGxeev6Ii/bp5Q17ReuqO7IwqhjhDvPeaBUgpXsFdt8+VmqpZa1Q0SFNmR+mVjQRmqNpGzVPN1Waq5hNSAeOU2X9IznO9JlIBYCCdyf6sUlk8/jqfeyMqtfvR5rfwFxerocOMwmVBX1kWGpuOmM5GU4srpC252P54lXaKbpEvYkxoQb9jtw5Vrjk+buJzgSux28wJZki5Rci3C06kdmElahtbyfDoT+cgQwsl0bpXC8ukn8NQbWbXNj96vhpWr0YBdh2RCXXmhc4Umt0bx7Z02kZ6Rq7pEdwmK7Ckk2ECbRrfSJm7l7TrST6sqYzJpaNckhXq1Mh3dnXJLo3HutAkJiIVwQp2iUljx2Qm8PIz8+ZcfvV+tV26CYskfLl/UPGJ7T6xbuc2PlDQttQMzadNIvizZm/qlY0FsZQf3xDpdQtwdNSBeutG/1OuHO5oExEI4qY4tc4Li2O2+PDy2HmllPChWFNh16FaFCRkhLhdahN8aIbZzQLwwV7qE5JDa34CuiQBs2O3N5QTHpU0cOqVn9xEvXLUKj/SQgPhudWieQmW/bK4lubJln7eju1OqJCAWwol1aJETFK/eUfaD4nNXdCQk6nDVKjStLxPqygN1Yt3uI552m1hnTpcwl4qSxThKR50gA20bp6AoGn5Z67jJderocM97kqjq73y1c23N1RV6dUgEnC9tQgJiIZxchxYprPz8ON6eRtbs8KXXmLIbFKv5w43D0tG7y4S68qBp/TRcXBTir+u4lKCzyzFWbPUjNV1LnaBMWku6RKlRv3wsdFC1CZMJ5qnpEjKZzmZyr1pXGtVhygoJiIUQ3Nc8lZX/396dh0V13XED/84MMOwgKJuAIIqoIOISq0SR4G58o5ik2YNtTU0gCSFtYvK4pM1i4vPGmsVokqamjfq2Wdxi1UpQEaxbEIxWBdeIKOAGw85s7x/DDBBBEefOnbn3+3keHuXOZeaHB/Hr4XfO+dAUincest9QzAM5HI+7qxExEaZT6gqL3QR5ja+z2S4hhgdbAvGeQk9cFqFtIr/IExfK1fD20FtmNenuTfqVBm5qA85fUuNIiTB/Z+0RAzERAQASh9bhPx+dgpeHKRTfn9kPdQ329S3CsqBuIBfUORIhD+iob1RgSz7bJcQQHqTFr+Ja2iZybD9LbG6XeDDlBrdgtCJ3VyMmj64GIK+2Cfv6146IRDUmvjUU7/rRvkKxaUFdy5ZrnCF2KMME3Gli215Tu0RESBNGDOLXha1Z2iZsHIgbmxSWnww8Me2aTV9bDtq2TciFffxLR0R2Y/SQ1lC8u8AL01+0j1B8odwF16qd4Oxk4II6B5MQI9wMseUwjhS2S4jhwRRTIM4r9MSlK8L0iHfk3/k+qK51QmhgM5KG1drsdeXi/nuroVIZcaTE3SaH6tgD8f+VIyK7M3pIHXZ8fAreHnrkHvbCtBf7obZe3G8X5u3WYqMaoXbhj0cdiXnrtZ8vq3G9WmW1561vVGBLXku7xES2S4ghLEiL0UPMbRO+Nntdc7vEY5Ov81RCAfj76jEuoQaAfNom+GVERB36VVwddqwogbeHHnvsIBTzQA7H5eulR2Rv0wli1myb2Jrvg/pGFSJ7N7GNRkTmtomvbbTbxLUqFf7d0jf+JNslBCO3tgkGYiLq1KjYemSvKIGPpw55heKGYh7Z7NiE6CM2B7CHubuEqMxtE3uPeKKsUvi2iW9+6AGtTon46HrE9msU/PXk6oEk08K6/CJPXLkh3uErtsJATES3dE9sPbJXnLKE4qkv9ENNnW2/dRiNbWeIGYgdkbV3mqhrUGJLni8A03ZrJJ7QQC0S482HdPgK/nprtvkD4FHNQusT3IxhMXUwGBT4vuXgGyljICai2xo5uDUU5xd5YeoL/W0ais9fcsH1lgV1sVFcUOeIzCfWWWsv4q17vdHQpETf3k2W5ybxmP9T8nW2n6Cvc/aiC/Ye8YRCYcRjUxiIhWZpm5BBHzEDMRF1ycjB9fjhk1Pw9dJh7xFPTHm+PzS1tvkWYj6QI65fAxfUOSjzDHHxz65W2bXEHLwennid7RJ2oG3bxMUK4dom1m43jXvKyBqE9NIK9jpkYg7EOw54i76wWmjS/uyIyKpGDDKF4h7eOvz3J09MecE2obj1QA7OBDqqoJ46BPlrYTQq7vr0q9p6pWVRFQ/jsA+9A7S4d6hpV4LvdgqzuM5oBNZsbWmX4GI6m4iNakRUaCOampX4zz5vscsRFAMxEd2R4QPr8cMnJejhrcM+G4ViHsghDa1tE3fXR/zvfB80NCkRFdqIoQPYQmMvLLtNZAsTiH887o6SC65wUxuQmlwlyGtQewqFfNomGIiJ6I4Ni2loF4onP98f1QKF4vYL6rjlmiOz1sK6b8y7S0zk7hL2ZHZKFRQKI/77kydKy63fNmHee3jm+Cp4eRis/vzUMXMg3pLvA61O3FqExEBMRN0yLKYBOZ+UwM9Hh/1HPTE5Q5hQfK7MBTc0TnBxNiA2ilssOTJrzBDX1ivx771sl7BHIb20uHeo6dS4b618lLNWB/y//5gC8RNT2S5hS6Pj6tCrhxZVNU7ILfASuxzBMBATUbcltAnFB455YlJ6NKpqrHcSGdA6OzykfwNcnLmgzpGZZ4iPnXFFs7Z7U7tb8nzQ2KRE//BGxEezXcLemP+T8o2VA3H2fm9cueGMXj20mPgrjVWfm25NpQIeSKoCIO22CQZiIrorQwc0YOfKEvj76HDwfx6YlN7fqqGYB3JIR0RIM3y9dNDqlPjfGdduPYf5MI6HUtguYY9mp9yAQmHEvp88ccGKbRPmvYcfnXwdztI/I8LutD21zijReQkGYiK6a/HRDchpCcWHjntgYnp/3NBYJxSzf1g6FIq76yOuqVNi239b2iUmsl3CHgX31GFsQkvbhJWOcq6pU1pmJnkYhzhSRtbA012PskoX/HjceqdN2hMGYiKyivjoBuxcVYKevlr8aKVQbDS27kHMGWJpuJs+YnO7RHR4I4b0Z7uEvbLsNmGlQLx+ly8aWsadJ1WKw1VtxNQxpqOcpdo2wUBMRFYzpH9rKC44cfeh+GyZGlU1pgV1g7mgThISWrZJO9yNQPw1d5dwCLPvM7VNHDjmiZ8vu9z187Xde5jjLp62