diabetes-classification-eda-nn-knightbearr.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "058dee5b",
   "metadata": {
    "papermill": {
     "duration": 0.035628,
     "end_time": "2021-12-06T23:15:36.675194",
     "exception": false,
     "start_time": "2021-12-06T23:15:36.639566",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Introduction**\n",
    "\n",
    "Thank you [**Mr.Larxel**](https://www.kaggle.com/andrewmvd) for creating this very intersting Data. Hope you're doing well as always.\n",
    "\n",
    "Okay, In this notebook, I'll create a Classification Model to predict Diabetes, and before we build our model, let me try to find some common features that associate with diabetic risk, okay, prepare your coffee, and let's get started.\n",
    "\n",
    "Don't forget to upvote if you found this notebook useful, and don't forget to give me a feedback!\n",
    "\n",
    "Sorry if my english is bad.\n",
    "\n",
    "**regards,** <br>\n",
    "**Azmi**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1159268c",
   "metadata": {
    "papermill": {
     "duration": 0.032995,
     "end_time": "2021-12-06T23:15:36.741827",
     "exception": false,
     "start_time": "2021-12-06T23:15:36.708832",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **About this Dataset**\n",
    "\n",
    "Diabetes is one of the fastest growing chronic life threatening diseases that have already affected $422$ million people worldwide according to the report of World Health Organization (WHO), in $2018$. Due to the presence of a relatively long asymptomatic phase, early detection of diabetes is always desired for a clinically meaningful outcome. Around $50$% of all people suffering from diabetes are undiagnosed because of its long-term asymptomatic phase.\n",
    "\n",
    "This dataset contains $520$ observations with $17$ characteristics, collected using direct questionnaires and diagnosis results from the patients in the Sylhet Diabetes Hospital in Sylhet, Bangladesh.\n",
    "\n",
    "**Data from:**\n",
    "\n",
    "Islam M.M.F., Ferdousi R., Rahman S., Bushra H.Y. ($2020$) Likelihood Prediction of Diabetes at Early Stage Using Data Mining Techniques. In: Gupta M., Konar D., Bhattacharyya S., Biswas S. (eds) Computer Vision and Machine Intelligence in Medical Image Analysis. Advances in Intelligent Systems and Computing, vol $992$. Springer, Singapore. https://doi.org/10.1007/978-981-13-8798-2_12"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c0e289d0",
   "metadata": {
    "papermill": {
     "duration": 0.032918,
     "end_time": "2021-12-06T23:15:36.808361",
     "exception": false,
     "start_time": "2021-12-06T23:15:36.775443",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Target**\n",
    "\n",
    "Predict the Presence of Diabetes."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13e7ded5",
   "metadata": {
    "papermill": {
     "duration": 0.032923,
     "end_time": "2021-12-06T23:15:36.876562",
     "exception": false,
     "start_time": "2021-12-06T23:15:36.843639",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "*Let's get started...*\n",
    "\n",
    "# **Import Necessary Libraries**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "41a00ecd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:36.950127Z",
     "iopub.status.busy": "2021-12-06T23:15:36.948248Z",
     "iopub.status.idle": "2021-12-06T23:15:43.283910Z",
     "shell.execute_reply": "2021-12-06T23:15:43.282960Z",
     "shell.execute_reply.started": "2021-12-06T23:14:37.150129Z"
    },
    "papermill": {
     "duration": 6.374342,
     "end_time": "2021-12-06T23:15:43.284137",
     "exception": false,
     "start_time": "2021-12-06T23:15:36.909795",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.6.2\n",
      "Setup complete!\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import os\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import warnings\n",
    "import tensorflow as tf\n",
    "from matplotlib import pylab as plt\n",
    "from IPython.core.interactiveshell import InteractiveShell\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n",
    "warnings.simplefilter(action=\"ignore\", category=Warning)\n",
    "InteractiveShell.ast_node_interactivity = 'all'\n",
    "\n",
    "%reload_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "sns.set_style('whitegrid')\n",
    "sns.set_context('paper', font_scale=1.5)\n",
    "plt.style.use('fivethirtyeight')\n",
    "pd.set_option(\"display.width\", 100)\n",
    "pd.set_option(\"display.max_columns\", 25)\n",
    "pd.set_option(\"display.max_rows\", 25)\n",
    "\n",
    "print(tf.__version__)\n",
    "print(\"Setup complete!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "02333b93",
   "metadata": {
    "papermill": {
     "duration": 0.033313,
     "end_time": "2021-12-06T23:15:43.352565",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.319252",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Read in updated DataFrame**\n",
    "\n",
    "Let's see the data and how it looks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "33820e5e",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:43.424597Z",
     "iopub.status.busy": "2021-12-06T23:15:43.423930Z",
     "iopub.status.idle": "2021-12-06T23:15:43.536890Z",
     "shell.execute_reply": "2021-12-06T23:15:43.537410Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.150245Z"
    },
    "jupyter": {
     "source_hidden": true
    },
    "papermill": {
     "duration": 0.15144,
     "end_time": "2021-12-06T23:15:43.537616",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.386176",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>polyuria</th>\n",
       "      <th>polydipsia</th>\n",
       "      <th>sudden_weight_loss</th>\n",
       "      <th>weakness</th>\n",
       "      <th>polyphagia</th>\n",
       "      <th>genital_thrush</th>\n",
       "      <th>visual_blurring</th>\n",
       "      <th>itching</th>\n",
       "      <th>irritability</th>\n",
       "      <th>delayed_healing</th>\n",
       "      <th>partial_paresis</th>\n",
       "      <th>muscle_stiffness</th>\n",
       "      <th>alopecia</th>\n",
       "      <th>obesity</th>\n",
       "      <th>class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>40</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>58</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>41</td>\n",
       "      <td>Male</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>45</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>60</td>\n",
       "      <td>Male</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>515</th>\n",
       "      <td>39</td>\n",
       "      <td>Female</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>516</th>\n",
       "      <td>48</td>\n",
       "      <td>Female</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>517</th>\n",
       "      <td>58</td>\n",
       "      <td>Female</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>518</th>\n",
       "      <td>32</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>519</th>\n",
       "      <td>42</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>520 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     age  gender  polyuria  polydipsia  sudden_weight_loss  weakness  polyphagia  genital_thrush  \\\n",
       "0     40    Male         0           1                   0         1           0               0   \n",
       "1     58    Male         0           0                   0         1           0               0   \n",
       "2     41    Male         1           0                   0         1           1               0   \n",
       "3     45    Male         0           0                   1         1           1               1   \n",
       "4     60    Male         1           1                   1         1           1               0   \n",
       "..   ...     ...       ...         ...                 ...       ...         ...             ...   \n",
       "515   39  Female         1           1                   1         0           1               0   \n",
       "516   48  Female         1           1                   1         1           1               0   \n",
       "517   58  Female         1           1                   1         1           1               0   \n",
       "518   32  Female         0           0                   0         1           0               0   \n",
       "519   42    Male         0           0                   0         0           0               0   \n",
       "\n",
       "     visual_blurring  itching  irritability  delayed_healing  partial_paresis  muscle_stiffness  \\\n",
       "0                  0        1             0                1                0                 1   \n",
       "1                  1        0             0                0                1                 0   \n",
       "2                  0        1             0                1                0                 1   \n",
       "3                  0        1             0                1                0                 0   \n",
       "4                  1        1             1                1                1                 1   \n",
       "..               ...      ...           ...              ...              ...               ...   \n",
       "515                0        1             0                1                1                 0   \n",
       "516                0        1             1                1                1                 0   \n",
       "517                1        0             0                0                1                 1   \n",
       "518                1        1             0                1                0                 0   \n",
       "519                0        0             0                0                0                 0   \n",
       "\n",
       "     alopecia  obesity  class  \n",
       "0           1        1      1  \n",
       "1           1        0      1  \n",
       "2           1        0      1  \n",
       "3           0        0      1  \n",
       "4           1        1      1  \n",
       "..        ...      ...    ...  \n",
       "515         0        0      1  \n",
       "516         0        0      1  \n",
       "517         0        1      1  \n",
       "518         1        0      0  \n",
       "519         0        0      0  \n",
       "\n",
       "[520 rows x 17 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw = \"../input/early-diabetes-classification/diabetes_data.csv\"\n",
    "diabetes_data = pd.read_csv(raw, sep=\";\")\n",
    "diabetes_data "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d435086d",
   "metadata": {
    "papermill": {
     "duration": 0.034411,
     "end_time": "2021-12-06T23:15:43.607933",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.573522",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Looks good... Let's continue.."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ca5a85ff",
   "metadata": {
    "papermill": {
     "duration": 0.034085,
     "end_time": "2021-12-06T23:15:43.676594",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.642509",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Let's Check our data**\n",
    "\n",
    "Let's check our data before we move on to the preprocessing steps..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cbea15b4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:43.753208Z",
     "iopub.status.busy": "2021-12-06T23:15:43.752496Z",
     "iopub.status.idle": "2021-12-06T23:15:43.826542Z",
     "shell.execute_reply": "2021-12-06T23:15:43.827289Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.256101Z"
    },
    "papermill": {
     "duration": 0.115001,
     "end_time": "2021-12-06T23:15:43.827525",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.712524",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 520 entries, 0 to 519\n",
      "Data columns (total 17 columns):\n",
      " #   Column              Non-Null Count  Dtype \n",
      "---  ------              --------------  ----- \n",
      " 0   age                 520 non-null    int64 \n",
      " 1   gender              520 non-null    object\n",
      " 2   polyuria            520 non-null    int64 \n",
      " 3   polydipsia          520 non-null    int64 \n",
      " 4   sudden_weight_loss  520 non-null    int64 \n",
      " 5   weakness            520 non-null    int64 \n",
      " 6   polyphagia          520 non-null    int64 \n",
      " 7   genital_thrush      520 non-null    int64 \n",
      " 8   visual_blurring     520 non-null    int64 \n",
      " 9   itching             520 non-null    int64 \n",
      " 10  irritability        520 non-null    int64 \n",
      " 11  delayed_healing     520 non-null    int64 \n",
      " 12  partial_paresis     520 non-null    int64 \n",
      " 13  muscle_stiffness    520 non-null    int64 \n",
      " 14  alopecia            520 non-null    int64 \n",
      " 15  obesity             520 non-null    int64 \n",
      " 16  class               520 non-null    int64 \n",
      "dtypes: int64(16), object(1)\n",
      "memory usage: 69.2+ KB\n"
     ]
    }
   ],
   "source": [
    "# getting the information \n",
    "diabetes_data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b33a0ec",
   "metadata": {
    "papermill": {
     "duration": 0.036271,
     "end_time": "2021-12-06T23:15:43.899859",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.863588",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### **Uniqueness Categorical Variables**\n",
    "Let's have a look at categorical variables. How many unique values of these variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "73c76419",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:43.977397Z",
     "iopub.status.busy": "2021-12-06T23:15:43.976643Z",
     "iopub.status.idle": "2021-12-06T23:15:44.039187Z",
     "shell.execute_reply": "2021-12-06T23:15:44.039677Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.346410Z"
    },
    "papermill": {
     "duration": 0.103951,
     "end_time": "2021-12-06T23:15:44.039859",
     "exception": false,
     "start_time": "2021-12-06T23:15:43.935908",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "gender : 2 unique values(s)\n"
     ]
    }
   ],
   "source": [
    "# Getting the uniqueness categorical variable\n",
    "categorical = diabetes_data.select_dtypes([\"category\", \"object\"]).columns\n",
    "for cat_col in categorical:\n",
    "    print(f\"{cat_col} : {diabetes_data[cat_col].nunique()} unique values(s)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b62c99d5",
   "metadata": {
    "papermill": {
     "duration": 0.035203,
     "end_time": "2021-12-06T23:15:44.110821",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.075618",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Hmm, great...\n",
    "\n",
    "How bout the discrete and continuous variables? Let's have a look."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "602dfb33",
   "metadata": {
    "papermill": {
     "duration": 0.03497,
     "end_time": "2021-12-06T23:15:44.181256",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.146286",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "\n",
    "#### **Discrete and Continuous Variables**\n",
    "Let's have a look at Discrete and Continuous variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "eabf90f8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:44.258849Z",
     "iopub.status.busy": "2021-12-06T23:15:44.257846Z",
     "iopub.status.idle": "2021-12-06T23:15:44.320463Z",
     "shell.execute_reply": "2021-12-06T23:15:44.321160Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.425739Z"
    },
    "papermill": {
     "duration": 0.104201,
     "end_time": "2021-12-06T23:15:44.321395",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.217194",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "age : 51 unique values(s)\n",
      "polyuria : 2 unique values(s)\n",
      "polydipsia : 2 unique values(s)\n",
      "sudden_weight_loss : 2 unique values(s)\n",
      "weakness : 2 unique values(s)\n",
      "polyphagia : 2 unique values(s)\n",
      "genital_thrush : 2 unique values(s)\n",
      "visual_blurring : 2 unique values(s)\n",
      "itching : 2 unique values(s)\n",
      "irritability : 2 unique values(s)\n",
      "delayed_healing : 2 unique values(s)\n",
      "partial_paresis : 2 unique values(s)\n",
      "muscle_stiffness : 2 unique values(s)\n",
      "alopecia : 2 unique values(s)\n",
      "obesity : 2 unique values(s)\n",
      "class : 2 unique values(s)\n"
     ]
    }
   ],
   "source": [
    "# Getting the uniqueness discrete and continuous variables\n",
    "numeric = diabetes_data.select_dtypes([\"int\", \"float\"]).columns\n",
    "for num_col in numeric: # print every unique values\n",
    "    print(f\"{num_col} : {diabetes_data[num_col].nunique()} unique values(s)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69f1dea4",
   "metadata": {
    "papermill": {
     "duration": 0.035512,
     "end_time": "2021-12-06T23:15:44.395080",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.359568",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### **Check the shape**\n",
    "\n",
    "Let's check the shape, n-dimension of our data, also the features and the label... It's important to check the shape and dimension of our data... "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8ca6038c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:44.469837Z",
     "iopub.status.busy": "2021-12-06T23:15:44.469094Z",
     "iopub.status.idle": "2021-12-06T23:15:44.530605Z",
     "shell.execute_reply": "2021-12-06T23:15:44.529954Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.498038Z"
    },
    "papermill": {
     "duration": 0.099968,
     "end_time": "2021-12-06T23:15:44.530753",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.430785",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape: (520, 17)\n",
      "N-Dimension: 2\n",
      "Features Shape: (520, 16)\n",
      "Features N-Dimension: 2\n",
      "Label Shape: (520,)\n",
      "Label N-Dimension: 1\n"
     ]
    }
   ],
   "source": [
    "# Get the features and label form our data\n",
    "features, label = diabetes_data.drop(columns=[\"class\"]), diabetes_data[\"class\"] \n",
    "print(f\"Shape: {diabetes_data.shape}\") # print-out the car shape\n",
    "print(f\"N-Dimension: {diabetes_data.ndim}\") # print-out the car n-dimensional \n",
    "print(f\"Features Shape: {features.shape}\") # print-out the features shape\n",
    "print(f\"Features N-Dimension: {features.ndim}\") # print-out the features n-dimension\n",
    "print(f\"Label Shape: {label.shape}\") # print-out the label shape\n",
    "print(f\"Label N-Dimension: {label.ndim}\") # print-out the label n-dimension"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ce1a977e",
   "metadata": {
    "papermill": {
     "duration": 0.035288,
     "end_time": "2021-12-06T23:15:44.601950",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.566662",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### **Check the missing value**\n",
    "\n",
    "Let's check the missing value...   \n",
    "\n",
    "> **Question:** How many missing data points do we have?\n",
    "\n",
    "Let's see how many we have in each column. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "743cbd09",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:44.678413Z",
     "iopub.status.busy": "2021-12-06T23:15:44.676963Z",
     "iopub.status.idle": "2021-12-06T23:15:44.741778Z",
     "shell.execute_reply": "2021-12-06T23:15:44.741269Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.572081Z"
    },
    "papermill": {
     "duration": 0.103613,
