From 2ec0020b28e9bec84b67fc05ebae259cb2fdcf81 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pawe=C5=82=20=C5=81=C4=85czkowski?= <broketmpl@gmail.com>
Date: Mon, 10 Jun 2024 12:20:15 +0200
Subject: [PATCH] IUM_13 - project for overleaf

---
 IUM_13.ipynb | 1601 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 1601 insertions(+)
 create mode 100644 IUM_13.ipynb

diff --git a/IUM_13.ipynb b/IUM_13.ipynb
new file mode 100644
index 0000000..6233abb
--- /dev/null
+++ b/IUM_13.ipynb
@@ -0,0 +1,1601 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Experiments - neural networks in breast cancer classification problem"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "e1e08c454a98dd01"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "outputs": [],
+   "source": [
+    "# Data manipulation\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Data visualization\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "sns.set_style('whitegrid')\n",
+    "\n",
+    "# Data preprocessing\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "# Metrics\n",
+    "from sklearn.metrics import confusion_matrix, classification_report\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "\n",
+    "# Deep learning\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T15:50:23.912931300Z",
+     "start_time": "2024-06-08T15:50:19.472582100Z"
+    }
+   },
+   "id": "c0c219cc1bbd4c7a"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Methods for visualizing confusion matrix and classification report"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "6064474e7a56f80e"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [],
+   "source": [
+    "# Plot confusion matrix\n",
+    "def plot_confusion_matrix(cm, classes, title='Confusion matrix', cmap='Blues', figsize=(10, 6), axis=None):\n",
+    "    \"\"\"\n",
+    "    Plot the confusion matrix.\n",
+    "    \"\"\"\n",
+    "    if axis is None:\n",
+    "        fig, ax = plt.subplots(figsize=figsize)\n",
+    "    else:\n",
+    "        ax = axis\n",
+    "        \n",
+    "    sns.heatmap(cm, annot=True, fmt='d', xticklabels=classes, yticklabels=classes, cmap=cmap, ax=ax)\n",
+    "    \n",
+    "    ax.set_title(title)\n",
+    "    ax.set_xlabel('Predicted label')\n",
+    "    ax.set_ylabel('True label')\n",
+    "    \n",
+    "    if axis is None:\n",
+    "        plt.show()  \n",
+    "    \n",
+    "# Plot classification report\n",
+    "def plot_classification_report(report, title='Classification report', axis=None):\n",
+    "    \"\"\"\n",
+    "    Plot the classification report.\n",
+    "    \"\"\"\n",
+    "    if axis is None:\n",
+    "        fig, ax = plt.subplots(figsize=(10, 6))\n",
+    "    else:\n",
+    "        ax = axis\n",
+    "        \n",
+    "    sns.heatmap(pd.DataFrame(report).iloc[:-1, :].T, annot=True, cmap='Blues', ax=ax)\n",
+    "    \n",
+    "    ax.set_title('Classification report')\n",
+    "    ax.set_xlabel('Metrics')\n",
+    "    ax.set_ylabel('Classes')\n",
+    "    \n",
+    "    if axis is None:\n",
+    "        plt.show()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T15:51:26.166904900Z",
+     "start_time": "2024-06-08T15:51:26.145794400Z"
+    }
+   },
+   "id": "689b41e45e990a1b"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Load data"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "c7ad4d251442c34c"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "outputs": [],
+   "source": [
+    "# Load data\n",
+    "data = pd.read_csv('datasets/data.csv')\n",
+    "\n",
+    "# Delete unnecessary columns\n",
+    "data.drop(['id'], axis=1, inplace=True)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T15:52:50.237396100Z",
+     "start_time": "2024-06-08T15:52:50.201061700Z"
+    }
+   },
+   "id": "54411dcad03637c2"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "     diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean  \\\n0          1.0     0.521037      0.022658        0.545989   0.363733   \n1          1.0     0.643144      0.272574        0.615783   0.501591   \n2          1.0     0.601496      0.390260        0.595743   0.449417   \n3          1.0     0.210090      0.360839        0.233501   0.102906   \n4          1.0     0.629893      0.156578        0.630986   0.489290   \n..         ...          ...           ...             ...        ...   \n564        1.0     0.690000      0.428813        0.678668   0.566490   \n565        1.0     0.622320      0.626987        0.604036   0.474019   \n566        1.0     0.455251      0.621238        0.445788   0.303118   \n567        1.0     0.644564      0.663510        0.665538   0.475716   \n568        0.0     0.036869      0.501522        0.028540   0.015907   \n\n     smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n0           0.593753          0.792037        0.703140             0.731113   \n1           0.289880          0.181768        0.203608             0.348757   \n2           0.514309          0.431017        0.462512             0.635686   \n3           0.811321          0.811361        0.565604             0.522863   \n4           0.430351          0.347893        0.463918             0.518390   \n..               ...               ...             ...                  ...   \n564         0.526948          0.296055        0.571462             0.690358   \n565         0.407782          0.257714        0.337395             0.486630   \n566         0.288165          0.254340        0.216753             0.263519   \n567         0.588336          0.790197        0.823336             0.755467   \n568         0.000000          0.074351        0.000000             0.000000   \n\n     symmetry_mean  ...  radius_worst  texture_worst  perimeter_worst  \\\n0         0.686364  ...      0.620776       0.141525         0.668310   \n1         0.379798  ...      0.606901       0.303571         0.539818   \n2         0.509596  ...      0.556386       0.360075         0.508442   \n3         0.776263  ...      0.248310       0.385928         0.241347   \n4         0.378283  ...      0.519744       0.123934         0.506948   \n..             ...  ...           ...            ...              ...   \n564       0.336364  ...      0.623266       0.383262         0.576174   \n565       0.349495  ...      0.560655       0.699094         0.520892   \n566       0.267677  ...      0.393099       0.589019         0.379949   \n567       0.675253  ...      0.633582       0.730277         0.668310   \n568       0.266162  ...      0.054287       0.489072         0.043578   \n\n     area_worst  smoothness_worst  compactness_worst  concavity_worst  \\\n0      0.450698          0.601136           0.619292         0.568610   \n1      0.435214          0.347553           0.154563         0.192971   \n2      0.374508          0.483590           0.385375         0.359744   \n3      0.094008          0.915472           0.814012         0.548642   \n4      0.341575          0.437364           0.172415         0.319489   \n..          ...               ...                ...              ...   \n564    0.452664          0.461137           0.178527         0.328035   \n565    0.379915          0.300007           0.159997         0.256789   \n566    0.230731          0.282177           0.273705         0.271805   \n567    0.402035          0.619626           0.815758         0.749760   \n568    0.020497          0.124084           0.036043         0.000000   \n\n     concave points_worst  symmetry_worst  fractal_dimension_worst  \n0                0.912027        0.598462                 0.418864  \n1                0.639175        0.233590                 0.222878  \n2                0.835052        0.403706                 0.213433  \n3                0.884880        1.000000                 0.773711  \n4                0.558419        0.157500                 0.142595  \n..                    ...             ...                      ...  \n564              0.761512        0.097575                 0.105667  \n565              0.559450        0.198502                 0.074315  \n566              0.487285        0.128721                 0.151909  \n567              0.910653        0.497142                 0.452315  \n568              0.000000        0.257441                 0.100682  \n\n[569 rows x 31 columns]",
+      "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>diagnosis</th>\n      <th>radius_mean</th>\n      <th>texture_mean</th>\n      <th>perimeter_mean</th>\n      <th>area_mean</th>\n      <th>smoothness_mean</th>\n      <th>compactness_mean</th>\n      <th>concavity_mean</th>\n      <th>concave points_mean</th>\n      <th>symmetry_mean</th>\n      <th>...</th>\n      <th>radius_worst</th>\n      <th>texture_worst</th>\n      <th>perimeter_worst</th>\n      <th>area_worst</th>\n      <th>smoothness_worst</th>\n      <th>compactness_worst</th>\n      <th>concavity_worst</th>\n      <th>concave points_worst</th>\n      <th>symmetry_worst</th>\n      <th>fractal_dimension_worst</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1.0</td>\n      <td>0.521037</td>\n      <td>0.022658</td>\n      <td>0.545989</td>\n      <td>0.363733</td>\n      <td>0.593753</td>\n      <td>0.792037</td>\n      <td>0.703140</td>\n      <td>0.731113</td>\n      <td>0.686364</td>\n      <td>...</td>\n      <td>0.620776</td>\n      <td>0.141525</td>\n      <td>0.668310</td>\n      <td>0.450698</td>\n      <td>0.601136</td>\n      <td>0.619292</td>\n      <td>0.568610</td>\n      <td>0.912027</td>\n      <td>0.598462</td>\n      <td>0.418864</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1.0</td>\n      <td>0.643144</td>\n      <td>0.272574</td>\n      <td>0.615783</td>\n      <td>0.501591</td>\n      <td>0.289880</td>\n      <td>0.181768</td>\n      <td>0.203608</td>\n      <td>0.348757</td>\n      <td>0.379798</td>\n      <td>...</td>\n      <td>0.606901</td>\n      <td>0.303571</td>\n      <td>0.539818</td>\n      <td>0.435214</td>\n      <td>0.347553</td>\n      <td>0.154563</td>\n      <td>0.192971</td>\n      <td>0.639175</td>\n      <td>0.233590</td>\n      <td>0.222878</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>1.0</td>\n      <td>0.601496</td>\n      <td>0.390260</td>\n      <td>0.595743</td>\n      <td>0.449417</td>\n      <td>0.514309</td>\n      <td>0.431017</td>\n      <td>0.462512</td>\n      <td>0.635686</td>\n      <td>0.509596</td>\n      <td>...</td>\n      <td>0.556386</td>\n      <td>0.360075</td>\n      <td>0.508442</td>\n      <td>0.374508</td>\n      <td>0.483590</td>\n      <td>0.385375</td>\n      <td>0.359744</td>\n      <td>0.835052</td>\n      <td>0.403706</td>\n      <td>0.213433</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1.0</td>\n      <td>0.210090</td>\n      <td>0.360839</td>\n      <td>0.233501</td>\n      <td>0.102906</td>\n      <td>0.811321</td>\n      <td>0.811361</td>\n      <td>0.565604</td>\n      <td>0.522863</td>\n      <td>0.776263</td>\n      <td>...</td>\n      <td>0.248310</td>\n      <td>0.385928</td>\n      <td>0.241347</td>\n      <td>0.094008</td>\n      <td>0.915472</td>\n      <td>0.814012</td>\n      <td>0.548642</td>\n      <td>0.884880</td>\n      <td>1.000000</td>\n      <td>0.773711</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>1.0</td>\n      <td>0.629893</td>\n      <td>0.156578</td>\n      <td>0.630986</td>\n      <td>0.489290</td>\n      <td>0.430351</td>\n      <td>0.347893</td>\n      <td>0.463918</td>\n      <td>0.518390</td>\n      <td>0.378283</td>\n      <td>...</td>\n      <td>0.519744</td>\n      <td>0.123934</td>\n      <td>0.506948</td>\n      <td>0.341575</td>\n      <td>0.437364</td>\n      <td>0.172415</td>\n      <td>0.319489</td>\n      <td>0.558419</td>\n      <td>0.157500</td>\n      <td>0.142595</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>564</th>\n      <td>1.0</td>\n      <td>0.690000</td>\n      <td>0.428813</td>\n      <td>0.678668</td>\n      <td>0.566490</td>\n      <td>0.526948</td>\n      <td>0.296055</td>\n      <td>0.571462</td>\n      <td>0.690358</td>\n      <td>0.336364</td>\n      <td>...</td>\n      <td>0.623266</td>\n      <td>0.383262</td>\n      <td>0.576174</td>\n      <td>0.452664</td>\n      <td>0.461137</td>\n      <td>0.178527</td>\n      <td>0.328035</td>\n      <td>0.761512</td>\n      <td>0.097575</td>\n      <td>0.105667</td>\n    </tr>\n    <tr>\n      <th>565</th>\n      <td>1.0</td>\n      <td>0.622320</td>\n      <td>0.626987</td>\n      <td>0.604036</td>\n      <td>0.474019</td>\n      <td>0.407782</td>\n      <td>0.257714</td>\n      <td>0.337395</td>\n      <td>0.486630</td>\n      <td>0.349495</td>\n      <td>...</td>\n      <td>0.560655</td>\n      <td>0.699094</td>\n      <td>0.520892</td>\n      <td>0.379915</td>\n      <td>0.300007</td>\n      <td>0.159997</td>\n      <td>0.256789</td>\n      <td>0.559450</td>\n      <td>0.198502</td>\n      <td>0.074315</td>\n    </tr>\n    <tr>\n      <th>566</th>\n      <td>1.0</td>\n      <td>0.455251</td>\n      <td>0.621238</td>\n      <td>0.445788</td>\n      <td>0.303118</td>\n      <td>0.288165</td>\n      <td>0.254340</td>\n      <td>0.216753</td>\n      <td>0.263519</td>\n      <td>0.267677</td>\n      <td>...</td>\n      <td>0.393099</td>\n      <td>0.589019</td>\n      <td>0.379949</td>\n      <td>0.230731</td>\n      <td>0.282177</td>\n      <td>0.273705</td>\n      <td>0.271805</td>\n      <td>0.487285</td>\n      <td>0.128721</td>\n      <td>0.151909</td>\n    </tr>\n    <tr>\n      <th>567</th>\n      <td>1.0</td>\n      <td>0.644564</td>\n      <td>0.663510</td>\n      <td>0.665538</td>\n      <td>0.475716</td>\n      <td>0.588336</td>\n      <td>0.790197</td>\n      <td>0.823336</td>\n      <td>0.755467</td>\n      <td>0.675253</td>\n      <td>...</td>\n      <td>0.633582</td>\n      <td>0.730277</td>\n      <td>0.668310</td>\n      <td>0.402035</td>\n      <td>0.619626</td>\n      <td>0.815758</td>\n      <td>0.749760</td>\n      <td>0.910653</td>\n      <td>0.497142</td>\n      <td>0.452315</td>\n    </tr>\n    <tr>\n      <th>568</th>\n      <td>0.0</td>\n      <td>0.036869</td>\n      <td>0.501522</td>\n      <td>0.028540</td>\n      <td>0.015907</td>\n      <td>0.000000</td>\n      <td>0.074351</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.266162</td>\n      <td>...</td>\n      <td>0.054287</td>\n      <td>0.489072</td>\n      <td>0.043578</td>\n      <td>0.020497</td>\n      <td>0.124084</td>\n      <td>0.036043</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.257441</td>\n      <td>0.100682</td>\n    </tr>\n  </tbody>\n</table>\n<p>569 rows × 31 columns</p>\n</div>"
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T17:45:09.614420700Z",
+     "start_time": "2024-06-08T17:45:09.479821700Z"
+    }
+   },
+   "id": "4294a8ce6b3bf0d5"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Data preprocessing"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "74e70a93ab91ece2"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "outputs": [],
+   "source": [
+    "# Split data into training and testing sets\n",
+    "X = data.iloc[:, 1:]\n",
+    "y = data.iloc[:, 0]\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# Standardize the data\n",
+    "scaler = StandardScaler()\n",
+    "X_train = scaler.fit_transform(X_train)\n",
+    "X_test = scaler.transform(X_test)\n",
+    "\n",
+    "# Convert data to PyTorch tensors\n",
+    "X_train = torch.FloatTensor(X_train)\n",
+    "X_test = torch.FloatTensor(X_test)\n",
+    "y_train = torch.FloatTensor(y_train.values).view(-1, 1)\n",
+    "y_test = torch.FloatTensor(y_test.values).view(-1, 1)\n",
+    "\n",
+    "# Transfer data to GPU if available\n",
+    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
+    "\n",
+    "X_train = X_train.to(device)\n",
+    "X_test = X_test.to(device)\n",
+    "y_train = y_train.to(device)\n",
+    "y_test = y_test.to(device)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:03:06.981298Z",
+     "start_time": "2024-06-08T16:03:06.957759100Z"
+    }
+   },
+   "id": "1fcdf94e46907575"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Neural network architectures"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "1a150bd5c3a959"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "outputs": [],
+   "source": [
+    "# V1\n",
+    "# Three fully connected layers with ReLU activation function\n",
+    "# Output layer with Sigmoid activation function\n",
+    "class NeuralNetworkV1(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size):\n",
+    "        super(NeuralNetworkV1, self).__init__()\n",
+    "        \n",
+    "        self.fc1 = nn.Linear(input_size, hidden_size)\n",
+    "        self.fc2 = nn.Linear(hidden_size, hidden_size // 2)\n",
+    "        self.fc3 = nn.Linear(hidden_size // 2, 1)\n",
+    "\n",
+    "        self.relu = nn.ReLU()\n",
+    "        self.sigmoid = nn.Sigmoid()\n",
+    "        \n",
+    "    def forward(self, x):\n",
+    "        out = self.fc1(x)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.fc2(out)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.fc3(out)\n",
+    "        out = self.sigmoid(out)\n",
+    "        return out"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:04:14.970423300Z",
+     "start_time": "2024-06-08T16:04:14.953618100Z"
+    }
+   },
+   "id": "9fba79643e9e76f3"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "outputs": [],
+   "source": [
+    "# V2\n",
+    "# Four fully connected layers with ReLU activation function and dropout layers\n",
+    "# Output layer with Sigmoid activation function\n",
+    "class NeuralNetworkV2(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size):\n",
+    "        super(NeuralNetworkV2, self).__init__()\n",
+    "        \n",
+    "        self.fc1 = nn.Linear(input_size, hidden_size)\n",
+    "        self.dropout1 = nn.Dropout(0.5)\n",
+    "        self.fc2 = nn.Linear(hidden_size, hidden_size // 2)\n",
+    "        self.dropout2 = nn.Dropout(0.5)\n",
+    "        self.fc3 = nn.Linear(hidden_size // 2, hidden_size // 4)\n",
+    "        self.fc4 = nn.Linear(hidden_size // 4, 1)\n",
+    "\n",
+    "        self.relu = nn.ReLU()\n",
+    "        self.sigmoid = nn.Sigmoid()\n",
+    "        \n",
+    "    def forward(self, x):\n",
+    "        out = self.fc1(x)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.dropout1(out)\n",
+    "        out = self.fc2(out)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.dropout2(out)\n",
+    "        out = self.fc3(out)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.fc4(out)\n",
+    "        out = self.sigmoid(out)\n",
+    "        return out"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:04:15.743609500Z",
+     "start_time": "2024-06-08T16:04:15.731835400Z"
+    }
+   },
+   "id": "d9d6297f85fb83fc"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "outputs": [],
+   "source": [
+    "# V3\n",
+    "# Four fully connected layers with Leaky ReLU activation function\n",
+    "# Output layer with Sigmoid activation function\n",
+    "class NeuralNetworkV3(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size):\n",
+    "        super(NeuralNetworkV3, self).__init__()\n",
+    "        \n",
+    "        self.fc1 = nn.Linear(input_size, hidden_size)\n",
+    "        self.fc2 = nn.Linear(hidden_size, hidden_size // 2)\n",
+    "        self.fc3 = nn.Linear(hidden_size // 2, hidden_size // 4)\n",
+    "        self.fc4 = nn.Linear(hidden_size // 4, 1)\n",
+    "\n",
+    "        self.leaky_relu = nn.LeakyReLU(0.1)\n",
+    "        self.sigmoid = nn.Sigmoid()\n",
+    "        \n",
+    "    def forward(self, x):\n",
+    "        out = self.fc1(x)\n",
+    "        out = self.leaky_relu(out)\n",
+    "        out = self.fc2(out)\n",
+    "        out = self.leaky_relu(out)\n",
+    "        out = self.fc3(out)\n",
+    "        out = self.leaky_relu(out)\n",
+    "        out = self.fc4(out)\n",
+    "        out = self.sigmoid(out)\n",
+    "        return out"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:04:15.989218400Z",
+     "start_time": "2024-06-08T16:04:15.971488Z"
+    }
+   },
+   "id": "e9d8ad2014841d93"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "outputs": [],
+   "source": [
+    "# V4\n",
+    "# Two convolutional layers with ReLU activation function and max pooling layers\n",
+    "# Two fully connected layers with ReLU activation function\n",
+    "# Output layer with Sigmoid activation function\n",
+    "class NeuralNetworkV4(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size):\n",
+    "        super(NeuralNetworkV4, self).__init__()\n",
+    "        \n",
+    "        self.conv1 = nn.Conv1d(1, 16, kernel_size=3, stride=1, padding=1)\n",
+    "        self.conv2 = nn.Conv1d(16, 32, kernel_size=3, stride=1, padding=1)\n",
+    "        self.pool = nn.MaxPool1d(kernel_size=2, stride=2, padding=0)\n",
+    "        \n",
+    "        # Calculate the output size after the conv and pooling layers\n",
+    "        conv_output_size = input_size // 2  # After two pooling layers with stride 2\n",
+    "        conv_output_size = conv_output_size // 2  # After the second pooling layer\n",
+    "        \n",
+    "        self.fc1 = nn.Linear(32 * conv_output_size, hidden_size)\n",
+    "        self.fc2 = nn.Linear(hidden_size, 1)\n",
+    "\n",
+    "        self.relu = nn.ReLU()\n",
+    "        self.sigmoid = nn.Sigmoid()\n",
+    "        \n",
+    "    def forward(self, x):\n",
+    "        x = x.unsqueeze(1)  # Add channel dimension\n",
+    "        out = self.conv1(x)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.pool(out)\n",
+    "        out = self.conv2(out)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.pool(out)\n",
+    "        out = out.view(out.size(0), -1)  # Flatten the tensor\n",
+    "        out = self.fc1(out)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.fc2(out)\n",
+    "        out = self.sigmoid(out)\n",
+    "        return out"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:25:44.294141500Z",
+     "start_time": "2024-06-08T16:25:44.266927300Z"
+    }
+   },
+   "id": "19adc0031ce51f33"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "outputs": [],
+   "source": [
+    "# V5\n",
+    "# LSTM layer with ReLU activation function\n",
+    "# Two fully connected layers with ReLU activation function\n",
+    "# Output layer with Sigmoid activation function\n",
+    "class NeuralNetworkV5(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size):\n",
+    "        super(NeuralNetworkV5, self).__init__()\n",
+    "        \n",
+    "        self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)\n",
+    "        self.fc1 = nn.Linear(hidden_size, hidden_size // 2)\n",
+    "        self.fc2 = nn.Linear(hidden_size // 2, 1)\n",
+    "\n",
+    "        self.relu = nn.ReLU()\n",
+    "        self.sigmoid = nn.Sigmoid()\n",
+    "        \n",
+    "    def forward(self, x):\n",
+    "        out, _ = self.lstm(x)\n",
+    "        out = out[:, -1, :]  # Take the last output of the LSTM\n",
+    "        out = self.fc1(out)\n",
+    "        out = self.relu(out)\n",
+    "        out = self.fc2(out)\n",
+    "        out = self.sigmoid(out)\n",
+    "        return out"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:25:45.194410100Z",
+     "start_time": "2024-06-08T16:25:45.173984800Z"
+    }
+   },
+   "id": "3b404d9e7019d04"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Training and evaluation"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "7966001ff35b88d7"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "outputs": [],
+   "source": [
+    "# Training function\n",
+    "def train(model, X_train, y_train, criterion, optimizer, epochs=100):\n",
+    "    \"\"\"\n",
+    "    Train the neural network.\n",
+    "    \"\"\"\n",
+    "    for epoch in range(epochs):\n",
+    "        optimizer.zero_grad()\n",
+    "        y_pred = model(X_train)\n",
+    "        loss = criterion(y_pred, y_train)\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "        \n",
+    "        if (epoch + 1) % 10 == 0:\n",
+    "            print(f'Epoch {epoch + 1}/{epochs}, Loss: {loss.item()}')"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:25:46.534167500Z",
+     "start_time": "2024-06-08T16:25:46.524741Z"
+    }
+   },
+   "id": "ebab09eac524c418"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "outputs": [],
+   "source": [
+    "# Evaluation function\n",
+    "def evaluate(model, X_test, y_test):\n",
+    "    \"\"\"\n",
+    "    Evaluate the neural network.\n",
+    "    \"\"\"\n",
+    "    with torch.no_grad():\n",
+    "        y_pred = model(X_test)\n",
+    "        y_pred = (y_pred > 0.5).float()\n",