bRNSxEBMRFYV168Ru1aVoFcPUyie8Fx/XK/uXig+3DI7HM8FdZJhniE+UuIGvb7rH9e2XeIh7i5h14J66jDO3DaR43tXz3XpijNyDpl2NnicRzWLalqiBk4qI46fdUPJz2qxy7E6BmIisrrYfo3YudIUig+f9MCE56K7FYoLTvBADqmJDm+Eu6se9Y0qlFzo+sK67/N80NSsxIA+jYjrx3YJe2fu8TYfsd1d67b7wWhUIDG+Fn1Dm61RGnWTr5ce94007fAhxbYJBmIiEkRsy0xxgJ8WhcXuSHk2Gteq7iwUF540BeIRA7mgTipUKli2Syss7voRzuZg9fDE6/yxuQNITb4BpdKIg//zwPlL3W+bMB/Gwb2H7YOU2yYYiIlIMIOjWkNxUYk7JjzX9VBsNLbuRMAZYmkx7zTR1YV1mloltu/zBsDDOBxFUE8dkobVAOj+IR1HT7viSIk7nJ0MbJOxE/9nnGlh3f6jHrh8VVr73zEQE5GgBvU1heJAf1MoTnkuGle7EIrLyz1QXesEtYsBg6P4I3IpudOt177P80VTsxIxEQ1cXOlAzCH26+zuBeK1LXsPT7+3Gv6+d9BwToLpHaDFqNhaGI0KbJbYLDEDMREJrm0oPlJiap+4XSg+fdoXgGlBHTfil5a2W691ZZN/c6Di7hKOJTW5CkqlEYeOe+Bc2Z21TRgMwNrt5nYJLqazJ1Jtm2AgJiKbGBjZiN2fFiPIX4ufTt0+FJ85Y9pRgAdySM/gvo1wUhlxQ+N02225qtku4bAC/XUYP7x7bRO5hz1xscIFPp46TL+3WojyqJvMgTjnoBc0tdKJkdL5TIjI7sVENGFXm1B837xoXLnR8fTvmTO+AHgghxSpXYyIjTIvrLt128TmXF80a5UYGMl2CUfU3UM6zHsPPzzxBlzV3HLRnsRENCEmogFanRJb9/qIXY7VMBATkU3FRDRh96fFCO7ZjKOnTaG48nr7UGwwtAnEXFAnSV3tI/7GfBgHZ4cd0qyWtokfj3vg7MWutU00NCosM8psl7BPlrYJCW2/xkBMRDY3IKIJuz8tQUivZhw743ZTKD5zUY36eme4qg0Y1JcL6qSotY+4863XqmpU+M9+U7sEdxlwTAF+OiSPMLVNfNPFWeLv83yhqVMhPKgJ9w6tFbI86iZzIN76Xx80NUujsZ+BmIhEEd2nNRT/72xrKNbrW39cGhHcBKU0vtfSL3Rlhnhzrg+atUoM7st2CUdmnt3/pot9xGu2mhbTPT71OpRMKXZp5KB6BPdsRk2dCjtbThJ0dPxSIyLR9A83heLeAaZQPPzJGIRNj8OSv/UGAJw874aIGXFYv9NX3ELJ6uKjG6BQGHH5qgvKO9nP1Nx3ytlhxzYruQoqlREFJzxw5jZtE1erVJYjutkuYb+USum1TTAQE5GozKHYz1uLixVqXL7q3O7xskpnPPhKX4ZiifF0NyA6vAlAxwvrqmpU2MF2CUno1UOH5OFda5v41w4/6PQKDIupw6C+/KmAPTMH4k17fGEwiFuLNTAQE5HoIkOa4OJsBGAE0L5Hwtjyfub7YdBzb35Jabsf8S9tyvWBVqdEbFQDg5EEPDzRfEiH3y3vaz2qmbPD9m788Fr4eOpQcc0Z+496iF3OXWMgJiLR5RV6ovyaC34Zhs2MUKC0wgV5hZ62LYwEdas+YnNwengig5EUzEq+AZXKiMJid5wuVXd4z+lSNfYf9YRSacQjkznu9s7F2WjZI1oKbRMMxEQkul+2SdztfeQYOpshvqFRIfuAaaEO2yWkoaevHvfdZreJtS2zwxNHaRDcU2ez2qj7zG0TG3b7dunUSXvGQExEogvuqbXqfeQYzDPEZ8vUqKppPbVwU64vtDol4vrVIyaiSazyyMrMs/3mo7jbMhqBr7ayXcLRTBmtgdrFgNOlrjhxzlXscu4KAzERiW5sQi1CA5qhQMdTDAoYERbYjLEJ3JNUSvx89AgPMgXeIyWts8TmwMTDOKRl1njTbhNFJe44daF928SBYx44c9EV7q56y6wj2T8vDwMm3KMBAGzY5StuMXeJgZiIRKdSAR/8oRQAbgrF5veXv1wKleqmDyUHZ26bKGppm7herUL2Ae4uIUX+vnpLePpl24R57+HU5Cp4uktgywIZsWy/lusrah13i4GYiOxC6n1V+HbpWfQOaN8WERqoxbdLzyL1vipxCiNBJQwwnURo7iP+fk8P6PQKDOlfjwFsl5Cch1JadptoE4ibtQr8c0dLu8Q0tks4mhljq6FQmI7nLi133HUeDMREZDdS76vC+e+PInvlSWRl/YjslSdxbvNRhmEJ++UM8bc/sF1CymaOr4KTyogjJe4o/tnUc7pjvzeuVTsh0F+LlJEakSukOxXor0NivKmdbZMDzxIzEBORXVGpgKThNRg3rgxJw2vYJiFx5oV1J8+74epVV+QcZLuElPn76jFhlCn0ftfyn59123oCAB6ddB1OHR9aSHZOCm0TDMRERCSakF5a9OqhhcGgwPLlw6DTKxHfvx7RfdguIVXm2f+/f98T2dnhllnFJ6dfE7EquhsPJJn2I95d4IUbGsecxWAgJiIi0WzY5QtNnekf0GPHegEAzl1y4VHdEqZUmk6lPHfJFStWJECrVcJJZcC5so4P7CD71y+sCbFRDdDrFdiS5yN2Od3CQExERKJYv9MXD77SF03N7U8orKlT4cFX+jIUS9D6nb6Y80bETdd1egUeepVj7shmJZtm/h311DoGYiIisjm9Hnjx/4a1bKrXPhAbW97PfD8Mer3NSyOB3GrMwTF3eOY+4u37vNHQ+MvxtX8MxEREZHN5hZ64WOmCm4ORiREKlFa4IK/Q07aFkWA45tKWMKAB4UFNqG9s3UvckTAQExGRzV2+2rX9Srt6H9k/jrm0KRRtdptwwLYJBmIiIrK54J7a2990B/eR/eOYS585EG/e4wudTtxa7hQDMRER2dzYhFqEBjTfdFS3mQJGhAU2Y2xCrY0rI6FwzKVv7NBa+PnocK3aCXuPOFbrCwMxERHZnEoFfPCHUgC4KSCZ31/+cikPZpEQjrn0OTkBM8ZWAXC8tgkGYiIiEkXqfVX4dulZ9A5o/yPy0EAtvl16lkd2SxDHXPranlpn7PiHAXaJhyQ6miYZnt5kMJh+bWwElPw/nCxwzGUjdUw5HvimHLuKvLDt52ZM7eOC5KEtR3Y3il0dCYFjLm2ThjbDTR2J85fU+OmY6eTJdpqbxSnsNhiIHYVKBbi7A/X1dvvFJBjzfzFra03LWEn6OOayogKQ1F+Duj7NSHJxgaqeYy51HHPpcgcwedhVbNwXiA0/eCE+qKL9Debv73bWG8NA7CjUamDUKMhyx3KdDti1C0hMNDUokfRxzOWHYy4/HHPJmpmmwsZ9wMaf+uKNcSHtHzSPu4uLOMV1gl+BjkQt03PetS29Zm5ugDP3p5QFjrn8cMzlh2MuWffPBlTPAUeOKnGuwh2RkW0e1NrntnpsziMiIiIiq/H3B8aNM/1+40ZRS+kyBmIiIiIisqqZM02/MhB30YoVKxAREQFXV1eMGjUKBw8e7PRerVaLP//5z4iKioKrqyvi4+Oxffv2dvcsWbIEI0eOhJeXFwICAjBz5kwUFxe3u2f8+PFQKBTt3ubNmyfI50dEREQkNw88YPo1Px+4ckXcWrpC1ED8r3/9C1lZWVi8eDEOHz6M+Ph4TJ48GZWVlR3ev2DBAnz66af46KOPcPz4ccybNw+zZs1CYWGh5Z7c3Fykp6dj//79yM7OhlarxaRJk1BXV9fuuebOnYvLly9b3pYuXSro50pEREQkF336AAkJpl00v/9e7GpuT9RAvGzZMsydOxdz5szBoEGDsGrVKri7u+Nvf/tbh/d/9dVXeP311zFt2jT07dsXzz77LKZNm4b333/fcs/27duRlpaGwYMHIz4+Hl9++SUuXLiAgoKCds/l7u6OoKAgy5u3t7egnysRERGRnMyaZfrVEdomRNtlorm5GQUFBXjttdcs15RKJSZMmIB9+/Z1+DFNTU1wdXVtd83NzQ35+fmdvk51dTUAwM/Pr931tWvXYs2aNQgKCsKMGTOwcOFCuLu7d/o8TU1NaGpzKIZGowFgauPQ2umKSakw//nyz1k+OObywzGXH4659E2fDixa5IwdO4y4cUMHT0/bj3tXX0e0QHz16lXo9XoEBga2ux4YGIiTJ092+DGTJ0/GsmXLMG7cOERFRSEnJwfr16+HvpO9eQ0GAzIzM5GYmIjY2FjL9cceewx9+vRBSEgIfvrpJ7z66qsoLi7G+vXrO613yZIl+NOf/nTT9R07dtwySJP1ZGdni10C2RjHXH445vLDMZcuoxEIDJyAigoPvPtuIcaMuWx5zFbjXl9ff/ub4GD7EH/wwQeYO3cuYmJioFAoEBUVhTlz5nTaYpGeno5jx47dNIP8zDPPWH4fFxeH4OBgpKSk4MyZM4iKiurwuV577TVkZWVZ3tdoNAgLC8OkSZPYbiEwrVaL7OxsTJw4Ec7cq1IWOObywzGXH465PDz2mBJ/+Qtw8eIITJumt/m4m3+ifzuiBeKePXtCpVKhoqL9kX4VFRUICgrq8GN69eqFjRs3orGxEdeuXUNISAjmz5+Pvn373nRvRkYGtmzZgj179iA0NPSWtYwaNQoAcPr06U4DsVqthrqDgzGcnZ35F9lG+GctPxxz+eGYyw/HXNpSU4G//AXYulUJQGk5g8VW497V1xBtUZ2LiwuGDx+OnJwcyzWDwYCcnByMHj36lh/r6uqK3r17Q6fT4bvvvsMD5r09ABiNRmRkZGDDhg3YuXMnItsdj9KxoqIiAEBwcHD3PhkiIiIiusno0UCvXkBVFZCbK3Y1nRN1l4msrCx8/vnn+Pvf/44TJ07g2WefRV1dHebMmQMAeOqpp9otujtw4ADWr1+Ps2fPIi8vD1OmTIHBYMArr7xiuSc9PR1r1qzBunXr4OXlhfLycpSXl6OhoQEAcObMGbz55psoKCjA+fPnsXnzZjz11FMYN24chgwZYts/ACIiIiIJU6la9yS2590mRO0h/vWvf40rV65g0aJFKC8vx9ChQ7F9+3bLQrsLFy5AqWzN7I2NjViwYAHOnj0LT09PTJs2DV999RV8fX0t96xcuRKA6fCNtlavXo20tDS4uLjghx9+wPLly1FXV4ewsDDMnj0bCxYsEPzzJSIiIpKbmTOBv/7VFIiXLRO7mo6JvqguIyMDGRkZHT62e/fudu8nJSXh+PHjt3w+o9F4y8fDwsKQa89z9kREREQSkpICeHoCZWXAX/+qxJkzveHhoUBysmkG2R6IfnQzEREREUmXqysQF2f6fXq6CsuWjcDEiU6IiABuseOtTTEQExEREZFg1q8HOjpzrawMePBB+wjFDMREREREJAi9HnjxxY4fM3e5Zmaa7hMTAzERERERCSIvD7h4sfPHjUagtNR0n5gYiImIiIhIEJcv3/6eO7lPKAzERERERCSIrp55JvbZaAzERERERCSIsWOB0FBAoej4cYUCCAsz3ScmBmIiIiIiEoRKBXzwgen3vwzF5veXLxd/P2IGYiIiIiISTGoq8O23QO/e7a+Hhpqup6aKU1dbop9UR0RERETSlpoKPPAAsGuXDtu2FWHq1KFITnYSfWbYjIGYiIiIiASnUgFJSUbU1ZUhKSnebsIwwJYJIiIiIpI5BmIiIiIikjUGYiIiIiKSNQZiIiIiIpI1BmIiIiIikjUGYiIiIiKSNQZiIiIiIpI1BmIiIiIikjUGYiIiIiKSNQZiIiIiIpI1Ht3cTUajEQCg0WhErkT6tFot6uvrodFo4OzsLHY5ZAMcc/nhmMsPx1yebD3u5pxmzm2dYSDuppqaGgBAWFiYyJUQERER0a3U1NTAx8en08cVxttFZuqQwWDApUuX4OXlBYVCIXY5kqbRaBAWFobS0lJ4e3uLXQ7ZAMdcfjjm8sMxlydbj7vRaERNTQ1CQkKgVHbeKcwZ4m5SKpUIDQ0VuwxZ8fb25jdNmeGYyw/HXH445vJky3G/1cywGRfVEREREZGsMRATERERkawxEJPdU6vVWLx4MdRqtdilkI1wzOWHYy4/HHN5stdx56I6IiIiIpI1zhATERERkawxEBMRERGRrDEQExEREZGsMRATERERkawxEJNdWrJkCUaOHAkvLy8EBARg5syZKC4uFrsssqF3330XCoUCmZmZYpdCAisrK8MTTzwBf39/uLm5IS4uDj/++KPYZZFA9Ho9Fi5ciMjISLi5uSEqKgpvvvkmuMZfOvbs2YMZM2YgJCQECoUCGzdubPe40WjEokWLEBwcDDc3N0yYMAGnTp0Sp9gWDMRkl3Jzc5Geno79+/cjOzsbWq0WkyZNQl1dndilkQ0cOnQIn376KYYMGSJ2KSSwGzduIDExEc7Ozti2bRuOHz+O999/Hz169BC7NBLIe++9h5UrV+Ljjz/GiRMn8N5772Hp0qX46KOPxC6NrKSurg7x8fFYsWJFh48vXboUH374IVatWoUDBw7Aw8MDkydPRmNjo40rbcVt18ghXLlyBQEBAcjNzcW4cePELocEVFtbi2HDhuGTTz7BW2+9haFDh2L58uVil0UCmT9/Pvbu3Yu8vDyxSyEbuf/++xEYGIgvvvjCcm327Nlwc3PDmjVrRKyMhKBQKLBhwwbMnDkTgGl2OCQkBC+//DL+8Ic/AACqq6sRGBiIL7/8Eo888ogodXKGmBxCdXU1AMDPz0/kSkho6enpmD59OiZMmCB2KWQDmzdvxogRI/DQQw8hICAACQkJ+Pzzz8UuiwQ0ZswY5OTkoKSkBABw5MgR5OfnY+rUqSJXRrZw7tw5lJeXt/se7+Pjg1GjRmHfvn2i1eUk2isTdZHBYEBmZiYSExMRGxsrdjkkoH/+8584fPgwDh06JHYpZCNnz57FypUrkZWVhddffx2HDh3CCy+8ABcXFzz99NNil0cCmD9/PjQaDWJiYqBSqaDX6/H222/j8ccfF7s0soHy8nIAQGBgYLvrgYGBlsfEwEBMdi89PR3Hjh1Dfn6+2KWQgEpLS/Hiiy8iOzsbrq6uYpdDNmIwGDBixAi88847AICEhAQcO3YMq1atYiCWqK+//hpr167FunXrMHjwYBQVFSEzMxMhISEccxINWybIrmVkZGDLli3YtWsXQkNDxS6HBFRQUIDKykoMGzYMTk5OcHJyQm5uLj788EM4OTlBr9eLXSIJIDg4GIMGDWp3beDAgbhw4YJIFZHQ/vjHP2L+/Pl45JFHEBcXhyeffBIvvfQSlixZInZpZANBQUEAgIqKinbXKyoqLI+JgYGY7JLRaERGRgY2bNiAnTt3IjIyUuySSGApKSk4evQoioqKLG8jRozA448/jqKiIqhUKrFLJAEkJibetKViSUkJ+vTpI1JFJLT6+noole3jh0qlgsFgEKkisqXIyEgEBQUhJyfHck2j0eDAgQMYPXq0aHWxZYLsUnp6OtatW4dNmzbBy8vL0lfk4+MDNzc3kasjIXh5ed3UI+7h4QF/f3/2jkvYSy+9hDFjxuCdd97Bww8/jIMHD+Kzzz7DZ599JnZpJJAZM2bg7bffRnh4OAYPHozCwkIsW7YMv/nNb8QujayktrYWp0+ftrx/7tw5FBUVwc/PD+Hh4cjMzMRbb72F/v37IzIyEgsXLkRISIhlJwoxcNs1sksKhaLD66tXr0ZaWpptiyHRjB8/ntuuycCWLVvw2muv4dSpU4iMjERWVhbmzp0rdlkkkJqaGixcuBAbNmxAZWUlQkJC8Oijj2LRokVwcXERuzyygt27dyM5Ofmm608//TS+/PJLGI1GLF68GJ999hmqqqpw77334pNPPkF0dLQI1ZowEBMRERGRrLGHmIiIiIhkjYGYiIiIiGSNgZiIiIiIZI2BmIiIiIhkjYGYiIiIiGSNgZiIiIiIZI2BmIiIiIhkjYGYiIiIiGSNgZiIiG4yfvx4ZGZm3vKeiIgIniJIRJLAQExEJFFpaWlQKBQ3vZ0+fVrs0oiI7IqT2AUQEZFwpkyZgtWrV7e71qtXL5GqISKyT5whJiKSMLVajaCgoHZvKpUKubm5uOeee6BWqxEcHIz58+dDp9N1+jyVlZWYMWMG3NzcEBkZibVr19rwsyAiEhZniImIZKasrAzTpk1DWloa/vGPf+DkyZOYO3cuXF1d8cYbb3T4MWlpabh06RJ27doFZ2dnvPDCC6isrLRt4UREAmEgJiKSsC1btsDT09Py/tSpUxEdHY2wsDB8/PHHUCgUiImJwaVLl/Dqq69i0aJFUCrb//CwpKQE27Ztw8GDBzFy5EgAwBdffIGBAwfa9HMhIhIKAzERkYQlJydj5cqVlvc9PDyQnp6O0aNHQ6FQWK4nJiaitrYWFy9eRHh4eLvnOHHiBJycnDB8+HDLtZiYGPj6+gpePxGRLTAQExFJmIeHB/r16yd2GUREdo2L6oiIZGbgwIHYt28fjEaj5drevXvh5eWF0NDQm+6PiYmBTqdDQUGB5VpxcTGqqqpsUS4RkeAYiImIZOa5555DaWkpnn/+eZw8eRKbNm3C4sWLkZWVdVP/MAAMGDAAU6ZMwe9//3scOHAABQUF+N3vfgc3NzcRqicisj4GYiIimenduze2bt2KgwcPIj4+HvPmzcNvf/tbLFiwoNOPWb16NUJCQpCUlITU1FQ888wzCAgIsGHVRETCURjb/syMiIiIiEhmOENMRERERLLGQExEREREssZATERERESyxkBMRERERLLGQExEREREssZATERERESyxkBMRERERLLGQExEREREssZATERERESyxkBMRERERLLGQExEREREsvb/Ad+LWVXkX+KjAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Scores for each fold: [0.93490643 0.93246542 0.93083808 0.92676973 0.94711147 0.92595606\n",
      " 0.93816111 0.92595606 0.93729642 0.9242671 ]\n",
      "Mean Accuracy: 0.93\n",
      "Standard Deviation: 0.01\n"
     ]
    }
   ],
   "source": [
    "cross_validate_and_visualize_accuracy(final_model, X, y, cv=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Metrics:\n",
      "Accuracy: 0.96\n",
      "Precision: 0.93\n",
      "Recall: 0.98\n",
      "F1 Score: 0.96\n",