     "end_time": "2021-12-06T23:15:44.741921",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.638308",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>gender</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>polyuria</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>polydipsia</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sudden_weight_loss</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weakness</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>polyphagia</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>genital_thrush</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>visual_blurring</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>itching</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>irritability</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>delayed_healing</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>partial_paresis</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>muscle_stiffness</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>alopecia</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>obesity</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>class</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    0\n",
       "age                 0\n",
       "gender              0\n",
       "polyuria            0\n",
       "polydipsia          0\n",
       "sudden_weight_loss  0\n",
       "weakness            0\n",
       "polyphagia          0\n",
       "genital_thrush      0\n",
       "visual_blurring     0\n",
       "itching             0\n",
       "irritability        0\n",
       "delayed_healing     0\n",
       "partial_paresis     0\n",
       "muscle_stiffness    0\n",
       "alopecia            0\n",
       "obesity             0\n",
       "class               0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get the number of missing data points per column\n",
    "missing_values_count = diabetes_data.isnull().sum()\n",
    "# Look at the missing points\n",
    "missing_values_count.to_frame()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b8e44471",
   "metadata": {
    "papermill": {
     "duration": 0.037142,
     "end_time": "2021-12-06T23:15:44.816402",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.779260",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Great! our data is not have a missing value, then let's visualize our data!"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e23079a",
   "metadata": {
    "papermill": {
     "duration": 0.037024,
     "end_time": "2021-12-06T23:15:44.890245",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.853221",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **EDA (Explanatory Data Analysis)**\n",
    "\n",
    "In statistics, exploratory data analysis is an approach of analyzing data sets to summarize their main characteristics, often using statistical graphics and other data visualization methods."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "7d6c05de",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:44.969874Z",
     "iopub.status.busy": "2021-12-06T23:15:44.969249Z",
     "iopub.status.idle": "2021-12-06T23:15:46.911180Z",
     "shell.execute_reply": "2021-12-06T23:15:46.911947Z",
     "shell.execute_reply.started": "2021-12-06T23:14:43.649217Z"
    },
    "jupyter": {
     "source_hidden": true
    },
    "papermill": {
     "duration": 1.984896,
     "end_time": "2021-12-06T23:15:46.912193",
     "exception": false,
     "start_time": "2021-12-06T23:15:44.927297",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1728x1008 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# let's make a correlation matrix\n",
    "plt.figure(figsize=(24, 14))\n",
    "sns.heatmap(diabetes_data.corr(), annot=True);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c4844d61",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:47.007081Z",
     "iopub.status.busy": "2021-12-06T23:15:47.006278Z",
     "iopub.status.idle": "2021-12-06T23:15:47.075805Z",
     "shell.execute_reply": "2021-12-06T23:15:47.075267Z",
     "shell.execute_reply.started": "2021-12-06T23:14:45.489538Z"
    },
    "papermill": {
     "duration": 0.119613,
     "end_time": "2021-12-06T23:15:47.075960",
     "exception": false,
     "start_time": "2021-12-06T23:15:46.956347",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "class                 1.000000\n",
       "polyuria              0.665922\n",
       "polydipsia            0.648734\n",
       "sudden_weight_loss    0.436568\n",
       "partial_paresis       0.432288\n",
       "polyphagia            0.342504\n",
       "irritability          0.299467\n",
       "visual_blurring       0.251300\n",
       "weakness              0.243275\n",
       "muscle_stiffness      0.122474\n",
       "genital_thrush        0.110288\n",
       "age                   0.108679\n",
       "obesity               0.072173\n",
       "delayed_healing       0.046980\n",
       "itching              -0.013384\n",
       "alopecia             -0.267512\n",
       "Name: class, dtype: float64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "diabetes_data.corr()['class'].sort_values(ascending=False) # the correlation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6dd9edbf",
   "metadata": {
    "papermill": {
     "duration": 0.04318,
     "end_time": "2021-12-06T23:15:47.162868",
     "exception": false,
     "start_time": "2021-12-06T23:15:47.119688",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "We can see the features that associate with diabetic risk above... Let's check the skewness value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d9dbb499",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:47.256071Z",
     "iopub.status.busy": "2021-12-06T23:15:47.255369Z",
     "iopub.status.idle": "2021-12-06T23:15:47.320550Z",
     "shell.execute_reply": "2021-12-06T23:15:47.321183Z",
     "shell.execute_reply.started": "2021-12-06T23:14:45.555387Z"
    },
    "papermill": {
     "duration": 0.11477,
     "end_time": "2021-12-06T23:15:47.321351",
     "exception": false,
     "start_time": "2021-12-06T23:15:47.206581",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "obesity               1.769420\n",
       "genital_thrush        1.334223\n",
       "irritability          1.206305\n",
       "alopecia              0.657608\n",
       "muscle_stiffness      0.517893\n",
       "sudden_weight_loss    0.336359\n",
       "age                   0.329359\n",
       "partial_paresis       0.280426\n",
       "polydipsia            0.209426\n",
       "visual_blurring       0.209426\n",
       "polyphagia            0.178134\n",
       "delayed_healing       0.162537\n",
       "itching               0.054022\n",
       "polyuria              0.015430\n",
       "weakness             -0.352476\n",
       "class                -0.475715\n",
       "dtype: float64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking skewness value\n",
    "# if value lies between -0.5 to 0.5  then it is normal otherwise skewed\n",
    "skew_value = diabetes_data.skew().sort_values(ascending=False)\n",
    "skew_value"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2095c7c5",
   "metadata": {
    "papermill": {
     "duration": 0.04313,
     "end_time": "2021-12-06T23:15:47.407956",
     "exception": false,
     "start_time": "2021-12-06T23:15:47.364826",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Okay great! "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "441c97ac",
   "metadata": {
    "papermill": {
     "duration": 0.043636,
     "end_time": "2021-12-06T23:15:47.495017",
     "exception": false,
     "start_time": "2021-12-06T23:15:47.451381",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## **Gender Distribution**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "55265887",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:47.589196Z",
     "iopub.status.busy": "2021-12-06T23:15:47.588206Z",
     "iopub.status.idle": "2021-12-06T23:15:47.891041Z",
     "shell.execute_reply": "2021-12-06T23:15:47.890502Z",
     "shell.execute_reply.started": "2021-12-06T23:14:45.621083Z"
    },
    "jupyter": {
     "source_hidden": true
    },
    "papermill": {
     "duration": 0.352351,
     "end_time": "2021-12-06T23:15:47.891193",
     "exception": false,
     "start_time": "2021-12-06T23:15:47.538842",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABiAAAAIZCAYAAAAvJff7AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8/fFQqAAAACXBIWXMAAAsTAAALEwEAmpwYAAA3VElEQVR4nO3de5RW9X3v8c8MyHAb7hYIqYgICKlAvFCIsTXxGmuKCtVotauJR4sSNcZjErtC6jKpRryDiZDEECtqbFXEeEe8nOhpxHhpGkFnNEIMghwEhBmG28ycP6wTJ4A6uuFhxtdrrVlh9u/3PM93P3/Fea+9d9maNWsaAwAAAAAAUKDyUg8AAAAAAAC0PQIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAIAWW7NmTS699NIcffTROfjgg3PyySfn3//933foZz7zzDMZM2ZMjjnmmB36OQAAQDEECAAAoEXWr1+ff/qnf8qcOXOyatWqdO/ePYsXL87Pf/7zUo8GAADsQtqXegAAAKB1ufXWW/Pqq6+mZ8+emTFjRgYNGpS33norN998c6lHAwAAdiECBAAA0CIPPfRQkuTkk0/OoEGDkiTdu3fPWWedlSRpbGzMLbfckjvvvDPLli1Lr169csQRR2TSpEnp0KFDkmTSpEl59tlnM2nSpDz99NN54YUXMnLkyFx88cXp1atXkuSNN97Id7/73fzXf/1XhgwZkuOPP36rWT7IZyXJ+PHjs2zZslx00UWZN29efv3rX6dDhw75xje+kSOPPHKHfl8AAPBx5RZMAADAB7Zx48YsWbIkSTJ69Oht7pk5c2auvfbavP766+nVq1dWrVqV2bNn5+KLL95q7+zZs1NdXZ2NGzdmwYIFmTVrVtPalClTsmDBgmzevDmLFy/OVVdd9ZE+K0muuuqq/OpXv0r37t1TW1ubVatWfYhvAQAA+CAECAAA4ANbt25dGhoakiS9evXKmjVrcvzxxzf9/Pa3v83s2bNTUVGR2bNn55577sndd9+d7t2756GHHsrSpUubvd+IESPy0EMP5Z/+6Z+SJP/93/+dJHnttdfy/PPPJ0mmTZuWefPmZdiwYc1eu3bt2hZ9VpL07t07c+fOzT333JMHH3ww+++/f9FfEQAA8D/cggkAAPhQNm/enC1btuQPf/hD07G1a9dm06ZN2W233XLBBRc0Ha+rq0uSvPTSSxkwYEDT8c9+9rMpLy/P8OHDkyRr1qxJkrz88stJkv79+2fMmDFJki9+8Yt55plnml7729/+tkWflbx926g/+7M/S/L2baO6d+/+0b4EAABgu1wBAQAAfGCVlZUpL3/7PyNWr16dPn36ZMGCBfmbv/mbJMlbb72V5O048Yc//KHpZ9OmTUmS9evXN3u/jh07JknatWuX5O1nOiRv3+opSdPzIP703x/ms5Kkb9++H/bUAQCAFnIFBAAA8IFVVFRk4MCBefXVV/PrX/96q1sYVVZWJkn23HPP/Pu///uH/px3rkx49zMa/vR5DR/ms96JJwAAwI7n/30DAAAtcsQRRyRJ5syZk9deey3J21chJGm6JdLixYvz4IMPNr1m+fLlmTZtWtO+97PnnnsmSZYtW5YFCxakvr4+v/jFL5rt+Yu/+ItCPgsAANgxXAEBAAC0yEknnZQHHnggS5YsyQknnJDevXtnxYoVSZIePXrk5JNPzo033pgpU6bk8ssvT/L2syGSND1s+v30798/Bx54YJ5++umcc8456dy581ZXLxT1WQAAwI7hCggAAKBFOnfunJkzZ+aLX/xiunXrllWrVmXQoEE599xzM2rUqJx11lm54IILMnjw4GzYsCGNjY3ZZ5998r/+1//Kbrvt9oE/59vf/nb222+/tG/fPnvuuWe+9rWvbbWnqM8CAACKV7ZmzZrGUg8BAAAAAAC0La6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwrUv9QDsel57a0OW1Wwq9RgAAG1O/64d8ufdO5Z6DAAAgJ1CgGAry2o25ctzXyz1GAAAbc6s8fsIEAAAwMeGWzABAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAArXvlQffMMNN+See+7JmjVr0r59++yzzz45++yzM3To0CTJSy+9lKlTp6aqqio9evTIKaeckhNPPLHp9Rs2bMjVV1+d+fPnp76+PuPGjcs3v/nNdO/evVSnBAAAAAAA/I+SXQFx2GGH5cYbb8yjjz6a++67L2PHjs25556bhoaG1NTU5Nxzz83YsWPz8MMP55JLLsmPf/zjzJ8/v+n1V199dRYtWpRbb701c+fOTV1dXS666KJSnQ4AAAAAAPAuJQsQAwcOTLdu3ZIkjY2NKS8vz5tvvpmampo89thjKS8vz2mnnZaKiorsu+++GT9+fG6//fYkb1/9cN9992XSpEnZfffd061bt5xzzjl58skns3z58lKdEgAAAAAA8D9KdgumJHniiSfyne98JzU1NSkrK8vJJ5+cbt26paqqKsOGDUt5+R/7yPDhwzN37twkye9///ts3Lgxw4cPb1ofNGhQOnbsmKqqqvTr12+nnwsAAAAAAPBHJQ0Qn/3sZ/PII4/krbfeyr333tsUDmpra9O1a9dmeysrK1NbW9u0/s6x7e3Znurq6qLGb7PqyrqVegQAgDaprq4u1dVvlHoMAACAQgwZMuQ910saIN7RvXv3fOlLX8qhhx6agQMHpkuXLlm1alWzPevWrUuXLl2SpOl/a2pq0qNHj23u2Z73+0JIVi9dW+oRAADapE6dOmXIgL6lHgMAAGCnKNkzIP5UQ0NDtmzZktdeey1Dhw5NVVVVGhoamtZffPHFpniwxx57pKKiIosWLWpaX7x4cTZs2CAwAAAAAADALqBkAeK2227LypUrkySrV6/O1KlT06FDh+y777455JBDUl9fn1mzZmXTpk154YUXctddd2XChAlJko4dO+boo4/OzJkzs3LlyqxduzbTpk3LQQcdlP79+5fqlAAAAAAAgP9RslswPf3005k1a1bWr1+fLl265FOf+lR+8IMfpHfv3kmSa6+9Npdddll+9rOfpXv37jn99NNz2GGHNb3+vPPOy1VXXZUTTzwxDQ0NGTt2bL71rW+V6nQAAAAAAIB3KVuzZk1jqYdg17Jg6dp8ee6LpR4DAKDNmTV+n4wZ0K3UYwAAAOwUu8wzIAAAAAAAgLZDgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACte+VB88ffr0PPHEE1mxYkU6deqUcePG5eyzz06PHj2a9owZMyYVFRUpL/9jJ7nhhhuy9957J0kaGhoyY8aM3H333amrq8uoUaNy4YUXpn///jv7dAAAAAAAgHcp2RUQ7dq1y8UXX5x58+Zl9uzZWbFiRS6++OKt9l1zzTV5/PHHm37eiQ9JctNNN+XBBx/MzJkzc//996dfv345//zz09DQsDNPBQAAAAAA+BMlCxBnnXVWhg0blvbt26dXr1454YQT8txzz7XoPe68886ceuqpGThwYDp37pyzzz47S5YsyfPPP79jhgYAAAAAAD6QXeYZEE8//XSzqxve8e1vfzuHHXZYTj311Nx1111Nx2tqarJs2bKMGDGi6VhlZWU++clPprq6emeMDAAAAAAAbEfJngHxbvPmzcvdd9+dGTNmNDt+3XXXZeTIkWnXrl1+/etfZ8qUKdmyZUsmTpyY2traJEnXrl2bvaaysjI1NTXb/Sxx4v3VlXUr9QgAAG1SXV1dqqvfKPUYAAAAhRgyZMh7rpc8QDz00EO57LLLcsUVV2SfffZptjZmzJimf48bNy4nnXRS7r///kycODFdunRJkq1iw7p167aKEu/2fl8Iyeqla0s9AgBAm9SpU6cMGdC31GMAAADsFCW9BdPcuXMzderUXHXVVTnggAPed395eXkaGxuTvH3lQ//+/bNo0aKm9ZqamixdulRkAAAAAACAEitZgLjtttty3XXXZdq0aRk1atRW6y+++GIWLlyYzZs3Z8uWLXnqqadyyy235Mgjj2zac/zxx2f27NlZsmRJ6urqMn369Oyxxx4ZPXr0TjwTAAAAAADgT5XsFkxXXnll2rVrlzPPPLPZ8dtuuy39+vXL//t//y/Tp0/PG2+8kXbt2qVfv36ZNGlSJkyY0LT31FNPTU1NTc4444zU1dVl1KhRueKKK1Jevss8WxsAAAAAAD6WytasWdNY6iHYtSxYujZfnvtiqccAAGhzZo3fJ2MGdCv1GAAAADuFSwUAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOHal+qDp0+fnieeeCIrVqxIp06dMm7cuJx99tnp0aNH056XXnopU6dOTVVVVXr06JFTTjklJ554YtP6hg0bcvXVV2f+/Pmpr6/PuHHj8s1vfjPdu3cvwRkBAAAAAADvKNkVEO3atcvFF1+cefPmZfbs2VmxYkUuvvjipvWampqce+65GTt2bB5++OFccskl+fGPf5z58+c37bn66quzaNGi3HrrrZk7d27q6upy0UUXleBsAAAAAACAdytZgDjrrLMybNiwtG/fPr169coJJ5yQ5557rmn9scceS3l5eU477bRUVFRk3333zfjx43P77bcnefvqh/vuuy+TJk3K7rvvnm7duuWcc87Jk08+meXLl5fqtAAAAAAAgJTwFkx/6umnn87ee+/d9HtVVVWGDRuW8vI/NpLhw4dn7ty5SZLf//732bhxY4YPH960PmjQoHTs2DFVVVXp16/fNj+nurp6B51B21FX1q3UIwAAtEl1dXWprn6j1GMAAAAUYsiQIe+5vksEiHnz5uXuu+/OjBkzmo7V1tama9euzfZVVlamtra2af2dY9vbsy3v94WQrF66ttQjAAC0SZ06dcqQAX1LPQYAAMBOUbJbML3joYceyve///1cccUV2WeffZqOd+nSJTU1Nc32rlu3Ll26dGlaT/KeewAAAAAAgNIoaYCYO3dupk6dmquuuioHHHBAs7WhQ4emqqoqDQ0NTcdefPHFpisY9thjj1RUVGTRokVN64sXL86GDRtc5QAAAAAAACVWsgBx22235brrrsu0adMyatSordYPOeSQ1NfXZ9asWdm0aVNeeOGF3HXXXZkwYUKSpGPHjjn66KMzc+bMrFy5MmvXrs20adNy0EEHpX///jv7dAAAAAAAgHcpW7NmTWMpPnjMmDFp165dOnTo0Oz4bbfd1vQA6ZdeeimXXXZZqqur071795x66qk58cQTm/Zu2LAhV111VebPn5+GhoaMHTs23/rWt9K9e/edei5tzYKla/PluS+WegwAgDZn1vh9MmZAt1KPAQAAsFOULECw6xIgAAB2DAECAAD4OCn5Q6gBAAAAAIC2R4AAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCtS/1AAAAAHx49SvfSOOaN0s9BgBAm1LWo3fa9elb6jFaPQECAACgFWtc82bqfvDdUo8BANCmdJo8JREgPjK3YAIAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOFaFCB+8pOf5JVXXtnu+iuvvJKf/OQnH3koAAAAAACgdWtRgPjxj3+c6urq7a7/7ne/EyAAAAAAAIBib8FUW1ub9u3bF/mWAAAAAABAK/S+taC6ujpVVVVNvz///POpr6/fat+6detyxx13ZODAgcVOCAAAAAAAtDrvGyAee+yxptsqlZWVZc6cOZkzZ84291ZWVubiiy8udkIAAAAAAKDVed8Acdxxx+Wzn/1sGhsb8+UvfzlnnHFGPvOZzzTbU1ZWlk6dOmXAgAFuwQQAAAAAALx/gOjTp0/69OmTJLn++uuz5557plevXjt8MAAAAAAAoPVq0eUK++23346aAwAAAAAAaENafL+k//zP/8zdd9+dpUuXZt26dWlsbGy2/s5zIgAAAAAAgI+vFgWIm266KT/4wQ/Sq1evjBgxInvvvfeOmgsAAAAAAGjFWhQgbrvtthxwwAG55pprPGwaAAAAAADYrvKWbF67dm0+//nPiw8AAAAAAMB7alGA+NSnPpUlS5bsqFkAAAAAAIA2okUB4hvf+EYee+yxPPDAAztqHgAAAAAAoA1o0b2UvvWtb2Xz5s256KKLcumll2b33XdPu3btttp32223FTYgAAAAAADQ+rQoQPTs2TO9evXKwIEDd9Q8AAAAAABAG9CiADFjxowdNQcAAAAAANCGtOgZEAAAAAAAAB9Ei66AePbZZz/Qvv322+9DDQMAAAAAALQNLQoQZ555ZsrKyt53369+9asPPRAAAAAAAND6tShAXH/99Vsdq6+vz7Jly3LXXXeloaEhkydPLmw4AAAAAACgdWpRgHivWysdc8wxOeOMM/Lss8/mwAMP/MiDAQAAAAAArVdhD6EuLy/P4Ycfnrlz5xb1lgAAAAAAQCtVWIBIkrVr12bdunVFviUAAAAAANAKtegWTMuXL9/m8XXr1uW5557L7NmzM3r06CLmAgAAAAAAWrEWBYjx48enrKxsm2uNjY35i7/4i1x44YWFDAYAAAAAALReLQoQU6ZM2epYWVlZunXrlgEDBmSvvfYqbDAAAAAAAKD1alGAOOaYY3bUHAAAAAAAQBvSogDxjvr6+rz00kt5/fXXkySf+MQnss8++6S8vNBnWgMAAAAAAK1UiwPEvHnzcs011+TNN99MY2Njkrdvw9S7d+987Wtfy+GHH174kAAAAAAAQOvSogDx+OOPZ8qUKRk4cGD+8R//MXvuuWeSZPHixbnjjjvyne98JxUVFfmrv/qrHTErAAAAAADQSrQoQMyaNSv77LNPZs6cmYqKiqbjBx54YMaPH5/TTz89P/3pTwUIAAAAAAD4mGvRQxteeeWVfOELX2gWH97RoUOHHH300XnllVcKGw4AAAAAAGidWhQgOnbsmDVr1mx3ffXq1enYseNHnQkAAAAAAGjlWhQgDjzwwPz85z/Pc889t9Xaf/3Xf+W2227LmDFjChsOAAAAAABonVr0DIizzz47zz//fM4888wMGzYsAwcOTJIsWbIkL730Unr37p2vfvWrO2RQAAAAAACg9WjRFRD9+/fPzTffnBNPPDHr16/Po48+mkcffTTr16/PSSedlNmzZ6d///47alYAAAAAAKCVaNEVEHV1ddm4cWPOO++8nHfeeVutL1++PBs2bPAcCAAAAAAA+Jhr0RUQV199df73//7f212/4IILcu21137koQAAAAAAgNatRQHiqaeeyiGHHLLd9UMOOSS/+tWvPupMAAAAAABAK9eiAPHmm2+mT58+213v3bt3Vq5c+ZGHAgAAAAAAWrcWBYgePXrk1Vdf3e767373u3Tt2vUjDwUAAAAAALRuLQoQBx10UObMmZOFCxdutbZw4cLMmTMnn/nMZwobDgAAAAAAaJ3at2Tz6aefnieffDKnnXZaDjrooOy1115JkldeeSX/9//+3/Tu3TuTJk3aIYMCAAAAAACtR4sCRJ8+fXLjjTfmuuuuy+OPP55f/vKXSZIuXbrkC1/4Qs4666z3fEYEAAAAAADw8dCiAJG8/aDpf/mXf0ljY2NWr16dJOnZs2fKysoKHw4AAAAAAGidWhwg3lFWVpZevXoVOQsAAAAAANBGtOgh1AAAAAAAAB/Eh74CoggPPfRQ/uM//iMvv/xyamtrs2DBgmbrY8aMSUVFRcrL/9hJbrjhhuy9995JkoaGhsyYMSN333136urqMmrUqFx44YXp37//Tj0PAAAAAACguZIGiMrKykycODEbN27M9773vW3uueaaa7L//vtvc+2mm27Kgw8+mJkzZ2b33XfPNddck/PPPz+zZ89uFi0AAAAAAICdq6R/pR83blyOPPLIDBgw4EO9/s4778ypp56agQMHpnPnzjn77LOzZMmSPP/888UOCgAAAAAAtEhJr4D4IL797W9n8+bN6d+/fyZMmJBjjz02SVJTU5Nly5ZlxIgRTXsrKyvzyU9+MtXV1dlvv/22+X7V1dU7Y+xWra6sW6lHAABok+rq6lJd/Uapx6CN6Ve3vtQjAAC0OXXr12e5vyW/ryFDhrzn+i4dIK677rqMHDky7dq1y69//etMmTIlW7ZsycSJE1NbW5sk6dq1a7PXVFZWpqamZrvv+X5fCMnqpWtLPQIAQJvUqVOnDBnQt9Rj0MZseXlh6ko9BABAG9Opc+cM2dvfkj+qXfpBCWPGjEnHjh2z2267Zdy4cTnppJNy//33J0m6dOmSJFvFhnXr1m0VJQAAAAAAgJ1rlw4Qf6q8vDyNjY1J3r7yoX///lm0aFHTek1NTZYuXeoqBwAAAAAAKLGSBoj6+vps3LgxmzdvTpJs3LgxGzduTENDQ1588cUsXLgwmzdvzpYtW/LUU0/llltuyZFHHtn0+uOPPz6zZ8/OkiVLUldXl+nTp2ePPfbI6NGjS3RGAAAAAABAUuJnQNx///25+OKLm34/+OCDkyTXX3991q9fn+nTp+eNN95Iu3bt0q9fv0yaNCkTJkxo2n/qqaempqYmZ5xxRurq6jJq1KhcccUVKS9vVRd2AAAAAABAm1PSAHHMMcfkmGOO2e76O0Fie8rLyzN58uRMnjy56NEAAAAAAICPwKUCAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDh2pfywx966KH8x3/8R15++eXU1tZmwYIFzdZfeumlTJ06NVVVVenRo0dOOeWUnHjiiU3rGzZsyNVXX5358+envr4+48aNyze/+c107959Z58KAAAAAADwLiW9AqKysjITJ07Meeedt9VaTU1Nzj333IwdOzYPP/xwLrnkkvz4xz/O/Pnzm/ZcffXVWbRoUW699dbMnTs3dXV1ueiii3biGQAAAAAAANtS0gAxbty4HHnkkRkwYMBWa4899ljKy8tz2mmnpaKiIvvuu2/Gjx+f22+/PcnbVz/cd999mTRpUnbfffd069Yt55xzTp588sksX758Z58KAAAAAADwLrvsMyCqqqoybNiwlJf/ccThw4enuro6SfL73/8+GzduzPDhw5vWBw0alI4dO6aqqmqnzwsAAAAAAPxRSZ8B8V5qa2vTtWvXZscqKytTW1vbtP7Ose3t2ZZ3AgbbV1fWrdQjAAC0SXV1damufqPUY9DG9KtbX+oRAADanLr167Pc35Lf15AhQ95zfZcNEF26dMmqVauaHVu3bl26dOnStJ68/ayIHj16bHPPtrzfF0KyeunaUo8AANAmderUKUMG9C31GLQxW15emLpSDwEA0MZ06tw5Q/b2t+SPape9BdPQoUNTVVWVhoaGpmMvvvhiU0DYY489UlFRkUWLFjWtL168OBs2bBAZAAAAAACgxEoaIOrr67Nx48Zs3rw5SbJx48Zs3LgxDQ0NOeSQQ1JfX59Zs2Zl06ZNeeGFF3LXXXdlwoQJSZKOHTvm6KOPzsyZM7Ny5cqsXbs206ZNy0EHHZT+/fuX8rQAAAAAAOBjr6QB4v7778/BBx+cc845J0ly8MEH5+CDD85zzz2Xrl275tprr82TTz6ZQw89NN/85jdz+umn57DDDmt6/XnnnZehQ4fmxBNPzPjx41NRUZGLLrqoRGcDAAAAAAC8o2zNmjWNpR6CXcuCpWvz5bkvlnoMAIA2Z9b4fTJmQLdSj0Ebs+Xlhan7wXdLPQYAQJvSafKUtN97RKnHaPV22WdAAAAAAAAArZcAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUrn2pB3gvP/rRj/LTn/40FRUVTccOPvjgfO9730uSvPTSS5k6dWqqqqrSo0ePnHLKKTnxxBNLNS4AAAAAAPA/dukAkSSjR4/OjBkztjpeU1OTc889NxMmTMgPf/jDVFVV5bzzzkufPn1y6KGHlmBSAAAAAADgHa32FkyPPfZYysvLc9ppp6WioiL77rtvxo8fn9tvv73UowEAAAAAwMfeLn8FxKJFi3LEEUekY8eOGTlyZM4888wMGDAgVVVVGTZsWMrL/9hQhg8fnrlz55ZwWgAAAAAAINnFA8Shhx6aL37xi+nXr19WrlyZ6667Ll/96ldz8803p7a2Nl27dm22v7KyMrW1te/5ntXV1Tty5DahrqxbqUcAAGiT6urqUl39RqnHoI3pV7e+1CMAALQ5devXZ7m/Jb+vIUOGvOf6Lh0gBg8e3PTv3XffPVOmTMnnPve5/OY3v0mXLl2yatWqZvvXrVuXLl26vOd7vt8XQrJ66dpSjwAA0CZ16tQpQwb0LfUYtDFbXl6YulIPAQDQxnTq3DlD9va35I+q1T0DoqysLI2NjRk6dGiqqqrS0NDQtPbiiy8KDAAAAAAAsAvYpQPEvHnzsnr16iTJqlWrcskll6Rnz54ZOXJkDjnkkNTX12fWrFnZtGlTXnjhhdx1112ZMGFCiacGAAAAAAB26VswPfDAA7n88stTV1eXbt265dOf/nSuu+66ptssXXvttbnsssvys5/9LN27d8/pp5+eww47rMRTAwAAAAAAu3SAuPLKK99zfdiwYfnpT3+6k6YBAAAAAAA+qF36FkwAAAAAAEDrJEAAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIUTIAAAAAAAgMIJEAAAAAAAQOEECAAAAAAAoHACBAAAAAAAUDgBAgAAAAAAKJwAAQAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFA4AQIAAAAAACicAAEAAAAAABROgAAAAAAAAAonQAAAAAAAAIVr9QGioaEhP/zhD3PUUUflr//6r3POOedk2bJlpR4LAAAAAAA+1lp9gLjpppvy4IMPZubMmbn//vvTr1+/nH/++WloaCj1aAAAAAAA8LFVtmbNmsZSD/FRjB8/PqeeemomTpyYJFm3bl2OOuqoTJ8+Pfvtt1+JpwMAAAAAgI+nVn0FRE1NTZYtW5YRI0Y0HausrMwnP/nJVFdXl3AyAAAAAAD4eGvVAaK2tjZJ0rVr12bHKysrU1NTU4qRAAAAAACAtPIA0aVLlyTZKjasW7duqygBAAAAAADsPK06QHTt2jX9+/fPokWLmo7V1NRk6dKlGTJkSAknAwAAAACAj7dWHSCS5Pjjj8/s2bOzZMmS1NXVZfr06dljjz0yevToUo8GwE72zDPPZMyYMaUeAwAAKMikSZPyox/9qNRjAPAhtS/1AB/Vqaeempqampxxxhmpq6vLqFGjcsUVV6S8vNW3FYCPjUmTJuXZZ5/NP//zP+fYY49tOl5TU5O/+Zu/SV1dXe6666584hOfKN2QAADwMTFp0qT85je/yW677dZ0bPTo0bn22mtLOBUArVGrDxDl5eWZPHlyJk+eXOpRAPgI9tprr9x5553NAsS9996b/v3753e/+13pBgMAgI+hf/zHf8wZZ5xR6jEAaOVafYAAoG34q7/6q/ziF7/IwoULM2LEiCTJnDlzctxxx+XKK69Mkrzyyiu54oor8vLLL6e+vj5Dhw7N17/+9QwdOnS773vvvffm5ptvzrJly/Jnf/ZnOe2003LEEUfslHMCAIC2ZMWKFZk2bVqee+65bNmyJQceeGDOP//89OzZM8nbV04MGTIkK1asyFNPPZUePXrkwgsvTLt27XLllVdm+fLl2X///XPRRRela9euSZIZM2bkoYceyptvvpnu3bvn6KOPzhlnnLHdO1u83wwA7FrcpwiAXUL79u0zfvz43HHHHUmSZ599NuvXr89nP/vZZvu+/OUv55577sm9996bgQMH5oILLsiWLVu2+Z733HNPfvSjH2XKlCmZP39+Lrzwwlx66aV5/vnnd/TpAABAm7Jp06ZMnjw5ffv2ze233545c+akXbt2mTJlSrN9999/f/7+7/8+8+fPzxFHHJF/+Zd/ye23354ZM2Zkzpw5WbJkSW699dam/QMHDsz111+fxx57LN///vdzxx135O677/5IMwCw6xAgANhlHHfccXnkkUdSU1OTO++8M+PHj09ZWVnT+uDBgzNmzJhUVFSkU6dOmTx5cpYtW5bXXnttm+93yy235Ctf+UqGDx+e8vLyjB49OkceeWTuueeenXVKAADQKv3bv/1bPv/5zzf9PPnkk9mwYUO++tWvplOnTuncuXPOOeecLFiwIG+88UbT6w499NCMHDky7dq1y1FHHZVVq1bl5JNPTvfu3dOjR4985jOfyaJFi5r2f+ELX0jfvn1TVlaWESNG5KijjsqCBQu2OdMHnQGAXYdbMAGwy+jbt2/233//zJ49O7/85S/zta99LZs2bWpaf/311zNt2rT89re/TW1tbVOcWL16dQYNGrTV+7322mu56qqrmj0sr76+Pp/+9Kd3/MkAAEAr9g//8A/NngFx4403ZuXKlTn00EOb7evQoUPeeOON9O3bN0nSu3fvprWOHTsmSfr06dPs2Pr165t+f+dKhuXLl6exsTGbNm3Kvvvuu82Zfv/733+gGQDYdQgQAOxSJkyYkK997Wv53Oc+lz59+uT1119vWrv00kvTvXv33HTTTenZs2fWrl2bww47LI2Njdt8r169euXMM8/MUUcdtbPGBwCANql37975xCc+0XTL1CL85je/ydVXX53p06dn5MiRad++fa688spUV1fvtBkA2LHcggmAXcrYsWMzffr0nHfeeVut1dTUpFOnTqmsrExNTU2mT5/+nu910kkn5Sc/+UkWLlyYhoaGbNq0KQsXLmx2yTcAAPD+Pve5z2XTpk350Y9+lJqamiTJqlWrMm/evA/9njU1NSkvL0/Pnj3Trl27PPfcc3nggQd26gwA7FiugABgl1JWVpYxY8Zsc+3rX/96vv/97+fzn/98dt9990yaNClz587d7nt96UtfSo8ePfL9738/f/jDH9KuXbsMHjy42aXkAADA++vSpUtuuOGG/PCHP8xJJ52Umpqa9OzZM2PHjs3hhx/+od5z7Nix+du//ducfvrpaWxszIEHHpijjjpqu1dA7IgZANixytasWbPt+1YAAAAAAAB8SG7BBAAAAAAAFE6AAAAAAAAACidAAAAAAAAAhRMgAAAAAACAwgkQAAAAAABA4QQIAAAAAACgcAIEAADQak2aNCmTJk0q9RgAAMA2tC/1AAAAwK5v9erVufXWW/PEE0/k9ddfz5YtW9KnT5+MGjUqX/ziF3PAAQeUekQAAGAXI0AAAADvaeHChfn617+empqaHHbYYTnuuOPSoUOHvP766/nlL3+Zs846K9dcc00+85nPlHpUAABgFyJAAAAA27Vu3bp84xvfSFlZWWbPnp0999yz2fqZZ56ZRx99NJ06dSrNgAVqbGzMxo0b07Fjx1KPAgAAbYIAAQAAbNedd96ZFStW5F//9V+3ig/v+NznPrfVsZUrV2bGjBl54oknsm7dugwYMCAnnHBCJk6c2LTnmWeeyZlnnpnvfve7ef3113PHHXdkzZo1GTlyZC688ML8+Z//ebP3nDNnTv7t3/4tK1euzODBg3Puueduc55NmzblxhtvzAMPPJDly5enR48eOfTQQ3PWWWc1iwtjxozJcccdlwMOOCA//elPs2TJkvzzP/9zjjnmmA/xTQEAAH9KgAAAALbrl7/8ZSoqKrYZGbZn1apV+cpXvpKGhoZMnDgxPXv2zNNPP52pU6fmrbfeymmnndZs/0033ZTy8vL8/d//fWpqanLTTTflO9/5TmbNmtW0Z+7cubn00kszcuTIfOlLX8qyZctywQUXpLKyMn379m3a19jYmG984xt59tlnc+yxx2bQoEF59dVXc8cdd+TVV1/NtGnTUlZW1rT/+eefzyOPPJK/+7u/S+/evTNw4MCP8G0BAADvJkAAAADbtXjx4gwcODDt2zf/T4fa2tps3ry56fcOHTqkc+fOSZIZM2Zk06ZNufXWW9OzZ88kyYQJE/Kv//qv+dnPfpYTTjghlZWVTa/dtGlTbr755uy2225Jkm7duuXKK6/MK6+8ksGDB2fLli25/vrrM3To0Fx//fVN+/baa69873vfaxYgHnzwwfznf/5nrr/++uy3335Nx0eMGJHvfOc7eeqppzJ27Nhm53fTTTdl6NChRX1lAADA/ygv9QAAAMCuq7a2dpvPd7jkkktyxBFHNP1cfvnlSd6+AuGRRx7JQQcdlLKysqxZs6bp5y//8i+zcePG/Pa3v232XkcffXRTVEiS0aNHJ0mWLl2a5O2HYK9atSrHHntss31HH310s5CRJA8//HD22GOP7LXXXs0++9Of/nTKysryzDPPNNs/cuRI8QEAAHYQV0AAAADb1blz56xfv36r41/5ylcyfvz4JMn555/fdHz16tVZu3ZtfvGLX+QXv/jFNt9z9erVzX7v169fs9/fiQpr165NkixfvjxJtnomRPv27fOJT3yi2bHXXnstS5YsyRFHHLHNz161alWz3wcMGLDNfQAAwEcnQAAAANu15557pqqqKlu2bGl2G6bBgwdn8ODBSZLy8j9eWN3Q0JAkOeKII/K3f/u323zPvfbaq9nv7379R9XQ0JBBgwY1iyLv1qdPn2a/V1RUFPbZAABAcwIEAACwXQcffHD++7//O/Pnz8+RRx75vvt79uyZLl26pL6+PmPGjClkhneukHjttdfyl3/5l03Ht2zZktdffz1DhgxpOvbJT34yixYtyoEHHtjsYdMAAMDO5xkQAADAdh1//PHp06dPrrnmmixevPh997dr1y6f//zn8/jjj6eqqmqr9T+9/dIHMWLEiPTs2TN33XVXswdf33fffVm3bl2zvYcddlhWrVqVO+64Y6v32bRpU2pra1v8+QAAwIfjCggAAGC7unXrlssvvzznnXdeTjnllBx++OH51Kc+lfbt22fFihV59NFHU1dX1+w5DpMnT84zzzyT0047Lccee2z22muvrF27NtXV1XnsscfyxBNPtGiG9u3bZ9KkSbn00ktz5pln5vDDD8+yZctyzz33bPUMhy984Qt55JFHMnXq1Dz77LMZNWpUkmTJkiV5+OGHc+mll2b//ff/6F8MAADwvgQIAADgPX3qU5/Kz3/+89xyyy154oknMn/+/DQ0NKRPnz4ZNWpUvv71r+fAAw9s2t+rV6/MmjUrN9xwQx5//PHccccd6datWwYNGpRzzz33Q81w3HHHpb6+PrNnz8706dMzePDgXH755Zk5c2azfeXl5bnsssvy85//PPfee2/+z//5P6moqMiAAQMyceLE7L333h/puwAAAD64sjVr1jSWeggAAAAAAKBt8QwIAAAAAACgcAIEAAAAAABQOAECAAAAAAAonAABAAAAAAAUToAAAAAAAAAKJ0AAAAAAAACFEyAAAAAAAIDCCRAAAAAAAEDhBAgAAAAAAKBwAgQAAAAAAFC4/w/2UMVCN9UJpQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1728x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# let's plot it\n",
    "plt.figure(figsize=(24, 8)) # figuring the size\n",
    "# makes count plot \n",
    "sns.countplot(x='gender', data=diabetes_data)\n",
    "# title\n",
    "plt.title('Gender', fontname='monospace', fontweight='bold', fontsize=15)\n",
    "# x-label\n",
    "plt.xlabel('Gender');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c6cc2c0e",
   "metadata": {
    "papermill": {
     "duration": 0.04458,
     "end_time": "2021-12-06T23:15:47.980691",
     "exception": false,
     "start_time": "2021-12-06T23:15:47.936111",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Okay, the most distribution is Male..."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c0a1082f",
   "metadata": {
    "papermill": {
     "duration": 0.044412,
     "end_time": "2021-12-06T23:15:48.070512",
     "exception": false,
     "start_time": "2021-12-06T23:15:48.026100",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## **Age distribution**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "6a2f2897",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:48.165653Z",
     "iopub.status.busy": "2021-12-06T23:15:48.164958Z",
     "iopub.status.idle": "2021-12-06T23:15:48.597222Z",
     "shell.execute_reply": "2021-12-06T23:15:48.597975Z",
     "shell.execute_reply.started": "2021-12-06T23:14:45.928062Z"
    },
    "jupyter": {
     "source_hidden": true
    },
    "papermill": {
     "duration": 0.482835,
     "end_time": "2021-12-06T23:15:48.598181",
     "exception": false,
     "start_time": "2021-12-06T23:15:48.115346",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1728x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(24, 8))\n",
    "sns.distplot(diabetes_data['age'], kde=True, color=\"black\");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "110094ad",
   "metadata": {
    "papermill": {
     "duration": 0.046349,
     "end_time": "2021-12-06T23:15:48.692087",
     "exception": false,
     "start_time": "2021-12-06T23:15:48.645738",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Okay, great, now let's move on to Data Preprocessing..."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2d60003b",
   "metadata": {
    "papermill": {
     "duration": 0.046182,
     "end_time": "2021-12-06T23:15:48.784918",
     "exception": false,
     "start_time": "2021-12-06T23:15:48.738736",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Data Preprocessing**\n",
    "\n",
    "In terms of scaling values, neural networks tend to prefer normalization.\n",
    "\n",
    "If you're not sure on which to use, you could try both and see which performs better."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ed71fa78",
   "metadata": {
    "_kg_hide-output": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:48.881624Z",
     "iopub.status.busy": "2021-12-06T23:15:48.880841Z",
     "iopub.status.idle": "2021-12-06T23:15:49.027861Z",
     "shell.execute_reply": "2021-12-06T23:15:49.028403Z",
     "shell.execute_reply.started": "2021-12-06T23:14:46.375681Z"
    },
    "papermill": {
     "duration": 0.197017,
     "end_time": "2021-12-06T23:15:49.028583",
     "exception": false,
     "start_time": "2021-12-06T23:15:48.831566",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Input shape: [17]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "User settings:\n",
      "\n",
      "   KMP_AFFINITY=granularity=fine,verbose,compact,1,0\n",
      "   KMP_BLOCKTIME=0\n",
      "   KMP_DUPLICATE_LIB_OK=True\n",
      "   KMP_INIT_AT_FORK=FALSE\n",
      "   KMP_SETTINGS=1\n",
      "   KMP_WARNINGS=0\n",
      "\n",
      "Effective settings:\n",
      "\n",
      "   KMP_ABORT_DELAY=0\n",
      "   KMP_ADAPTIVE_LOCK_PROPS='1,1024'\n",
      "   KMP_ALIGN_ALLOC=64\n",
      "   KMP_ALL_THREADPRIVATE=128\n",
      "   KMP_ATOMIC_MODE=2\n",
      "   KMP_BLOCKTIME=0\n",
      "   KMP_CPUINFO_FILE: value is not defined\n",
      "   KMP_DETERMINISTIC_REDUCTION=false\n",
      "   KMP_DEVICE_THREAD_LIMIT=2147483647\n",
      "   KMP_DISP_NUM_BUFFERS=7\n",
      "   KMP_DUPLICATE_LIB_OK=true\n",
      "   KMP_ENABLE_TASK_THROTTLING=true\n",
      "   KMP_FORCE_REDUCTION: value is not defined\n",
      "   KMP_FOREIGN_THREADS_THREADPRIVATE=true\n",
      "   KMP_FORKJOIN_BARRIER='2,2'\n",
      "   KMP_FORKJOIN_BARRIER_PATTERN='hyper,hyper'\n",
      "   KMP_GTID_MODE=3\n",
      "   KMP_HANDLE_SIGNALS=false\n",
      "   KMP_HOT_TEAMS_MAX_LEVEL=1\n",
      "   KMP_HOT_TEAMS_MODE=0\n",
      "   KMP_INIT_AT_FORK=true\n",
      "   KMP_LIBRARY=throughput\n",
      "   KMP_LOCK_KIND=queuing\n",
      "   KMP_MALLOC_POOL_INCR=1M\n",
      "   KMP_NUM_LOCKS_IN_BLOCK=1\n",
      "   KMP_PLAIN_BARRIER='2,2'\n",
      "   KMP_PLAIN_BARRIER_PATTERN='hyper,hyper'\n",
      "   KMP_REDUCTION_BARRIER='1,1'\n",
      "   KMP_REDUCTION_BARRIER_PATTERN='hyper,hyper'\n",
      "   KMP_SCHEDULE='static,balanced;guided,iterative'\n",
      "   KMP_SETTINGS=true\n",
      "   KMP_SPIN_BACKOFF_PARAMS='4096,100'\n",
      "   KMP_STACKOFFSET=64\n",
      "   KMP_STACKPAD=0\n",
      "   KMP_STACKSIZE=8M\n",
      "   KMP_STORAGE_MAP=false\n",
      "   KMP_TASKING=2\n",
      "   KMP_TASKLOOP_MIN_TASKS=0\n",
      "   KMP_TASK_STEALING_CONSTRAINT=1\n",
      "   KMP_TEAMS_THREAD_LIMIT=4\n",
      "   KMP_TOPOLOGY_METHOD=all\n",
      "   KMP_USE_YIELD=1\n",
      "   KMP_VERSION=false\n",
      "   KMP_WARNINGS=false\n",
      "   OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}'\n",
      "   OMP_ALLOCATOR=omp_default_mem_alloc\n",
      "   OMP_CANCELLATION=false\n",
      "   OMP_DEFAULT_DEVICE=0\n",
      "   OMP_DISPLAY_AFFINITY=false\n",
      "   OMP_DISPLAY_ENV=false\n",
      "   OMP_DYNAMIC=false\n",
      "   OMP_MAX_ACTIVE_LEVELS=1\n",
      "   OMP_MAX_TASK_PRIORITY=0\n",
      "   OMP_NESTED: deprecated; max-active-levels-var=1\n",
      "   OMP_NUM_THREADS: value is not defined\n",
      "   OMP_PLACES: value is not defined\n",
      "   OMP_PROC_BIND='intel'\n",
      "   OMP_SCHEDULE='static'\n",
      "   OMP_STACKSIZE=8M\n",
      "   OMP_TARGET_OFFLOAD=DEFAULT\n",
      "   OMP_THREAD_LIMIT=2147483647\n",
      "   OMP_WAIT_POLICY=PASSIVE\n",
      "   KMP_AFFINITY='verbose,warnings,respect,granularity=fine,compact,1,0'\n",
      "\n",
      "2021-12-06 23:15:49.002015: I tensorflow/core/common_runtime/process_util.cc:146] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.\n"
     ]
    }
   ],
   "source": [
    "from sklearn.compose import make_column_transformer\n",
    "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "def preprocessing_data(data):\n",
    "    \"\"\"Returns Data that have been preprocessed and split\"\"\"\n",
    "    # Create a columns transformer\n",
    "    features_num = [\"polyuria\", \"age\", \"polydipsia\", \"sudden_weight_loss\", \"weakness\", \\\n",
    "                    \"polyphagia\", \"genital_thrush\", \"visual_blurring\", \"itching\", \"irritability\", \\\n",
    "                    \"delayed_healing\", \"partial_paresis\", \"muscle_stiffness\", \"alopecia\", \"obesity\"]\n",
    "    features_cat = ['gender']\n",
    "\n",
    "    preprocessor = make_column_transformer(\n",
    "        (StandardScaler(), features_num),\n",
    "        (OneHotEncoder(), features_cat),\n",
    "    )\n",
    "    \n",
    "    # Create X & y (features and label)\n",
    "    X = data.drop(columns=[\"class\"])\n",
    "    y = data[\"class\"]\n",
    "    \n",
    "    # Build our train and test sets\n",
    "    X_train, X_test, y_train, y_test = train_test_split(\n",
    "        X, y, test_size=0.2, random_state=42\n",
    "    )\n",
    "    \n",
    "    # Fit the columns transformer to our training data\n",
    "    preprocessor.fit(X_train)\n",
    "    \n",
    "    # Transform training and test data with normalization (MinMaxScaler) and encoder (OneHotEncoder, LabelEncoder)\n",
    "    X_train_normal = preprocessor.transform(X_train)\n",
    "    X_test_normal = preprocessor.transform(X_test)\n",
    "    \n",
    "    # X_train and X_test (features)\n",
    "    X_train, X_test = tf.constant(X_train_normal), tf.constant(X_test_normal)\n",
    "    \n",
    "    # y_train and y_test (label)\n",
    "    y_train, y_test = tf.constant(y_train), tf.constant(y_test)\n",
    "    \n",
    "    return X_train, X_test, y_train, y_test\n",
    "\n",
    "# Call the function\n",
    "X_train, X_test, y_train, y_test = preprocessing_data(diabetes_data)\n",
    "input_shape = [X_train.shape[1]]\n",
    "print(\"Input shape: {}\".format(input_shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "333d2846",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:49.129865Z",
     "iopub.status.busy": "2021-12-06T23:15:49.127959Z",
     "iopub.status.idle": "2021-12-06T23:15:49.187620Z",
     "shell.execute_reply": "2021-12-06T23:15:49.188133Z",
     "shell.execute_reply.started": "2021-12-06T23:14:46.511883Z"
    },
    "papermill": {
     "duration": 0.111458,
     "end_time": "2021-12-06T23:15:49.188305",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.076847",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(TensorShape([416, 17]), TensorShape([104, 17]), 2, 2)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking the shape and dimension of rows and columns (features)\n",
    "X_train.shape, X_test.shape, X_train.ndim, X_test.ndim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "c42f3846",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:49.289433Z",
     "iopub.status.busy": "2021-12-06T23:15:49.288457Z",
     "iopub.status.idle": "2021-12-06T23:15:49.348559Z",
     "shell.execute_reply": "2021-12-06T23:15:49.347949Z",
     "shell.execute_reply.started": "2021-12-06T23:14:46.573733Z"
    },
    "papermill": {
     "duration": 0.111801,
     "end_time": "2021-12-06T23:15:49.348706",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.236905",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(TensorShape([416]), TensorShape([104]), 1, 1)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking the shape and dimension of rows and columns (label)\n",
    "y_train.shape, y_test.shape, y_train.ndim, y_test.ndim"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "b9b14438",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:49.450151Z",
     "iopub.status.busy": "2021-12-06T23:15:49.449475Z",
     "iopub.status.idle": "2021-12-06T23:15:49.506427Z",
     "shell.execute_reply": "2021-12-06T23:15:49.506870Z",
     "shell.execute_reply.started": "2021-12-06T23:14:46.636012Z"
    },
    "papermill": {
     "duration": 0.109658,
     "end_time": "2021-12-06T23:15:49.507055",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.397397",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(tf.float64, tf.float64, tf.int64, tf.int64)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking the type (features and label)\n",
    "X_train.dtype, X_test.dtype, y_train.dtype, y_test.dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "bf274872",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:49.609150Z",
     "iopub.status.busy": "2021-12-06T23:15:49.607763Z",
     "iopub.status.idle": "2021-12-06T23:15:49.668791Z",
     "shell.execute_reply": "2021-12-06T23:15:49.668284Z",
     "shell.execute_reply.started": "2021-12-06T23:14:46.698322Z"
    },
    "papermill": {
     "duration": 0.113575,
     "end_time": "2021-12-06T23:15:49.668931",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.555356",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(416, 104, 416, 104)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking the len (feature and label)\n",
    "len(X_train), len(X_test), len(y_train), len(y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "97a99fcf",
   "metadata": {
    "papermill": {
     "duration": 0.048115,
     "end_time": "2021-12-06T23:15:49.765599",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.717484",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Okay, Let's build the Model**\n",
    "\n",
    "## Steps in modelling\n",
    "\n",
    "Now we know what data we have as well as the input and output shapes, let's see how we'd build a neural network to model it.\n",
    "\n",
    "In TensorFlow, there are typically 3 fundamental steps to creating and training a model.\n",
    "\n",
    "1. **Creating a model** - piece together the layers of a neural network yourself (using the [functional](https://www.tensorflow.org/guide/keras/functional) or [sequential API](https://www.tensorflow.org/api_docs/python/tf/keras/Sequential)) or import a previously built model (known as transfer learning).\n",
    "2. **Compiling a model** - defining how a model's performance should be measured (loss/metrics) as well as defining how it should improve (optimizer). \n",
    "3. **Fitting a model** - letting the model try to find patterns in the data (how does `X` get to `y`). \n",
    "\n",
    "Let's see these in action using the Sequential API to build a model for our regression data. And then we'll step through each."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "813c19a0",
   "metadata": {
    "papermill": {
     "duration": 0.047958,
     "end_time": "2021-12-06T23:15:49.861893",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.813935",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## **Typical architecture of a classification neural network**\n",
    "\n",
    "The word *typical* is on purpose.\n",
    "\n",
    "Because the architecture of a classification neural network can widely vary depending on the problem you're working on.\n",
    "\n",
    "However, there are some fundamentals all deep neural networks contain:\n",
    "* An input layer.\n",
    "* Some hidden layers.\n",
    "* An output layer.\n",
    "\n",
    "Much of the rest is up to the data analyst creating the model.\n",
    "\n",
    "The following are some standard values you'll often use in your classification neural networks.\n",
    "\n",
    "| **Hyperparameter** | **Binary Classification** | **Multiclass classification** |\n",
    "| --- | --- | --- |\n",
    "| Input layer shape | Same as number of features (e.g. 5 for age, sex, height, weight, smoking status in heart disease prediction) | Same as binary classification |\n",
    "| Hidden layer(s) | Problem specific, minimum = 1, maximum = unlimited | Same as binary classification |\n",
    "| Neurons per hidden layer | Problem specific, generally 10 to 100 | Same as binary classification |\n",
    "| Output layer shape | 1 (one class or the other) | 1 per class (e.g. 3 for food, person or dog photo) |\n",
    "| Hidden activation | Usually [ReLU](https://www.kaggle.com/dansbecker/rectified-linear-units-relu-in-deep-learning) (rectified linear unit) | Same as binary classification |\n",
    "| Output activation | [Sigmoid](https://en.wikipedia.org/wiki/Sigmoid_function) | [Softmax](https://en.wikipedia.org/wiki/Softmax_function) |\n",
    "| Loss function | [Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy#Cross-entropy_loss_function_and_logistic_regression) ([`tf.keras.losses.BinaryCrossentropy`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/BinaryCrossentropy) in TensorFlow) | Cross entropy ([`tf.keras.losses.CategoricalCrossentropy`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/CategoricalCrossentropy) in TensorFlow) |\n",
    "| Optimizer | [SGD](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/SGD) (stochastic gradient descent), [Adam](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/Adam) | Same as binary classification |\n",
    "\n",
    "***Table 1:*** *Typical architecture of a classification network.* ***Source:*** *Adapted from page 295 of [Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow Book by Aurélien Géron](https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/)*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "a171671b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:15:49.966055Z",
     "iopub.status.busy": "2021-12-06T23:15:49.964977Z",
     "iopub.status.idle": "2021-12-06T23:16:02.394598Z",
     "shell.execute_reply": "2021-12-06T23:16:02.394012Z",
     "shell.execute_reply.started": "2021-12-06T23:14:46.760656Z"
    },
    "papermill": {
     "duration": 12.482302,
     "end_time": "2021-12-06T23:16:02.394746",
     "exception": false,
     "start_time": "2021-12-06T23:15:49.912444",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2021-12-06 23:15:51.346492: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/100\n",
      "13/13 [==============================] - 1s 21ms/step - loss: 0.5467 - accuracy: 0.7812 - val_loss: 0.3886 - val_accuracy: 0.8558\n",
      "Epoch 2/100\n",
      "13/13 [==============================] - 0s 8ms/step - loss: 0.3505 - accuracy: 0.9038 - val_loss: 0.2973 - val_accuracy: 0.8846\n",
      "Epoch 3/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.2860 - accuracy: 0.8966 - val_loss: 0.2610 - val_accuracy: 0.8846\n",
      "Epoch 4/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.2205 - accuracy: 0.9255 - val_loss: 0.2282 - val_accuracy: 0.8942\n",
      "Epoch 5/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.2143 - accuracy: 0.9279 - val_loss: 0.2101 - val_accuracy: 0.9038\n",
      "Epoch 6/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1690 - accuracy: 0.9399 - val_loss: 0.1950 - val_accuracy: 0.9038\n",