+    "        cm = confusion_matrix(y_test.cpu(), y_pred.cpu())\n",
+    "        cr = classification_report(y_test.cpu(), y_pred.cpu(), target_names=['Benign', 'Malignant'], output_dict=True)\n",
+    "        acc = accuracy_score(y_test.cpu(), y_pred.cpu())\n",
+    "        \n",
+    "        return cm, cr, acc"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:25:46.825080Z",
+     "start_time": "2024-06-08T16:25:46.805541600Z"
+    }
+   },
+   "id": "b89d7e317f1c8b63"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "outputs": [],
+   "source": [
+    "# Neural network parameters\n",
+    "input_size = X_train.shape[1]\n",
+    "hidden_size = 128\n",
+    "learning_rate = 0.001\n",
+    "weight_decay = 0.0001\n",
+    "epochs = 1000"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:25:47.991207300Z",
+     "start_time": "2024-06-08T16:25:47.974823800Z"
+    }
+   },
+   "id": "d967f53803f97353"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Neural network V1"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "b8df2e2d1ce6e786"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/1000, Loss: 0.4779872000217438\n",
+      "Epoch 20/1000, Loss: 0.27251550555229187\n",
+      "Epoch 30/1000, Loss: 0.15164388716220856\n",
+      "Epoch 40/1000, Loss: 0.10145729035139084\n",
+      "Epoch 50/1000, Loss: 0.07789547741413116\n",
+      "Epoch 60/1000, Loss: 0.06484830379486084\n",
+      "Epoch 70/1000, Loss: 0.05551866441965103\n",
+      "Epoch 80/1000, Loss: 0.04840008169412613\n",
+      "Epoch 90/1000, Loss: 0.042578838765621185\n",
+      "Epoch 100/1000, Loss: 0.03765585273504257\n",
+      "Epoch 110/1000, Loss: 0.03336893767118454\n",
+      "Epoch 120/1000, Loss: 0.02957029454410076\n",
+      "Epoch 130/1000, Loss: 0.02613999880850315\n",
+      "Epoch 140/1000, Loss: 0.023030269891023636\n",
+      "Epoch 150/1000, Loss: 0.02021847851574421\n",
+      "Epoch 160/1000, Loss: 0.01771070621907711\n",
+      "Epoch 170/1000, Loss: 0.015495861880481243\n",
+      "Epoch 180/1000, Loss: 0.013572530820965767\n",
+      "Epoch 190/1000, Loss: 0.011898759752511978\n",
+      "Epoch 200/1000, Loss: 0.010441687889397144\n",
+      "Epoch 210/1000, Loss: 0.009163236245512962\n",
+      "Epoch 220/1000, Loss: 0.00809294544160366\n",
+      "Epoch 230/1000, Loss: 0.007174020167440176\n",
+      "Epoch 240/1000, Loss: 0.006399359088391066\n",
+      "Epoch 250/1000, Loss: 0.005741355009377003\n",
+      "Epoch 260/1000, Loss: 0.005172951612621546\n",
+      "Epoch 270/1000, Loss: 0.004688368644565344\n",
+      "Epoch 280/1000, Loss: 0.004283885937184095\n",
+      "Epoch 290/1000, Loss: 0.003929890692234039\n",
+      "Epoch 300/1000, Loss: 0.0036243184003978968\n",
+      "Epoch 310/1000, Loss: 0.0033553754910826683\n",
+      "Epoch 320/1000, Loss: 0.0031130558345466852\n",
+      "Epoch 330/1000, Loss: 0.0028987200930714607\n",
+      "Epoch 340/1000, Loss: 0.0027084406465291977\n",
+      "Epoch 350/1000, Loss: 0.0025372877717018127\n",
+      "Epoch 360/1000, Loss: 0.002381594618782401\n",
+      "Epoch 370/1000, Loss: 0.002238793997094035\n",
+      "Epoch 380/1000, Loss: 0.002110145753249526\n",
+      "Epoch 390/1000, Loss: 0.001990949036553502\n",
+      "Epoch 400/1000, Loss: 0.0018805447034537792\n",
+      "Epoch 410/1000, Loss: 0.0017787017859518528\n",
+      "Epoch 420/1000, Loss: 0.0016847399529069662\n",
+      "Epoch 430/1000, Loss: 0.001597930327989161\n",
+      "Epoch 440/1000, Loss: 0.001518208417110145\n",
+      "Epoch 450/1000, Loss: 0.0014447758439928293\n",
+      "Epoch 460/1000, Loss: 0.0013784606708213687\n",
+      "Epoch 470/1000, Loss: 0.0013172627659514546\n",
+      "Epoch 480/1000, Loss: 0.0012608648976311088\n",
+      "Epoch 490/1000, Loss: 0.001208683243021369\n",
+      "Epoch 500/1000, Loss: 0.0011611600639298558\n",
+      "Epoch 510/1000, Loss: 0.0011176610132679343\n",
+      "Epoch 520/1000, Loss: 0.0010775947012007236\n",
+      "Epoch 530/1000, Loss: 0.0010414356365799904\n",
+      "Epoch 540/1000, Loss: 0.0010077828774228692\n",
+      "Epoch 550/1000, Loss: 0.000977047486230731\n",
+      "Epoch 560/1000, Loss: 0.0009483486064709723\n",
+      "Epoch 570/1000, Loss: 0.0009219619678333402\n",
+      "Epoch 580/1000, Loss: 0.000897533493116498\n",
+      "Epoch 590/1000, Loss: 0.0008748812833800912\n",
+      "Epoch 600/1000, Loss: 0.0008537117973901331\n",
+      "Epoch 610/1000, Loss: 0.0008338657789863646\n",
+      "Epoch 620/1000, Loss: 0.0008152445661835372\n",
+      "Epoch 630/1000, Loss: 0.000797846878413111\n",
+      "Epoch 640/1000, Loss: 0.0007811780087649822\n",
+      "Epoch 650/1000, Loss: 0.0007652725907973945\n",
+      "Epoch 660/1000, Loss: 0.0007502862135879695\n",
+      "Epoch 670/1000, Loss: 0.0007362824399024248\n",
+      "Epoch 680/1000, Loss: 0.0007233091746456921\n",
+      "Epoch 690/1000, Loss: 0.0007109907455742359\n",
+      "Epoch 700/1000, Loss: 0.0006993163260631263\n",
+      "Epoch 710/1000, Loss: 0.0006883330643177032\n",
+      "Epoch 720/1000, Loss: 0.000678009819239378\n",
+      "Epoch 730/1000, Loss: 0.0006681602098979056\n",
+      "Epoch 740/1000, Loss: 0.0006588594405911863\n",
+      "Epoch 750/1000, Loss: 0.0006500912713818252\n",
+      "Epoch 760/1000, Loss: 0.0006416388787329197\n",
+      "Epoch 770/1000, Loss: 0.0006337724043987691\n",
+      "Epoch 780/1000, Loss: 0.0006261061644181609\n",
+      "Epoch 790/1000, Loss: 0.0006186887621879578\n",
+      "Epoch 800/1000, Loss: 0.0006119576282799244\n",
+      "Epoch 810/1000, Loss: 0.0006054439581930637\n",
+      "Epoch 820/1000, Loss: 0.0005992540973238647\n",
+      "Epoch 830/1000, Loss: 0.0005932800122536719\n",
+      "Epoch 840/1000, Loss: 0.000587515824008733\n",
+      "Epoch 850/1000, Loss: 0.0005819853395223618\n",
+      "Epoch 860/1000, Loss: 0.0005764576490037143\n",
+      "Epoch 870/1000, Loss: 0.0005712246056646109\n",
+      "Epoch 880/1000, Loss: 0.0005661725299432874\n",
+      "Epoch 890/1000, Loss: 0.0005614019464701414\n",
+      "Epoch 900/1000, Loss: 0.0005567952175624669\n",
+      "Epoch 910/1000, Loss: 0.0005523671861737967\n",
+      "Epoch 920/1000, Loss: 0.000548191019333899\n",
+      "Epoch 930/1000, Loss: 0.0005440027453005314\n",
+      "Epoch 940/1000, Loss: 0.0005400135414674878\n",
+      "Epoch 950/1000, Loss: 0.0005360668292269111\n",
+      "Epoch 960/1000, Loss: 0.0005323308287188411\n",
+      "Epoch 970/1000, Loss: 0.0005282927886582911\n",
+      "Epoch 980/1000, Loss: 0.0005240424652583897\n",
+      "Epoch 990/1000, Loss: 0.0005197781720198691\n",
+      "Epoch 1000/1000, Loss: 0.0005156174884177744\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Neural network V1\n",
+    "model_v1 = NeuralNetworkV1(input_size, hidden_size).to(device)\n",
+    "criterion_v1 = nn.BCELoss()\n",
+    "optimizer_v1 = optim.Adam(model_v1.parameters(), lr=learning_rate, weight_decay=weight_decay)\n",
+    "\n",
+    "# Train the model\n",
+    "train(model_v1, X_train, y_train, criterion_v1, optimizer_v1, epochs)\n",
+    "\n",
+    "# Evaluate the model\n",
+    "cm_v1, cr_v1, acc_v1 = evaluate(model_v1, X_test, y_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:07:07.255395800Z",
+     "start_time": "2024-06-08T16:07:04.326790700Z"
+    }
+   },
+   "id": "7f48dfd17faaa0b3"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot confusion matrix\n",
+    "plot_confusion_matrix(cm_v1, ['Benign', 'Malignant'], title='Confusion matrix - Neural Network V1')"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:07:09.111692Z",
+     "start_time": "2024-06-08T16:07:08.856357500Z"
+    }
+   },
+   "id": "dd60663756e0d8c0"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAw0AAAIhCAYAAAAM+FYZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAACHk0lEQVR4nOzdd3hU1dbH8e+kTBJSIAQIVToEAoQQIHRBQOkglov6gggqKCBKU+BKkyYqKqACKioWpFsQEOlSBAxdEjoYWgik9zbvH8iYcRBJrslJyO9zn3kus8+eM+tENpk1a+99TBaLxYKIiIiIiMjfcDA6ABERERERKdiUNIiIiIiIyG0paRARERERkdtS0iAiIiIiIrelpEFERERERG5LSYOIiIiIiNyWkgYREREREbktJQ0iIiIiInJbShpERAoB3Yfz7+lnIyKS95Q0iEiBcuTIEUaPHk3btm1p0KABHTp04NVXXyU8PNymX+3atZk7d26+xjZ37lxq165tfZ6QkMDgwYMJCAigSZMmnDt3jtq1a7Nq1ap/9X03bdrEyy+/bH2+Z88eateuzZ49e/7V9yls4uLiGDNmDL/++qvRoYiI3PWcjA5AROSmL7/8kunTpxMcHMzIkSMpU6YM58+f5+OPP2bDhg189tln+Pn5GRbfI488QuvWra3Pv/nmG7Zs2cKECROoWbMm5cuXZ+nSpdxzzz3/6vt++umnNs/9/f1ZunQpNWrU+Fffp7AJDQ3l22+/5aGHHjI6FBGRu56SBhEpEEJCQpg2bRpPPPEE48ePt7YHBwfToUMHevXqxbhx4/71b/FzomzZspQtW9b6PCYmBoDHH38ck8kEQMOGDfM8Dg8Pj3x5HxERkZs0PUlECoSPP/4YT09PRowYYXesZMmSvPLKK7Rv356kpKRbvj4sLIyhQ4fSrFkz/P39ad26NVOnTiUlJcXaZ+fOnTz66KMEBgbSpEkTnnvuOU6fPm09/vvvvzN48GCCg4MJCAjgP//5D9u2bbMezz49qW/fvtbpUX5+frzyyitcuHDBbnrSmTNnGDp0KE2bNqVJkyYMGjTI5j0vXLjAmDFjaNWqFf7+/jRv3pwxY8YQHR1tfZ+9e/eyd+9e65SkW01POnLkCAMHDiQ4OJhGjRoxePBgTp48aT1+8zW7d+9mwIABBAQE0LJlS9544w0yMzP/9r/LqlWrqFu3LsuXL6dly5Y0bdqUU6dOAbBx40Z69+5N/fr1admyJVOnTrX57zN37lzuu+8+tmzZQqdOnQgICODRRx+1m1Z19epVxo4dy7333kuDBg14+OGH2bRpk02f2rVrM2/ePHr37k2DBg2YN28e/fr1A6Bfv3707dv3b69BRET+d0oaRMRwFouFHTt20Lx5c9zc3G7Zp0uXLgwZMoRixYrZHbt69SpPPPEEycnJzJw5kw8//JCuXbvy+eefs3jxYgDCw8N5/vnnqVevHh988AHTpk3j7NmzPPvss2RlZZGVlcWgQYNITk5m1qxZvP/++5QoUYLnnnuO8+fP273nxIkTefjhhwFYunQpzz//vF2fiIgI/vOf/3Du3DkmTZrEG2+8wbVr13jyySeJiYkhOTmZfv36cfr0aSZOnMjHH39Mv379+OGHH3j77bet71O3bl3q1q3L0qVL8ff3t3ufX375hcceewyA6dOnM3XqVC5fvkyfPn1sEhSAUaNGERQUxPz58+nWrRsfffQRy5cvv91/HjIzM1m0aBHTpk1j7NixVK9ene+//54hQ4ZQrVo13nvvPYYOHcp3333H888/b7MwOSoqipdffpnHH3+cd999F1dXVwYOHEhoaCgA165d4+GHH+bXX3/lpZdeYu7cuVSoUIEhQ4bw3Xff2cQxf/58unfvzpw5c+jQoQMTJkwAYMKECUycOPG21yAiIv8bTU8SEcNFR0eTmppKxYoVc/X6EydOUKdOHd599108PDwAaNGiBTt37mTPnj08++yzHD58mJSUFAYNGoSvry9wY7rRpk2bSEpKIjk5mTNnzvD8889z7733Ali/0U5LS7N7zxo1alinKt2cKnThwgWbPp9++ilpaWl88sknlC5dGrhRlXjsscc4dOgQZcqUoWzZsrz++utUqlQJgGbNmnHo0CH27t1rfZ+b1/R3U5LeeustKleuzMKFC3F0dASgVatWdOzYkTlz5vDuu+9a+z7yyCMMGTIEgObNm7Nx40a2bt1Knz59bvszHjx4MG3btgVuJHlvvvkmrVu35s0337T2qVKlCv3792fbtm3WvsnJyUyaNIlevXpZr69Dhw4sXLiQt99+m08++YSoqCh+/PFHKlSoAMC9995L//79mTVrFt26dcPB4cb3W40bN+app56yvl9sbKz1Z1TU13eIiOQ1JQ0iYribH3RvN03mdlq1akWrVq1IT0/n1KlTnD9/nhMnThAVFUWJEiUACAgIwMXFhYcffphOnTrRpk0bgoODadCgAQDu7u7UqFGDV199lR07dtCqVSvatGnD2LFjc31dISEhNGzY0JowwI1EZcuWLdbnX331FVlZWZw7d47z589z6tQpzpw5Q0ZGxh29R1JSEkeOHGHo0KHWnyOAl5cX7dq1s5leBRAYGGjzvGzZsn875Su7OnXqWP985swZrly5wqBBg2zibNKkCR4eHuzcudOaNDg5OdGtWzdrH1dXV9q0acP27dsB2Lt3L4GBgdaE4aYePXowduxYzpw5Y00IsscgIiL5S0mDiBiuePHiuLu7c+nSpb/tk5SURHp6OsWLF7c7lpWVxezZs/nyyy9JSkqiXLlyNGjQABcXF2ufihUr8sUXX7Bw4UJWrFjB4sWL8fLy4vHHH+fFF1/EZDKxaNEiPvjgA3766Se++eYbnJ2d6dChA5MnT77l+/6TmJiYf6yefPLJJ8yfP5+YmBhKlSpFvXr1cHNzIz4+/o7eIz4+HovFQqlSpeyOlSpVyu48rq6uNs8dHBzu6D4H2aeF3VwAPnnyZCZPnmzX9+rVqzYxODnZ/qrx8fGxniM2NtZaZflr7HBjW9VbxSAiIvlLSYOIFAitWrViz549pKam2nzYv2nZsmW8/vrrrFixwm5e/8KFC/n000+ZPHky999/P56engDWNQc3ZZ9uFBISwtKlS5k/fz5+fn507twZX19fJk2axMSJEwkLC2P9+vV8+OGHeHt752rOvKenJ1FRUXbtu3fvpmLFihw8eJCZM2cyevRoevfuTcmSJQEYPnw4R44cueP3MJlMXLt2ze5YZGSktdLyb/Ly8gJgzJgxNG3a1O549gTrZnKQ3bVr1/Dx8bH2jYyMtOtzs83b2/vfCFlERP5HWggtIgXCgAEDiImJ4Z133rE7FhkZyaJFi6hRo8YtFwKHhIRQo0YNHnroIWvCEBERwYkTJ8jKygJurC9o164daWlpmM1mmjdvzmuvvQbApUuXOHDgAC1atODw4cOYTCbq1KnDSy+9RK1atW5bAbmdxo0bc+jQIZvE4fr16zz99NNs27aNkJAQvLy8ePrpp60JQ2JiIiEhIda4Aeuc/lspVqwY9erVY926dTbTu+Lj49m6dStBQUG5iv12qlWrho+PDxcuXKB+/frWh6+vL2+99RbHjh2z9k1JSeHnn3+2eb59+3aaN28O3JjSdODAAS5evGjzHt999x2lS5emcuXKfxtH9ulYIiKSt1RpEJECoWHDhgwfPpx33nmH06dP06tXL7y9vTl58iQff/wxqampt0wo4EYF4f3332fhwoU0bNiQ8+fPs2DBAtLS0khOTgZuLMB98803GTJkCP/3f/+Ho6MjX3/9NWazmXbt2lGhQgVcXV0ZM2YMw4YNo1SpUuzatYvQ0FDr1p451b9/f7755huefvppBg0ahLOzMx988AFly5ale/fubNq0iSVLljBz5kzatWvH1atX+fjjj7l27ZrNt/VeXl4cOHCA3bt3U7duXbv3GTlyJAMHDuTZZ5/l8ccfJz09nYULF5KWlmZd9PxvcnR05KWXXmLChAk4OjrSrl074uLieP/994mIiLBL7MaOHcuLL76Ij48PH3/8MUlJSTz33HMAPPXUU3z33Xf079+foUOHUqJECb755ht++eUXpk+fftuE6WaCuHXrVooXL27ojf9ERO52ShpEpMB47rnnqFu3rvXO0LGxsZQrV462bdsyePBgypUrd8vXDRo0iOjoaBYvXsx7771HuXLl6NmzJyaTiQULFhAXF4efnx/z58/nvffeY8SIEWRmZlKvXj0WLVpEtWrVAFi0aBFvvfUW06ZNIy4ujipVqjBlyhR69+6dq+spV64cX331FW+88QavvPIKZrOZ4OBg3n77bYoXL86DDz7IhQsXWLlyJV999RW+vr7ce++9PP7447z66qucPn2a6tWr88QTT3D06FGeeeYZZsyYQZkyZWzep3nz5nzyySfMmTOHESNGYDabady4Ma+//jo1a9bMVez/5JFHHsHd3Z2PPvqIpUuXUqxYMRo1asSbb75pt0Zh0qRJTJ8+naioKBo1asSSJUusFYTSpUuzZMkS3nrrLaZOnUp6ejp+fn68//77tG/f/rYx1KxZk27duvHll1/y888/s2bNmjy5VhERAZPlTlbAiYiI5NDcuXOZN28ex48fNzoUERH5H2lNg4iIiIiI3JaSBhERERERuS0lDSIikieGDRumqUkiIv+CtLQ0unXrxp49e/62z7Fjx3jkkUcICAjgoYce4ujRozbH16xZQ4cOHQgICGDIkCG33BL8dpQ0iIiIiIgUUKmpqYwYMYKTJ0/+bZ+kpCSeffZZGjduzKpVqwgMDGTQoEEkJSUBcPjwYcaPH8/QoUNZunQpcXFxjB07NkdxKGkQERERESmATp06xaOPPsrvv/9+235r167FxcWFMWPGUL16dcaPH4+7uzvr168H4IsvvqBz58706tULPz8/Zs2axbZt2wgPD7/jWJQ0iIiIiIgUQHv37iU4OJilS5fett+hQ4cICgrCZDIBYDKZaNSoEQcPHrQeb9y4sbV/uXLlKF++PIcOHbrjWHSfBhERERGRfJKWlkZaWppNm9lsxmw22/V9/PHH7+ickZGR1KhRw6bNx8fHOqXp6tWrdvf48fHx4cqVK3cc912ZNLzz81mjQxAplMa+8JbRIYgUSrV6PGh0CCKFzqHJt7+Bo5HcAofm2blnDajNvHnzbNqGDh3KsGHDcn3O5ORku6TDbDZbk5OUlJTbHr8Td2XSICIiIiJSEA0aNIinnnrKpu1WVYaccHFxsUsA0tLScHV1ve1xNze3O34PJQ0iIiIiItmZ8m7Z799NRfpf+Pr6cu3aNZu2a9euWack/d3x0qVL3/F7aCG0iIiIiEh2JlPePfJAQEAABw4cwGKxAGCxWNi/fz8BAQHW4yEhIdb+ly9f5vLly9bjd0JJg4iIiIhIIRMZGUlKSgoAnTp1Ii4ujmnTpnHq1CmmTZtGcnIynTt3BuCxxx7j22+/Zfny5YSFhTFmzBjatm1LpUqV7vj9lDSIiIiIiGRncsi7x7+kVatWrF27FgAPDw8WLFhASEgIvXv35tChQyxcuJBixYoBEBgYyJQpU3jvvfd47LHHKF68ODNmzMjR+2lNg4iIiIhIAXf8+PHbPm/QoAGrV6/+29f37t2b3r175/r9lTSIiIiIiGSXR2sPCjNNTxIRERERkdtSpUFEREREJLs83HK1sNJPREREREREbkuVBhERERGR7LSmwY6SBhERERGR7DQ9yY5+IiIiIiIicluqNIiIiIiIZKfpSXZUaRARERERkdtSpUFEREREJDutabCjn4iIiIiIiNyWKg0iIiIiItlpTYMdVRpEREREROS2VGkQEREREclOaxrsKGkQEREREclO05PsKI0SEREREZHbUqVBRERERCQ7TU+yo5+IiIiIiIjclioNIiIiIiLZqdJgRz8RERERERG5rQJTaTh//jxHjx4lPT3d7livXr3yPyARERERKZoctHvSXxWIpOGjjz7izTffpHjx4ri7u9scM5lMShpERERERAxUIJKGRYsWMXr0aAYOHGh0KCIiIiJS1GlNg50CkTSkpqZy//33Gx2GiIiIiIhu7nYLBSKN6t69O1999RUWi8XoUERERERE5C8KRKUhISGBFStWsGbNGipWrIizs7PN8cWLFxsUmYiIiIgUOZqeZKdAJA1VqlRh8ODBRochIiIiIiK3UCCShqFDhxodgoiIiIjIDVrTYKdAJA19+/bFdIv/OCaTCWdnZ0qXLk3nzp1p06aNAdGJiIiIiBRtBWLCVpMmTdi/fz+lS5emY8eOdOjQgbJlyxISEkKZMmVwc3NjxIgRrFy50uhQRURERORuZ3LIu0chVSAqDbt372bs2LE88cQTNu2NGzfm22+/5csvv6RZs2bMnj2bhx56yKAoRURERESKpgKR7hw7doyWLVvatTdt2pQjR44AUK9ePS5fvpzfoYmIiIhIUWMy5d2jkCoQSYOfnx9ffPGF3X0avvrqK2rUqAHAkSNHKFu2rBHhiYiIiEhRoulJdgrE9KRXX32VZ555hq1bt1K3bl0AQkNDSUhIYP78+YSEhDB69GgmTJhgcKRyKxnpafz85TzOhOzEyWwm4P6HafjAraeRhf8Wwu7lHxEbeRnfan60fmII3mUrAfDB051u+Zr7BoyidosOeRa/SGFgdnZi11djeGnmcn4OOWl0OCKGMTs5MK5rbdrXKU1qRhaLd/3O4l2/37Jv8+oleen+GlTyduPwhTim/3Cc89eTrMf7tbiHPk0r4unqxJawSGasPUFyWmZ+XYpIoVIgkoZ69erx008/8cMPP3DixAkcHR1p3bo1Xbt2pVixYly4cIFly5bh5+dndKhyC7uXf0TkuZP0GDWT+OtX2bzoLTx9ylC9cWubflEXz7F2zgQCO/+Hms3aEfbzj3z/5is8NvUjnF3dePKtr2z6H/ppNaf3baNKw+b5eTkiBY6L2YnPpvfHv0Z5o0MRMdyI+2tQt7wnz3x2gPLFXXntwbpciklh47GrNv2ql3Zn7hMBLPr5PD8cvsKDjcrzUf9Aesz9heS0TB5uXIHn2lZl8ndhnIxIYHSnmsx8yJ/hSw4bdGVSoBTiaUR5pUAkDQAeHh785z//ueWxihUr5nM0cqfSU1MI/Xk9XYe/RunKNSlduSbRl85zdPN3dknDb1t/wLd6XZr26gdAs4cHcv7wXk7s2Yz/vV0pVryktW9c5BWObPqWLsMm4VLMPV+vSaQg8atWlk+n99fvLxHAzdmBBxuVZ8gXBwm7HE/Y5Xiq7zxPn6YV7ZKGR5tU4FB4LO9vOQPAOz+dok2tUnRtUJYVv17ksaYVWbz7d9YfjQDgv6uP8dPIVlT2KWZTjRCRGwxLGtq3b8+KFSvw9vbmvvvuu+V9Gm7atGlTPkYmOXE9/AxZmRmUrVHX2la2hj8hP3yNJSsLk8Ofc/fiIq/gW7W29bnJZKJkhSpEnA7F/96uNufd9+1iKtZpSMW6jfL+IkQKsNZBNdi+7wQT3/ueqN1vGx2OiKFqlfXEycHEwfBYa9uB32N4uk0VTCbIvjSygrcbRy7E2bz+1NUEGlT0YsWvF+2OX0tIIzopnYBKxZU0SKFee5BXDEsahg4dirv7jW+Qhw0bZlQY8j9KjI3C1aM4jk7O1rZiXt5kpqeRkhiHm2cJa7ubVwkSY67bvD4hOhJXd0+btvjrVzm5ZysPjp2dp7GLFAYfLt9hdAgiBUYpDzMxSelkZP6ZHVxPSMPV2ZESbs5EJ6Vb26MS0yjj5WLzel8vF+KSM2553M3ZAS83J0oUc0ZE7BmWNDz44IO3/LMULhlpKTYJA4Cj843nmenpNu01mt7LurmTqNG0LffUa8yJXzYTee4E5WsH2PQL3fEjpavUxLea1rCIiMif3JwdScvMsmm7+dzZyfab4fVHI5jzWADrj1xh56koutT3xb+CF7+ejQbgx6MRDGxVhQPnY7gYk8KoTrVunMdRcwEFrWm4hQKxpiEuLo5FixZx5MgRMjIy7LZeXbx4sUGRyT9xcjaTmWGbHNxMFpzMrjbt99RrTOPuT/DjB1OxZGZS3q8BtZq3Jy3Ztgx8JuRnu+lKIiIiqRlZmB1tk4Obz1PSbXc92nUqivnbzvLWfxrg6GBi39lo1hy6gofLjY8+C7edpYK3G6uGNCMjy8KKXy9y/EoCianaPUnkVgpE0jBmzBiOHDlC9+7d8fDwMDocyQH3EqVISYglKzMTB0dHAJLionEyu9xyAXNQt8do+MBDpCYnUcyrBBvmT8PTx9d6PCEqkuhLv2vHJBERsXM1PpUSxZxxdDCRmXXjC8ZSHi4kp2USn5Jh1/+j7ef4bOd5PF2diEpMZ9Yj9bgUkwxAcnoWY5YfxcPFEQuQmJrJltGtrceliNOaBjsFImnYtWsXX3zxBQ0aNDA6FMkhn0rVcHB0IuJMKOVq1gPg8smjlK5Sy2YRNMDJPVuIOHucVn0GU8zZTEZaKhfDDnPfgBHWPhFnwvAoWRpPnzL5eh0iIlLwHb8ST0aWhQYVvTjw+43F0IGVi/PbpTj+MkmBTvV8qV/RizfWnyQqMR0XJweaVPVmwupjALzYsQanrybw/aErAPiX98TD1clmkbUUYUoa7BSIn4ivry8ODgUiFMkhZxdXarfowLbP53L17HHOHtjFoQ0radC+JwBJsVFkpKUCUMK3Ise2/sCZkB3ERFxk44ev41GyFPfUa2I9X9TFc3iXu8eQaxERkYItJT2L7w9e5r/d/PAv70k7v1L0a1GZr34JB8DHw4zLH2sbzl9P4pHGFWhfpzT3lHRj5sP+RMSmsOPUjQ05IuNTGdy2Gv7lPalTzpPpD/mzbN8F60JpEbFVICoNY8aMYdKkSbzwwgtUrlwZZ2fbhbXly+uGRgVZi0efZfsX8/j2zZdxcXOncY++VAtqBcBnIx+n3VMj8Gt5P6Wr1KTN/w1j1/IPSUmIp2KdhnR5YYpNRSIpLgYXd01RExGRW3vzx5OM7+bHR/0bkZCawQdbzrApNBKAzaNb8+rqY3x38DKhl+OZtuY4Ix+oSXE3Z/aejWLol4esFYkle8IpX8KV9/6vIRYLrDl8mXd+Om3glUmBooXQdkyWv646NsBf7/R8854NFosFk8lEaGhojs73zs9n/7XYRIqSsS+8ZXQIIoVSrR7aBVAkpw5Nbm90CH/LrccHeXbu5O+ey7Nz56UCUWnQzdtEREREpMDQmgY7BeInUqFCBSpUqEBSUhLHjh3D29ubrKwsypcvT4UKFYwOT0RERESkSCsQlYbY2FiGDx/O3r17Afjxxx+ZNm0a4eHhLFy4UImDiIiIiOQfrWmwUyAqDVOnTsXNzY1ffvkFF5cbt3SfPn06ZcuWZerUqQZHJyIiIiJStBWISsPPP//M559/jpeXl7WtZMmSjB07lj59+hgYmYiIiIgUOVrTYKdAJA0Aqampdm1RUVE4ORWYEEVERESkKND0JDsFIo3q1q0b06ZN4+TJk5hMJpKSkvjll1949dVX6dKli9HhiYiIiIgUaQXia/wxY8Ywe/ZsevfuTXp6Oj179sTR0ZFHHnmEMWPGGB2eiIiIiBQhJlUa7BSIpMFsNvPKK6/w4osvEh4eTmZmJpUqVcLd3d3o0EREREREirwCMT3pJldXV3x8fAgJCWH16tVcunTJ6JBEREREpIgxmUx59iisDKs0JCcnM2vWLNauXQtAz5496du3L3369CE5ORmLxcIbb7zBRx99RJMmTYwKU0RERESkyDOs0jB9+nT279/PxIkTmTFjBqdOneLRRx+lRYsW7Nmzh3379tGzZ0/mzJljVIgiIiIiUhSZ8vBRSBlWadi0aRPz58+nQYMGADRs2JAWLVrwf//3fzg7OwMwYMAAHnzwQaNCFBERERERDEwaoqKiKFu2rPV5yZIlcXNzw9vb29rm4eFBSkqKEeGJiIiISBFVmNce5BVDd09ydHS0a9N/JBERERExkj6P2jM0aThw4ADFixe3PrdYLBw+fJgrV64AEBsba1RoIiIiIiLyB0OThqFDh9q1jRw50ua5Mj0RERERyU/6/GnPsKQhLCzMqLcWEREREZEcKBB3hBYRERERKShUabBXoO4ILSIiIiIiBY8qDSIiIiIi2anQYEeVBhERERERuS1VGkREREREstGaBnuqNIiIiIiIyG2p0iAiIiIiko0qDfaUNIiIiIiIZKOkwZ6mJ4mIiIiIyG2p0iAiIiIiko0qDfZUaRARERERkdtSpUFEREREJDsVGuyo0iAiIiIiIrelSoOIiIiISDZa02BPlQYREREREbktVRpERERERLJRpcGekgYRERERkWyUNNjT9CQREREREbktVRpERERERLJTocGOKg0iIiIiInJbqjSIiIiIiGSjNQ32VGkQEREREZHbuisrDWNfeMvoEEQKpeh984wOQaRQGrc2zOgQRORfpEqDPVUaRERERETktpQ0iIiIiIhkYzKZ8uyRE6mpqYwbN47GjRvTqlUrFi1a9Ld9d+zYQY8ePQgMDKR///6cOXPGesxisfDxxx9z33330bhxY8aOHUtiYmKOYlHSICIiIiKSTUFJGmbNmsXRo0f57LPPmDhxIvPmzWP9+vV2/U6ePMmgQYNo3749K1eupG7dujz55JPWxGDp0qXMmzePESNGsGTJEiIiIhg5cmSOYlHSICIiIiJSwCQlJbF8+XLGjx+Pv78/HTt25Omnn+bLL7+067tkyRICAwMZPnw41apVY/To0Xh6evL9998D8MUXX/DUU0/RrVs3atasycyZM9m6datNNeKfKGkQEREREcnOlIePOxQWFkZGRgaBgYHWtqCgIA4dOkRWVpZN3/DwcBo0aPBn+CYTtWrV4uDBg9bjAQEB1uNlypShZMmS1uN34q7cPUlEREREpCBKS0sjLS3Nps1sNmM2m23aIiMj8fb2tmkvVaoUqampxMTEULJkSZv2iIgIm9dfuXKF4sWLA+Dj42NzPCkpidjYWKKjo+84blUaRERERESyycs1DQsWLCAoKMjmsWDBArsYkpOT7RKJm8//mnR07tyZH3/8kS1btpCRkcHq1as5cuQI6enpAHTp0oUFCxZw+vRpUlNTmTlzJoD1+J1QpUFEREREJJ8MGjSIp556yqbtr8kBgIuLi11ycPO5q6urTXubNm0YMmQIw4YNIzMzk+DgYHr27ElCQgIAzz//POHh4XTt2hUnJyf69OmDn58fHh4edxy3kgYRERERkWzy8uZut5qKdCu+vr5ER0eTkZGBk9ONj+yRkZG4urri5eVl1/+5555j4MCBxMfH4+Pjw/Dhw6lQoQIAxYoV49133yU+Ph6TyYSHhwfNmze3Hr8Tmp4kIiIiIlLA1KlTBycnJ5vFyiEhIdSvXx8HB9uP8GvWrGHatGmYzWZ8fHxISUlhz549BAcHAze2bl29ejWenp54eHhw+PBh4uPjbRZZ/xMlDSIiIiIi2RSE+zS4ubnRq1cvJk2axOHDh9m4cSOLFi2iX79+wI2qQ0pKCgBVqlTh66+/ZsOGDZw7d46RI0dSrlw52rRpA9zYLWnevHkcPnyYo0ePMnr0aB577DFKlChxx/FoepKIiIiISHZ5NzspR8aOHcukSZN48skn8fDwYNiwYdx///0AtGrVihkzZtC7d2/q1avHpEmTmDlzJjExMTRv3pwFCxZYKxJ9+/bl4sWLPPPMMzg4ONCzZ09GjRqVo1hMFovF8q9focHcAocaHYJIoRS9b57RIYgUSuPWhhkdgkihM7uHn9Eh/K1KQ7/Ns3OHz+uZZ+fOS6o0iIiIiIhkk5cLoQsrrWkQEREREZHbUqVBRERERCQbVRrsqdIgIiIiIiK3VSCShkuXLnGr9diZmZn89ttvBkQkIiIiIkVVQdhytaApEElD+/btiY6Otmu/cOECjz/+uAERiYiIiIjITYataVi+fDnz588HwGKx8NBDD9nd3S4uLo7q1asbEZ6IiIiIFFGFuSKQVwxLGnr16oWzszNZWVmMGzeOp556Ck9PT+txk8mEm5sbzZo1MypEERERESmKlDPYMSxpcHZ2plevXgBUrFiRRo0a4eSkzZxERERERAqaAvEpvWnTpuzevZsjR46Qnp5utyh66FDd4VlERERE8oemJ9krEEnDzJkzWbx4MX5+fri7u9sc0380ERERERFjFYikYeXKlcycOZMePXoYHYqIiIiIFHH60tpegdhy1dHRkQYNGhgdhoiIiIiI3EKBSBqeeOIJ5s6dS1JSktGhiIiIiEgRZzLl3aOwKhDTk/bu3cuBAwdYv349Pj4+ODs72xzftGmTQZGJiIiIiEiBSBp69+5N7969jQ5DRERERERrGm6hQCQNDz744N8eS09Pz8dIRERERKSoU85gr0AkDdeuXWPBggWcOnWKzMxMACwWC+np6Zw+fZp9+/YZHKGIiIiISNFVIBZCjxs3jp9//pn69euzf/9+AgICKFmyJIcPH2bYsGFGhyciIiIiRYjJZMqzR2FVICoN+/btY9GiRQQGBrJz507atm1LUFAQCxcuZPv27fTr18/oEEVEREREiqwCUWmwWCz4+voCUKNGDY4dOwZA586dOXLkiJGhiYiIiEgRoy1X7RWIpKFu3bp8++23ANSpU4edO3cCcOHCBSPDEhERERERCsj0pJEjRzJ48GDc3Nzo2bMnH330Ed27d+fSpUv06NHD6PBEREREpAhxcCjEJYE8UiCShqCgILZs2UJKSgre3t6sXLmSjRs3UqJECTp37mx0eCIiIiIiRVqBSBoAPDw88PDwAMDX15cnnnjC4IhEREREpCgqzGsP8kqBSBqOHTvG1KlTOXLkCBkZGXbHQ0NDDYhKRERERIqiwrw1al4pEEnDuHHj8PT05N1337VWG+TuZHZ2YtdXY3hp5nJ+DjlpdDgihklNTWX61Mls+mkDLi6u9HtqAE/2H3DLvrt27uDtN2cRHh5Og4AAxv13AlWqVrMeb9WsMfHx8Tav2b13P8Xc3fP0GkSM4ORg4qH6vjQo70l6poUtp6PYdjrqln1rlS5Gj7pl8HE3cz46mZWHI4hMTLMef6B2KYLvKY7Z0YHjkYmsOhJBYlpmfl2KSKFSIJKGM2fO8P3331O5cmWjQ5E85GJ24rPp/fGvUd7oUEQMN/vNWRw7epQPF33GpUuXeHXcy5QvV56OD3Sy6Xfq1EmGPT+IAU8/S9du3Vm9cgVPD3iS79asp5i7OxEREcTHx/PD+o24urpaX+dWrFh+X5JIvuhetwyVSrjy/q7fKenmzGOB5YhOSufwZdvE2dfTzDPBldh08johF+IIrlyc51tUYsbmM6RlWmheuQRN7ynOl/svkZiWycMNyvKfgLIs2nfRoCuTgkSFBnsFYsvVOnXqcPr0aaPDkDzkV60s2xaPomqlUkaHImK4pKQkVq9czpix46lT15/2HTrSf8DTfL3kS7u+y75eQkDDQIYMG06VqtV4ceRoPD08+eGH7wE4e+Y0pUuXpmKlSpQqXdr6UGld7kZmRxPNKhdn9dGrXIxN5ciVBDafiqJVVW+7vi2reHMuKpn1x68RmZjGmmORJGdkEVSxOAB1yrhz8GIcp68ncyU+jc2noqhZWtU5kb9TICoNPXv25L///S+9e/emcuXKODs72xzv1auXMYHJv6Z1UA227zvBxPe+J2r320aHI2KoE8fDyMjIoGHDQGtbYKMgPlo4n6ysLBwc/vw+5+KFcOrXb2B9bjKZqFGrFocPHuSRR/tw+vQpKlepmq/xixilvJcrDiYT56KSrG1no5LpWMsHE2DJ1tenmDPnY5JtXn85LpXK3m7sPh9DYnomdX092H4mmqS0TBpV8ORibEr+XIgUePrixV6BSBo++ugjXF1dWbt2rd0xk8mkpOEu8OHyHUaHIFJgXIuMpEQJb5zNZmubj08pUlNTiYmJoWTJktb2kj6luHo1wub1EVeu4FX8xrelZ8+cJjk5mYH9+3Lu7Fn86tRh9CvjqKJEQu5CXq5OJKZlkpktO4hPzcDZ0YFiZkeb9QjxqRkUd7X9mFPCzYmktCwANhy/ztPBFZh4fw0ysyzEpWYw5+fz+XIdIoVRgUgaNm/ebHQIIiL5JjklGXO2hAGwPk9PS7Np79SpMy8MfZ5OXbrRslVr1q75nt+OHqFx02AAzp45Q1xsLC+8OAJ3dw8++fhDnh3Yn9Xf/YC7uzaWkLuLs6OJjCyLTdvN505/uRnXwYvxDAiuyIGLcYRdTaRRRS/uKeHGqWs3qhQlizmTlmnhoz3hJKVn0aNuGfo0LMeCX8Lz52KkQFOlwV6BSBq++eabvz1mNpspXbo0AQEBdr9kRUQKIxcXF9L+khzcfJ59MTNAy9ZtGPz8EEa+OIzMzEyaNA2mW4+eJMQnAPDBwo/JSE+37pQ0Y9abPND+XrZt2UKXbt3z4WpE8k9GpsUuObj5PD0zy6Y9LDKRDcev0b9xBRwcTJy6lsSv4bG4Ot+Y/vd4YDm+P3aVYxGJACz+9SL/7Vide0q48nuMpimJ/FWBSBpWrVrFr7/+iouLC1WrVsVisXD+/HmSk5MpX748cXFxeHp68uGHH1K9enWjwxUR+Z+UKeNLTEw0GRkZODnd+Gf42rVIXF1d8fTysuv/zKDnePKpgcTHx+Pj48PoEcMpX6ECcOOLlexfqLi4uFC+QkW7KU0id4PYlAzczY44mOBmwcHLxYm0jCyS07Ps+m88eZ0tp6Nwc3IgIS2TfkHliUpKx8PsiHcxZy7FpVr7xqRkkJiWiXcxZyUNot2TbqFA7J5Uq1Yt7r33XrZt28aqVatYvXo127dvp2PHjjzwwAP88ssvtGvXjunTpxsdqojI/6y2Xx2cnJw4fOigte3A/hD869W3WQQNsO6HNcyaMQ2z2YyPjw8pKSns27uHJk2DsVgsdO3UgW9Xr7L2T0pK4vffz9vcx0HkbnExLoUsi4XK3m7Wtqo+boTHpGD5S9/ACp708i9DZpaFhLRMnB1M1ChVjFPXkkhKzyQ9Mwtfzz8TbnezI+5mR6KS0vPpaqQgM5lMefYorApE0vDNN98watQovLJ9w+bh4cHw4cNZtmwZjo6O9OvXj/379xsYpYjIv8PNzY3uPXsxdcokjh45zOZNG1n86SIe/79+wI2F0ikpN77prFylCsuXfc3GnzZw/vw5XhkzEt+y5WjVug0mk4nWbdrywXtz2bd3D6dOnWT82DH4+paldZt7DbxCkbyRnmlhX3gsDzcoS6USrtQr60Hb6iXZfvbGzd08XRxx/mO6UmRCGs2rlKB+OQ9KuTvzf0HliUnOIOxqIlkW2BseS4+6ZahW0o2ynmaeaFSO89HJhKvKIHJLBWJ6UrFixTh9+rTd1KMzZ85Yy+5JSUl2c31FRAqrUWPGMm3KJJ5+6kk8PD14bsgwOnS8H4D2bVsxZeoMej7Ym7r+9Rg/YRJvvTGT2JgYmjZrzrwPFlgrEi+NHI2TkxNjx4wkPiGBpk2b8d4HC3F0dDTw6kTyzre/XeXhBmV5vsU9pKRn8uPxaxy5fGONz+QHarLkwGX2hcdyITaVFYcj6FG3DO5mR05eS+LDPeHWisS3R6+S5leK/wsqj7OjAyciE/ly/2XjLkwKlEJcEMgzJovF8teKXr779NNPmTdvHv3796devXpYLBZ+++03PvvsMwYOHEivXr144YUXqFatGjNnzvzH87kFDs2HqEXuPtH75hkdgkihNG5tmNEhiBQ6s3v4GR3C32o0Je929tw/4b48O3deKhCVhv79+1OyZEm++uorPv74Y5ycnKhRowaTJ0+mS5cu7Nu3j8DAQIYPH250qCIiIiJylyvMaw/ySoFIGgB69OhBjx49bnmsSZMmNGnSJJ8jEhERERERMDBpmDdvHgMHDsTNzY15824/JWLoUE03EhEREZH8oUKDPcOShj179tCvXz/c3NzYs2fP3/ZTeUhERERExFiGJQ2ff/75Lf8sIiIiImIkfWltz7Ck4Ztvvrnjvr169cqzOERERERE5PYMSxrmzJlzR/1MJpOSBhERERHJNyo02DMsadi8Oe/2vxURERERyS1NT7JXYLZcjYqK4uzZs2RlZQFgsVhIS0vj2LFjPPvsswZHJyIiIiJSdBWIpGHZsmVMmTKFjIwMTCYTN29SbTKZaNCggZIGEREREck3KjTYczA6AID58+czePBgDh8+jI+PD1u2bGHNmjXUqVOHjh07Gh2eiIiIiEiRViCShqtXr9KrVy/MZjP+/v4cPHiQGjVqMG7cOJYvX250eCIiIiJShJhMpjx7FFYFImkoWbIkUVFRAFSrVo3Q0FAAfH19iYiIMDI0EREREZEir0AkDZ07d+bll19m//79tG7dmlWrVvHjjz/y3nvvUblyZaPDExEREZEixGTKu0dhVSAWQo8aNQpPT0+io6Np3749Dz30EBMnTqREiRJMnz7d6PBERERERIq0ApE0ODs7M3ToUOvzl156iZdeesnAiERERESkqCrMaw/yimFJw7x58+64b/aEQkREREQkLylnsGdo0uDg4ECdOnVwd3e33pvhr5TpiYiIiIgYy7CkYeLEiWzcuJGDBw/SpEkT2rdvT/v27SlZsqRRIYmIiIiI6EvrWzAsaXjsscd47LHHSEhIYNu2bfz000+88cYb1KpViw4dOtCxY0cqVKhgVHgiIiIiIvIHwxdCe3h40LVrV7p27UpaWhq7d+9m06ZN9OnTh1KlStGhQweGDBlidJgiIiIiUkSo0mCvQNyn4Saz2Uzr1q3p3r07Xbt25ffff+fDDz80OiwRERERkSLN8EoDQGJiIj///DObN29m+/btALRt25YZM2bQqlUrg6MTERERkaJEhQZ7hiUNV65cYdOmTWzevJl9+/bh6+vLfffdx5w5cwgKCsLR0dGo0EREREREJBvDkoZ27drh5OREkyZNePnll6lVq5b12P79+236NmnSJL/DExEREZEiSmsa7BmWNFgsFtLT09m1axe7du36234mk4nQ0NB8jExEREREijLlDPYMSxrCwsKMemsREREREcmBArEQWkRERESkoND0JHsFastVEREREREpeFRpEBERERHJRoUGe6o0iIiIiIjIbanSICIiIiKSjYNKDXZUaRARERERkdtSpUFEREREJBsVGuwpaRARERERyUZbrtrT9CQREREREbktVRpERERERLJxUKHBjioNIiIiIiJyW6o0iIiIiIhkozUN9lRpEBERERGR21KlQUREREQkGxUa7N2VSUOLAU8YHYJIodT1g91GhyAiIiIF0F2ZNIiIiIiI5JYJlRr+SkmDiIiIiEg22nLVnhZCi4iIiIjIbanSICIiIiKSjbZctadKg4iIiIiI3JYqDSIiIiIi2ajQYE+VBhERERERuS1VGkREREREsnFQqcGOKg0iIiIiIgVQamoq48aNo3HjxrRq1YpFixb9bd8dO3bQo0cPAgMD6d+/P2fOnLEes1gszJ07lzZt2tCkSRNefPFFoqKichSLkgYRERERkWxMprx75MSsWbM4evQon332GRMnTmTevHmsX7/ert/JkycZNGgQ7du3Z+XKldStW5cnn3ySxMREAJYuXcqKFSt48803+fLLL7l69Srjx4/PUSxKGkREREREsjGZTHn2uFNJSUksX76c8ePH4+/vT8eOHXn66af58ssv7fouWbKEwMBAhg8fTrVq1Rg9ejSenp58//33AGzbto0uXbrQtGlTatWqxdNPP80vv/ySo5+JkgYRERERkXySlpZGQkKCzSMtLc2uX1hYGBkZGQQGBlrbgoKCOHToEFlZWTZ9w8PDadCggfW5yWSiVq1aHDx4EIASJUqwdetWIiIiSElJ4YcffqBOnTo5iltJg4iIiIhINnk5PWnBggUEBQXZPBYsWGAXQ2RkJN7e3pjNZmtbqVKlSE1NJSYmxqZvqVKliIiIsGm7cuUK0dHRAAwZMgQnJyfatGlDo0aN+PXXX5k9e3aOfiZKGkRERERE8smgQYMICQmxeQwaNMiuX3Jysk3CAFif/7Uy0blzZ3788Ue2bNlCRkYGq1ev5siRI6SnpwNw8eJFXF1dmT9/Pp9//jlly5Zl3LhxOYpbW66KiIiIiGSTl1uums1mu2TgVlxcXOySg5vPXV1dbdrbtGnDkCFDGDZsGJmZmQQHB9OzZ08SEhKwWCy8/PLLjBkzhnbt2gHwzjvv0K5dOw4dOkRAQMAdxa1Kg4iIiIhIAePr60t0dDQZGRnWtsjISFxdXfHy8rLr/9xzz7F//3527NjBp59+SmJiIhUqVCAqKorLly9Tu3Zta99y5crh7e3NxYsX7zgeJQ0iIiIiItmY8vBxp+rUqYOTk5N1MTNASEgI9evXx8HB9iP8mjVrmDZtGmazGR8fH1JSUtizZw/BwcEUL14cs9nM6dOnrf2joqKIiYmhYsWKdxyPkgYRERERkQLGzc2NXr16MWnSJA4fPszGjRtZtGgR/fr1A25UHVJSUgCoUqUKX3/9NRs2bODcuXOMHDmScuXK0aZNG5ycnOjduzevv/46+/bt48SJE4wePZqAgADq169/x/EoaRARERERyaYg3KcBYOzYsfj7+/Pkk08yefJkhg0bxv333w9Aq1atWLt2LQD16tVj0qRJzJw5k969ewM3dmm6WZEYN24c999/PyNHjqRv3754eXnx/vvv5ygek8ViseQo+n9ZeHg4lSpV+lfP2X7u7n/1fCIiIiLy79o0rLnRIfytJz4/mGfn/rJvwzw7d14yvNLQqVMnHnnkET799FO7/WVFRERERMR4hicNP//8M71792bz5s20b9+e//u//+Orr74iKirK6NBEREREpAgqKNOTChLDk4aSJUvy2GOPsXjxYrZt20bXrl3Zvn07HTp0YODAgaxevZrk5GSjwxQRERERKbJylTRkZGSwZMkSLl26BMC7775L165dGT16tN1trXMiMjKSyMhIrly5QlZWFu7u7ixbtoy2bduyYcOGXJ9XREREROROmUx59yiscnVH6JkzZ/Ljjz8SGBjIsWPH+PDDD3nhhRfYvn07r732Gm+99dYdnys0NJT169ezfv16Ll68SIsWLXjqqafo0KED7u7uALz//vu8+uqr1tXiIiIiIiKSf3KVNKxdu5b3338fPz8/PvzwQ1q1asWzzz5Lu3bt6NOnT47O1bt3b4KCgujfvz+dOnXC29vbrk9QUBDh4eG5CVVEREREJEcK89qDvJKrpCE5ORkfHx8yMjLYvn07o0aNAiArKwsnp5ydcsuWLZQqVYrY2FhrwnDgwAH8/f0xm80ABAcHExwcnJtQRURERETkf5SrNQ2NGjXijTfeYMKECSQnJ9OhQwfCwsKYMmUKzZo1y9G5oqOjad++PR9//LG1bdSoUXTq1ImTJ0/mJjwRERERkVxzMOXdo7DKVdIwdepU0tPT+e2335gxYwY+Pj6sW7cOHx8fJk6cmKNzTZkyhY4dO/LSSy9Z23766Sfuu+8+pkyZkpvwRERERERyTVuu2svV9KRy5crxwQcf2LRl/9CfE6GhocyaNQtnZ2drm4ODA/369aNnz565OqeIiIiIiPx7cn2fhpCQEF544QV69uzJ5cuXWbhwIT/88EOOz1OuXDl2795t175//35KlSqV2/BERERERHLFlIePwipXlYYNGzYwduxYHn30UbZu3UpGRgZOTk688sorxMbG8vjjj9/xuQYPHsz48eM5cOAA9erVAyAsLIzvvvsux1OdRERERETk35erpGHevHlMmjSJ7t278/XXXwMwYMAASpcuzZw5c3KUNPTs2ZOSJUuybNkylixZgpOTE5UrV+bjjz+mcePGuQlPRERERCTXHArx2oO8kquk4fz58zRs2NCuvUGDBkREROT4fK1bt6Z169a5CUVERERERPJYrpKGGjVq8PPPP9tVFFavXk2NGjVydK7k5GSWLl3KqVOnyMzMtLanpaVx7Ngx1q1bl5sQRURERERyRYUGe7lKGsaOHcvgwYP55ZdfSE9PZ/78+Zw/f56jR4/a7ar0T/773/+ye/dumjdvzvr16+ncuTPnz5/nyJEjDB06NDfhiYiIiIjIvyhXSUPjxo1Zt24dX331FQAxMTE0bNiQWbNmUb58+Ryda/v27bz77ru0aNGCkydP0r9/f+rVq8fMmTN1czcRERERyXeF+X4KeSVXSQNA6dKlGT58OAApKSmcOHECT0/PHJ8nNTWVKlWqAFCzZk2OHj1KvXr1+M9//sP//d//5TY8ERERERH5l+QqaTh16hTjxo3jlVdeoUaNGvznP//h7NmzuLm58cEHH9CsWbM7Plf16tXZtWsXDz/8MDVr1iQkJIQ+ffoQHx9PampqbsKTfObsaGL4vdVoXaMkqRlZLD9wieUHLt+yb1Cl4gxqVZnyXq4ci4hnztazXIhJsR7v17QiXfzL4OrkyK/hMczdepbYlIz8uhSRfKNxI5I7GjuSH1RosJerm7tNnjyZSpUqUaVKFVasWEF8fDw7duxg8ODBvP766zk619ChQ5k0aRLLli2jZ8+ebNq0icGDBzN8+HDtqFRIDGpZmVq+7oxafYx3t56lb9OKtKle0q5f5ZJuTO/ux64z0QxeephTVxN560F/XJ1v/DXs5l+GznXLMP3HU7y48iil3M2MbF89vy9HJF9o3IjkjsaO5AcHkynPHoVVrpKGw4cP8+KLL1KyZEk2btxIx44dKVWqFN26dePMmTM5Olf79u1Zt24dwcHBlCtXjq+++oqqVavy2GOPMX369NyEJ/nI1cmBLv6+vLf9HCcjE9l5JoqlIZfo2aCsXd8e9cvy25UEPt0TzoWYFBbu+p3EtAw61Lpx5++mVbzZevI6hy/FcS4qmaUhl2hUsXh+X5JIntO4EckdjR0R4+QqafD09OTatWtcvnyZgwcP0rZtWwBCQ0Px8fHJ0bl69+5NUlISlStXBsDPz4+XX36ZZ599Fjc3t9yEJ/moWqliODmY+O1yvLXt6OV46pT1tLtVejkvF8KuxNu0nbmeRN1yN9bCxKVkEFylBKXczZgdHWhXqxSnriXm9SWI5DuNG5Hc0diR/GIy5d2jsMrVmobevXvz3HPPYTabqVixIq1atWLJkiXMmjXLujj6Tl29ehVHR8fchCEFgI+7mdjkdDKyLNa26KR0XJwc8HJ1spkbGp2Ujo+H2eb1ZTxciP+jz+d7LzC1mx9LBwSRmWXhemIaw5YfzZ8LEclHGjciuaOxI2KcXCUNI0aMoH79+ly8eJFu3brh6OhI+fLlmT17Nu3atcvRuXr16sXTTz9Njx49qFChAi4uLnbHpeBycXIgPdNi05aemQWAs6NtIWvryeu81q02W05cY+/5GDrULk3tMu4cvBgHQFkvF1IzMhn/fSjxqZkMblmZ0R2q8/K3oflzMSL5RONGJHc0diS/aMtVe7necrVjx45kZWXh4ODA1atXSUpKonbt2jk+z9q1a3FwcGDNmjV2x0wmk5KGAi4tMwtnR9uBdfMf7tSMLJv2fb/HsHjvBSZ2qY2jycTBi7H8FHYNd5cblaaXO9Zg4c7z/HIuBoAp60/wVf9G+Pl6EBaRkPcXI5JPNG5EckdjR8Q4uUoaQkJCePHFF3njjTeoVq0avXv3JjU1leTkZN544w06d+58x+favHlzbkKQAuJaQhrF3ZxxMMHNanHJYs6kpGeSkGq/bd1Xv15k+f5LuLs4EpOcwaudanIlLpUSbk74erpwOtt80siENGKTM/D1dNE/4HJX0bgRyR2NHckvuVr0e5fL1c9kxowZdOnShYCAAJYtW4aLiws7d+7ktddeY86cOTk61759+277kILt9LUkMrIs1C3754396pX35PjVRCx/6duupg/Pt65CepaFmOQMzI4ONKxYnIMXY4lLySAtI4vKJYtZ+3u5OuHl6sSVuBRE7iYaNyK5o7EjYpxcVRpOnDjBnDlzcHNzY/Pmzdx///2YzWaaNm3KpEmTcnSuvn373rLdbDZTunRpNm3alJsQJZ+kZmSxIfQqL7arxhsbT1HKw8wjgeV5Y9NpALyLOZOYmklaZhYXYlIY06EGhy/FcfZaEs+2rExkfCp7z8VgAdaHXmVQy8rEJqcTn5LBoFZVCL0Sz/Gr2s1C7i4aNyK5o7Ej+UVrGuzlKmkoVaoUp06dIikpiWPHjvHKK68AsGvXLsqVK5ejc4WFhdk8z8zM5Pfff+e1116je/fuuQlP8tkHO87zYtuqvPWgP4lpmXy2J5wdp6MAWDGwMbN+OsWPYZGcjEzkna1nGNyyMl5uThwIj2Pc92HWb4fe//kcA5rdw/gHauLi6EBIeCwzN5w17sJE8pDGjUjuaOxIfnBQzmDHZLFY/lrR+0eLFy/mjTfewMHBgVq1arF8+XLmz5/PvHnzmDFjxr/yYf/EiRM8++yzbN26NcevbT939//8/iIiIiKSdzYNa250CH/rxW/D/rlTLr3T0y/Pzp2XclVp6NevH40bN+bSpUu0atUKgGbNmtG2bVv8/P6dH8T169eJi4v7V84lIiIiInKnVGmwl+stV+vWrUvdunWtzxs2bEhaWhqHDh0iICDgjs8zduxYu7bExER27dpFp06dchueiIiIiIj8S3KVNOzfv5/Jkydz6tQpsrJs90V2dHTk6NH/7Y6KJUqU4OWXX6Znz57/03lERERERHJKC6Ht5SppmDp1KhUqVGDUqFEMHz6cWbNmERERwbx583j11VdzdK4ZM2aQkZFBbGwsPj4+ABw4cAB/f3/MZvM/vFpERERERPJaru7TcPLkSUaOHEnr1q3x9/fH2dmZJ554gokTJ/Lxxx/n6FyhoaG0b9/e5nWjRo2iU6dOnDx5MjfhiYiIiIjkmoMp7x6FVa6SBjc3Nxwdb9yGvVq1ahw/fhyABg0acPZszrYrmzJlCh07duSll16ytv3000/cd999TJkyJTfhiYiIiIjIvyhXSUOzZs146623iIiIIDAwkLVr1xITE8PmzZvx8vLK0blCQ0N58skncXZ2/jMoBwf69ev3P6+NEBERERHJKZMp7x6FVa6ShvHjxxMbG8uGDRvo2rUrHh4eNGvWjBkzZjBkyJAcnatcuXLs3m1/X4X9+/dTqlSp3IQnIiIiIpJrDiZTnj0Kq1wthPb19WXx4sXW559//jmnTp3Cy8sLX1/fHJ1r8ODBjB8/ngMHDlCvXj3gxl2iv/vuOyZOnJib8ERERERE5F90x0nDvn37/rFPTEwMv//+O02aNLnjAHr27EnJkiVZtmwZS5YswcnJicqVK/Pxxx/TuHHjOz6PiIiIiMi/IVdTce5yd5w09O3b9476mUwmQkNDcxRE3bp1GTFiBFWrVgVg7dq1VK5cOUfnEBERERGRvHHHSUNYWBgA586do3z58jb3UNi9ezdlypShevXqOQ5g9+7dDBkyhP79+/PCCy8AsHjxYiZOnMj8+fMJCgrK8TlFRERERHKrEC89yDM5qr5MnTqVLl26cPDgQZv2zz//nG7dujFz5kwsFkuOAnj99dcZPHiwNWEA+Prrr3n66aeZPn16js4lIiIiIiL/vjtOGj777DPWrl3Le++9R9OmTW2Ovf/++7z33nusXr2aJUuW5CiAc+fO0alTJ7v2zp07c+rUqRydS0RERETkf6Xdk+zdcdKwbNkyXn31Vdq1a3fL4/fddx+jRo3KcdJQrVo11q1bZ9e+efNm7rnnnhydS0RERERE/n13vKbh4sWLNGjQ4LZ9mjVrxrRp03IUwIsvvsjzzz/Pzp078ff3B26sn/j111+ZN29ejs4lIiIiIvK/KsQFgTxzx5UGHx8fLl68eNs+V65coUSJEjkKoE2bNnzzzTfUrVuXM2fOEB4eTt26dVm7di0tWrTI0blERERERP5XDqa8exRWd5w0dOzYkblz55Kenn7L4xkZGcybN49WrVrlKIBr166xdOlSjh8/TnJyMrGxsRw+fJjRo0craRARERERKQDuOGl4/vnniYiIoHfv3ixbtoxjx44RHh7O0aNHWbp0KQ8++CDh4eEMGzYsRwGMGzeOn3/+mfr167N//34aNmyIj48Phw8fzvG5RERERET+V1oIbe+O1zR4eXmxbNky3nzzTWbOnElycjIAFosFT09PunTpwrBhwyhVqlSOAti3bx+LFi0iMDCQnTt30rZtW4KCgli4cCHbt2+nX79+ObsiERERERH5V91x0gBQokQJpk6dyoQJEwgPDycuLo4SJUpwzz334OjomKsALBYLvr6+ANSoUYNjx44RFBRE586d+fjjj3N1ThERERGR3CrEBYE8k6Obu91kNpupXr06gYGBVK1aNdcJA0DdunX59ttvAahTpw47d+4E4MKFC7k+p4iIiIiI/HtyVGnICyNHjmTw4MG4ubnRs2dPPvroI7p3786lS5fo0aOH0eGJiIiISBFTmHc5yiuGJw1BQUFs2bKFlJQUvL29WblyJRs3bqREiRJ07tzZ6PBERERERIo8w5MGAA8PDzw8PADw9fXliSeeMDgiERERESmqTKjU8FcFImkQERERESkoND3JXq4WQouIiIiISNGhSoOIiIiISDaqNNhTpUFERERERG5LlQYRERERkWxMurubHVUaRERERETktlRpEBERERHJRmsa7KnSICIiIiIit6VKg4iIiIhINlrSYE9Jg4iIiIhINg7KGuxoepKIiIiIiNyWKg0iIiIiItloIbQ9VRpEREREROS2VGkQEREREclGSxrsqdIgIiIiIiK3pUqDiIiIiEg2DqjU8Fd3ZdIQGZlodAgihdK9gRWMDkGkUDp7NcHoEERE8tRdmTSIiIiIiOSW1jTYU9IgIiIiIpKNtly1p4XQIiIiIiJyW6o0iIiIiIhk46D5SXZUaRARERERkdtSpUFEREREJBsVGuyp0iAiIiIiIrelSoOIiIiISDZa02BPlQYREREREbktVRpERERERLJRocGekgYRERERkWw0FceefiYiIiIiInJbqjSIiIiIiGRj0vwkO6o0iIiIiIjIbanSICIiIiKSjeoM9gxPGvz8/P62BOTs7Ezp0qXp3Lkzw4cPx9nZOZ+jExERERExRmpqKpMnT2bDhg24uroyYMAABgwYcMu+O3bsYNasWYSHhxMQEMCECROoVq0aALVr177la15//XV69ep1R7EYnjRMmjSJefPmMWzYMBo2bIjFYuHo0aPMnTuXhx56iFq1avHee+9hsVgYPXq00eGKiIiIyF2uoNzcbdasWRw9epTPPvuMS5cu8fLLL1O+fHk6depk0+/kyZMMGjSIZ599lu7du7NixQqefPJJ1q9fj7u7Ozt27LDp/+mnn7Ju3Trat29/x7EYnjR8/PHHTJ8+nTZt2ljb/Pz8KFeuHFOmTOGFF17A19eXYcOGKWkQERERkSIhKSmJ5cuX8+GHH+Lv74+/vz8nT57kyy+/tEsalixZQmBgIMOHDwdg9OjRbN26le+//54+ffpQunRpa9/w8HA+//xz5s+fj6en5x3HY/hC6GvXrlG2bFm79lKlShEREQFA6dKlSUxMzO/QRERERKQIMuXh406FhYWRkZFBYGCgtS0oKIhDhw6RlZVl0zc8PJwGDRr8Gb/JRK1atTh48KDdeefMmUPz5s1p0aJFDqIpAElDy5YtmTJlChcvXrS2Xbx4kWnTptGsWTMyMzNZuXIltWrVMjBKERERESkqTKa8e6SlpZGQkGDzSEtLs4shMjISb29vzGazta1UqVKkpqYSExNj0zf7l+03XblyhejoaJu2S5cusWbNGp5//vkc/0wMTxqmTp2Ks7Mz7du3p1mzZgQHB9OhQwdcXFx47bXX2LZtG0uWLOHll182OlQRERERkf/JggULCAoKsnksWLDArl9ycrJNwgBYn/81yejcuTM//vgjW7ZsISMjg9WrV3PkyBHS09Nt+q1YsYJ69eoREBCQ47gNX9NQokQJPvnkE86ePcuJEydwdHSkRo0aVKlSBYAWLVqwe/du3WRDRERERPJFXn7uHDRoEE899ZRN21+TAwAXFxe75ODmc1dXV5v2Nm3aMGTIEIYNG0ZmZibBwcH07NmThIQEm34//vgjffr0yVXchicNAwYMoGvXrnTs2JEHHnjA7vhffygiIiIiIoWV2Wy+ZZLwV76+vkRHR5ORkYGT042P7JGRkbi6uuLl5WXX/7nnnmPgwIHEx8fj4+PD8OHDqVChgvX45cuXOXXqVI52TMrO8OlJ9erV48MPP6Rly5YMHjyY7777ToueRURERMQwDnn4uFN16tTBycnJZjFzSEgI9evXx8HB9kxr1qxh2rRpmM1mfHx8SElJYc+ePQQHB1v7HDp0iHLlylG+fPkcRPEnw5OGESNGsH79elasWIG/vz8ffvghLVq04IUXXmD9+vVGhyciIiIiku/c3Nzo1asXkyZN4vDhw2zcuJFFixbRr18/4EbVISUlBYAqVarw9ddfs2HDBs6dO8fIkSMpV66czS0NTp48SfXq1XMdj+FJw021a9dm2LBhfPXVVwwZMoQdO3bw0ksvGR2WiIiIiBQxJpMpzx45MXbsWPz9/XnyySeZPHkyw4YN4/777wegVatWrF27Frgxc2fSpEnMnDmT3r17AzcWXGevSFy7do3ixYvn/mdisVgsuX71vyQqKopNmzaxYcMGfvnlF2rUqEHnzp3p2rWrzVysO9VgwsY8iFLk7ndvYM7Hm4jA2asJ/9xJRGysGdTE6BD+1rKDl/Ls3I82zN30IKMZvhC6b9++7N+/n8qVK9OlSxfGjh1LtWrVjA5LRERERIoo7dlpz/CkoWHDhowfPx4/Pz+jQxERERERkVswPGkYOXIkGRkZREREkJmZCYDFYiEtLY3Q0FC6dOlicIQiIiIiUpTo/mD2DE8aNm3axH//+1+722EDlC5dWkmDiIiIiOSrArNTUAFi+M/kzTffpGPHjvzwww94eXnx9ddfM3/+fCpUqMCLL75odHgiIiIiIkWe4ZWG8PBwFixYwD333EO9evWIjIykQ4cOODg4MGvWLOu2USIiIiIi+UHTk+wZXmnw8vIiOTkZgKpVqxIWFgZAtWrVuHDhgpGhiYiIiIgIBSBpuPfee5k8eTKnTp0iODiYb7/9lt9++42lS5dSpkwZo8MTERERkSLGlIePwsrwpGH8+PFUrlyZo0eP0qFDBwICAnj44Yf58ssvefnll40OT0RERESkyCsQd4T+q4SEBFxcXHB2ds7V63VHaJHc0R2hRXJHd4QWybmCfEfob49cybNz96xfNs/OnZcMXwh9Kx4eHkaHICIiIiIifyiQSYOIiIiIiFEcCvXqg7yhpEH+Z2YnB8Z1rU2HumVIzcjis53nWbzr91v2bV69JCMeqEklbzcOX4hl+prjnLueZD3+ZMt76NO0Ep6uTmwOjWTG2uMkp2Xm16WI5BsnBxOPBpQloLwn6VkWNp+8zuZTUbfs61fGnV71ylDK3cy5qGSWHbrC1YQ06/HOfqVoXqUELo4OhF1NZPmhKyRo3MhdytnRxHOtKtOiqjdpGVmsPnyF1Ycjbtk3sKIXA5pVoqyXC8cjEvhgx+9cjE2xHn88qDz3+5XG1dmB/RfimL/jPHEpGfl1KVKAacdVe4YvhJbCb8T9NfGv4MUzn+5n2powBretRse69jtfVS/tzrz/a8iWsEj6zN9L6OV4PnyqEW5mRwAeblyB59pWY87GUzz50a+U8XLh9Yfr5ffliOSLXvXKcI+3K3N3/M6yg1fo5FeKhuU97fqV9TQzuHklDl+OZ9aWs4THpDCs1T2YHW/8RmtZpQTNK5dg8b5LvLP9PMVdnXisUbn8vhyRfDOgWSVqlnZn/JrjfLDjPI8FVaBlVW+7fvd4uzKxU01+ORfNiyuPcfpaEtO718bV6cZHn051StPRrzRvbj7Dy9+G4VPMmRfurZLPVyNSeBSIpGHjxo306dOHpk2bEhQUxMMPP8w333xjdFhyB9ycHegdVJ7X154g9HI8m0Mj+WTnefoEV7Lr+2jTihwKj+X9zWc4dz2JtzecIiElg64NbiwIejy4Eot3/c66IxGcjkzkv6t+o02tUlTxKZbflyWSp8yOJppXKcGKwxFciE3h8OV4Np28Tptq9h98Wlf15kxUEmtDr3E1IY1vf7tKcnoWTSoVB6BuWQ/2X4zj1PUkLsensvHkdWqXds/vSxLJFy5ODtzvV5qFO3/n9LUkdp+LYeXBy3SrZ/9FVZe6ZQiNSODLXy9xMTaFT/ZcIDEtk7Y1fQBofE9xfj4dxdHL8ZyPTmblocsEVPDK70uSAsqUh/8rrAxPGr7++mtGjx5NkyZNmDlzJq+//jpNmzZl8uTJLF++3Ojw5B/UKuuJk4OJg+Ex1rYD52OoX9HLrrRX0duNIxdibdpORiQQ8MeHnwp/TFm66VpCGtFJaTT447jI3aJCcVccTSbOZpuad/p6MpVLutn9OvFxN3M+KsWm7XJcKlVLugGQmJaJf1kPirs64exgIqiiFxdiUhC5G1X1KYaTg4nQiD93qzp2JYFaZTzsxk5ZLxdOXE20aTsXlYyf743NVuJTMmhyT3F8ijljdjTRproPZ64lISK3Zviaho8++oiJEyfSq1cva1uHDh2oWbMm8+fP55FHHjEuOPlHpT1diElKJyPzz517ryek4ursSAk3Z6KT0rO1p1HG08Xm9WWLuxKbfKNPVGIavl5/HndzdsDLzRlv99xtvStSUHm5OpGYlkm2YUN8agZmRwfczY426xHiUzMo7mb7T3UJNyeS0m/0WR92jUHNKjK1c00ysyzEpWQwe9u5/LgMkXxXspgzcSkZZGT9OXiik9NxcXLA09XJZj1CdHI6Pu5mm9eXdjcTn3qjz5KQS0zoVJPP+jYkM8tCVFI6o745lj8XIgWe1jTYM7zScP36dRo2bGjXHhgYyOXLl/M/IMkRV2cH0jKzbNrS/vgkZHay/ev149EI7vf3pU2tUjg6mOjRsBz+FbxwdrzRb/3RCAa2rkLVUsUwOzkwqlMtAOtxkbuF2dFk86EHsCbeTg62v6n2X4gjsIIX/mU9cDBB03uKU9nbDcc/fqOVLOZMWqaF+bvDeffn88SkpPO41jTIXcrFyYH0v/zOSf9j7Dg72o6dn09H0bKaN03uKY6DCe6r5UPN0sWsY8zX04XUjCwmrzvBK9+FcT0xjeH3Vs2fCxEphAyvNNSpU4dvvvmGF1980aZ99erV1KhRw5ig5I6lZmRh/suH+psLNJPTbXdv2XnqOvO3nmF2nwY4OpjYdzaK7w9extP1xl/DhVvPUNHbjdVDm5ORZWH5rxc4fiWeBO1kIXeZ9EyLXXLg9Me4+WsSHno1kXWhkQxsWgFHBxMnI5PY+3ssrs43xl3foPJ8ezSC367cmK6xaO9FJj9Qg8rerpyP1jQlubukZWbZfZF0M1lIzbAdO/vD41gScolx99fAwWTiyKU4Np+8jvsfm2+81K4qn+y5wL7fb0yLnfnTaRY90YBaZdztpjVJ0aMtV+0ZnjSMHj2a/v37s2fPHgICAgA4ePAgYWFhzJ8/3+Do5J9cjUulRDFnHB1MZP7xzWkpTxeS0zKJv8WH/Q+3n+PTnefxdHUiKjGdNx6tz6U/5l8np2cxetkRPFwcsQCJqZlsHdPGelzkbhGbkoG72REHE9wsOHi5OJGWkUVyepZd/w0nbmzH6urkQEJaJk81qUBUUjoeZkdKFnPmYmyqtW9McgaJaZmULOaspEHuOtcT0/FydbIZO97FnElJzyQx1X6b4WUHLrPq0BXczY7EpmTwcofqRMSnUdzViTKeLjbriq4lphGXkkEZD7OSBpFbMHzeR2BgIKtWrSIgIIDTp09z4cIFmjRpwrp162jWrJnR4ck/OH4lnowsCw0q/rnjROA9JfjtUhwW29kXdK7vy5jOtUjPtBCVeGMOapOq3uw9e2Nv+pfur0GPhuVISL3xj79/eS88XJ1sFlmL3A0uxKaQabFQ5Y/FzADVfIpxPiaZvwwbgip60bu+LxlZFhLSMnF2MFGzdDFORiaRlJ5JemYWZbOtBXI3O+JuduR6Yjoid5uz15PIyLJYFzMD+Jf14GRkot3YaVO9JM+0qERGloXYlAzMjiYalPfk8KU44lMzSMvIopL3n2PQy9UJTxcnIuLTEDGZ8u5RWBleaXj++ecZOXIkr7zyitGhSC6kpGfx3cHLvNq9Dq+uPkYZLxeebFmZCat/A8DHw0xCSgapGVmcu5bElF51CTkXzcmIBF66vyYRsSnsOHkdgMj4VAa3rcrpq4lkWSzMeNifZfsuEJes6Ulyd0nPtLD391j+07AsX4ZcpoSbE+1rluTL/TfWcXm6OJKSnkV6loWrCWk80agcp68ncSk2hZ71fIlJzuBYRAIW4JfzsfSqV4aE1AyS0rLoVb8M56KS+V0VOrkLpWZksfnENYa0rsw7W8/h4+7Mgw3K8s4fi/9LuDmRlJZJWqaFi7EpvNi2KkcvJ3D+ehJPNatEZEIaIb/HYgE2Hr/GwGYViUtJJyElkwHNK3H8agInI1VlkML94T6vmCyWv34fnL+aNWvG0qVLqVy58r92zgYTNv5r55J/5urswH+7+dGhbhniUzP4bOd5vtgdDsDhKR3476rf+O7gjQ9DPQPLMbhtNYq7ObPnTBTT1oRx7Y872zqYYFSnWnRtUBaLBb4/dJl3fjplnfYkee/ewApGh1BkODua+E/DsjQs70VyeiabTl5n6+loAOY+WIcvQi6x54+51sH3FKezXymKmR05EZnEsoNXiPtjBxgnBxPd6pamUUUvzI4mwq4msuJQhO4Inc/OXk34507yr3BxcuD5VpVpUc2bpLRMVh66wndHbtwRes2gJry95QybTtz4MqpD7VL0aVQeL1cnDl2M4/0d5627+jk7mujbpCJtqpfE7OTAwQuxzN/5u+4InY/WDGpidAh/a0NoZJ6d+/46pfPs3HnJ8KRhzpw5bN26lT59+lC+fHlcXGy35GzSJOd/oZQ0iOSOkgaR3FHSIJJzBTlp+Cn0Wp6du2OdUnl27rxk+PSk999/H4AJEybYHTOZTISGhuZ3SCIiIiIiko3hSUNYWJjRIYiIiIiIWDloTYMdw3dPSktLY9asWXz55ZfWtt69e/Pmm2+Snq7dP0REREREjGZ40jB16lS2bduGn5+fte35559n69atvP766wZGJiIiIiJFkSkP/1dYGZ40bNiwgTfffJOgoCBrW4cOHZgxYwZr1641MDIREREREYECsKbBYrGQmpp6y3ZNTxIRERGR/Kb7NNgzvNLwwAMP8Oqrr/Lrr7+SlJREUlIS+/fvZ9KkSXTs2NHo8ERERESkiNH0JHuGVxrGjh3L+PHjefLJJ8nKygLAwcGBXr16MW7cOIOjExERERERw5MGNzc3Zs+eTVxcHOfPn8fZ2ZmKFSvi4eFhdGgiIiIiUgRpy1V7hicNAFFRUZw9e5asrCxSUlI4duwYaWlpHDt2jGeffdbo8EREREREijTDk4Zly5YxZcoUMjIyMJlMWCwW4MbdoBs0aKCkQURERETyVWFee5BXDF8IPX/+fAYPHszhw4fx8fFhy5YtrFmzhjp16mghtIiIiIhIAWB40nD16lV69eqF2WzG39+fgwcPUqNGDcaNG8fy5cuNDk9EREREihiTKe8ehZXhSUPJkiWJiooCoFq1aoSGhgLg6+tLRESEkaGJiIiIiAgFIGno3LkzL7/8Mvv376d169asWrWKH3/8kffee4/KlSsbHZ6IiIiIFDGmPHwUVoYvhB41ahSenp5ER0fTvn17HnroISZOnEiJEiWYPn260eGJiIiISBHjUJjnEeURk+XmdkV3kQYTNhodgkihdG9gBaNDECmUzl5NMDoEkUJnzaAmRofwt3afismzczevUSLPzp2XDK80JCUlsXz5cs6cOUNaWprd8RkzZhgQlYiIiIgUVaoz2DM8aRgxYgQHDhygRYsWuLq6Gh2OiIiIiIj8heFJw549e1i0aBGBgYFGhyIiIiIiolLDLRi+e1K1atVISUkxOgwREREREfkbhlcaZs6cydChQ+nevTvly5fHwcE2j+nVq5cxgYmIiIhIkWRSqcGO4UnDsmXLOH/+PEuWLMHFxcXmmMlkUtIgIiIiImIww5OGFStWMHv2bLp06WJ0KCIiIiIi6DYN9gxPGry9valRo4bRYYiIiIiIAFoHfSuGJw0TJ05kypQpDBkyhIoVK+Lo6GhzvHz58gZFJiIiIiIiUACShkGDBgHw1FNPYcpWC7JYLJhMJkJDQ40KTURERESKIpUa7BieNGzatMnoEERERERE5DYMTxoqVKhgdAgiIiIiIlbactWe4Td3ExERERGRgs3wSoOIiIiISEGiLVftqdIgIiIiIiK3pUqDiIiIiEg2KjTYU9IgIiIiIpKdsgY7mp4kIiIiIiK3pUqDiIiIiEg22nLVnioNIiIiIiJyW6o0iIiIiIhkoy1X7anSICIiIiIit6VKg4iIiIhINio02Lsrk4aSJYsZHYJIoXTsQozRIYgUSg6ayyAid7m7MmkQEREREck1fQ9gR0mDiIiIiEg22nLVnhZCi4iIiIjIbanSICIiIiKSjZYp2VOlQUREREREbkuVBhERERGRbFRosGd40rBv375btptMJpydnSldujTly5fP56hEREREROQmw5OG8ePHc+HCBbKysihevDgWi4W4uDhMJhMmkwmLxUKDBg2YO3cuZcqUMTpcEREREbnbqdRgx/A1DQ8++CD169dn3bp17Nmzh7179/LTTz/RuHFjRo8ezc6dO/H19WXq1KlGhyoiIiIiUiQZnjR89tlnTJ48mapVq1rbKlWqxPjx41mwYAElS5Zk+PDh7N6928AoRURERKSoMOXh/worw5MGgOjo6Fu2ZWZmWp+btPeViIiIiIghDF/T8PDDD/Pyyy/z0ksvUa9ePSwWC7/99hvvvvsuDz74INHR0bzxxhs0bdrU6FBFREREpAjQd9X2DE8aRo4cibu7O2+//TZXr14FoEyZMvzf//0fAwcOZNeuXTg5OTFhwgSDIxURERGRokA5gz2TxWKxGBlAWloaZrMZuDElycnJCU9Pz//pnG3f2fVvhCZS5Dg66p9Jkdxw0NeSIjn209BmRofwt0IvJebZueuUd8+zc+clwysNzZs3p0OHDnTp0oWWLVvi5GR4SCIiIiJSlOl7ADuGL4R+9913cXFxYdy4cbRs2ZLx48eza9cusrKyjA5NREREREQoANOTbsrKymLfvn389NNPbNq0ibS0NB544IFcrWXQ9CSR3NH0JJHc0fQkkZwryNOTwi4n5dm5/coVy7Nz56UCMxfIwcGBoKAgUlJSyMzM5Ntvv2X79u1GhyUiIiIiUuQZnjSkpqayfft2fvzxR7Zt20axYsXo1KkTn3zyCQEBAUaHJyIiIiJFjIqH9gxPGoKDgylWrBgdO3bkvffeo0mTJrqRm4iIiIhIAWJ40jB37lxatGiBo6Oj0aGIiIiIiGjzpFswPGlo3bo1oaGhnDx50rpjksViIS0tjWPHjjF58mSDIxQRERGRIkVZgx3Dk4Z58+Yxb948SpUqxfXr1/H19eXatWtkZmbSsWNHo8MTERERETFEamoqkydPZsOGDbi6ujJgwAAGDBhwy747duxg1qxZhIeHExAQwIQJE6hWrZr1+Pr163n77beJiIigUaNGvPbaa1SoUOGOYzH8Pg1Lly5l8uTJ7Nixg3LlyvH555+za9cuWrRowT333GN0eCIiIiJSxJjy8H85MWvWLI4ePcpnn33GxIkTmTdvHuvXr7frd/LkSQYNGkT79u1ZuXIldevW5cknnyQx8cadrffv38/IkSN56qmnWLVqFWazmREjRuQoFsOThujoaFq3bg1AnTp1OHDgAF5eXrz00kusXbvW4OhERERERPJfUlISy5cvZ/z48fj7+9OxY0eefvppvvzyS7u+S5YsITAwkOHDh1OtWjVGjx6Np6cn33//PQCLFi2iR48e9OnTh2rVqjF+/HgiIyOJioq643gMTxp8fX0JDw8HoHr16hw7dgwADw+PHF2IiIiIiMi/wWTKu8edCgsLIyMjg8DAQGtbUFAQhw4dsq4Dvik8PJwGDRpki99ErVq1OHjwIAB79+61mfZfqVIlNm/eTMmSJe84HsPXNDzyyCOMGDGC6dOn06FDB/r370+ZMmXYtWsXfn5+RocnIiIiIvKvSUtLIy0tzabNbDZjNptt2iIjI/H29rZpL1WqFKmpqcTExNh84C9VqhQRERE2r79y5QrFixcnLi6O2NhYMjMzGThwIGFhYTRo0IBJkybh6+t7x3EbXmkYPHgwo0ePxs3NjQYNGjB27Fh++OEHLBYL06dPNzo8ERERESliTHn4WLBgAUFBQTaPBQsW2MWQnJxsl0jcfP7XpKNz5878+OOPbNmyhYyMDFavXs2RI0dIT08nKSkJgKlTp9K9e3c++OAD0tLSGDRokF3F4nYMrzQA9OrVy/rnRx55hEceecS4YERERERE8sigQYN46qmnbNr+mhwAuLi42CUHN5+7urratLdp04YhQ4YwbNgwMjMzCQ4OpmfPniQkJFjvhfbII49YP3O/+eabtGzZkoMHD9KoUaM7irtAJA0iIiIiIgVGHt6n4VZTkW7F19eX6OhoMjIycHK68ZE9MjISV1dXvLy87Po/99xzDBw4kPj4eHx8fBg+fDgVKlTA29sbZ2dnm+1Xvb29KVGiBFeuXLnjuA2fniQiIiIiUpAUhC1X69Spg5OTk3UxM0BISAj169fHwcH2I/yaNWuYNm0aZrMZHx8fUlJS2LNnD8HBwTg5OeHv709YWJi1f1RUFNHR0YXrPg0iIiIiImLLzc2NXr16MWnSJA4fPszGjRtZtGgR/fr1A25UHVJSUgCoUqUKX3/9NRs2bODcuXOMHDmScuXK0aZNGwCeeuopPv/8c9atW8fp06cZN24cderUsdlx6Z9oepKIiIiISDY52Ro1L40dO5ZJkybx5JNP4uHhwbBhw7j//vsBaNWqFTNmzKB3797Uq1ePSZMmMXPmTGJiYmjevDkLFiywViQ6depEXFwcb7zxBtevX6dp06a8//77mHJwoSaLxWLJk6u8jb59+95xkIsXL87x+du+syvHrxERcHQsIP9KihQyDgXlE4ZIIfLT0GZGh/C3zl5LybNzVy3l+s+dCiBDKg3BwcHWP0dHR7N06VI6dOhA/fr1cXZ2JjQ0lLVr1/LEE08YEZ6IiIiIFGH6GsCeIUnD0KFDrX/u378/48aN4/HHH7fp06RJE5YuXZrfoYmIiIiIyF8YvhD64MGDNG/e3K49ICCA48ePGxCRiIiIiBRpeXl3t0LK8KShbt26LFy4kNTUVGtbQkICc+bMoWHDhsYFJiIiIiIiQAHYPem1117j2WefpWXLllSuXBmLxcK5c+coX778LW+pLSIiIiKSl3JyP4WiwvCkoXr16qxbt45du3Zx+vRpAGrWrEmLFi2sd7+Tgs3saGJ4u2rcW9OH1IwsloZcYtn+S7fs2/ie4gxuXYUKxV05diWed7acITz6zx0K+jerRFf/Mrg6O7Lv9xje3XKG2OSM/LoUkXzj7Ghi+L3VaF2jJKkZWSw/cInlBy7fsm9QpeIMalWZ8l6uHIuIZ87Ws1yI+XPc9GtakS7+ZXB1cuTX8Bjmbj1LbIrGjdydnB1NDLu3Kq2r3xg7Kw5cZsXBvx87z7S8h/JeroRGJDB3m+3Y6du0Ip3rlsbVyZGQ8FjmbdPYkRu0IZo9w6cnwY3baVeoUIF77rmHPn36ULVqVRwdHY0OS+7Q4NZVqO3rwUsrfuPtzWd4Mrgi99bwsetXpaQbM3vWYefpKJ5dcogTVxOZ/ZA/bs43/hp2r+9LF/8yTF1/kheWH6WUu5nRHWrk9+WI5ItBLStTy9edUauP8e7Ws/RtWpE21Uva9atc0o3p3f3YdSaawUsPc+pqIm896I/rH+Omm38ZOtctw/QfT/HiyhvjZmT76vl9OSL55tmWlalVxp3R3xxj7raz/F/TCrT+m7EztVttdp+J5vllRzgZmcgbvepax05X/zJ0qlOamRtOMWLVb/i4OzPivmr5fTkihYbhSUNsbCz9+/enZ8+eDB8+nKioKKZNm0a3bt24ePGi0eHJP3B1cqBrvTLM23aWk5GJ7Dgdxdchl3iwYVm7vj0blOXo5Xg++SWc8OgUFuw4T2JqJh38SgMQXMWbLSeucehiHGevJ7Hk14sEVSqe35ckkudcnRzo4u/Le9vPcTIykZ1nolgacomeDezHTY/6ZfntSgKf7gnnQkwKC3f9TmJaBh1qlQKgaRVvtp68zuFLcZyLSmZpyCUaVdS4kbuTq5MDneuW4f2fz3MqMomdZ6JZtv/yLcdO93q+HLuSwGd7L3AhJoWP/hg77W+Oncol2HbqOocvxXMuKpll+y8RqLEjf9A6aHuGJw1Tp07Fzc2NX375BRcXFwCmTZtG2bJlmTp1qsHRyT+pXtodJwcHjl6Kt7YduRRHnbIedgOjXHFXQq8k2LSduZ6EfzlPAOJS0mlW1ZtS7mbMjg60r12Kk5GJeX0JIvmuWqliODmY+O3yn+Pm6OV46pT1tB83Xi6EXYm3aTtzPYm61nGTQXCVEtZx065WKU5d07iRu9PNsXPsL2PHz/cWv3O8XAiNsP2dc/Z6MnXLZhs7lb3xcXfG7GjS2BH5B4YvGvj555/5/PPP8fLysrb5+PgwduxY+vTpY2Bkcid83J2JTU4nI+vPG4tHJabj4uSIl5uTzXqE6KR0SnmYbV5fxsNM/B/zRxfvucD0Hn6seKYxmVkWriemMWTpkfy5EJF85ONuths30UnpuDg54OXqZDOnOjopHR+7ceNiHTef773A1G5+LB0QZB03w5YfzZ8LEclnJW8xdmKS0m49dpLTKeVuO3ZKe5iJT73R54t9F3mtW22+furPsTN8xW/5cyFS4GlNgz3DKw2AzXarN0VFRWkhdCHg4uRIWqbFpi09MwsAs6PtX68tJ67RtqYPzat642iCB+qUxs/XA6c/+pX1ciElI4ux34YyfPlRIhPSGNNRaxrk7uPi5ED634wb57+Mm60nr3NvDR+aVSmBgwnu9ytN7TLuODne+I1W1suF1IxMxn8fykurfuNaQhqjO2hNg9ydXG8xdm7+DrrV2GlToyTBf4ydjn6lqF3GHWeHG2PH18uFlPQs/rsmjJGrfuNaYhqj2mtNg8jfMfxTebdu3Zg2bRpTpkzBZDKRlJTEL7/8wsSJE+nSpYvR4ck/SMvMwuxom47f/Ic7JT3Lpn3v+Rg++yWcyV1r4+hg4uCFWH4MjcTD5cZfw7H312T+jnPsPhsNwKQfjrN0YBB1ynrYTWsSKczSMrNw/ptxk5phO272/R7D4r0XmNilNo4mEwcvxvJT2DXcXW5sFvFyxxos3HmeX87FADBl/Qm+6t8IP18PwiI0buTukpZhP3Zu/g5Kzci0af/191i+2HuBCZ1r4WgycehiHD8dv4a7+Y+x06E6C3f+zp4/xs7U9Sf54slAjR35g0oNf2V40jBmzBhmz55N7969SU9Pp1evXjg6OvLwww8zZswYo8OTf3AtIY3ibs44muDmlz8l3Z1JSc8kIdV+27ov9l1k6f5LuJudiElOZ2KXWlyJS6GEmzO+Xi6cjkyy9o1MSCM2OQNfTxclDXJXuTluHExwc5ZFyWJ/P26++vUiy/dfwt3FkZjkDF7tVJMrcamUcHPC19OF09nmYWcfN/rgI3eba4n2Y8e7mPmPsZNp1/+rkBtbGd8cO/99oCYR8TfGThlPF87cYuyU8TQTFpFfVyRSeBg+PclsNvPKK6+wb98+vv/+e1avXs2ePXuYNGkSSUlJ/3wCMdSpyEQysrKsizIB6pf3IiwiActf+t5XuxRD761CeqaFmOR0zI4OBFYszoHwOOJT0knLyKJySTdr/+KuTni5OnE5zn76mkhhdvpaEhlZFuuCTIB65T05fjXRbty0q+nD862rkJ5lISY5A7OjAw0rFufgxVjiUjL+GDfFrP29/hg3V+JSELnb3Bw7dbKPnXKenPibsfNcq8rZxo6JgIpeHLwQl23s/Pk758+xo985cmNNQ149CivDk4Y6deoQFRWFq6srNWvWxM/PD3d3dy5evEj79u2NDk/+QWpGFj8ei2TEfdWp7etBq+ol+U9QeVb+cZOqksWcrWsbLkQn06N+WVpXL0mFEq682rkmVxNS2XMumkwLrDt2lefaVKFBBS+q+hRjfKeaHLsSz3F9Wyp3mdSMLDaEXuXFdtWoXcadltW8eSSwPKsO3Rg33tnHTUwK3ev50qp6SSoUd2X8AzWJjE9l77kYsiywPvQqg1pWpn55T6qUdGPs/TUJvRLP8avaBUbuPqkZWfwUFsnwtlWpVcadFlW9eSSwHKttxs6NT2UXYlLoVs+XVtW8qVDclbH31yQyPo1952+MnR9DI3k229h5pWMNwiISOKGxI2jL1VsxWSyWvybnee6bb75h1apVAOzdu5fAwECcnZ1t+ly9epWsrCw2bNiQ4/O3fWfXvxKn3BkXJwdeuq8a99bwISEtg6Uhl1jxR9Kw9cUWzNxwkvXHIgHoVLcMTwZXxMvVif3hsby9+QxRSenAjXmpA1vcw321SmF2ciDk91je3ao7QucnR8fC/M9Z4eLi5MCLbavSuroPiWmZLN1/kVWHrgCwaVhzZv10ih/DboybB+qUpm+Tini5OXEgPI53t/45bpwdTQxodg/tavng4uhASHgsc3VX23znUJi/PixkXJwceKFtVVpXK0liWibLDlxi9R9j56ehzXhj42k2ZBs7TzSpgJfrjbEzd9tZm7HzVLNKtK3pg8sfv3Pe235OYycf/TS0mdEh/K1LMWl5du7yJcz/3KkAMiRpSExM5JNPPgFg3rx5PPXUU7i7u9v0KVasGB07dqRSpUo5Pr+SBpHcUdIgkjtKGkRyriAnDZdj8y5pKFe8cCYNhiyEdnd3Z+jQoQBUqFCBLl26WG/sJiIiIiIiBYvhuyc9+OCDnDlzhuPHj9/yfg29evXK/6BEREREpMgyFerVB3nD8KTh008/ZebMmXh5eeHh4WFzzGQyKWkQERERETGY4UnDhx9+yCuvvEL//v2NDkVEREREpHBvc5RHDN9yNSUlRVurioiIiIgUYIYnDT179uSrr74yOgwREREREUD3abgVQ6Yn9e3bF9Mf29Olp6dz4MAB1q1bR8WKFXFwsM1jFi9ebESIIiIiIlJEaRdle4YkDcHBwTbPW7ZsaUQYIiIiIiJyBwxJGm7eo0FEREREpKDRlqv2DN89KftUpexMJhPOzs6ULl2azp0706ZNGwOiExERERERwxdCN2nShP3791O6dGk6duxIhw4dKFu2LCEhIZQpUwY3NzdGjBjBypUrjQ5VRERERIoCrYS2Y3ilYffu3YwdO5YnnnjCpr1x48Z8++23fPnllzRr1ozZs2fz0EMPGRSliIiIiEjRZXil4dixY7dcCN20aVOOHDkCQL169bh8+XJ+hyYiIiIiRZAKDfYMTxr8/Pz44osvsFgsNu1fffUVNWrUAODIkSOULVvWiPBERERERIo8w6cnvfrqqzzzzDNs3bqVunXrAhAaGkpCQgLz588nJCSE0aNHM2HCBIMjFREREZGiQPdpsGey/PUrfgMkJCTwww8/cOLECRwdHalZsyZdu3alWLFiXLhwgYSEBPz8/O74fG3f2ZWH0YrcvRwd9a+kSG446BOGSI79NLSZ0SH8rajEzDw7d0l3xzw7d14yvNIA4OHhwX/+859bHqtYsWI+RyMiIiIiItkZkjS0b9+eFStW4O3tzX333XfL+zTctGnTpnyMTERERESKOhUP7Rl2R2h3d3cAhg0bZkQIIiIiIiJyhwxJGh588MFb/jk2NhZPT09MJtNtqw8iIiIiIpJ/DN9y1WKx8MEHHxAcHEzz5s25ePGidbektLQ0o8MTERERESnyDE8a3nvvPb777jtmzpyJ2WwGblQfdu7cyaxZswyOTkRERESKGpMp7x6FleFJw+rVq5kyZQrt2rWzTklq2bIlr7/+OuvWrTM4OhERERERMXzL1evXr1OmTBm7di8vL5KSkgyISERERESKMhOFuCSQRwyvNDRr1oyPP/7Ypi0hIYHZs2cTHBxsUFQiIiIiUlRpepI9w5OGSZMmcezYMVq2bElqairPP/889957LxcvXuS///2v0eGJiIiIiBR5hk9PKlu2LCtWrGD37t2cOXOGjIwMqlatSqtWrXBwMDynEREREZEiphAXBPKM4UnD448/zr333kurVq144oknjA5HRERERET+wvCkoVevXuzcuZNPPvkER0dHWrZsSevWrWnVqhXe3t5GhyciIiIiRY1KDXZMFovFYnQQcOMmb8eOHWP37t3s3LmTffv2UadOHZYvX57jc7V9Z1ceRChy93N01L+SIrnhUJhXN4oY5KehzYwO4W/Fp2bl2bk9XQrn9HvDKw0AmZmZ/Pbbb+zfv59Dhw5x4sQJzGYzXl5eRocmIiIiIkWMtly1Z3jS0LdvX44ePYqXlxcBAQEEBQUxaNAg6tatq4XQIiIiIiIFgOFJg5OTEyaTCW9vb8qUKYOvry++vr5KGERERETEEJpxaK9ArGnIyMjgt99+Y9++ffz6668cPHgQT09PGjduzIwZM3J8Pq1pEMkdrWkQyR2taRDJuYK8piExLe8+HrubC+e/F4ZXGuBGtSEgIAB3d3fc3Nwwm81s2bKFX375xejQRERERKSIKZwf6/OW4UnDl19+yd69e/n1119JSkqiSZMmtGzZkuHDh1O9enWjwxMRERGRokZZgx3Dk4Zly5bRqlUr+vTpQ1BQEGaz2eiQREREREQkG8OThm+//dboEERERERErLTlqj1tUSQiIiIiIrdleKVBRERERKQg0YZo9lRpEBERERGR2yoQ92kQEREREZGCS5UGERERERG5LSUNIiIiIiJyW0oaRERERETktpQ0iIiIiIjIbSlpEBERERGR21LSICIiIiIit6WkQUREREREbktJg4iIiIiI3JaSBhERERERuS0lDZKv9uzZQ+3atf+1fiJi78KFC9SuXZsLFy4AULt2bfbs2WNwVCK3tmnTJtq0aUNAQAA///wzAGlpaXTr1k1/b0UKECUNkq8CAwPZsWPHv9ZPREQKtzlz5tCqVSvWrl1LkyZNSE1NZcSIEZw8edLo0EQkGyUNkq/MZjOlS5f+1/qJiEjhFh8fT1BQEBUqVODChQs8+uij/P7770aHJSJ/oaRBgD+nM3z//fe0bt2axo0bM3XqVDIyMpg7dy7PP/88TzzxBE2bNmXv3r2kpaUxdepUgoODCQ4OZtSoUcTExFjPd/78eQYOHEhgYCBt27Zl8eLFgP20o8WLF9OuXTvq169P7969+fXXX2/Z78qVKwwfPpymTZsSHBzM1KlTSUtLA2DVqlX07duXOXPmEBwcTOPGjZkxYwYWiyUffnIid+7mOHvvvfdo0qQJU6ZM4aeffqJLly4EBATw8MMPs3fvXmv/jIwMZs+eTatWrQgKCuKFF14gOjoagIiICF544QWaNGlCvXr1ePDBBwkJCTHq0kRy5b777uPixYuMGzeO++67j7179xIcHMzSpUvv6PVhYWH06dOHgIAAWrduzbx586zHkpKSmDBhgvX31KuvvkpqaioAsbGxvPrqq7Ro0YKgoCBGjx5NbGwscOP3z3333cfEiRMJCgpi4cKFAHz99dfcd999BAYG0rdvX44fP/4v/zRECjYlDWJj3rx5vP3228ybN48NGzYwd+5c4Mac027duvHZZ5/RoEEDZs+ezdGjR/nwww9ZvHgxCQkJDB8+HIDU1FQGDBiAu7s7y5YtY8KECbz99tts2bLF5r2OHTvGrFmzmDhxIuvWraNx48a8+OKLZGVl2fRLS0vjySefJDk5mc8//5x33nmHrVu3MmvWLGufAwcOcPbsWZYsWcKrr77K4sWL2bVrVx7/tERyZ//+/axcuZJHH32Ul19+meeee47vvvuOHj168Mwzz3D+/HkA3n33XVavXs306dNZunQp169fZ+LEiQCMGjWKzMxMvv76a7755ht8fX2ZNGmSgVclknMrVqygbNmyjBs3jhUrVvD4448zbtw43Nzc7uj1Y8aMoU6dOqxZs4Zp06bx0UcfsW3bNgD++9//EhISwvvvv8+iRYsICQnhnXfeAWDo0KGEhoYyf/58PvnkE06fPs0rr7xiPe/FixdJS0tj1apVdOvWjc2bNzNv3jxeffVVVq9eTVBQEP369bMmGiJFgkXEYrGEh4dbatWqZfnpp5+sbStWrLA0a9bM8u6771patGhhbU9KSrL4+/tbwsLCrG2xsbEWPz8/S1hYmGXjxo2Whg0bWuLj423OtXXrVssvv/xiqVWrlsVisVg2bNhgqVevnuX48eMWi8ViSUxMtOzatcuSnp5u02/jxo2WgIAAS0xMjPV827Zts9StW9eSkJBgWblypcXPz8/m/Xr16mX54IMP/uWfksj/5uY427Ztm8VisVhGjRplmTFjhk2foUOHWmbMmGHJysqyNG3a1LJy5UrrsZMnT1rmzJljycrKsnz66aeWy5cvW49t377d4ufnZ/M+4eHhFovFYqlVq5bll19+yevLE8mVdu3a2fw9v+lO/t42atTI8s4771gyMzMtFovFsn//fsvVq1ctMTExljp16ti8ft++fZbFixdbQkNDLbVq1bKcOXPGeuzUqVOWWrVqWU6fPm39/XPq1Cnr8ccee8yyePFim/d+8MEH7dpE7mZORictUrA0atTI+ud69eoRFRVFdHQ0FSpUsLaHh4eTnp5Onz59bF6blZXFuXPnCA8Pp2rVqnh4eFiPPfTQQwA2O2G0atWKWrVq0b17d+rWrUv79u155JFHcHKy/Wt5+vRpqlSpQvHixW3izMjIsM579fHxsXk/Dw8PMjIy/pcfhUieuTmeTp8+zbp162ymYqSnp9OqVSuio6OJiYnB39/feqxGjRoMGzYMgMcee4y1a9eyf/9+zp49y9GjR+2qdCJ3k6efftpmCt6BAwcYNGgQs2fPZunSpbRt25aePXtSunRpDh8+TGZmps34ady4MY0bN2bt2rV4eXlRtWpV67Hq1atTvHhxzpw5g6enJwAVK1a0Hj99+jRvvPEGs2fPtralpqZy7ty5PLxikYJFSYPYcHZ2tv755gcQBwcHXFxcrO2ZmZkAfPXVVxQrVszm9T4+PqxYseKO3svNzY3ly5ezd+9etmzZwqpVq1iyZAmrVq2y6Zf9vf8aw83/N5vNdn0sWtMgBdTNv9OZmZk888wz9OrVy+a4q6urXfKcXVZWFgMGDCAuLo4uXf6/vbuPaepq4Dj+RTphgeBUMklYRytKhZCoEUUicY6yLW3wNYoxiy/VDMhcDOqESXAxw7pNpgad4lsManw3Ytw6XAYVTRxsbpOAmRrfEHFBI4lu+IK6uD+MfdZUOp49Vp/g7/NXc+7puffc5Pbmd8+5p3bS0tK4f/8+H3zwQSAPW+S5cjqd3L1716ssKysLm81GZWUlbreb6dOnU1RURGJiYoftPOl+AY+ux8f3FMDnvldQUEBKSorXd/7+sEqkq9M7DeLl1KlTns8nT57k1Vdf5ZVXXvGqYzQaCQ4O5saNG8TExBATE0N4eDiffvopra2tmEwmLl26xJ07dzzf+fzzz1myZIlXOydOnGD9+vUMHz6chQsXcujQIdrb231e5jSbzTQ2Nnq9aF1XV4fBYOD1119/ep0XecbMZjPNzc2e6ygmJobdu3dz9OhRIiIi6NmzJ6dPn/bUP3XqFCNHjuTs2bMcP36csrIycnJyGDVqFNeuXQMUlqXr6tOnj9e10t7ezpIlS+jevTsOh4Nt27aRmZnJt99+67lP/f36qaysZPz48ZjNZn7//XcuXLjg2Xbu3Dna2tq8Rh/+zmw209LS4rX/devWUVdXF+hui/zfUGgQL06nk4aGBr7//ntKSkp49913feqEh4czadIkFi9ezA8//MC5c+fIy8vj0qVLvPbaa6SmphIZGcnHH3/M+fPnqaqqYteuXaSmpnq1Exoaypo1a9i7dy/Nzc24XC5u377t86duI0aMwGg0kpeXx5kzZ6itraWoqIiMjAwiIiICej5EAmnGjBl88803bN26laamJsrKyigrK8NkMgEwdepUSkpKqK2t5ezZszidTgYNGkSPHj3o1q0bLpeLK1eucOjQIc+iBY9XFRPp6kJCQvjll18oKiriwoULNDQ08NNPP5GQkEB4eDjjxo3D6XRSX19PQ0MDK1euZPjw4cTGxjJy5Ejy8/Opr6+nvr6e/Px8hg4dSlxc3BP35XA42LJlCwcOHKCpqYni4mIqKiqIjY19xr0WeX4UGsSL3W4nOzubefPmMWnSJLKysp5Y76OPPiIlJYU5c+aQmZmJwWBgw4YNBAcHYzAYWLt2LdeuXWP8+PE4nU7y8vIYNWqUVxvx8fGe1S5sNhvr1q2juLjY50c4ODiYtWvXApCZmcm8efOwWq188sknATkHIs/KoEGDWLZsGTt27MBut7Nnzx6WL1/O0KFDgUdTL95++21yc3OZMmUKUVFRFBUVERUVxeLFi9m4cSMZGRls2LCBwsJCDAYDv/7663Pulcizs3LlSu7cucPEiROZNWsWSUlJvP/++wAUFBQwYMAAHA4H7733HsnJycydOxd4NPptNBqZMWMGs2bNon///qxZs6bD/djtdubOncuqVavIyMigpqaG0tJST8AXeREEPdRYtvBo/Xir1UpVVZXXy18iIiIiIhppEBERERERvxQaRERERETEL01PEhERERERvzTSICIiIiIifik0iIiIiIiIXwoNIiIiIiLil0KDiIiIiIj4pdAgIiIiIiJ+KTSIiDxlFosFi8XCb7/95rNt586dWCwWVq9e3am2Wltbqaio6HD7/v37SUtL+9fHKiIi0hkKDSIiAfDSSy/hdrt9yisrKwkKCup0O1988QVHjhzpcLvdbmffvn3/6hhFREQ6S6FBRCQAkpKSfEJDW1sbJ06cICEhodPt/NNf6YSGhtKrV69/dYwiIiKdpdAgIhIAVquVH3/8kba2Nk9ZdXU1SUlJhIWFedXdtWsXaWlpDB48mKlTp3LmzBkAVq9eTXl5OeXl5Z4pSBaLhZKSEpKTk8nJyfGZnlRfX8+UKVMYOHAg77zzDi6XC4D79+9TWFhIcnIygwcPJicnh6tXrwb6NIiISBeh0CAiEgBxcXH06dOHo0ePesq+++470tPTveq53W6+/PJLFi1aRHl5OUOGDGHatGncvHmTmTNnYrPZsNlsXlOQDh8+zM6dO/nwww+92mptbWXmzJnEx8dTXl5OdnY2+fn5nD59mu3bt3P8+HE2b97Mvn37uHXrFkuXLg3sSRARkS5DoUFEJECsVqtnitK9e/c4duwYVqvVq86mTZvIzs7mzTffxGQykZubS3R0NAcPHiQsLIzQ0FCfKUiTJ0+mb9++9OvXz6stl8tFjx49KCwspG/fvkyYMIH58+dz9+5dmpubCQkJITo6mtjYWD777DOysrICfxJERKRLMDzvAxAR6aqsVitz5szhwYMH1NTUEBcXR+/evb3qnD9/nuLiYlasWOEpa29vp7GxscN2o6Ojn1h+8eJFEhIS6NbtP8+DHA4HAGFhYbhcLlJTUxk2bBjp6elMmDDhf+idiIi8SBQaREQCZMiQIQD8/PPPVFZW8tZbb/nU+fPPPykoKCAlJcWrPDw8vMN2Q0JCnlhuMHT8k96/f3/cbjfV1dVUV1ezYsUKvv76a7Zv3/5freYkIiIvJoUGEZEAMRgMvPHGG7jdbg4fPvzE6UBms5mWlhZiYmI8ZQsXLiQ9PR2r1UpQUNA/rqD0mMlk4siRIzx8+NATBHJzc0lMTCQyMpLu3btjt9ux2WzU1dUxefJkWltbiYyMfDodFhGRLkvvNIiIBJDVamXv3r307t0bo9Hos93hcLBlyxYOHDhAU1MTxcXFVFRUEBsbC8DLL7/MlStXOrXS0ejRo7lx4wbLli2jsbGR/fv3U1VVxYgRI/jjjz9wOp3U1NRw+fJlvvrqK6KioujZs+dT77OIiHQ9GmkQEQmg1NRUHjx44LNq0mN2u53r16+zatUqrl+/Tr9+/SgtLcVkMgEwduxYZs+ezZgxY6itrfW7r4iICNavX8/SpUvZtm0bRqOR5cuXEx8fj8VioaWlhQULFnDz5k0SExMpLS0lODj4aXdZRES6oKCHnR33FhERERGRF5KmJ4mIiIiIiF8KDSIiIiIi4pdCg4iIiIiI+KXQICIiIiIifik0iIiIiIiIXwoNIiIiIiLil0KDiIiIiIj4pdAgIiIiIiJ+KTSIiIiIiIhfCg0iIiIiIuKXQoOIiIiIiPj1F5/jh9OfZ11eAAAAAElFTkSuQmCC"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot classification report\n",
+    "plot_classification_report(cr_v1)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:07:10.698060100Z",
+     "start_time": "2024-06-08T16:07:10.328701100Z"
+    }
+   },
+   "id": "9a5ab9310c986f72"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "c3b0d585910aef3e"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Neural network V2"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "19a30f696980b3ee"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/1000, Loss: 0.6100791096687317\n",
+      "Epoch 20/1000, Loss: 0.40138334035873413\n",
+      "Epoch 30/1000, Loss: 0.2066049426794052\n",
+      "Epoch 40/1000, Loss: 0.1198694109916687\n",
+      "Epoch 50/1000, Loss: 0.10492949932813644\n",
+      "Epoch 60/1000, Loss: 0.08525355905294418\n",
+      "Epoch 70/1000, Loss: 0.07265784591436386\n",
+      "Epoch 80/1000, Loss: 0.07437089085578918\n",
+      "Epoch 90/1000, Loss: 0.04634793847799301\n",
+      "Epoch 100/1000, Loss: 0.04539191350340843\n",
+      "Epoch 110/1000, Loss: 0.03791217878460884\n",
+      "Epoch 120/1000, Loss: 0.056155040860176086\n",
+      "Epoch 130/1000, Loss: 0.02974613755941391\n",
+      "Epoch 140/1000, Loss: 0.028519876301288605\n",
+      "Epoch 150/1000, Loss: 0.02841273508965969\n",
+      "Epoch 160/1000, Loss: 0.02827402390539646\n",
+      "Epoch 170/1000, Loss: 0.03137960284948349\n",
+      "Epoch 180/1000, Loss: 0.021595297381281853\n",
+      "Epoch 190/1000, Loss: 0.03367958217859268\n",
+      "Epoch 200/1000, Loss: 0.03138892352581024\n",
+      "Epoch 210/1000, Loss: 0.024735331535339355\n",
+      "Epoch 220/1000, Loss: 0.013547890819609165\n",
+      "Epoch 230/1000, Loss: 0.016778510063886642\n",
+      "Epoch 240/1000, Loss: 0.013662113808095455\n",
+      "Epoch 250/1000, Loss: 0.014643474481999874\n",
+      "Epoch 260/1000, Loss: 0.04232195019721985\n",
+      "Epoch 270/1000, Loss: 0.011198709718883038\n",
+      "Epoch 280/1000, Loss: 0.014255641028285027\n",
+      "Epoch 290/1000, Loss: 0.017376599833369255\n",
+      "Epoch 300/1000, Loss: 0.006715432740747929\n",
+      "Epoch 310/1000, Loss: 0.015104355290532112\n",
+      "Epoch 320/1000, Loss: 0.005779958330094814\n",
+      "Epoch 330/1000, Loss: 0.006878014653921127\n",
+      "Epoch 340/1000, Loss: 0.010289205238223076\n",
+      "Epoch 350/1000, Loss: 0.008154270239174366\n",
+      "Epoch 360/1000, Loss: 0.0052977693267166615\n",
+      "Epoch 370/1000, Loss: 0.0059393011033535\n",
+      "Epoch 380/1000, Loss: 0.003750022267922759\n",
+      "Epoch 390/1000, Loss: 0.006243106909096241\n",
+      "Epoch 400/1000, Loss: 0.0048174685798585415\n",
+      "Epoch 410/1000, Loss: 0.008404634892940521\n",
+      "Epoch 420/1000, Loss: 0.005285304039716721\n",
+      "Epoch 430/1000, Loss: 0.003210554365068674\n",
+      "Epoch 440/1000, Loss: 0.0030219131149351597\n",
+      "Epoch 450/1000, Loss: 0.003663143841549754\n",
+      "Epoch 460/1000, Loss: 0.004113232716917992\n",
+      "Epoch 470/1000, Loss: 0.011188282631337643\n",
+      "Epoch 480/1000, Loss: 0.008383953012526035\n",
+      "Epoch 490/1000, Loss: 0.005484223831444979\n",
+      "Epoch 500/1000, Loss: 0.001833457383327186\n",
+      "Epoch 510/1000, Loss: 0.0026361148338764906\n",
+      "Epoch 520/1000, Loss: 0.0018964618211612105\n",
+      "Epoch 530/1000, Loss: 0.005411419551819563\n",
+      "Epoch 540/1000, Loss: 0.005162812303751707\n",
+      "Epoch 550/1000, Loss: 0.004074939526617527\n",
+      "Epoch 560/1000, Loss: 0.001993684796616435\n",
+      "Epoch 570/1000, Loss: 0.002496592467650771\n",
+      "Epoch 580/1000, Loss: 0.012827489525079727\n",
+      "Epoch 590/1000, Loss: 0.0010587115539237857\n",
+      "Epoch 600/1000, Loss: 0.0020602247677743435\n",
+      "Epoch 610/1000, Loss: 0.0010980992810800672\n",
+      "Epoch 620/1000, Loss: 0.0023741163313388824\n",
+      "Epoch 630/1000, Loss: 0.00123070168774575\n",
+      "Epoch 640/1000, Loss: 0.011475415900349617\n",
+      "Epoch 650/1000, Loss: 0.00989847257733345\n",
+      "Epoch 660/1000, Loss: 0.0012280159862712026\n",
+      "Epoch 670/1000, Loss: 0.0017485406715422869\n",
+      "Epoch 680/1000, Loss: 0.0012420162092894316\n",
+      "Epoch 690/1000, Loss: 0.0004315624828450382\n",
+      "Epoch 700/1000, Loss: 0.0007627215818502009\n",
+      "Epoch 710/1000, Loss: 0.00213691801764071\n",
+      "Epoch 720/1000, Loss: 0.0021272513549774885\n",
+      "Epoch 730/1000, Loss: 0.0009174205479212105\n",
+      "Epoch 740/1000, Loss: 0.0015678246272727847\n",
+      "Epoch 750/1000, Loss: 0.0018770662136375904\n",
+      "Epoch 760/1000, Loss: 0.00043499123421497643\n",
+      "Epoch 770/1000, Loss: 0.001615240820683539\n",
+      "Epoch 780/1000, Loss: 0.0023441719822585583\n",
+      "Epoch 790/1000, Loss: 0.0004717250994872302\n",
+      "Epoch 800/1000, Loss: 0.0006681744707748294\n",
+      "Epoch 810/1000, Loss: 0.0018840441480278969\n",
+      "Epoch 820/1000, Loss: 0.0016851990949362516\n",
+      "Epoch 830/1000, Loss: 0.006307181902229786\n",
+      "Epoch 840/1000, Loss: 0.00034771396894939244\n",
+      "Epoch 850/1000, Loss: 0.0006758614326827228\n",
+      "Epoch 860/1000, Loss: 0.0003922640171367675\n",
+      "Epoch 870/1000, Loss: 0.0011983055155724287\n",
+      "Epoch 880/1000, Loss: 0.0005702194175682962\n",
+      "Epoch 890/1000, Loss: 0.0027277739718556404\n",
+      "Epoch 900/1000, Loss: 0.000657720142044127\n",
+      "Epoch 910/1000, Loss: 0.0007201721309684217\n",
+      "Epoch 920/1000, Loss: 0.002012366196140647\n",
+      "Epoch 930/1000, Loss: 0.0005625162739306688\n",
+      "Epoch 940/1000, Loss: 0.0008252564002759755\n",
+      "Epoch 950/1000, Loss: 0.0021678118500858545\n",
+      "Epoch 960/1000, Loss: 0.002342545660212636\n",
+      "Epoch 970/1000, Loss: 0.0015022775623947382\n",
+      "Epoch 980/1000, Loss: 0.0007447443204000592\n",
+      "Epoch 990/1000, Loss: 0.00044577810331247747\n",
+      "Epoch 1000/1000, Loss: 0.0006745096179656684\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Neural network V2\n",
+    "model_v2 = NeuralNetworkV2(input_size, hidden_size).to(device)\n",
+    "criterion_v2 = nn.BCELoss()\n",
+    "optimizer_v2 = optim.Adam(model_v2.parameters(), lr=learning_rate, weight_decay=weight_decay)\n",
+    "\n",
+    "# Train the model\n",
+    "train(model_v2, X_train, y_train, criterion_v2, optimizer_v2, epochs)\n",
+    "\n",
+    "# Evaluate the model\n",
+    "cm_v2, cr_v2, acc_v2 = evaluate(model_v2, X_test, y_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:07:41.007361Z",
+     "start_time": "2024-06-08T16:07:37.052988100Z"
+    }
+   },
+   "id": "cb37345ed4ad8443"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot confusion matrix\n",
+    "plot_confusion_matrix(cm_v2, ['Benign', 'Malignant'], title='Confusion matrix - Neural Network V2')"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:07:41.268092300Z",
+     "start_time": "2024-06-08T16:07:41.007361Z"
+    }
+   },
+   "id": "d288d528576840f0"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxUAAAIhCAYAAAA4gZcFAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAACTbElEQVR4nOzdd3gUVdvH8e+mbBJSSCWEgPQSQouU0BUBpTf1kUcfKeJLERAFEQEVULrYADWIYEWkiQrSkSJFQCAUAYFQDC0EUkhIL+8fyJoliGwwmRB+H6+5LvfM2Zl7AkP23vucM6bs7OxsRERERERE8sjO6ABEREREROTupqRCRERERETuiJIKERERERG5I0oqRERERETkjiipEBERERGRO6KkQkRERERE7oiSChERERERuSNKKkRERERE5I4oqRARuQvoOaV/Tz8bERHjKakQkULlwIEDDB8+nAcffJBatWrRqlUrXnvtNSIjI636Va1alRkzZhRobDNmzKBq1aqW14mJifTv35/atWtTv359Tp06RdWqVfn222//1fOuX7+eESNGWF7v2LGDqlWrsmPHjn/1PHebK1eu8PLLL/Prr78aHYqIyD3PwegARESumzdvHhMnTiQ0NJRhw4ZRokQJTp8+zZw5c1izZg2ff/451apVMyy+xx9/nGbNmllef/fdd2zYsIHXX3+dypUrU6pUKRYsWMB99933r573s88+s3odHBzMggULqFSp0r96nrvN4cOH+f7773n00UeNDkVE5J6npEJECoXdu3czYcIEnnrqKUaPHm1pDw0NpVWrVnTp0oVRo0b961UAW5QsWZKSJUtaXsfFxQHw5JNPYjKZAKhTp06+x+Hm5lYg5xEREbldGv4kIoXCnDlzcHd3Z+jQobn2eXt788orr9CyZUuSkpJu+v4jR44waNAgGjZsSHBwMM2aNWP8+PGkpKRY+mzdupX//Oc/hISEUL9+fQYMGEBERIRl/x9//EH//v0JDQ2ldu3aPPHEE2zatMmyP+fwp6efftoy/KpatWq88sornDlzJtfwpxMnTjBo0CAaNGhA/fr16devn9U5z5w5w8svv0zTpk0JDg6mUaNGvPzyy8TGxlrOs3PnTnbu3GkZ8nSz4U8HDhygT58+hIaGcv/999O/f3+OHTtm2X/9Pdu3b+eZZ56hdu3aNGnShLfeeovMzMy//XP59ttvqV69OosWLaJJkyY0aNCA48ePA7Bu3Tq6detGzZo1adKkCePHj7f685kxYwYPPfQQGzZsoE2bNtSuXZv//Oc/uYZtXbx4kZEjR/LAAw9Qq1YtHnvsMdavX2/Vp2rVqsycOZNu3bpRq1YtZs6cSY8ePQDo0aMHTz/99N9eg4iI5D8lFSJiuOzsbLZs2UKjRo1wcXG5aZ927doxcOBAihUrlmvfxYsXeeqpp0hOTmby5MnMnj2b9u3b8+WXX/LFF18AEBkZyXPPPUeNGjX46KOPmDBhAidPnqRv375kZWWRlZVFv379SE5OZurUqXz44Yd4enoyYMAATp8+neucY8aM4bHHHgNgwYIFPPfcc7n6REVF8cQTT3Dq1CnGjh3LW2+9xaVLl+jZsydxcXEkJyfTo0cPIiIiGDNmDHPmzKFHjx78+OOPvPvuu5bzVK9enerVq7NgwQKCg4NzneeXX37hv//9LwATJ05k/PjxnD9/nu7du1slMAAvvfQSdevWJSwsjA4dOvDJJ5+waNGiW/3xkJmZydy5c5kwYQIjR46kYsWKLFu2jIEDB1KhQgU++OADBg0axA8//MBzzz1nNXE6JiaGESNG8OSTT/L+++/j7OxMnz59OHz4MACXLl3iscce49dff+XFF19kxowZBAYGMnDgQH744QerOMLCwujYsSPTp0+nVatWvP766wC8/vrrjBkz5pbXICIi+UvDn0TEcLGxsaSmplK6dOk8vf/o0aMEBQXx/vvv4+bmBkDjxo3ZunUrO3bsoG/fvuzfv5+UlBT69euHv78/cG040/r160lKSiI5OZkTJ07w3HPP8cADDwBYvhFPS0vLdc5KlSpZhkJdH4p05swZqz6fffYZaWlpfPrpp/j5+QHXqhr//e9/2bdvHyVKlKBkyZJMmTKFMmXKANCwYUP27dvHzp07Lee5fk1/N+Tp7bffpmzZsnz88cfY29sD0LRpU1q3bs306dN5//33LX0ff/xxBg4cCECjRo1Yt24dGzdupHv37rf8Gffv358HH3wQuJYETps2jWbNmjFt2jRLn3LlytGrVy82bdpk6ZucnMzYsWPp0qWL5fpatWrFxx9/zLvvvsunn35KTEwMq1evJjAwEIAHHniAXr16MXXqVDp06ICd3bXvv+rVq0fv3r0t54uPj7f8jO71+SUiIkZTUiEihrv+QfhWw3BupWnTpjRt2pT09HSOHz/O6dOnOXr0KDExMXh6egJQu3ZtnJyceOyxx2jTpg3NmzcnNDSUWrVqAeDq6kqlSpV47bXX2LJlC02bNqV58+aMHDkyz9e1e/du6tSpY0ko4Fois2HDBsvrr7/+mqysLE6dOsXp06c5fvw4J06cICMj47bOkZSUxIEDBxg0aJDl5wjg4eFBixYtrIZvAYSEhFi9Llmy5N8OKcspKCjI8v8nTpzgwoUL9OvXzyrO+vXr4+bmxtatWy1JhYODAx06dLD0cXZ2pnnz5mzevBmAnTt3EhISYkkoruvUqRMjR47kxIkTloQhZwwiIlK4KKkQEcMVL14cV1dXzp0797d9kpKSSE9Pp3jx4rn2ZWVl8c477zBv3jySkpIICAigVq1aODk5WfqULl2ar776io8//pjFixfzxRdf4OHhwZNPPskLL7yAyWRi7ty5fPTRR6xdu5bvvvsOR0dHWrVqxbhx42563n8SFxf3j9WXTz/9lLCwMOLi4vD19aVGjRq4uLiQkJBwW+dISEggOzsbX1/fXPt8fX1zHcfZ2dnqtZ2d3W095yHnsLPrE9THjRvHuHHjcvW9ePGiVQwODta/anx8fCzHiI+Pt1Rpbowdri0be7MYRESkcFFSISKFQtOmTdmxYwepqalWycB1CxcuZMqUKSxevDjXvIKPP/6Yzz77jHHjxvHwww/j7u4OYJnzcF3O4Uy7d+9mwYIFhIWFUa1aNdq2bYu/vz9jx45lzJgxHDlyhFWrVjF79my8vLzyNGbf3d2dmJiYXO3bt2+ndOnShIeHM3nyZIYPH063bt3w9vYGYMiQIRw4cOC2z2Eymbh06VKufdHR0ZZKzb/Jw8MDgJdffpkGDRrk2p8zAbuePOR06dIlfHx8LH2jo6Nz9bne5uXl9W+ELCIi+UwTtUWkUHjmmWeIi4vjvffey7UvOjqauXPnUqlSpZtOVN69ezeVKlXi0UcftSQUUVFRHD16lKysLODa/IYWLVqQlpaG2WymUaNGvPnmmwCcO3eOvXv30rhxY/bv34/JZCIoKIgXX3yRKlWq3LKCciv16tVj3759VonF5cuXefbZZ9m0aRO7d+/Gw8ODZ5991pJQXL16ld27d1viBixzCm6mWLFi1KhRg5UrV1oNH0tISGDjxo3UrVs3T7HfSoUKFfDx8eHMmTPUrFnTsvn7+/P2229z6NAhS9+UlBR+/vlnq9ebN2+mUaNGwLUhU3v37uXs2bNW5/jhhx/w8/OjbNmyfxtHzuFeIiJiLFUqRKRQqFOnDkOGDOG9994jIiKCLl264OXlxbFjx5gzZw6pqak3TTjgWgXiww8/5OOPP6ZOnTqcPn2aWbNmkZaWRnJyMnBtgvC0adMYOHAg//vf/7C3t+ebb77BbDbTokULAgMDcXZ25uWXX2bw4MH4+vqybds2Dh8+bFm61Fa9evXiu+++49lnn6Vfv344Ojry0UcfUbJkSTp27Mj69euZP38+kydPpkWLFly8eJE5c+Zw6dIlq2/7PTw82Lt3L9u3b6d69eq5zjNs2DD69OlD3759efLJJ0lPT+fjjz8mLS3NMin732Rvb8+LL77I66+/jr29PS1atODKlSt8+OGHREVF5Ur8Ro4cyQsvvICPjw9z5swhKSmJAQMGANC7d29++OEHevXqxaBBg/D09OS7777jl19+YeLEibdMqK4nkBs3bqR48eKGPhhRRORep6RCRAqNAQMGUL16dcuTtePj4wkICODBBx+kf//+BAQE3PR9/fr1IzY2li+++IIPPviAgIAAOnfujMlkYtasWVy5coVq1aoRFhbGBx98wNChQ8nMzKRGjRrMnTuXChUqADB37lzefvttJkyYwJUrVyhXrhxvvPEG3bp1y9P1BAQE8PXXX/PWW2/xyiuvYDabCQ0N5d1336V48eJ07dqVM2fOsGTJEr7++mv8/f154IEHePLJJ3nttdeIiIigYsWKPPXUUxw8eJD/+7//Y9KkSZQoUcLqPI0aNeLTTz9l+vTpDB06FLPZTL169ZgyZQqVK1fOU+z/5PHHH8fV1ZVPPvmEBQsWUKxYMe6//36mTZuWa47E2LFjmThxIjExMdx///3Mnz/fUoHw8/Nj/vz5vP3224wfP5709HSqVavGhx9+SMuWLW8ZQ+XKlenQoQPz5s3j559/Zvny5flyrSIi8s9M2bczQ09ERMRGM2bMYObMmfz+++9GhyIiIvlMcypEREREROSOKKkQEREREZE7ouFPIiIiIiJyR1SpEBERERGRO6KkQkRERERE7oiSChERERERuSNKKkRERERE5I4UyYffPTp3t9EhiNyVVsz41OgQRO5KXqEPGR2CyF3nXFjeHixaEFxCBuXbsZP3zsy3YxtJlQoREREREbkjRbJSISIiIiKSZyZ9724rJRUiIiIiIjmZTEZHcNdRGiYiIiIiIndElQoRERERkZw0/Mlm+omJiIiIiMgdUaVCRERERCQnzamwmSoVIiIiIiKFUGpqKqNGjaJevXo0bdqUuXPn/m3fLVu20KlTJ0JCQujVqxcnTpyw7MvOzmbGjBk0b96c+vXr88ILLxATE2PZv3btWqpWrWq1Pf/88zbFqqRCRERERCQnk13+bTaYOnUqBw8e5PPPP2fMmDHMnDmTVatW5ep37Ngx+vXrR8uWLVmyZAnVq1enZ8+eXL16FYAFCxawePFipk2bxrx587h48SKjR4+2vP/48eO0aNGCLVu2WLbx48fbFKuSChERERGRQiYpKYlFixYxevRogoODad26Nc8++yzz5s3L1Xf+/PmEhIQwZMgQKlSowPDhw3F3d2fZsmUAbNq0iXbt2tGgQQOqVKnCs88+yy+//GJ5f0REBFWqVMHPz8+yeXh42BSvkgoRERERkZxMpvzbbtORI0fIyMggJCTE0la3bl327dtHVlaWVd/IyEhq1aqVI3wTVapUITw8HABPT082btxIVFQUKSkp/PjjjwQFBVn6R0REUK5cubz9rP6kidoiIiIiIjnl45KyaWlppKWlWbWZzWbMZrNVW3R0NF5eXlbtvr6+pKamEhcXh7e3t1V7VFSU1fsvXLhA8eLFARg4cCADBgygefPm2Nvb4+fnx4IFC4Br8y1OnjzJli1bmDVrFpmZmbRp04bnn38+V0y3okqFiIiIiEgBmTVrFnXr1rXaZs2alatfcnJyrg/111/fmJS0bduW1atXs2HDBjIyMli6dCkHDhwgPT0dgLNnz+Ls7ExYWBhffvklJUuWZNSoUQCcO3fOcq733nuPESNGsGzZMqZOnWrTdalSISIiIiKSUz4uKduvXz969+5t1XazioCTk1Ou5OH6a2dnZ6v25s2bM3DgQAYPHkxmZiahoaF07tyZxMREsrOzGTFiBC+//DItWrQA4L333qNFixbs27eP2rVrs2PHDooXL47JZCIoKIisrCyGDx/OyJEjsbe3v63rUqVCRERERKSAmM1m3NzcrLabJRX+/v7ExsaSkZFhaYuOjsbZ2fmmk6gHDBjAnj172LJlC5999hlXr14lMDCQmJgYzp8/T9WqVS19AwIC8PLy4uzZs8C1ORemHIlUxYoVSU1NJT4+/ravS0mFiIiIiEhOhWBJ2aCgIBwcHCyTrQF2795NzZo1sbOzPs7y5cuZMGECZrMZHx8fUlJS2LFjB6GhoRQvXhyz2UxERISlf0xMDHFxcZQuXZqff/6Z0NBQkpOTLfsPHz6Mp6en1byNf6KkQkRERESkkHFxcaFLly6MHTuW/fv3s27dOubOnUuPHj2Aa1WLlJQUAMqVK8c333zDmjVrOHXqFMOGDSMgIIDmzZvj4OBAt27dmDJlCrt27eLo0aMMHz6c2rVrU7NmTUJCQnBycuLVV1/lxIkTbNq0ialTp/Lss8/aFK+SChERERGRnArBkrIAI0eOJDg4mJ49ezJu3DgGDx7Mww8/DEDTpk1ZsWIFADVq1GDs2LFMnjyZbt26AdcmhF+vaIwaNYqHH36YYcOG8fTTT+Ph4cGHH36IyWTCzc2NOXPmEBMTw6OPPsro0aN54oknbE4qTNnZ2dk2veMu8Ojc3UaHIHJXWjHjU6NDELkreYU+ZHQIInedc2HdjA7hb7k0Gf3PnfIoeeuEfDu2kbT6k4iIiIhITvn4nIqiSkmFiIiIiEhO+bikbFGlNExERERERO6IKhUiIiIiIjlp+JPN9BMTEREREZE7okqFiIiIiEhOqlTYTD8xERERERG5I4WmUnH69GkOHjxIenp6rn1dunQp+IBERERE5N5kp9WfbFUokopPPvmEadOmUbx4cVxdXa32mUwmJRUiIiIiIoVYoUgq5s6dy/Dhw+nTp4/RoYiIiIjIvU5zKmxWKJKK1NRUHn74YaPDEBERERHRw+/yoFCkYR07duTrr78mOzvb6FBERERERMRGhaJSkZiYyOLFi1m+fDmlS5fG0dHRav8XX3xhUGQiIiIics/R8CebFYqkoly5cvTv39/oMEREREREJA8KRVIxaNAgo0MQEREREblGcypsViiSiqeffhrTTf7wTCYTjo6O+Pn50bZtW5o3b25AdCIiIiIiciuFYsBY/fr12bNnD35+frRu3ZpWrVpRsmRJdu/eTYkSJXBxcWHo0KEsWbLE6FBFREREpKgz2eXfVkQVikrF9u3bGTlyJE899ZRVe7169fj++++ZN28eDRs25J133uHRRx81KEoREREREbmZQpEuHTp0iCZNmuRqb9CgAQcOHACgRo0anD9/vqBDExEREZF7jcmUf1sRVSiSimrVqvHVV1/lek7F119/TaVKlQA4cOAAJUuWNCI8EREREbmXaPiTzQrF8KfXXnuN//u//2Pjxo1Ur14dgMOHD5OYmEhYWBi7d+9m+PDhvP766wZHKjfjaG/i/xrdR8OynqRlZvP9wQssO3jxpn1rl3KnR4PS+Ls7cSz6KrO3/cG5K6kALHmm7k3fM33zSTYdj8m3+EWM4GR24L2R/6FLyzokp6Tz/pfref/Ln27at2XDakx8sQsVSvux88BJXpi0kGOn/7rHXni6Jf2eaIanRzF++Gk/Q6cs5GpyWkFdikiBcnKwY+J/69AupBQp6VmErT3KrHXHb9r3gaASvPpoDcr5urHnZAyjvgknIirRsn9YhyD+26Qcxcz2bD58kVHfhBOTqHtHJC8KRbpUo0YN1q5dy//93//h5+dHyZIl6du3L+vXr6d27dr4+/uzcOFCHnvsMaNDlZvoUb80FX2LMWbVUT7e/gf/qVOKhuU8c/Ur4+nMqIcrs+t0HC9/f5gTl5IY27YKzg7X/hr2mb/Palu6/wIXE1LZdTquYC9IpABMerEr91e/j7Z9p/PCpAWM6tuWrq3q5OoXVKEkS6cPYPnGAzR+cgrhhyNZ9fHzuLqYAejzaBNG92/HmJnLeKjXO5QqUZzPJvUu4KsRKTivPVqTWmU9+c+7Wxg5P5yh7YNof3+pXP2qBLjzxaDGrNl3njaTfuJAZBwLX2xGMSd7AP7XrDz/bVyWQXN30fXtzfgXd+btp+8v6MuRwkrDn2xWKCoVAG5ubjzxxBM33Ve6dOkCjkZul5ODHS2r+DJhzTFOXk7m5OVkvvO8QNugEvxyKs6q7yPV/Pg9KpFv9l6bG/Plr2epW6Y4zSp6s/b3S8QlZ1j6lnAz0656CSavO05SelZBXpJIvivmbKZXl0Z0HvQR4UfOEH7kDEGfr6P/Ew+wdF24Vd++jzfjl/0nePOjHwEY/f73tG1eg+7t6jNnyVYGdH+A979cz8JVuwH4v9e/JGL1eCqXLWFVzRApClzM9vy3STn+N3MrByLjOBAZx4cB7vR+sCI/7jln1bfnAxX4NeIyby07DMD4bw/SqmZJujW4j69+PknLGv78sPsMvxy7BMCHa47yYZ8GBX5NIkWFYZWKli1bEhsbC8BDDz1Ey5Yt/3aTwquctwsOdiZ+v3jV0nYkKpHKfq7cmItfH/KU0x+xyVQt4ZrruN3vL8WBc1fYfy4hP8IWMVStqoE4Otjzy74TlrZte09Qv0bZXM/sKVfal10HTlm1/XbsHKG1ygNQPtCXXQf/2n/h0hWiYxMt+0WKkuDSxXG0N/FrxGVL286Iy4SU8871BfB9vq7sPRVr1Xbk7BXqVvAGIDYxjZY1SlLS0xlnRzu61C/Dwci4/L4EuVtoToXNDKtUDBo0CFfXax8mBw8ebFQYcoe8XBy5kpJBRtZfk+zjkjNwcrDD3dmBKykZOdrT8XZ1tHq/j6uZxNQMqzZfV0eaVvBm9I9H8jd4EYOU9C3OpbirpGdkWtouxlzBxdmMj6crl2L/GvN98XICpUp4Wr2/dEkvYuKTLO8r5ffX/mLOZrw9XPH1dMvXaxAxQonizsQkppGe+dfvnOgrqbiY7fFyNVvNh7h0JZWSns5W7y/l5ULs1Wt93llxhM+fa8Seye3IyMziYnwKHaduKpgLESmCDEsqunbtetP/l7uLk4MdGVnWw5Ouv3aws/7aaOvJWF5pVZEtJ2LZeyae5hW9qeTnysHz1tWIllV8ibicxLHopPwNXsQgLs6OpKVbJ9OpaddeOzla/7O8eM1uFr/Xj4WrdrNm2yG6t6tP3epl2fTr0T/372H4Mw+zLTyCU2cvM2VYNwAcHe0L4EpECpaL2Z60DOvfOWl/JudODtZ/57//9QyfPdeI73adYcNvUXRrUIba5bzY9ns0AGV8ipGclkmPD7YRn5TGa4/W5J0e9/Pf6VsL5mKkcCvCcx/yS6GYU3HlyhXmzp3LgQMHyMjIyLW07BdffGFQZPJP0jKzcLCzLuVdf33jP/zhZ6+wKPw8wx+qgJ3JxG8XEth0/DLFbvjw06icF6uPROdv4CIGSk3NwHxD8uBkvvY6KcV65Zm12w4zYdZK5k/rg4O9PZt+Pcq8H3dQ3M0FgEkfr6J8oC97Fo8mPSOTOUu2sv/oGRKuphTMxYgUoNT0LMwO1r9zzH8mE8lp1on6xkNRvPPjYWb3DcXB3o5tv0ez+Jc/cHe5VjGf3qseby45wLoDFwDoP3snOye0IaScV65hUyLyzwpFUvHyyy9z4MABOnbsiJubSvZ3k5ikdDycHbAzwfURUF4uDqRmZHE1LTNX/yX7LvD9gSiKme25kpLBsBbluZiYatnv4+pIGS8Xdv0RV0BXIFLwzkXH4evpir29HZmZ15Jvfx8PkpLTiEtIztV/6pzVvPfFeoq7ORMdm8hXU57h9LlryywnpaTxvxFz8XBzJjsbEq6mcHr9JMt+kaLkQlwy3m5m7O1MZP75S6eEhxPJaRnEJ6fn6j995e+ErT2Gu4sjlxNSCfu/Bpy5fBUfdycCvYtx6Ey8pe+52GRiElMp7VNMSYUU6bkP+aVQJBXbtm3jq6++olatWkaHIjY6eTmJjKxsqpRw5UjUtUnY1fzdOB59lewb+jat4EVlP1c+3XGGKykZmO1NBJd0Z+bPpyx9Kvu5Ep2YxqWruX85iBQV+34/Q3pGJqE1y7Et/Npk7cYhFdl96HSuSu1/2tSlfo1yDJ+2hOjYRJydHGlevzJ9X/8KgAlDOnPoxAXmLdsBQN3q91HczdlqErhIUfFbZDzpmdnULe/Nzj8nazeo5Ev4qVhuuHXoUq80IeW9GbNoP5cTUnF2tKNJFT9e+Hw3cVfTSEnPpHKAB8f/fG6Ft6sZLzcn/rikobeCkoo8KBQ/MX9/f+zsCkUoYqO0zGw2Hr9Mv8ZlqehbjAb3FadTzZL8eOjaUpaeLg6Y7a+NSzwXn8rDVf0ILetJgIcTLzxYnstX09l75orlePd5uXAmLvc3tSJFSXJKOl8t38n00d2pW/0+Oj5YixeebskHX28EwN/HHWena0M0jp2+yLOPNaXzQ7WpeJ8fn0/sxZkLcazeegiA89HxjO7blrrV7yMkqAxzJ/Rk9qItxF7RByMpepLTM1n0y2kmP1mH2mW9aFM7gP6tK/PJTxEA+Hk44ex47fNExMVEnm5enrZ1SlG+hCsf9GnAudhkfvrtAplZ2SzYdprXH61JaCUfqpbyYMYz9dlzMoZ9p1WlEMkLU/aNX4sZYO3atcyaNYvnn3+esmXL4uhovUJQqVK5H2pzK4/O3f1vhif/wGxvom/jsjQs50lSWibfH4iyJBVLnqnLzM2n2HD82jdKLSr78HidANydHDhw/gofb/vD6vkUfRvdh6uTPe9uPGnItdzrVsz41OgQ7hkuzo5MH9WdLi3rcCUxmXc/X8fMP5OK5L0z+b/Xv+SrP6sPT3dqyKi+bfAu7srGnUcZMmkBFy5dS8bt7ExMGdqN7u3qk5WdzfwfdzL6/e8tw6qkYHiFPmR0CPcMF0d7Jj1Zh/YhgVxJSeejNUctScW5sG688PmvLNz+BwBPNCrLi+2r4eVqZsvv0Yz8OpyLV67NN3JysGNE5+p0qlcGZ0c7fj58kdEL9umJ2gXoXFg3o0P4Wy6dPsq3Yyf/MCDfjm2kQpFUVKtWzer19XXas7OzMZlMHD582KbjKakQyRslFSJ5o6RCxHZKKoqWQjGnYv369UaHICIiIiJyjeZU2KxQ/MQCAwMJDAwkKSmJQ4cO4eXlRVZWFqVKlSIwMNDo8ERERERE5BYKRaUiPj6eIUOGsHPnTgBWr17NhAkTiIyM5OOPP1ZiISIiIiIFRw+/s1mhqFSMHz8eFxcXfvnlF5ycnACYOHEiJUuWZPz48QZHJyIiIiIit1IoKhU///wzX375JR4eHpY2b29vRo4cSffu3Q2MTERERETuOZpTYbNCkVQApKam5mqLiYnBwaHQhCgiIiIi9wINf7JZoUjDOnTowIQJEzh27Bgmk4mkpCR++eUXXnvtNdq1a2d0eCIiIiIicguFogzw8ssv884779CtWzfS09Pp3Lkz9vb2PP7447z88stGhyciIiIi9xCTKhU2KxRJhdls5pVXXuGFF14gMjKSzMxMypQpg6urq9GhiYiIiIjIPygUw5+uc3Z2xsfHh927d7N06VLOnTtndEgiIiIico8xmUz5thVVhlUqkpOTmTp1KitWrACgc+fOPP3003Tv3p3k5GSys7N56623+OSTT6hfv75RYYqIiIiIyD8wrFIxceJE9uzZw5gxY5g0aRLHjx/nP//5D40bN2bHjh3s2rWLzp07M336dKNCFBEREZF7kSkftyLKsErF+vXrCQsLo1atWgDUqVOHxo0b87///Q9HR0cAnnnmGbp27WpUiCIiIiIichsMSypiYmIoWbKk5bW3tzcuLi54eXlZ2tzc3EhJSTEiPBERERG5RxXluQ/5xdDVn+zt7XO16Q9RRERERIykz6O2MzSp2Lt3L8WLF7e8zs7OZv/+/Vy4cAGA+Ph4o0ITEREREZHbZGhSMWjQoFxtw4YNs3qtTFFERERECpI+f9rOsKTiyJEjRp1aRERERET+RYXiidoiIiIiIoWFKhW2K1RP1BYRERERkbuPKhUiIiIiIjmpUGEzVSpEREREROSOqFIhIiIiIpKD5lTYTpUKERERERG5I6pUiIiIiIjkoEqF7ZRUiIiIiIjkoKTCdhr+JCIiIiIid0RJhYiIiIhIDiaTKd82W6SmpjJq1Cjq1atH06ZNmTt37t/23bJlC506dSIkJIRevXpx4sQJy77s7GxmzJhB8+bNqV+/Pi+88AIxMTF5Os/fUVIhIiIiIlIITZ06lYMHD/L5558zZswYZs6cyapVq3L1O3bsGP369aNly5YsWbKE6tWr07NnT65evQrAggULWLx4MdOmTWPevHlcvHiR0aNH23yeW1FSISIiIiKSkykft9uUlJTEokWLGD16NMHBwbRu3Zpnn32WefPm5eo7f/58QkJCGDJkCBUqVGD48OG4u7uzbNkyADZt2kS7du1o0KABVapU4dlnn+WXX36x+Ty3oqRCRERERKSQOXLkCBkZGYSEhFja6taty759+8jKyrLqGxkZSa1atSyvTSYTVapUITw8HABPT082btxIVFQUKSkp/PjjjwQFBdl8nlvR6k8iIiIiIjnk5+pPaWlppKWlWbWZzWbMZrNVW3R0NF5eXlbtvr6+pKamEhcXh7e3t1V7VFSU1fsvXLhA8eLFARg4cCADBgygefPm2Nvb4+fnx4IFC2w+z62oUiEiIiIiUkBmzZpF3bp1rbZZs2bl6pecnJwr0bj++sakpG3btqxevZoNGzaQkZHB0qVLOXDgAOnp6QCcPXsWZ2dnwsLC+PLLLylZsiSjRo2y+Ty3okqFiIiIiEgO+Vmp6NevH71797Zqu/FDPYCTk1OuD/XXXzs7O1u1N2/enIEDBzJ48GAyMzMJDQ2lc+fOJCYmkp2dzYgRI3j55Zdp0aIFAO+99x4tWrRg3759Np3nVpRUiIiIiIjkkJ9Jxc2GOt2Mv78/sbGxZGRk4OBw7SN7dHQ0zs7OeHh45Oo/YMAA+vTpQ0JCAj4+PgwZMoTAwEBiYmI4f/48VatWtfQNCAjAy8uLs2fPUrJkSZvO83c0/ElEREREpJAJCgrCwcHBMtkaYPfu3dSsWRM7O+uP8MuXL2fChAmYzWZ8fHxISUlhx44dhIaGUrx4ccxmMxEREZb+MTExxMXFUbp0aZvOcytKKkREREREcioES8q6uLjQpUsXxo4dy/79+1m3bh1z586lR48ewLVqQkpKCgDlypXjm2++Yc2aNZw6dYphw4YREBBA8+bNcXBwoFu3bkyZMoVdu3Zx9OhRhg8fTu3atalZs+Y/nud2KakQERERESmERo4cSXBwMD179mTcuHEMHjyYhx9+GICmTZuyYsUKAGrUqMHYsWOZPHky3bp1A65NCL9eaRg1ahQPP/www4YN4+mnn8bDw4MPP/zQMszrVue5Xabs7Ozsf+vCC4tH5+42OgSRu9KKGZ8aHYLIXckr9CGjQxC565wL62Z0CH/L/9lF+XbsqE8ez7djG0mVChERERERuSNFcvWn46fjjA5B5K4