      "------------------------------\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing Metrics:\n",
      "Accuracy: 0.92\n",
      "Precision: 0.79\n",
      "Recall: 0.95\n",
      "F1 Score: 0.86\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Fungsi untuk menampilkan confusion matrix dan metrik evaluasi\n",
    "def evaluate_model(y_true, y_pred, dataset_name):\n",
    "    # Confusion matrix\n",
    "    cm = confusion_matrix(y_true, y_pred)\n",
    "    \n",
    "    # Plot confusion matrix\n",
    "    plt.figure(figsize=(6, 4))\n",
    "    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=['Not Churn', 'Churn'], yticklabels=['Not Churn', 'Churn'])\n",
    "    plt.xlabel('Predicted')\n",
    "    plt.ylabel('Actual')\n",
    "    plt.title(f'Confusion Matrix ({dataset_name})')\n",
    "    plt.show()\n",
    "    \n",
    "    # Hitung metrik evaluasi\n",
    "    accuracy = accuracy_score(y_true, y_pred)\n",
    "    precision = precision_score(y_true, y_pred, zero_division=0)\n",
    "    recall = recall_score(y_true, y_pred, zero_division=0)\n",
    "    f1 = f1_score(y_true, y_pred, zero_division=0)\n",
    "    \n",
    "    print(f'{dataset_name} Metrics:')\n",
    "    print(f'Accuracy: {accuracy:.2f}')\n",
    "    print(f'Precision: {precision:.2f}')\n",
    "    print(f'Recall: {recall:.2f}')\n",
    "    print(f'F1 Score: {f1:.2f}')\n",
    "    print('-' * 30)\n",
    "\n",
    "# Prediksi untuk data training dan testing\n",
    "y_train_pred = final_model.predict(X_train_res)\n",
    "y_test_pred = final_model.predict(X_test)\n",
    "\n",
    "# Evaluasi untuk data training\n",
    "evaluate_model(y_train_res, y_train_pred, 'Training')\n",
    "\n",
    "# Evaluasi untuk data testing\n",
    "evaluate_model(y_test, y_test_pred, 'Testing')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Metrics:\n",
      "Accuracy: 0.95\n",
      "Precision: 0.92\n",
      "Recall: 0.99\n",
      "F1 Score: 0.96\n",
      "------------------------------\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing Metrics:\n",
      "Accuracy: 0.92\n",
      "Precision: 0.77\n",
      "Recall: 0.96\n",
      "F1 Score: 0.85\n",
      "------------------------------\n"
     ]
    }
   ],
   "source": [
    "y_train_pred = model.predict(X_train_res)\n",
    "y_test_pred = model.predict(X_test)\n",
    "\n",
    "# Evaluasi untuk data training\n",
    "evaluate_model(y_train_res, y_train_pred, 'Training')\n",
    "\n",
    "# Evaluasi untuk data testing\n",
    "evaluate_model(y_test, y_test_pred, 'Testing')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>employee_id</th>\n",
       "      <th>domisili</th>\n",
       "      <th>jenis_kelamin</th>\n",
       "      <th>date_of_birth</th>\n",
       "      <th>join_date</th>\n",
       "      <th>resign_date</th>\n",
       "      <th>marriage_stat</th>\n",
       "      <th>dependant</th>\n",
       "      <th>education</th>\n",
       "      <th>absent_90D</th>\n",
       "      <th>...</th>\n",
       "      <th>total_income_work</th>\n",
       "      <th>income_dependant_ratio</th>\n",