      "Epoch 7/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1567 - accuracy: 0.9471 - val_loss: 0.1878 - val_accuracy: 0.9038\n",
      "Epoch 8/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1382 - accuracy: 0.9519 - val_loss: 0.1682 - val_accuracy: 0.9327\n",
      "Epoch 9/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1392 - accuracy: 0.9399 - val_loss: 0.1491 - val_accuracy: 0.9327\n",
      "Epoch 10/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1218 - accuracy: 0.9519 - val_loss: 0.1376 - val_accuracy: 0.9327\n",
      "Epoch 11/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1025 - accuracy: 0.9615 - val_loss: 0.1307 - val_accuracy: 0.9327\n",
      "Epoch 12/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.1069 - accuracy: 0.9519 - val_loss: 0.1230 - val_accuracy: 0.9327\n",
      "Epoch 13/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0946 - accuracy: 0.9639 - val_loss: 0.1039 - val_accuracy: 0.9519\n",
      "Epoch 14/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0856 - accuracy: 0.9688 - val_loss: 0.1067 - val_accuracy: 0.9519\n",
      "Epoch 15/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0955 - accuracy: 0.9591 - val_loss: 0.0962 - val_accuracy: 0.9519\n",
      "Epoch 16/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0624 - accuracy: 0.9760 - val_loss: 0.0927 - val_accuracy: 0.9615\n",
      "Epoch 17/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0754 - accuracy: 0.9688 - val_loss: 0.0869 - val_accuracy: 0.9712\n",
      "Epoch 18/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0598 - accuracy: 0.9832 - val_loss: 0.0894 - val_accuracy: 0.9519\n",
      "Epoch 19/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0659 - accuracy: 0.9663 - val_loss: 0.0972 - val_accuracy: 0.9519\n",
      "Epoch 20/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0595 - accuracy: 0.9856 - val_loss: 0.0894 - val_accuracy: 0.9712\n",
      "Epoch 21/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0625 - accuracy: 0.9856 - val_loss: 0.0902 - val_accuracy: 0.9519\n",
      "Epoch 22/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0602 - accuracy: 0.9712 - val_loss: 0.0890 - val_accuracy: 0.9519\n",
      "Epoch 23/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0464 - accuracy: 0.9784 - val_loss: 0.0823 - val_accuracy: 0.9712\n",
      "Epoch 24/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0395 - accuracy: 0.9832 - val_loss: 0.0863 - val_accuracy: 0.9519\n",
      "Epoch 25/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0433 - accuracy: 0.9808 - val_loss: 0.0811 - val_accuracy: 0.9519\n",
      "Epoch 26/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0527 - accuracy: 0.9784 - val_loss: 0.0752 - val_accuracy: 0.9615\n",
      "Epoch 27/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0380 - accuracy: 0.9880 - val_loss: 0.0629 - val_accuracy: 0.9712\n",
      "Epoch 28/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0475 - accuracy: 0.9808 - val_loss: 0.0660 - val_accuracy: 0.9615\n",
      "Epoch 29/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0291 - accuracy: 0.9928 - val_loss: 0.0682 - val_accuracy: 0.9615\n",
      "Epoch 30/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0379 - accuracy: 0.9880 - val_loss: 0.0652 - val_accuracy: 0.9615\n",
      "Epoch 31/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0400 - accuracy: 0.9880 - val_loss: 0.0627 - val_accuracy: 0.9615\n",
      "Epoch 32/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0282 - accuracy: 0.9928 - val_loss: 0.0595 - val_accuracy: 0.9615\n",
      "Epoch 33/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0299 - accuracy: 0.9880 - val_loss: 0.0596 - val_accuracy: 0.9615\n",
      "Epoch 34/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0308 - accuracy: 0.9928 - val_loss: 0.0705 - val_accuracy: 0.9615\n",
      "Epoch 35/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0241 - accuracy: 0.9976 - val_loss: 0.0621 - val_accuracy: 0.9615\n",
      "Epoch 36/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0359 - accuracy: 0.9832 - val_loss: 0.0465 - val_accuracy: 0.9808\n",
      "Epoch 37/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0247 - accuracy: 0.9928 - val_loss: 0.0564 - val_accuracy: 0.9712\n",
      "Epoch 38/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0319 - accuracy: 0.9856 - val_loss: 0.0534 - val_accuracy: 0.9712\n",
      "Epoch 39/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0181 - accuracy: 0.9976 - val_loss: 0.0556 - val_accuracy: 0.9712\n",
      "Epoch 40/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0201 - accuracy: 0.9904 - val_loss: 0.0697 - val_accuracy: 0.9712\n",
      "Epoch 41/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0248 - accuracy: 0.9904 - val_loss: 0.0726 - val_accuracy: 0.9615\n",
      "Epoch 42/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0215 - accuracy: 0.9928 - val_loss: 0.0532 - val_accuracy: 0.9712\n",
      "Epoch 43/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0239 - accuracy: 0.9928 - val_loss: 0.0519 - val_accuracy: 0.9712\n",
      "Epoch 44/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0195 - accuracy: 0.9928 - val_loss: 0.0714 - val_accuracy: 0.9615\n",
      "Epoch 45/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0231 - accuracy: 0.9904 - val_loss: 0.0606 - val_accuracy: 0.9615\n",
      "Epoch 46/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0201 - accuracy: 0.9904 - val_loss: 0.0524 - val_accuracy: 0.9808\n",
      "Epoch 47/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0190 - accuracy: 0.9928 - val_loss: 0.0439 - val_accuracy: 0.9808\n",
      "Epoch 48/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0257 - accuracy: 0.9904 - val_loss: 0.0474 - val_accuracy: 0.9615\n",
      "Epoch 49/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0270 - accuracy: 0.9928 - val_loss: 0.0485 - val_accuracy: 0.9712\n",
      "Epoch 50/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0258 - accuracy: 0.9880 - val_loss: 0.0282 - val_accuracy: 0.9808\n",
      "Epoch 51/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0272 - accuracy: 0.9880 - val_loss: 0.0316 - val_accuracy: 0.9904\n",
      "Epoch 52/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0229 - accuracy: 0.9904 - val_loss: 0.0370 - val_accuracy: 0.9808\n",
      "Epoch 53/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0267 - accuracy: 0.9904 - val_loss: 0.0394 - val_accuracy: 0.9712\n",
      "Epoch 54/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0170 - accuracy: 0.9976 - val_loss: 0.0428 - val_accuracy: 0.9808\n",
      "Epoch 55/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0283 - accuracy: 0.9904 - val_loss: 0.0361 - val_accuracy: 0.9808\n",
      "Epoch 56/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0174 - accuracy: 0.9928 - val_loss: 0.0316 - val_accuracy: 0.9808\n",
      "Epoch 57/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0233 - accuracy: 0.9928 - val_loss: 0.0378 - val_accuracy: 0.9808\n",
      "Epoch 58/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0223 - accuracy: 0.9904 - val_loss: 0.0376 - val_accuracy: 0.9712\n",
      "Epoch 59/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0224 - accuracy: 0.9904 - val_loss: 0.0429 - val_accuracy: 0.9808\n",
      "Epoch 60/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0223 - accuracy: 0.9880 - val_loss: 0.0462 - val_accuracy: 0.9808\n",
      "Epoch 61/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0251 - accuracy: 0.9904 - val_loss: 0.0438 - val_accuracy: 0.9712\n",
      "Epoch 62/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0168 - accuracy: 0.9928 - val_loss: 0.0442 - val_accuracy: 0.9712\n",
      "Epoch 63/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0182 - accuracy: 0.9904 - val_loss: 0.0459 - val_accuracy: 0.9712\n",
      "Epoch 64/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0165 - accuracy: 0.9952 - val_loss: 0.0433 - val_accuracy: 0.9712\n",
      "Epoch 65/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0190 - accuracy: 0.9880 - val_loss: 0.0397 - val_accuracy: 0.9712\n",
      "Epoch 66/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0163 - accuracy: 0.9952 - val_loss: 0.0408 - val_accuracy: 0.9712\n",
      "Epoch 67/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0222 - accuracy: 0.9832 - val_loss: 0.0411 - val_accuracy: 0.9712\n",
      "Epoch 68/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0209 - accuracy: 0.9928 - val_loss: 0.0405 - val_accuracy: 0.9712\n",
      "Epoch 69/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0146 - accuracy: 0.9928 - val_loss: 0.0393 - val_accuracy: 0.9712\n",
      "Epoch 70/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0193 - accuracy: 0.9928 - val_loss: 0.0398 - val_accuracy: 0.9712\n",
      "Epoch 71/100\n",
      "13/13 [==============================] - 0s 8ms/step - loss: 0.0124 - accuracy: 0.9976 - val_loss: 0.0403 - val_accuracy: 0.9712\n",
      "Epoch 72/100\n",
      "13/13 [==============================] - 0s 8ms/step - loss: 0.0133 - accuracy: 0.9928 - val_loss: 0.0407 - val_accuracy: 0.9712\n",
      "Epoch 73/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0232 - accuracy: 0.9904 - val_loss: 0.0685 - val_accuracy: 0.9615\n",
      "Epoch 74/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0281 - accuracy: 0.9928 - val_loss: 0.0668 - val_accuracy: 0.9615\n",
      "Epoch 75/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0162 - accuracy: 0.9928 - val_loss: 0.0499 - val_accuracy: 0.9712\n",
      "Epoch 76/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0184 - accuracy: 0.9952 - val_loss: 0.0271 - val_accuracy: 0.9808\n",
      "Epoch 77/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0117 - accuracy: 0.9952 - val_loss: 0.0279 - val_accuracy: 0.9808\n",
      "Epoch 78/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0095 - accuracy: 0.9952 - val_loss: 0.0297 - val_accuracy: 0.9808\n",
      "Epoch 79/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0199 - accuracy: 0.9928 - val_loss: 0.0324 - val_accuracy: 0.9904\n",
      "Epoch 80/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0152 - accuracy: 0.9952 - val_loss: 0.0310 - val_accuracy: 0.9808\n",
      "Epoch 81/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0169 - accuracy: 0.9928 - val_loss: 0.0272 - val_accuracy: 0.9808\n",
      "Epoch 82/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0133 - accuracy: 0.9952 - val_loss: 0.0271 - val_accuracy: 0.9808\n",
      "Epoch 83/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0100 - accuracy: 0.9976 - val_loss: 0.0305 - val_accuracy: 0.9808\n",
      "Epoch 84/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0137 - accuracy: 0.9952 - val_loss: 0.0325 - val_accuracy: 0.9808\n",
      "Epoch 85/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0164 - accuracy: 0.9952 - val_loss: 0.0290 - val_accuracy: 0.9808\n",
      "Epoch 86/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0149 - accuracy: 0.9952 - val_loss: 0.0292 - val_accuracy: 0.9904\n",
      "Epoch 87/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0160 - accuracy: 0.9928 - val_loss: 0.0287 - val_accuracy: 0.9808\n",
      "Epoch 88/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0136 - accuracy: 0.9952 - val_loss: 0.0290 - val_accuracy: 0.9808\n",
      "Epoch 89/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0155 - accuracy: 0.9928 - val_loss: 0.0315 - val_accuracy: 0.9808\n",
      "Epoch 90/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0141 - accuracy: 0.9928 - val_loss: 0.0311 - val_accuracy: 0.9712\n",
      "Epoch 91/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0138 - accuracy: 0.9952 - val_loss: 0.0278 - val_accuracy: 0.9808\n",
      "Epoch 92/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0134 - accuracy: 0.9928 - val_loss: 0.0240 - val_accuracy: 0.9808\n",
      "Epoch 93/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0122 - accuracy: 0.9952 - val_loss: 0.0261 - val_accuracy: 0.9904\n",
      "Epoch 94/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0169 - accuracy: 0.9952 - val_loss: 0.0271 - val_accuracy: 0.9904\n",
      "Epoch 95/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0167 - accuracy: 0.9928 - val_loss: 0.0241 - val_accuracy: 0.9808\n",
      "Epoch 96/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0144 - accuracy: 0.9952 - val_loss: 0.0205 - val_accuracy: 0.9904\n",
      "Epoch 97/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0152 - accuracy: 0.9928 - val_loss: 0.0256 - val_accuracy: 0.9904\n",
      "Epoch 98/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0106 - accuracy: 0.9952 - val_loss: 0.0269 - val_accuracy: 0.9904\n",
      "Epoch 99/100\n",
      "13/13 [==============================] - 0s 6ms/step - loss: 0.0101 - accuracy: 0.9976 - val_loss: 0.0280 - val_accuracy: 0.9712\n",
      "Epoch 100/100\n",
      "13/13 [==============================] - 0s 5ms/step - loss: 0.0207 - accuracy: 0.9904 - val_loss: 0.0272 - val_accuracy: 0.9712\n"
     ]
    }
   ],
   "source": [
    "# Set the random seed\n",
    "tf.random.set_seed(42)\n",
    "\n",
    "def model():\n",
    "    # Create the model\n",
    "    model = tf.keras.Sequential([\n",
    "        tf.keras.layers.Dense(128, activation=\"relu\", input_shape=input_shape, name=\"input_1\"),\n",
    "        tf.keras.layers.Dropout(rate=0.3),\n",
    "        tf.keras.layers.Dense(128, activation=\"relu\", name=\"input_2\"),\n",
    "        tf.keras.layers.Dropout(rate=0.3),\n",
    "        tf.keras.layers.Dense(1, activation=\"sigmoid\", name=\"output_layer\")\n",
    "    ], name=\"our_model\")\n",
    "\n",
    "    # Compile the model\n",
    "    model.compile(loss=tf.keras.losses.BinaryCrossentropy(), # binary since we are working with 2 clases (0 & 1)\n",
    "                    optimizer=tf.keras.optimizers.Adam(),\n",
    "                    metrics=['accuracy'])\n",
    "    \n",
    "    return model\n",
    "\n",
    "model = model()\n",
    "\n",
    "# Fit the model\n",
    "history = model.fit(\n",
    "    X_train, y_train,\n",
    "    validation_data=(X_test, y_test),\n",
    "    batch_size=32,\n",
    "    epochs=100,\n",
    "    verbose=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2dfb7aa5",
   "metadata": {
    "papermill": {
     "duration": 0.111952,
     "end_time": "2021-12-06T23:16:02.621538",
     "exception": false,
     "start_time": "2021-12-06T23:16:02.509586",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Looks like our model is good! let's see its Architecture..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "4acdf5ed",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:16:02.848087Z",
     "iopub.status.busy": "2021-12-06T23:16:02.847378Z",
     "iopub.status.idle": "2021-12-06T23:16:02.914670Z",
     "shell.execute_reply": "2021-12-06T23:16:02.915678Z",
     "shell.execute_reply.started": "2021-12-06T23:14:56.368663Z"
    },
    "papermill": {
     "duration": 0.182894,
     "end_time": "2021-12-06T23:16:02.915946",
     "exception": false,
     "start_time": "2021-12-06T23:16:02.733052",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"our_model\"\n",
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "input_1 (Dense)              (None, 128)               2304      \n",
      "_________________________________________________________________\n",
      "dropout (Dropout)            (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "input_2 (Dense)              (None, 128)               16512     \n",
      "_________________________________________________________________\n",
      "dropout_1 (Dropout)          (None, 128)               0         \n",
      "_________________________________________________________________\n",
      "output_layer (Dense)         (None, 1)                 129       \n",
      "=================================================================\n",
      "Total params: 18,945\n",
      "Trainable params: 18,945\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c026591b",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:16:03.147661Z",
     "iopub.status.busy": "2021-12-06T23:16:03.146995Z",
     "iopub.status.idle": "2021-12-06T23:16:04.083821Z",
     "shell.execute_reply": "2021-12-06T23:16:04.084447Z",
     "shell.execute_reply.started": "2021-12-06T23:14:56.438887Z"
    },
    "papermill": {
     "duration": 1.052946,
     "end_time": "2021-12-06T23:16:04.084626",
     "exception": false,
     "start_time": "2021-12-06T23:16:03.031680",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from tensorflow.keras.utils import plot_model\n",
    "\n",
    "plot_model(model=model, show_shapes=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "14d8bdf2",
   "metadata": {
    "papermill": {
     "duration": 0.112399,
     "end_time": "2021-12-06T23:16:04.310813",
     "exception": false,
     "start_time": "2021-12-06T23:16:04.198414",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Let's Evaluate it**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7ecca79e",
   "metadata": {
    "papermill": {
     "duration": 0.11302,
     "end_time": "2021-12-06T23:16:04.536930",
     "exception": false,
     "start_time": "2021-12-06T23:16:04.423910",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## **History Curves**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "4706950a",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:16:04.764846Z",
     "iopub.status.busy": "2021-12-06T23:16:04.764231Z",
     "iopub.status.idle": "2021-12-06T23:16:05.242421Z",
     "shell.execute_reply": "2021-12-06T23:16:05.242925Z",
     "shell.execute_reply.started": "2021-12-06T23:14:57.328063Z"
    },
    "papermill": {
     "duration": 0.593779,
     "end_time": "2021-12-06T23:16:05.243109",
     "exception": false,