Uu2um0SGI3JW+P3DW6BBE5F+Un6s/FVWqVIiIiIiIyB0pkpUKEREREZG8UqXCdkoqRERERERyUFJhOw1/EhERERGRO6JKhYiIiIhITipU2EyVChERERERuSOqVIiIiIiI5KA5FbZTpUJERERERO6IKhUiIiIiIjmoUmE7VSpEREREROSOqFIhIiIiIpKDKhW2U1IhIiIiIpKTcgqbafiTiIiIiIjcEVUqRERERERy0PAn26lSISIiIiIid0SVChERERGRHFSpsJ0qFSIiIiIickcKRVJx7tw5srOzc7VnZmby22+/GRCRiIiIiNyrTCZTvm1FVaFIKlq2bElsbGyu9jNnzvDkk08aEJGIiIiIiNwuw+ZULFq0iLCwMACys7N59NFHsbOzznGuXLlCxYoVjQhPRERERO5RRbmikF8MSyq6dOmCo6MjWVlZjBo1it69e+Pu7m7ZbzKZcHFxoWHDhkaFKCIiIiL3IuUUNjMsqXB0dKRLly4AlC5dmvvvvx8HBy1GJSIiIiJytykUn+IbNGjA9u3bOXDgAOnp6bkmbQ8aNMigyERERETkXqPhT7YrFEnF5MmT+eKLL6hWrRqurq5W+/SHKiIiIiJSuBWKpGLJkiVMnjyZTp06GR2KiIiIiNzj9KW27QrFkrL29vbUqlXL6DBERERERCQPCkVS8dRTTzFjxgySkpKMDkVERERE7nEmU/5tRVWhGP60c+dO9u7dy6pVq/Dx8cHR0dFq//r16w2KTERERERE/kmhSCq6detGt27djA5DRERERERzKvKgUCQVXbt2/dt96enpBRiJiIiIiNzrlFPYrlAkFZcuXWLWrFkcP36czMxMALKzs0lPTyciIoJdu3YZHKGIiIiIiPydQjFRe9SoUfz888/UrFmTPXv2ULt2bby9vdm/fz+DBw82OjwRERERuYeYTKZ824qqQlGp2LVrF3PnziUkJIStW7fy4IMPUrduXT7++GM2b95Mjx49jA5RRERERET+RqGoVGRnZ+Pv7w9ApUqVOHToEABt27blwIEDRoYmIiIiIvcYLSlru0KRVFSvXp3vv/8egKCgILZu3QrAmTNnjAxLRERERERuQ6EY/jRs2DD69++Pi4sLnTt35pNPPqFjx46cO3eOTp06GR2eiIiIiNxD7OyKcEkhnxSKpKJu3bps2LCBlJQUvLy8WLJkCevWrcPT05O2bdsaHZ6IiIiIiNxCoUgqANzc3HBzcwPA39+fp556yuCIREREROReVJTnPuSXQpFUHDp0iPHjx3PgwAEyMjJy7T98+LABUYmIiIjIvagoL/2aXwpFUjFq1Cjc3d15//33LdUKuXuYHewY1b4qLYP8SM3I4ottf/DFtj9u2rdRRW9efLgSZbxc2H/mChN//J3Tl5Ms+/s/WJ5u95fCxWzP9ogYJv34O7FJeqq6FD2pqalMHD+O9WvX4OTkTI/ez9Cz1zM37btt6xbenTaVyMhIatWuzahXX6dc+QqW/U0b1iMhIcHqPdt37qGYq2u+XoOIEdLT0vhx7vsc2rkZB7MTTTr8hyYd/nPTvsf37WL1vFnERp2jdOXqdHjmeXxL3WfZ/9svm1j3zRyuxF7ivirBdO47DE+/kgV1KSJFSqFIKk6cOMGyZcsoW7as0aFIHgx9uBLVS7nzf5/vpVRxZ97sWp1zcSmsO3TRql9FP1dmPFWbuT+f5sf9F+h6fyk+6RVCpxm/kJyWyWP1Aul6fylGLvmN+OR0RneoxpjOQbwwf79BVyaSf96ZNpVDBw8ye+7nnDt3jtdGjaBUQClaP9LGqt/x48cY/Fw/nnm2L+07dGTpksU8+0xPfli+imKurkRFRZGQkMCPq9bh7OxseZ9LsWIFfUkiBWLNvDDOnvidXq+9TVx0FEs/moKnrz/BDR+w6ncx8iRfTR1Fs85PUrtpS3ZvWMmnbw7j+Xe/wMnZhT9+P8iiGeNp3/t5ylevzaqvwlg4fTx935xp0JVJYaJChe0KxZKyQUFBREREGB2G5IGLox1d7y/F1JVHOXI+gZ+ORPPZ1tN0b1A6V9//1A9kX2Q8H244wenLSby39jgJKZm0r3XtW6GmlX1YfTCK3afjOH7xKp9tOU1oea+CviSRfJeUlMTSJYt4eeRogqoH07JVa3o98yzfzJ+Xq+/Cb+ZTu04IAwcPoVz5CrwwbDjubu78+OMyAE6eiMDPz4/SZcrg6+dn2VS6l6IoLSWZ3T+toF3PQZQqX4XqDZrRpOMT7Fj9Xa6+O9f+QJkqwbT8T298S93Hw0/2xbmYG/u3rANg6/KF1G7aivqtOuJb6j7a9xpMYuxlrl6JL+CrEikaCkVS0blzZ1599VWmTZvGokWL+O6776w2KbyqlHTHwc5EeORf/wjv/SOOmqU9cmX5gV4uHDhzxart+MVEapX2ACA+KZ1mVXwp4e6Ek4MdbWr6c+RCYr5fg0hBO/r7ETIyMqhTJ8TSFnJ/XQ7s30dWVpZV37NnIqlZs5bltclkolKVKuwPDwcgIuI4ZcuVL5C4RYx24XQEWZkZlKkabGkrW7UmZ44fznXvxF48T+lKQZbXJpMJ/zLliTx67QG7pw7tI6hBM8t+rxIBDJ05H1eP4vl8FXI3MJlM+bYVVYVi+NMnn3yCs7MzK1asyLXPZDLRpUuXgg9Kbouvm5m4pHQyMrMtbZcT03B2tMfTxdFqPkTM1TRKeDhZvd/fw4krydcm58/adJLpT9Zm7UtNycjM4lJiGk9/8mvBXIhIAboUHY2npxeOZrOlzcfHl9TUVOLi4vD29ra0e/v4cvFilNX7oy5cwKP4tQ8+J09EkJycTJ9eT3Pq5EmqBQUx/JVRlFOiIUVQQlwMxdyL4+DgaGlz8/QiIz2N5MQruHp4/tVe3IuEmEtW74+/fBEXNw+SryaSfDWBrMxMPp/4MlGnIyhdKYgOfYbg4e1XUJcjUqQUikrFTz/99Lfb+vXrjQ5PbsHF0Z60TOtvh66/dnSw/uu16mAUD1cvQfMqPtjbmehYuyTBgR442l/L2kt5OpOSnsngeeH0+XQPUVdSeaNzECJFTXJKMuYcCQVgeZ2elmbV3qZNW9asXs2mjRvIyMjgh++W8tvBA6SnX0vYT544wZX4eP6v3wDem/EhTk7O9O3Ti6tXVeWToic9NQV7R0erNvs/E4yMdOtFPWo0asFvv2zi993byczMZO+m1Zw98TuZGemkpSQDsOKzmdRu2oqnXp5ARkY6X00dnaviIfcmVSpsVygqFbca4mQ2m/Hz86N27dq5fgmL8VIzsjDbWycP11+npGdatW87HkPYppO8/UQt7O1M7DoZy/J9F3BzuvbXcHzXYN5dc4zNRy8DMHzhAVa92ISagR4cOGs9bErkbubk5ETaDcnD9dc5J1sDNGnWnP7PDWTYC4PJzMykfoNQOnTqTGLCtaTho4/nkJGeblnpadLUaTzS8gE2bdhAuw4dC+BqRAqOg9lM5g3JQ2bGtdeOTtaV8Mp1GvDgYz345t2xZGVmUj64DnWaPUxK0lXs7O0BqPtQO+o0fxiAxwaNYmq/Rzlz7BD3Va1RAFcjUrQUiqTi22+/5ddff8XJyYny5cuTnZ3N6dOnSU5OplSpUly5cgV3d3dmz55NxYoVjQ5XcriYkIpnMUfs7UxkZl0bAuXr5kRyWiYJKbmfOfLJ5lN8vvU07s4OxFxNZ+rjNTgXl4y3qyMBns78HvXXt6tRV1KJS0onwNNZSYUUKSVK+BMXF0tGRgYODtf+Gb50KRpnZ2fcPTxy9f+/fgPo2bsPCQkJ+Pj4MHzoEEoFBgLXvnjJ+YWLk5MTpQJL5xoyJVIUeHj5kpQQT2ZmJvZ/JgYJcTE4mp1wLpZ7SfoHuv6PJh3+Q0rSVdyKe7HgvXF4+vlTzL049vYOVsvLFnMvjot7ceIvRxfY9UjhVYQLCvmmUAx/qlKlCg888ACbNm3i22+/ZenSpWzevJnWrVvzyCOP8Msvv9CiRQsmTpxodKhyg98vJJCRlW2ZbA0QUrY4v527Qna2dd82NfwZ3qYy6ZnZxFxNx8nBjvrlvdh1Mpb45AxS0zOp6PfXuvqexRwpXsyRs7HJBXU5IgWiarUgHBwc2L8v3NK2d89ugmvUxM7O+p/llT8uZ+qkCZjNZnx8fEhJSWHXzh3UbxBKdnY27du04vul31r6JyUl8ccfp62eYyFSVJQsVwk7ewfOHDtkafvjyEFKVaya697Zv3U9Kz6fiYOjGbfiXqSnpXLyt3DKB4dgb29PQIUqXDj918qTV6/Ek3QlXs+pEEDDn/KiUCQV3333HS+99BIeOb6hc3NzY8iQISxcuBB7e3t69OjBnj17DIxSbiYlPYtl4ed5tUM1gku506KaLz0al+XrXyIB8HEz4/Tn3IrTl5N4vF4gLYP8uM/bhcmPBRMVn8KW45fJzMrm+/DzDH24MveX9aRSCVcmdgtm/5l4fjuXcKsQRO46Li4udOzchfFvjOXggf38tH4dX3w2lyf/1wO4NpE7JSUFgLLlyrFo4TesW7uG06dP8crLw/AvGUDTZs0xmUw0a/4gH30wg107d3D8+DFGj3wZf/+SNGv+wC0iELk7mZ2cqfPAIyz75F3ORhzh8K4tbF2+kEZtuwHXqhbpaakA+AaU4dd1yzi0czOXz59h8YzxFPfxo3KdBgA0af84O1Z9y8FfNhJ99jRLw6ZQslxFSleqZtj1idzNCsXwp2LFihEREZFraNOJEycsZf2kpKRcY42lcJi2+hijO1Tjk173k5iawUcbTrD+8LXy8U/Dm/Ha0kP8EH6ew+cTmLD8d4Y9UpniLo7sPBnDoHn7LBWNt1YdY9BDmUx+NBgnR3t+iYhh9Le/GXhlIvnnpZdHMuGNsTzbuydu7m4MGDiYVq2vje1u+WBT3hg/ic5du1E9uAajXx/L229NJj4ujgYNGzHzo1mWb2VfHDYcBwcHRr48jITERBo0aMgHH31sGRoiUtS0eXoAy+e8x6dvDMWpmCstHu9J9QbNAXir/2N07f8yIQ+2oVSFKnTo8wKrvgwjOfEKFWqE8L8Rkyz3TnDDB0i+msCar2Zx9Uoc5arX5smXxhfpb5Ll9umvge1M2dk3DlIpeJ999hkzZ86kV69e1KhRg+zsbH777Tc+//xz+vTpQ5cuXXj++eepUKECkydP/sfj1R6jFaNE8mLHay2NDkHkrvT9gbNGhyBy13kiJNDoEP7W/W/8lG/H3vP6Q/l2bCMVikpFr1698Pb25uuvv2bOnDk4ODhQqVIlxo0bR7t27di1axchISEMGTLE6FBFREREpIhTxcp2hSKpAOjUqROdOnW66b769etTv379Ao5IRERERERuh2FJxcyZM+nTpw8uLi7MnDnzln0HDRpUQFGJiIiIyL1OhQrbGZZU7Nixgx49euDi4sKOHTv+tp/KTyIiIiIihZthScWXX3550/8XERERETGSvtS2nWFJxXfffXfbfbt06ZJvcYiIiIiIyJ0xLKmYPn36bfUzmUxKKkRERESkwBSWQkVqairjxo1jzZo1ODs788wzz/DMM8/ctO+WLVuYOnUqkZGR1K5dm9dff50KFSoAULVq1Zu+Z8qUKXTp0oW1a9fmmsP8yCOP3PbndTAwqfjpp/xb/1dEREREJK8Ky/CnqVOncvDgQT7//HPOnTvHiBEjKFWqFG3atLHqd+zYMfr160ffvn3p2LEjixcvpmfPnqxatQpXV1e2bNli1f+zzz5j5cqVtGx57flUx48fp0WLFrz55puWPk5OTjbFWmiWlI2JieHkyZNkZWUBkJ2dTVpaGocOHaJv374GRyciIiIiUnCSkpJYtGgRs2fPJjg4mODgYI4dO8a8efNyJRXz58+3eqbb8OHD2bhxI8uWLaN79+74+flZ+kZGRvLll18SFhaGu7s7ABEREVSpUsWqn60KRVKxcOFC3njjDTIyMjCZTFx/yLfJZKJWrVpKKkRERESkwBSGQsWRI0fIyMggJCTE0la3bl3CwsLIysrCzs7O0h4ZGUmtWrUsr00mE1WqVCE8PJzu3btbHXf69Ok0atSIxo0bW9oiIiKsXueF3T93yX9hYWH079+f/fv34+Pjw4YNG1i+fDlBQUG0bt3a6PBERERERP4VaWlpJCYmWm1paWm5+kVHR+Pl5YXZbLa0+fr6kpqaSlxcnFVfX19foqKirNouXLhAbGysVdu5c+dYvnw5zz33nKUtOzubkydPsmXLFh555BFatWrFtGnTbhrTrRSKpOLixYt06dIFs9lMcHAw4eHhVKpUiVGjRrFo0SKjwxMRERGRe4jJZMq3bdasWdStW9dqmzVrVq4YkpOTrRIKwPL6xg/8bdu2ZfXq1WzYsIGMjAyWLl3KgQMHSE9Pt+q3ePFiatSoQe3atS1t586ds5zrvffeY8SIESxbtoypU6fa9DMrFMOfvL29iYmJoXTp0lSoUIHDhw/Ttm1b/P39c2VdIiIiIiJ3q379+tG7d2+rthuTB7g2UfrG5OH6a2dnZ6v25s2bM3DgQAYPHkxmZiahoaF07tyZxMREq36rV6/ONRwqMDCQHTt2ULx4cUwmE0FBQWRlZTF8+HBGjhyJvb39bV1XoahUtG3blhEjRrBnzx6aNWvGt99+y+rVq/nggw8oW7as0eGJiIiIyD3EZMq/zWw24+bmZrXdLKnw9/cnNjaWjIwMS1t0dDTOzs54eHjk6j9gwAD27NnDli1b+Oyzz7h69SqBgYGW/efPn+f48eOWFZ9y8vT0tFrxqmLFiqSmphIfH3/bP7NCkVS89NJLtG/fntjYWBo3bsyjjz7KmDFjCA8PZ8yYMUaHJyIiIiJSoIKCgnBwcCA8PNzStnv3bmrWrGk1SRtg+fLlTJgwAbPZjI+PDykpKezYsYPQ0FBLn3379hEQEECpUqWs3vvzzz8TGhpKcnKype3w4cN4enri7e192/EWiuFPjo6OVg/cePHFF3nxxRcNjEhERERE7lWF4TkVLi4udOnShbFjxzJx4kQuXrzI3LlzmTRpEnCtauHu7o6zszPlypVj5MiR1K9fnypVqvDWW28REBBA8+bNLcc7duwYFStWzHWekJAQnJycePXVVxk4cCCRkZFMnTqVZ5991qZ4DUsqZs6cedt9b3zCn4iIiIhIfikEOQUAI0eOZOzYsfTs2RM3NzcGDx7Mww8/DEDTpk2ZNGkS3bp1o0aNGowdO5bJkycTFxdHo0aNmDVrllVF49KlSxQvXjzXOdzc3JgzZw4TJ07k0UcfxdXVle7du9ucVJiyrz8UooBVq1YNOzs7goKCcHV15e/CMJlMfPHFFzYdu/aY9f9GiCL3nB2v5R5nKSL/7PsDZ40OQeSu80RI4D93MkjTaT/n27G3vNQs345tJMMqFWPGjGHdunWEh4dTv359WrZsScuWLW0auyUiIiIi8m8rDMOf7jaGJRX//e9/+e9//0tiYiKbNm1i7dq1vPXWW1SpUoVWrVrRunVrqxnrIiIiIiJSOBk+UdvNzY327dvTvn170tLS2L59O+vXr6d79+74+vrSqlUrBg4caHSYIiIiInKPUKXCdoViSdnrzGYzzZo1o2PHjrRv354//viD2bNnGx2WiIiIiIjcguGVCoCrV6/y888/89NPP7F582YAHnzwQSZNmkTTpk0Njk5ERERE7iUqVNjOsKTiwoULrF+/np9++oldu3bh7+/PQw89xPTp06lbt+5tPxJcRERERESMZVhS0aJFCxwcHKhfvz4jRoygSpUqln179uyx6lu/fv2CDk9ERERE7lGaU2E7w5KK7Oxs0tPT2bZtG9u2bfvbfiaTicOHDxdgZCIiIiJyL1NOYTvDkoojR44YdWoREREREfkXFYqJ2iIiIiIihYWGP9muUC0pKyIiIiIidx9VKkREREREclChwnaqVIiIiIiIyB1RpUJEREREJAc7lSpspkqFiIiIiIjcEVUqRERERERyUKHCdkoqRERERERy0JKyttPwJxERERERuSOqVIiIiIiI5GCnQoXNVKkQEREREZE7okqFiIiIiEgOmlNhO1UqRERERETkjqhSISIiIiKSgwoVtiuSSYWvbzGjQxC5K7X/aLvRIYiIyD3iiZBAo0OQf1GRTCpERERERPLKhEoVtlJSISIiIiKSg5aUtZ0maouIiIiIyB1RpUJEREREJActKWs7VSpEREREROSOqFIhIiIiIpKDChW2U6VCRERERETuiCoVIiIiIiI52KlUYTNVKkRERERE5I6oUiEiIiIikoMKFbZTUiEiIiIikoOWlLWdhj+JiIiIiMgdUaVCRERERCQHFSpsp0qFiIiIiIjcEVUqRERERERy0JKytlOlQkRERERE7ogqFSIiIiIiOahOYTtVKkRERERE5I6oUiEiIiIikoOeU2E7wysVkZGRRocgIiIiImJhZ8q/ragyPKlo06YNjz/+OJ999hlRUVFGhyMiIiIiIjYyPKn4+eef6datGz/99BMtW7bkf//7H19//TUxMTFGhyYiIiIi9yCTyZRvW1FleFLh7e3Nf//7X7744gs2bdpE+/bt2bx5M61ataJPnz4sXbqU5ORko8MUEREREZG/kaekIiMjg/nz53Pu3DkA3n//fdq3b8/w4cOJi4vLczDR0dFER0dz4cIFsrKycHV1ZeHChTz44IOsWbMmz8cVEREREbldJlP+bUVVnlZ/mjx5MqtXryYkJIRDhw4xe/Zsnn/+eTZv3sybb77J22+/fdvHOnz4MKtWrWLVqlWcPXuWxo0b07t3b1q1aoWrqysAH374Ia+99hoPP/xwXsIVEREREZF8lKekYsWKFXz44YdUq1aN2bNn07RpU/r27UuLFi3o3r27Tcfq1q0bdevWpVevXrRp0wYvL69cferWratVokRERESkQBTluQ/5JU9JRXJyMj4+PmRkZLB582ZeeuklALKysnBwsO2QGzZswNfXl/j4eEtCsXfvXoKDgzGbzQCEhoYSGhqal1BFRERERCSf5WlOxf33389bb73F66+/TnJyMq1ateLIkSO88cYbNGzY0KZjxcbG0rJlS+bMmWNpe+mll2jTpg3Hjh3LS3giIiIiInmm51TYLk9Jxfjx40lPT+e3335j0qRJ+Pj4sHLlSnx8fBgzZoxNx3rjjTdo3bo1L774oqVt7dq1PPTQQ7zxxht5CU9EREREJM+0pKzt8jT8KSAggI8++siqLWdSYIvDhw8zdepUHB0dLW12dnb06NGDzp075+mYIiIiIiJScPL8nIrdu3fz/PPP07lzZ86fP8/HH3/Mjz/+aPNxAgIC2L59e672PXv24Ovrm9fwRERERETyxJSPW1GVp0rFmjVrGDlyJP/5z3/YuHEjGRkZODg48MorrxAfH8+TTz5528fq378/o0ePZu/evdSoUQOAI0eO8MMPP9g8lEpERERERApenpKKmTNnMnbsWDp27Mg333wDwDPPPIOfnx/Tp0+3Kano3Lkz3t7eLFy4kPnz5+Pg4EDZsmWZM2cO9erVy0t4IiIiIiJ5ZleE5z7klzwlFadPn6ZOnTq52mvVqkVUVJTNx2vWrBnNmjXLSygiIiIiImKwPCUVlSpV4ueff85VkVi6dCmVKlWy6VjJycksWLCA48ePk5mZaWlPS0vj0KFDrFy5Mi8hioiIiIjkiQoVtstTUjFy5Ej69+/PL7/8Qnp6OmFhYZw+fZqDBw/mWhXqn7z66qts376dRo0asWrVKtq2bcvp06c5cOAAgwYNykt4IiIiIiJSgPK0+lO9evVYuXIlFStW5KGHHiIuLo46deqwYsUKGjVqZNOxNm/ezLRp03j77bepWLEivXr1YtGiRfTq1UsPvxMRERGRAldYnlORmprKqFGjqFevHk2bNmXu3Ll/23fLli106tSJkJAQevXqxYkTJyz7qlatetPtu+++s/k8fydPlQoAPz8/hgwZAkBKSgpHjx7F3d3d5uOkpqZSrlw5ACpXrszBgwepUaMGTzzxBP/73//yGp6IiIiIyF1t6tSpHDx4kM8//5xz584xYsQISpUqRZs2baz6HTt2jH79+tG3b186duzI4sWL6dmzJ6tWrcLV1ZUtW7ZY9f/ss89YuXIlLVu2tOk8t5KnpOL48eOMGjWKV155hUqVKvHEE09w8uRJXFxc+Oijj2jYsOFtH6tixYps27aNxx57jMqVK7N79266d+9OQkICqampeQlPCpijvYkhD1SgWSVvUjOyWLT3HIv2nr9p37plitOvaVlKeThzKCqB6RtPciYuBYD1g29e5Zq89hhrj1zKt/hFjKD7RiRvdO9IQSgMcyqSkpJYtGgRs2fPJjg4mODgYI4dO8a8efNyfdifP38+ISEhli/8hw8fzsaNG1m2bBndu3fHz8/P0jcyMpIvv/ySsLAw3N3dbTrPreQpqRg3bhxlypShXLlyLF68mISEBLZs2cKSJUuYMmUKS5cuve1jDRo0iCFDhpCVlUXnzp1p3749/fv35/fff9eKUHeJfk3KUsXflZeWHqKEuxMjWlck6koqmyNirPqV9XZhYsdqzN99jnW/R9Ouegne7hpMz6/2kpKexWNzfrXq/1idAB6s7MO2E7EFeTkiBUL3jUje6N6RgpCfS8qmpaWRlpZm1WY2mzGbzVZtR44cISMjg5CQEEtb3bp1CQsLIysrCzu7v2YxREZGUqtWLctrk8lElSpVCA8Pp3v37lbHnT59Oo0aNaJx48Y2n+dW8jSnYv/+/bzwwgt4e3uzbt06Wrduja+vLx06dLAav3U7WrZsycqVKwkNDSUgIICvv/6a8uXL89///peJEyfmJTwpQM4OdrQL9ueDzac4Fn2VrSdiWLD7HJ1rlczVt1PNkvx2IZHPdkRyJi6Fj7f9wdW0DFpVufbk9NikdMvm5GBH19oBvP3TCa6mZeY6lsjdTPeNSN7o3pGiYNasWdStW9dqmzVrVq5+0dHReHl5WSUbvr6+pKamEhcXZ9XX19c312MdLly4QGysdZJ87tw5li9fznPPPZen89xKnpIKd3d3Ll26xPnz5wkPD+fBBx8E4PDhw/j4+Nh0rG7dupGUlETZsmUBqFatGiNGjKBv3764uLjkJTwpQBV8i+FgZ+K38wmWtoPnEwgq6Z7rUfQBHk4cuZBg1XbichLVA3LPxekVWoa9kfHsiYzPj7BFDKX7RiRvdO9IQTGZ8m/r168fu3fvttr69euXK4bk5ORc1Yvrr2+sdLRt25bVq1ezYcMGMjIyWLp0KQcOHCA9Pd2q3+LFi6lRowa1a9fO03luJU/Dn7p168aAAQMwm82ULl2apk2bMn/+fKZOnWoZy3W7Ll68iL29fV7CkELAx9VMfHI6GVnZlrbr3/p4ODsQn5Jh1e7jZv2XtoSbEwk5+lxrM/NQFV+eX3wwf4MXMYjuG5G80b0jRcHNhjrdjJOTU64P9ddfOzs7W7U3b96cgQMHMnjwYDIzMwkNDaVz584kJiZa9Vu9enWu4VC2nOdW8pRUDB06lJo1a3L27Fk6dOiAvb09pUqV4p133qFFixY2HatLly48++yzdOrUicDAQJycnHLtl8LLycGO9Mxsq7b0zCwAHO2tC2Ebj13mzQ5V2XD0EjtPx9Gqqh9VS7gSfvaKVb+2wSU4ejGRI1HWN4JIUaH7RiRvdO9IQbF16df84O/vT2xsLBkZGTg4XPvIHh0djbOzMx4eHrn6DxgwgD59+pCQkICPjw9DhgwhMDDQsv/8+fMcP37csuJTXs/zd/K8pGzr1q0tkzcuXrxIUlISVatWtfk4K1aswM7OjuXLl+faZzKZlFQUcmmZWTjaW9941/9hT83Ismrf9UccX+w8w5h2VbE3mQg/G8/aI5dwdbKuVDWv6MOyg9bjAkWKEt03Inmje0fuJUFBQTg4OBAeHk69evUA2L17NzVr1sw1eXr58uXs27eP0aNH4+PjQ0pKCjt27GDy5MmWPvv27SMgIIBSpUrl+Ty3kqekYvfu3bzwwgu89dZbVKhQgW7dupGamkpycjJvvfUWbdu2ve1j/fTTT3kJQQqJS4lpFHdxxM4E16vR3sUcSUnPJDE1I1f/r389y6I953B1sicuOYPX2lTmwpW/lg72czNTzqcY207E5HqvSFGh+0Ykb3TvSEHJ06Tjf5mLiwtdunRh7NixTJw4kYsXLzJ37lwmTZoEXKsmuLu74+zsTLly5Rg5ciT169enSpUqvPXWWwQEBNC8eXPL8Y4dO0bFihVtPs/tytPPbNKkSbRr147atWuzcOFCnJyc2Lp1K2+++SbTp0+36Vi7du265SaFW8SlJDKysqle8q+JbzVKufP7xatk39C3RWUfnmtWjvSsbOKSMzDb21GndHHCz/41MS7I342ohFQuJt7+xCCRu43uG5G80b0j95qRI0cSHBxMz549GTduHIMHD+bhhx8GoGnTpqxYsQKAGjVqMHbsWCZPnky3bt2Aa6tM5aw0XLp0ieLFi9t8ntuVp0rF0aNHmT59Oi4uLvz00088/PDDmM1mGjRowNixY2061tNPP33TdrPZjJ+fH+vXr89LiFJAUjOyWHP4Ii+0qMBb647j62bm8ZBSvLU+AgCvYo5cTc0kLTOLM3EpvNyqEvvPXeHkpST6NilLdEIqO0/FWY5XzqcYp2OSDboakYKh+0Ykb3TvSEEpDHMq4FoVYcqUKUyZMiXXvt9//93q9aOPPsqjjz76t8caN25cns5zu/KUVPj6+nL8+HGSkpI4dOgQr7zyCgDbtm0jICDApmMdOXLE6nVmZiZ//PEHb775Jh07dsxLeFLAPtpymhceLM/bXYO5mpbJ5zsi2fLnQ4gW96nH1LXHWX0kmmPRV3lv4wn6NymLh4sDeyOvMGrZEatvl7yKOd60hC1S1Oi+Eckb3TtSEOwKR05xVzFlZ2ffWDH8R1988QVvvfUWdnZ2VKlShUWLFhEWFsbMmTOZNGnSv5IMHD16lL59+7Jx40ab39tyxvY7Pr+IiIiI5J/1gxsZHcLfeuH7I//cKY/e61wt345tpDxVKnr06EG9evU4d+4cTZs2BaBhw4Y8+OCDVKv27/ygLl++zJUrV/65o4iIiIjIv0iVCtvleUnZ6tWrU716dcvrOnXqkJaWxr59+6ye0vdPRo4cmavt6tWrbNu2jTZt2uQ1PBERERERKSB5Sir27NnDuHHjOH78OFlZ1utC29vbc/DgnT2V0tPTkxEjRtC5c+c7Oo6IiIiIiK0Ky0Ttu0mekorx48cTGBjISy+9xJAhQ5g6dSpRUVHMnDmT1157zaZjTZo0iYyMDOLj4/Hx8QFg7969BAcH39YjzEVERERExFh5ek7FsWPHGDZsGM2aNSM4OBhHR0eeeuopxowZw5w5c2w61uHDh2nZsqXV+1566SXatGnDsWPH8hKeiIiIiEie2Znybyuq8pRUuLi4YG9/7TH3FSpUsKyTW6tWLU6ePGnTsd544w1at27Niy++aGlbu3YtDz30EG+88UZewhMRERERkQKUp6SiYcOGvP3220RFRRESEsKKFSuIi4vjp59+wsPDw6ZjHT58mJ49e+Lo6PhXUHZ29OjR447nZoiIiIiI2Mpkyr+tqMpTUjF69Gji4+NZs2YN7du3x83NjYYNGzJp0iQGDhxo07ECAgLYvj33cyX27NmDr69vXsITEREREckzO5Mp37aiKk8Ttf39/fniiy8sr7/88kuOHz+Oh4cH/v7+Nh2rf//+jB49mr1791KjRg3g2lO2f/jhB8aMGZOX8EREREREpADddlKxa9euf+wTFxfHH3/8Qf369W87gM6dO+Pt7c3ChQuZP38+Dg4OlC1bljlz5lCvXr3bPo6IiIiIyL8hT0N57nG3nVQ8/fTTt9XPZDJx+PBhm4KoXr06Q4cOpXz58gCsWLGCsmXL2nQMERERERExxm0nFUeOHAHg1KlTlCpVyuoZEtu3b6dEiRJUrFjR5gC2b9/OwIED6dWrF88//zwAX3zxBWPGjCEsLIy6devafEwRERERkbwqwlMf8o1N1Z3x48fTrl07wsPDrdq//PJLOnTowOTJk8nOzrYpgClTptC/f39LQgHwzTff8OyzzzJx4kSbjiUiIiIiIgXvtpOKzz//nBUrVvDBBx/QoEEDq30ffvghH3zwAUuXLmX+/Pk2BXDq1CnatGmTq71t27YcP37cpmOJiIiIiNwprf5ku9tOKhYuXMhrr71GixYtbrr/oYce4qWXXrI5qahQoQIrV67M1f7TTz9x33332XQsEREREREpeLc9p+Ls2bPUqlXrln0aNmzIhAkTbArghRde4LnnnmPr1q0EBwcD1+Zv/Prrr8ycOdOmY4mIiIiI3KkiXFDIN7ddqfDx8eHs2bO37HPhwgU8PT1tCqB58+Z89913VK9enRMnThAZGUn16tVZsWIFjRs3tulYIiIiIiJ3ys6Uf1tRddtJRevWrZkxYwbp6ek33Z+RkcHMmTNp2rSpTQFcunSJBQsW8Pvvv5OcnEx8fDz79+9n+PDhSipERERERO4Ct51UPPfcc0RFRdGtWzcWLlzIoUOHiIyM5ODBgyxYsICuXbsSGRnJ4MGDbQpg1KhR/Pzzz9SsWZM9e/ZQp04dfHx82L9/v83HEhERERG5U5qobbvbnlPh4eHBwoULmTZtGpMnTyY5ORmA7Oxs3N3dadeuHYMHD8bX19emAHbt2sXcuXMJCQlh69atPPjgg9StW5ePP/6YzZs306NHD9uuSERERERECtRtJxUAnp6ejB8/ntdff53IyEiuXLmCp6cn9913H/b29nkKIDs7G39/fwAqVarEoUOHqFu3Lm3btmXOnDl5OqaIiIiISF4V4YJCvrHp4XfXmc1mKlasSEhICOXLl89zQgFQvXp1vv/+ewCCgoLYunUrAGfOnMnzMUVEREREpODYVKnID8OGDaN///64uLjQuXNnPvnkEzp27Mi5c+fo1KmT0eGJiIiIyD2mKK/SlF8MTyrq1q3Lhg0bSElJwcvLiyVLlrBu3To8PT1p27at0eGJiIiIiMg/MDypAHBzc8PNzQ0Af39/nnrqKYMjEhEREZF7lQmVKmxVKJIKEREREZHCQsOfbJenidoiIiIiIiLXqVIhIiIiIpKDKhW2U6VCRERERETuiCoVIiIiIiI5mPT0O5upUiEiIiIiIndElQoRERERkRw0p8J2qlSIiIiIiMgdUaVCRERERCQHTamwnZIKEREREZEc7JRV2EzDn0RERERE5I6oUiEiIiIikoMmattOlQoREREREbkjqlSIiIiIiOSgKRW2U6VCRERERETuiCoVIiIiIiI52KFSha2KZFKRkZFldAgid6Va5byNDkHkrnQhPtnoEEREDFUkkwoRERERkbzSnArbKakQEREREclBS8raThO1RURERETkjqhSISIiIiKSg53GP9lMlQoREREREbkjqlSIiIiIiOSgQoXtVKkQEREREZE7okqFiIiIiEgOmlNhO1UqRERERETkjqhSISIiIiKSgwoVtlNSISIiIiKSg4by2E4/MxERERERuSOqVIiIiIiI5GDS+CebqVIhIiIiIiJ3RJUKEREREZEcVKewneGVimrVqhEUFHTTrVatWrRs2ZJp06aRnp5udKgiIiIiIgUmNTWVUaNGUa9ePZo2bcrcuXP/tu+WLVvo1KkTISEh9OrVixMnTljtX7VqFY888gh16tThmWee4ezZs5Z9a9eupWrVqlbb888/b1Oshlcqxo4dy8yZMxk8eDB16tQhOzubgwcPMmPGDB599FGqVKnCBx98QHZ2NsOHDzc6XBEREREp4grLw++mTp3KwYMH+fzzzzl37hwjRoygVKlStGnTxqrfsWPH6NevH3379qVjx44sXryYnj17smrVKlxdXdmzZw/Dhg3jtddeo0GDBkydOpWhQ4eyYMECAI4fP06LFi148803Lcd0cnKyKVbDk4o5c+YwceJEmjdvbmmrVq0aAQEBvPHGGzz//PP4+/szePBgJRUiIiIick9ISkpi0aJFzJ49m+DgYIKDgzl27Bjz5s3LlVTMnz+fkJAQhgwZAsDw4cPZuHEjy5Yto3v37sydO5dOnTrRvXt3AEaPHk3Pnj2JiYnB29ubiIgIqlSpgp+fX57jNXz406VLlyhZsmSudl9fX6KiogDw8/Pj6tWrBR2aiIiIiNyDTPm43a4jR46QkZFBSEiIpa1u3brs27ePrKwsq76RkZHUqlXrr/hNJqpUqUJ4eDgAO3fupHXr1pb9ZcqU4aeffsLb2xuAiIgIypUrZ0N0uRmeVDRp0oQ33njDalzX2bNnmTBhAg0bNiQzM5MlS5ZQpUoVA6MUERERkXuFyZR/W1paGomJiVZbWlparhiio6Px8vLCbDZb2nx9fUlNTSUuLs6qb84v46+7cOECsbGxXLlyhfj4eDIzM+nTpw9NmjRhwIABlv7Z2dmcPHmSLVu28Mgjj9CqVSumTZt205huxfCkYvz48Tg6OtKyZUsaNmxIaGgorVq1wsnJiTfffJNNmzYxf/58RowYYXSoIiIiIiJ3ZNasWdStW9dqmzVrVq5+ycnJVgkFYHl94wf+tm3bsnr1ajZs2EBGRgZLly7lwIEDpKenk5SUBFz7zN2xY0c++ugj0tLS6NevH1lZWZw7d85yrvfee48RI0awbNkypk6datN1GT6nwtPTk08//ZSTJ09y9OhR7O3tqVSpkqUE07hxY7Zv366HkIiIiIhIgcjPz539+vWjd+/eVm03Jg9wbaL0jcnD9dfOzs5W7c2bN2fgwIEMHjyYzMxMQkND6dy5M4mJidjb2wPw+OOP06VLFwCmTZtGkyZNCA8P5/7772fHjh0UL14ck8lEUFAQWVlZDB8+nJEjR1re/08MTyqeeeYZ2rdvT+vWrXnkkUdy7b/xhyYiIiIicrcym803TSJu5O/vT2xsLBkZGTg4XPvIHh0djbOzMx4eHrn6DxgwgD59+pCQkICPjw9DhgwhMDAQLy8vHB0dqVChgqWvl5cXnp6eXLhwAbj2JX9OFStWJDU1lfj4eMu8i39i+PCnGjVqMHv2bJo0aUL//v354YcfNClbRERERAxjl4/b7QoKCsLBwcEy2Rpg9+7d1KxZEzs76yMtX76cCRMmYDab8fHxISUlhR07dhAaGoqDgwPBwcEcOXLE0j8mJobY2FgCAwP5+eefCQ0NJTk52bL/8OHDeHp63nZCgY3Xli+GDh3KqlWrWLx4McHBwcyePZvGjRvz/PPPs2rVKqPDExEREREpcC4uLnTp0oWxY8eyf/9+1q1bx9y5c+nRowdwrWqRkpICQLly5fjmm29Ys2YNp06dYtiwYQQEBFge2dC7d2++/PJLVq5cSUREBKNGjbI8aDokJAQnJydeffVVTpw4waZNm5g6dSrPPvusTfGasrOzs//dH8GdSUhIYP78+YSFhZGcnMzhw4dtPsYD727Nh8hEir5a5W7/GwkR+cuF+OR/7iQiVhb1ut/oEP7WwvBz+Xbs/9Qpddt9k5OTGTt2LGvWrMHNzY0+ffrQq1cvAKpWrcqkSZPo1q0bAEuWLOGDDz4gLi6ORo0aMWbMGEqUKGE51sKFCwkLC+Py5cs0aNCAN9980/JYh2PHjjFx4kTCw8NxdXWle/fuDBw40Ka5JYUiqYiJiWH9+vWsWbOGX375hUqVKtG2bVvat29PYGCgzcdTUiGSN0oqRPJGSYWI7ZRUFC2GT9R++umn2bNnD2XLlqVdu3aMHDnSaiKJiIiIiEhB0pqjtjM8qahTpw6jR4+mWrVqRociIiIiIiJ5YHhSMWzYMDIyMoiKiiIzMxO49mS/tLQ0Dh8+TLt27QyOUERERETuJXo+mu0MTyrWr1/Pq6++mutx4wB+fn5KKkRERESkQBm+POpdyPCf2bRp02jdujU//vgjHh4efPPNN4SFhREYGMgLL7xgdHgiIiIiIvIPDK9UREZGMmvWLO677z5q1KhBdHQ0rVq1ws7OjqlTp1qWyRIRERERKQga/mQ7wysVHh4elif4lS9f3vK0vwoVKnDmzBkjQxMRERERkdtgeFLxwAMPMG7cOI4fP05oaCjff/89v/32GwsWLLB6YIeIiIiISEEw5eNWVBmeVIwePZqyZcty8OBBWrVqRe3atXnssceYN28eI0aMMDo8ERERERH5B4Xiido3SkxMxMnJCUdHxzy9X0/UFskbPVFbJG/0RG0R2xXmJ2p/f+BCvh27c82S+XZsIxk+Uftm3NzcjA5BRERERERuU6FMKkREREREjGJXpGc/5A8lFXLHzPYmXnioIs0r+ZCWmcU3v55l4Z5zN+1b7z5PBjQvR6nizhy6kMB7P50gMvbasIFNLza56XsmrjrK6sPR+Ra/iBEc7Ez8p3ZJapdyJz0rm5+OXean4zE37VuthCtdapTA19XMqZhkFu67wMXENABmdA266Xu+/PUcOyPj8y1+EaM42pt4NrQMoeU8ScvI5offolj+28Wb9q1Vyp2n6wVS0t2Jo9FXmfNLJOeupAJ/P/Rmxs+n2Bxx83tR7h1aUdZ2Sirkjg1oVo6q/m68uOQgJd2dGPlIZaISUtl07LJVv3I+LkzpEsS8XWdZeySa9jVK8O5jwTz92R6S07PoOmunVf/H7y9Fiyq+bNE/7lIEdalRgvu8nJmx5Q+8iznyv7oBxCSlE34uwapfSXcz/RuVYc3RS/waeYVGZT0Z3PQ+3lwbQVpmNqNWHLXq36KSN/cHerD/vPVxRIqKp+sFUsG3GONWHcPPzczApuW4lJjGL6fjrPqV9nRmZKtKfLf/Aj+fiOGhyr6MeaQyQ5YeIiUji/9bsN+qf/vqJWhc3otf/7A+jojcHsNXfwJYt24d3bt3p0GDBtStW5fHHnuM7777zuiw5DY4O9jRvqY/Mzae4NjFq/wcEcP8X8/StXZArr6dawVw8HwCc7f/QWRsMmE/n+ZqaiatqvkBEJOUbtnMDnY8GhLAW+uOczUts6AvSyRfme1NNCrnyeL9UZyJT2H/+QTWH7tM8wpeufo2K+/FiZgkVhy+xMXENL7/7SLJ6VnUL1McgITUTMtmtrfjgYrezN97npSMrIK+LJF85+RgR8vKvny68wwnY5LZ+Uc83x+Mok2QX66+j1T15ejFRBaEn+fclVS+2n2WpPRMmla4tiBFXHKGZTPb29EuqARhW/8gKV33joApH/8rqgxPKr755huGDx9O/fr1mTx5MlOmTKFBgwaMGzeORYsWGR2e/IOKfq7Y29lxMMe3qwfOXaF6gFuu26ZUcScOX7D+9vTEpSSCA9xzHbdP4/vY/Uc8u//Q8A0pegKLO2NvMnHycpKlLeJyMmW9XXLdNz6uZk7HpFi1nb+SSnlvl1zHbRfkx9Hoq/wenZRrn0hRUNbLBXs7E0cvXrW0HbmYSGVf11z3Tgl3J47dcC/8EZtC1RKuuY77REgAB84ncEAVPpE8M3z40yeffMKYMWPo0qWLpa1Vq1ZUrlyZsLAwHn/8ceOCk3/k42omPjmdjKy/ViaOTUrHycEeDxcH4pMzrNp9XZ2s3l/C3cyVlIxcbS2r+jHwhtK0SFHh4ezA1bRMMnMs6J2Qeu3bUlezPYk5qnMJqRkUd7H+p9rTxYGkdOsKnpeLA/XKePDOplP5GbqIobyKOZKQmmH1Oyc+OQOzgx3uTg5cSc2wavcuZr00vY+rI4mp1veOr6sjTct7M3rF7/kbvNxVNKfCdoZXKi5fvkydOnVytYeEhHD+/PmCD0hs4uxoR3qmdak47c/XZnvrv14//X6JB6v40Ki8F/YmeKS6H9X83XC0t75z29fw5/eoRA5fSMzf4EUMYrY3WX0oAsj4M8NwsLO+H/acuUJIoAfBJd2wM0GD+4pf+7b2ht94jcp68kdsCqdjrasaIkWJk33u3znXXzvc8Ltk26lYGpXz5P7SHtiZ4IGK3lT0dc11jz1U2ZeIy0kcv6QKn8idMLxSERQUxHfffccLL7xg1b506VIqVapkTFBy29IysnC8IXm4nkyk3DAudefpOD77JZI3OlTD3s7E3jPxrD4cjauTvVW/Byr78sP+/HvojIjR0jOzc32wuf6BKO2GD0yHL15l5eFo+jQIxN7OxLHoJHb+EY+zo/V9VyfQgy0nY/M3cBGDpWXm/p1z/XXaDfOIws9eYdG+C7zUogL2JhMHLySw+fhlipmtf+c0LOvJmt8v5W/gctfRkrK2MzypGD58OL169WLHjh3Url0bgPDwcI4cOUJYWJjB0ck/iU5Mo7iLI/YmLEM5vIuZSUnPJDE1I1f/r3aeYcHus7iaHYhLTmds+6pciE+17PdzM1PepxhbIi7neq9IURGfkoGr2R47E1wvWHg4OZCWkUXyTSaJrjl6bblZZwc7EtMy6V0/kJikdMt+TxcHAjycNB5ciryYpHTcnRys7h1PFwdSM7JuuqjHt/sv8MPBKIqZ7bmSksGLD5S3LMcM4FPMkTJeLvwaGVdAVyBSdBk+/CkkJIRvv/2W2rVrExERwZkzZ6hfvz4rV66kYcOGRocn/+B49FUys7KonmOydc1Ad45EJZJ9Q9+WVX0Z9EB50jOziUtOx2xvR0jp4uw989dk7OoB7kRdSeViQhoiRdWZ+BQys7Mpl2OydQWfYpyOS85139Qt7UG3mv5kZGWTmJaJo52Jyn7FrCaglvNyISYpndjk3Im8SFFyKiaJzKxsqvj9Ndm6Wgk3Ii5dzXXvNCnvRa8GpcnIyuZKSgZmexM1Atz4LceCIZX9XLmUmMalq+mI5GQy5d9WVBleqXjuuecYNmwYr7zyitGhSB6kZmSx6lA0Q1tWZMqa4/i6mXmibiCT1xwDwLvYtUlxaZlZRMYmM+Lhyuw7G8+JS0kMaFaOiwmp7MgxZKO8TzFOxWhcqxRt6ZnZ7PwjnifqlGTe7vN4ujjQsrI38/Zcm0fm7mRPSnoW6VnZXExM46n7A4i4nMS5+BQ61/AnLjmDQ1F/zTkK8HDiQkLq351OpMhIy8xmY8Rl/q/RfXy45TTero50quHPB1tOA38uYpCWSVpmNuevpPBc07IcupDIH7HJPF0vkEtX09l75orleGW8XDgTn2zU5UghVpQ//OcXwysVe/bswcHB8NxG7sAHm05y9OJV3n2sBi88VIFPt//Bz38+GXhpvwY8VNUX4Fqf9REMbF6e2U9eG+o24vtDVt8ueRdzJDFF37ZK0fftgSgi41J4vllZHq9dkhWHo9n359LME9tV4f7SHgBExqWwIPwCXWuUYHiL8gCEbYu0um/cnRxI1vNc5B7x+c4znLicxNg2lXk2tAwLws+x888H1s1+ohaNy1973suJy8nM3v4HPesHMqVjNQAmrTtude94OjvkWg1KRPLGlJ2dfWPFsEBNnz6djRs30r17d0qVKoWTk/WSo/Xr17f5mA+8u/XfCk/knlKrnLfRIYjclS7o224Rmy3qdb/RIfyttYfzb/J+6yDffDu2kQwvEXz44YcAvP7667n2mUwmDh8+XNAhiYiIiIiIDQxPKo4cOWJ0CCIiIiIiFnaaU2Ezw+dUpKWlMXXqVObNm2dp69atG9OmTSM9XasxiIiIiIgUdoYnFePHj2fTpk1Uq1bN0vbcc8+xceNGpkyZYmBkIiIiInIvMuXjf0WV4UnFmjVrmDZtGnXr1rW0tWrVikmTJrFixQoDIxMRERERkdth+JyK7OxsUlNzr6+enZ2t4U8iIiIiUuD0nArbGV6peOSRR3jttdf49ddfSUpKIikpiT179jB27Fhat25tdHgiIiIico/R8CfbGV6pGDlyJKNHj6Znz55kZWUBYGdnR5cuXRg1apTB0YmIiIiIyD8xPKlwcXHhnXfe4cqVK5w+fRpHR0dKly6Nm5ub0aGJiIiIyD1IS8razvCkAiAmJoaTJ0+SlZVFSkoKhw4dIi0tjUOHDtG3b1+jwxMRERERkVswPKlYuHAhb7zxBhkZGZhMJrKzs4FrT9OuVauWkgoRERERKVBFee5DfjF8onZYWBj9+/dn//79+Pj4sGHDBpYvX05QUJAmaouIiIiI3AUMTyouXrxIly5dMJvNBAcHEx4eTqVKlRg1ahSLFi0yOjwRERERuceYTPm3FVWGJxXe3t7ExMQAUKFCBQ4fPgyAv78/UVFRRoYmIiIiIiK3wfCkom3btowYMYI9e/bQrFkzvv32W1avXs0HH3xA2bJljQ5PRERERO4xpnzciirDJ2q/9NJLuLu7ExsbS8uWLXn00UcZM2YMnp6eTJw40ejwREREROQeY1eUxynlE1P29eWWipAH3t1qdAgid6Va5byNDkHkrnQhPtnoEETuOot63W90CH9r+/G4fDt2o0qe+XZsIxleqUhKSmLRokWcOHGCtLS0XPsnTZpkQFQiIiIicq9SncJ2hicVQ4cOZe/evTRu3BhnZ2ejwxERERERERsZnlTs2LGDuXPnEhISYnQoIiIiIiIqVeSB4as/VahQgZSUFKPDEBERERGRPDK8UjF58mQGDRpEx44dKVWqFHZ21nlOly5djAlMRERERO5JJpUqbGZ4UrFw4UJOnz7N/PnzcXJystpnMpmUVIiIiIiIFHKGJxWLFy/mnXfeoV27dkaHIiIiIiKCHlNhO8OTCi8vLypVqmR0GCIiIiIigOZp54XhScWYMWN44403GDhwIKVLl8be3t5qf6lSpQyKTEREREREbofhSUW/fv0A6N27N6Yctabs7GxMJhOHDx82KjQRERERuRepVGEzw5OK9evXGx2CiIiIiIjcAcOTisDAQKNDEBERERGx0JKytjP84XciIiIiInJ3M7xSISIiIiJSmGhJWdupUiEiIiIiIndElQoRERERkRxUqLCdkgoRERERkZyUVdhMw59EREREROSOKKkQEREREcnBlI//2SI1NZVRo0ZRr149mjZtyty5c/+275YtW+jUqRMhISH06tWLEydOWO1ftWoVjzzyCHXq1OGZZ57h7NmzeTrP31FSISIiIiJSCE2dOpWDBw/y+eefM2bMGGbOnMmqVaty9Tt27Bj9+vWjZcuWLFmyhOrVq9OzZ0+uXr0KwJ49exg2bBi9e/fm22+/xWw2M3ToUJvPcytKKkREREREcjCZ8m+7XUlJSSxatIjRo0cTHBxM69atefbZZ5k3b16uvvPnzyckJIQhQ4ZQoUIFhg8fjru7O8uWLQNg7ty5dOrUie7du1OhQgVGjx5NdHQ0MTExNp3nVpRUiIiIiIgUMkeOHCEjI4OQkBBLW926ddm3bx9ZWVlWfSMjI6lVq5bltclkokqVKoSHhwOwc+dOWrdubdlfpkwZfvrpJ7y9vW06z60oqRARERERycGUj1taWhqJiYlWW1paWq4YoqOj8fLywmw2W9p8fX1JTU0lLi7Oqq+vry9RUVFWbRcuXCA2NpYrV64QHx9PZmYmffr0oUmTJgwYMMDS35bz3EqRXFLWwUG5kkheHDoTZ3QIInclOz1+V0Ru06xZs5g5c6ZV26BBgxg8eLBVW3JystUHfcDy+sYkpG3btjz33HN06NCBZs2asWzZMg4cOEBoaChJSUkAjB8/nhdffJEhQ4bw/vvv069fP7799lubznMrRTKpEBERERHJs3z8nqBfv3707t3bqu3GD/UATk5OuT7UX3/t7Oxs1d68eXMGDhzI4MGDyczMJDQ0lM6dO5OYmIi9vT0Ajz/+OF26dAFg2rRpNGnShPDwcJvOcytKKkREREREcrB16VdbmM3mmyYRN/L39yc2NpaMjAwcHK59ZI+OjsbZ2RkPD49c/QcMGECfPn1ISEjAx8eHIUOGEBgYiJeXF46OjlSoUMHS18vLC09PTy5cuEDJkiVtOs/f0TghEREREZFCJigoCAcHB8tka4Ddu3dTs2ZN7OysP8IvX76cCRMmYDab8fHxISUlhR07dhAaGoqDgwPBwcEcOXLE0j8mJobY2FgCAwNtOs+tKKkQEREREcmhMCwp6+LiQpcuXRg7diz79+9n3bp1zJ07lx49egDXqgkpKSkAlCtXjm+++YY1a9Zw6tQphg0bRkBAAM2bNwegd+/efPnll6xcuZKIiAhGjRpFUFAQtWrV+sfz3PbPLDs7O9umd9wFWs7YbnQIIiJyD9FEbRHbrR3U0OgQ/taBM4n5duyapd1uu29ycjJjx45lzZo1uLm50adPH3r16gVA1apVmTRpEt26dQNgyZIlfPDBB8TFxdGoUSPGjBlDiRIlLMdauHAhYWFhXL58mQYNGvDmm29SsmTJfzzP7VJSISIicoeUVIjYrjAnFQfzMamoYUNScTcxfKL2rl27btpuMplwdHTEz8+PUqVKFXBUIiIiIiJyuwxPKkaPHs2ZM2fIysqiePHiZGdnc+XKFUwmEyaTiezsbGrVqsWMGTOsSjgiIiIiIvlCxUebGT5Ru2vXrtSsWZOVK1eyY8cOdu7cydq1a6lXrx7Dhw9n69at+Pv7M378eKNDFRERERGRmzA8qfj8888ZN24c5cuXt7SVKVOG0aNHM2vWLLy9vRkyZAjbt2uehIiIiIjkP1M+/ldUGZ5UAMTGxt60LTMz0/LapElwIiIiIiKFkuFzKh577DFGjBjBiy++SI0aNcjOzua3337j/fffp2vXrsTGxvLWW2/RoEEDo0MVERERkXuAvsu2neFJxbBhw3B1deXdd9/l4sWLAJQoUYL//e9/9OnTh23btuHg4MDrr79ucKQiIiIici9QTmE7w59TkZaWhtlsBq4NeXJwcMDd3f2OjqnnVIiISEHScypEbFeYn1Nx+NzVfDt2UCnXfDu2kQyvVDRq1IhWrVrRrl07mjRpgoOD4SGJiIiIyL1M3xPYzPCJ2