       "      <th>work_efficiency</th>\n",
       "      <th>active_work_category</th>\n",
       "      <th>work_stability_score</th>\n",
       "      <th>position_score</th>\n",
       "      <th>job_income_position_score</th>\n",
       "      <th>education_score</th>\n",
       "      <th>education_income_ratio</th>\n",
       "      <th>weighted_satisfaction_performance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>EM6407</td>\n",
       "      <td>Kota Jakarta Selatan</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1981-03-05</td>\n",
       "      <td>2022-03-13</td>\n",
       "      <td>2023-08-08</td>\n",
       "      <td>Married</td>\n",
       "      <td>3</td>\n",
       "      <td>D3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.169413e+08</td>\n",
       "      <td>1.719725e+06</td>\n",
       "      <td>1.22500</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>4.250000</td>\n",
       "      <td>4</td>\n",
       "      <td>1.719725e+06</td>\n",
       "      <td>4</td>\n",
       "      <td>1.719725e+06</td>\n",
       "      <td>3.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>EM6881</td>\n",
       "      <td>Tangerang</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1974-04-26</td>\n",
       "      <td>2022-04-11</td>\n",
       "      <td>2023-05-31</td>\n",
       "      <td>Married</td>\n",
       "      <td>0</td>\n",
       "      <td>D3</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.369110e+08</td>\n",
       "      <td>1.053162e+07</td>\n",
       "      <td>1.17375</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>4.333333</td>\n",
       "      <td>4</td>\n",
       "      <td>2.632904e+06</td>\n",
       "      <td>4</td>\n",
       "      <td>2.632904e+06</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>EM9588</td>\n",
       "      <td>Kota Depok</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>1980-01-08</td>\n",
       "      <td>2022-02-22</td>\n",
       "      <td>2023-08-30</td>\n",
       "      <td>Married</td>\n",
       "      <td>3</td>\n",
       "      <td>D1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.408170e+08</td>\n",
       "      <td>1.955791e+06</td>\n",
       "      <td>1.18625</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>4</td>\n",
       "      <td>1.955791e+06</td>\n",
       "      <td>2</td>\n",
       "      <td>3.911582e+06</td>\n",
       "      <td>3.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>EM6817</td>\n",
       "      <td>Kota Jakarta Timur</td>\n",
       "      <td>Perempuan</td>\n",
       "      <td>1985-06-15</td>\n",
       "      <td>2021-09-04</td>\n",
       "      <td>2023-01-13</td>\n",
       "      <td>Married</td>\n",
       "      <td>2</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>10.0</td>\n",
       "      <td>...</td>\n",
       "      <td>3.969525e+07</td>\n",
       "      <td>8.269843e+05</td>\n",
       "      <td>1.13125</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>1.454545</td>\n",
       "      <td>1</td>\n",
       "      <td>2.480953e+06</td>\n",
       "      <td>1</td>\n",