     "start_time": "2021-12-06T23:16:04.649330",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABoMAAAIGCAYAAACfyvZnAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8/fFQqAAAACXBIWXMAAAsTAAALEwEAmpwYAADl3ElEQVR4nOzdd5xcV33///e9U3a2F+1qm/qupFWvliwb2VZxAVeMwQajEEoc8yPGtC/BSUjAhC8QTIAQsA2Ov0lswKYY4y4XueGi3stq1aXt0vY65d7fH7Ma7WzvszN6PR8PP6w5c+fOmXZ35r7P+Ryjrq7OFgAAAAAAAAAAAGKSGekOAAAAAAAAAAAAYPQQBgEAAAAAAAAAAMQwwiAAAAAAAAAAAIAYRhgEAAAAAAAAAAAQwwiDAAAAAAAAAAAAYhhhEAAAAAAAAAAAQAwjDAIAAAAwLDfffLNuvvnmSHcDAAAAANALZ6Q7AAAAACDyVqxYIUnasmVLr9vcfffd2rFjhx588EEtW7ZsRO87NzdXf/7zn0dsn2OtsrJSf/zjH7V582aVlpaqublZSUlJKiws1Ac+8AFdf/31SktLi3Q3AQAAAFykCIMAAAAADMvPf/7zSHchov785z/rhz/8obxerwoLC7V+/XqlpKSooaFBe/fu1U9/+lM98sgjeuGFFxQfHx/p7gIAAAC4CBEGAQAAABiWSZMmRboLEfPSSy/pu9/9rpKTk/W9731Pq1ev7rbN/v379aMf/Uh+vz8CPQQAAAAA1gwCAAAAMEw9rRnk8/n05JNP6q/+6q+0fv16rV69WjfeeKPuvfdevf7665Kk7du3h8rTlZeXa8WKFaH/vv3tb4ftb/v27fryl7+s9evX6/LLL9ctt9yif//3f1dtbW23/nz729/WihUrtH37dr3wwgv61Kc+pSuuuEJ33nmn3nvvPa1YsUL3339/j48lEAjohhtu0JVXXqmmpqY+H3dzc7MeeOABSdJ3vvOdHoMgSZo3b55++ctfKjExUZJUVlbW42Ps2v+ysrJQ2/nb3H333aqurtZ3vvMdffCDH9Sll16qN954Qx/72Me0atUqnTt3rsd9/u53v9OKFSv0y1/+Mqz97Nmz+vd//3d95CMf0Qc+8AGtW7dO99xzT4/lAgfymgIAAAAYn5gZBAAAAGDEffvb39bLL7+s6dOn67rrrlN8fLyqq6t14MABvf7661qzZo1yc3P1uc99To888oiSkpJ0xx13hG4/a9as0L+ffvppfe9731NcXJzWrVunzMxM7dmzR0888YTeeOMN/epXv1J2dna3Pjz++OPatm2bVq9erUsuuUQ+n0+XXnqpJk2apFdeeUVf/vKXlZycHHabv/zlL6qqqtJNN92kpKSkPh/jpk2b1NDQoPnz5+uyyy7rc1unc2R+etXX1+uzn/2skpKStG7dOtm2rZSUFF1//fX6+c9/rpdeekl33nlnt9s9//zzMgxD119/fajtyJEj+ru/+zvV1tZq5cqVuuKKK1RfX68333xT99xzj/7xH/9RN910U2j7gbymAAAAAMYnwiAAAAAAIV1njnRWXl4+oH00NTXplVdeUVFRkR599NFuQUhdXZ0kKS8vT3fddZceeeQRJScn66677uq2r8rKSv3whz+Ux+PRo48+qoKCgtB1Dz30kB599FF9//vf149//ONut92+fbv+67/+KyxYkqRbb71V//Ef/6EXXnhBt99+e9h1Tz31VGib/uzatUuSdMkll/S77Ug5evSoPvjBD+qb3/xm2PM6efJkPfTQQ3r++ee7hUHHjh3TwYMHtXTpUuXn50sKzoD6xje+oaamJj344INaunRpaPuzZ8/qr//6r/XDH/5QH/jAB5SRkTHg1xQAAADA+EQYBAAAACDkkUceGZH92LYtl8slh8PR7bq0tLQB7+f555+Xz+fT7bffHhYESdKnP/1pPfvss3rnnXdUXV2trKyssOtvueWWbkGQJN144416+OGH9dRTT4WFQWVlZdq8ebOKioo0d+7cfvt2viTbxIkTB/x4hsvlcunee+/tFsZkZWVpxYoVeu+991RcXKzZs2eHrnvuueckSTfccEOo7d1339WpU6f08Y9/PCwIkqTMzExt2LBBP/rRj7Rp0ybddtttkkbuNQUAAAAw9giDAAAAAIT0tFbMeXfffbd27NjR7z6SkpK0evVqvf322/rEJz6hNWvWaNGiRVqwYIESEhIG1Z/i4mJJPc++iYuL06JFi/Tqq6+quLi4Wxg0b968HveZmpqq9evX6/nnn9euXbu0ePFiScFydJZlDWhWUKTk5uYqIyOjx+tuuOEGvffee3r++edDYVAgENBLL72k+Ph4rV27NrTt7t27JQVnXvU0G+z06dOSpOPHj0sa2dcUAAAAwNgjDAIAAAAw4r773e/q8ccf18aNG0OzjZxOp1avXq17771XeXl5A9pPU1OTJGnChAk9Xp+ZmRm2XWe93UaSbrvtNj3//PN66qmntHjxYvn9fj377LNKTEzUtddeO6C+nd9/VVXVgLYfCX09piuvvFIpKSnauHGjvvjFL8rpdGrLli06e/asrr/++rDQpr6+XlJw3aNNmzb1us/W1tbQv0fqNQUAAAAw9giDAAAAAIw4j8ejz33uc/rc5z6n6upq7dq1Sxs3btTrr7+uY8eO6be//W23Umc9SUpKknShJFtXZ8+elSQlJiZ2u84wjF73O2/ePBUVFWnTpk36yle+ou3bt+vcuXP66Ec/qvj4+IE8RC1evFjPPvustm7dqs9//vMDuo0kmaYpKThrpyeNjY293ravx+R2u3X11Vfrj3/8o9555x1deeWVPZaIky48rz/4wQ+0Zs2aAfV7pF5TAAAAAGPPjHQHAAAAAMS2rKwsXX311XrggQe0YMECnTx5UseOHQtdb5pmr8HI+XJn27Zt63ad1+vVnj17JElFRUWD7tdtt90mr9er559/Xn/6058kaVAl4tauXauUlBTt27dP7733Xp/b+v1+WZYlSUpOTpYULNHW03aHDx8ecB+6Oh/6PP/882pqatJbb72lvLy8busCLViwQJK0c+fOId1Pf68pAAAAgPGFMAgAAADAiKqtrVVJSUm3dq/XGyrn5vF4Qu2pqamqq6tTW1tbt9t88IMflMvl0h//+EedOHEi7Lr//u//VlVVlS6//PJu6wUNxDXXXKOUlBT95je/0datW7Vo0SIVFBQM+PaJiYn62te+Jkn65je/qXfeeafH7Q4dOqS77rpLzc3NodtNnz5de/bs0ZEjR0Lb2batRx55RBUVFYN+LOfNmzdP06dP1zvvvKPf//73am9v14c+9KFuM4quuOIKTZ48WX/605/01ltv9biv4uJi1dXVSRr8awoAAABgfGEOPwAAAIARVV1drU9+8pMqKChQYWGhsrOz1draqvfff1+nT5/W2rVrNWXKlND2K1as0MaNG3XvvfdqyZIlcrlcmjVrllavXq3c3Fx99atf1Q9+8AN96lOf0vr16zVhwgTt2bNHO3bs0MSJE/X3f//3Q+qnx+PR9ddfr9/+9reSBjcr6LzrrrtObW1teuCBB/TlL39ZhYWFWrx4sZKTk9XQ0KD9+/fr0KFDSk5ODiuhtmHDBt1///36m7/5G61fv17x8fHavXu3KisrtWzZMm3fvn1Ij0kKzg762c9+pl/96lcyDEPXX399t22cTqf+7d/+Tffcc4++9rWvaf78+Zo9e7bi4+NVVVWl4uJinTx5Uo8//rjS0tIG/ZoCAAAAGF8IgwAAAACMqNzcXP3t3/6ttm3bpp07d6q2tlbJycmaNGmSNmzY0G39mq985SsyTVNbtmzR7t27ZVmWrr/+eq1evVpSMKSZPHmyHn/8cb355ptqaWlRVlaWPvaxj+nTn/60JkyYMOS+3nTTTfrtb3+r1NRUrVu3bkj7uOWWW7Rq1Sr94Q9/0ObNm7Vx40a1tLQoMTFRM2bM0D333KObbropbC2i88/Br3/9a73wwgtKSEjQypUr9W//9m966KGHhvx4pOBsql/84hfy+/1aunSp8vPze9yuoKBAv/nNb/Tb3/5Wb7/9tp5//nnZtq3MzEzNmDFDn/zkJ0MBz2BfUwAAAADji1FXV2dHuhMAAAAAEAkbN27UN7/5Td1555269957I90dAAAAABgVrBkEAAAA4KIUCAT061//WqZp6rbbbot0dwAAAABg1FAmDgAAAMBFZdeuXdqxY4d27typQ4cO6eabb+61lBoAAAAAxALCIAAAAAAXlS1btuiRRx5RSkqKbrzxRn3lK1+JdJcAAAAAYFSxZhAAAAAAAAAAAEAMY80gAAAAAAAAAACAGEYYBAAAAAAAAAAAEMMIgwAAAAAAAAAAAGIYYVCUKCkpiXQXAKBfHKsARAOOVQCiAccqANGAYxWAaMCxKogwCAAAAAAAAAAAIIYRBgEAAAAAAAAAAMQwwiAAAAAAAAAAAIAYRhgEAAAAAAAAAAAQwwiDAAAAAAAAAAAAYhhhEAAAAAAAAAAAQAwjDAIAAAAAAAAAAIhhhEEAAAAAAAAAAAAxjDAIAAAAAAAAAAAghhEGAQAAAAAAAAAAxDDCIAAAAAAAAAAAgBhGGAQAAAAAAAAAABDDCIMAAAAAAAAAAABimHMgG7388sv6/e9/ryNHjqi5uVlbtmzpc/vS0lL94Ac/0O7duxUfH6+bb75Zd999twzDGJFOAwAAAAAAAAAAYGAGNDMoOTlZt912m7785S/3u20gENBXvvIV5eTk6MUXX9TDDz+sl156Sb/+9a+H3VkAAAAAAAAAAAAMzoDCoFWrVunaa69Vfn5+v9vu2rVLZ86c0T333KOEhARNnTpVGzZs0B/+8IdhdxYAACBmWZZk25Huxdi62B4vMF7YtmQFIt0LAGPN5+VvL2KD3x98PwOILlaAz26EDahM3GCUlJRo0qRJSk5ODrXNnTtXZWVlampqUlJS0kjfJQAAQHTw+2ScrZBZWSqzqkxGVemFf58tlwxTgfnL5Vt7iwLzlklmjC3v6PfJsW+rnO9vknP3+5K3Xdak6bKmFykwo0jW9CJZ+VMl0xHpngIxxag7J/N4sRzHD8k8dkiOE8UyGutlZeUpMGN28DM4vUjWtJmSJyHS3UW0sm2J0vCRZdsy6muC3y+qyoLfLzq+Z5iVpTKaG2R74mVNzJM9MV/WxDxZE/NlT8wLtk2YyN/g8/z+yNyvaYz9a2Dbwf/G+nunbUttLTKaGmS0NMloapCaG2U0N8pobpDR3NTx/8aO9gYZTY0yWhpltLUGd+GOk52YLDsxRUpMDv47KUV2QlLw/4nJHe0pHdsF/1OcR1IEjlcOx9gfJy0reJ/RdHy2ApJhRuC5CkjWEANzQ5JjxE+z988KROa47W3v+Ow2Suc/l02Noc9s8HPb6XPcsY1ammTYNt9BI2jE36XNzc1hQZCkUADU3NzcaxhUUlIy0l2JOTxHAKIBxypc7Exvm+Jqq+WurVZcbbXiaqo6LlfJ3VAjo58Ruc4d78i54x21pU/U2WVXqmbR5QrEJ45R70eBZSn5xCGlHdiqtEM75GxrCbvaceKwHCcOy/X6M5KkgMut1pwpasmbppbcaWrOmy5vetaI/xjkWIVY5WhrUULZCSWUnwj+v+yE3I21PW5rVpfJrC6TNr8uSbINQ22ZuWrJnRb8DOZNU+vESbKdrrF8COhkvB2rDL9P7rqziqutCv2NO//3zl13VlbnY3jedDXnTpMvNWPkjuGWJc/Z8k7v8ePynK2QPyFJ9bMXq3beCrXkTY+uk56DZQXkrq8JfbeIO/99o7ZK7tqzcvja+7y50dYqx6mj0qmj3XdtOuRNy1R7epbaMybKm54V/Hf6RHnTMqPvWGBZcrS3ytHaLGdbsxytzXK0tcjZ2tzR1tLR1ixna0vH/4PbmH5fxLodcHvkj09UID5RAU9C8N+eRAXiE+T3BNv9noTg9Z3+bTmccra1ytHW0+NrlqO1pfvz0PHYDSsgf1x8+H2e/3eP99nRn/hEyXTo+K7twfvs2PeF57zT89rDc27Y1rCeK8PbLsPbLtWeHaFnf3TZhil/fIICHc+l35N44d+dX+eOf3duk2V1es06Pc89POdhr3Nbi2zTEXr9/B2va3D/CR37T+x+fUfbkAMO25bpaw9/3Tv9u9v7o/Pj8bbJcjgv9KuvPob1N1EBT7xMny/sc9/TZ+HC/V74/Du8fR8/+2M5XRdes66fo86fV094vwNx8XJ427odozo/N+f72vn1dba2yPR7FXC5w5+Dnu4z7D0VvM5ye7ocI1u632e348XIHCMj9R10vH2vGg0zZ87s83qjrq5uwJHn9u3b9fnPf15btmzpdZsnnnhCTz/9tJ544olQ24EDB/TXf/3X2rRpEzODhqikpKTfFxMAIo1jVWwx6s7JufVNOTdvknnmuOyklI6RpMFRpKGRpNl5Ulx8ZDrZ3CizY3aN0TEC9vwoWKOlUXZ6lqzs/PB+Z+fLzsyR3HFDu0/blprqL4yyPX+/laUyqktl1vd80nWobJdb/kvXybfuZlnTi0Zmp411cu7fLsferXIc2imjtVXW5OnBUVkds3TszJyhn0yzLJlH9su5eZOcW98Y9nNiJyYrMG22rBlFCkwPjiCzM7KGvL+S4mLNzM8NH2HaMZKtpxGpodFuzQ2SP0KlteLiwka1ho1yTTr/7yQpbORriuSJH95JUb+/Y8TfhVF+F56fjpG6nUb0htpamqROo3XtpGTZCclSUtfRuSlSYtKFbRKTJbcnOIuuuWP0YNh9dx4h3NjtOrW1yk5Jv/CZz84PG/WuhBj7LdLeJvNkSXDGz/FiOY4dkll5ZkTvwnY4ZU0p6Bi5Gfz8WXlTJJ837D3R/T3S82dKHaO5h8ThCL7PEy6858PfX+Ejv4Ojw5OlxKTIjNYdppLDxZqZn3fh+Ts/qrbLyNvQc9t5G0l2QvD4oM7PVefnJanL85iYLMUnSu2tF2avdv5bV1kqo7a630ENXVkp6bKmz5Y1fXbw78yMItkp6f3f0LZlVJWFv79PHpbR3tb3/WXmyL9yrfyXrpM1ecbIBUO2LfPMcTn2bQ3+/TyyT/KOfamb4Z48HyrbMKT4xLDP3IX3V3Kfx3u544KjyEOjxbu8h5saej/etzZLQx2oH6HnCogltjHUGWP2oP9eAJ3ZTpesyQUdFSQ6fQcd4kwozlcFjXgYtH37dt1777166aWXQsHPH//4Rz322GN6+umnh93hixVvWADRgGNVDGhqkHPbW3Ju3iTHwV0D/hFtpWaEhy0dJ16tiXlSUurQT8TYtoy6c6GTUGZV59CnNHiSYCi7NQzZ6ZmdThLndzpxnCd5EmTUng3eR6ikW/A+zaoyGa3NQ3s8wxSYXiTfupvlX7l2cGGW3x8MZ/ZtlWPfVpknDvf748xOSgmdtAuGRLNlp03o4wa2zJMlwQBo8+syz1UOvH9DYLvcwfIRg79lcATpRcJ2OCTHEEfU2ZaMCNT0th0OGYHRCd3s5NROZZHyQ8cpOzs/eHJ6gMcqy7JUdu64jpTt05HSfaptOqv0pAkqzJqlmSlTlO9IlqO1uYeQsYeQZBgnOuXzcrJzgGx3nIZcEsjpCJ747hScKHQyvPeQVm5P8D3lbe+lBFKnE+MdpVYulFhpCrYP+c0xNLZhjsl7ysrMljVtdqhEaGDaLBntbTKPHwqGPseL5TheHPysDOd+8qbKt3Kt/JeulZ0zefA7aKyTc9/2YAC0b5vMuuiYfdAb2zAicnJ2NI/rFzOvaehYWpwOZcTrcLpHrU5Tkxq9ml3TqqKaNmW2RajU3RiwDVMyJMMa338DG9ymitPjVZzh0fHUODlsqaCuTbNr2jSrtk0J/vHd/1hnSypPdKk4w6NDGfE6nexWwBzadwXDlnKafZpd26rZNW2a2tAuxygcbi1Jp5PdKs6I16EMj8qS3LIjMBnWHbA191yrrjtep/T2wR3fh/O3yHfFh9T+2a8P6bacrwoaUBgUCATk9/u1c+dOffGLX9Tbb78tSXK5XDK71BQNBAL6xCc+ocWLF+tLX/qSqqqqdO+99+ojH/mINmzYMDqP4iLAGxZANOBYNQpsW0b5KTn3bQuexC87KTsl/cLJk+mzgyc3hlPju60lWJps8yY59m6VERjZH462J37oJ6O9bTF3MtpKz+x2Evr8yWmz9IRcm/4s55Y3+nwd7MRk+VZ/UL61N8nOntTjNkZlaXB9nn1b5TiwU0aX8mxD6ntG1oW6zjNmKzBttoz6Grne3xScQVZxut992Mmp8l9ylXwr18rOmSTzxOHQqG/z2CGZjXXD7icwFLbbI7ncvV5f5zJUnOpScapLh1OdanH2ftxN9AY0q7ZNs2uCJwTSvJE9CdrjyMrM7OAsh2OHgifgjx+SWd7/ZxgDZztdkmleVAH0eBaYOkv+S9fKv3KN7AnZPW80hMET443tSej2/eL8v+30zGDweH4doa6DXvgbHGIbZnD9njHW1/dPW1JFokuHOk5cH0v1yO/ovY8TWn0qqgn+LZpZ2yZPYPy9l223p9MM5+QL6/50mmmmjllonQN4eRKCYXtba99rlHSbpdpxeZR+X/gN6VhqnIrTPSpOj1NZUu/fKwzb1pQGr4pqWlVU06rJjd5RCQ8Qrsll6nC6R8UZwZCuPm50Zg57fJZm1bZqdm2bimpaldE29O+CdXEOFacHP/eHMzxqcY2ftd2clrS6ya01gQx5EtO6DJDpNGP0fHtCUvBv7akjF9ayPF48oN+RktT+yS/Kd/WtQ+or56uCBhQGPffcc7r//vu7tT/44IPKz8/X7bffrp/85CdasmSJJKm0tFTf//73tXv3bsXHx+vmm2/W5z//eRmxXLd3lPGGBTCq/H653nhWzrdflFFXM+TdNKdOkOuaD8u/Ys3QS3BBam6U48B2Ofd2jELtZ4aFHZ+owLRZHeW9OkpoTcjue4S7t12OPZvlfH+TnLvf40TVCLJNU3ZmTpfyVB3/z8rtWLC2b0Z9jZxvvSjX68/0+/r7F1wi39pbFJi9UI7i3R3vm60yq8pG6iENmx2fKP+y1fJfulaBOUslZy8/umxbxrnKjpHhxcH/nzgcsZlYuLh1HnFdnO5RRR8ndPqT0+QNnZCbUd8u91AXJx4A2zBl5U8LzuqbNlvWjNmyJhdIA6m53tIkx4nDYbMzRnuWH6JLcGZtVs9hQ1aujIa6Tid3Dsk8WTLi3zHs5NROZU2D72/z2EG53t8kx+73ZPj6X8cgMHN+sJTciqukttYRHzwx2qyU9E6zsPPDymIqeRgzslubL5QI7BwSDbFE4HhgxyeGl49MTLlwkjIpRXZCkuyklG4nLkMz+8aaZUmtzaGSeS31VTpafVgldSdV0lqpBntonydThqa40jUrOV+FGQXKzZwhs/PMRqczWKqvOXyGYrdynz2Uq1TAH/78dXpuL5Tv7FROMClFSkgK3m8fgzCigW3bOltfHpwpXLZPxysOyucfWtAUL6cKlKTZPrdmN1rKaGrpNMO4STLNnkszdj753lEGNBSwJXWU/wwELsxQbRnYa2w0NQa3Hcbn3na5u4d6fZUL7gj8FJ8YVo5WXcpK9jXb1mhpCoaMHfsNJCXpRLJbxQm2DjtaVWo3j/Gc26BMw6NZVqJmtzlU0OiXp7FTqeq2Ftme+NAM5PbEZB1LcelwfEDFZouq7GGU2B0jCXFJumrRzbpk9lo5h1Kat7nxwnfQ84MEa6q6bdbyz7+QVTB3SH3k3HrQoMrEIXJ4wwIXiZYmud55Wc4trwcXebzqRvlXXjXkmqj9sm05tv9Fcb//5YBHYgxot4kp8l3xQfnW3CQ7O3/E9jtk3vZOZb7O18AvlXmuSrbTGf6jsMsaBOpaAub8KLSRFPDLPF4s594tcuzdKvPYoWGXaLGS02R1jAAP1edPSJZj//ZgGa/tbw/oZEdgSmFwFO2yK2T4veHr45wfUXq2ImIlGmyXS3ZWl5MhE/NlZefJTkqVea6y+5oHVWUyaqqG98PGHdexJkl+txMx9oSJI7c2hRWQY/dmuV57Ws69vZfpHYrAlEIFFlyiwPxLZE2YKMeJkgsngE8U97smQ39sd5z8Sy6Tf+VaBRasGHpAbFkyKk4HfxSc79+pI8OeMWYnJF4o+9TrejZdyj4lJkUm6LbtjpGvvZQZ62nNnvM/iod5EtY2zI4f6T08N11POJwvn5WYHDwB5G0f/LpMTQ0y/D7ZptnpuU9S+MmOlG73GXqt4jzBEo/dyjuWyqiukNHHYreDHXE9VK6ApRn17SrqmDWU0+wbavEySZI1Ma/jOD8neGJ86swRXcfNqK/pKNkVPoPPdrk6PffhJ/l6PLna+e/oUEfb+/0X3v9d3le9jgpv6Vh7KgpPYkvBWR7dT6B2HmXbZTT9+fWApAufqZamLms6NVz4PHZdp6WtRbbDKTsrN/j3Laz06xDW3Av4ZZaevDD77FixzDNHBzz71vYkBAe8dC5Z2teadq3NF2Y779s64rN8bbdHgTmLFZh/ifwLLonc99zR+m3Ql4D/QljQHP7ZUw8nkYPvr45/B/yyHY4u37m7HBs6HTvCThQnJA5jBrwxvNnzERCw/DpdfVRHSvfqSOk+lZ07IXsUTl0nxCWpIG+eCvMWqDB/vlISBrCOV09sO3i+ataske3gONba3qyj5Qd0tGyvSkr3qb753KjcT2ZKrgrz52tm/gJNmzhbblfc2AeUlqWh17JVZI5Vtq2axiqVdJTyPV5xQO2+4f2uGWkO06EpE2eqIC/4+uakTVZVQ1nwc1+2TycrDstv9T+wYTzKSM7WNcs+qrlTlw97UkjwO+iFQYLmqaNq+eGvh/x7jHPrQYRBUYI3LBDbzFNHgqWh3n2l2wlYK3uSvDfcKf9lV/c+mn4o93n0gOKeeFCOw3tHbJ898S9YId+6WxRYtHJ0vww2N14odxEWWJTKrB25+u7hJyiTu5yg6X5StPMJms6jso2zFXLs2xYMgA7sCJ6oGWW2yz2gE+hWzmT5L10bLOOVN7X/Hfv9wdkcXU+8ng9ehnsyOiFRVlZ+2Cjk0Gyb9Myh/cj3eWVUl3e8Zzotkt3phLGdmNJjKTc7O192asaY/xgzKs/I9fqzcr31YtgaCqeS3XptSooa3Q5Na2jX7Jo2zahvk6tLPmelpCswf7kC8y9RYN6yvtf/sQIyy04Fv3SfX7T79NE+T6RLwYXmAwtWyH/pOvmXrAqe9B0NVmBY5T1KTpzUzNlFI9ihccznDT5fg+AP+LSl5C3tP71Dbf6h/Xg2DFOTs2Zo9fzrlZHSSzmmnth2sM8u98h/xqyAjJrqsJHurdWnVNJcrsNGkw6nugZVKiTeFywFV1TTpsmN7TqVHKfirCQdTnOrdRAhUkp8mgpz5qogd44Kc+YoIS5p4I/JdAxqVHVd0zkdKQueYDzbUC57qAGJbUdkxLzL6daUiTM1M2+BpubMlts5wJMBgzxm2LatyrpSHak4oKMVh9TQUhvch2UFA2rLunDZtsKuC15//jpb8X5LBQ1ezWoxNVUJcvQ2IrpzmNPx3eFwWYVmFs0Z4rM1RH5/MKwbze9s3naZp492WhvokIzyU5LTKWtKYadZP0XDK4XbVC/ntrc71kHcOeRAMDR4YsEKBQrnRf1MhjE3msf1EVbffE5HSoMzPKrry4Z+jBxmHwZz4jotMVOF+fNVmDdfaUmZOlZ+IHgyufKwAtbASz+nJ2fJ5Rjae9vr9crtvjg+F5Zl6VxjxYDfG4YM5WVOC4ZuefPkD/h0pGyfSkr3qaruzIDv12E6lZEyUcawho8MTVpSpgpy56kwf76yUvNGrepTu69NJyoOqaR0r85UH5UvMLTv+u2+tkEFdC6nW9Nz5mhm/gIV5M5TamIfv5H60Opt1rHyAyop3aujZfvV0j7wtW2dpmtQ4Y/HnRB6TQpy5ynRkzKULg+ZLVv7TmzRazv/qMaWuh63mTKxUNcu/7imTCwc0771hXPrQYRBUYI3LBCDfF45t70l12tPy1Gyr9/NrQnZ8l7/cflXf3BYI9ONqjK5f/8ruba8PuR9DIU1IVu+NTfJf+WHgot0D3lHAZllJ2Ue6xilfPKwzIrSYS8wPBZsT3xwtK5pyDw78LI7tsutQNGi4En82Qtl1FSHpk47ThQHR2QOkzUhO1gu5dK1sqYUjtyPdduWmhs15BFlpiNYJmAsTx6cP2k4giPrR5S3Xc4tr6vxjT/pJdc57chO7LaJK2CpoN6rWc4MFU5dooxFV8meUji80bF+n8zTRy989o4fkll6UpIUmLskGAAtWy0lJg/9PsYI36t6ZtvBH3avbP+9apuqR2SfDtOhFUXrdNXCm5XgGUTIMUqGM+LakKHJE6apILtIM7OLlJ8xVaZhhq5VfILkcCpgBVR69ngodDlz9ugQThrNV2H+Ak3OKpDDHPpAEK+vXScqgydWjpTt09n68iHva7xxmi5NzZkVeq6y0yYN6wRVc1uDjpTtD43KbWqtH8HeBrmdHs3InRPq84R+gtKL6ljl9wX/1o/UzNoujLpzcm55IxgMHdnf57ZhgyfmLw8OAEFM8vrbdaLiULDEV2kwABrvwk5c581XZkpOj8e+sON/xwAAjI3khDTNzFugwo5wobfvPw3NNcG/O2Xnw4PRHxw4XCkJGZqZP18FefNVkDdvcANYurBsSxU1pzoC2L06VVWiwCAHMA1VbsbU0N/iKRML5Rzq+ra9sGxL5edOho4tp6pKZNlDf2yGYWhyVkFHqDhf+ZkzZI6DWY9eX7veOfCS/rL3BXl7GUA2b+olunrZR/v9zjMWLqrvVX0gDIoSvGGBsWcW75HrnZdlNNbJmjT9QqmtvkbTD4BxtkKu15+V883nh7RIq5WaId8Hb5dvzY2DG3XfVC/3nx+T67Wne1yY3jZM+a/4kLwf/NiQToIbLY1qfPYJTdz7fp/BjO1wyr/iKvnW3ixr5vy+T/LbtoyqslBpGsexYPgz3PJV0SAwaXrHSYhgANRrAGjbMqpKL6yvcvyQzBMlMrz9P0dWarr8K9bIf+m6YN3dcT5aE0Gt7c16c8+zev/gKwMe8ZmamBH6wVOQO0/xcd0DpCHxtksOx6idvBstfK/q7kRlsTZufUJnzh4blf17XAm6ctGNWlm0Xi7n2I4ermmoHHKpkM4jrmfkzh3SZ6e1vbljpPbgy8nEuTyanjNXM/ODn9+M5Il9bm/bdvDESsfaBYMdGR7NkuPTOo5zwRNU/Y2S9Qf8Ol19pCP82auycyfHqKcXpCdnBfuct0AzcufK4w7//sWxanQY1eVybnldzvc3yXHqiGynS4FZC0LhjzW5IOpKi2FgbNtWZe3pjpkZe6PmGDkSJ67rms6GHvexsgNq843/tbGihdPh0rTsotD3hYlp+YMenGBZlsprTnYM3tir01VHhxUejAXDMJQ/YUbocU/KKpCjn1mljS11oe8oR8v2q7ltbAZ0JnlSVZA/r+Nv7nwlxaeOyf2e1+5r1bHygzraMSusprH/gaGh76D5CzQjZ87I/X4bBU2t9dq060/afvhNWT2Uu3eYDl0ye62uWnSzEj2RGzjI96ogwqAowRsWGCO2Lcf+7XI/85gcxbt73MRKzwyVrrCmFykwfXb/I+EtS459W+V67c9y7H6/z/VgrLRM+a+6XkZNtZzvbOy11rmdlCLvNbfJt/7Dfd+/t12uV/8k97OP91qKzL/oUnk/9reyJk3v+3H0o6SkRDOnTpFzy+vBx3rsYJ/bByYXyLfuZvlXrZc8CcF1HjotWu04XjwiM35sw5A9YWLHui75F0p/TcwLlnPpvEBml7UHzi/YGWobpSDKTkqRf97y0Boudnrm0HcW8MssPxU+g+PU0WC99sRk+ZdfIf+l6xQoWhSZOs4YEn/Ary2HXtMbu/+sVm/zkPfT+YfbzPwFys+c0e8Pt1jD96oLquvL9cr23+ngqR1jcn9piZlav+w2LZi+stOsmpF1/gd3cDTmXtU0dl98tjcDHXE9VLZt62xDRWj2yWAXms5InqjC/AUd4dQcxbni1dTaEJyFVLZPR0v3q6lt5Ge0RBtDhnInTA09V5OzCuUwHapprAzNkjpefqjXUayRYBqmJmcVhk785GVM09GjRzlWjbb2tmDwQ+m3mDUWs/5G2mifuA7NYO14TgYzgxVBE9MmBQdq5M3X1OzZIz7Qpc3bquMVB0Ov0WC+y0RKnCteM3LnambH39705Cz5Az6drDwcmiFTUXtqTPriMJ2amj0r9BnKzpg8at87h6KmsSo0I+pYeXCgktsZp+k5czrCteDs4dEqyTdaqurK9PL2J1V8eleP13tcCbpi4Q26dM7VYz44TOI34HmEQVGCNywwymxbjp3vBkOg44cGfXMrOz9U37w+f5IOu9p14txRGX6/Lq83NOWtN2RW9112wD93aXBtncWXhdYGMs5WyPXCE3K99bwMX881ZO34RPnWf1jea26TUtI6dcqSc/Mmuf/wq15LkgWmzpT3js8rMHepTlYe1q6jf1GcK0Eri9YpPTlr0M9D12OVefyQXJuekfO9V/tcq8b2JMj2JMisG/jaPrakAxPitTsrQRltfl1e2abEtOywdV1CoU9mzsj9yPd5Oy2UG76Yu9HcGFyguetizOcDpU4hoO1wyCqcL/+CjlGoU2f1OgrVsiyV1ZzQkdK9OtdQqZSOWR6TswrlHOiMDJ9XRlOD7OS0EV17CqMvVLprx+9V29hz6a7s9Mm6ZPYalZ0Lvk8aWmoHvH+PK0H5WdOHVYoqEhI9yZqRO3dIJ0kG+73q/DorxysOqc079JG0qYkZKsidN+QZJiOpqbVBr+9+WtuKX+9xBJ9pOHTJ7Ku0bOaVMocQFpadO6HXdj7V6yyY/AnTde0ld2h6zvDXbjpfiiNYo32fTlUdGdRo2pyMKaFyLqNRKqQv/oBPp6pKQgFFRc3AT5KYhkPpyZk61zDwsqOm4dDkiQWhmU5xrnFaDrMHtmyda6gMlfirax74dwa306OEuKRB3ubCSZkpE2cO6Rhp25YqOmYhDDaoi49LVHp8tpKSxn/pTVwcTMPUxPRJmpk3X5MG8x10jA1n1p9pmJqUVRAaie9xj9Lah31wOVxKS84a0xPXbd4W1TfXDPn2J0+e1NSpA1hnNEYkelKUFD+2a7TUN9cM6zvoUF0Ic/bqREXxoNbxSU/KUlNr/aBuk5GcHZpp1N9s6P7u2+0aemn9sRSw/Gppa1J8XOKYfgcdTcfLD+qlbU+o7NyJHq9PTcxQdvrkIe37yoU3DXkdIs6tBxEGRQnesLjotLZ0LEDfsah7ZTBICcycN/xZE51ZATm3vinXM4/LcWZopXH8hnQ81aNDGR4VZ8SrNDk8dDBsW5dUNOuDx+qU5g0/OWUnJMr3gevkW3OT7Lzev0AbdefkevFJuTY902v5L9vtkW/tTfJd9zEZlWcU98SDchwv7nFba0K2vB/5rPyr1utcU5Ve3v57HTi5LXS9w3Tq0jlX68qFNw7qhGWvx6qmBrn+slGuTU/LrCwd8P56cyo7Q3+emaFjrgsBWZwrXlcsuEGr5l4TkVEm/bIsqbU5GBS1tcrKzAmuL9GL+uaa0Aiqo+X71NrefSaI2+nR9Nyi0EnMjOSJUTd6CH07WXlYL219QmfOHu3x+pSEdK1b8hEtLrg8VDfatm1V15fpSGmwJNWJykPyBwa+IGk0ysmYosK84EynKRNn9vtDqr/vVaO9zophGJqUWRAa+ZefOX3MZmd5/e1678DLenvvc72WS5szZZmuWfYxZabmDOu+fH6v3jv4it7a86zafa09bjN78mJds+x2TUzLG9S+G1pqQyMqB1tnP9GTEionFolSIX1pbKnT0fL9oQXMR6J8SnpylmbmBWc69VSKLBrZdkcw1LEu0/GKg/L624e937wJU1WQN18z8xZo8sSZI3qy27ItVdacvihL+CH2hNa/6pgBEMm1IGzbHtasv7SkzI7v0uePkWMfAEU7zlddHHx+b9gAlsra08PeZ5zL0zG4K/gZHE4AhPHFsi3tPb5Zr27/w6AG4/Tn42u+qLlTlw3pthyrggiDogRvWMQc25Ya62VWlcqsLO0IfspkVpXJqCztdy2dwKQZwYVdF6xQYNaC3tdT6Y3fL+d7r8j93G9kVvT+JcY/b7n8y1fLPHNcjuPFMk8dkfw+VSU4VZwer0MTPDqa5pHX0f/ILVfA0lWnG7T2VINc+QXyrbtF/lXrBrc+T2Od3Bv/INerf5LR2nOZKNvh6L20XHyivDfeKd/VH1Gz1a7Xd/1ZW4tf73UEdXxcoq5aeLNWFK0b0AmRfo9VliXHgR1yvfa0HDvf7bNcXqjPngQFps2SNaNIZ/PztbHliPaU7ep1+9TEDK1b8hEtKrhsXE0F74/P79WJyuJQKYCqusGHZulJWWFrW/BjNnqdra/Qy9t/p4Ontvd4vdvp0RULg+Gn29n38c/n9+pk1eHQe6uy9sxodHncOF/m63xt/Z7KfHU9Vtm2HRy93/EcjfVJWo87QQW580LhUFrS8Nam64llWdp97F29uuMPvc4cm5RZoOsuuUNTs2eN6H03tzXqjd1/1pZDm3r8e2MappbNulJrF3+412Cm8/u4pHSfquoG/j4+XyokeJJ//JUK6U1wYeXToXJ3p6oOD2hh5fF0knasBGdYHQmFQ+U1A5sJkBSfGiohU5A3f0xHerO4O2LJWIfObd6W4FpsHcF5bVPPM6d74nbGaXrunNAgkozk6CvFNN5wvuridH79n+DM7P1qaW/s9zaGDOVlTlNh3gLNzF+gSVkzoq46AQbH5/dq86FX9ebuZ0dkrTLCoOEjDIoSvGER7YzKM3JueVOOk4eDYU9VmYy2kZnmbLvcChQtUmD+imC5rfxpUm9f6L3tcr79ktwv/KbX0mmS5F9yubw3flJWwRxJwcWfj5Yf0NEze3Tk9C7VtQ99pG6iK0Frl96mZbOvGvpI8OZGuV57Wu6Nv5fR1H9fbIdDvrW3yHvzBvniE/TegZf11t7neh2p3VV6cpauXvpRzZ+2os8fS4M5VhnnquR641k533xOZn3wxKTtcsmaUhgquReYUSQ7Z7Jafa16c8+zev/gKwM+QZubMVXXLr9dBXnzBrT9WLNtW5V1Z3S0dJ9KyvbqZMVh+a2Rm71xfu2Bgvzgyc+8CdNDM0cwfjW3NfQZ0pqGqeWz12jNoluGfNLywoyKfQP+4RbNUhMndNR0XxAqz1ZSUqLcSdnBRVzL9o67dVYyU3NDJ6mmZRcNu8zFkbJ92rj1yV7rtA/0GD9c5xoqus1E7czt9Gj1gg/psnnXyeVwq6quNDRDcrAz3DJTckPh+PScOVFTKqQv7b42nag4FDrxcq6hQlL4+jjjvXzTWGlqrdfRsv3dPt/ng8Hza0LlpE8eNyeBzy/uHpwRvD8i5YCAkdC5HOX59a+G+x3UsiyVnTuuko5w/Ez10R5LnPYmb8LU4MyDvPkjPusPnK/ChZK95/+OnaoqCf2WSUlIDx0PCnLnKcGTFOHeIhJa2pr0xp4/a8uh1wY0uKk3hEHDRxgUJXjDYkTYtoyyk3Lu3y6juUGByQUKzF0qJYzOH2PjXJWcW16X8/3X5DhxeFTuoydWRpYC84PrsPjnLZOSUqX2Vrlef1auF5+UWdfz+gW2Yci/4ir5bvikfJOmdVpUc6/OnD024EU1DdvW5EavCuradGBCvCoTey5Zlpmaq2uWfUxFk5cM/UREW4tcbzwn1wtPyKzvuc6zf/kVav/oXQpk52nPsff06o4/9FoTOm/CNDW11vc6anxyVoGuXd77qPEhHav8PpmlJyQpGOQ5L5R38gf82nLoNb2x5889lkmTpGnZs1VRe7rXkyYz8xfq2uW3Kzt90uD6NQqa2xp1tKM8zJGyfWpsqRvwbePdiZqRN1dTsgpVXnNq0AvgxsclakbuXCV5xk85JIQLWD7tPb6l15C2aPJSXbPso8oaZDmtvpyfedA4iDWGxgPLtoLH6LK9Kjt7QrYGeHzuKM/W3NKkmuaKAd/fhRNbC5SdPmlIs0r8AZ9OVR/RkSHOaslKzZU0+L8V1fVlOlZ+oMfr4t2JumrRzVpRtHZMa5SfqirRS1uf0OnqIz1enxyfJsMwBr321Yy84KLFBbnzhrTuXbSpbaxWY2udJqRkK9EztmsXRBPLtlRdVyavr03Z6ZOjIhgMWAGV15xUydFDyssbuWM+MBwt7U3B2TiD/A6aEJekGblzh3ycamqr17HyA73+FuhJaNZf/gIV5s3jGDnKOF+Frtp9raqsLVW8O0GZqbnjZuAFIq+5rUFlZ08MKtDvLG/CNCUnpA3pthyrggiDogRvWAxZU4Oc+7fLsW+rHPu2yqwJn0Jvm6asgrnyL+iYVTN9tjSMdQuMhlo5tr4p1/uvyXF475D3YzucsjNzZE3Mk5WdL3tinoyWJjn2bpV57NCAyotJwYDHmjZL5tkKGY09/2ixTVP+y65R5boP6Yi/RiWle3Ws/MCgRmR2G+0SsGWePqaAO07bvKXatOvPvY46n5ZdpOsuuUP5mdMHfH/dnJ/x9PxvZJ4LzngKFM5T+x2flzVzvo6W7dfGbU/2WjYlLSkzOCp8+gr5A74hrycxUscq27a1/+RWvbz9d6pt7LnsQ076FF17ye0qzJuvlvYmvbnnWW0++GqPM4cMw9DSwiu0bsmtQ/7iMBQBy6/TVUdCoxjLz50c8Enr4AK2M0KjGPMzZ4SNqrRtW5W1pzuNmi9m7YEYlZ85Xdctv0PTcooi3ZVxqaWtqWONlb0qKds7qJC1LxnJE0PH9ek5c0a05E3D+TXBQrOzBr7ezUgY6rpwIyl4nN+mV7b/TjWNVYO+fWjdpY7XaCzXXQLGCr8BMR6dL616tGOW4nhY/8ppujQ1e1ZoRmj2OJr1dzHgWAUgGnCsCiIMihK8YTFgAb/MowflPB/+HCsecHAiSXZiivzzlimwIDizxs4YwAJ+zY1ybv9LcAbQgR0DD2rcnlDQ0zn0sSbmy87Iknqbvt/UIMfBHXLu3RoMh2oGfxJJktrcbh2+/HIdmpajkprjg6rV7nS4NC27KPSDY2Jafp8/ONp9rfrLvhf1zv4X5fN7e9xmwfRLdfXS24Y3mtnvl+PwHtnuOFkFc1VZV6qXt/9Oh8/s7nFzjztBVy28SSvnrO82KryptUFv7H66o1xV99fUNBy6ZPYarVl8c2i03Ugcq05WHtbGbU/odPXRHq9PSUjX+qW3adGMy7qVnKhprNIr2/+gfSc293hbl9OtD8z7kC6f/0HFuTzD6mdvahoqQ+HPsfKDg1vANjEz+J7KX6AZOXMGdZLW628PlQ86UrpP1fVlQ+k+xpHOIW00rG8yHti2PeTSYnEuj6bnzFVhR2nFjDFaZ8WyLJXVnOgo3bdXp6uO9rqO20hYOGOV1i/5yLiZOeMP+LW1eJPe2P3nfkOx8yX/CvIWqKCj5B8Qy/gNiGhwfv2r8yVox+o7aFZqXsff7AWamjO73zUUMXo4VgGIBhyrggiDogRvWPTFqC6XY9/WYDhyYIeM1oFPoe9PIG9aKBgKFC2W3B1fsttb5dz5rpzvb5Jj7xYZ/r5PttmGocDsRfKvuErW5ALZE/Nkp2b0vrbPQNm2jPJTwfBr71Y5Du2S4W3veVNJZUkuHcpK1sHp+TphNA+qVunEtEkd607M19Ts2XI5ey7/1peGllpt2vmUdhx5u8eycyM1WruxpU6bdj2l7SVv9Xo/K+es15ULb1RCXN9lAqvry/XK9t/p4KkdPV4f54rXFQuCC9mfOH5yyMeq/taSiHN5tLrjfvr7sXem+qhe2vaETlb2XJ4wKT5V65bcqiWFq4c9krzN26rjFQdDC88PZoS72xkXXOi+Yz2TCSkjt4BtffM5HelYj+hY2QG1ekfuuIDRFe9O1JWLbtLKonVjWrorFvn8Xp2sLO5YYyW8PJshQ3kTpoVC/ckTC8fFAradjyklZXt7nR05WCMyC3UUtbY36629z+n9A6+E1k9zOd3BY2Re8DWizAguNvwGRDSqazqnI2V7R3z9q3h3ogry5nXMCJ2v1MQJI7JfDB/HKgDRgGNVEGFQlOANOw41N8qsLJVZVSq1tcqaPlvWlMLhhxsD4ffLcWC7HLvfl3PvVpmVA197wHbHKTB7kayJeXIe3CmzrOeyYT3e1uVSYNYi2QlJcu5+X4a3/xkPgYI58q9cK+8lV+pYW7Uqa08PsEjWEPn9Ms+Wyyg/LbPitMy6s7JlqCzJpeKMBDW6Bz66PiEu6cIPjrz5SknMGLFuVtSe1svbnlRJac+l9OLjErVi9rohBUKNLXXaWrxJXn/Podj8aSt19bLblJE8gFlfnZyoLNbGrU/ozNljPV6fmpih6RMWKic7d9B9Pldfoe0lb/U4Gt40TC2fvUZrFt2ipPiB1/u2bVsHT+3Qy9t/F1pku6ustDwtKfiAzCEEQu3eVh2rODDoUfy5GVND4c+UiYVjcrLfsiyVnj2m8pqTQ67Ni7GREJekmfkLmfEwShqaa3Sq+ogqKyp16eKrlOhJjnSX+lXTUKkTlYcHNcuwq7wJ0zQ5qzAqgpSG5hodLT+g1MQMTZk4k0AUFzV+AyLajcR3UNNwKHfCVOVPmN6tKgDGB45VAKIBx6ogwqAowRs2AmxbRt05GVVlodDHqCqTWVUqs6pMRnNjt5tYuZPlX7lWvpVrZedNHdn+WJbMw3vken+TnNve7HX9m54EJs0Izu5ZcIkCMxdcmN0jyThXKce+bXLs3Srnge09Pq7BCkwukH/lWvlXrpE9MU/Hyg9q47YnVHbuxLD3PZpMw6EpEwtVkDdfM/MXKHfC1FEvzXSkbJ82bn1SFbWnRvV+JGlq9ixdt/wOTcoqGPI+bNvWvhNb9Mr236u2aWRGq/dlzpSlunrZxzoWTh+agOXXtsNv6vVdf1Jz2/Df34OV5ElVQf48zcxboIK8eUqKTx3zPgAIx/cqANGAYxWAaMCxCkA04FgVRBgUJXjDjqL2NpknS2SePtYR9JwPfcp6LTc2EIEphfJfulb+FWtkZw3xRLZtyzx2SM7Nm+Tc/LrMurMDu1lyqvzzlgfDn3nLZadnDuz+rIDM48XBYGjvVpnHDsiwBjaCy8rOl//SdcEgLH+aJKmqrkwvb3tSxWd2Dez+I2A0FwgfKMuytPvYu3p1xx/V0FIz4vufkJKja5ffrqLJS0ZsVLg/4NPmQ6/pzd3PjEr5sUmZM3TtJXdoWvbsEdtnm7dVb+97Xu/uf2nAa4gMhcN0Bhew7XhfZadPYr0XYJzhexWAaMCxCkA04FgFIBpwrAoiDIoSvGFHiN8v88wxmccPyXHskMzjxTJLjw848BiqQOG84EyZFVfJTuu/trF5+lgwAHp/k8zq/hfgtB0OWTPnyz//EgXmXyJr6kxpJKbQNzfKcXBnaD0e82x4qS0rI6tjBtBaWdNmhUrkNbbU6fVdT2t7yZvjriRVpBYIHwif36t3D2zU23ufU7tv6OWAzkv0JGvN4g9r+awrR20djNb2Zr255xm9f/BVBSz/sPeXlpSpa5Z9TPOnrRi1ckb1zTV6bccftevoO7JHqGhhZkpu8D2Vv0DTsovkdrGALTCe8b0KQDTgWAUgGnCsAhANOFYFEQZFCd6wQ2BZMipOd4Q+h+Q4fkjmqSMyfCMzI8B2uWRl5cuemCfZlhz7tskI9H0y3DZMBeYsDgYoy1dLSRfKRRmVZ+R8f5OcmzfJUXqi//tPSJJ/+RXyL7lcgTlLpPiE4T6kfu7QllF5Ro79O2S0typQOFdW4fyw0Mnra9c7+1/UX/a90Ot6NUWTlwx6rZqR4HEnaHpO0bhZILwvTa0N2nv8fdU1DWwmWE8mpORo4YxVYzbTqbaxWntPbNGZ8pNKT0sb/A4MQ7kZUzR/2ooxWx+iova0Dp7cPuRFbQ3DUGZqrgrz5istaYCz7wCMC3yvAhANOFYBiAYcqwBEA45VQeP7jCgwGI11chzcFQx9jh2S48RhGW1DO8l7nh2fKGtivqyJebKzO/4/MU9Wdr7stMzw2TfNjXJueysY5hzYKaOHGTGGbcl5YIecB3bI/t8fKzD/EgWmF8m56105Thzuvz9xHvmXfkD+S9cqMP8SyTmGiyobhuycyfLnTO52lWVZ2nnkbb228yk1ttb1ePMpEwt17fKPa8rEwlHuaPRLik/RqrnXRLobg5KenKUrFlyvEk/0/HHNSZ+snPTu72cAAAAAAAAg1hAGIbq1NMm54y9yvr9Jjv3bhlzuzZqYp8D02bLypoXCHmtiXnDmzkBLVSUmy3/l9fJfeb2M+ho5t7wRDIZK9vW4uREIyLn7fTl3v9/nbm2XS4FFq+RbuVaBRZdKcZ7BPrxRY9u2jpTu1cbtT6qy9kyP22QkZ+uaZR/V3KnLR63sFwAAAAAAAACgd4RBiD7tbXLuei8YtOx5f9Bl36y0TFkzZiswvUjW9CIFps+WklJGtIt2aoZ8V98q39W3yjhXKefm14OB1cn+Z/9Ikm2aCsy/JFhObunlUkLSiPZvJJSfO6mN257U0fL9PV6fEJekNYtv0fJZa+R0cKgBAAAAAAAAgEjhDC2ig98nx96tcm7eJOeOv8hobxvQzezEFAVmzA6FPtb0ItnpI7u2h8/v1bmGCll2H8tvrVwlrVwl41yFHHu2yrl3i8yz5eF9NQxZU2cpsHCF/HOXSgnJwStazwX/GycCll9bD23SrqPvyFb3x+w0XVo19xpdsfAGedyjvI4RAAAAAAAAAKBfhEEYvwJ+OQ7tkvP