u+//z5OTk6MGjWKJk2aMHr0aLZt20ZWVpbRoYmIiIiIyG0wfPjTdVlZWezatYu1a9eyfv160tLSeOSRR/I0l0LDn0REpCBp+JOI7Qrz8Kcj55Py7djVAorl27GNVGjGGtnZ2VG3bl1SUlLIzMzk+++/Z/PmzUaHJSIiIiIi/8DwpCI1NZXNmzezevVqNm3aRLFixWjTpg2ffvoptWvXNjo8EREREbnHqPhoO8OTitDQUIoVK0br1q354IMPqF+/vh50JyIiIiJyFzE8qZgxYwaNGzfG3t7e6FBERERERLT4Ux4YnlQ0a9aMw4cPc+zYMcuKT9nZ2aSlpXHo0CHGjRtncIQiIiIick9RVmEzw5OKmTNnMnPmTHx9fbl8+TL+/v5cunSJzMxMWrdubXR4IiIiIiLyDwx/TsWCBQsYN24cW7ZsISAggC+//JJt27bRuHFj7rvvPqPDExEREZF7jCkf/yuqDE8qYmNjadasGQBBQUHs3bsXDw8PXnzxRVasWGFwdCIiIiIi8k8MTyr8/f2JjIwEoGLFihw6dAgANzc3YmJijAxNRERERO5BJlP+bUWV4XMqHn/8cYYOHcrEiRNp1aoVvXr1okSJEmzbto1q1aoZHZ6IiIiIiPwDw5OK/v37U7JkSVxcXKhVqxYjR47km2++wdPTk4kTJxodnoiIiIjcY4pwQSHfmLKzs7ONDuLf1nLGdqNDEBGRe4hdUR7TIJJP1g5qaHQIfyviYnK+HbtiCZd8O7aRDK9UiIiIiIgUKvqewGZKKkREREREcijKS7/mF8NXfxIRERERkbubKhUiIiIiIjlompTtDEkqnn76aUy3+af1xRdf5HM0IiIiIiJyJwxJKkJDQy3/Hxsby4IFC2jVqhU1a9bE0dGRw4cPs2LFCp566ikjwhMRERGRe5gKFbYzJKkYNGiQ5f979erFqFGjePLJJ6361K9fnwULFhR0aCIiIiIiYiPDJ2qHh4fTqFGjXO21a9fm999/NyAiEREREbmnmfJxK6IMTyqqV6/Oxx9/TGpqqqUtMTGR6dOnU6dOHeMCExERERGR22L46k9vvvkmffv2pUmTJpQtW5bs7GxOnTpFqVKlmDVrltHhiYiIiMg9Rs+psJ3hSUXFihVZuXIl27ZtIyIiAoDKlSvTuHFjHBwMD09ug6O9iSEPVKBZJW9SM7JYtPcci/aev2nfumWK069pWUp5OHMoKoHpG09yJi4FgPWDcw+DA5i89hhrj1zKt/hFjKD7RiRvHO1NDH6gPM0qXrt3Fu89z+Lwv793/q/JfZTycOZwVCIzNv1176wd1PCm75my9jjrfte9c6/TkrK2KxSf2s1mM4GBgaSnp9O4cWNiYmKwt7c3Oiy5Tf2alKWKvysvLT1ECXcnRrSuSNSVVDZHxFj1K+vtwsSO1Zi/+xzrfo+mXfUSvN01mJ5f7SUlPYvH5vxq1f+xOgE8WNmHbSdiC/JyRAqE7huRvOnbpCxVSrgy/LtD+Ls7MbxVRaISUvn5JvfO+A5V+Wb3OdYfvUSb6iV4q0t1es8LJyU9i//M3W3V/9HaATxQ2YdtJ3XviOSF4XMq4uPj6dWrF507d2bIkCHExMQwYcIEOnTowNmzZ40OT/6Bs4Md7YL9+WDzKY5FX2XriRgW7D5H51olc/XtVLMkv11I5LMdkZyJS+HjbX9wNS2DVlV8AYhNSrdsTg52dK0dwNs/neBqWmZBX5ZIvtJ9I5I3zg52tK1egg9/Ps3x6CS2nohl4Z7zN713Otbw59CFRD7feYYzcSl88ue90/Jm9469HV1ql+SdnyJI0r0jaJ52XhieVIwfPx4XFxd++eUXnJycAJgwYQIlS5Zk/PjxBkcn/6SCbzEc7Ez8dj7B0nbwfAJBJd1z3TgBHk4cuZBg1XbichLVA9xzHbdXaBn2RsazJzI+P8IWMZTuG5G8uX7vHLrh3qnm73bTe+dwVKJV28nLyVQvmfve6Rlamr1n4tl75kp+hC1yTzA8qfj5558ZOnQoHh4eljYfHx9GjhzJrl27DIxMboePq5n45HQysrItbde/MfVwth5dF5uUjo+b2aqthJsTxZ0db2gz81AVX77cdSb/AhcxkO4bkbzxvsm9E5eUdvN7JzkdX1fre8fPzYyHi0OuthZVfJm3S6Mj5C8mU/5tRZXhSQVgtZzsdTExMZqofRdwcrAjPTPbqi09MwsAR3vrv14bj13mgUo+NCzniZ0JHq7mR9USrjjYW99hbYNLcPRiIkdu+IZJpKjQfSOSN843uXfS/nx9s3uneSVvQv+8d1pX86VqCVcc7W64d6qX4OjFq7p3RO6Q4Z/aO3TowIQJE3jjjTcwmUwkJSXxyy+/MGbMGNq1a2d0ePIP0jKzcLzhw831f9hTM7Ks2nf9EccXO88wpl1V7E0mws/Gs/bIJVydrCflN6/ow7KDUfkbuIiBdN+I5E1aRu57x/zn69QM67kQv/4Rz1c7z/B62yrYm0zsO3uFtb9fwtVsfe80q+jN8t9078iNinBJIZ8YnlS8/PLLvPPOO3Tr1o309HS6dOmCvb09jz32GC+//LLR4ck/uJSYRnEXR+xMcL0a7V3MkZT0TBJTM3L1//rXsyzacw5XJ3vikjN4rU1lLlz5q1Ll52amnE8xtp2IyfVekaJC941I3ly6mvve8Spm/vPeyT3B+uvd15Zqvn7vvPpIZaISbnbvaMUnkTtl+PAns9nMK6+8wq5du1i2bBlLly5lx44djB07lqSkJKPDk38QcSmJjKxsq4lvNUq58/vFq2Tf0LdFZR+ea1aO9Kxs4pIzMNvbUad0ccLP/jWpNMjfjaiEVC4mphXQFYgUPN03Inlz/d4JynnvBLhz9G/unQFNy+a4d0zULu1BeI7J2NX83biYkEq07h25geZU2M7wpCIoKIiYmBicnZ2pXLky1apVw9XVlbNnz9KyZUujw5N/kJqRxZrDF3mhRQWqlnClSQUvHg8pxbf7rj2IyKuYI+Y/h3WciUuhYw1/mlb0JrC4M6MfqUx0Qio7T8VZjlfOpxinY5KNuBSRAqP7RiRvUjOyWHskmiEPlqdKCVcal/fi8ZAAllrdO9c+tZ2JS6FDDX+aVvAisLgzIx+uTHRCGrtOx1mOp3tH/o6WlLWdIcOfvvvuO7799lsAsrOzGThwII6O1iuZXLx4ET8/PyPCExt9tOU0LzxYnre7BnM1LZPPd0Sy5c+HEC3uU4+pa4+z+kg0x6Kv8t7GE/RvUhYPFwf2Rl5h1LIjVt8ueRVzvOnwD5GiRveNSN6EbTnN8w+WZ1qX6tfunZ1n2PLn8KWFz9TlrXURrPnz3pm+6SR9m5bFw/navfPq8hvuHRfdOyL/FlN2dvaNFcN8d/XqVT799FMAZs6cSe/evXF1dbXqU6xYMVq3bk2ZMmVsPn7LGdv/lThFRERuh11RHtMgkk/WDmpodAh/63x8/g2JCyhu/udOdyFDKhWurq4MGjQIgMDAQNq1a2d58J2IiIiIiNxdDF/9qWvXrpw4cYLff//9ps+r6NKlS8EHJSIiIiL3LFORnv2QPwxPKj777DMmT56Mh4cHbm5uVvtMJpOSChERERGRQs7wpGL27Nm88sor9OrVy+hQRERERESK9jJN+cTwJWVTUlK0dKyIiIiIyF3M8KSic+fOfP3110aHISIiIiIC6DkVeWHI8Kenn34a05/L76Wnp7N3715WrlxJ6dKlsbOzznO++OILI0IUERERkXuUVom2nSFJRWhoqNXrJk2aGBGGiIiIiIj8CwxJKq4/o0JEREREpLDRkrK2M3z1p5xDoXIymUw4Ojri5+dH27Ztad68uQHRiYiIiIjIPzF8onb9+vXZs2cPfn5+tG7dmlatWlGyZEl2795NiRIlcHFxYejQoSxZssToUEVERETkXqCZ2jYzvFKxfft2Ro4cyVNPPWXVXq9ePb7//nvmzZtHw4YNeeedd3j00UcNilJERERERP6O4ZWKQ4cO3XSidoMGDThw4AAANWrU4Pz58wUdmoiIiIjcg1SosJ3hSUW1atX46quvyM7Otmr/+uuvqVSpEgAHDhygZMmSRoQnIiIiIiL/wPDhT6+99hr/93//x8aNG6levToAhw8fJjExkbCwMHbv3s3w4cN5/fXXDY5URERERO4FheU5FampqYwbN441a9bg7OzMM888wzPPPHPTvlu2bGHq1KlERkZSu3ZtXn/9dSpUqGDZX69ePRISEqzes2fPHlxdXVm7dm2u1VkfeeQRpk+fftuxGp5U1KhRg7Vr1/Ljjz9y9OhR7O3tadasGe3bt6dYsWKcOXOGhQsXUq1aNaNDFREREZF7QGFZUnbq1KkcPHiQzz//nHPnzjFixAhKlSpFmzZtrPodO3aMfv360bdvXzp27MjixYvp2bMnq1atwtXVlaioKBISEli3bh3Ozs6W9xUrVgyA48eP06JFC958803LPicnJ5tiNTypAHBzc+OJJ5646b7SpUsXcDQiIiIiIsZKSkpi0aJFzJ49m+DgYIKDgzl27Bjz5s3LlVTMnz+fkJAQhgwZAsDw4cPZuHEjy5Yto3v37kRERODn50eZMmVueq6IiAiqVKmCn59fnuM1JKlo2bIlixcvxsvLi4ceeuimz6m4bv369QUYmYiIiIjc6wrD8KcjR46QkZFBSEiIpa1u3bqEhYWRlZWFnd1fU6MjIyOpVauW5bXJZKJKlSqEh4fTvXt3jh8/Tvny5f/2XBERETRu3PiO4jXsidqurq4ADB482IgQREREREQKXFpaGmlpaVZtZrMZs9ls1RYdHY2Xl5dVu6+vL6mpqcTFxeHt7W3VHhUVZfX+CxcuULx4ceBa0pCcnMzTTz/NyZMnCQoKYtSoUZQvX57s7GxOnjzJli1bmDVrFpmZmbRp04bnn38+V0y3YkhS0bVr15v+f3x8PO7u7phMpltWL0RERERE7kazZs1i5syZVm2DBg3K9UV7cnJyrg/111/fmJS0bduW5557jg4dOtCsWTOWLVvGgQMHCA0NBeDEiRPEx8czdOhQ3NzcmD17Nr169eLHH38kPj7ecq733nuPM2fOMH78eFJSUnj11Vdv+7oMn1ORnZ1NWFgYn332GQkJCaxevZr333+fYsWK8eqrr9qUIYmIiIiIFGb9+vWjd+/eVm03+7zr5OSUK3m4/jrnZGuA5s2bM3DgQAYPHkxmZiahoaF07tyZxMREAObMmUN6erplpNC0adN44IEH2LBhAx07dmTHjh0UL14ck8lEUFAQWVlZDB8+nJEjR2Jvb39b12X4cyo++OADfvjhByZPnmz5gXbt2pWtW7cydepUg6MTERERkXuNyZR/m9lsxs3NzWq7WVLh7+9PbGwsGRkZlrbo6GicnZ3x8PDI1X/AgAHs2bOHLVu28Nlnn3H16lUCAwOBa+e8nlDAtYSldOnSliFTnp6eVqOEKlasSGpqKvHx8bf9MzM8qVi6dClvvPEGLVq0sFxMkyZNmDJlCitXrjQ4OhERERGRghcUFISDgwPh4eGWtt27d1OzZk2rSdoAy5cvZ8KECZjNZnx8fEhJ+f/27j2qyirx//gbIdCBMEdTZswRxECQGSRANI83cGrJolLLWy40NS/TmJrXZLwwKdrohBe8ZWWKy7whOBXYKKLYKIjXQVMcBVGxzBWJSSgIPL8/XJ7pfNHfSMfj0fy8/EPW3vvsZz/POofD5+y9n3Odffv2ERYWhmEYdOvWjeTkZHP7srIyzp49S4sWLfjyyy8JCwvj2rVr5voTJ07wxBNPWOzb+F/sHiqKi4tp3LhxjXJ3d3fKysrsMCIREREReZQ52PDf3apXrx49evQgNjaW3Nxc0tPTWblyJQMHDgRuzlpcv34dAE9PT9avX8+2bdsoLCxk/Pjx/OY3v6FTp044ODjQpUsXEhIS2LdvH6dOnWLSpEl4eHjQuXNngoKCcHFxYerUqRQUFJCZmcncuXN5/fXXa3XN7B4q2rVrx0cffWRRVlpaSnx8vHlziYiIiIjI/WLL5U+1MWXKFFq3bs2gQYP461//yptvvslzzz0HgMlkIi0tDbj5ZdKxsbG8++679OrVC7i5IfzWjMbEiRN5/vnnGT9+PL1796ayspIVK1bg6OiIm5sbH330Ed9//z0vv/wyf/nLX+jbt2+tQ4WDYRhG7U7v3rp48SKjRo3im2++4fLly3h7e/P111/z29/+lmXLlv2sL7+LSMiywUhFRERur47uWChSa9tHtbP3EO7oh+vVNuvbva7dP9O3Cbvf/cnDw4OkpCSysrIoKCigsrISLy8vTCZTjfViIiIiIiK2po8Jas/uoeLVV1+lc+fOmEwmBgwYYO/hiIiIiIhILdk9VPTo0YM9e/bw8ccf4+joSIcOHejYsSMmk4kGDRrYe3giIiIi8qjRVEWt2X1PxS2GYXD8+HGysrLYs2cP+/fvx8/Pj02bNtW6L+2pEBGR+0l7KkRq70HeU3G13HZ7Kh53+WUu77f7TAVAVVUVX331FYcOHeLf//43//nPf3B2dr7tF3uIiIiIiNhSbW79KjfZPVRER0dz7Ngx3N3dCQwMJDg4mBEjRuDv76+N2iIiIiIiDwG7hwonJyccHBxo0KABjRs3pkmTJjRp0kSBQkRERETsQisaa++B2FNRWVnJV199xf79+zlw4ABHjhzh8ccfJyQkhDlz5tS6P+2pEBGR+0l7KkRq70HeU/Fjhe3+PHZ1/mX+vrD7TAXcnK0IDAzE1dWVevXq4ezszM6dO8nOzrb30ERERETkEfPL/LPftuweKtauXUtOTg4HDhygrKyM0NBQOnTowJgxY/D29rb38ERERETkUaNUUWt2DxUbN27EZDLRr18/goODcXZ2tveQRERERESkFuweKv7xj3/YewgiIiIiIma6pWzt6RZLIiIiIiJiFbvPVIiIiIiIPEh0Q7fa00yFiIiIiIhY5YH4ngoREREREXl4aaZCRERERESsolAhIiIiIiJWUagQERERERGrKFSIiIiIiIhVFCpERERERMQqChUiIiIiImIVhQoREREREbGKQoWIiIiIiFhFoUJERERERKyiUCH31b59+/D19b1n7USkpqKiInx9fSkqKgLA19eXffv22XlUIre3Y8cOOnXqRGBgIF9++SUAFRUVREVF6Xkr8hBRqJD7KigoiH/961/3rJ2IiDzcFi1ahMlkIi0tjdDQUMrLyxk3bhynTp2y99BEpBYUKuS+cnZ25sknn7xn7URE5OF29epVgoODadq0KUVFRfTp04dz587Ze1giUksKFQL8d7nEZ599RseOHQkJCWHWrFlUVlaSkJDAG2+8wYABA2jbti05OTlUVFQwa9YswsLCCAsLY8KECZSUlJj7O3v2LEOHDiUoKIguXbqQmJgI1FzWlJiYSNeuXfn9739Pr169OHDgwG3bXbx4kTFjxtC2bVvCwsKYNWsWFRUVACQnJxMdHc2iRYsICwsjJCSEOXPmYBjGfbhyInfv1utsyZIlhIaG8s4777B9+3YiIyMJDAzklVdeIScnx9y+srKS+Ph4TCYTwcHBjB49msuXLwPw7bffMnr0aEJDQwkICKBnz54cPHjQXqcm8rOEh4dz4cIFYmJiCA8PJycnh7CwMDZs2HBXj8/Ly6Nfv34EBgbSsWNHFi9ebK4rKytj+vTp5vepadOmUV5eDsCVK1eYNm0azz77LMHBwUycOJErV64AN99/wsPDmTFjBsHBwaxYsQKA9evXEx4eTlBQENHR0Zw8efIeXw2Rh5tChVhYvHgx8+fPZ/HixWzbto2EhATg5prXqKgoVq9ezR/+8Afi4+M5duwYH3zwAYmJiZSWljJmzBgAysvLGTJkCK6urmzcuJHp06czf/58du7caXGs48ePM3fuXGbMmMHWrVsJCQlh7NixVFdXW7SrqKhg0KBBXLt2jTVr1rBgwQJ27drF3LlzzW0OHz7MmTNnWLduHdOmTSMxMZG9e/fa+GqJ/DyHDh1i8+bN9OnTh8mTJ/OnP/2JTz/9lBdffJFhw4Zx9uxZABYuXEhKSgqzZ89mw4YNFBcXM2PGDAAmTJhAVVUV69evZ8uWLTRp0oTY2Fg7npVI7SUlJeHh4UFMTAxJSUm8+uqrxMTEUK9evbt6/KRJk/Dz8+Pzzz8nLi6ODz/8kMzMTACmTp3KwYMHWbp0KStXruTgwYMsWLAAgFGjRnHixAmWL1/Oxx9/TH5+Pm+//ba53wsXLlBRUUFycjJRUVFkZGSwePFipk2bRkpKCsHBwQwcONAcREQEMEQMwzh//rzh4+NjbN++3VyWlJRktGvXzli4cKHx7LPPmsvLysqM1q1bG3l5eeayK1euGK1atTLy8vKM9PR0o02bNsbVq1ct+tq1a5eRnZ1t+Pj4GIZhGNu2bTMCAgKMkydPGoZhGD/++KOxd+9e48aNGxbt0tPTjcDAQKOkpMTcX2ZmpuHv72+UlpYamzdvNlq1amVxvB49ehjLli27x1dJxDq3XmeZmZmGYRjGhAkTjDlz5li0GTVqlDFnzhyjurraaNu2rbF582Zz3alTp4xFixYZ1dXVxqpVq4xvvvnGXLd7926jVatWFsc5f/68YRiG4ePjY2RnZ9v69ER+lq5du1o8z2+5m+ftM888YyxYsMCoqqoyDMMwDh06ZFy6dMkoKSkx/Pz8LB6/f/9+IzEx0Thx4oTh4+NjFBQUmOtOnz5t+Pj4GPn5+eb3n9OnT5vr+/fvbyQmJlocu2fPnjXKRB5lTvYONfJgeeaZZ8w/BwQE8P3333P58mWaNm1qLj9//jw3btygX79+Fo+trq6msLCQ8+fP4+XlhZubm7nu5ZdfBrC4k4fJZMLHx4cXXngBf39/IiIi6N27N05Olk/L/Px8PD09qV+/vsU4KysrzetuGzZsaHE8Nzc3KisrrbkUIjZz6/WUn5/P1q1bLZZ63LhxA5PJxOXLlykpKaF169bmupYtW/Lmm28C0L9/f9LS0jh06BBnzpzh2LFjNWb5RH5JXn/9dYslfocPH2bEiBHEx8ezYcMGunTpwksvvcSTTz5Jbm4uVVVVFq+fkJAQQkJCSEtLw93dHS8vL3Odt7c39evXp6CggMcffxyAp556ylyfn5/PvHnziI+PN5eVl5dTWFhowzMWebgoVIiFxx57zPzzrT9Q6tSpg4uLi7m8qqoKgE8++YRf/epXFo9v2LAhSUlJd3WsevXqsWnTJnJycti5cyfJycmsW7eO5ORki3Y/Pfb/HcOt/52dnWu0MbSnQh5Qt57TVVVVDBs2jB49eljU161bt0a4/qnq6mqGDBnCDz/8QGRkJOHh4dy4cYNRo0bZctgidhUXF8f169ctyoYPH0737t1JT08nIyODQYMGMXPmTAICAu7Yz+3eL+Dm6/HWewpQ430vJiaG9u3bWzzmpx9miTzqtKdCLJw4ccL887Fjx2jcuDFPPPGERZtmzZrh6OhISUkJzZs3p3nz5ri5uTFnzhyKi4vx9PTk7NmzXLt2zfyYv/3tb8yaNcuin8OHD/P+++/Trl07pkyZwhdffEF5eXmNzaZeXl4UFhZabAQ/cuQITk5O/O53v7t3Jy9yn3l5eVFUVGR+HTVv3pwNGzawe/du3N3dadCgAXl5eeb2J06coFOnTpw6dYr9+/ezatUqRo4cSZcuXbh06RKgMC2/XE2aNLF4rZSXlzNr1iycnZ0ZPHgwa9asoU+fPvzzn/80v0/99PWTnp5Oz5498fLy4ocffqCgoMBcd/r0aUpLSy1mL37Ky8uLixcvWhx/+fLlHDlyxNanLfLQUKgQC3FxcRw9epS9e/eycOFCBgwYUKONm5sbvXv3JjY2ln379nH69GkmTZrE2bNneeqppzCZTDRq1Ijp06eTn5/Pjh07WL9+PSaTyaKfunXrsmTJEjZt2kRRURGpqamUlZXV+NK7Dh060KxZMyZNmsTJkyfJzs5m5syZREVF4e7ubtPrIWJLr732GmlpaSQmJnLu3DlWrVrFqlWr8PT0BCA6OpqFCxeSnZ3NqVOniIuLo02bNtSvX586deqQmprKhQsX+OKLL8w3Vbh1VzSRXzoXFxcOHTrEzJkzKSgo4OjRoxw4cAB/f3/c3Nzo0aMHcXFx5ObmcvToUebPn0+7du3w9vamU6dOTJ48mdzcXHJzc5k8eTKhoaH4+Pjc9liDBw9m9erVbNmyhXPnzjFv3jy2bt2Kt7f3fT5rkQeXQoVYiIyMZMSIEYwbN47evXszfPjw27Z7++23ad++PaNHj6ZPnz44OTmxYsUKHB0dcXJyYunSpVy6dImePXsSFxfHpEmT6NKli0Uffn5+5rt1dO/eneXLlzNv3rwav6QdHR1ZunQpAH369GHcuHFERETwzjvv2OQaiNwvbdq0Ye7cuXzyySdERkayceNG3nvvPUJDQ4GbSzuee+45xo4dS//+/fHw8GDmzJl4eHgQGxvLBx98QFRUFCtWrGDq1Kk4OTlx/PhxO5+VyP0zf/58rl27xiuvvMLQoUMJCQnhjTfeACAmJoZWrVoxePBghg0bRlhYGG+99RZwc/a8WbNmvPbaawwdOpSnn36aJUuW3PE4kZGRvPXWWyxatIioqCiysrJYtmyZ+QMAEQEHQ3Plws3750dERLBjxw6LzWkiIiIiIv+LZipERERERMQqChUiIiIiImIVLX8SERERERGraKZCRERERESsolAhIiIiIiJWUagQERERERGrKFSIiIiIiIhVFCpERERERMQqChUiIveYr68vvr6+fP311zXq1q1bh6+vLwkJCXfVV3FxMVu3br1jfXJyMuHh4T97rCIiIveCQoWIiA089thjZGRk1ChPT0/HwcHhrvv5+9//TmZm5h3rIyMjSUpK+lljFBERuVcUKkREbCAkJKRGqCgtLeXw4cP4+/vfdT//66uE6taty69//eufNUYREZF7RaFCRMQGIiIiyMnJobS01Fy2a9cuQkJCcHV1tWi7fv16wsPDCQoKIjo6mpMnTwKQkJBASkoKKSkp5iVOvr6+LFy4kLCwMEaOHFlj+VNubi79+/cnMDCQ559/ntTUVABu3LjB1KlTCQsLIygoiJEjR/Ltt9/a+jKIiMgjQqFCRMQGfHx8aNKkCbt37zaXbd++nW7dulm0y8jIYPHixUybNo2UlBSCg4MZOHAgV65cYciQIXTv3p3u3btbLHHauXMn69atY8KECRZ9FRcXM2TIEPz8/EhJSWHEiBFMnjyZvLw81q5dy/79+1m5ciVJSUn8+OOPzJ4927YXQUREHhkKFSIiNhIREWFeAlVRUcGePXuIiIiwaPPhhx8yYsQIunbtiqenJ2PHjqVp06Z8+umnuLq6Urdu3RpLnPr27UuLFi1o2bKlRV+pqanUr1+fqVOn0qJFC3r16sX48eO5fv06RUVFuLi40LRpU7y9vXn33XcZPny47S+CiIg8EpzsPQARkV+qiIgIRo8eTWVlJVlZWfj4+NCwYUOLNvn5+cybN4/4+HhzWXl5OYWFhXfst2nTprctP3PmDP7+/tSp89/PiwYPHgyAq6srqampmEwm2rZtS7du3ejVq5cVZyciIvJfChUiIjYSHBwMwMGDB0lPT+ePf/xjjTZVVVXExMTQvn17i3I3N7c79uvi4nLbcienO/9Kf/rpp8nIyGDXrl3s2rWL+Ph4Pv/8c9auXVuru1GJiIjcjkKFiIiNODk50blzZzIyMti5c+dtlxt5eXlx8eJFmjdvbi6bMmUK3bp1IyIiAgcHh/95B6hbPD09yczMxDAMc1AYO3YsAQEBNGrUCGdnZyIjI+nevTtHjhyhb9++FBcX06hRo3tzwiIi8sjSngoRERuKiIhg06ZNNGzYkGbNmtWoHzx4MKtXr2bLli2cO3eOefPmsXXrVry9vQGoV68eFy5cuKs7Nb3wwguUlJQwd+5cCgsLSU5OZseOHXTo0IGrV68SFxdHVlYW58+f57PPPsPDw4MGDRrc83MWEZFHj2YqRERsyGQyUVlZWeOuT7dERkby3XffsWjRIr777jtatmzJsmXL8PT0BOCll17iz3/+My+++CLZ2dn/32O5u7vz/vvvM3v2bNasWUOzZs1477338PPzw9fXl4sXLzJx4kSuXLlCQEAAy5Ytw9HR8V6fsoiIPIIcjLudVxcREREREbkNLX8SERERERGrKFSIiIiIiIhVFCpERERERMQqChUiIiIiImIVhQoREREREbGKQoWIiIiIiFhFoUJERERERKyiUCEiIiIiIlZRqBAREREREasoVIiIiIiIiFUUKkRERERExCr/D5PAxdoSzOaSAAAAAElFTkSuQmCC"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot classification report\n",
+    "plot_classification_report(cr_v2)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:07:43.343425300Z",
+     "start_time": "2024-06-08T16:07:42.949867200Z"
+    }
+   },
+   "id": "967251e118adbb60"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Neural network V3"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "9900eac2f18370e5"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/1000, Loss: 0.5781828761100769\n",
+      "Epoch 20/1000, Loss: 0.35954442620277405\n",
+      "Epoch 30/1000, Loss: 0.16433778405189514\n",
+      "Epoch 40/1000, Loss: 0.09435044229030609\n",
+      "Epoch 50/1000, Loss: 0.06897494941949844\n",
+      "Epoch 60/1000, Loss: 0.05602168291807175\n",
+      "Epoch 70/1000, Loss: 0.046810463070869446\n",
+      "Epoch 80/1000, Loss: 0.03961234167218208\n",
+      "Epoch 90/1000, Loss: 0.033818356692790985\n",
+      "Epoch 100/1000, Loss: 0.02865622565150261\n",
+      "Epoch 110/1000, Loss: 0.023877572268247604\n",
+      "Epoch 120/1000, Loss: 0.019604215398430824\n",
+      "Epoch 130/1000, Loss: 0.01610736735165119\n",
+      "Epoch 140/1000, Loss: 0.01334200520068407\n",
+      "Epoch 150/1000, Loss: 0.011029877699911594\n",
+      "Epoch 160/1000, Loss: 0.009049472399055958\n",
+      "Epoch 170/1000, Loss: 0.007442420814186335\n",
+      "Epoch 180/1000, Loss: 0.0061035449616611\n",
+      "Epoch 190/1000, Loss: 0.004539611749351025\n",
+      "Epoch 200/1000, Loss: 0.0030651914421468973\n",
+      "Epoch 210/1000, Loss: 0.0022714021615684032\n",
+      "Epoch 220/1000, Loss: 0.001738564227707684\n",
+      "Epoch 230/1000, Loss: 0.0013824186753481627\n",
+      "Epoch 240/1000, Loss: 0.0011372618610039353\n",
+      "Epoch 250/1000, Loss: 0.0009611304849386215\n",
+      "Epoch 260/1000, Loss: 0.0008317003957927227\n",
+      "Epoch 270/1000, Loss: 0.0007334426045417786\n",
+      "Epoch 280/1000, Loss: 0.0006564902723766863\n",
+      "Epoch 290/1000, Loss: 0.0005941776908002794\n",
+      "Epoch 300/1000, Loss: 0.0005428834119811654\n",
+      "Epoch 310/1000, Loss: 0.0005009892047382891\n",
+      "Epoch 320/1000, Loss: 0.00046646010014228523\n",
+      "Epoch 330/1000, Loss: 0.00043750536860898137\n",
+      "Epoch 340/1000, Loss: 0.0004131169698666781\n",
+      "Epoch 350/1000, Loss: 0.0003923749318346381\n",
+      "Epoch 360/1000, Loss: 0.00037453131517395377\n",
+      "Epoch 370/1000, Loss: 0.0003590169653762132\n",
+      "Epoch 380/1000, Loss: 0.0003454721299931407\n",
+      "Epoch 390/1000, Loss: 0.00033352847094647586\n",
+      "Epoch 400/1000, Loss: 0.0003230379370506853\n",
+      "Epoch 410/1000, Loss: 0.00031372407102026045\n",
+      "Epoch 420/1000, Loss: 0.00030547339702025056\n",
+      "Epoch 430/1000, Loss: 0.0002980876306537539\n",
+      "Epoch 440/1000, Loss: 0.0002914170909207314\n",
+      "Epoch 450/1000, Loss: 0.00028551131254062057\n",
+      "Epoch 460/1000, Loss: 0.000280180451227352\n",
+      "Epoch 470/1000, Loss: 0.00027529962244443595\n",
+      "Epoch 480/1000, Loss: 0.00027088262140750885\n",
+      "Epoch 490/1000, Loss: 0.00026690459344536066\n",
+      "Epoch 500/1000, Loss: 0.0002632274990901351\n",
+      "Epoch 510/1000, Loss: 0.00025982430088333786\n",
+      "Epoch 520/1000, Loss: 0.000256663013715297\n",
+      "Epoch 530/1000, Loss: 0.00025376983103342354\n",
+      "Epoch 540/1000, Loss: 0.0002510569174773991\n",
+      "Epoch 550/1000, Loss: 0.0002485134173184633\n",
+      "Epoch 560/1000, Loss: 0.0002461685216985643\n",
+      "Epoch 570/1000, Loss: 0.00024397078959736973\n",
+      "Epoch 580/1000, Loss: 0.00024182727793231606\n",
+      "Epoch 590/1000, Loss: 0.0002398582291789353\n",
+      "Epoch 600/1000, Loss: 0.00023796758614480495\n",
+      "Epoch 610/1000, Loss: 0.00023617268016096205\n",
+      "Epoch 620/1000, Loss: 0.00023440059158019722\n",
+      "Epoch 630/1000, Loss: 0.00023271011014003307\n",
+      "Epoch 640/1000, Loss: 0.00023108486493583769\n",
+      "Epoch 650/1000, Loss: 0.00022952101426199079\n",
+      "Epoch 660/1000, Loss: 0.00022804134641774\n",
+      "Epoch 670/1000, Loss: 0.00022659693786408752\n",
+      "Epoch 680/1000, Loss: 0.00022519213962368667\n",
+      "Epoch 690/1000, Loss: 0.0002238261658931151\n",
+      "Epoch 700/1000, Loss: 0.0002225149655714631\n",
+      "Epoch 710/1000, Loss: 0.000221233261981979\n",
+      "Epoch 720/1000, Loss: 0.00022013885609339923\n",
+      "Epoch 730/1000, Loss: 0.0002189427614212036\n",
+      "Epoch 740/1000, Loss: 0.00021769681188743562\n",
+      "Epoch 750/1000, Loss: 0.00021648130496032536\n",
+      "Epoch 760/1000, Loss: 0.00021531064703594893\n",
+      "Epoch 770/1000, Loss: 0.00021418495452962816\n",
+      "Epoch 780/1000, Loss: 0.0002131147193722427\n",
+      "Epoch 790/1000, Loss: 0.00021202574134804308\n",
+      "Epoch 800/1000, Loss: 0.0002110681962221861\n",
+      "Epoch 810/1000, Loss: 0.00021014301455579698\n",
+      "Epoch 820/1000, Loss: 0.0002092804352287203\n",
+      "Epoch 830/1000, Loss: 0.00020846931147389114\n",
+      "Epoch 840/1000, Loss: 0.00020768567628692836\n",
+      "Epoch 850/1000, Loss: 0.00020691761164925992\n",
+      "Epoch 860/1000, Loss: 0.00020612987282220274\n",
+      "Epoch 870/1000, Loss: 0.00020533577480819076\n",
+      "Epoch 880/1000, Loss: 0.00020457926439121366\n",
+      "Epoch 890/1000, Loss: 0.00020382019283715636\n",
+      "Epoch 900/1000, Loss: 0.00020311155822128057\n",
+      "Epoch 910/1000, Loss: 0.00020234761177562177\n",
+      "Epoch 920/1000, Loss: 0.00020164126181043684\n",
+      "Epoch 930/1000, Loss: 0.00020095478976145387\n",
+      "Epoch 940/1000, Loss: 0.0002003153640544042\n",
+      "Epoch 950/1000, Loss: 0.00019972550217062235\n",
+      "Epoch 960/1000, Loss: 0.00019920482009183615\n",
+      "Epoch 970/1000, Loss: 0.0001986794959520921\n",
+      "Epoch 980/1000, Loss: 0.00019817189604509622\n",
+      "Epoch 990/1000, Loss: 0.00019766329205594957\n",
+      "Epoch 1000/1000, Loss: 0.00019715774396900088\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Neural network V3\n",
+    "model_v3 = NeuralNetworkV3(input_size, hidden_size).to(device)\n",
+    "criterion_v3 = nn.BCELoss()\n",
+    "optimizer_v3 = optim.Adam(model_v3.parameters(), lr=learning_rate, weight_decay=weight_decay)\n",
+    "\n",
+    "# Train the model\n",
+    "train(model_v3, X_train, y_train, criterion_v3, optimizer_v3, epochs)\n",
+    "\n",
+    "# Evaluate the model\n",
+    "cm_v3, cr_v3, acc_v3 = evaluate(model_v3, X_test, y_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:08:02.306988400Z",
+     "start_time": "2024-06-08T16:07:58.364980300Z"
+    }
+   },
+   "id": "1647870c14f1d6eb"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot confusion matrix\n",
+    "plot_confusion_matrix(cm_v3, ['Benign', 'Malignant'], title='Confusion matrix - Neural Network V3')"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:08:05.178318100Z",
+     "start_time": "2024-06-08T16:08:04.939888900Z"
+    }
+   },
+   "id": "352c5a8e9037cbf9"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot classification report\n",
+    "plot_classification_report(cr_v3)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:08:10.217195900Z",
+     "start_time": "2024-06-08T16:08:09.908834700Z"
+    }
+   },
+   "id": "e7870deb507d0eab"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Neural network V4"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "d32e69740aecec91"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/1000, Loss: 0.4186047613620758\n",
+      "Epoch 20/1000, Loss: 0.20972707867622375\n",
+      "Epoch 30/1000, Loss: 0.14643631875514984\n",
+      "Epoch 40/1000, Loss: 0.1106308326125145\n",
+      "Epoch 50/1000, Loss: 0.09039844572544098\n",
+      "Epoch 60/1000, Loss: 0.07973706722259521\n",
+      "Epoch 70/1000, Loss: 0.07261230796575546\n",
+      "Epoch 80/1000, Loss: 0.06730187684297562\n",
+      "Epoch 90/1000, Loss: 0.06239919736981392\n",
+      "Epoch 100/1000, Loss: 0.05727291852235794\n",
+      "Epoch 110/1000, Loss: 0.05158916860818863\n",
+      "Epoch 120/1000, Loss: 0.04558803513646126\n",
+      "Epoch 130/1000, Loss: 0.03927084803581238\n",
+      "Epoch 140/1000, Loss: 0.03285034000873566\n",
+      "Epoch 150/1000, Loss: 0.026732975617051125\n",
+      "Epoch 160/1000, Loss: 0.021154126152396202\n",
+      "Epoch 170/1000, Loss: 0.016432005912065506\n",
+      "Epoch 180/1000, Loss: 0.012630755081772804\n",
+      "Epoch 190/1000, Loss: 0.009745683521032333\n",
+      "Epoch 200/1000, Loss: 0.007611896842718124\n",
+      "Epoch 210/1000, Loss: 0.0060510095208883286\n",
+      "Epoch 220/1000, Loss: 0.004891632590442896\n",
+      "Epoch 230/1000, Loss: 0.004030665848404169\n",
+      "Epoch 240/1000, Loss: 0.003379524452611804\n",
+      "Epoch 250/1000, Loss: 0.002879904117435217\n",
+      "Epoch 260/1000, Loss: 0.002489611506462097\n",
+      "Epoch 270/1000, Loss: 0.002184198470786214\n",
+      "Epoch 280/1000, Loss: 0.0019437369192019105\n",
+      "Epoch 290/1000, Loss: 0.0017541276756674051\n",
+      "Epoch 300/1000, Loss: 0.0016026693629100919\n",
+      "Epoch 310/1000, Loss: 0.0014796099858358502\n",
+      "Epoch 320/1000, Loss: 0.0013786517083644867\n",
+      "Epoch 330/1000, Loss: 0.0012941397726535797\n",
+      "Epoch 340/1000, Loss: 0.0012196070747449994\n",
+      "Epoch 350/1000, Loss: 0.0011414645705372095\n",
+      "Epoch 360/1000, Loss: 0.001061757793650031\n",
+      "Epoch 370/1000, Loss: 0.0009867347544059157\n",
+      "Epoch 380/1000, Loss: 0.0009273262694478035\n",
+      "Epoch 390/1000, Loss: 0.0008805892430245876\n",
+      "Epoch 400/1000, Loss: 0.0008431114838458598\n",
+      "Epoch 410/1000, Loss: 0.0008109930204227567\n",
+      "Epoch 420/1000, Loss: 0.0007825929205864668\n",
+      "Epoch 430/1000, Loss: 0.0007562871905975044\n",
+      "Epoch 440/1000, Loss: 0.0007321131997741759\n",
+      "Epoch 450/1000, Loss: 0.0007092245505191386\n",
+      "Epoch 460/1000, Loss: 0.0006881365552544594\n",
+      "Epoch 470/1000, Loss: 0.0006688928115181625\n",
+      "Epoch 480/1000, Loss: 0.0006500301533378661\n",
+      "Epoch 490/1000, Loss: 0.0006336761871352792\n",
+      "Epoch 500/1000, Loss: 0.0006172554567456245\n",
+      "Epoch 510/1000, Loss: 0.00060228758957237\n",
+      "Epoch 520/1000, Loss: 0.0005888384766876698\n",
+      "Epoch 530/1000, Loss: 0.0005763943772763014\n",
+      "Epoch 540/1000, Loss: 0.0005643281037919223\n",
+      "Epoch 550/1000, Loss: 0.0005541218561120331\n",
+      "Epoch 560/1000, Loss: 0.0005427465075626969\n",
+      "Epoch 570/1000, Loss: 0.0005325390957295895\n",
+      "Epoch 580/1000, Loss: 0.0005224572960287333\n",
+      "Epoch 590/1000, Loss: 0.0005137791740708053\n",
+      "Epoch 600/1000, Loss: 0.0005050148465670645\n",
+      "Epoch 610/1000, Loss: 0.0004971114685758948\n",
+      "Epoch 620/1000, Loss: 0.0004892157157883048\n",
+      "Epoch 630/1000, Loss: 0.00048245518701151013\n",
+      "Epoch 640/1000, Loss: 0.0004754861583933234\n",
+      "Epoch 650/1000, Loss: 0.0004669078625738621\n",
+      "Epoch 660/1000, Loss: 0.0004601963155437261\n",
+      "Epoch 670/1000, Loss: 0.00045247498201206326\n",
+      "Epoch 680/1000, Loss: 0.00044596134102903306\n",
+      "Epoch 690/1000, Loss: 0.0004407193046063185\n",
+      "Epoch 700/1000, Loss: 0.000434816291090101\n",
+      "Epoch 710/1000, Loss: 0.00042790695442818105\n",
+      "Epoch 720/1000, Loss: 0.0004230188496876508\n",
+      "Epoch 730/1000, Loss: 0.00041854308801703155\n",
+      "Epoch 740/1000, Loss: 0.0004127133288420737\n",
+      "Epoch 750/1000, Loss: 0.00040834766696207225\n",
+      "Epoch 760/1000, Loss: 0.0004034344747196883\n",
+      "Epoch 770/1000, Loss: 0.00039839293458499014\n",
+      "Epoch 780/1000, Loss: 0.0003941936884075403\n",
+      "Epoch 790/1000, Loss: 0.00039072500658221543\n",
+      "Epoch 800/1000, Loss: 0.0003858723503071815\n",
+      "Epoch 810/1000, Loss: 0.0003812974609900266\n",
+      "Epoch 820/1000, Loss: 0.00037719475221820176\n",
+      "Epoch 830/1000, Loss: 0.0003737532824743539\n",
+      "Epoch 840/1000, Loss: 0.00036979030119255185\n",
+      "Epoch 850/1000, Loss: 0.00036644612555392087\n",
+      "Epoch 860/1000, Loss: 0.0003625146928243339\n",
+      "Epoch 870/1000, Loss: 0.000359336263500154\n",
+      "Epoch 880/1000, Loss: 0.00035612270585261285\n",
+      "Epoch 890/1000, Loss: 0.00035236674011684954\n",