       "      <td>2.480953e+06</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>EM0933</td>\n",
       "      <td>Kota Jakarta Timur</td>\n",
       "      <td>Laki-laki</td>\n",
       "      <td>1981-10-31</td>\n",
       "      <td>2022-03-20</td>\n",
       "      <td>2024-09-08</td>\n",
       "      <td>Married</td>\n",
       "      <td>1</td>\n",
       "      <td>SLTA</td>\n",
       "      <td>7.0</td>\n",
       "      <td>...</td>\n",
       "      <td>2.918537e+08</td>\n",
       "      <td>4.864228e+06</td>\n",
       "      <td>1.14125</td>\n",
       "      <td>Mid-term</td>\n",
       "      <td>3.750000</td>\n",
       "      <td>4</td>\n",
       "      <td>2.432114e+06</td>\n",
       "      <td>1</td>\n",
       "      <td>9.728456e+06</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  employee_id              domisili jenis_kelamin date_of_birth   join_date  \\\n",
       "0      EM6407  Kota Jakarta Selatan     Laki-laki    1981-03-05  2022-03-13   \n",
       "1      EM6881             Tangerang     Laki-laki    1974-04-26  2022-04-11   \n",
       "2      EM9588            Kota Depok     Perempuan    1980-01-08  2022-02-22   \n",
       "3      EM6817    Kota Jakarta Timur     Perempuan    1985-06-15  2021-09-04   \n",
       "4      EM0933    Kota Jakarta Timur     Laki-laki    1981-10-31  2022-03-20   \n",
       "\n",
       "  resign_date marriage_stat  dependant education  absent_90D  ...  \\\n",
       "0  2023-08-08       Married          3        D3         3.0  ...   \n",
       "1  2023-05-31       Married          0        D3         2.0  ...   \n",
       "2  2023-08-30       Married          3        D1         4.0  ...   \n",
       "3  2023-01-13       Married          2      SLTA        10.0  ...   \n",
       "4  2024-09-08       Married          1      SLTA         7.0  ...   \n",
       "\n",
       "   total_income_work income_dependant_ratio work_efficiency  \\\n",
       "0       1.169413e+08           1.719725e+06         1.22500   \n",
       "1       1.369110e+08           1.053162e+07         1.17375   \n",
       "2       1.408170e+08           1.955791e+06         1.18625   \n",
       "3       3.969525e+07           8.269843e+05         1.13125   \n",
       "4       2.918537e+08           4.864228e+06         1.14125   \n",
       "\n",
       "   active_work_category  work_stability_score position_score  \\\n",
       "0              Mid-term              4.250000              4   \n",
       "1              Mid-term              4.333333              4   \n",
       "2              Mid-term              3.600000              4   \n",
       "3              Mid-term              1.454545              1   \n",
       "4              Mid-term              3.750000              4   \n",
       "\n",
       "  job_income_position_score  education_score  education_income_ratio  \\\n",
       "0              1.719725e+06                4            1.719725e+06   \n",
       "1              2.632904e+06                4            2.632904e+06   \n",
       "2              1.955791e+06                2            3.911582e+06   \n",