9TXJue0tGS1P/N8mbpsDCFbJmFCkwvUh2Vu7Ay7wNwcnKw3ryzZ+rsaVucDecbkjT83q4olEqfy34XxRaVHCZ1i+5TWlJEyLdFQAAAAAAAABAB8IgjB+WJbU2yyw9HiyrtuUNmQ21/d8sK0/+S9fKf+laWZNmjEFHg7aXvKVn3/tvBazAmN3neDUjd66uXX678iZMi3RXAAAAAAAAAABdEAZhdDQ1yKivkdHcIKOpUUZLY/D/zQ1Sc6OM5uC/jeam0DZqaZJhWwPavZWeGVxPZ+VaWdNnj+rsn273bVnauP1Jvbv/pTG7z/EqKy1P1y2/QzPzF8oYw9cAAAAAAAAAADBwhEEYUUZDreIefUCOXe/K6GsNnSGwk1Plv+Qq+VaulTVrgWSaI7r/gWjztuh3b/5CJaV7u12XnT75oglEEuKStGD6Si0pXC2H6Yh0dwAAAAAAAAAAfSAMwogxTx2R5yf/KPNc5Yjt045PlH/ZavkvXavAnKWSM3Jv2XMNlXr8tR/rbH15WLvT4dKtH/gbLZi+MkI9AwAAAAAAAACgd4RBGBGO7W/L8/B3ZbS3DWs/tidedlKKAgVz5V+5VoEFKyR33Aj1cuiOlR/QE6//p1q9zWHtyQlpunPtl5SfOT1CPQMAAAAAAAAAoG+EQRge25bruV8r7g+PdLvKypgoOz1TdlKK7MRk2YnJUmKy7MQLl+2kFNkJSVJSiuyE5IjO/OnNlkOv6fnNj8vqsp5RfuZ0fWLtvUpJSI9QzwAAAAAAAAAA6N/4O/OO6OFtV9x//Ztc77/W/ap1t8j7ib8bl+HOQAUsv17Y8httOdT98S2csUq3XPYZuZzuCPQMAAAAAAAAAICBi94z9Ygoo/asPD/9JzmOHwprtx0OtX/yi/KvvTlCPRsZLe1NevKNn+tY+YFu161fepuuWHCDDMOIQM8AAAAAAAAAABgcwiAMmnn8kDw/+SeZdWfD2u3EFLXd820F5iyJUM9GRlVdmX792k9U01gZ1u52xum2K+7WnClLI9QzAAAAAAAAAAAGjzAIg+LcvElxv/q+DJ83rN3Km6rWL/1f2dn5EerZyCg5s0dPvvkLtftaw9rTEjN157p7lZMxJUI9AwAAAAAAAABgaAiDMDCWJfef/p/czzzW7Sr/okvVdvc/SQlJEejYyLBtW+8deFkvbfutbNsOu27qxFm6Y809SopPiVDvAAAAAAAAAAAYOsKgGObcvEnO15+V4hMUmF4ka3qRAtNnS0mDDDXaW+X55ffk3PZWt6u8131M3tv/VjIdw+pra3uzjlUc1JHSvSqvOamAFRjW/gYrEPCrur6sW/vSwtW6cdWn5HS4xrQ/AAAAAAAAAACMFMKgGGWUn1Lcg/8qw7YkSc4d74SusybmBcOhGUXB/0+bKcXF97yfc5Xy/OQf5Dh1NKzddrrU/tdfkX/1B4fUP8uyVHr2mErK9upo2T6dqT4mq6Ov44FhGLpu+R1aNfdaGYYR6e4AAAAAAAAAADBkhEExyrnljVAQ1JVZVSazqkzavEmSZBumrPypHTOHimTNmC1rcoHM48Xy/Mc3ZTbUht3eSklX2z33y5q1YFB9qm8+p5LSvTpSuk9Hy/erzdsytAc3yuJc8frYlZ/XrEmLIt0VAAAAAAAAAACGjTAoRjn3bBnwtoZtyXHmuBxnjsv19ouSgjN/ZFsyAuHl2gJTCtR273dlZ+b0u1+vv10nKg7pSOk+lZTt1dn68sE9iAjITM3Vx9d8URPT8iLdFQAAAAAAAAAARgRhUCxqapB59EBYk+/ya2WeOiKz9LgMq/9ybIbf163Nv2y12u66T/Ik9Hgb27ZVUXtaR8v2qaR0r05WHlbA8g+421lpeZqZt0AFefOUFJ824NuNFIfpUGZqjhwmHwsAAAAAAAAAQOzgrHcMcu7fHlYiLjBputrvui94ob1N5skSOY4fknm8WI5jh2RWnul3n96bNsj74U9LphnW3tTaoKNl+3Sk47+m1voB9zM+LlEFufNUmL9AhXnzlZqYMeDbAgAAAAAAAACAgSEMikGOPZvDLgcWrrxwIc4ja9aC8PV+mhvlOFEs81hxR0h0SGZNtSTJjvOo/dP/R/5V6yRJ/oBfp6tKVFK2V0fL9qns3MkB98s0TE3OKlRB/nzNzJuvvAnTZXYJlwAAAAAAAAAAwMgiDIo1liXH3vD1ggILVvR9m8RkBeYtV2Decp0vDmfUnZNRVapA9mSdU7uOHHxFR0r36XjFQXn97QPuTnpSlgrz56swb4Fm5M6Rx91ziTkAAAAAAAAAADA6CINijHn6qMz6GklSRYJL2/NT1dJwQNpyaND7avO16tie/1Fd09kB38bt9Gh6bpFm5i1QYf58ZSRnyzCMQd83AAAAAAAAAAAYGYRBMcaxJzgraMfEBD1RNEE+hykdemVU7zNvwjQV5s1XYf4CTc4qlNPB2woAAAAAAAAAgPGCs/Yxxtzzvl6YnqZXpqWO2n0kxaeGwp/CvHlK9KSM2n0BAAAAAAAAAIDhIQyKIe31Z/VkXIX25Y9sEOQ0XZqaPatj7Z/5yk6fTOk3AAAAAAAAAACiBGFQjKhrOqtfv/CvqshMCGt3mE59YP4HFR+XNOh9GjKUlZqrqTmz5XbGjVRXAQAAAAAAAADAGCIMigEnKw/rt6//h5rbG8Pak+TUx6+7T1MmFkaoZwAAAAAAAAAAINIIg6LcjpK39Mx7/62AFQhrz2/06s7L/1rJBEEAAAAAAAAAAFzUCIOilGVZ2rj9Sb27/6Vu1y2satbHjzbJf/flEegZAAAAAAAAAAAYTwiDolCbt0W/e/NBlZTu6XbdNcfrdO2JelmLV8nvckegdwAAAAAAAAAAYDwhDIoy5xoq9evXfqLq+rKwdqctfeJAtZZUtUiSvAtXRqJ7AAAAAAAAAABgnCEMiiLHyg/oiTf+U63tzWHtKfFp+uw7xZpS3xZqCxAGAQAAAAAAAAAAEQZFjeLy7dp6fKMs2wprn5Q5Q5+ccKmyX9gdarNyJ8vOyh3rLgIAAAAAAAAAgHHIjHQH0LeA5dez7/+vNh97sVsQtHDGKn3muvuUcXBvWLt/wYqx7CIAAAAAAAAAABjHmBk0zh0t268th17r1r5+6W26YsENMiQ59m4Ou44ScQAAAAAAAAAA4DxmBo1zsyYt0uXzrgtddjvj9Im19+rKhTfKMAyZpSdk1lSHrrfdcQrMXhSJrgIAAAAAAAAAgHGImUFR4Jplt+tE2RE1e+t057p7lZMxJXSdY0+XWUFzlkjuuLHuIgAAAAAAAAAAGKcIg6KAaZpaPevDmjptipLiU8Kuc+zdEnY5wHpBAAAAAAAAAACgE8rERQm3M65bEKTWFjmK94Q1+RcSBgEAAAAAAAAAgAsIg6KY4+BOGQF/6LKVnS87e1IEewQAAAAAAAAAAMYbwqAo5uyyXpB/4coI9QQAAAAAAAAAAIxXhEHRyrbl2BseBrFeEAAAAAAAAAAA6IowKEoZ5adknq0MXbZdLgWKFkeuQwAAAAAAAAAAYFwiDIpSzj1bwi4HihZLcZ7IdAYAAAAAAAAAAIxbhEFRytFlvaAA6wUBAAAAAAAAAIAeEAZFo/ZWOYp3hzX5CYMAAAAAAAAAAEAPCIOikOPgThl+X+iylZUrO3tSBHsEAAAAAAAAAADGK8KgKOTosl6Qf+FKyTAi1BsAAAAAAAAAADCeEQZFG9uWs0sYFFi4IkKdAQAAAAAAAAAA4x1hUJQxKs/IrC4LXbadLgXmLIlgjwAAAAAAAAAAwHhGGBRlnHs2h10OzF4oxcVHqDcAAAAAAAAAAGC8IwyKMl3XCwosXBmhngAAAAAAAAAAgGhAGBRNvO1yHNoV1uQnDAIAAAAAAAAAAH0gDIoijoO7ZPi8octWZrbs3CkR7BEAAAAAAAAAABjvCIOiiGNvl/WCFqyQDCNCvQEAAAAAAAAAANGAMCiKOPeEh0GUiAMAAAAAAAAAAP1xDmQjy7L00EMP6ZlnnlFra6sWLVqk++67T7m5uT1u/9JLL+l//ud/VFFRocTERK1du1Z/93d/J7fbPaKdv5i4a6pkVpaGLtsOpwJzlkawRwAAAAAAAAAAIBoMaGbQY489po0bN+rhhx/Wiy++qJycHH31q1+VZVndtj18+LC+9a1v6XOf+5w2bdqkX/3qV3r//ff16KOPjnjnLyYpR/eFXQ7MXijFJ0SoNwAAAAAAAAAAIFoMKAx66qmntGHDBk2dOlUJCQm65557dPLkSe3atavbtqWlpUpJSdG6detkGIZyc3N1+eWX6/DhwyPd94tKtzBowYoI9QQAAAAAAAAAAESTfsOgpqYmlZeXa+7cuaG25ORkTZo0SSUlJd22X7VqlfLy8vTyyy8rEAjozJkzevvtt7VmzZqR7fnFxNuu5BPFYU2BhYRBAAAAAAAAAACgf/2uGdTc3CxJSkpKCmtPTk5WU1NTt+09Ho9uuukmff/739e//Mu/KBAI6Prrr9eHPvShPu+np2AJQclH96vQ7w1d9ianq7jFL/GcARiHOJ4DiAYcqwBEA45VAKIBxyoA0eBiOFbNnDmzz+v7DYMSExMlqVvw09jY2C0gkqTnnntOv/jFL/SjH/1IixYtUk1Njb773e/q29/+tu6///4hd/Ri5t6yMeyysfRyzZw1K0K9AYDelZSUcDwHMO5xrAIQDThWAYgGHKsARAOOVUH9lolLSkpSbm6uDh48GGprampSaWlpj0/gwYMHtWzZMi1ZskSmaSozM1Mf/vCH9dZbb41szy8izr2bwy77KREHAAAAAAAAAAAGqN8wSJJuvfVWPf744zp58qRaW1v1s5/9TFOmTNHixYu7bbt48WJt375de/bskW3bqqmp0Z/+9CcVFRWNdN8vCkZ1uczy06HLtsOhwLxlEewRAAAAAAAAAACIJv2WiZOkDRs2qKmpSXfddZdaW1u1aNEiPfDAAzJNUzt37tSXvvQlPfnkk8rJydHVV1+tc+fO6Tvf+Y6qq6vl8Xi0dOlSfeMb3xjtxxKTHHu2hF22Zs6X4hMj1BsAAAAAAAAAABBtBhQGmaapL3zhC/rCF77Q7bolS5bozTffDGu74447dMcdd4xMDy9yzj1dS8StjFBPAAAAAAAAAABANBpQmThEiM8rx8EdYU2BBYRBAAAAAAAAAABg4AiDxjO/X96bNihQtEi26ZCVlilr8oxI9woAAAAAAAAAAESRAZWJQ4TEJ8h3w53y3XCnju7drZnJ8ZJhRLpXAAAAAAAAAAAgihAGRQnLkyBr2sxIdwMAAAAAAAAAAEQZysQBAAAAAAAAAADEMMIgAAAAAAAAAACAGEYYBAAAAAAAAAAAEMMIgwAAAAAAAAAAAGIYYRAAAAAAAAAAAEAMIwwCAAAAAAAAAACIYYRBAAAAAAAAAAAAMYwwCAAAAAAAAAAAIIYRBgEAAAAAAAAAAMQwwiAAAAAAAAAAAIAYRhgEAAAAAAAAAAAQwwiDAAAAAAAAAAAAYhhhEAAAAAAAAAAAQAwjDAIAAAAAAAAAAIhhhEEAAAAAAAAAAAAxjDAIAAAAAAAAAAAghhEGAQAAAAAAAAAAxDDCIAAAAAAAAAAAgBhGGAQAAAAAAAAAABDDCIMAAAAAAAAAAABiGGEQAAAAAAAAAABADCMMAgAAAAAAAAAAiGGEQQAAAAAAAAAAADGMMAgAAAAAAAAAACCGEQYBAAAAAAAAAADEMMIgAAAAAAAAAACAGEYYBAAAAAAAAAAAEMMIgwAAAAAAAAAAAGIYYRAAAAAAAAAAAEAMIwwCAAAAAAAAAACIYYRBAAAAAAAAAAAAMYwwCAAAAAAAAAAAIIYRBgEAAAAAAAAAAMQwwiAAAAAAAAAAAIAYRhgEAAAAAAAAAAAQwwiDAAAAAAAAAAAAYhhhEAAAAAAAAAAAQAwjDAIAAAAAAAAAAIhhhEEAAAAAAAAAAAAxjDAIAAAAAAAAAAAghhEGAQAAAAAAAAAAxDDCIAAAAAAAAAAAgBhGGAQAAAAAAAAAABDDCIMAAAAAAAAAAABiGGEQAAAAAAAAAABADCMMAgAAAAAAAAAAiGGEQQAAAAAAAAAAADGMMAgAAAAAAAAAACCGEQYBAAAAAAAAAADEMMIgAAAAAAAAAACAGEYYBAAAAAAAAAAAEMMIgwAAAAAAAAAAAGIYYRAAAAAAAAAAAEAMIwwCAAAAAAAAAACIYYRBAAAAAAAAAAAAMYwwCAAAAAAAAAAAIIYRBgEAAAAAAAAAAMQwwiAAAAAAAAAAAIAYRhgEAAAAAAAAAAAQwwiDAAAAAAAAAAAAYhhhEAAAAAAAAAAAQAwjDAIAAAAAAAAAAIhhhEEAAAAAAAAAAAAxjDAIAAAAAAAAAAAghhEGAQAAAAAAAAAAxDDCIAAAAAAAAAAAgBhGGAQAAAAAAAAAABDDCIMAAAAAAAAAAABiGGEQAAAAAAAAAABADCMMAgAAAAAAAAAAiGGEQQAAAAAAAAAAADGMMAgAAAAAAAAAACCGOQeykWVZeuihh/TMM8+otbVVixYt0n333afc3Nwet29ra9NDDz2kV199VQ0NDcrMzNTXvvY1XXbZZSPaeQAAAAAAAAAAAPRtQGHQY489po0bN+rhhx9WVlaWfvKTn+irX/2qHn/8cZlm+OQi27b19a9/XZL08MMPKz8/X5WVlQoEAiPfewAAAAAAAAAAAPRpQGHQU089pQ0bNmjq1KmSpHvuuUfXXXeddu3apaVLl4Ztu3nzZu3cuVPPPvus0tLSJEnZ2dkj22sAAAAAAAAAAAAMSL9rBjU1Nam8vFxz584NtSUnJ2vSpEkqKSnptv22bduUl5enRx99VNddd51uvvlm/fCHP1RLS8vI9hwAAAAAAAAAAAD96ndmUHNzsyQpKSkprD05OVlNTU3dtq+rq9Px48e1cuVKPf3006qrq9PXv/51/fSnP9V9993X6/30FCwhHM8RgGjAsQpANOBYBSAacKwCEA04VgGIBhfDsWrmzJl9Xt9vGJSYmChJ3YKfxsbGbgGRJCUkJMjhcOgLX/iC4uLilJOTo7/6q7/SAw880GcY1F9HL3YlJSU8RwDGPY5VAKIBxyoA0YBjFYBowLEKQDTgWBXUb5m4pKQk5ebm6uDBg6G2pqYmlZaW9vgEFhUVSZIMwwi1df43AAAAAAAAAAAAxk6/YZAk3XrrrXr88cd18uRJtba26mc/+5mmTJmixYsXd9v2qquuUkZGhh588EF5vV5VV1frscce09q1a0e67wAAAAAAAAAAAOjHgMKgDRs2aP369brrrrt07bXXqqysTA888IBM09TOnTt15ZVXqqKiQlKwTNx//Md/6NChQ7r66qv16U9/WgsXLtQXv/jFUX0gAAAAAAAAAAAA6M6oq6uzI90J9I+6hgCiAccqANGAYxWAaMCxCkA04FgFIBpwrAoa0MwgAAAAAAAAAAAARCfCIAAAAAAAAAAAgBhGGAQAAAAAAAAAABDDCIMAAAAAAAAAAABiGGEQAAAAAAAAAABADCMMAgAAAAAAAAAAiGGEQQAAAAAAAAAAADGMMAgAAAAAAAAAACCGEQYBAAAAAAAAAADEMMIgAAAAAAAAAACAGEYYBAAAAAAAAAAAEMMIgwAAAAAAAAAAAGIYYRAAAAAAAAAAAEAMIwwCAAAAAAAAAACIYYRBAAAAAAAAAAAAMYwwCAAAAAAAAAAAIIY5I90B9K7Fb2lLlVf7anx6/6RbE6pq9dPL0yPdLQAAAAAAAAAAEEUIg8axqlZLt2w813HJqdS6Vv3ksjQZhhHRfgEAAAAAAAAAgOhBmbhxbEqSQ0nOC8FPvddWaXMggj0CAAAAAAAAAADRhjBoHDMNQ3PTXWFtB2r9EeoNAAAAAAAAAACIRoRB49zc9PBKfvtrfRHqCQAAAAAAAAAAiEaEQePcvIyuM4MIgwAAAAAAAAAAwMARBo1zXcvE7a8hDAIAAAAAAAAAAANHGDTOzesSBh2u98sbsCPUGwAAAAAAAAAAEG0Ig8a5tDhT+QmO0GW/HQyEAAAAAAAAAAAABoIwKArMy3CGXWbdIAAAAAAAAAAAMFCEQVGAdYMAAAAAAAAAAMBQEQZFga7rBjEzCAAAAAAAAAAADBRhUBToOjPoQC1rBgEAAAAAAAAAgIEhDIoCM1Odchp26HJpS0B17VYEewQAAAAAAAAAAKIFYVAUcDsMTYu3w9r2UyoOAAAAAAAAAAAMAGFQlChIDJ8JtL+GMAgAAAAAAAAAAPSPMChKzOwSBh1gZhAAAAAAAAAAABgAwqAoUZjQZWYQYRAAAAAAAAAAABgAwqAoUZgYvmbQwVq/LNvuZWsAAAAAAAAAAIAgwqAoMdFtK9VthC43+W2dagpEsEcAAAAAAAAAACAaEAZFCcOQ5qW7wtr211AqDgAAAAAAAAAA9I0wKIp0C4NYNwgAAAAAAAAAAPSDMCiKzMsID4MO1Poj1BMAAAAAAAAAABAtCIOiyNx0Z9hlZgYBAAAAAAAAAID+EAZFkTldysQdbfCr1W9HqDcAAAAAAAAAACAaEAZFkWSXqalJjtBly5aK65gdBAAAAAAAAAAAekcYFGW6rhtEqTgAAAAAAAAAANAXwqAoM7dLqbgDtf4I9QQAAAAAAAAAAEQDwqAoMy/dGXaZmUEAAAAAAAAAAKAvhEFRZl63mUGEQQAAAAAAAAAAoHeEQVFmRopTcY4Ll6taLVW3BiLXIQAAAAAAAAAAMK4RBkUZp2moKI3ZQQAAAAAAAAAAYGAIg6LQ3C6l4vbV+iPUEwAAAAAAAAAAMN4RBkWheenOsMvMDAIAAAAAAAAAAL0hDIpC87rMDNpfQxgEAAAAAAAAAAB6RhgUheZlhIdBh+p8Clh2hHoDAAAAAAAAAADGM8KgKDQx3qFMz4WXri0gHWtk3SAAAAAAAAAAANAdYVCU6loq7kAtYRAAAAAAAAAAAOiOMChKzU13hl3ex7pBAAAAAAAAAACgB4RBUarrukEHagmDAAAAAAAAAABAd4RBUaprmbj9hEEAAAAAAAAAAKAHhEFRanaaU0anyycaA2ryWRHrDwAAAAAAAAAAGJ8Ig6JUgtNUQUr4ukGH6vwR6g0AAAAAAAAAABivCIOi2Nz08DBofw2l4gAAAAAAAAAAQDjCoCg2L4N1gwAAAAAAAAAAQN8Ig6LY3HTCIAAAAAAAAAAA0DfCoCg2v0sYdKDWJ9u2I9QbAAAAAAAAAAAwHhEGRbGpyQ4lOo3Q5dp2W+UtVgR7BAAAAAAAAAAAxhvCoChmGobmpDvD2g5QKg4AAAAAAAAAAHRCGBTlWDcIAAAAAAAAAAD0hTAoys0jDAIAAAAAAAAAAH0gDIpy3WYG1RAGAQAAAAAAAACACwiDoty8LmsGHa73y2fZEeoNAAAAAAAAAAAYbwiDolyGx6HchAsvo8+SSur9EewRAAAAAAAAAAAYTwiDYkDXUnEHWDcIAAAAAAAAAAB0IAyKAfMIgwAAAAAAAAAAQC8Ig2JA15lB+2sIgwAAAAAAAAAAQBBhUAyYl9ElDKplzSAAAAAAAAAAABBEGBQDZqU65TAuXD7THFBduxW5DgEAAAAAAAAAgHGDMCgGxDkMzUp1hrUdrKNUHAAAAAAAAAAAGGAYZFmWfvGLX+i6667TlVdeqS9+8YsqLy/v93YHDx7UqlWrdPfddw+7o+gb6wYBAAAAAAAAAICeDCgMeuyxx7Rx40Y9/PDDevHFF5WTk6OvfvWrsqzeS5G1t7fr/vvv19KlS0ess+hd13WDDrBuEAAAAAAAAAAA0ADDoKeeekobNmzQ1KlTlZCQoHvuuUcnT57Url27er3Ngw8+qEsuuUSLFi0aqb6iD3PTw8vE7a9lZhAAAAAAAAAAAJCc/W3Q1NSk8vJyzZ07N9SWnJysSZMmqaSkpMeZPzt27NBf/vIXPf744/rf//3fAXWkpKRkEN2+OPX1HCW2GZLiQ5f3nWvX4cMlMowx6BgAdMLxHEA04FgFIBpwrAIQDThWAYgGF8OxaubMmX1e328Y1NzcLElKSkoKa09OTlZTU1O37VtaWvSv//qv+qd/+id5PJ4R6+jFrqSkpM/nqNC2lbKnXA1eW5LUHDAUlztdU5P7fYkBYMT0d6wCgPGAYxWAaMCxCkA04FgFIBpwrArqt0xcYmKiJHULfhobG7sFRJL005/+VJdddhlrBY0xwzA0L73rukGUigMAAAAAAAAA4GLX77SRpKQk5ebm6uDBg6FScU1NTSotLe0xTXv//ffV2NiojRs3SpLa2trk9/t19dVX67//+7+Vn58/wg8B581Nd+m9Sm/o8v5avz44JYIdAgAAAAAAAAAAETegGmK33nqrHn/8cS1fvlwTJ07Uz372M02ZMkWLFy/utu1//dd/KRAIhC7/5je/0d69e/W9731PmZmZI9bxi47tl9V0QmbStF43mZse/nIyMwgAAAAAAAAAAAwoDNqwYYOampp01113qbW1VYsWLdIDDzwg0zS1c+dOfelLX9KTTz6pnJycboFPYmKi3G63srOzR+UBxDqr6bh85S8ru+wVtVW5FH/ZYzLMnl+2rmXi9tcQBgEAAAAAAAAAcLEbUBhkmqa+8IUv6Atf+EK365YsWaI333yz19veddddQ+/dRc4OeNW6/atSoEUOSbZXCpzbKmfWqh63n9MlDDrS4Fd7wFacwxiD3gIAAAAAAAAAgPHIjHQH0DvD4ZYz+8qwNn/5y71un+o2NTnJEbocsKXiOmYHAQAAAAAAAABwMSMMGuecudeGXQ6c2yLbW9vr9nO7loqr9Y9KvwAAAAAAAAAAQHQgDBrnzJTZMhKmXGiwA/JXbOp1+/np4ZX/DtQyMwgAAAAAAAAAgIsZYdA4ZxiGXHnXhLX5yjfKtu0et+82M6iGMAgAAAAAAAAAgIsZYVAUcOask93ppbKbT8lqPNzjtvMywsMgZgYBAAAAAAAAAHBxIwyKAoY7XW2eeWFt/rKNPW5bkOKUu9OrWtFq6VxbYDS7BwAAAAAAAAAAxjHCoCjRmnRp2GV/5RuyA23dtnOZhmandSkVV+sf1b4BAAAAAAAAAIDxizAoSrR55kmutAsNgRYFqt/pcdu56c6wy6wbBAAAAAAAAADAxYswKFoYDrly14U1+cpf6XHT+emsGwQAAAAAAAAAAIIIg6KIM/easMtW7S5ZrRXdtpub0bVMHGEQAAAAAAAAAAAXK8KgKGImTpWZUhTW5u9hdtDcLjODDtX5FbDsUe0bAAAAAAAAAAAYnwiDokzX2UH+8ldk21ZYW068qYy4Cy9ti9/WicbAmPQPAAAAAAAAAACML4RBUcaZfaVkxoUu2+1Vsmp3hW1jGIbmpjvD2igVBwAAAAAAAADAxYkwKMoYzkQ5si4Pa/OVv9xtu3nprBsEAAAAAAAAAAAIg6KSK+/asMuB6ndk+xrD2uZlhIdBz5xoZd0gAAAAAAAAAAAuQoRBUchMWyDDk32hwfLJX/lm2Darc+JkdLp8sM6vJ462jE0HAQAAAAAAAADAuEEYFIUMw5Qz95qwNn/5xrDL01Ocur0gPqzt/+5oVKuf2UEAAAAAAAAAAFxMCIOilDNnvdRp7o/VWCKr6XjYNv+wNEXuTq9waUtAvzrYNEY9BAAAAAAAAAAA4wFhUJQy47Nlpi8Oa/OVvxx2eUqSU38zJyms7Ud7GlXXbo129wAAAAAAAAAAwDhBGBTFXF1LxVVskm35wtq+ujBJKe4LM4jqvbZ+vKdxTPoHAAAAAAAAAAAijzAoijmyLpOcnWb++OoVOLs5bJsMj0NfXpAc1vbQwSadafKPRRcBAAAAAAAAAECEEQZFMcMRJ2f2VWFt/vJXum33t3MTlZtw4aVuD0jf28XsIAAAAAAAAAAALgaEQVHO2aVUXODcVlnt58LaEpym7luSEtb22yMtOlAbXlIOAAAAAAAAAADEHsKgKGcmz5SROK1TiyV/xWvdtvtEYYJmpzovbGVL929vGP0OAgAAAAAAAACAiCIMinKGYciVd21Ym7/8Zdm2HdbmNA3987Lw2UEvnW7TuxXto95HAAAAAAAAAAAQOYRBMcCZvUYyHKHLdssZWQ0Hu233oSkerZzoDmv71raGbsERAAAAAAAAAACIHYRBMcBwp8mReWlYm79sY/ftDEPfWh4+O2hLtVfPnWob1f4BAAAAAAAAAIDIIQyKEc7ca8Iu+6vekh3oHvKsyo7TByd7wtru394gv8XsIAAAAAAAAAAAYhFhUIxwZCyX4c640BBolb/q7R63/ZflKTKNC5dL6v36dUnLKPcQAAAAAAAAAABEAmFQjDBMh5w568Pa/OUv97htUZpLdxYmhLV9b2eDWvzWqPUPAAAAAAAAAABEBmFQDHHmXh122arbK6ulrMdtv7EkRR7HhcsVrZYe3N88mt0DAAAAAAAAAAARQBgUQ8zEyTJT54a19TY7KD/RobvnJoW1/XRvo861BUatfwAAAAAAAAAAYOwRBsUYZ+41YZf9Fa/KtnsOeL60IFlp7guLBzX4bP1oT+Oo9g8AAAAAAAAAAIwtwqAY45x4hWTGhS7b7WcVqNnZ47Zpcaa+uig5rO2Rg8062egf1T4CAAAAAAAAAICxQxgUYwxngpwTV4e19VYqTpL+pihJkxIvLB7ktaT/u7Nh1PoHAAAAAAAAAADGFmFQDHLmXht2OVD9nmxfzwGPx2noH5aEzw763dFW7a3xjVr/AAAAAAAAAADA2CEMikFm2nwZ8XkXGmyffKf/1Ov2txckaG6688Lmkr69rX4UewgAAAAAAAAAAMYKYVAMMgxDztxrwtp8J34r35lne9zeYRr61rLUsLZXS9v1Zln7qPURAAAAAAAAAACMDcKgGOXKu1ZyJoa1eQ//XL6yntcPunpSnC7PcYe1fWt7vWzbHrU+AgAAAAAAAACA0UcYFKMMd7o8878pmeEBj/fQT+SvfKP79oahby8Pnx2086xPfz7RNprdBAAAAAAAAAAAo4wwKIY5MhYrbsE3JcPZqdVS+4F/k7/63W7bL89y6+ZpnrC2+7fXy2cxOwgAAAAAAAAAgGhFGBTjnBMuUdy8b0hGp5fattS+73vyn9vWbftvLk2Rw7hw+VhjQP9T3DwGPQUAAAAAAAAAAKOBMOgi4Jz4AcXN+T+SOqU8tk/te+9XoHZ32LaFqS59alb4WkP/trtRzT5rDHoKAAAAAAAAAABGGmHQRcKZs0buoi+FN1pete35FwXqD4Q1f31xshKcF4KjqlZLDx1gdhAAAAAAAAAAANGIMOgi4sq7Vu5Z/194Y6BNbbu/qUBjSagpJ8Ghz88Nnx30072NqmkLjEU3AQAAAAAAAADACCIMusi4Jt0kV8Fnwxv9zWrb9Y+ymk6Emr64IFnpcRdmBzX4bP14b9MY9RIAAAAAAAAAAIwUwqCLkHvqR+Wadmd4o69Bbbvuk9VyRpKU6jb1lQXJYZv88mCTSpuZHQQAAAAAAAAAQDQhDLpIuaZ/Uq4pt4W12d5ate38hqzWCknS5+YkKS/hwlukPSB9f2fDmPYTAAAAAAAAAAAMD2HQRcowDLkKPitn/o1h7Xb72WAg1H5W8U5D31iSEnb9r4+06HCdbyy7CgAAAAAAAAAAhoEw6CJmGIbcsz4vZ+41Ye12W4Xadn5DtrdWnyhM0MxUZ+g6y5b+dQezgwAAAAAAAAAAiBaEQRc5wzDlLrpXjuyrwtrtljNq3XmfHIFG/dPS8NlBz5xs045q7xj2EgAAAAAAAAAADBVhEGQYDsXN+ZocmZeFtdvNJ9S26x91Y55fSzJdYdd9a3uDbNsey24CAAAAAAAAAIAhIAyCJMkwnYqb/w05MpaHtVuNJWrf9Q396yIrrP2t8na9UdY+ll0EAAAAAAAAAABDQBiEEMN0K27BN2WmLQprt5qOaknZP+kjeU1h7d/e3iCL2UEAAAAAAAAAAIxrhEEIYzji5Fn4LZmp88La7ZYz+lHCv2q6szLUtuucT8+caBvrLgIAAAAAAAAAgEEgDEI3hjNensXflSNjaVi7y1etF/J/oCLXmVDbd3bUy2cxOwgAAAAAAAAAgPGKMAg9MhwexS38lhxZl4e1p6hef8z+gRa7j0mSjjYE9OuSlkh0EQAAAAAAAAAADABhEHplmG7FzfsHOXPWh7WnOVr0ZPYDuizukCTpB7sa1OK3ItFFAAAAAAAAAADQD8Ig9MkwHXLP+Yqck24Ka08y2/VY9o91dfwulbdY+uWB5gj1EAAAAAAAAAAA9IUwCP0yDFPumZ+Xa9rHw9o9hl+/yvqFbk7YrB/vbVRdO7ODAAAAAAAAAAAYbwiDMCCGYcg941NyFXw2rN1lBPSfmb/SDe439NO9jRHqHQAAAAAAAAAA6A1hEAbFPfWjcs++R5IRajMNW/824X/lO/VHlbcEItc5AAAAAAAAAADQDWEQBs2Vf73i5n5dXd8+96X9Ttu3PiLbtiPTMQAAAAAAAAAA0A1hEIbEmbNGcQv/WQG5wtrXBP6k6n2/kG2zfhAAAAAAAAAAAOMBYRCGzJl5qeIWfUcttiesPbH6WXkP/li2Rck4AAAAAAAAAAAijTAIwxI3YbH25H1LtYGEsHZ/xStq3/ddWe01EeoZAAAAAAAAAACQCIMwAtYULdI/tP2DqgIpYe2Bs++q9b1Py3vkv2T7GiLUOwAAAAAAAAAALm6EQRg20zD0qaXzdWvFN3TGnxF+pdUu36nfq+Xdv5b3+K9l+5sj00kAAAAAAAAAAC5ShEEYEWvz4jQpc7I+XHGfDnnzum8QaJHv+GNqee/T8p36g+xA+9h3EgAAAAAAAACAixBhEEaEYRj6l+WpKgtk6IPl/6x/OHenKv2p3Tf0Nch75BE1vftpec88K9vyjX1nAQAAAAAAAAC4iBAGYcQsz3LrhikeeeXS/zSt1WVl39N3aj+q2kBit21NX418h3+u469/Rr/+y5/1v8UN2lHtVYvfikDPAQAAAAAAAACIXYRBGFHfWp6iZJchSWqz4/RQw3W6tPQHeqDuJjVanm7bZxvVusX7oBYcv1c/2vSiJj1WquV/rNR3dzTIb9lj3X0AAAAAAAAAAGIOYRBGVGGqS5tuzNJXFybp2klxmpToUJMdrx/X36xVpT/QL+qvU6vl7na7We5y/TLrQb2Q8x1N8e7QD3c36NvbGyLwCAAAAAAAAAAAiC3OSHcAsWdmqkvfXHZhvaC6dkv7a33aX5Oq/bWf0udrP6R11tO6PfFNuY1A2G0XxJ3SY9k/1Y72GfrVsfV6Lutq3TAteawfAgAAAAAAAAAAMYMwCKMuLc7U5TlxujwnrqMlXZb9f3Tq7J3yHf+1cppel6nwknBL447pwaxfqqLk96pov1HZ06+X4U7tvnMAAAAAAAAAANAnwiBEhGkYmpaVL2V9XVbzx+U9/pgCVW912y7HUSuV/q9ayp+QM3uNXJNvkZk0PQI9BgAAAAAAAAAgOg0oDLIsSw899JCeeeYZtba2atGiRbrvvvuUm5vbbdu9e/fq0Ucf1cGDB9Xe3q5JkybpM5/5jNasWTPinUdsMBMnyzP/HxRovF2+Y/+rwLnN3TeyvPKXb5S/fKPMtEVyTb5FjswVMgzH2HcYAAAAAAAAAIAoYg5ko8cee0wbN27Uww8/rBdffFE5OTn66le/Ksuyum3b0NCg9evX64knntBrr72mT3/60/rmN7+p/fv3j3jnEVscyQXyLPq2PCse1ltarxbL3eN2Vt1ute/9tlrf+6x8p/4o2988xj0FAAAAAAAAACB6DCgMeuqpp7RhwwZNnTpVCQkJuueee3Ty5Ent2rWr27aXX365rr/+eqWlpck0Ta1du1YzZszocVugJ46kqfrA6q/oY40/0f21H9Vp/4Qet7PbKuQ98iu1vHOn2ot/LqvlzBj3FAAAAAAAAACA8a/fMnFNTU0qLy/X3LlzQ23JycmaNGmSSkpKtHTp0j5vX11drRMnTmjmzJl9bldSUjLALl+8Lrbn6OvTDX1697V6pOFqXRO/S59NeVWrPIe7bxhok7/0WflLn1WbZ65aE5bK554qv3OiZAwo7wQwgi62YxWA6MSxCkA04FgFIBpwrAIQDS6GY1V/GUy/YVBzc7AEV1JSUlh7cnKympqa+rxtS0uL/v7v/16rV6/WihUrhtXRi11JSclF9xzNlPTT5Bb97Vu1erF1mV5sXaZ5rlP6l9zXdbn5rmT7u93G03ZAnrYDwQuOBJnJhXKkzJKZMktm8iwZnmwZhjG2DwS4iFyMxyoA0YdjFYBowLEKQDTgWAUgGnCsCuo3DEpMTJSkbsFPY2Njt4Cos6amJn35y1/WhAkT9K1vfWt4vcRF6/aCBG2u9OrR4mAoud83RR879Sn9YOlf6dMpb8pf+pxsb23PNw60yKrbI6tuz4U2V2owHEoOBkSOlFky3Olj8EgAAAAAAAAAAIiMfsOgpKQk5ebm6uDBg6FScU1NTSotLe01Taurq9MXv/hFTZkyRd/61rfkdPZ7N0CvvrcyVTvPebXzrC/Udt9OQ/Ouu02XX/YxBarelu/007Iaeygh15WvXoFzWxU4tzXUZMRlhWYOOSd+QGZC/mg8DAAAAAAAAAAAImJAC6rceuutevzxx3Xy5Em1trbqZz/7maZMmaLFixd32/bs2bO6++67NXPmTN1///0EQRi2OIeh/74qQ2nuC+XdLFv6zBs1qmwz5cxZK8/yn8qz7MdyTb1DZvpSydn7rLWu7PZqBarfke/Y/1Pr5r9Re/F/yvbWjcIjAQAAAAAAAABg7A0oqdmwYYOampp01113qbW1VYsWLdIDDzwg0zS1c+dOfelLX9KTTz6pnJwc/elPf9KxY8dUVlamV199NbSP6667Tvfdd9+oPRDEtqnJTj18RYZuf/VcqK2q1dJn3qjRM9dlymkacqTOkSN1jiTJtm3ZreWyGooVaDwsq6FEVmOJZLX3fUe2JX/pc/JXbJJr2sflmnSzDId7NB8aAAAAAAAAAACjyqirq7Mj3Qn0j0Wugv51e4Me2NMY1nbv/CR9+5LUfm9r2wHZzacVaDgsq/GwrIZiWU3HJdvf620MT7bcBZ+RY+IVMgyj1+0ABHGsAhANOFYBiAYcqwBEA45VAKIBx6ogarghqty3JFlbq716s/zCDJ+f7mvSioluXT81vs/bGoZDRtI0mUnTJF0jSbItr6ym47LqD8l35mnZreVht7HbKtW+/3syTz8t98y7QjOPAAAAAAAAAACIFgNaMwgYLxymoUeuTFdeQvhb9/N/qdXxht5n+PTGMN1ypMyWa/LNil/5sNyFf9PjekNWw0G1bf+y2vZ9T1ZrxZD7DwAAAAAAAADAWCMMQtTJinfo/12VIWenqm0NXlt/9XqNWv1Dr3pomG65pnxECaselXPSzZLh6LZNoOpNtW7+G3mPPCrb3zzk+wIAAAAAAAAAYKwQBiEqrcyO0/1d1gnaW+PT19+vG/a+DVeK4mZ9XvErH5Yjc1X3DSyffKd+p5b3PiPfmedkW4Fh3ycAAAAAAAAAAKOFMAhR6/NzE3XzNE9Y22MlLXrs8MjM2DETJsmz8F/kWfIDmUkF3Tfw1ct7+D/VuuXz8p/dItse+qwkAAAAAAAAAABGC2EQopZhGPrZ5ekqTHGGtd/zTp2uea5avzzQpOrW4c/acaQvkueSn8k956sy3BO6XW+3nFL7nn9W265/UKDx6LDvDwAAAAAAAACAkUQYhKiW4jb1P2syFO8wwtq3VHv19c31KnqyQh95+ax+e6RFDV5ryPdjGKZcuVcrftV/yTV9g2TGddvGqt2ptq1/p/YDD8hqqxryfQEAAAAAAAAAMJKc/W8SOX6/X83NI1PyK9p5PB7V19dHuhsR5XQ6lZiY2K19XoZLP74sTXe/XdvtuoAtvVbartdK2+VxSNdNjtdtM+J19SSP4roESANhODxyT79Tzrzr5Dv2P/KXvyKpc3k4W/6KV+WvelOuSR+Wa9rtMpzd+wwAAAAAAAAAwFgZt2GQ3+9XY2Oj0tLSZBiDP2kfa+Li4uTxePrfMIY1Nzervb1dcXHdZ+XcUZigjDhT/76nUe9XeXu8fVtAevpEq54+0apUt6GbpsbrthkJ+kCOWw5zcO8xM26C4uZ8Rc5JN8t75FeyaneFb2D55Dv1O/nKX5J72ifkzL9ehuka1H0AAAAAAAAAADASxm0Y1NzcTBCEMAkJCWpoaOgxDJKkayZ7dM1kj042+vXU8Vb9/liLDtT6e9y23mvrsZIWPVbSopx4U7fOiNfHZiRo0QTXoN5zjuQCeRZ/T4GabfIe+S/ZzSfCN/A1yFvykHxn/ix3waflyFrNexoAAAAAAAAAMKbG9ZpBnDRHZwN9P0xNdurLC5P17i3ZeufmifrKwiRNTnL0un1Fq6Vf7G/WVc9W66pnq/VaaZts2+51+5765ZxwieJX/Fzuoi/JcGd028ZuLVf7vv+rtu1fVqBu34D3DQAAAAAAAADAcI3rMAgYrnkZLv3zslTtuS1bGz+Uqb8pStSEuN7f9rvP+fSRl8/pxpfOamsv5eZ6YxgOufKuU/yqR+Wa/leSI77bNlbDIbXt+Jra9twvq/n0oB8PAAAAAAAAAACDRRiEi4JhGFqZHacfrkrToTty9IerJ+j2gnglOXuebfSXCq+ufr5an3jtnA7W+gZ3Xw6P3NM/oYRVj8qZf4NkdP+YBc6+q9Ytf6v24v+U7a0d0mMCAAAAAAAAAGAgCINGyN13361f/vKXke4GBsBlGlo/yaOHr8jQ4Y/n6P9dla5rJ/W8DtELp9p02dNVuvutGp1s7Hn9od4Y7nTFzf47xa94WI7My7pvYFvylz6nlvc+o/bDDylQt1+2bQ3lIQEAAAAAAAAA0CvCIFzUEpymPjw9QU9enak3bszS2rzuoZAt6YmjrVr+VKX+/v06VbcGBnUfZuJkeRb+szxLH5CZUtR9g0Cr/GeeVtuOr6r1nQ1qP/wLBWr3yrYHdz8AAAAAAAAAAPSEMAjosDjz/2/vvuPjqO/8j7+mbN9Vr5abXLGNCw4Y00IPtgnVSUj4US4hcE4lgZAjcS7ccVxycCSEkgAh9UIKAQIxppqWQmih27jIvUm21aXtM/P9/TG7K8mSbclWtT/Px2M9ZdvsejUrzXs+n6+XP51TwrIFJRxb6ul2fdqB+1dHmfPILv777VZaUn2r4jEKjsb/kTvwHf1ttEBlj7dRqQas7ctIvHMD8VcuI7n2HuzGd1GOBENCCCGEEEIIIYQQQgghDo451BvQVwW/3DEoz9P82aqDvu+GDRv40Y9+xOrVqwkGg5x55pksWbIEn8+HUoqf/vSnPPHEE7S3txMOh1m0aBFf/OIXSafT/PCHP+Sll14ikUiQn5/PpZdeyiWXXNKPr0wcyEcrfaw4t5Qntya45e1W1jR3bQ8XtRT/+14bP18T5euzwlx9VBj/PsYe2pumaZhlH8UoOQFrx5OkNv8O0q093lalmrB2LMfasRw8+ZilJ2KWnYJeMAtNH3E/ukIIIYQQQgghhBBCCCGGiBxR7mft7e18+ctf5rzzzuP222+noaGBG264gXQ6zTe+8Q3eeOMNnnjiCX72s59RUVFBS0sLW7ZsAeDJJ5/kgw8+4A9/+AMFBQXU19dTX18/xK/oyKRpGh8fF2DhGD8PbYjx/Xfb2NbetTqnMenw72+2ct+qKP92TIRZRR6StiLlQMpR7rzdad7Za9k+A8d3IlM973KK503y298EO9HzBqVbsHY+jbXzaTAjmKUnYJSdglE4B03vXsUkhBBCCCGEEEIIIYQQQmRJGNTPXnnlFQD+9V//FcMwGDVqFEuWLOHb3/42119/PR6Ph2QyycaNGykoKCA/P59Zs2YBYJom8XicjRs3MmvWLEpKSigpKRnKl3PEM3SNSyeHWDwhyC/XRrn9vTbqE13bw+2I2Xz1leZDeJYZwAzOqvws/zlxPRNTr2LXvw52rOebW21Ytc9h1T4HZggjbxp6ZBJ63mT0yBQ0Xwma1rtKJSGEEEIIIYQQQgghhBCHPwmD+tmuXbuorKzEMIzcujFjxpBMJmlqamLu3Ll85Stf4de//jVLly5l6tSpfO5zn2PevHksXLiQ5uZm7r77bjZv3szs2bP5whe+wNSpU4fwFQkAn6GxZHqY/zc5yL2r2rl7ZTttadWvz/F8reL52omcWjmdb83+Esd6VmHv/htW/Wtgtfd8JyuK3fhP7MZ/dqzz5GNEJncKiCaj+UolIBJCCCGEEEIIIYQQQogj1IgLgw5lLJ/BUF5eTm1tLY7joOs6ANu3b8fn81FYWAjA+eefz/nnn08qleLhhx/m+uuvZ8WKFfj9fi677DIuu+wyYrEY999/PzfccAPLli0bypckOol4dL45J4+rjgpxx/vtPLCmnaR94Pv1xV9qk/ylNsmplRP5tzlzOOGoa7Gb3nODoT3/AKtt/w+QbpGASAghhBBCCCGEEEIIIUTOiAuDhruTTjqJO+64g5/+9Kd87nOfo6Ghgfvvv5/zzz8fTdNYtWoVyWSS6dOn4/P5CIVCgDtGzZtvvkkoFGLy5Ml4vV6CwWAuUBLDS7Hf4JZ5+SyZHuKule28tisFgM8Aj67hMzS8hoZPB6+h4dW1Ltf5dA1vZvmlnUn+Wpvs9hzZUOijlT5unDOTE6cdi3fqV3Ca38fa/XesPa9AuqV3G7yvgCjvKPT8o9xp3lQ0M9gfb48QQgghhBBCCCGEEEKIYUTCoH4WDoe55557uOOOO1i0aBGBQIAzzjiDL3zhCwDEYjHuvvtutm7diqZpjB07lttuuw2fz0dTUxM/+MEPqK2txTRNJk2axPe+970hfkVif0aHTW6bX3BIj/H1WRFeqUty67ttPYZCf611w6KPVvr4tzkRTqqYi1E0F+/UL6Gi27Db1uO01WQuG8Dp/hg9SrdgN7yO3fA6aQA0tNA4jPxp6HnTMPKPQguORtMkkBRCCCGEEEIIIYQQQoiRTGtubu7fgU/6SUtLC/n5+UO9GcNGIpHA7/cP9WYMucP9c7G/UCjrlAovNx6Tx0kVvm7XKWUfWkC0NzOEkTcVPW8aev40jLypaJ7IwT2WOCLU1NQwefLkod4MIYTYL9lXCSFGAtlXCSFGAtlXCSFGAtlXuaQySIhh5KQKH8sW+PYbCv2tLsXfnq7vMRTSNAMtPB49PB4qzwIyAVFsO3ZrTd8DIiuK3fg2duPbHc8RHIORPw1z1EKM/GmH/JqFEEIIIYQQQgghhBBCDCwJg4QYhrKh0D8yodBf9hMKnTbKx83H5jGr2NvjY2magRYahx4a1zUgim7FblmD07oau2UNKra1V9umYtuwYtuwap/DKD0Z78TPogerDv7FCiGEEEIIIYQQQgghhBhQEgYJMYydWOHjzwcIhV7emeTUZXv49KQg35mbR1XIOODjuhVE1ejhaqhaCIBKt2O3rsFpXYPTsga7dQ1Y7ft9HHvP34nXv4o5ahHe6v+H5i04qNcphBBCCCGEEEIIIYQQYuBIGCTECHCgUEgBv18f47FNMb40I8y1MyPkefU+PYfmCWMWHwvFx7qPqRxUbAd262qcTAWR074FcLreUdlYO57AqnsBz7hP4hlzEZoh41sJIYQQQgghhBBCCCHEcCFhkBAjSDYUenVXku+93crf6lJdrk/Y8IP32/n1uhg3zolw5dQQHl07qOfSNB0tNAY9NAYqPwaAsmLYzR+Q3vQgTltN1zvYMdIbf421fTmeCZdjVp6Nph24SkkIIYQQQgghhBBCCCHEwOpb6YAQYlg4odzHsgUl/PGsYo4q6J7p1iccvvFaCyc+vpuntsZRSvXL82pmELPkePzH3olvxrfQ/BXdbqNSDaTW/Ij4G1/Eqn+j355bCCGEEEIIIYQQQgghxMGRMEiIEUrTND42xs/fLyjjzhMLKAt0/3GuabG49IVGzn26nrf3pHp4lIN9bh2z/FQC83+Kd/K/ghnpdhsV3ULy/e+SeOdG7NZ1/fbcQgghhBBCCCGEEEIIIfpG2sQJMcKZusaVU0MsnhDgrpXt3LOynZjVtRrnH7tSnLF8D5+cEOA7c/MYF+ndj77lKHZEbba222xtt9jSbrO1zUIBp1T6OG9cgPwxF2FWnE16yx9Jb38MnHSXx3Ca3yPxz69ilJ+Gd8K/oAe6VxNlKSeFSreiUq2Qbnbn062oVAsq3QK6B6NgFkbRMTIukRBCCCGEEEIIIYQQQvSShEFCHCbCHp1vH5PHZ6eG+N7brfx2fQxnrw5tD2+M8+fNcZZMD3PdrAgRj8bOmJ0LedzQpyP42Rm1sffR5e2hDXGuf7WZc0b7+cSEIB8b/1kCoz9OeuP/YdW9AHS9o73rZeK7X8GsPAuMAKRbOgU9rW7YY8cP+DqtbY+5oVDhHIyS+RjF89D9pQf5rgkhhBBCCCGEEEIIIcThT8IgIQ4zlUGDu08uZMn0MDf9s4XndyS7XJ9y4K6V7TywOkraUViHMKRP0oZlWxIs25Igz6Nx3vgAn5rwZU4cfRH2xl9gN77V9Q4qjbXz6YN/wiwnjd3wJnbDmwDo4YkYJcdjlByPHpmMpkkHTCGEEEIIIYQQQgghhMiSMEiIw9SMIg+PfKyEl3Yk+Pd/trKysWv7tvi+Sn4OUmta8duaGL+tiVEeCHJx9Q38S/Vaxuz5Nap9Y78+196c9g047RtIb/4dmrcQo9gNhqSdnBBCCCGEEEIIIYQQQkgYdNhJp9N4PJ6h3gwxjJxe5ecvlT4e2hDjlrdb2Rlz+nT/soDO2LDB2LDJ2LDBuLDJjpjNIxtjbG6ze7zPrrjDvR9GuffD0UzK+w5Lq97mzPQfMNL1+38yTUfz5IMnD82Th+bJR/Pm5+adeC12/euoRN0+H0KlmrBqn8GqfQZ0L0bhbLedXNFcNF8Zmm706fWPJCrdht2yGqdtPegmRmQKet5UNDMw1JsmhBBCCCGEEEIIIYQYQiMuDApfedqgPE/7r1/u0+0ffvhhHnnkEXbt2kUoFOLUU0/lq1/9Kn6/H8uy+P3vf88TTzzB7t27ycvL4/LLL+eTn/wkAO+99x733XcfNTU1AEybNo27774bgHnz5nHvvfcyY8YMAHbu3MmFF17I448/zqhRo1i+fDkPPPAAn/70p/nd735HOp3mmWee4b777uO5556joaGB/Px8Fi1axDXXXIOuu+2zEokEP//5z3nhhRdobGykuLiYL33pSxx77LGce+65/PjHP2bWrFm513fTTTeh6zo33XTTob61YggYusalk0NcWB3g3lVR7lzZRmvKrQwq8XeEPePCBmMjHcHPmLBB0Oy55drSYyK8VZ/m4Q0x/rQpzp5EzyHT+lbFZ1uPwcfRfLH8Hc4u2s24gnzK8go6hT1u4IMZOmCLNzV5CSq6Bav+deyG13FaVrP3+EQ5TqpLOzmFhu4tQPMVo3mL0XxFaL4Sd+otRvMVo/uK3TBqmLeaU8pBRbdit67GaVmN3bIaFdvW5TZuLZiOHq5Gz5+GnncURv50tEAlmqYNxWYLIYQQQgghhBBCCCGGwIgLg4arkpISbr/9dkaPHs2WLVu4/vrr+cUvfsEXv/hF7r//fl588UVuueUWjjrqKJqbm9m5cycAGzZs4Etf+hLXXXcdd9xxB4Zh8Pbbb/fpuXfv3s3WrVv54x//mDvAO27cOO69917KyspYvXo11157LRUVFVx44YUA3HLLLezcuZM77riDcePGsWvXLlpbW8nLy+Pss8/msccey4VBra2tvPjii/zkJz/pvzdMDImgqXP97Ahfmxlme9SmxK8T8hxc6KFpGseWejm21Mt/z8vnr7VJHt4YZ/mWOG3p7uFMEg937JrHHbvc5YqAzkcrfZxS6eOjlT7GBXu3O9I0DS08Hm94PIy/BJVqxmr4J3b9a1iNb6HZ8X3fF4VKNaFSTcD6/TyJieYtyoRFxWj+MvTgGPTQOPTQWDRPpFfb2p+UFcVpXetW/rR8iN26BqxoL+7p5NrosWO5u8qTj5E/DT1/OkbeNPS8ydJOTwghhBBCCCGEEEKIw5iEQf3k9NNPz82PHz+exYsXs2LFCpRSPPzww/zHf/wH06ZNA6CwsJDCwkIAHn30UebPn8/FF1+cu//xxx/fp+fWNI2vfe1r+Hy+3LqFCxfm5qdPn86CBQt44403uPDCC2lqauK5557jwQcfZNy4cQCUl5dTXl4OwOLFi1myZAnXX3894XCYp556ijFjxjBz5sw+vitiuDJ0jXGR/vvxN3WNM6r8nFHl54cnFPDstgQPb4yxYnuC1D660tXFHf64Mc4fN7rhzbiwwUczwdAplT4qggdu56aUYnU0xPP1x7Ni+2ze2h3jI961nBV4j7MD7zHOc4C2dPt8YAuV3I1K7u7xas1bhJYJhvRO0/4IiZSdQlltkG7BbtuQqfr5EBXdwj4roPoq3YJd/xp2/Wtu9ZBmoIcnoOdPw8ibhhYoBycNykY5aVAWODaoNMqxMsvuVGVuR+Z2keYWUpsq0Awf6F7QfWi6FzLLmu4DIzvde523f16fEEIIIYQQQgghhBCiCwmD+skLL7zAb3/7W7Zt24ZlWViWRVFREc3NzcRisVzosrfa2lomTJhwSM9dXFzcJQgCeOSRR3jssceoq6tDKUUqlcqFObW1tQCMHTu2x8ebMWMG1dXVPP3003zyk5/k8ccf5xOf+MQhbaM4cgRMjQurA1xYHaA56bBsS5yHN8T4e11qv1HGlnab39TE+E1NDICp+WYuGDql0kehz61gak05vLwzyfM7ErywPcmOWOdxi0z+lpjB3xIzuKnpM0zx7OTswHucEXifiZ5dlBqt/fIaVaoRlWrEaXqny3rNW7hXSOQGRCrdlrtgtWbmWzut61jGSR7Cluno4XHoedPcFnmtq1GxHb14QTZOWw1OWw0Wyw7h+SECpNsO8s6efPTwRIzIRPTIRPTIJLTAqGHfsk8IIYQQQgghhBBCiOFuxIVBfR3LZzDs2rWLpUuX8t///d+ccsopeL1efve73/HQQw9RUFBAMBhk69atVFdXd7tvZWUlW7du3edjB4NB4vGOtlf19d0rHbLjAGW9//773HHHHdx9993MmjUL0zT5wQ9+kBuTqLKyEoCtW7cyZcqUHp/34osv5uGHH2bq1KnU1tayYMGCA78RQuylwKdzxZQQV0wJsSNq89imGC/vTPKPXSli1v6rXNa2WKxtsXhgTRQNmFnkIezReGN3igPcNUNjq1PF2sgEVMEn+eSHUQxlUWq0UGE0U240c9WEBB8tbkclG3GSDahkAyrV0Mv2a91lW9A5Te8e1P37zAy77d4yYwHpeVPRzGDXbUq3ZlrLueMKOW1rwU4Mzvb1VboFp+ltnKZOrTKNgDvmUWQSeniSGxKFxqLpnl4/rLJiqMRunGQ9KrHbvSTrcRK7UalGNDOCHqxCC45GD1a584FR0jpPCCGEEEIIIYQQQhw2RlwYNBzFYjEcx6GgoACv10tNTQ2PPPII4LZw+9SnPsU999xDRUUFU6ZMobm5mdraWqZPn87ixYu58sorefzxx1m4cCG6rvPOO+8wb948AKZNm8by5cuZOXMm0WiUBx544IDb097ejq7rFBYWYhgG77zzDs888wwTJ04E3DZ1H/vYx7jtttv47ne/y9ixY3NjBk2ePBmAc845h7vuuovbb7+ds88+m3A4PEDvnjhSVIUMvnx0hC8fHSFlK96qT/HX2iR/rU3y5u7UPtvJgdsc7f3GdK+eZ2KewVlVfs4e7eekCh8B0x1H6/gyH5//SyM77WJ22sUAPL0Kbpgd4dvHRHLjbQEoO4FKNqKS9ahkA058B050K050i1tpo6yDfh8OhRYai5E33W3nlj8NLTj6gFUzmicPs+R4KHHbTyrHxoludscdalmN07oaFa8djM0/OHYcp+VDnJYPO9ZpHrf6KpIJh8ITQTmo5B434EnuQSU65g8U7inAaV3dbb3mK0ULVqFnQiIt4M5r/nI0/cBtDIUQQgghhBBCCCGEGC4kDOoH1dXVLFmyhKVLl5JMJjn66KNZtGgRTzzxBADXXHMNoVCIpUuXsmfPHvLz87niiiuYPn06EydO5O677+bee+/l7rvvRtM0pk2blguDbrjhBm655RbOP/98qqqquPzyy3n99df3uz3z58/n/PPP5+qrr0YpxXHHHceCBQtylUEAS5cu5YEHHuCrX/0qTU1NlJSU8OUvfzkXBgUCARYuXMjDDz/MjTfeOEDvnDhSeQ2NE8p9nFDu49/mQMxyeGN3Rzj0dn0ap5fD4wQMjY9WejlrtJ+zqvxU5/W8W7tgfICAUcwVLzWQ6NRZ7n/fa6M97fC9efm5QEgz/GjBURAc1e1xlGOh4jtz4VBHSLS9f0IizQAzgubJQ/eXoOdNy4zlM7VfxiTSdAMj4rZi84w+DwCVau6oHmpbB3YSdBM0Ey0z7Vj2uNuoe9zlTtehmzTU76a4IIxyUuCkwE6inCQ4SZSdctvgOam95pPgJEDtJxHsTKVx2jfgtG+AAcyxVHKPGzDtXemlGWiBykwV0Vi3NWB4nDtv+Hp8LCGEEEIIIYQQQgghhpLW3NzcTyOS96+Wlhby8/OHejOGjUQigd8/uC2Lfve73/HUU0/x4IMPDurz7o98Lo4MLSmHV3cl+ctONxxa1dQ1ZJmSb3JmlY+zR/s5sdyH39T28Ujd/a02yWeeb6B9r15zV0wJcscJBRh67x+rMzckqs0ERG5IpGJbUXYKzeOGO5onAp48NDOcW9Y8eZnwx71gBLtUKY00NTU1uVC5L5SyUbEdOG0bcNrXY7dtwGlbD1b7AGzlQNHdkCg8LjNm1Hh33KjgaDdUE0IMGwe7rxJCiMEk+yohxEgg+yohxEgg+yqXHJ0SPWpububhhx/mqquuGupNEUegfK/OgjEBFowJAFCfsHl1V4qkrTi21Mv4yMHvuk6p9PH4ghIWP1dPS6ojEPq/dTGiacV9Hy3EcxCBkKabaKEx6KExwMkA7InbKKAsIC3FDkTTDLTQWPTQWOB0AJRS7lg/7RtyIZHTtgGV7D522v4f3IPmL0HzlaL7y9B8JWj+MvfiLYJ0M05sO05shxtIxXagEruAXlYq5Tio+A7s+A7sPf/o9PymOx5RKBMShcejh8ajBSoO2OZPCCGEEEIIIYQQQoj+IGGQ6Oauu+7ikUce4dRTT2XhwoVDvTlCUOI3OG9coN8e79hSL08uLOWiZ+vZk+g44P/opjgxS/HL04r6VG3UWWvK4fHNcX6/Psaru1IAnF3l48tHh/lopW9EV/0MNk3T0ALl6IFyKD0xt16lmt3KoWxIFN2CZvjcMX782cDHndd8pWjeggOGLkbR3C7Lykmh4nU4sR04se1uSBTfgYptR6Wa+vZClIWKbsaObqZTh0I0bzFG+amY5aejRybJZ0MIIYQQQgghhBBCDBhpEzdCDEWbuOFIPheiP9W0pLnwmQZ2xOwu60+t9PHbM4sIe3pXtWE7ir/UJvn9+hjLtySI2z3vVmcUmnxpRphPTAjiNQ7PA/9HQtmtsqI4sZ2o2PZMS8DNOO1bUImDH8BIC1Rhlp+GWXE6enB0P26tGGxKKVAOmi4VgYNJ2QlUqhmVbnGnqRZUugXSHfO59VYrab2QUPVizFELh/3/lUo1Y9W/imaGMIo+gmaGhnqThBCD5Ej4vUoIMfLJvkoIMRLIvsolYdAIIWGQSz4Xor9tabO44Nl6Nrd1DYSOL/Py0FnFFPj2HQita07z+/UxHtoQY2es9y3FKgI6V08L87mjQhTu5/FHoiP5y1VZcZzYVjcgat+Cim7GiW7pc1s7PTIZs/w0jPJT0X0lA7S1faOcFNhJd0yrYX7gfCgoO4Hd8E/s+lex6l8Hqx0tOBqjYCZ6/gx3Gigf6s08LChlYzf8E6vuRVR8Z0fo4yQP6vG04Fi8k67CKJ437KrzlJ0ive0x0lseAjvmrtRM9IJZmKUnYJTMR/eXDu1GCiEG1JH8e5U4fCg7hRPdApqBZgbQjAAYQdA9w+67Vxwc2VcJIUYC2Ve5JAwaISQMcsnnQgyE2pjNRc/Ws6bZ6rJ+VpGHP51TTIm/4+B3U9Lh0Y0xfr8+xlv16UN63qCpcemkIF+YHmZifv917WxNORgahHpZ2dSf5Mu1O5Vuw4ludSuIoltw2jfjtK0DO3GAe2ruQd+K0zBLT0bzRA5+Gxw7UyXRgrKiKKsdrGhmPgpWOyodRdlRVDoKdvY2MXfqZD/rGnjy0Lz5aJ58twWfp8Cdegs6rXOnmOHD9o98t1rjdez6f2A3vgNOar+313xl6AVuMGQUHI0WHHPYvjcDwUk2YO18Fmvn06jknn5/fL1wDt5JV2NEJvb7Y/eVUgp718ukNv4Sldi939vqkckYJSdglp6IFhonnykhDjPye5UY6ezWtSRX/nfP32eaAUYmHDIDaEYQDD+aEUQzAx3XeSIYRcdgRORnYbiSfZUQYiSQfZVLwqARQsIgl3wuxEBpSNhc/FwD7zV0DXim5ps88rFiVjW5VUBPb02QOkAR0OiQwacnBfnMxCD1CZsfr2pn+dYEzj72thqwcKyfL88Ic0K5t9cH8+KWYm1zmg+b0nzYZGWmaeri7gZWRwyOLvK4l0IPM4o8jAsbA3qwUL5ce0fZCez617F2vYTd8E9Q1v7voJkYxce5FUMlx6MZfndco1QLKtWUuWTm082Z5Y4p6VZgCL7uNSMTFuW7IZIngmZG0DLzeDLzndeZkWFbfeTEdrrVP3texWn5EOh9RWA3nnyMTDikFxyNHp6Apg3P1z1UlHJwmt4lveNJ7PpXQR3C+90rGmbFWXgmXjlkVXl2y4ekan6K07qmz/fV/JUYpSdglpyAXjBdPk9CHAbk9yoxkqV3Pktq7T2gDu0EuiyjaC6e8ZdiFBzdL48n+o/sq4QQI4Hsq1wSBo0QEga55HMhBlJLyuGSFQ28trvrGf4aBz6MHjI1zhvn5zOTQpxS6UXfK3DZ3GZx76p2HqyJEbX2/WjHlHj48oww548P4NHdx7AdxaY2q0vg82GTxcY2a58B077keTRmZMKhbFA0rdAkaPauiiiadtiTcKhPOOyJ213mGxIO0fY2xpTkk+/VKfDqFPh0Cryau+zLrtMIGJqcwZ6h0m1Ye/6OVfcyTvP7HPDTpvtA94DVPijbNySMYC4c0jx5HZVH3sJOF3cZT96AHfRWSuG0r8fe8yrWnn+gopsH5HkAMIIY+dPRC2a6Y0f5ywbuuYY5lWomXbsCa+dTqHgvx+LSPJ0q1vKhS5Vafi6U1DwFANR/8FNC0dfp8edN9+EZuxjP2E+6ZyYPAideS2rDL7B3/63nG5hhNG8BKra9dw/oyccsnodReiJG0TFohvwOKcRIJActxEiknDSpmvuxdiwfkMfXC2biHf8Z9MJj5O+JYUL2VUKIkUD2VS4Jg0YICYNc8rkQAy2advh/Lzby8s7ejT9xSoWXz0wKcv74AOFetGVrTjr8el2U+z9s3+84Q6NDBidWeFnXbLG22SJuD9yuWgMm5pm5cChoatQnbPbEs8GPO1+fcPYbZPWFRycXFuV7NQq8OtMLPXxmUpBphZ5+eY6RyEnWY+/6C9aul3HaaoZ6czpohhtCZcctGVZ09yC/twA8hZ1CIzcIIHuMQGX/UR0rcus6TZV7Gye2DXvPq71uSab5yzBKT3KrMsITsFvX4jR/gN2yyq3ycPpwVqymY5SegmfsYoy8Kb2/3wimlMJpWeVWAe3++/7PItZ9mOWnYpafgeYvc8MfI9inA0I1NTVMqDBIrX8Ap+mdHm+jeQvxTLgCs/JjAxc4pttJb/k96W3Len7NmoE5+ny84y9F80Rwotuw6l/F3vNqpnqoF/tk3YdROAs9/2iMghnokSlohrffX4sQov/JQQsx0jjJBpIr/ztTQd2VFhwDThJlxd12yYdYMaTnHYVn/GeG5bh/RxrZVwkhRgLZV7kkDBohJAxyyedCDIaEpfjsy408va3nMV0mRAw+MynIJZOCjA0f3Fg/KVvx+OY496xs5/3G/mmdkOXRwXKGpClYv5hf5uWKKUEurA70umLpcOREt2Htehlr18uo+I5Df8BMZYHbki0MZggtc8EIoXnC7nxufcdt0H1omoZyLFS6FdLNmTZ0LZm2dD3PY8cPfbuHMT08EaP0BIySE9HD1fs8EKHsFE7bOuzmlTjNK7FbPux1sKYXzMQz5mK3PaA2cD8PSqkhOZCi0u1YdS+Q3vkkKrp1v7fVQmPxjDoXs+JM9zN8CLJ/CCilsBveJLXhZ/t8fi00Hu+kz2MWH3tIz9mZciysnU+R2vRgpo1jd0bpiXgnXoUerOrxeifZiJ0bt+rd3h9U0zzoeZMx8o92x7HKn35IY5IJIQaOHLQQI4nd8iHJD25BpRq7XqH78E37Omb5aV1WKycNdhxlxcBOoOxYJiiKo+x47jq78S2c5g/2+bx6eIIbCpWeNKC/K4l9k32VEGIkkH2VS8KgYWDJkiXMnTuXa665Zp+3SSQSPP/88zzwwAP8+c9/HsStG16OpM+FGFppR/Hlvzfx0Ab3YHaeR+Oi6gCfmRTk+LLej+tzIEop/l6X4p5V7Ty7j/Bpf8aFDaYVephRaDK90MP0Qg+T8k3SjmJ1k8XKxrR7aUqzqjFNa3pY7vJ7lOfVuGRikCunhDi66MitFlJK4bTVYO16GXvXy53+wO5cEbN3G7WCrq3VPPlo+uC/h8pOZIKhlkyI1Iay2lDpNlS61V1ntWfm2zLLUYZvlKmjFxyNWXoiRsl89EDFQT2Kcmyc6EY3GGr+ALt5FaRb9nsfLViFZ8zFbhDSDy2/VKoZu/FtrIY3cZreRaVa3JZ72c9Nts2atyDTYq2gU7u1AndQ532FX44FVhRlRVFWu/t/nJuPotKZ5VQTdsOb4OynElPzYJSdjKfqXPT8Gf227937DwHl2Fi1z5Da+BtIN/d4H6PoI3gnfR49XH3Qz+uGT6+TWv+zfbZ80yOT8U66BqNwZu8fN3OwzNrzD/c97WMbSS00DiN/hls5lD8DzV8uZ1kLMQzIQQsxUqR3PElq3b3dxsHU/BX4Zn4XIzLhkB7fbvqA1Obf4zS9vc/baMGxeMd/GqPs1GE7/uThSvZVQoiRQPZVLgmDhgEJg3rvSPpciOHhzd0pYpbDvDIfAXNgD4zVtKT5yap2fr8+RsLuel2xT2d6oZkJftzQ56hCk0gvWtNlKaXY2m7nwqFsULSpzT7wnTO8OpT6DUoCOqV+nRK/TmnAoMyvU+zXqa3bha+wlOaUoiXp0JxyaE46tKSUO59ZTvVxHPhjSz1cOSXExdUBQn14zcNN2lG8uTvFlnab8RGD+X0MFpWyUckGNN0LnshhOUC8UnYmMMgGRC2ZaqOmzKW5y3TAx07SfRhFH8EoPQGzeJ7bkqyfKaVQsW3YTe+S3rF8/xUynjw8VR/HM/o8d8ykXj+HjdO6Drvhn9gNb2baEB7Cr4C6NzcOD7oHZUUzAVC72/rlEGmBSjxV52JWnD0g7/m+/hBQVoz0lj+S3vYncFI93FPHKJmP5it03wPdB4bf/Zk0fG4VXedp9jrdh0q3kNr4a5ymd3vcJs1XgmfCv2BWnHFIZzYrx8Jp/iDXTq63rQ733hY9fzpG/gz0gqPRw+MPy/2NEMOdHLQQw51yUqTW3Yu18+lu1xlFc/HN+Fa/Vp/aLWtIb/k9dv3r+7yNFqjEM+4S9wSaITgZ6kgk+yohxEgg+yrXiAuDoi8uGJTnD53xzKA8D0gY1BcSBokjQUPC5tltCVrTiqn5bsVPWUAfsLO029IOq5vSrGy0WN2cRikoDeiU+o3MVM8FQHkebb/b0ZsvV6UUCZtcMNScctjUavG79TH+XtfTwdcOEY/GJycEuWJKkDklw3/MC6UUNS0WL+1M8uLOJK/UJmnvNO7S1HyTq6eFuGRSsE/BnuignJRbfdQtLGrKVBl1pkGXz6/W8zpNA92LUTALo+iYfqnE6S2lHOzGt0hvfXSfoQEAugez/Aw8Yy9GD43r+bFSTVgNb2E3vInd+DZYbQOz0f1F0zFKTsRTtQi9cM6Atno50L7KSewhvfFXWHUvDNg25Bh+PGM/hWfsxf3+WVNKoaJbsFtWuW0KW1ahErv7/kBm2K0cKpyJXjATPTxJzroWYhDIQQsxnDnJepIf3JIZw64rz7hP4Zlw5YCdSGC3bSC95Q/uOIP7OLlF85XiGfdJzMoFMlbeAJN9lRBiJJB9levgBrsQXTzyyCM89NBDPPzww7l10WiURYsWcfvtt/PWW2/x3HPP0dDQQH5+PosWLeKaa65B1w/tIEcikeC+++7jxRdfJBaLMW3aNL7+9a8zYYJbgv3Pf/6Tu+66i23btmEYBuPHj+eHP/wheXl5rFixgp/97Gfs3r0b0zSZMmUKP/7xjw9pe4QQ/aPYb3Dp5NCgPV/EozOvzMe8Mt+gPJ+maQRMCJgGlUH3D8QTyn1cOjnE+pY0/7cuxm9rYjQku5cPtaUVv1gb5Rdro8wp9vAvU0MsnhAYVkFKfcLmLzuTvLQzycs7k2yP7rvyam2LxTdea+E/32rlM5OCXD0txOT8gTmDsT3tsLHVYkq+B/8AV7kNJk33ovlLwV861JvSLzRNxyw+DrP4OOy2DVjb/oS162VQe32OnDRW7bNYtc9iFB+HZ8zF6AWzcFrXZMKftzLVP8Of5ivFHLUQc9Q56L7iod4cAHR/Kb7pN2COuZBUzQM4ze8PxLNgjjoHT/Xl6L6iAXh8d3+rhcejh8fjqToXcIMup2UVdvMqnJZVOO2bOGCVmNWO3fA6dkPmTGwjgJE/Hb1gJkbBTPS8yW4F1CFSSrkVZqkmlJMAJw12EuWk3HmnY17ZSbd6y0mjnGTmeveEAr3gaMzyM9B0+VNHCCEGgt28kuTK/3ZPvunM8OObdj1m2SkD+vxGZCLG0UtxoltJb3kIa9dLoLr+7aCSe0it+wnprY/gO+prGEVzB3SbhBBCiJFA/kLqB+eccw533nkn7733HrNnzwZgxYoVFBUVceyxx1JfX8+9995LWVkZq1ev5tprr6WiooILL7zwkJ73zjvvZOXKldx///0UFRXxwAMP8JWvfIU//vGPhEIhbrrpJpYsWcLHP/5xLMti9erVeDweEokEN910E3feeSfHHXccyWSS998fiIMcQgjRN5PyPdx8XD7fmZvHU1sT/GpdlJd39jyeyLsNab72j2aWvtHCgjF+jinxMKfEy6wiD3newQuHEpbi9d1u+PPSziTvNfRyEPdO2tKKn66O8tPVUU4f5eOaaSE+NtqPoR98aGM7ivcb07y4I8mLOxO8sTtF2oEin851s8J8/qjwYRUKHY6MyESM6TfgmfhZrG3LSO98sodqJ9zwp+FN0D3uAfFe0sMTMYqPxSg+Dj0yCWW1Zyqr3Au5Fn3NqHR2fQsq3XSA59HBDKGZYTRPCMwwmhlCMzvPh8EMofvL0QumD9sWZEZkMv5jbsWuf43Uhp/vc5yfvtIL5+KbfPUhjT900M/tL0X3n5YbyFtZUeyW1e4YVi2rcFrX7qNFXid2HLvxLbeKDUD3oudNwyjMhkNHuW3yMpRSYMdQyUZUsgGVasBJNqJSmeVkQ2a+cf9jSPVW7XPuwb/JS+TgnxgUyk51qlBtcj/P2SpVx3L3fZ4wmhlB84Qzy5FOy6EB3w8qxwI7jrJi7tSOoax4Zj7e5To0A82T57b38uS582YEzZOX2Vb5/eFIpZTC2vEEqZr7u52oogVG4Z/5XfTw+EHbHj00Ft/0G/CM/3+kt/wRq+75buMWqcRuEu9+G7PyY3gnXd2vbeuEEEKIkUbCoH4QiUQ4/fTTWbZsWS4MWrZsGeeddx6aprFw4cLcbadPn86CBQt44403DikMchyH5cuX8z//8z9UVlYC8IUvfIHly5fzyiuv8LGPfQzTNNm+fTt79uyhrKyMWbNmAW5FkWmabN68mcmTJ1NQUMBxxx138G+AEEL0M6+hcWF1gAurA2xqtfhNTZQHa2LsjnevFopaikc3xXl0Uzy3bmKewZxiL7OLPczOTAt8hxYQOUrRkHDYEbXZGbPZ0GLxcm2Sf9SliNu977haFtA5qsDDK3VJerpbNlQaGzb4/FEhLpscpMjfuwNE29ut3P1f3pmksYfqqsakw3febOXeVVH+7ZgIl04KYh5C6CQGnu4rwTvpc3jGfwar9lnS2x5HJeq63/BAQZAZxiia6wZARR/pVoWjGX7wlRxwe9wD+/FcSIRjdwl9MAID2uJtsGmahll6AkbxcW4lTWI32Em3SmUfU5wUyk5kqlqSYKfASaKFxuIZuxij6NhhczBVM0OYxcdC8bEAKCeN07YhUz30AXbzygOPzeWkcJrfw2l+zw2HNA963mTQjFzY0y8hTx+o6FYS734bo+REvJOvRg9UDurzD2fKSbshhZ1A81dI+6T9UE4KFa/FSezJBJZ7Bz79OH5dNkQ3w+64gGaYgmiSRCqcqXhw3Gn2kllWey3n5p0UysoGPbE+nSywX5oOmWBI82Sn7sUNjgrQfMXovmI0X4mER4cRZadIrb0bq25Ft+uM4uPwTf83N9wcAnpwFL5pX8NTfSnprY+4Yxjt9Zm3ap/DbngT79SvYJaeOCTbKYQQQgy1ERcGDeZYPn1xwQUXcN1113H99ddTV1fH6tWrufXWWwG3jdxjjz1GXV0dSilSqRQzZ848pOdrbm4mmUxSVVWVW2cYBqNGjaKuzj1A9IMf/IBf/epXXHHFFYRCIRYsWMDnPvc5/H4/d955J7/73e+4//77KSsr48ILL+RTn/rUIW2TEEIMhOo8k+9+JJ9vHZPH01sT/N+6KC/sSO63qdGGVpsNrV0DovERg9nFnlxINKfYkwtZLEdRF3NDntpYJvCJZpdtdkTdabp7tnJAfgNOLPdxepWP00f5mVFoomkaO6M2v1wb5Vdro+xJdH/gre023/1nK997p5VPTHBbyM0u7nrArj3t8Epdihd3JHh5Z5K1LVa3x9mXHTGbr77SzF0ftPOduXmcP96PLgdrhjXNDOAZcyFm1XnY9f9wxxXqoU9/Z3pkcqfqn6n9Ms6LpmlgBtHMIDDqkB9vpNB0E6NwNsOzhqn/aLoHI/8ojPyj8IxdjFIOKroZu3kldtP7bjiUbt7/g6g0TsuHg7K9B2LX/4N445t4xizGM/7TgzoG2GBTdjJXYaVSDZlpY26arcYi3dpxJ81AC47BiExCj0xED09Ej0x0g90jhFIKlaxHxbbjxHbgxLbn5lViF3AQX/4Hw4qirCiKXblVQdwcZ1hRjls5mm45UINJl+5D85Wg+Yq7hETZZc1XguYt6rGto1JOrgVkR7vIVEdrSDu7PtUpEFOA45640GnZDco6r1OZ+yjc8QKNThfd/dnYa7nH9brXbZNp+N15w+e+5iFqU6mUcit2lO1WyCgHlI3KrcteOoWJdCx3XOzM++jk7pPe/PseW9B6xl+Kp/qyYXEiiO4vwzfli3jGXeK2j9v+BJ1boapUE8kPbsYq+yi+KV9E8xYM2bYKIYQQQ2HEhUHD1dy5cykpKWHFihVs3ryZ+fPnU1payvvvv88dd9zB3XffzaxZszBNkx/84AfU1BxaH/+CggJ8Ph87d+5k/PjxANi2TW1tLRUVFQBMmjSJW265BYB169bx1a9+lYqKCs477zyOOeYYjjnmGJRSvP3221x77bVMmDCBY4899pC2SwghBopH1zh/fIDzxwfY0mbxm5oYv62JUhvr3UGazW02m9ts/rw5kVs3OmRgK8WuuIPT++KeA5pV5OH0UT7OqPJxfJmvx3Zso0IGS+fm8Y3ZEZZtjvPA6ihv7Onemilhw4M1MR6siTG/zMvlU4Lsiju8uCPB65nWb71lamDt9TrXt1r8y8uNzC728N2P5HHGKF+/nsHrKEVdzKE55dCacmhNKVrTDi3Z+ZRDazozTTm07LXOUXBcmZeLqgN8fKy/11VShzNNNzDLTsEoPRmn5UPS2x7F3vMqoMCMYBR/BKPoWMziY+UghzhkmqajhSeghyfgGX2+e+A8th272Q2GnOYPUMn6/ntC3eceGDaDoHszB1e9HfO6B3Rfx7zhcw/EZtY7Lauwap/r+phOmvSWP2DVPY934lUY5acN60oFt/ougbLaUOl2sNpQ6ba9ltvd5VRrpkKlscc2kgd+MhsV3YwV3Qx1z+dWa/5KNxzqFBAN9ZheSqlOLQw10DLT7KXTck//v8qKugFPbDtONuzJzA925doRxUmi4jtQ8R0A9DySouZ+X2XanSon5VZUqn6qZhoKmtGxr8oGREbX5VwglQtrnL3Cmsx6MuudjpAmd51jdbn9oIWXAEYQ3/RvDMsqG91XjG/KFzHLTye5+g5UbGuX6+3dfyXW9K7bTrT89GH9nSCEEEL0JwmD+ommaZx33nm5CqAbb7wRgPb2dnRdp7CwEMMweOedd3jmmWeYOHHiIT2fruuce+653HfffUyYMIHCwkJ+/vOfo2kaJ510Eul0mmeeeYaTTz6ZwsJCQqEQuq6j6zr19fW8++67HH/88UQiESKRCJqmoetDfyaPEEL0xriIyXfm5nHjnAhv7knxTn2a9xpSvNeQZl2L1etgZ3u050MSfVUVNDityscZo3ycOspHSR8CC5+h8cmJQT45Mci79SkeWBPlkY0xkj1s2mu7U7y2+wBjeXSS59U4rdLHGVV+ThvlI+zR+OH7bfx8TbTb47/XkGbxcw2cVOHlpo/kMa/M1/ODHoCjFKubLP5el+RvtUle2ZWkKXloSVu29d11/4DTRvm4qDrAuWMDh9z6b6TTNA2jYAZGwQwaW/eQSLRQXjIeY4jORhZHBk3T0EJj0ENj8FSd64ZD8dpMMPQ+dvMHmWqKveheNG8xmq/IvXizVQJFbviTqRLACB7aQblR52BWnUtq3b3dKudUsp7kh7ei71iOd8oXMCKTDv55DpJSTqcqFPei4nWZsKcdlW4Dq63bWByDvp2JWuxELfaev+fWad7CTDA0AT08ES04Ct1fMSDjb6h0O050M077ZpzoJpz2TTjRLQcReHUKitQAHiTXdDRPIZqvEM2bvRSheQtB96CsdsgGeJn/a6z2XKh3UEFen+lgBtCMgPtzZvjdKk8j4Lb37DSPslHp1sylDaxO83b8wE/VZ8ptt3c4UbZb1mXHcplWP553NOS04Gh3fKDQ2KHelP0y8qcRmHcP6c2/J73lj133relWkh/ehrHrZbxTv4LuLx26DRVCCCEGidbc3DwsfydpaWkhPz9/qDejT/bs2cP5559Pfn4+y5cvxzRNHMfhBz/4Ac8++yxKKY477jhKS0upqanhvvvuA2DJkiXMnTuXa665Zp+PnUgkeP7553nggQf485//nFv3k5/8hJdeeol4PM7UqVO57rrrmDhxIul0mm9+85t8+OGHxONx8vPzWbhwIUuWLKGxsZHvfve7rFu3jnQ6TXFxMZ/4xCe49NJLB+V9OhQj8XMhxJGkpqaGyZMnD+k2RNMOKxvTvNuQ5r2GNO82pFjbbPU4Pk9f5Xs1RgUNRoUMKoMGRxd5OGOUj8n5Zr+eUdiQsPnNuhg/WxPtU2BlaHBcqZfTq3ycMcrPMSWeHscD2t5uceu7bfx2fWyfwdmCMX7+fW4eM4o8+31OpRRrWyz+VpsJf+pSNPQwVlF/8+hwxigfF1YHWTTWT773yAuGamM2yzbHeWxTPBcSVgUNFo3zc964ACeWe2U8qH0YDvuqw5mT2I3TtgHN8OWCHszwoJ55rZSDVfci6Q0/38dBZg1z1AK8E64ckAo6ZcU7tRvb3mV+6KtQMlUYmolK7jn0hzNDbigUKEfzV6AHKtD85bnp/lrzKSeNim1zQ59c8LO5f7arn2i+UrRApRtYejvCHjfIdOfx5B1SiyylbLBi3SrA6mq3U1FRCWTblGluazL0TMsyd17rNJ9br3vQjCCamQl49P6p/FVOyg2FOoVFHcFRqzueUrJ+yMYLEwPPKJmPb/oNI66dpN22kdSaH+K0re9+pRHEO+nzmKMWSpXQQZDfq4QQI4Hsq1wSBo0QiUQCv//w7XHeW/K5EGJ4G65frnFLsaopzbv1qUxAlGZ1U7pLy7QSv54LeqpCBqOCBpVB3Z3PhD9hz+AGDrajeGZbggfWRHl5Z88HUyZEjFzlzymVvj6FIjUtaf777TYe39zzWb4a8MkJAb49N4/xEbfaRClFTYvF3+qS/L02xd/rkj2OeTSYvDqcWeXnouoAC8f6iQzy/xO474ulIGkrDE0j0ENrwP6wO+4GQH/aFOfVXan9nmVc5NNZNNYNhk6t7Lld4cFqSTm8W5/m/cYUPl3j7NF+qvNGTkXScN1Xif6nrBjpzX8gve1P7vgZezPDeKsvw6z6eJ/G+FBOCpVs6hibJ1nfJfTp19Z5vaXpuWoUN7jIVmEVdV32FOTGD1PpNpz2jTht67HbNuC0b0BFt9GfraY0b6EbCgUq0P0VYPhwolvc0Ce2bciroAAwgujB0WjB0ejBKvTgmMz8qCEdZ2qk76uUUm4FVLIBJxcQdQRFKlmPk2zY/zhkuqdjXJ5MO8iO+ex6L+gGbhiWbRWo41aF9TDtsi67sZn2bI7dabycnsbZsTvG0XEsUGmUnXTb4dlJt5WhnWRQ27Xtrcv4R8Z+xj/Kholdl3PzmpEJGjPvreHDLDkBo/zUYTE+0MFQjk166yOkNz/ojju1F71gNr6jrkUPDq8xEd3AOIpKtXQKX1sywWxLx7KdzI1hpek+t5Wq4XfbEhr+TIvCzHTv2xhB9ztC3/+JYD0Zyn1VrrWqHesYe82Kge3OY8VQVsydt2OZ66NompH5vizqqFzu/L1pHFyXhJGsa5vaVsicoIByejgRQevYR+T2rQZd97M6mid8xL6fYvgZ6b9X9RcJg0YICYNc8rkQYngbSV+uCUuxsc0iaGpUBg18xvA+C3Btc5qfr4nyYVOaQp/OGaP8nF7ly4U0h+Ld+hT/9XYrL+zoOXAyNfjMpCAxS/H3uiS74n07wJHncd/jPK9Gnlcnz6Pn5vO9OnmezPrc9Rr5mevq4jaPb3KrX9a29HAgdy8+A87OBEPnjPETNDWiliKaVrSnHdrTKrcctbout6cd2jPzMUuRtBUpJzO1IekoUnZ2vRv8dKzr2v5lfMRgdrGH2cVeZhV5mF3soTRwcOMd1Sdsntic4LHNcf5elzyo8a3CpsbHxvg5b5yfs0b3LTCLW4oPGlO8XZ/m7Xq3LWNND/8Xp43yceWUIOeODeAd5j9PI2lfJfqHE9tBquan2A2v93i9FhqLb/IS9Pyj3TF4kg2ZaWMu8HGSjR3j86RbB3aDdQ+aGQFPBM0Mo2WmXZcz13sL3fF8DrE6JUvZSbdFW9t6nExA5LRv6jRezxDSTPdgvwL3n8yly/K+7mu4gVRwtBv8BNypHhoNnoJhWQ1wpOyrlJN2K/iU4372dW9mvB1zRIYOSik3fHZSKDuRC4iUkwQ75U6dJNmDqV1Cl70DG/Z1XeeAJ3PJBGLD8bM83DjRbSTX3IHT8mH3K3Uf3glXYo65wH2P+4Fy7EwQkWkdaMfdeSuGsqNgxVHZ661op7CnNXNQvp3BChjdgKTErYr0l6D5StB97lTzl7onF+jeLvfp732VGyS3Zb6DO33/dvpOVqnGTOvK2MC0ATXDncKhwi5tbTGCdHz/ZL93Oi/38N2kOn0/5cLrjp/pLsHrXtd3XEfmtSr3PcLJPG7nafd1Sjlgxzu1/sy0LM1erEzwk24fuLHasmFj7qQVd76jynZoKsnFkeVI+b3qQCQMGkaeeeYZvv/97/d43WWXXcbVV189yFs0/ByJnwshRhL5ch3Z/l6X5OZ/tvLGnkM74Jfn0TihwsfJFV5OqfAxs8iD0Q/tyj5sSvNYJhha33rgYEjXOKjgZKCMCurMLPa6IVGRh1nFHkaHjB7/4GlKOjyxxX2tf61N9qrNoc+gx7GmerrdaaPcYGjRGD9Fnca4shzFh01p3skEP2/Xd6+iO5ASv86lk4JcMSXIpPy+n106GGRfNbJYjiKeCWLjliLRZQoJW+UuSVvh0TUChobPgICp4TOyyxr57W8R2fYAemLH0L0gM9wRSGQqUTRvYdewZz9n0NqOYnfCoTZq024pZhSaFPdhrLqDoRybjbs2sXLbWtqaaihXO6n21FOm12OoAQiJNMN9b0Lj0cPV6OHx6KFqNH9Zrw4SqW4H5wBNG3HBguyrxJGkNeWwsdViU5vFxlabjW0WG1stWpIORxd5uKg6wBlV/n47gUspB2v7E6Q2/hLsRLfr9byjMIo+4gZ7ykI5VqeKMAulrNw8ys5cb3VUjFkx9wC8FTv82iV68t2AyO+GRk1tFkXFJbh9BXCnmSq9npa1TvPKTmTaS3YOfJoGLpQQw5vm6QiLMuNJar7SToFkiVvJZXgP/Fh9pJRyw3snhXJSbvWgk3Z/nrPzTqrTfBql0p1uZ4EZciuwvZmLp8CtwhtBAZdybHASmRMaspWvqU4VsMnMCQ6pzPuV7vR+Zd+f1F7vVarrbZTthu26xz3RRzfdqkTNzJzc4EHLrM/eRtNN0EzMso+ih8cf1GuT36tcEgaNEFIZ5JLPhRDDm3y5jnxKKZ7eluCWt1r5sPnAgQtAxKNxQrmXkyvcVnUzi3oeq6g/t3FVk8Vjm2I8tinOxrZh0GLoIBX5dGYXe3LVQ3Fb8fimOC/tTPYqgJlT7OHi6gAXjA9QGtB5aUeSJ7bEeXpbgpbUgR/A0OCkCh9TC0zeb0jzXkOKRD++nSdXePmXqSE+PjbQr23q+ippK7a2W2xus9nSZrFr9x6OHldBRUCnPGhQFtAJmgN3kFgpRbul8BsaHhnHqQulFNujtvv5a3THelvXnKY93RH69CWM7A0PFp+LvMDXC5YR0bsfAOwPltLZYZeyW6uk1agi7avCEx5NJG8sFflFjImYPbYeTdmK2pjNzphNbdRmR8xmZzS77LjTmN0lINaAY0o8nFHl58wqH8eV9s94YUopPmhMs2xLgic291ydqeFQbrSysKyZj5W08JFII/nObpz4LlSizh375wBnbGu+Ejfw6RT8aMHR3c48Pxw5StGSUjQkbBoSDvUJh4akQ2NmGm1p4mNTyzm+zEehb2QFWUL0pDnpBj7ZoMe9uMFPfS/aDud7NT4+LsDi6gAfrfT1y77OideRXHMnTtM7h/xYQohBkg0kfSWZwMgNivTMsnJst02plW0XuPd8DGW1d2otGAUr2nNL4UOlezMBUX4uIMqGRXjyO4Ijb5E7HYATV5Ry3Kr32Hac2A6c+A53PrHHDcM7Bz3DoX3vfviO/jZm2UcP6r5yvMolYdAIIWGQSz4XQgxv8uV6+LAdxSOb4nzv7Va2tHf9hTBkaswvd6t+Tq70Mad4YMOf/VFK8X5jR8XQ3ts6mAwNfIZGwlYDWpE0s8gNgC4cH9jnOD1pR/H32iTLtyZYviXe59Z+B6IBUwtM5hR7WN9q8c89+z97s8in8+lJAa6cEmJqQf9XCymlqE84bG6z2dxmuZf2zHyreyD9QP8lEY9GWUCnLGBQHjAo7xQUlQc6pgDNKYempENzMjNNqczUXdecdGhKOTQnO9bbyq1WGxU0GBs2GBcxGRvuOl8VNA6qis5Rij1xh9pMUFAX6wgNdsdtfIZGiV+nxG9Q6tfd+UDHfJFP75fqvd5s58ZWi/ca0rnw5/2GNI3JoRlbo1Rv4cbCR/l0+JU+39dWGnvsPHbbBeyyC9hl57PZKmNDuoIN6Qq2WqWk2X8bz0KfxpiQSVlApz7h/p/t7oef1TyvxqmVPs6s8nNGlY+x4d63E3WU4q09aZZtifPEljibDyJsn1nk4dyxfs4dF2BGPpBqQMXrcBJ1qHgdyk644/KEq9FD49A8kR4fpz3tsLbZ4sOmNGuaLVY3palPOHgN8OoafkPDm6kA8xkaPt2t/vIauNdlln2Z23h0DaXcilG3XkihMvO5dblllevu03nfoWnu/k/TNLLntefWdbkeNNzbJGxFQ8KhIdkR+DQmHRoy095UfgJMLzCZX+7jhHIv88u9jOnD/6voLmEpalotaprT2MqtIgya7ucqaLpj/3WeDxjaoOwnDycJS/GPXUlWbE/w5p4UG1vtft3fF/t0zh/v5+LqICeWew/p/0cphVX7HKn1P3UPCA9HZgjNk4fmyc9M89z2oNl13jzQ/Zkz8pNui8Jce8JEpzP6E5n2hZmDv3bCvU26FZVqZr/tNocr3YdmBsEMohlB970yQ13nc9eHwAy61V25aqSGLlVJKtU4MK3nRgLdg2bmuZXKmQuaJzeWmvtF6ZBtSeeOodaxnG1jlx1nTaVbMpVewztgGDY0o2Osx05Bl56rksqs28d4hirdmhnDcgcqtsMdyzK+Aye287CpUPTNvAmz9ISDuq8cr3JJGDRCSBjkks+FEMObfLkeflK24g8bYvyjLsmUAg8nV3g5psQ7LKsblFK82+AGQ49vjrM1EwyFTI2wRyNkaoQ8eqd5jZCpE/JohE2NsEfPrHMP/mQPIroHFOky793rwKNP7zhIFLMcPmyycpU27zWk+bApTeoQ/qacXmhy0fgAF1UH+tx6zVGKN3enWL41cdAHd8eFDeaWeJlb4uGYUrfVXedxh1Y2pvn1uigPbYjReoCKpBPK3Wqh88cFCOyjWkgpRcJ2W8a0ph3aUorWtENLSmXWKXZGO4KfLW1uu6yRztSgKtQRDo0LG4zNzLsVIx2BT+fgpy5mH1L1jAYUZ0Miv06p38gERjphj44/8/nPtlrzZ6bZFmw9Xa9psKbZ4v3Mz8AHjWk+aEgPy/+nOd6NLC18hON869FQ7LHz2WXns8suYLedT11mutsuyM3X23k4jIxKjSn5JmdUueHQSRXeblVwtqP4x64Uy7bEeXJLnJ2x/jsANjZscO5YPx8fF2B+Wc8Ha+OWYm1zR+CzpjnNh80W24Yw3B8JRoeMXDB0QrmPowpM9BHUhmawWI4bQq/OBIurM+Hihlar10FcllcHv6kRzOz/AqbG6JDB0UUeji70cHSRh4l55oCGRipTTRbxDM9walOrxYrtCZ7fkeBvtSnifX2TD1J5QOeC8W7F0HFl3oP+WXCSDaTW3oNd/2o/b6EGRqBrYGEE0Uz3krsuu66nwEffdwCcdhRv7E5RG7OpDBpUR0wqgnqf3wflWG4wkqzPXZzEni7LKtnIoIxfZATRfJmxZHJj9xR1GrunyG3BZQbd9lL9SCkH0i17jVXUERrhZE+CypwKoHWe1zrmofsy5IISyEyVnQlV7I5AJRe+dLou9/jZscH0jsfX9P1ONSOA5gm7nykzkvl8dQp8suv206b20N7Ptk7jPzV1C9+y7zF2vN+f/7BkhtF8xe6YkWYEldiFE9sOVvtQb9mA883+L8zi4w7qvnK8yiVh0AghYZBLPhdCDG/y5SqGk4Sl8BoMi4NjaUexptnivYYU72eqIj5oTBPdz4HxqfkmF1W7AVB/VdMopVjZZLE8c9b/h03dWyGUB3SOyQQ/c0u8HFPi6fV4JDHL4fFNcf5vXYzXdu9/HJF8r8YZo/wkbEVb2qE1E/i0ptzl9BF6QqboToPcWfoBQ8NvdoRP/swZ+/7MvFfXsBzVaRwhd1/QeVyhhK1y6zqHtF7SWBg46Gi4QXL2gG/Q7KgQyB4IdtfpBEwNXYPamM22dptt7Ra1MWdAz60u9GmMChooRa9beoI7ZtgJ5T7OrPJRHTF5bnuCp7YmetWeydTgo5U+zh8fYHqhyQs7kjy5NcHKxt6N61Ds01kw1s/xZV62ttmsbnYPzG9qO3DlnjiwfK/G/DI3GJpf7mVSvkncclstxva6xG1FLK2I2dnrHXd95npNg4hHz5wo4Z4sEfFq7rpOJ1CEPRqRzPXeTuO4WI5bFZm9NHaaNicVTSm3FV7naXPSwdSh2GdQ5NMp8usU+3WKfXrHsi+zLlPRWODtqGp0lGJru83qpjSrM8Hi6maLdc2HdjJGX/kNmFbYEQ4dXeRhRqGHgj60+Ut1am26qc0dQ2dzm83mVrfqNWYpgqbGzMz4g3OKPcwu9jK1wBz0k3XiluLvdW71z/PbE4fUutejw/iIyYSIQXWeyYSIyYQ8E0ODJ7Yk+PPmOA29qCwaHTK4qDrAxdUB5hR7cmN1KOV+vptTipZsJW/KPdGkOem461IOzQmb8vRqJqsPKfJrlAV9lAe9lAa9GIaZGdOiY/wKdGOvdZnxLozOwY+v31s/NSZsnt+R5Jltbvi298k4fsN9P8dHTKojbkBUnefOjw2bXX5m+0I5dubg/R6cRD3p+B4a92yjrLgItyKkhzHbsvOZisyOZdA0Ty7o6TLdR+WDOLwpK94pIMoGkvWDF0hqHvfnVfe487p70fTsvLfLdbn1moeEo4HVjpZuQUs3o6VbIN2MNuLGv9LA8LkVd7o38374Muu8bmCYvS5zceez70l2vafT+sz7lr1OMzLhZ7pjHDYn3WlctjTRVJrVjXHWNMbZ2JLAcSy8msUXTzuPkqIxB/XK5HiVS8KgEULCIJd8LoQY3uTLVYjesx3Fxja3ZVa2bVbaUZxY4ePi6gDTCswBH2x0Y6vFc9sTtKYcphW64c+ooN4vz7u6Kc3/rYvy+/UxmnsxftFA0shW3BiMC5vE2lpJeMPsjrttuXbF7QEPnwKGNmhnSI80ocxBzZnFntwYWuUBA38mAPLqDNjPgu0oko4bDiUdcoGTzzi050zZip0xmy1tNtuiViYkcoOibVGb7e09V3NpQFlAZ1TIYFQwcwkZXZYrQ13HuNoVs3lxZ5IXdyR4cUeyVwdLe8tnwOmj/Jw/zs/CsYEex63Z3Gbx5NYET26J89ru1IC2yTwcRTwaRZmQI9u2sdjvBiKraxtYnQjwYZM17AMznwFhUyftKFrTg7O1GlDo0ynwauyKO/s9wWKo5SqIijzMLPIwrcAkaik2ZQKeTa1upeumNpsd0YMLSP0GzCh0g6HZmf3ptEIPvoM86N8TpRQbWi1WbE/y/I4Er9Ql+zTWoM/ADSUyQc+EPIMJmZBiTGj/rVItR/G32iSPbnJPaOnN2IijQwZ+Q8uEPod2okn2/Z1V3PEeTyvwDNqYiEopalosntmW4OltCV4/hP2tnqlEro6YjM8ERWUBnbiliFqK9rSiPe3+TEXT7riH0U7L0bSizXKIplWuwi7fq1EZNKgIGlQE9I75oEFlUM+sNw46hBpISrn7rYaE06WtZ8ey0+U6W0HQzHYT0N15T8eJI/tbDxrJzIkpSdsN5zuWya3PnrjS+bZeQ6PQp1Po1d2pT6fA1zFf6HWvD5par3+HSTuKtpRDW1plLg7taXddu+VW5Btax8kxgU7tM7OtNQNm15aaA90+XDk2Kt2E2iskcpL17rpUY6bdXQjNDHdqFbiv+RCaJwxGCM3Y93iF2aB+U5u7z84F9Zlpz7/nK8JaghKjlRKjjSK9zZ3X2yjOrCvRWykzWik3m8nXYwP2vll6iLi3iphnFO3mKFrNStqNCopCEaoiAcpDAQyPHzTPgP8Nui+b2yye2prg6a1x/rEr1WMF7z0nF3DZ5NBBPb4cr3JJGDRCSBjkks+FEMObfLkKIfaWsBTLtsT59boor9Ttv1roUIRMjXERI3MGrHtwY3xmOiZkdjlYs/e+Sin3LPZdcYfdcZtdmYBod6fp7pidG3vJ/aNboyDzx3h+9g9yr547MJn7A93rTn2GRtxSbI9abG13Q4Kt7VbHtN3uVXXGvuR73UqR7MGXUUGDiqA77lHaVuzJjFVSn7DZE3cPbOyJu8uDGdYV+jRmF3uZVZQ9oOZhQmRg2yoNR7ajqIs7bGt3B00v9etUhg79QJmjFO81pHlhR5IXdiR4Y3fPf0jvT8jUOHu0GwCdPcbfpSXkgdQnbJ7emuDJrQle2pkgeQid3nQNJkRMphWaHFXgHjwfFzGxlXvALJk5OJZy3AqwVGY5abvBXtJWpOxsBZjCcrqP76N3Gvsn2+lH72HcH03rPp5Qdrnz2EId6zvGI/LqGkWZoCdb2VLkN3Lz+ztQn91XNScd3tid4tVdSV7bneKtPalBrXY5XI0JG0wrMIl49FzFVKJT9VS2sio7PywPnByAR4dpBR7mlGTDdi9BUyPtZH9+3IPBKUeRsslMFWknM++4P1spR7Er5vDizkSf2s2OCuqcNdrPmVV+5pZ4GHWQY+PtLWUrXtyZ4E+b4jy9NUHbIAWQezM1dwzFWZ0CuKOLPH3ab+5P2lH8oy7FM9viPLMtwaZDqLwaLop9OhXBrmFReWZcxux4jeUBY5+thPvCbbHb0Vp3Z8yhNuqOJbknbncJeYZxltxnXp2OgMink+/VUZALfdrTHdO+hLl9ef7OwZCuud+tOu73rt75+zbzXaxnljtuq2Ho7rypaRiaOz6robvzpg7GXutNLbNOd1t4Z6vHfUbXCvNsq2N/p2m2wtzUYEfUzgU9m9qsTPBz8EF9XwS0JBVGMxVGExVmZmo0UWk0U240U2E2UW604NF6/o+LO142WWVsSpez0SpnY7qcjVYFG9LlNDlhurQr3ItXh7HhjoB4XO5vKXdduJ/2a505SvFOfZqntrr78t5Uu5871s9vzyw+qOeT41UuCYOGgSVLljB37lyuueaafd5GwiDXkfS5EGIkki9XIcT+1LSk+b91MX5XEztg9YJHhzyPTp5XI8+rk+dxp5HMtMSvZ0If9w+UEn/vK5qG674qmnbY2m5nwiIrM2+xPWrjM7Jn3LoHUDpfKoJ6t3Fg+iJlKxqSmbAo7oZSexIODQm3HVHSZq8zV90Do3ufydr5bNa0A5VBnVmZ4Cd7kGx0yBiysw2PRC0ph7/WulVDL+xI5sZS21ueV2PhGD/njQtwZpW/Xw7CtacdXtyRZPnWOM9uS+z3LP7xEYOjCjxMzwQ/RxWYTMkfvDPuh6t97asSluKdhhSv7UrxWiYg6k2VxJGqPKAzrdANFKcVephe6GFqJgTqLaU69oXZkKgt7bCm2WJlY5qVTWlWNqYPKdTvLa/OsA0DPTrML/Ny9mg/Z432D0qVc9xSrNie4LFNbmAy1FW4Gu4+rdRvkO/VyM8cjM/3aplpz/N5XjccbkzYrNiR5JmtCV7Ykeh1pV2xT+fYUg91cYdNbdYBx3Ac7vK8WkdAFDAoD2YDo47QSINMyGOzM9o18KmN2ewZhJ9HIQabhkOx3kaF2Uyl0USBHqXWLmRjuoJauwA1QGNalvr1TifbmYwJu5WXbjjXEcyZmWBO1zRM3Q3Nc2Fd5nbb2m2e2urus7Mn2x1IWUBnwRg/548LcNbogzs+Plz/BhxsEgYNAxIG9d6R9LkQYiSSL1chRG8kbbfVy664TcTjHgjpHPTkefQBPQgs+6qB5yg1LMbrEh2y7Z1e2OGGQ/UJhxlFHs4fF+Cjlb4Bbd3jnt2e5KmtCWpjNuMiJkcVmEwv9DAl3yQ0AGebHg56u69ylGJ1k8Vru5O8uivFG7tTtKYcQpkxrbqMedXDfHbsq+x4WI7KtImyMq2COrUO6ryuPdMqqj2turSr0nCrFYsyZ6UXdWpntPe6ok5nr6cdlTtTvzHpjifU0GVqd1neOwAr8Gq5sCcb/EwrMCnq5bh3/WFXzM4FQ9nLuharzxV6VUG3tWl1nsn4cGaaGfulyKezI2q7bWYb3Vaz79WnqOvlAbX+NjpkcPZoH2dV+fnoKF+/VcUcjPa0w7Pb3Iqh53d0r070G5DvdSt58706BZkq33yvnglt3OUCn46j4IPGNB80pHivIT0o72/A0Eg6qtft36YXmiwY42fBGD8fKfHmqq6yFc+b9qps2NRmsaXNYmes/16LVwdbKWwl3/niyBY23aojB/dnuKOiOHPJrHc6rRf7N63AZOFYPwvHBPhIqeeQ/7aQvwFd5lBvgBi5LMvCNOUjJIQQQoi+8RnaQZ/RJUYGCYKGH03TmJTvYVK+h3+dHh7U5/boGqeO8nPqKPm5Hwi6pjGjyMOMIg9XHTX4z6+U21qtPa3w6O7B9oNtBVYa6H1wk3bcA95NSYc8r05FoH/GvDsU5UGD8qDBmVUdn/WkrVjT3DUg2tBqkefVGZcJeDq3OB0XNg94QsTosMnosMm54wK5dXUxm/cb0rybCS/ea0izPdr/PaC8OpxY4eOsKh9nj/YzJX/gq396K+zRWTwhyOIJQVpTDhtbLQKmlguA+nqiyQXju7+/7zemeS/zHu+r2vJgHaiqyavDKZU+zhnt55wxfsZFej4eo2kaRX6DIr/BR0q7j4EStxRb2ruGRC0ph7CpE/K4Y9uEPRphj04oM+5NyNQJe9z5sOleFzQ1vIbG2nU1FI2ZQG3Mpi7mUBe3M/M2tTGHusz87oQzbA+Ah0y3pWexLzN+W661Z0dbz+zFo2lELYdYpq1kNDONpVWP67NjMcUyg1b5M63K/JnwwJ9pZZZbn21l1mnZa7j7kqZkx36vKeXk5puTDs0pN0jvS4tWXXPHrot49Nw07NGIeN3/47CpoSDXMjP7ehKd5vdeN0z/i/vFqGB2v+3uu6vzOvbdRb6+fwcp5QZEloLWlJMZ30zRnHTHOeu8nB37rDmpctc1J90TMkzdbUvrzYy16cnMezLrfZ3mPZnbeHUNW8HWdrclXmM/jjl5sAwNTij3snBsgEVj/FTnyTHngTDi3tV//9WVg/I8//Uvv+71bR955BEeeughHn744dy6aDTKokWLuP3223nrrbd47rnnaGhoID8/n0WLFnHNNdeg6307Y2bDhg3cfvvtrF+/Htu2mTJlCtdddx1TpkzJ3ea9997jvvvuo6amBoBp06Zx9913A9Dc3My9997La6+9RktLCxUVFdx4443MmTOH//zP/wTgpptuyj3W3hVL8+bN47rrruPZZ59l/fr1fO973yMYDPLjH/+YrVu3AjBr1iyuv/56qqqqco/z17/+lV/+8pds3boVwzA45ZRT+Pd//3eWLl1KKBTi29/+du62b7zxBt/85jd58sknCYUObkAwIYQQQgghhBCDQ9MyB4s9g/u8Hl2jLGBQ1ocAaSj4DHestNnF+x6YvD9kx1/52JiOIKo+4QYY72VCoprMeAyeTgcMfT0cPHTXdT14GDA0ZhSZnFLhGxHVfHlenTkl/fee9/T+NiUdNyBqSPFeY5r3G9LUtFj9ejC81K/zsTF+zhnt5/Sq/qm8CphapiVn//zQ6pob5JYGDGbtZygPy3HHMMy2cavNjMe4O25Tlx23MeaO1dgfY/houK2lRoXctrrZsRVHhdxWc8V+nRK/exC/P9qjDhdxq3tgZGhuWJq3V+ATMLR+DXM7t9SMWQpbdVTJ7F0d4y53BCKdq2jcajOwlVv9ajnuvOWozDqwMrfJrrMd936WIte2ONFpPDi3pTF7LXe6TabdcVnA6BbSV+eZjAub/f450bLjHtHxMzRUWlIOW9rcgHhLZsykzW0Wm9ostrXbAzauVtjUOHO0j0VjA5xd5RvUat4jVa/CIMdxuO+++1i2bBnxeJzZs2fzrW99i8rKyh5vv3btWm677TbWrVtHQUEBl112GZdcckm/bvhwcs4553DnnXfy3nvvMXv2bABWrFhBUVERxx57LPX19dx7772UlZWxevVqrr32WioqKrjwwgv7/Fyf/exnmT17No7j8KMf/YgbbriBRx99FNM02bBhA1/60pe47rrruOOOOzAMg7fffhtw/w9vuOEGIpEIP/3pTykrK2Pbtm193uk/9thj3HrrrYwbN45kMsnatWv5+te/zrRp04hGo/zXf/0XN910Ez/72c8AePXVV1m6dCk333wzJ598MrZts3LlSgAWL17Mddddx9e+9jWCwSAAjz/+OOecc44EQUIIIYQQQgghxCEo8RucUWVwRpVU5Q2EQp/OqaN8nDrKl1vXnhn/ryVzFn9LStGS7DSf2vd8tjBoRqHJwjEBzhnj75fWSMOFqWu58Q73x1GKxqTDrpjDrrgbGO2K2R3zcZtdMQdHKSqCBlWhjnEUR4WyoY87rpDnIKsUR7KAqREw3fdisGmaht8Ev6lR6Dvw7cXwke/NjPXZQ6BrOYodUTsXEG1us6iN2bnAznLcEM7OBHPWXiHd3sGdqWscX+Zl0Vg/J1f48A1gq2LRXa/CoN/85jc8++yz3H///ZSWlvKjH/2I66+/ngcffLBbdUt7ezvXXnstixcv5ic/+Qnr1q3j61//OiUlJZx55pkD8iKGWiQS4fTTT2fZsmW5MGjZsmWcd955aJrGwoULc7edPn06CxYs4I033uhzGDRx4kQmTpyYW/7Sl77EY489xrZt26iurubRRx9l/vz5XHzxxbnbHH/88QCsWbOGDz74gGeffTY35s7YsWP7/FovvfRSxo8fD4Df78+9XoD8/HyuvvpqrrjiitwYR3/84x+56KKLOP300wHweDwce+yxAMydO5fy8nKeffZZLrroIpqamvjLX/7CL37xiz5vlxBCCCGEEEIIIcRQCnt0phf2vXpHKbeVmIIhHXdpONA1jRK/QYnfYAaDXHIohOjG1DXGRUzGRUxORVK+ka5XYdCf/vQnLr/8csaNGwfAV77yFRYsWMC7777L3Llzu9z25ZdfRtd1rrrqKnRdZ+bMmVxwwQU88sgjh20YBHDBBRdw3XXXcf3111NXV8fq1au59dZbAbeN3GOPPUZdXR1KKVKpFDNnzuzzc+zcuZO77rqLlStXEo1Gc1U9TU1NVFdXU1tby4QJE/Z534KCglwQdLBGjRrVZXndunW50C8ejwOZwQqbmqisrGTnzp2cdNJJ+3y8iy++mMcff5yLLrqIJ598ksmTJzN16tRD2kYhhBBCCCGEEEKIkULT3HF6hBBCiIF0wDCovb2d2tpapk+fnlsXiUQYPXo0NTU13cKgdevWMXXq1C4VQ9OmTePPf/7zfp8nO8ZNlt/vx+frnjYu/fT9B9rkfpFIJPp0++nTp1NUVMRTTz3Fli1bmDdvHpFIhDfffJM77riDH/zgBxx99NGYpsmdd97Jhg0bcs/hOA6WZR3wOW+55RYKCgr42c9+RkFBAW1tbZx77rkkk0kSiQSlpaVs3ry5x8cpLi6mubmZPXv2EIlEul3v8/lobGzsct/du3d32669l2+88UZOOukkli5dSiQSYd26dXz+858nkUiQSCQoLy9n06ZN+3xtZ555Jj/+8Y95//33eeyxx/jMZz6z3/ehtbWV3bt37/d9EkIMrb3350IIMRzJvkoIMRLIvkoIMRLIvkoIMRIcCfuqyZMn7/f6A4ZB0WgUgHA43GV9JBKhvb29x9v3dNvs4/R2Q1taWvD7R1Zf2wsuuIDly5dTV1fHjTfeiN/vJ51Oo+s65eXlhEIh3n33XZ5//nkmTpyYe326rmOa5n5fbyKRIB6PU1VVRUlJCYlEgp/+9KcAeL1e/H4/l1xyCVdeeSXPPPMMCxcuRNd13nnnHebNm8ecOXOYOXMmt956K//2b/9GSUlJbsygMWPGcPTRR/OjH/2IXbt2UVVVxcMPP0xtbW237co+V1YsFiM/P5/i4mKampr41a9+Bbjhkt/v59JLL+Wb3/wmxx13HCeffDKWZbFy5cpcqzi/388555zD7bffTmNjI+eee+5+34e8vDzGjBlz0P9HQoiBVVNTc8AvHiGEGGqyrxJCjASyrxJCjASyrxJCjASyr3IdsBFpKBQC6Bb8tLW1dQt9srfv6bbZxzmcnXvuuaxduxaAk08+GYD58+dz/vnnc/XVV3PWWWfx0EMPsWDBgoN6/Ouuu44PP/yQM844gyuvvJJ58+Z1uX7ixIncfffdPPXUUyxatIiFCxfym9/8BnBLjv/3f/+XwsJCPvvZz3L66afzzW9+k8bGRgAWLFjAmWeeyVVXXcXHP/5x2trauowHtC9Lly7l6aef5rTTTuPLX/5ybmygrPnz53PzzTfzi1/8grPPPpvzzz+fp59+usttLr74YtasWcPChQsJBAIH9d4IIYQQQgghhBBCCCGEEKJnWnNzszrQjS644AKuuOIKFi9eDLjB0IIFC7jrrru6tYlbvnw59957L0888USuVdw999zDqlWruPfee3u9YS0tLYc8vs3hJJFIjLhKqd5qbm5m4cKF/PrXv2bKlCn7va18LoQY3uRMCyHESCD7KiHESCD7KiHESCD7KiHESCD7KtcBK4PArdx48MEH2bJlC/F4nLvvvpuxY8cyZ86cbrc97bTTsG2bX/7yl6RSKVatWsXjjz+eC5KE6Cz7WZkzZ84BgyAhhBBCCCGEEEIIIYQQQvTdAccMArj88stpb2/nmmuuIR6PM3v2bG6//fbcmDRf+9rXeOihh6ioqCAcDnPnnXdy66238qtf/Yr8/PxcizSxf8888wzf//73e7zusssu4+qrrx7kLRpY69at4/Of/zzl5eXceuutQ705QgghhBBCCCGEEEIIIcRhqVdt4oaCtAPr6nBuE9cX8rkQYniTslshxEgg+yohxEgg+yohxEgg+yohxEgg+ypXr9rECSGEEEIIIYQQQgghhBBCiJFJwiAhhBBCCCGEEEIIIYQQQojD2LAOg5Qalh3sxBCRz4MQQgghhBBCCCGEEEII0XfDNgwKhUI0NzdLACByYrGYjJskhBBCCCGEEEIIIYQQQvSROdQbsC+maRKJRGhtbR3qTRkWWltbycvLG+rNGFKmaeLz+YZ6M4QQQgghhBBCCCGEEEKIEWXYhkHgHvzPz88f6s0YFnbv3s2YMWOGejOEEEIIIYQQQgghhBBCCDHCDNs2cUIIIYQQQgghhBBCCCGEEOLQSRgkhBBCCCGEEEIIIYQQQghxGJMwSAghhBBCCCGEEEIIIYQQ4jCmNTc3q6HeCCGEEEIIIYQQQgghhBBCCDEwpDJICCGEEEIIIYQQQgghhBDiMCZhkBBCCCGEEEIIIYQQQgghxGFMwiAhhBBCCCGEEEIIIYQQQojDmIRBQgghhBBCCCGEEEIIIYQQhzEJg4QQQgghhBBCCCGEEEIIIQ5jEgYNY47j8JOf/IQFCxZw6qmn8tWvfpXa2tqh3iwhxBHs7rvv5pJLLuH0009n0aJF/Nd//RfNzc1dbrN27VquuuoqTjnlFM477zweeuihodlYIYTIuOGGG5g3bx5vvfVWbt0bb7zBpZdeyimnnMLixYtZsWLFEG6hEOJI9/bbb3P11Vdz6qmnctZZZ/GNb3wjd53sr4QQw0FDQwPf+c53OOecczjjjDO46qqrePvtt3PXy75KCDHYnnvuOa6++mpOP/105s2b1+36Ax2fSiQSfP/73+ess87i9NNP59vf/jYtLS2DtflDQsKgYew3v/kNzz77LPfffz9PP/00FRUVXH/99TiOM9SbJoQ4QhmGwc0338yKFSt48MEH2b17NzfffHPu+vb2dq699lrmz5/P888/z/e+9z0eeOABXnjhhSHcaiHEkezJJ58kkUh0Wbdz506uv/56LrnkEl588UW+9rWvcfPNN7Ny5coh2kohxJHs7bff5vrrr2fx4sU8++yzPP3003z2s58FZH8lhBg+brvtNurr63nooYdYsWIFZ5xxBtdddx1tbW2yrxJCDIlIJMInPvEJvv71r3e7rjfHp+644w5Wr17N73//e/785z8Tj8f5j//4j0F8BYNPwqBh7E9/+hOXX34548aNIxgM8pWvfIUtW7bw7rvvDvWmCSGOUF/84heZOnUqpmlSVFTEpz71Kd55553c9S+//DK6rnPVVVfh8/mYOXMmF1xwAY888sgQbrUQ4ki1a9cu7rvvPpYuXdpl/fLly5k0aRIXXHABHo+HU045hVNOOYXHHntsiLZUCHEk+/GPf8xFF13EggUL8Pv9eDweZsyYAcj+SggxfGzbto0zzzyTgoICDMPgoosuIhaLsX37dtlXCSGGxAknnMA555xDVVVVt+sOdHwqkUjw1FNPsWTJEkpLS8nLy+OrX/0qr7zyCnV1dYP9UgaNhEHDVHt7O7W1tUyfPj23LhKJMHr0aGpqaoZwy4QQosObb77JpEmTcsvr1q1j6tSp6HrH18u0adNkvyWEGHRKKW655RY+97nPUVFR0eW6mpoapk2b1mXdtGnTWLdu3WBuohBCEI/HWbVqFQBXXHEFZ511Fp/73Od44403ANlfCSGGjyuuuIKXXnqJ+vp6LMvi4YcfZuzYsUycOFH2VUKIYedAx6e2bt1KMpnssu+qrq7G7/cf1vsuc6g3QPQsGo0CEA6Hu6yPRCK0t7cPxSYJIUQXK1asYNmyZdx33325ddFotMf9VnafJoQQg+XRRx9FKcVFF13U7bpoNEp1dXWXdbKvEkIMhdbWVhzH4emnn+ZHP/oREydOZPny5Vx//fX84Q9/kP2VEGLYmDVrFk899RSLFi3CMAzy8/O57bbb8Hq9sq8SQgw7Bzo+lZ1GIpF93uZwJJVBw1QoFALoFvy0tbV1+yALIcRge+655/if//kfbr/9do466qjc+lAo1ON+K7tPE0KIwbB9+3Z+/vOfd2sPlxUKhbr9gi/7KiHEUMjud84777xcK94LL7yQUaNG8eqrr8r+SggxLDiOw5e+9CXKysp4/vnn+dvf/sa3vvUtvva1r7F+/XrZVwkhhp0DHZ/a37H3w3nfJWHQMBUOh6msrGT16tW5de3t7ezYsYPJkycP4ZYJIY50f/7zn7ntttv44Q9/yLHHHtvluilTprBu3Tocx8mtW7Nmjey3hBCD6t1336WlpYUrrriCs88+m7PPPhuAb3zjG/zP//wPkydP7vI7Frj7qilTpgzF5gohjmDhcJiqqio0TeuyPrss+yshxHDQ2trKjh07+PSnP01eXh6maXLqqadSVVXF66+/LvsqIcSwc6DjU2PHjsXn83XZd23evJlEInFYH8OSMGgYu/jii3nwwQfZsmUL8Xicu+++m7FjxzJnzpyh3jQhxBHqoYce4p577uGuu+5i9uzZ3a4/7bTTsG2bX/7yl6RSKVatWsXjjz/O4sWLh2BrhRBHqrPOOovHHnuMBx98MHcBWLp0KV/84hc599xzqamp4YknnsCyLF555RX+9re/9dhSTgghBtonPvEJnnjiCdavX49t2zzxxBPU1tZy4oknyv5KCDEsFBQUUF1dzcMPP0x7ezuO4/DXv/6VjRs3ctRRR8m+SggxJGzbJplMkk6nAUgmkySTSRzHOeDxKb/fz6JFi7j//vupr6+ntbWVu+66i5NOOonKysqhfFkDSmtublZDvRGiZ47jcO+997Js2TLi8TizZ8/mW9/6FqNGjRrqTRNCHKHmzZuHYRh4vd4u6x966KHcAO1r167l1ltvpaamhvz8fC6//HIuueSSodhcIYTImTdvHvfeey8f+chHAHjjjTf40Y9+xLZt2ygrK2PJkiW5CiIhhBhMSil+/vOf86c//Yl4PE51dTVf/vKXmTt3LiD7KyHE8LB161buuusuPvjgA1KpFBUVFVxyySVceOGFgOyrhBCDb/ny5dx8883d1mf/7jvQ8alEIsEPf/hDXnjhBRzHYf78+dx4443k5+cP5ssYVBIGCSGEEEIIIYQQQgghhBBCHMakTZwQQgghhBBCCCGEEEIIIcRhTMIgIYQQQgghhBBCCCGEEEKIw5iEQUIIIYQQQgghhBBCCCGEEIcxCYOEEEIIIYQQQgghhBBCCCEOYxIGCSGEEEIIIYQQQgghhBBCHMYkDBJCCCGEEEIIIYQQQgghhDiMSRgkhBBCCCGEEEIIIYQQQghxGJMwSAghhBBCCCGEEEIIIYQQ4jAmYZAQQgghhBBCCCGEEEIIIcRh7P8DcwGryA55GCEAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1872x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame(history.history).plot(figsize=(26, 8), title=\"History Curves\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "94006c3b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-12-06T23:16:05.479173Z",
     "iopub.status.busy": "2021-12-06T23:16:05.478136Z",
     "iopub.status.idle": "2021-12-06T23:16:05.763493Z",
     "shell.execute_reply": "2021-12-06T23:16:05.764013Z",
     "shell.execute_reply.started": "2021-12-06T23:14:57.799721Z"
    },
    "papermill": {
     "duration": 0.405517,
     "end_time": "2021-12-06T23:16:05.764209",
     "exception": false,
     "start_time": "2021-12-06T23:16:05.358692",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4/4 [==============================] - 0s 3ms/step - loss: 0.0272 - accuracy: 0.9712\n",
      "y_pred: [1.4569774e-07]\n",
      "Model loss on the test set: 0.02716439589858055\n",
      "Model accuracy on the test set: 97.12%\n"
     ]
    }
   ],
   "source": [
    "# Check kthe accuracy of our model\n",
    "y_pred = model.predict(X_test)\n",
    "loss, accuracy = model.evaluate(X_test, y_test)\n",
    "print(f\"y_pred: {y_pred[0]}\")\n",
    "print(f\"Model loss on the test set: {loss}\")\n",
    "print(f\"Model accuracy on the test set: {(accuracy*100):.2f}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "683a7406",
   "metadata": {
    "papermill": {
     "duration": 0.118777,
     "end_time": "2021-12-06T23:16:05.999420",
     "exception": false,
     "start_time": "2021-12-06T23:16:05.880643",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Looks like our model is good!"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36b8c04b",
   "metadata": {
    "papermill": {
     "duration": 0.116271,
     "end_time": "2021-12-06T23:16:06.232735",
     "exception": false,
     "start_time": "2021-12-06T23:16:06.116464",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### **Let's plot the Confusion Matrix**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "1af915ef",
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-12-06T23:16:06.467143Z",
     "iopub.status.busy": "2021-12-06T23:16:06.466468Z",
     "iopub.status.idle": "2021-12-06T23:16:06.843873Z",
     "shell.execute_reply": "2021-12-06T23:16:06.843236Z",
     "shell.execute_reply.started": "2021-12-06T23:15:08.653178Z"
    },
    "papermill": {
     "duration": 0.49563,
     "end_time": "2021-12-06T23:16:06.844046",
     "exception": false,
     "start_time": "2021-12-06T23:16:06.348416",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Note: the confusion matrix code we're about to ride is a remix of scikit-learn's plot confusion matrix function\n",
    "import itertools\n",
    "\n",
    "figsize = (10, 10)\n",
    "\n",
    "# Create the confusion matrix\n",
    "cm = confusion_matrix(y_test, tf.round(y_pred))\n",
    "cm_norm = cm.astype(\"float\") / cm.sum(axis=1)[:, np.newaxis] # normalize our confusion matrix\n",
    "n_classes = cm.shape[0]\n",
    "\n",
    "# Let's prettify it \n",
    "fig, ax = plt.subplots(figsize=figsize)\n",
    "# Create a matrix plot\n",
    "cax = ax.matshow(cm, cmap=plt.cm.Blues)\n",
    "fig.colorbar(cax)\n",
    "\n",
    "# Create classes\n",
    "classes= False\n",
    "\n",
    "if classes:\n",
    "    labels = classes\n",
    "else:\n",
    "    labels = np.arange(cm.shape[0])\n",
    "    \n",
    "# Label the axes\n",
    "ax.set(\n",
    "    title='Confusion Matrix',\n",
    "    xlabel='Predicted Label',\n",
    "    ylabel='True Label',\n",
    "    xticks=np.arange(n_classes),\n",
    "    yticks=np.arange(n_classes),\n",
    "    xticklabels=labels,\n",
    "    yticklabels=labels\n",
    ")\n",
    "\n",
    "# Set x-axis labels to bottom\n",
    "ax.xaxis.set_label_position(\"bottom\")\n",
    "ax.xaxis.tick_bottom()\n",
    "\n",
    "# Adjust the label size \n",
    "ax.yaxis.label.set_size(20)\n",
    "ax.xaxis.label.set_size(20)\n",
    "ax.title.set_size(20)\n",
    "\n",
    "# Set the threshold for diffenrent colors\n",
    "threshold = (cm.max() + cm.min()) / 2.\n",
    "\n",
    "# Plot the text on each cell\n",
    "for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n",
    "    plt.text(j, i, f\"{cm[i, j]} ({cm_norm[i, j] * 100:.1f}%)\",\n",
    "             horizontalalignment='center',\n",
    "             color='white' if cm[i, j] > threshold else 'black',\n",
    "             size=15);\n",
    "fig.show();"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "50dd45d6",
   "metadata": {
    "papermill": {
     "duration": 0.119436,
     "end_time": "2021-12-06T23:16:07.081944",
     "exception": false,
     "start_time": "2021-12-06T23:16:06.962508",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **On Going...**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49198307",
   "metadata": {
    "papermill": {
     "duration": 0.118194,
     "end_time": "2021-12-06T23:16:07.319086",
     "exception": false,
     "start_time": "2021-12-06T23:16:07.200892",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "#### **Next Updates will add More EDA, wait for it...**"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.12"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 43.759205,
   "end_time": "2021-12-06T23:16:10.248748",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2021-12-06T23:15:26.489543",
   "version": "2.3.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}