       "3              2.480953e+06                1            2.480953e+06   \n",
       "4              2.432114e+06                1            9.728456e+06   \n",
       "\n",
       "   weighted_satisfaction_performance  \n",
       "0                                3.4  \n",
       "1                                4.0  \n",
       "2                                3.6  \n",
       "3                                1.0  \n",
       "4                                4.0  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test = pd.read_csv('D:/Tugas Akhir/Codingan/Development/App/data/df_test_YESUSFIX.csv')\n",
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.9432835820895522\n",
      "Precision: 1.0\n",
      "Recall: 0.9432835820895522\n",
      "F1 Score: 0.9708141321044547\n"
     ]
    }
   ],
   "source": [
    "X_test = df_test.drop(['churn_status', 'employee_id', 'date_of_birth', 'join_date', \n",
    "                       'resign_date', 'active_work_months'], axis=1)\n",
    "\n",
    "cat_feature = ['departemen', 'position', 'domisili', 'marriage_stat', 'job_satisfaction', 'performance_rating',\n",
    "               'education', 'active_work_category', 'resign_risk_indicator', 'jenis_kelamin']\n",
    "\n",
    "y_pred = final_model.predict(X_test)\n",
    "\n",
    "X_test['predicted_churn'] = y_pred\n",
    "\n",
    "accuracy = accuracy_score(df_test['churn_status'], y_pred)\n",
    "precision = precision_score(df_test['churn_status'], y_pred, zero_division=0)\n",
    "recall = recall_score(df_test['churn_status'], y_pred, zero_division=0)\n",
    "f1 = f1_score(df_test['churn_status'], y_pred, zero_division=0)\n",
    "\n",
    "print(\"Accuracy:\", accuracy)\n",
    "print(\"Precision:\", precision)\n",
    "print(\"Recall:\", recall)\n",
    "print(\"F1 Score:\", f1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.9432835820895522\n",
      "Precision: 1.0\n",
      "Recall: 0.9432835820895522\n",
      "F1 Score: 0.9708141321044547\n"
     ]
    }
   ],
   "source": [
    "X_test = df_test.drop(['churn_status', 'employee_id', 'date_of_birth', 'join_date', \n",
    "                       'resign_date', 'active_work_months'], axis=1)\n",
    "\n",
    "cat_feature = ['departemen', 'position', 'domisili', 'marriage_stat', 'job_satisfaction', 'performance_rating',\n",
    "               'education', 'active_work_category', 'resign_risk_indicator', 'jenis_kelamin']\n",
    "\n",
    "y_pred = final_model.predict(X_test)\n",
    "\n",
    "X_test['predicted_churn'] = y_pred\n",
    "\n",
    "accuracy = accuracy_score(df_test['churn_status'], y_pred)\n",
    "precision = precision_score(df_test['churn_status'], y_pred, zero_division=0)\n",
    "recall = recall_score(df_test['churn_status'], y_pred, zero_division=0)\n",
    "f1 = f1_score(df_test['churn_status'], y_pred, zero_division=0)\n",
    "\n",
    "print(\"Accuracy:\", accuracy)\n",
    "print(\"Precision:\", precision)\n",
    "print(\"Recall:\", recall)\n",
    "print(\"F1 Score:\", f1)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.10.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}