+      "Epoch 900/1000, Loss: 0.0003493966069072485\n",
+      "Epoch 910/1000, Loss: 0.0003470622468739748\n",
+      "Epoch 920/1000, Loss: 0.00034316032542847097\n",
+      "Epoch 930/1000, Loss: 0.00034029941889457405\n",
+      "Epoch 940/1000, Loss: 0.00033748531132005155\n",
+      "Epoch 950/1000, Loss: 0.0003346360463183373\n",
+      "Epoch 960/1000, Loss: 0.00033203166094608605\n",
+      "Epoch 970/1000, Loss: 0.0003288303851149976\n",
+      "Epoch 980/1000, Loss: 0.0003261156671214849\n",
+      "Epoch 990/1000, Loss: 0.000323760905303061\n",
+      "Epoch 1000/1000, Loss: 0.0003211983712390065\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Neural network V4\n",
+    "model_v4 = NeuralNetworkV4(input_size, hidden_size).to(device)\n",
+    "criterion_v4 = nn.BCELoss()\n",
+    "optimizer_v4 = optim.Adam(model_v4.parameters(), lr=learning_rate, weight_decay=weight_decay)\n",
+    "\n",
+    "# Train the model\n",
+    "train(model_v4, X_train, y_train, criterion_v4, optimizer_v4, epochs)\n",
+    "\n",
+    "# Evaluate the model\n",
+    "cm_v4, cr_v4, acc_v4 = evaluate(model_v4, X_test, y_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:26:02.339239600Z",
+     "start_time": "2024-06-08T16:25:56.963561200Z"
+    }
+   },
+   "id": "b85c2f139ab4eeca"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot confusion matrix\n",
+    "plot_confusion_matrix(cm_v4, ['Benign', 'Malignant'], title='Confusion matrix - Neural Network V4')"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:26:02.503093100Z",
+     "start_time": "2024-06-08T16:26:02.331956800Z"
+    }
+   },
+   "id": "73954f54243ecb26"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot classification report\n",
+    "plot_classification_report(cr_v4)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:26:02.703936200Z",
+     "start_time": "2024-06-08T16:26:02.503093100Z"
+    }
+   },
+   "id": "7edf4cb0b06ec6"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#### Neural network V5"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "dff009e888af5074"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 10/1000, Loss: 0.6472257971763611\n",
+      "Epoch 20/1000, Loss: 0.5392731428146362\n",
+      "Epoch 30/1000, Loss: 0.36916524171829224\n",
+      "Epoch 40/1000, Loss: 0.21396635472774506\n",
+      "Epoch 50/1000, Loss: 0.13106301426887512\n",
+      "Epoch 60/1000, Loss: 0.09312008321285248\n",
+      "Epoch 70/1000, Loss: 0.07527194172143936\n",
+      "Epoch 80/1000, Loss: 0.06560871005058289\n",
+      "Epoch 90/1000, Loss: 0.05922595039010048\n",
+      "Epoch 100/1000, Loss: 0.054361775517463684\n",
+      "Epoch 110/1000, Loss: 0.050068166106939316\n",
+      "Epoch 120/1000, Loss: 0.04590252414345741\n",
+      "Epoch 130/1000, Loss: 0.042265865951776505\n",
+      "Epoch 140/1000, Loss: 0.03903531655669212\n",
+      "Epoch 150/1000, Loss: 0.03611545264720917\n",
+      "Epoch 160/1000, Loss: 0.03336109220981598\n",
+      "Epoch 170/1000, Loss: 0.030720891430974007\n",
+      "Epoch 180/1000, Loss: 0.028099115937948227\n",
+      "Epoch 190/1000, Loss: 0.02529078908264637\n",
+      "Epoch 200/1000, Loss: 0.022276364266872406\n",
+      "Epoch 210/1000, Loss: 0.01945570483803749\n",
+      "Epoch 220/1000, Loss: 0.016959620639681816\n",
+      "Epoch 230/1000, Loss: 0.014633278362452984\n",
+      "Epoch 240/1000, Loss: 0.012433870695531368\n",
+      "Epoch 250/1000, Loss: 0.01063645537942648\n",
+      "Epoch 260/1000, Loss: 0.009215538389980793\n",
+      "Epoch 270/1000, Loss: 0.008075335994362831\n",
+      "Epoch 280/1000, Loss: 0.007146317046135664\n",
+      "Epoch 290/1000, Loss: 0.006382191088050604\n",
+      "Epoch 300/1000, Loss: 0.005759004037827253\n",
+      "Epoch 310/1000, Loss: 0.005265630315989256\n",
+      "Epoch 320/1000, Loss: 0.004859541077166796\n",
+      "Epoch 330/1000, Loss: 0.0045250700786709785\n",
+      "Epoch 340/1000, Loss: 0.00425321189686656\n",
+      "Epoch 350/1000, Loss: 0.0040284693241119385\n",
+      "Epoch 360/1000, Loss: 0.0038447484839707613\n",
+      "Epoch 370/1000, Loss: 0.0036921321880072355\n",
+      "Epoch 380/1000, Loss: 0.003561016172170639\n",
+      "Epoch 390/1000, Loss: 0.003450624644756317\n",
+      "Epoch 400/1000, Loss: 0.003364400239661336\n",
+      "Epoch 410/1000, Loss: 0.0032908162102103233\n",
+      "Epoch 420/1000, Loss: 0.003222778672352433\n",
+      "Epoch 430/1000, Loss: 0.003165710251778364\n",
+      "Epoch 440/1000, Loss: 0.0031129783019423485\n",
+      "Epoch 450/1000, Loss: 0.0030633530113846064\n",
+      "Epoch 460/1000, Loss: 0.0029811717104166746\n",
+      "Epoch 470/1000, Loss: 0.0028529497794806957\n",
+      "Epoch 480/1000, Loss: 0.0026854067109525204\n",
+      "Epoch 490/1000, Loss: 0.0025055729784071445\n",
+      "Epoch 500/1000, Loss: 0.002334937220439315\n",
+      "Epoch 510/1000, Loss: 0.002182029653340578\n",
+      "Epoch 520/1000, Loss: 0.0020450232550501823\n",
+      "Epoch 530/1000, Loss: 0.0019291980424895883\n",
+      "Epoch 540/1000, Loss: 0.0018309173174202442\n",
+      "Epoch 550/1000, Loss: 0.0017435038462281227\n",
+      "Epoch 560/1000, Loss: 0.0016699342522770166\n",
+      "Epoch 570/1000, Loss: 0.0016051153652369976\n",
+      "Epoch 580/1000, Loss: 0.0015472021186724305\n",
+      "Epoch 590/1000, Loss: 0.0014925338327884674\n",
+      "Epoch 600/1000, Loss: 0.0014427873538807034\n",
+      "Epoch 610/1000, Loss: 0.0013984435936436057\n",
+      "Epoch 620/1000, Loss: 0.0013581964885815978\n",
+      "Epoch 630/1000, Loss: 0.00132227991707623\n",
+      "Epoch 640/1000, Loss: 0.0012905021430924535\n",
+      "Epoch 650/1000, Loss: 0.0012572426348924637\n",
+      "Epoch 660/1000, Loss: 0.001225507934577763\n",
+      "Epoch 670/1000, Loss: 0.0012008383637294173\n",
+      "Epoch 680/1000, Loss: 0.001180665334686637\n",
+      "Epoch 690/1000, Loss: 0.001158036757260561\n",
+      "Epoch 700/1000, Loss: 0.0011395757319405675\n",
+      "Epoch 710/1000, Loss: 0.0011222346220165491\n",
+      "Epoch 720/1000, Loss: 0.0011062605772167444\n",
+      "Epoch 730/1000, Loss: 0.0010908363619819283\n",
+      "Epoch 740/1000, Loss: 0.0010754970135167241\n",
+      "Epoch 750/1000, Loss: 0.0010610275203362107\n",
+      "Epoch 760/1000, Loss: 0.0010471524437889457\n",
+      "Epoch 770/1000, Loss: 0.0010340394219383597\n",
+      "Epoch 780/1000, Loss: 0.0010215329239144921\n",
+      "Epoch 790/1000, Loss: 0.0010098188649863005\n",
+      "Epoch 800/1000, Loss: 0.0009981722105294466\n",
+      "Epoch 810/1000, Loss: 0.000987424748018384\n",
+      "Epoch 820/1000, Loss: 0.0009770964970812201\n",
+      "Epoch 830/1000, Loss: 0.0009671879815869033\n",
+      "Epoch 840/1000, Loss: 0.000957623531576246\n",
+      "Epoch 850/1000, Loss: 0.00094812415773049\n",
+      "Epoch 860/1000, Loss: 0.0009392902138642967\n",
+      "Epoch 870/1000, Loss: 0.0009308967855758965\n",
+      "Epoch 880/1000, Loss: 0.0009222882217727602\n",
+      "Epoch 890/1000, Loss: 0.0009139023022726178\n",
+      "Epoch 900/1000, Loss: 0.0009058943251147866\n",
+      "Epoch 910/1000, Loss: 0.0008985912427306175\n",
+      "Epoch 920/1000, Loss: 0.0008904503774829209\n",
+      "Epoch 930/1000, Loss: 0.0008828166173771024\n",
+      "Epoch 940/1000, Loss: 0.0008756622555665672\n",
+      "Epoch 950/1000, Loss: 0.000868525356054306\n",
+      "Epoch 960/1000, Loss: 0.0008616363047622144\n",
+      "Epoch 970/1000, Loss: 0.0008551458013243973\n",
+      "Epoch 980/1000, Loss: 0.0008486591395922005\n",
+      "Epoch 990/1000, Loss: 0.0008415335905738175\n",
+      "Epoch 1000/1000, Loss: 0.0008350368589162827\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Neural network V5\n",
+    "model_v5 = NeuralNetworkV5(input_size, hidden_size).to(device)\n",
+    "criterion_v5 = nn.BCELoss()\n",
+    "optimizer_v5 = optim.Adam(model_v5.parameters(), lr=learning_rate, weight_decay=weight_decay)\n",
+    "\n",
+    "# Train the model\n",
+    "train(model_v5, X_train.unsqueeze(1), y_train, criterion_v5, optimizer_v5, epochs)\n",
+    "\n",
+    "# Evaluate the model\n",
+    "cm_v5, cr_v5, acc_v5 = evaluate(model_v5, X_test.unsqueeze(1), y_test)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:26:18.741105800Z",
+     "start_time": "2024-06-08T16:26:14.401969800Z"
+    }
+   },
+   "id": "ea7a761090fe566a"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot confusion matrix\n",
+    "plot_confusion_matrix(cm_v5, ['Benign', 'Malignant'], title='Confusion matrix - Neural Network V5')"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:26:18.901207300Z",
+     "start_time": "2024-06-08T16:26:18.741105800Z"
+    }
+   },
+   "id": "c50f0edf9c024c66"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 2 Axes>",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAx0AAAIhCAYAAAArVtfxAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAACHmUlEQVR4nOzdeXxN1/7/8dfJHIkYgpha8xBBRBBDDC1atCpV7XXba+41q5aiKKLGolpDaypt9ap5aCmq5poVMRRtxNCgCJIQmZPz+8PX+eU02kqak30q72cf+1Fn7XXW/uzIlvPJZ629TWaz2YyIiIiIiIiNOBgdgIiIiIiIPN6UdIiIiIiIiE0p6RAREREREZtS0iEiIiIiIjalpENERERERGxKSYeIiIiIiNiUkg4REREREbEpJR0iIiIiImJTSjpERP4B9BzXP6avjYiI/VPSISJ25eTJkwwZMoRmzZpRs2ZNWrRowahRo4iMjLTqV6VKFWbNmpWrsc2aNYsqVapYXsfFxdG7d2/8/f2pW7cuFy9epEqVKqxZsyZHj7tt2zaGDRtmeX3w4EGqVKnCwYMHc/Q4/zR37txh6NCh/Pjjj0aHIiIif8HJ6ABERB5YsmQJEydOJCgoiMGDB1OsWDEuXbrEwoUL2bJlC1988QVVq1Y1LL6XX36Zxo0bW16vW7eOHTt2MHr0aCpVqkTJkiVZvnw5Tz75ZI4e9/PPP7d67efnx/Lly6lYsWKOHuef5syZM3z99de89NJLRociIiJ/QUmHiNiFI0eOMGHCBF577TVGjhxpaQ8KCqJFixaEhIQwYsSIHK8iZEXx4sUpXry45XVMTAwAr776KiaTCYBatWrZPA5PT89cOY6IiEhO0fQqEbELCxcuJH/+/AwaNCjTvsKFC/POO+/QvHlz4uPjH/r+s2fP0r9/f+rXr4+fnx+NGzdm/PjxJCYmWvrs3buXV155hYCAAOrWrUufPn2IiIiw7P/111/p3bs3QUFB+Pv7869//Ytdu3ZZ9mecXtWpUyfL9K6qVavyzjvvcPny5UzTq86fP0///v2pV68edevWpVevXlbHvHz5MkOHDiU4OBg/Pz8aNGjA0KFDiY6Othzn0KFDHDp0yDKl6mHTq06ePEmPHj0ICgqidu3a9O7dm/DwcMv+B+/Zv38/3bt3x9/fn0aNGjF16lTS0tL+8O9lzZo1VKtWjZUrV9KoUSPq1avHuXPnANi6dSvt27enRo0aNGrUiPHjx1v9/cyaNYunn36aHTt20KpVK/z9/XnllVcyTQu7ceMGw4cPp2nTptSsWZMOHTqwbds2qz5VqlRh9uzZtG/fnpo1azJ79mw6d+4MQOfOnenUqdMfnoOIiBhPSYeIGM5sNrNnzx4aNGiAu7v7Q/u0adOGfv36kS9fvkz7bty4wWuvvUZCQgKTJ09mwYIFPPfcc3z55ZcsXrwYgMjISPr27Uv16tWZM2cOEyZM4MKFC/Ts2ZP09HTS09Pp1asXCQkJTJkyhU8++YSCBQvSp08fLl26lOmYY8aMoUOHDgAsX76cvn37Zupz/fp1/vWvf3Hx4kVCQ0OZOnUqN2/epEuXLsTExJCQkEDnzp2JiIhgzJgxLFy4kM6dO/Ptt9/y4YcfWo5TrVo1qlWrxvLly/Hz88t0nAMHDvDvf/8bgIkTJzJ+/Hh+++03OnbsaJXgALz99tsEBgYyd+5cnn/+eT799FNWrlz5Z389pKWlsWjRIiZMmMDw4cOpUKEC69evp1+/fpQvX56PP/6Y/v37880339C3b1+rhd23b99m2LBhvPrqq8yYMQM3Nzd69OjBmTNnALh58yYdOnTgxx9/5K233mLWrFmUKlWKfv368c0331jFMXfuXNq2bcvMmTNp0aIFo0ePBmD06NGMGTPmT89BRESMpelVImK46OhokpKSKF26dLbe/8svv+Dr68uMGTPw9PQEoGHDhuzdu5eDBw/Ss2dPTpw4QWJiIr169cLHxwe4P11q27ZtxMfHk5CQwPnz5+nbty9NmzYFsPxGPTk5OdMxK1asaJlq9WCq0+XLl636fP755yQnJ/PZZ59RtGhR4H5V5N///jfHjx+nWLFiFC9enPfff58nnngCgPr163P8+HEOHTpkOc6Dc/qjKVUffPABZcqUYf78+Tg6OgIQHBxMy5YtmTlzJjNmzLD0ffnll+nXrx8ADRo0YOvWrezcuZOOHTv+6de4d+/eNGvWDLifJE6bNo3GjRszbdo0S5+yZcvStWtXdu3aZembkJBAaGgoISEhlvNr0aIF8+fP58MPP+Szzz7j9u3bfPfdd5QqVQqApk2b0rVrV6ZMmcLzzz+Pg8P934/VqVOHbt26WY4XGxtr+Rrl9fUtIiL2TkmHiBjuwQflP5vm82eCg4MJDg4mJSWFc+fOcenSJX755Rdu375NwYIFAfD398fV1ZUOHTrQqlUrmjRpQlBQEDVr1gTAw8ODihUrMmrUKPbs2UNwcDBNmjRh+PDh2T6vI0eOUKtWLUvCAfcTnR07dlhef/XVV6Snp3Px4kUuXbrEuXPnOH/+PKmpqY90jPj4eE6ePEn//v0tX0cALy8vnnrqKavpYQABAQFWr4sXL/6HU9Yy8vX1tfz5/PnzXLt2jV69elnFWbduXTw9Pdm7d68l6XBycuL555+39HFzc6NJkybs3r0bgEOHDhEQEGBJOB544YUXGD58OOfPn7ckFBljEBGRfxYlHSJiuAIFCuDh4cHVq1f/sE98fDwpKSkUKFAg07709HSmT5/OkiVLiI+Pp0SJEtSsWRNXV1dLn9KlS/O///2P+fPns2rVKhYvXoyXlxevvvoqb775JiaTiUWLFjFnzhy+//571q1bh7OzMy1atGDs2LEPPe5fiYmJ+cvqzWeffcbcuXOJiYmhSJEiVK9eHXd3d+7evftIx7h79y5ms5kiRYpk2lekSJFM47i5uVm9dnBweKTnXGSc1vZgAf3YsWMZO3Zspr43btywisHJyfpHjbe3t2WM2NhYS5Xn97HD/dviPiwGERH5Z1HSISJ2ITg4mIMHD5KUlGSVLDywYsUK3n//fVatWpVpXcP8+fP5/PPPGTt2LM888wz58+cHsKy5eCDjdKkjR46wfPly5s6dS9WqVWndujU+Pj6EhoYyZswYzp49y+bNm1mwYAGFChXK1pqB/Pnzc/v27Uzt+/fvp3Tp0oSFhTF58mSGDBlC+/btKVy4MAADBw7k5MmTj3wMk8nEzZs3M+2LioqyVHpykpeXFwBDhw6lXr16mfZnTNAeJBcZ3bx5E29vb0vfqKioTH0etBUqVCgnQhYREYNpIbmI2IXu3bsTExPDRx99lGlfVFQUixYtomLFig9dSH3kyBEqVqzISy+9ZEk4rl+/zi+//EJ6ejpwf33FU089RXJyMi4uLjRo0IBx48YBcPXqVY4dO0bDhg05ceIEJpMJX19f3nrrLSpXrvynFZg/U6dOHY4fP26VeNy6dYvXX3+dXbt2ceTIEby8vHj99dctCce9e/c4cuSIJW7AsqbhYfLly0f16tXZtGmT1fS0u3fvsnPnTgIDA7MV+58pX7483t7eXL58mRo1alg2Hx8fPvjgA06fPm3pm5iYyA8//GD1evfu3TRo0AC4PyXr2LFjXLlyxeoY33zzDUWLFqVMmTJ/GEfG6WQiImLfVOkQEbtQq1YtBg4cyEcffURERAQhISEUKlSI8PBwFi5cSFJS0kMTErhfwfjkk0+YP38+tWrV4tKlS8ybN4/k5GQSEhKA+wuYp02bRr9+/fjPf/6Do6Mjy5Ytw8XFhaeeeopSpUrh5ubG0KFDGTBgAEWKFGHfvn2cOXPGcmvWrOratSvr1q3j9ddfp1evXjg7OzNnzhyKFy9O27Zt2bZtG0uXLmXy5Mk89dRT3Lhxg4ULF3Lz5k2raoGXlxfHjh1j//79VKtWLdNxBg8eTI8ePejZsyevvvoqKSkpzJ8/n+TkZMui8Zzk6OjIW2+9xejRo3F0dOSpp57izp07fPLJJ1y/fj1TYjh8+HDefPNNvL29WbhwIfHx8fTp0weAbt268c0339C1a1f69+9PwYIFWbduHQcOHGDixIl/mnA9SDB37txJgQIFDH1wpIiI/DklHSJiN/r06UO1atUsTyaPjY2lRIkSNGvWjN69e1OiRImHvq9Xr15ER0ezePFiPv74Y0qUKEG7du0wmUzMmzePO3fuULVqVebOncvHH3/MoEGDSEtLo3r16ixatIjy5csDsGjRIj744AMmTJjAnTt3KFu2LO+99x7t27fP1vmUKFGCr776iqlTp/LOO+/g4uJCUFAQH374IQUKFODFF1/k8uXLrF69mq+++gofHx+aNm3Kq6++yqhRo4iIiKBChQq89tprnDp1iv/+979MmjSJYsWKWR2nQYMGfPbZZ8ycOZNBgwbh4uJCnTp1eP/996lUqVK2Yv8rL7/8Mh4eHnz66acsX76cfPnyUbt2baZNm5ZpjUZoaCgTJ07k9u3b1K5dm6VLl1oqGEWLFmXp0qV88MEHjB8/npSUFKpWrconn3xC8+bN/zSGSpUq8fzzz7NkyRJ++OEHNmzYYJNzFRGRv89kfpQVhCIiIlk0a9YsZs+ezc8//2x0KCIiYjCt6RAREREREZtS0iEiIiIiIjal6VUiIiIiImJTqnSIiIiIiIhNKekQERERERGbUtIhIiIiIiI2paRDRERERERs6rF8OKB7QH+jQxARERGRP5FwbLbRIfwhW36WtOfztiVVOkRERERExKYey0qHiIiIiEi2mfR7+ZympENEREREJCOTyegIHjtK40RERERExKZU6RARERERyUjTq3KcvqIiIiIiImJTqnSIiIiIiGSkNR05TpUOERERERGxKVU6REREREQy0pqOHKevqIiIiIiI2JQqHSIiIiIiGWlNR45T0iEiIiIikpGmV+U4fUVFRERERMSmVOkQEREREclI06tynCodIiIiIiJiU6p0iIiIiIhkpDUdOU5fURERERERsSlVOkREREREMtKajhynSoeIiIiIiNiUKh0iIiIiIhlpTUeOU9IhIiIiIpKRplflOKVxIiIiIiJiU6p0iIiIiIhkpOlVOU5fURERERERsSlVOkREREREMlKlI8fpKyoiIiIiIjZlN5WOS5cucerUKVJSUjLtCwkJyf2ARERERCRvctDdq3KaXSQdn376KdOmTaNAgQJ4eHhY7TOZTEo6RERERET+wewi6Vi0aBFDhgyhR48eRociIiIiInmd1nTkOLtIOpKSknjmmWeMDkNERERERA8HtAG7SOPatm3LV199hdlsNjoUERERERHJYXZR6YiLi2PVqlVs2LCB0qVL4+zsbLV/8eLFBkUmIiIiInmOplflOLtIOsqWLUvv3r2NDkNERERERGzALpKO/v37Gx2CiIiIiMh9WtOR4+wi6ejUqROmh/zlmkwmnJ2dKVq0KK1bt6ZJkyYGRCciIiIiIn+HXUxYq1u3LkePHqVo0aK0bNmSFi1aULx4cY4cOUKxYsVwd3dn0KBBrF692uhQRURERORxZ3Kw3ZZH2UWlY//+/QwfPpzXXnvNqr1OnTp8/fXXLFmyhPr16zN9+nReeuklg6IUEREREZHssIt06/Tp0zRq1ChTe7169Th58iQA1atX57fffsvt0EREREQkrzGZbLflUXaRdFStWpX//e9/mZ7T8dVXX1GxYkUATp48SfHixY0IT0RERETyEk2vynF2Mb1q1KhR/Pe//2Xnzp1Uq1YNgDNnzhAXF8fcuXM5cuQIQ4YMYfTo0QZHKg/j6uLER8NfIaR5LRISU5jx5TZmfLn9oX2b16/KxLdCKF+6KIdOXuDNSSsIv3QDgIRjsx/6nh6jFvPVhkM2i1/ECLpuRLJH147IP5NdJB3Vq1fn+++/59tvv+WXX37B0dGRxo0b89xzz5EvXz4uX77MihUrqFq1qtGhykNMeutFald7ktY9Z/JkicIseK8Tv/52m7Vbw6z6+ZYvztqZfZj62RaWbTxM15AGbJ7/BjVD3uNeQjJlWwy36j/gtafp8GxtNuw8kYtnI5I7dN2IZI+uHckVdjINKikpibFjx7Jlyxbc3Nzo3r073bt3f2jfPXv2MGXKFCIjI/H392f06NGUL18egCpVqjz0Pe+//z4hISF/eZzIyEhGjRpFWFgYJUuWZMSIEQQHB2fpXOwi6QDw9PTkX//610P3lS5dOpejkUeVz82FriENaNd/DmFnLxN29jK+X2yl97+aZvoB0PPlxhw4cZ5xc74FYOSMr2ndpDod29Rl4eq9XL9119K3TElv+v67KS+9OY87cYm5eUoiNqfrRiR7dO1IXjNlyhROnTrFF198wdWrVxk2bBglS5akVatWVv3Cw8Pp1asXPXv2pG3btqxatYouXbqwefNmPDw82LNnj1X/zz//nE2bNtG8efO/PI7ZbKZfv35UrlyZ1atXs3XrVvr378/GjRspWbLkI5+LYRPLmjdvTnR0NABPP/00zZs3/8NN7FfNKqVwdnLkwPHzlrZ9x85Tt3qZTM9eKVu6CIdPXrRq+yn8KkE1y2Uad3Sf59hx6Bd2HPzZJnGLGEnXjUj26NqRXGMHazri4+NZuXIlI0eOxM/Pj5YtW/L666+zZMmSTH2XLl1KQEAAAwcOpHz58gwZMoT8+fOzfv16AIoWLWrZEhMT+fLLLxk/fjz58+f/y+McOHCAyMhI3nvvPSpUqECvXr2oVatWlh9lYVilo3///nh4eAAwYMAAo8KQv6l4kQLcjLlHSmqape3G7Tu4u7ngXdCDm9Fx/7/91l1KFito9f7SxQtxOzbequ2J4oX4V+s6PNX1A5vGLmIUXTci2aNrR/KSs2fPkpqaSkBAgKUtMDCQuXPnkp6ejoPD/09gIiMjqVmzpuW1yWSicuXKhIWF0bFjR6txZ86cSYMGDWjYsOEjHef48eNUq1aNfPnyWe0PCwvL0vkYlnS8+OKLD/2z/LO4uzmTnJJq1ZaUfP+1q7P1t9eqLUdY9VEvVmw+wpZ9p+nYpi6B1cqw68dfrPp1CWnA0dO/cvjUJdsGL2IQXTci2aNrR3KNDdd0JCcnk5ycbNXm4uKCi4uLVVtUVBSFChWyai9SpAhJSUnExMRQuHBhq/br169bvf/atWsUKFDAqu3q1ats2LCBZcuWPfJxoqKiKFasmNU43t7eXLt2LUvnbRdrOu7cucOiRYs4efIkqampmW6du3jxYoMik7+SlJSKy+/+oXd1uf86PtH6gvp+3xkmzNvE0mk9cHJ0ZNePv7Dk24MU8HS36vdiiwA+XWU991DkcaLrRiR7dO3I42DevHnMnm1997T+/ftnmvmTkJCQKRF58Pr3SUvr1q3p27cvzz//PI0bN2b9+vWcPHmSoKAgq36rVq2ievXq+Pv7P/Jx/mj/72P4K3aRdAwdOpSTJ0/Stm1bPD09jQ5HsuBqVAxFCnrg6OhAWlo6AD7eXsQnJBNzNyFT/ykLv+Ojxdso4OlGVHQc/3u/O5eu3rbsL+1TkGoVSujuIfJY03Ujkj26diTX2PB5Gr169aRbt25Wbb//UA/g6uqa6YP9g9dubm5W7U2aNKFfv34MGDCAtLQ0goKCaNeuHXFxcVb9vvvuu0zTrf7qOK6ursTExGTa//sY/opdJB379u3jf//7n9VcNPlnOP7zZVJS0wiqUZZ9YfcX9jUMqMCR05cyVaxeaRVI3eplGTJtNVHRcbi5OtOkbiV6jv6fpU/dGmWJ/O02kdeic/U8RHKTrhuR7NG1I7nGhknHw6ZSPYyPjw/R0dGkpqbi5HT/I3tUVBRubm54eXll6t+nTx969OjB3bt38fb2ZuDAgZQqVcqy/7fffuPcuXOZbtL0V8fx8fHh3LlzVu+5efNmpilXf8UuHovo4+NjtRhG/jkSElP434ZDzBzZkcBqT9K2WU3e7NScj7/aCYCPd37cXJ0BCL90g9c7BNPuaX8qPFmULyZ25fK1GL7be9oyXrUKJTlzPmtzBEX+aXTdiGSPrh3JS3x9fXFycrJasH3kyBFq1KiR6XPzhg0bmDBhAi4uLnh7e5OYmMjBgwetplcdP36cEiVKZLrN7V8dx9/fn59++onExESr/RmnaD0Ku/ikP3ToUEJDQ9m9ezeXLl3i6tWrVpvYt2EfrObYmUg2LxjIR8NfYfzcb/l6+3EALm6dRIdnagNw7Ewkb0xczuRBL7JvyVAA2r8xx+q3U8W88xNzNz7zQUQeM7puRLJH147kCpPJdtsjcnd3JyQkhNDQUE6cOMHWrVtZtGgRnTt3Bu5XIx4kAmXLlmXZsmVs2bKFixcvMnjwYEqUKEGTJk0s44WHh1OhQoUsH6devXqUKFGC4cOHEx4ezvz58zlx4gQdOnTI2pfU/Pt6pAF+/6TxB/faNpvNmEwmzpw5k6Xx3AP651hsIiIiIpLzEo7N/utOBnF/YY7Nxk74ps+j901IIDQ0lC1btuDp6UmPHj3o2rUrcP8p45MmTaJ9+/YArF69mo8//piYmBgaNGjAmDFjrKZAjRkzhrt37zJ9+vQsHQfg0qVLjBw5kuPHj1OmTBlGjBhhueXuo7KLpOPKlSt/uj/jfLRHoaRDRERExL7ZddLRbp7Nxk74upfNxrZndjG9qlSpUpQqVYr4+HhOnz5NoUKFSE9Pp2TJkllOOERERERExL7Yxd2rYmNjGThwIIcOHQLu385rwoQJREZGMn/+fCUeIiIiIpJ7bPhwwLzKLiod48ePx93dnQMHDuDq6grAxIkTKV68OOPHjzc4OhERERER+TvsotLxww8/8OWXX1rdc7hw4cIMHz480wNMRERERERsyobP6cir7CLpAEhKSsrUdvv2bctDSkREREREcoWmV+U4u0jjnn/+eSZMmEB4eDgmk4n4+HgOHDjAqFGjaNOmjdHhiYiIiIjI32AXZYShQ4cyffp02rdvT0pKCu3atcPR0ZGXX36ZoUOHGh2eiIiIiOQhJlU6cpxdJB0uLi688847vPnmm0RGRpKWlsYTTzyBh4eH0aGJiIiIiMjfZBfTqx5wc3PD29ubI0eOsHbtWq5evWp0SCIiIiKSx5hMJptteZVhlY6EhASmTJnCxo0bAWjXrh2dOnWiY8eOJCQkYDabmTp1Kp9++il169Y1KkwREREREfmbDKt0TJw4kaNHjzJmzBgmTZrEuXPneOWVV2jYsCEHDx7k8OHDtGvXjpkzZxoVooiIiIjkRSYbbnmUYZWObdu2MXfuXGrWrAlArVq1aNiwIf/5z39wdnYGoHv37rz44otGhSgiIiIiIjnAsKTj9u3bFC9e3PK6cOHCuLu7U6hQIUubp6cniYmJRoQnIiIiInlUXl57YSuG3r3K0dExU5v+kkVERETESPo8mvMMTTqOHTtGgQIFLK/NZjMnTpzg2rVrAMTGxhoVmoiIiIiI5BBDk47+/ftnahs8eLDVa2WaIiIiIpKb9Pkz5xmWdJw9e9aoQ4uIiIiISC6yiyeSi4iIiIjYC1U6cp5dPZFcREREREQeP6p0iIiIiIhkpEJHjlOlQ0REREREbEqVDhERERGRDLSmI+ep0iEiIiIiIjalSoeIiIiISAaqdOQ8JR0iIiIiIhko6ch5ml4lIiIiIiI2pUqHiIiIiEgGqnTkPFU6RERERETEplTpEBERERHJSIWOHKdKh4iIiIiI2JQqHSIiIiIiGWhNR85TpUNERERERGxKlQ4RERERkQxU6ch5SjpERERERDJQ0pHzNL1KRERERERsSpUOEREREZGMVOjIcap0iIiIiIiITanSISIiIiKSgdZ05DxVOkRERERExKYey0pH9OHZRocgIiIiIv9QqnTkPFU6RERERETEph7LSoeIiIiISHap0pHzlHSIiIiIiGSgpCPnaXqViIiIiIjYlCodIiIiIiIZqdCR41TpEBERERERm1KlQ0REREQkA63pyHmqdIiIiIiIiE2p0iEiIiIikoEqHTlPlQ4REREREbEpVTpERERERDJQpSPnqdIhIiIiIpKRyYZbFiQlJTFixAjq1KlDcHAwixYt+sO+e/bs4YUXXiAgIICuXbty/vx5q/2bN2/m2WefpVatWnTv3p0rV64AsGbNGqpUqZJpq1q1quW9ffr0ybR/x44dWToXVTpEREREROzQlClTOHXqFF988QVXr15l2LBhlCxZklatWln1Cw8Pp1evXvTs2ZO2bduyatUqunTpwubNm/Hw8ODo0aMMHjyYUaNGUa9ePaZMmcKgQYNYvnw5bdq0oXHjxpaxUlNT6dKlC82aNbO0RUREMHXqVBo0aGBpK1CgQJbORZUOEREREZEMTCaTzbZHFR8fz8qVKxk5ciR+fn60bNmS119/nSVLlmTqu3TpUgICAhg4cCDly5dnyJAh5M+fn/Xr1wOwaNEiXnjhBTp27Ej58uUZOXIkUVFR3L59Gzc3N4oWLWrZvvnmG8xmM2+//TYAycnJXL58mRo1alj1c3FxydLXVEmHiIiIiIidOXv2LKmpqQQEBFjaAgMDOX78OOnp6VZ9IyMjqVmzpuW1yWSicuXKhIWFAXDo0CFatmxp2f/EE0+wfft2ChcubDVOTEwMCxYsYPDgwZak4vz585hMJp544om/dT5KOkREREREMrBlpSM5OZm4uDirLTk5OVMMUVFRFCpUyKqiUKRIEZKSkoiJibHqW6RIEa5fv27Vdu3aNaKjo7lz5w6xsbGkpaXRo0cPGjVqRJ8+fTL1h/sVk2LFillN3zp//jyenp4MHTqU4OBgOnTowK5du7L8NVXSISIiIiKSS+bNm0dgYKDVNm/evEz9EhISMk1hevD690lK69at+e6779ixYwepqamsXbuWkydPkpKSQnx8PADjx4+nbdu2zJkzh+TkZHr16mVVMTGbzaxcuZL//Oc/VmOfP3+exMREgoOD+fTTT2natCl9+vTh5MmTWTpvu1hIfvXqVUqUKJFpnltaWhpnz57Fz8/PoMhEREREJK+x5S1ze/XqRbdu3azaHrY+wtXVNVNy8eC1m5ubVXuTJk3o168fAwYMIC0tjaCgINq1a0dcXByOjo4AvPzyy4SEhAAwbdo0GjVqRFhYGLVr1wbg5MmTXL9+neeee85q7L59+9KpUyfLwvGqVavy008/sWLFCmrUqPHI520XlY7mzZsTHR2dqf3y5cu8+uqrBkQkIiIiIpLzXFxc8PT0tNoelnT4+PgQHR1NamqqpS0qKgo3Nze8vLwy9e/Tpw9Hjx5lz549fP7559y7d49SpUpRqFAhnJ2dKV++vKVvoUKFKFiwINeuXbO0/fDDD9SpUyfTXakcHBwytZUvX/6h07P+jGGVjpUrVzJ37lzgfjnnpZdewsHBOge6c+cOFSpUMCI8EREREcmj7OHhgL6+vjg5OREWFkadOnUAOHLkCDVq1Mj0mXnDhg0cP36ckSNH4u3tTWJiIgcPHmTy5Mk4OTnh5+fH2bNnadOmDQC3b98mOjqaUqVKWcY4ceKEpeqR0TvvvIPJZGLSpEmWtrNnz1K5cuUsnY9hSUdISAjOzs6kp6czYsQIunXrRv78+S37TSYT7u7u1K9f36gQRURERCQvMj7nwN3dnZCQEEJDQ5k4cSI3btxg0aJFlg//UVFR5M+fHzc3N8qWLcvw4cOpW7culStXZurUqZQoUYImTZoA0K1bN4YPH46vr69lv6+vr9Udr8LDw3nhhRcyxfH0008zaNAggoKCCAgIYP369Rw5coT33nsvS+djWNLh7OxsmVdWunRpateujZOTXSwxEREREREx3PDhwwkNDaVLly54enoyYMAAnnnmGQCCg4OZNGkS7du3p3r16oSGhjJ58mRiYmJo0KAB8+bNs1REWrVqxZ07d5g6dSq3bt2iXr16fPLJJ1YVnZs3bz502tYzzzzDmDFjmDNnDlevXqVSpUp8+umnlC5dOkvnYjKbzea/8bXIMfv377essv99SP3798/SWImpf91HRERERIzjZse/ay4/aKPNxj4/vY3NxrZndvHXPXnyZBYvXkzVqlXx8PCw2mcPc+pERERERCT77CLpWL16NZMnT37oPDIRERERkdykX3rnPLu4Za6jo6PVQhYREREREXl82EXS8dprrzFr1izLExNFRERERIxiMtluy6vsYnrVoUOHOHbsGJs3b8bb2xtnZ2er/du2bTMoMhERERER+bvsIulo37497du3NzoMERERERGt6bABu0g6XnzxxT/cl5KSkouRiIiIiEhep5wj59lF0nHz5k3mzZvHuXPnSEtLA8BsNpOSkkJERASHDx82OEIREREREckuu1hIPmLECH744Qdq1KjB0aNH8ff3p3Dhwpw4cYIBAwYYHZ6IiIiI5CEmk8lmW15lF5WOw4cPs2jRIgICAti7dy/NmjUjMDCQ+fPns3v3bjp37mx0iCIiIiIikk12Uekwm834+PgAULFiRU6fPg1A69atOXnypJGhiYiIiEgeo1vm5jy7SDqqVavG119/DYCvry979+4F4PLly0aGJSIiIiIiOcAuplcNHjyY3r174+7uTrt27fj0009p27YtV69e5YUXXjA6PBERERHJQxwc8nBJwkbsIukIDAxkx44dJCYmUqhQIVavXs3WrVspWLAgrVu3Njo8ERERERH5G+wi6QDw9PTE09MTAB8fH1577TWDIxIRERGRvCgvr72wFbtIOk6fPs348eM5efIkqampmfafOXPGgKhEREREJC/Ky7e2tRW7SDpGjBhB/vz5mTFjhqXaIf8cSUlJTBw/lm3fb8HV1Y3O3brTpWv3h/bdt3cPH06bQmRkJDX9/Rnx7mjKlitv2R9cvw537961es/+Q0fJ5+Fh03MQyW26bkSyR9eOyD+TXSQd58+fZ/369ZQpU8boUCQbpk+bwulTp1iw6AuuXr3KqBHDKFmiJC2fbWXV79y5cAb07UX313vy3PNtWbt6Fa9378I3GzaTz8OD69evc/fuXb7dvBU3NzfL+9zz5cvtUxKxOV03Itmja0dygwodOc8ubpnr6+tLRESE0WFINsTHx7N29UqGDh+JbzU/mrdoSdfur7Ns6ZJMfVcsW4p/rQD6DRhI2XLleXPwEPJ75ufbb9cDcOF8BEWLFqX0E09QpGhRy6YSpzxudN2IZI+uHZF/LrtIOtq1a8e7777LtGnTWLlyJevWrbPaxH798vNZUlNTqVUrwNIWUDuQkyeOk56ebtX3yuVIatSoaXltMpmoWLkyJ8LCAIiIOEeZsuVyJW4RI+m6EckeXTuSW0wmk822vMoupld9+umnuLm5sXHjxkz7TCYTISEhuR+UPJKbUVEULFgIZxcXS5u3dxGSkpKIiYmhcOHClvbC3kW4ceO61fuvX7uGV4ECwP3fOiUkJNCjaycuXrhAVV9fhrwzgrL6oSCPGV03Itmja0fkn8suKh3bt2//w23btm1Ghyd/IiExAZcM//gDltcpyclW7a1atWbLd9+xa+cOUlNT+WbdWn46dZKUlBQALpw/z53YWP7bqw8fzfoEV1c3evboyr17cblzMiK5RNeNSPbo2pHcokpHzrOLSsefTaFycXGhaNGi+Pv7Z/qHRozn6upK8u/+oX/wOuPCPIBGjZvQu28/Br85gLS0NOrWC+L5F9oRd/f+P/Bz5i8kNSXFcteQSVOm8WzzpuzasYM2z7fNhbMRyR26bkSyR9eOyD+XXSQda9as4ccff8TV1ZVy5cphNpu5dOkSCQkJlCxZkjt37pA/f34WLFhAhQoVjA5XMihWzIeYmGhSU1Nxcrr/7XTzZhRubm7k9/LK1P+/vfrQpVsP7t69i7e3N0MGDaRkqVLA/QQzY2Lp6upKyVKlM5XHRf7pdN2IZI+uHcktebggYTN2Mb2qcuXKNG3alF27drFmzRrWrl3L7t27admyJc8++ywHDhzgqaeeYuLEiUaHKr9TpaovTk5OnDgeZmk7dvQIftVr4OBg/e216dsNTJk0ARcXF7y9vUlMTOTwoYPUrReE2WzmuVYt+HrtGkv/+Ph4fv31ktU91UUeB7puRLJH147kFk2vynl2kXSsW7eOt99+G68Mv6Xw9PRk4MCBrFixAkdHRzp37szRo0cNjFIext3dnbbtQhj/XiinTp5g+7atLP58Ea/+pzNwf9FfYmIiAGXKlmXlimVs/X4Lly5d5J2hg/EpXoLgxk0wmUw0btKMOR/P4vChg5w7F87I4UPx8SlO4yZNDTxDkZyn60Yke3TtiPxz2UXSkS9fvoc+p+P8+fOW0md8fHym+ZpiH94eOpxq1fx4vVsXJo4fS59+A2jR8hkAmjcL5rtN9+9KVs2vOiNHh/LB1Mn8++X2AMyeM8/y26m3Bg+hxTPPMnzoYF7r+DKpKal8PGc+jo6OxpyYiA3puhHJHl07khtMJttteZXJbDabjQ7i888/Z/bs2XTt2pXq1atjNpv56aef+OKLL+jRowchISG88cYblC9fnsmTJ//leImpuRC0iIiIiGSbm12sLH642u9tt9nYR0c/bbOx7Zld/HV37dqVwoUL89VXX7Fw4UKcnJyoWLEiY8eOpU2bNhw+fJiAgAAGDhxodKgiIiIi8pjLy2svbMUuKh05TZUOEREREftmz5WOwHE7bDb2kVFP2Wxse2bYX/fs2bPp0aMH7u7uzJ49+0/79u/fP5eiEhEREZG8ToWOnGdY0nHw4EE6d+6Mu7s7Bw8e/MN+Km+JiIiIiPyzaXqViIiIiOQ6e55eVXfCTpuNfXhkM5uNbc8M++tet27dI/cNCQmxWRwiIiIiImJbhiUdM2fOfKR+JpNJSYeIiIiI5BrN7s95hiUd27fb7v7HIiIiIiLZpTXFOc9uZtPdvn2bCxcukJ6eDoDZbCY5OZnTp0/Ts2dPg6MTEREREZHssoukY8WKFbz33nukpqZiMpl4sLbdZDJRs2ZNJR0iIiIikmtU6Mh5DkYHADB37lx69+7NiRMn8Pb2ZseOHWzYsAFfX19atmxpdHgiIiIiIvI32EXScePGDUJCQnBxccHPz4+wsDAqVqzIiBEjWLlypdHhiYiIiEgeYjKZbLblVXaRdBQuXJjbt28DUL58ec6cOQOAj48P169fNzI0ERERERH5m+wi6WjdujXDhg3j6NGjNG7cmDVr1vDdd9/x8ccfU6ZMGaPDExEREZE8xGSy3ZZX2cVC8rfffpv8+fMTHR1N8+bNeemllxgzZgwFCxZk4sSJRocnIiIiIiJ/g8n84FZRj5HEVKMjEBEREZE/42YXv/p+uEZTf7DZ2HuHNLbZ2PbMsL/u2bNnP3Lf/v372zASEREREZH/Ly9Pg7IVQ5MOBwcHfH198fDw4I8KLnl5lb+IiIiIyOPAsKRjzJgxbN26lbCwMOrWrUvz5s1p3rw5hQsXNiokERERERH90tsGDF/TERcXx65du/j+++/Zt28flStXpkWLFrRs2ZJSpUpla0yt6RARERGxb/a8pqPxB3tsNvYPg4NtNrY9MzzpyCg5OZn9+/ezbds2duzYQZEiRWjRogX9+vXL0jhKOkRERETsmz0nHU2m77XZ2LsHNbLZ2PbMLp7T8YCLiwuNGzembdu2PPfcc/z6668sWLDA6LBERERERORvsIsc8969e/zwww9s376d3bt3A9CsWTMmTZpEcHDeLEGJiIiIiDG0pCPnGVbpuHbtGkuWLKFHjx40aNCADz74gEKFCjFz5kz27t3L5MmTeeaZZ8iXL59RIYqIiIiIGCYpKYkRI0ZQp04dgoODWbRo0R/23bNnDy+88AIBAQF07dqV8+fPW+3fvHkzzz77LLVq1aJ79+5cuXLFsu/777+nSpUqVtsbb7xh2X/69Glefvll/P39eemllzh16lSWz8WwNR2+vr44OTlZ7lxVuXLlP+xbt27dLI2tNR0iIiIi9s2e13Q0+2ifzcbe+WbDR+47btw4Dh8+zKRJk7h69SrDhg1j4sSJtGrVyqpfeHg4ISEh9OzZk7Zt27Jq1SrWr1/P5s2b8fDw4OjRo3Tq1IlRo0ZRr149pkyZQnR0NMuXLwdgzpw5HD9+nHHjxlnGdHV1xcvLi/j4eJ555hnatm1Lhw4dWLp0KZs2beL777/PUnHAsL9us9lMSkoK+/btY9++P/6LNZlMnDlzJhcjExEREZG8zB6mV8XHx7Ny5UoWLFiAn58ffn5+hIeHs2TJkkxJx9KlSwkICGDgwIEADBkyhJ07d7J+/Xo6duzIokWLeOGFF+jYsSMAI0eOpEuXLty+fZvChQsTERFB5cqVKVq0aKY4Nm7ciKurK0OHDsVkMjFy5Eh2797N5s2bad++/SOfj2FJx9mzZ406tIiIiIiIXTt79iypqakEBARY2gIDA5k7dy7p6ek4OPz/VRKRkZHUrFnT8tpkMlG5cmXCwsLo2LEjhw4dYvLkyZb9TzzxBNu3b7e8joiIoGHDh1dgjh8/TmBgoOXZJSaTidq1axMWFpalpMOu7l4lIiIiImI0k8lksy05OZm4uDirLTk5OVMMUVFRFCpUCBcXF0tbkSJFSEpKIiYmxqpvkSJFuH79ulXbtWvXiI6O5s6dO8TGxpKWlkaPHj1o1KgRffr0sfQ3m81cuHCBPXv28Oyzz9KiRQumTZtmiSkqKopixYpZje3t7c21a9ey9DVV0iEiIiIikkvmzZtHYGCg1TZv3rxM/RISEqwSDsDy+vdJSuvWrfnuu+/YsWMHqamprF27lpMnT5KSkkJ8fDwA48ePp23btsyZM4fk5GR69epFeno6V69etRzro48+YtiwYaxfv54pU6b8aRwPS5T+jB0v4RERERERyX22XNPRq1cvunXrZtX2+w/1cH8h9+8/2D947ebmZtXepEkT+vXrx4ABA0hLSyMoKIh27doRFxeHo6MjAC+//DIhISEATJs2jUaNGhEWFkbt2rU5ePAgBQoUwGQy4evrS3p6OkOGDGH48OF/GMfvY/grSjpERERERHKJi4vLQ5OM3/Px8SE6OprU1FScnO5/ZI+KisLNzQ0vL69M/fv06UOPHj24e/cu3t7eDBw4kFKlSlGoUCGcnZ0pX768pW+hQoUoWLCgZYpUwYIFrcaqUKECSUlJxMbG4uPjw82bN63237x5M9OUq7+i6VUiIiIiIhk4mEw22x7Vg8dLhIWFWdqOHDlCjRo1rBaRA2zYsIEJEybg4uKCt7c3iYmJHDx4kKCgIJycnPDz87O6idPt27eJjo6mVKlS/PDDDwQFBZGQkGDZf+bMGQoWLEjhwoXx9/fn2LFjPHjKhtls5ujRo/j7+2fta5ql3iIiIiIiYnPu7u6EhIQQGhrKiRMn2Lp1K4sWLaJz587A/apHYmIiAGXLlmXZsmVs2bKFixcvMnjwYEqUKEGTJk0A6NatG19++SWbNm0iIiKCESNG4OvrS82aNQkICMDV1ZV3332X8+fPs2vXLqZMmcLrr78OQKtWrbhz5w4TJkzg3LlzTJgwgYSEBFq3bp2l8zHs4YC2pIcDioiIiNg3e3444DMfH7DZ2Fv61X/kvgkJCYSGhrJlyxY8PT3p0aMHXbt2BaBKlSpMmjTJctva1atX8/HHHxMTE0ODBg0YM2aM1RSoFStWMHfuXG7dukW9evUYN24cxYsXB+4/XHDixImEhYXh4eFBx44d6devn+U2uSdOnGDMmDFERERQpUoVxo4dS7Vq1bJ03ko6RERERCTX2XPS8ewnB2029nd9g2w2tj3T9CoREREREbEpO84xRURERERyn4MNb5mbV6nSISIiIiIiNqVKh4iIiIhIBiZbPh0wj1KlQ0REREREbEqVDhERERGRDFToyHmPZdLx3Jz9RocgIiIiIn9i24AGRocgueixTDpERERERLLLhEodOU1Jh4iIiIhIBrplbs7TQnIREREREbEpVTpERERERDLQLXNzniodIiIiIiJiU6p0iIiIiIhkoEJHzlOlQ0REREREbEqVDhERERGRDBxU6shxqnSIiIiIiIhNqdIhIiIiIpKBCh05T0mHiIiIiEgGumVuztP0KhERERERsSlVOkREREREMlChI+ep0iEiIiIiIjalSoeIiIiISAa6ZW7OU6VDRERERERsSpUOEREREZEMVOfIeap0iIiIiIiITanSISIiIiKSgZ7TkfMMr3RERkYaHYKIiIiIiIWDyXZbXmV40tGqVStefvllPv/8c65fv250OCIiIiIiksMMTzp++OEH2rdvz/bt22nevDn/+c9/+Oqrr7h9+7bRoYmIiIhIHmQymWy25VWGJx2FCxfm3//+N4sXL2bXrl0899xz7N69mxYtWtCjRw/Wrl1LQkKC0WGKiIiIiEg2ZSvpSE1NZenSpVy9ehWAGTNm8NxzzzFkyBBiYmKyHUxUVBRRUVFcu3aN9PR0PDw8WLFiBc2aNWPLli3ZHldERERE5FGZTLbb8qps3b1q8uTJfPfddwQEBHD69GkWLFjAG2+8we7duxk3bhwffPDBI4915swZNm/ezObNm7ly5QoNGzakW7dutGjRAg8PDwA++eQTRo0axTPPPJOdcEVERERExEDZSjo2btzIJ598QtWqVVmwYAHBwcH07NmTp556io4dO2ZprPbt2xMYGEjXrl1p1aoVhQoVytQnMDBQd7kSERERkVyRl9de2Eq2ko6EhAS8vb1JTU1l9+7dvP322wCkp6fj5JS1IXfs2EGRIkWIjY21JBzHjh3Dz88PFxcXAIKCgggKCspOqCIiIiIiYrBsremoXbs2U6dOZfTo0SQkJNCiRQvOnj3Le++9R/369bM0VnR0NM2bN2fhwoWWtrfffptWrVoRHh6enfBERERERLJNz+nIedlKOsaPH09KSgo//fQTkyZNwtvbm02bNuHt7c2YMWOyNNZ7771Hy5Yteeuttyxt33//PU8//TTvvfdedsITEREREck23TI352VrelWJEiWYM2eOVVvGpCErzpw5w5QpU3B2dra0OTg40LlzZ9q1a5etMUVERERExH5k+zkdR44c4Y033qBdu3b89ttvzJ8/n2+//TbL45QoUYL9+/dnaj969ChFihTJbngiIiIiItlisuGWV2Wr0rFlyxaGDx/OK6+8ws6dO0lNTcXJyYl33nmH2NhYXn311Uceq3fv3owcOZJjx45RvXp1AM6ePcs333yT5alaIiIiIiJif7KVdMyePZvQ0FDatm3LsmXLAOjevTtFixZl5syZWUo62rVrR+HChVmxYgVLly7FycmJMmXKsHDhQurUqZOd8EREREREss0hD6+9sJVsJR2XLl2iVq1amdpr1qzJ9evXszxe48aNady4cXZCERERERERO5etpKNixYr88MMPmSoaa9eupWLFilkaKyEhgeXLl3Pu3DnS0tIs7cnJyZw+fZpNmzZlJ0QRERERkWxRoSPnZSvpGD58OL179+bAgQOkpKQwd+5cLl26xKlTpzLd1eqvvPvuu+zfv58GDRqwefNmWrduzaVLlzh58iT9+/fPTngiIiIiImJHspV01KlTh02bNvHVV18BEBMTQ61atZgyZQolS5bM0li7d+9mxowZNGzYkPDwcLp27Ur16tWZPHmyHg4oIiIiIrkuLz9Pw1aylXQAFC1alIEDBwKQmJjIL7/8Qv78+bM8TlJSEmXLlgWgUqVKnDp1iurVq/Ovf/2L//znP9kNT0RERERE7ES2ko5z584xYsQI3nnnHSpWrMi//vUvLly4gLu7O3PmzKF+/fqPPFaFChXYt28fHTp0oFKlShw5coSOHTty9+5dkpKSshOe5DJnRxMDm5anccXCJKWms/LYVVYe++2hfQOfKECv4DKU9HLj9PW7zNx5gcsxiZb9TSoUpkeDJ/H2dOGn3+7ywfYIbtxNzq1TEck1um5EskfXjuQGFTpyXrYeDjh27FieeOIJypYty6pVq7h79y579uyhd+/evP/++1kaq3///oSGhrJixQratWvHtm3b6N27NwMHDtQdrf4hejUqQ2UfD95ee5oZOy/QqV5pmlQonKlfmcLuTGxblX3no+m9/ATnbtzjgxf9cHO+/21YrbgnI5+txMpjV+m97AQpaemMerZybp+OSK7QdSOSPbp2JDc4mEw22/KqbCUdJ06c4M0336Rw4cJs3bqVli1bUqRIEZ5//nnOnz+fpbGaN2/Opk2bCAoKokSJEnz11VeUK1eOf//730ycODE74UkucnNyoI2fDx/vvkh41D32nr/N8iNXaVezeKa+L9Qozk/X4vj8YCSXYxKZv+9X7iWn0qLy/SfPv1K7JFt/vsmGn25wOSaR2bsvUtjDGS+3bM8CFLFLum5EskfXjsg/V7aSjvz583Pz5k1+++03wsLCaNasGQBnzpzB29s7S2O1b9+e+Ph4ypQpA0DVqlUZNmwYPXv2xN3dPTvhSS4qXyQfTg4mfvrtrqXt1G938S2en9/n8iW8XDl77a5V2/lb8VQrcX8tkH+pAuyJuG3Zd+1OEq99cYw7iak2i1/ECLpuRLJH147kFpPJdltela10vn379vTp0wcXFxdKly5NcHAwS5cuZcqUKZbF5Y/qxo0bODo6ZicMsQPeHi7EJqSQmm62tEXHp+Dq5ICXmxOxGf7xjo5PwdvTxer9xTxduZuYioeLI15uTjg4mJj8gi8ViuTjzPU4Zu68wM17ml8rjxddNyLZo2tH5J8rW5WOQYMGMW7cOLp3785XX32Fo6MjJUuWZPr06XTt2jVLY4WEhPD6668zffp0li9fzrp166w2sW+uTg6kpJmt2lLS0gFwdrT+9toZfoumFb2pX7YgDiZ4pmpRqhTzwMnRhLvz/cSzf5OybP05inc3nMXZ0YHxbatm+u2VyD+drhuR7NG1I7nFZDLZbMursj1xsWXLlqSnp+Pg4MCNGzeIj4+nSpUqWR5n48aNODg4sGHDhkz7TCYTISEh2Q1RckFyWjrOjtYX0IN/+JNS063aD/8aw+JDlxnTpgqOJhNhV2L5/uxNPFwdSTPf/yGy8fQNtv58E4BJW8JZ1aMOvsU9OX0tLhfORiR36LoRyR5dO5LXJCUlMXbsWLZs2YKbmxvdu3ene/fuD+27Z88epkyZQmRkJP7+/owePZry5ctb9m/evJkPP/yQ69evU7t2bcaNG0epUqUAuH79OhMmTODAgQO4urrSpk0bBg0ahKurKwDjx4/nyy+/tDreqFGjsvR4i2wlHUeOHOHNN99k6tSplC9fnvbt25OUlERCQgJTp06ldevWjzzW9u3bsxOC2ImbcckUcHfGwQQPqt2F8zmTmJJGXFLmebFf/XiFlUev4uHqSExCKqNaVeLanSRiE1JISUsnMjrB0vdOYip3ElMolt9VPwDksaLrRiR7dO1IbsnWVCAbmDJlCqdOneKLL77g6tWrDBs2jJIlS9KqVSurfuHh4fTq1YuePXvStm1bVq1aRZcuXdi8eTMeHh4cPXqUwYMHM2rUKOrVq8eUKVMYNGgQy5cvx2w288Ybb+Dl5cWSJUuIjY1lxIgRODg4MGzYMAAiIiIYPHgwL774ouWYnp6eWTqXbH1NJ02aRJs2bfD392fFihW4urqyd+9exo0bx8yZM7M01uHDh/90E/sWcTOe1HQz1Yr//wdDVi+Zn59v3MP8u75PVfKmb+OypKSbiUlIxcXRgVqlCxB2JZZ0M4TfuEeFIvks/b3cnPByc+baHT2vRR4vum5EskfXjuQl8fHxrFy5kpEjR+Ln50fLli15/fXXWbJkSaa+S5cuJSAggIEDB1K+fHmGDBlC/vz5Wb9+PQCLFi3ihRdeoGPHjpQvX56RI0cSFRXF7du3OX/+PGFhYUyaNIlKlSpRp04d3njjDatZSBEREVSrVo2iRYtatqze8ClblY5ffvmFmTNn4u7uzvbt23nmmWdwcXGhXr16hIaGZmmsTp06PbTdxcWFokWLsm3btuyEKLkkKTWdLWdu8OZT5Zm69RxFPF14OaAkU7dFAFAonzP3ktJITkvnckwiQ1tU5MTVO1y4GU/PRmWIupvEoYsxAKw8dpWhLSoSHnWPi7cS6NnoSSJu3uPsdf3GSR4vum5EskfXjuQWe1h7cfbsWVJTUwkICLC0BQYGMnfuXMsShwciIyOpWbOm5bXJZKJy5cqEhYXRsWNHDh06xOTJky37n3jiCctsIycnJz799FOKFClidfy4uDjL/69fv07ZsmX/1vlkK+koUqQI586dIz4+ntOnT/POO+8AsG/fPkqUKJGlsc6ePWv1Oi0tjV9//ZVx48bRtm3b7IQnuWzOnku82awcH7zox73kNL44GGm5DeGqHnWY8v05vjsbRXjUPT7aeZ7ejcrg5e7Escg7jFh/1vLbqd0Rt/F0u0ivRmUo6O7M8St3GLXhZ+NOTMSGdN2IZI+uHckNDjbMOZKTk0lOtr5LmouLCy4u1ndbi4qKolChQlbtRYoUISkpiZiYGAoXLmzVfv36dav3X7t2jQIFCnDnzh1iY2NJS0ujR48enD17lpo1axIaGoqPjw9eXl5WD+ROT0/nf//7H/Xr1wfuVzlMJhNz585l9+7dFCxYkG7dullNtXoUJrPZ/PuK5F9avHgxU6dOxcHBgcqVK7Ny5Urmzp3L7NmzmTRpUo4kC7/88gs9e/Zk586dWX5v81n7//bxRURERMR2tg1oYHQIf+jNr8/+dadsqvDr98yePduqrX///gwYMMCqbd26dcyYMYMdO3ZY2iIjI2nRogW7du2iePH//1DM3bt307dvX2bNmkXjxo1Zv3497777LkFBQUycOJGmTZtSvHhx3nrrLcqXL8+MGTO4desWa9assaqYALz//vssWbKEVatWUblyZdauXcuIESMYMmQIDRs25PDhw7z//vt8+OGHtGzZ8pHPO1uVjs6dO1OnTh2uXr1KcHAwAPXr16dZs2ZUrVo1O0NmcuvWLe7cuZMjY4mIiIiIPCpbVjp69epFt27drNp+X+UAcHV1zVQRefDazc3Nqr1Jkyb069ePAQMGkJaWRlBQEO3atSMuLs7yPLyXX37ZclfYadOm0ahRI8LCwqhdu7ZlnKlTp/LFF1/w4YcfUrlyZeD+4y2eeuopChYsCNx/kPfFixdZunSp7ZMOgGrVqlGtWjXL61q1apGcnMzx48fx9/d/5HGGDx+eqe3evXvs27cv08p8EREREZF/sodNpXoYHx8foqOjSU1Nxcnp/kf2qKgo3Nzc8PLyytS/T58+9OjRg7t37+Lt7c3AgQMpVaoUhQoVwtnZ2er2uYUKFaJgwYJcu3bN0jZu3DiWLl3K1KlTefbZZy3tJpPJknA8UL58eQ4cOJCl887W3auOHj1Ku3bt8PPzw9fX17L5+/vz2muvZWdIKwULFmTYsGFZXpQuIiIiIvJ32cPDAX19fXFyciIsLMzSduTIEWrUqJFpStSGDRuYMGECLi4ueHt7k5iYyMGDBwkKCsLJyQk/Pz+rddS3b98mOjra8pyO2bNns2zZMqZPn85zzz1nNfaMGTMyPfz77NmzVknMo8hWpWP8+PGUKlWKt99+m4EDBzJlyhSuX7/O7NmzGTVqVJbGmjRpEqmpqcTGxuLt7Q3AsWPH8PPze6QsUERERETkcePu7k5ISAihoaFMnDiRGzdusGjRIiZNmgTcr3rkz58fNzc3ypYty/Dhw6lbty6VK1dm6tSplChRgiZNmgDQrVs3hg8fjq+vr2W/r68vNWvWJCIigk8++YSePXsSGBhIVFSUJYaiRYvy1FNPMX/+fBYuXEjLli3Zs2cP69atY/HixVk6n2wlHeHh4UydOpUKFSrg5+eHs7Mzr732Gt7e3ixYsIA2bdo88lhnzpyhd+/ePPfccwwdOhSAt99+G7PZzLx586hUqVJ2QhQRERERyRZbrunIiuHDhxMaGkqXLl3w9PRkwIABPPPMMwAEBwczadIk2rdvT/Xq1QkNDWXy5MnExMTQoEED5s2bZ6mItGrVijt37jB16lRu3bpFvXr1+OSTTzCZTGzbto20tDTmzJnDnDlzrI7/888/U7NmTWbMmMHMmTOZMWMGpUqV4oMPPrC6le+jyNbdq+rVq8eKFSsoW7YsY8aMoVSpUvTs2ZOrV6/y/PPPc/To0Uce69///jd+fn4MGzYMZ2dn4P6tuiZOnMjPP/+c6ZHrj0J3rxIRERGxb/Z896ohNrx98tTnq9hsbHuWrTUd9evX54MPPuD69esEBASwceNGYmJi2L59+0MXtvyZM2fO0KVLF0vCAeDg4EDnzp05depUdsITEREREck2k8l2W16VraRj5MiRxMbGsmXLFp577jk8PT2pX78+kyZNol+/flkaq0SJEuzfn7kycfTo0UxPRhQRERERsTUHk8lmW16VrTUdPj4+VotHvvzyS86dO4eXlxc+Pj5ZGqt3796MHDmSY8eOUb16deD+ivhvvvmGMWPGZCc8ERERERGxI4+cdBw+fPgv+8TExPDrr79St27dRw6gXbt2FC5cmBUrVrB06VKcnJwoU6YMCxcupE6dOo88joiIiIhITsjWVCD5U4+cdHTq1OmR+plMJs6cOZOlIKpVq8agQYMoV64cABs3bqRMmTJZGkNEREREROzTIycdDx4ocvHiRUqWLGn1DI39+/dTrFgxKlSokOUA9u/fT79+/ejatStvvPEGAIsXL2bMmDHMnTuXwMDALI8pIiIiIpJdeXjphc1kqXo0fvx42rRpY/VkRLi/puP5559n8uTJZPUOvO+//z69e/e2JBwAy5Yt4/XXX2fixIlZGktEREREROzPIycdX3zxBRs3buTjjz+mXr16Vvs++eQTPv74Y9auXcvSpUuzFMDFixdp1apVpvbWrVtz7ty5LI0lIiIiIvJ36e5VOe+Rk44VK1YwatQonnrqqYfuf/rpp3n77beznHSUL1+eTZs2ZWrfvn07Tz75ZJbGEhERERER+/PIazquXLlCzZo1/7RP/fr1mTBhQpYCePPNN+nbty979+7Fz88PuL9+5Mcff2T27NlZGktERERE5O/KwwUJm3nkSoe3tzdXrlz50z7Xrl2jYMGCWQqgSZMmrFu3jmrVqnH+/HkiIyOpVq0aGzdupGHDhlkaS0RERETk73Iw2W7Lqx456WjZsiWzZs0iJSXloftTU1OZPXs2wcHBWQrg5s2bLF++nJ9//pmEhARiY2M5ceIEQ4YMUdIhIiIiIvIYeOSko2/fvly/fp327duzYsUKTp8+TWRkJKdOnWL58uW8+OKLREZGMmDAgCwFMGLECH744Qdq1KjB0aNHqVWrFt7e3pw4cSLLY4mIiIiI/F1aSJ7zHnlNh5eXFytWrGDatGlMnjyZhIQEAMxmM/nz56dNmzYMGDCAIkWKZCmAw4cPs2jRIgICAti7dy/NmjUjMDCQ+fPns3v3bjp37py1MxIREREREbvyyEkHQMGCBRk/fjyjR48mMjKSO3fuULBgQZ588kkcHR2zFYDZbMbHxweAihUrcvr0aQIDA2ndujULFy7M1pgiIiIiItmVhwsSNpOlhwM+4OLiQoUKFQgICKBcuXLZTjgAqlWrxtdffw2Ar68ve/fuBeDy5cvZHlNEREREROxHliodtjB48GB69+6Nu7s77dq149NPP6Vt27ZcvXqVF154wejwRERERCSPyct3mbIVw5OOwMBAduzYQWJiIoUKFWL16tVs3bqVggUL0rp1a6PDExERERGRv8nwpAPA09MTT09PAHx8fHjttdcMjkhERERE8ioTKnXkNLtIOkRERERE7IWmV+W8bC0kFxEREREReVSqdIiIiIiIZKBKR85TpUNERERERGxKlQ4RERERkQxMejpgjlOlQ0REREREbEqVDhERERGRDLSmI+ep0iEiIiIiIjalSoeIiIiISAZa0pHzlHSIiIiIiGTgoKwjx2l6lYiIiIiI2JQqHSIiIiIiGWghec5TpUNERERERGxKlQ4RERERkQy0pCPnqdIhIiIiIiI2pUqHiIiIiEgGDqjUkdMey6SjWumCRocgIiIiIiL/57FMOkREREREsktrOnKekg4RERERkQx0y9ycp4XkIiIiIiJiU6p0iIiIiIhk4KD5VTlOlQ4REREREbEpVTpERERERDJQoSPnqdIhIiIiIiI2pUqHiIiIiEgGWtOR81TpEBERERERm1KlQ0REREQkAxU6cp6SDhERERGRDDQVKOfpayoiIiIiIjalSoeIiIiISAYmza/Kcap0iIiIiIiITanSISIiIiKSgeocOc/wSkfVqlXx9fV96FazZk2aN2/OtGnTSElJMTpUEREREZFck5SUxIgRI6hTpw7BwcEsWrToD/vu2bOHF154gYCAALp27cr58+et9m/evJlnn32WWrVq0b17d65cufLIx4mMjKRr167UqlWLNm3asGfPniyfi+FJR2hoKN7e3oSGhrJu3TrWrl3LuHHjKFasGK+//jpDhgxh165dfPTRR0aHKiIiIiJ5gIPJZLMtK6ZMmcKpU6f44osvGDNmDLNnz2bz5s2Z+oWHh9OrVy+aN2/O6tWrqVatGl26dOHevXsAHD16lMGDB9OtWzfWrFmDi4sLgwYNeqTjmM1m+vXrR5EiRVi9ejXt2rWjf//+XL16NUvnYvj0qoULFzJx4kSaNGliaatatSolSpTgvffe44033sDHx4cBAwYwZMgQAyMVEREREckd8fHxrFy5kgULFuDn54efnx/h4eEsWbKEVq1aWfVdunQpAQEBDBw4EIAhQ4awc+dO1q9fT8eOHVm0aBEvvPACHTt2BGDkyJF06dKF27dv4+bm9qfHOXDgAJGRkSxbtox8+fJRoUIF9u/fz+rVqxkwYMAjn4/hlY6bN29SvHjxTO1FihTh+vXrABQtWtSSqYmIiIiI2JLJhtujOnv2LKmpqQQEBFjaAgMDOX78OOnp6VZ9IyMjqVmz5v+P32SicuXKhIWFAXDo0CFatmxp2f/EE0+wfft2Chcu/JfHOX78ONWqVSNfvnxW+x+M/agMTzoaNWrEe++9ZzWv7MqVK0yYMIH69euTlpbG6tWrqVy5soFRioiIiEheYTLZbktOTiYuLs5qS05OzhRDVFQUhQoVwsXFxdJWpEgRkpKSiImJseqb8Zf1D1y7do3o6Gju3LlDbGwsaWlp9OjRg0aNGtGnTx9L/786TlRUFMWKFbMa29vbm2vXrmXpa2p40jF+/HicnZ1p3rw59evXJygoiBYtWuDq6sq4cePYtWsXS5cuZdiwYUaHKiIiIiLyt8ybN4/AwECrbd68eZn6JSQkWCUCgOX175OU1q1b891337Fjxw5SU1NZu3YtJ0+eJCUlhfj4eOD+Z+62bdsyZ84ckpOT6dWrF+np6X95nD/a/7BE6c8YvqajYMGCfPbZZ1y4cIFffvkFR0dHKlasSNmyZQFo2LAh+/fv10NaRERERCRX2PJzZ69evejWrZtV2+8/1AO4urpm+mD/4LWbm5tVe5MmTejXrx8DBgwgLS2NoKAg2rVrR1xcHI6OjgC8/PLLhISEADBt2jQaNWpEWFjYXx7H1dU1U2UlOTk5Uwx/xfCko3v37jz33HO0bNmSZ599NtP+rJ6QiIiIiIi9cnFxeWiS8Xs+Pj5ER0eTmpqKk9P9j+xRUVG4ubnh5eWVqX+fPn3o0aMHd+/exdvbm4EDB1KqVCkKFSqEs7Mz5cuXt/QtVKgQBQsW5Nq1axQvXvxPj+Pj48O5c+esjnXz5s1MU67+iuHTq6pXr86CBQto1KgRvXv35ptvvtGicRERERExjIMNt0fl6+uLk5OT1YLtI0eOUKNGDRwcrEfasGEDEyZMwMXFBW9vbxITEzl48CBBQUE4OTnh5+fH2bNnLf1v375NdHQ0pUqV+svj+Pv789NPP5GYmGi139/fPwtnYwdJx6BBg9i8eTOrVq3Cz8+PBQsW0LBhQ954442H3odYRERERORx5+7uTkhICKGhoZw4cYKtW7eyaNEiOnfuDNyvRjxIBMqWLcuyZcvYsmULFy9eZPDgwZQoUcLySIpu3brx5ZdfsmnTJiIiIhgxYoTlQdx/dZx69epRokQJhg8fTnh4OPPnz+fEiRN06NAhS+djMpvN5hz8+vxtd+/eZenSpcydO5eEhATOnDmT5TEGrM36e0REREQk98x60dfoEP7QirCsPfguK16pVfKR+yYkJBAaGsqWLVvw9PSkR48edO3aFYAqVaowadIk2rdvD8Dq1av5+OOPiYmJoUGDBowZM8ZqCtSKFSuYO3cut27dol69eowbN87y2Io/Ow7ApUuXGDlyJMePH6dMmTKMGDGChg0bZum87SLpuH37Ntu2bWPLli0cOHCAihUr0rp1a5577jlKlSqV5fGUdIiIiIjYNyUdeYvhC8k7derE0aNHKVOmDG3atGH48OFWC11ERERERHKT7pma8wxPOmrVqsXIkSOpWrWq0aGIiIiIiIgNGJ50DB48mNTUVK5fv05aWhoAZrOZ5ORkzpw5Q5s2bQyOUERERETyEj0fLucZnnRs27aNd999N9NDRwCKFi2qpENEREREcpXht3d9DBn+NZ02bRotW7bk22+/xcvLi2XLljF37lxKlSrFm2++aXR4IiIiIiLyNxle6YiMjGTevHk8+eSTVK9enaioKFq0aIGDgwNTpkyx3AZMRERERCQ3aHpVzjO80uHl5UVCQgIA5cqVszwtsXz58ly+fNnI0EREREREJAcYnnQ0bdqUsWPHcu7cOYKCgvj666/56aefWL58udUDTUREREREcoPJhlteZXjSMXLkSMqUKcOpU6do0aIF/v7+dOjQgSVLljBs2DCjwxMRERERkb/JLp5I/ntxcXG4urri7OycrffrieQiIiIi9s2en0j+9clrNhu7XY3iNhvbnhm+kPxhPD09jQ5BRERERERyiF0mHSIiIiIiRnHI06svbENJh/xtTg4mXvEvjn/J/KSkm9kefovt524/tG/VYh6EVC9GEQ8XLt5OYMXxa9yIS7bsr1UyP239ilLAzZnzt+JZeuw3ohNSc+tURHKNrhuR7NG1I7lBd8zNeYYvJJd/vpDqxXiykBuz9vzKirBrtKpahFol82fqVzy/C70bPMGJ3+4yZccFImMSGRD8JC6O96/scoXd6Vq3FNvDbzNlxwVS0810q1cqt09HJFfouhHJHl07Iv9MdpF0bN26lY4dO1KvXj0CAwPp0KED69atMzoseQQujiYalC3IqhPXuRybyInf7rIt/BZNyhfK1LdxuUKcvx3PxjM3uRGXzNc/3SAhJZ26TxQAoHmlwhyOjGXvxRhuxCWz+sR1vFyd8HBxzO3TErEpXTci2aNrR3KLyYb/5VWGJx3Lli1jyJAh1K1bl8mTJ/P+++9Tr149xo4dy8qVK40OT/5CqQJuOJpMXLgVb2mLuJVAmcLumS4rbw8XLt1OtGr77U4S5Qq7A1CxiAfHr9617LsVn0LolgjuJafZLH4RI+i6EckeXTsi/1yGr+n49NNPGTNmDCEhIZa2Fi1aUKlSJebOncvLL79sXHDyl7zcnLiXnEZahhsv301KxcXRAQ8XR+Iy/ON9NymVAu7W33IF3Z2IT0nD3fl+fweTib4Nn6BUATcuRiewIuwasYmaXyuPF103Itmja0dyi9Z05DzDKx23bt2iVq1amdoDAgL47bffcj8gyRIXRxOp6daPekn9v58GTg7WV+zRy3cIKOWFX3FPHExQ78kClCnkjqPJhKvj/W/FDjV9OBwZy7z9kTg5mOjV4Ik8XIiUx5WuG5Hs0bUj8s9leNLh6+v70PUba9eupWLFirkfkGRJSpo50z/0Tv+3SC85Ld2q/cyNe2w6E0WPeqX4sF1V6j1RgEO/xpKYmk7a/z2jcv+lGA5H3uHXmES++PEqJb1cKft/pXCRx4WuG5Hs0bUjucUBk822vMrw6VVDhgyha9euHDx4EH9/fwDCwsI4e/Ysc+fONTg6+Suxian/V6KGB7988nJ1Ijk1nYSU9Ez9t/xy/9aGbk4OxCWn0a1uKW7Hp3AvOY3UdDPX7yZZ+sYnp3EvOY1C7k5cyK0TEskFum5EskfXjsg/l+GVjoCAANasWYO/vz8RERFcvnyZunXrsmnTJurXr290ePIXLscmkmY2W/1mqLx3Pi7FJGD+Xd/A0l60r+FDarqZuOQ0nB1MVCqaj/CoeNLNEBmTQKkCbpb+Hi6OeLo6cis+JZfORiR36LoRyR5dO5JbTCbbbXmV4ZWOvn37MnjwYN555x2jQ5FsSEkzc+jXWP5VqzhLjvxGQXcnmlcqzJKj99fj5Hd1JDElnZR0MzfiknmtdgkibsVzNTaRdtV9iElI5fT1OAC2h9/mP4EliYxJ5Le7SbTzK8blmEQuRSf+WQgi/zi6bkSyR9eO5Ja8nBzYislsNv/+lwO5qn79+ixfvpwyZcrk2JgD1p7JsbHkrzk7mvhXreLUKulFQkoa28JvsTMiGoBZL/ryvyNXOfhrLABBTxagddUi5HNx5JeoeFaEXeNO0v+/U0jDsgV5prI3+V2dCL8Zz7JjvxGjO4nIY0jXjUj26Np5fMx60dfoEP7QljNRNhv7Gd+iNhvbnhmedMycOZOdO3fSsWNHSpYsiaurq9X+unXrZnlMJR0iIiIi9s2ek47vz9y02dgtfYvYbGx7Zvj0qk8++QSA0aNHZ9pnMpk4c0YJhIiIiIjIP5nhScfZs2eNDkFERERExMJBazpynOF3r0pOTmbKlCksWbLE0ta+fXumTZtGSoruICEiIiIi8k9neNIxfvx4du3aRdWqVS1tffv2ZefOnbz//vsGRiYiIiIieZHJhv/lVYYnHVu2bGHatGkEBgZa2lq0aMGkSZPYuHGjgZGJiIiIiEhOMHxNh9lsJikp6aHtml4lIiIiIrlNz+nIeYZXOp599llGjRrFjz/+SHx8PPHx8Rw9epTQ0FBatmxpdHgiIiIiksdoelXOM7zSMXz4cEaOHEmXLl1IT08HwMHBgZCQEEaMGGFwdCIiIiIi8ncZnnS4u7szffp07ty5w6VLl3B2dqZ06dJ4enoaHZqIiIiI5EG6ZW7OMzzpALh9+zYXLlwgPT2dxMRETp8+TXJyMqdPn6Znz55GhyciIiIiIn+D4UnHihUreO+990hNTcVkMmE2m4H7TyOvWbOmkg4RERERyVV5ee2FrRi+kHzu3Ln07t2bEydO4O3tzY4dO9iwYQO+vr5aSC4iIiIi8hgwPOm4ceMGISEhuLi44OfnR1hYGBUrVmTEiBGsXLnS6PBEREREJI8xmWy35VWGJx2FCxfm9u3bAJQvX54zZ84A4OPjw/Xr140MTUREREREcoDhSUfr1q0ZNmwYR48epXHjxqxZs4bvvvuOjz/+mDJlyhgdnoiIiIjkMSYbbnmV4QvJ3377bfLnz090dDTNmzfnpZdeYsyYMRQsWJCJEycaHZ6IiIiI5DEOeXkelI2YzA9uF/UYGbD2jNEhiIiIiMifmPWir9Eh/KH952JsNnaDigVtNrY9M7zSER8fz8qVKzl//jzJycmZ9k+aNMmAqEREREQkr1KdI+cZnnQMGjSIY8eO0bBhQ9zc3IwOR0REREREcpjhScfBgwdZtGgRAQEBRociIiIiIqJShw0Yfveq8uXLk5iYaHQYIiIiIiJiI4ZXOiZPnkz//v1p27YtJUuWxMHBOg8KCQkxJjARERERyZNMKnXkOMOTjhUrVnDp0iWWLl2Kq6ur1T6TyaSkQ0RERETkH87wpGPVqlVMnz6dNm3aGB2KiIiIiAh6TEfOMzzpKFSoEBUrVjQ6DBERERERQOvIbcHwpGPMmDG899579OvXj9KlS+Po6Gi1v2TJkgZFJiIiIiIiOcHwpKNXr14AdOvWDVOGWpbZbMZkMnHmjJ4uLiIiIiK5SKWOHGd40rFt2zajQxARERERsTtJSUmMHTuWLVu24ObmRvfu3enevftD++7Zs4cpU6YQGRmJv78/o0ePpnz58pb9derU4e7du1bvOXr0KN999x3Dhw/PNJ7JZOLs2bMA9OnTh+3bt1vtnzt3Lk899dQjn4vhSUepUqWMDkFERERExMJebpk7ZcoUTp06xRdffMHVq1cZNmwYJUuWpFWrVlb9wsPD6dWrFz179qRt27asWrWKLl26sHnzZjw8PLh+/Tp3795l69atuLm5Wd6XL18+2rRpQ+PGjS1tqampdOnShWbNmlnaIiIimDp1Kg0aNLC0FShQIEvnYnjSISIiIiIi1uLj41m5ciULFizAz88PPz8/wsPDWbJkSaakY+nSpQQEBDBw4EAAhgwZws6dO1m/fj0dO3YkIiKCokWL8sQTT2Q6jpubm1UiMm/ePMxmM2+//TYAycnJXL58mRo1alC0aNFsn4/hTyQXEREREbEnJpPttkd19uxZUlNTCQgIsLQFBgZy/Phx0tPTrfpGRkZSs2bNDPGbqFy5MmFhYQCcO3eOcuXK/eUxY2JiWLBgAYMHD8bFxQWA8+fPYzKZHpqwZIWSDhERERGRXJKcnExcXJzVlpycnKlfVFQUhQoVsnz4ByhSpAhJSUnExMRY9S1SpAjXr1+3art27RrR0dHA/elRCQkJdOrUieDgYP773/9y4cKFTMdcunQpxYoVs6qknD9/Hk9PT4YOHUpwcDAdOnRg165dWT5vJR0iIiIiIhmYbLjNmzePwMBAq23evHmZYkhISLBKOADL698nKa1bt+a7775jx44dpKamsnbtWk6ePElKSgpwP3GIjY2lT58+fPLJJ7i5udG1a1fi4uIsY5jNZlauXMl//vMfq7HPnz9PYmIiwcHBfPrppzRt2pQ+ffpw8uTJLH1NtaZDRERERCQjG64j79WrF926dbNq+31yAeDq6popuXjwOuMaDIAmTZrQr18/BgwYQFpaGkFBQbRr186SVCxcuJCUlBQ8PDwAmDZtGk2bNmXHjh20bdsWgJMnT3L9+nWee+45q7H79u1Lp06dLAvHq1atyk8//cSKFSuoUaPGI5+3kg4RERERkVzi4uLy0CTj93x8fIiOjiY1NRUnp/sf2aOionBzc8PLyytT/z59+tCjRw/u3r2Lt7c3AwcOtNwl9vfHdHV1pXTp0lZTsn744Qfq1KmT6a5UDg4OmdrKly/PuXPnHv2k0fQqERERERErJhv+96h8fX1xcnKyLAYHOHLkCDVq1MDBwfoj/IYNG5gwYQIuLi54e3uTmJjIwYMHCQoKwmw206JFC9asWWPpHx8fz6VLl6ye43HixAlq166dKY533nkn03M8zp49a/XeR6GkQ0RERETEzri7uxMSEkJoaCgnTpxg69atLFq0iM6dOwP3qx6JiYkAlC1blmXLlrFlyxYuXrzI4MGDKVGiBE2aNMFkMtGsWTNmzZrFwYMHCQ8PZ+jQoRQvXpymTZtajhceHk7FihUzxfH000+zfv161q1bx6VLl5g9ezZHjhzJtPbjr2h6lYiIiIhIBlm5ta0tDR8+nNDQULp06YKnpycDBgzgmWeeASA4OJhJkybRvn17qlevTmhoKJMnTyYmJoYGDRowb948S0VkyJAhODk5MXjwYOLi4qhfvz7z58/H0dHRcqybN28+dNrWM888w5gxY5gzZw5Xr16lUqVKfPrpp5QuXTpL52Iym83mv/G1sEsD1p4xOgQRERER+ROzXvQ1OoQ/FPbrXZuNXevJ/DYb256p0iEiIiIikoGdFDoeK49l0nH6cozRIYiIiIiIyP95LJMOEREREZFsU6kjxynpEBERERHJICu3tpVHo1vmioiIiIiITanSISIiIiKSgb3cMvdxokqHiIiIiIjYlCodIiIiIiIZqNCR8wxPOg4fPvzQdpPJhLOzM0WLFqVkyZK5HJWIiIiIiOQUw5OOkSNHcvnyZdLT0ylQoABms5k7d+5gMpkwmUyYzWZq1qzJrFmzKFasmNHhioiIiMjjTqWOHGf4mo4XX3yRGjVqsGnTJg4ePMihQ4f4/vvvqVOnDkOGDGHv3r34+Pgwfvx4o0MVEREREZFsMDzp+OKLLxg7dizlypWztD3xxBOMHDmSefPmUbhwYQYOHMj+/fsNjFJERERE8gqTDf/LqwxPOgCio6Mf2paWlmZ5bdK9y0RERERE/pEMX9PRoUMHhg0bxltvvUX16tUxm8389NNPzJgxgxdffJHo6GimTp1KvXr1jA5VRERERPIA/a475xmedAwePBgPDw8+/PBDbty4AUCxYsX4z3/+Q48ePdi3bx9OTk6MHj3a4EhFREREJC9QzpHzTGaz2WxkAMnJybi4uAD3p1Q5OTmRP3/+vzVm81la/yEiIiJiz7YNaGB0CH/ozNV7Nhvbt6SHzca2Z4ZXOho0aECLFi1o06YNjRo1wsnJ8JBEREREJC9TqSPHGb6QfMaMGbi6ujJixAgaNWrEyJEj2bdvH+np6UaHJiIiIiIiOcDw6VUPpKenc/jwYb7//nu2bdtGcnIyzz77bLbWcmh6lYiIiIh9s+fpVWd/i7fZ2FVL5LPZ2PbMbuYyOTg4EBgYSGJiImlpaXz99dfs3r3b6LBERERERORvMjzpSEpKYvfu3Xz33Xfs2rWLfPny0apVKz777DP8/f2NDk9ERERE8hjdMjfnGZ50BAUFkS9fPlq2bMnHH39M3bp19SBAEREREZHHiOFJx6xZs2jYsCGOjo5GhyIiIiIioptX2YDhSUfjxo05c+YM4eHhljtWmc1mkpOTOX36NGPHjjU4QhERERHJU5R15DjDk47Zs2cze/ZsihQpwq1bt/Dx8eHmzZukpaXRsmVLo8MTEREREZG/yfDndCxfvpyxY8eyZ88eSpQowZdffsm+ffto2LAhTz75pNHhiYiIiEgeY7Lhf3mV4UlHdHQ0jRs3BsDX15djx47h5eXFW2+9xcaNGw2OTkRERERE/i7Dkw4fHx8iIyMBqFChAqdPnwbA09OT27dvGxmaiIiIiORBJpPttrzK8DUdL7/8MoMGDWLixIm0aNGCrl27UqxYMfbt20fVqlWNDk9ERERERP4mw5OO3r17U7x4cdzd3alZsybDhw9n2bJlFCxYkIkTJxodnoiIiIjkMXm4IGEzJrPZbDY6iJzWfNZ+o0MQERERkT+xbUADo0P4QxE3Emw2doVi7jYb254ZXukQEREREbErKnXkOCUdIiIiIiIZ5OVb29qK4XevEhERERGRx5sqHSIiIiIiGeTlW9vaiiFJR6dOnTA94t/m4sWLbRyNiIiIiIjYkiFJR1BQkOXP0dHRLF++nBYtWlCjRg2cnZ05c+YMGzdu5LXXXjMiPBERERHJw1ToyHmGJB39+/e3/Llr166MGDGCV1991apP3bp1Wb58eW6HJiIiIiIiOczwheRhYWE0aJD5Ps3+/v78/PPPBkQkIiIiInmayYZbHmV40lGtWjXmz59PUlKSpS0uLo6ZM2dSq1Yt4wITEREREZEcYfjdq8aNG0fPnj1p1KgRZcqUwWw2c/HiRUqWLMm8efOMDk9ERERE8hg9pyPnGZ50VKhQgU2bNrFv3z4iIiIAqFSpEg0bNsTJyfDw5BE4O5oY2LQ8jSsWJik1nZXHrrLy2G8P7Rv4RAF6BZehpJcbp6/fZebOC1yOSbTsb1KhMD0aPIm3pws//XaXD7ZHcONucm6dikiu0XUjkj26diQ36Ja5Oc/w6VUALi4ulCpViieffJKOHTtSrlw5HB0djQ5LHlGvRmWo7OPB22tPM2PnBTrVK02TCoUz9StT2J2Jbauy73w0vZef4NyNe3zwoh9uzve/DasV92Tks5VYeewqvZedICUtnVHPVs7t0xHJFbpuRLJH147IP5PhSUdsbCxdu3alXbt2DBw4kNu3bzNhwgSef/55rly5YnR48hfcnBxo4+fDx7svEh51j73nb7P8yFXa1Syeqe8LNYrz07U4Pj8YyeWYRObv+5V7yam0qFwEgFdql2TrzzfZ8NMNLsckMnv3RQp7OOPlpoqXPF503Yhkj64dyS1aR57zDE86xo8fj7u7OwcOHMDV1RWACRMmULx4ccaPH29wdPJXyhfJh5ODiZ9+u2tpO/XbXXyL5890YZXwcuXstbtWbedvxVOtRH4A/EsVYE/Ebcu+a3eSeO2LY9xJTLVZ/CJG0HUjkj26dkT+uQxP53/44Qe+/PJLvLy8LG3e3t4MHz6cjh07GhiZPApvDxdiE1JITTdb2qLjU3B1csDLzYnYDP94R8en4O3pYvX+Yp6u3E1MxcPFES83JxwcTEx+wZcKRfJx5nocM3de4OY9za+Vx4uuG5Hs0bUjuUVrOnKe4ZUOwOp2uQ/cvn1bC8n/AVydHEhJM1u1paSlA+DsaP3ttTP8Fk0relO/bEEcTPBM1aJUKeaBk6MJd+f7a3j6NynL1p+jeHfDWZwdHRjftmqeLkXK40nXjUj26NoR+ecy/FP9888/z4QJE3jvvfcwmUzEx8dz4MABxowZQ5s2bYwOT/5Cclo6zo7W/0Q/+Ic/KTXdqv3wrzEsPnSZMW2q4GgyEXYllu/P3sTD1ZE08/0fIhtP32DrzzcBmLQlnFU96uBb3JPT1+Jy4WxEcoeuG5Hs0bUjuUfpZ04zPOkYOnQo06dPp3379qSkpBASEoKjoyMdOnRg6NChRocnf+FmXDIF3J1xMMGDanfhfM4kpqQRl5R5XuxXP15h5dGreLg6EpOQyqhWlbh2J4nYhBRS0tKJjE6w9L2TmMqdxBSK5XfVDwB5rOi6EckeXTsi/1yGT69ycXHhnXfe4fDhw6xfv561a9dy8OBBQkNDiY+PNzo8+QsRN+NJTTdTrXh+S1v1kvn5+cY9zL/r+1Qlb/o2LktKupmYhFRcHB2oVboAYVdiSTdD+I17VCiSz9Lfy80JLzdnrt3JPP1O5J9M141I9ujakdxiMtluy6sMTzp8fX25ffs2bm5uVKpUiapVq+Lh4cGVK1do3ry50eHJX0hKTWfLmRu8+VR5qhTzoFH5QrwcUJI1x+8/qKlQPmdc/q/0fTkmkbbVfQiuUJhSBdwY+Wwlou4mcehiDAArj13lxZolaFKxME8WcmdoiwpE3LzH2ev6jZM8XnTdiGSPrh3JLbplbs4zmc3m3/9ywObWrVvHmjVrADh06BABAQE4Oztb9blx4wbp6els2bIly+M3n7U/R+KUR+Pq5MCbzcrRuII395LTWH70CmuOXwNg24AGTPn+HN+djQLgWd+idKpbGi93J45F3mHGzvPcjk+xjNXGrxiv1SlFQXdnjl+5w/Tt53UnEXks6boRyR5dO4+PbQMaGB3CH7oaY7vvg5IFXf660/9JSkpi7NixbNmyBTc3N7p370737t0f2nfPnj1MmTKFyMhI/P39GT16NOXLl7fsr1OnDnfvWt9G+ujRo3h4ePD999/Tv39/q33PPvssM2fOBOD06dOMGTOGX375hYoVKzJ27FiqV6/+yOcBBiUd9+7d47PPPgNg9uzZdOvWDQ8PD6s++fLlo2XLljzxxBNZHl9Jh4iIiIh9s+ek47dY2yUdJQo8etIxbtw4Dh8+zKRJk7h69SrDhg1j4sSJtGrVyqpfeHg4ISEh9OzZk7Zt27Jq1SrWr1/P5s2b8fDw4Pr16zRp0oStW7fi5uZmeV+RIkUwmUzMmTOH48ePM27cOMs+V1dXvLy8iI+P55lnnqFt27Z06NCBpUuXsmnTJr7//nvy5cvHozJkIbmHh4clmypVqhRt2rSxPBhQRERERCSvi4+PZ+XKlSxYsAA/Pz/8/PwIDw9nyZIlmZKOpUuXEhAQwMCBAwEYMmQIO3fuZP369XTs2JGIiAiKFi36h7/Mj4iIoHLlyhQtWjTTvo0bN+Lq6srQoUMxmUyMHDmS3bt3s3nzZtq3b//I52P43atefPFFzp8/z88///zQ53WEhITkflAiIiIikmeZ7GD1xdmzZ0lNTSUgIMDSFhgYyNy5c0lPT8fB4f8vzY6MjKRmzZqW1yaTicqVKxMWFkbHjh05d+4c5cqV+8NjRURE0LBhw4fuO378OIGBgZj+bxW8yWSidu3ahIWF/bOSjs8//5zJkyfj5eWFp6en1T6TyaSkQ0REREQeG8nJySQnW0/fcnFxwcXFetpVVFQUhQoVsmovUqQISUlJxMTEULhwYav269evW73/2rVrFChQALifVCQkJNCpUycuXLiAr68vI0aMoFy5cpjNZi5cuMCePXuYN28eaWlptGrVijfeeAMXFxeioqKoWLGi1dje3t6Eh4dn6bwNTzoWLFjAO++8Q9euXY0ORURERETEpreZmjdvHrNnz7Zq69+/PwMGDLBqS0hIyJSIPHj9+6SldevW9O3bl+eff57GjRuzfv16Tp48SVBQEADnz58nNjaWQYMG4enpyYIFC+jatSvffvstsbGxlmN99NFHXL58mfHjx5OYmMi77777h3H8Poa/YnjSkZiYqFvjioiIiEie0KtXL7p162bV9vsP9XB/IffvP9g/eJ1xMThAkyZN6NevHwMGDCAtLY2goCDatWtHXNz9W0AvXLiQlJQUy42bpk2bRtOmTdmxYwdt27bl4MGDFChQAJPJhK+vL+np6QwZMoThw4f/YRy/j+GvGP6cjnbt2vHVV18ZHYaIiIiICGDb53S4uLjg6elptT0s6fDx8SE6OprU1FRLW1RUFG5ubnh5eWXq36dPH44ePcqePXv4/PPPuXfvHqVKlYL/O2bGO8W6urpSunRpy5SsggULWtZsAFSoUIGkpCRiY2Px8fHh5s2bVse6efMmxYoVe8Sv5n2GVDo6depkObGUlBSOHTvGpk2bKF26tNWiGIDFixcbEaKIiIiI5FH28ORwX19fnJycCAsLo06dOgAcOXKEGjVqZPq8vGHDBo4fP87IkSPx9vYmMTGRgwcPMnnyZMxmMy1btqRv376Whd/x8fFcunSJ8uXL88MPP/D222+zc+dO3N3dAThz5gwFCxakcOHC+Pv7s2DBAsxmMyaTCbPZzNGjR+ndu3eWzseQpOPB/LIHGjVqZEQYIiIiIiJ2yd3dnZCQEEJDQ5k4cSI3btxg0aJFTJo0Cbhf9cifPz9ubm6ULVuW4cOHU7duXSpXrszUqVMpUaIETZo0wWQy0axZM2bNmkWpUqUoXLgwM2bMoHjx4jRt2pSEhARcXV1599136devH5GRkUyZMoXXX38dgFatWvHBBx8wYcIEOnbsyLJly0hISKB169ZZOh9DHg5oa3o4oIiIiIh9s+eHA0bdTf3rTtlUNP+j/84/ISGB0NBQtmzZgqenJz169LDcfKlKlSpMmjTJUr1YvXo1H3/8MTExMTRo0IAxY8ZYpkAlJSXx4YcfsmHDBuLi4qhfvz5jxoyhRIkSwP2HC06cOJGwsDA8PDzo2LEj/fr1s8xMOnHiBGPGjCEiIoIqVaowduxYqlWrlqXzNjzpyDjVKiOTyYSzszNFixaldevWNGnS5JHHVNIhIiIiYt+UdOQthi8kr1u3LkePHqVo0aK0bNmSFi1aULx4cY4cOUKxYsVwd3dn0KBBrF692uhQRURERCQvsOVK8jzK8FRr//79DB8+nNdee82qvU6dOnz99dcsWbKE+vXrM336dF566SWDohQRERERkewyvNJx+vTphy4kr1evHidPngSgevXq/Pbbb7kdmoiIiIjkQSp05DzDk46qVavyv//9j98vLfnqq68sj1w/efIkxYsXNyI8ERERERH5mwyfXjVq1Cj++9//snPnTssq+DNnzhAXF8fcuXM5cuQIQ4YMYfTo0QZHKiIiIiJ5gT08p+NxY/jdqwDi4uL49ttv+eWXX3B0dKRSpUo899xz5MuXj8uXLxMXF0fVqlUfeTzdvUpERETEvtnz3atu30uz2diFPRxtNrY9M7zSAeDp6cm//vWvh+4rXbp0LkcjIiIiIiI5yZCko3nz5qxatYpChQrx9NNPP/Q5HQ9s27YtFyMTERERkbxO06tyniFJR//+/fHw8ABgwIABRoQgIiIiIiK5xJCk48UXX3zon2NjY8mfPz8mk+lPqx8iIiIiIvLPYfgtc81mM3PmzCEoKIgGDRpw5coVy92qkpOTjQ5PRERERET+JsOTjo8//phvvvmGyZMn4+LiAtyvfuzdu5cpU6YYHJ2IiIiI5DUmk+22vMrwpGPt2rW89957PPXUU5YpVY0aNeL9999n06ZNBkcnIiIiIiJ/l+G3zL116xbFihXL1O7l5UV8fLwBEYmIiIhIXmYiD5ckbMTwSkf9+vVZuHChVVtcXBzTp08nKCjIoKhEREREJK/S9KqcZ3jSERoayunTp2nUqBFJSUn07duXpk2bcuXKFd59912jwxMRERERkb/J8OlVxYsXZ9WqVezfv5/z58+TmppKuXLlCA4OxsHB8JxIRERERPKYPFyQsBnDk45XX32Vpk2bEhwczGuvvWZ0OCIiIiIiksMMTzpCQkLYu3cvn332GY6OjjRq1IjGjRsTHBxMoUKFjA5PRERERPIalTpynMlsNpuNDgLuPyTw9OnT7N+/n71793L48GF8fX1ZuXJllsdqPmu/DSIUERERkZyybUADo0P4Q3eT0m02dn7XvLl8wPBKB0BaWho//fQTR48e5fjx4/zyyy+4uLjg5eVldGgiIiIiksfolrk5z/Cko1OnTpw6dQovLy/8/f0JDAykV69eVKtWTQvJRUREREQeA4YnHU5OTphMJgoVKkSxYsXw8fHBx8dHCYeIiIiIGCIvP0/DVuxiTUdqaio//fQThw8f5scffyQsLIz8+fNTp04dJk2alOXxtKZDRERExL7Z85qOe8m2+3js4ZI3MxrDKx1wv9rh7++Ph4cH7u7uuLi4sGPHDg4cOGB0aCIiIiKSx+TNtMC2DE86lixZwqFDh/jxxx+Jj4+nbt26NGrUiIEDB1KhQgWjwxMRERGRvEZZR44zPOlYsWIFwcHBdOzYkcDAQFxcXIwOSUREREREcpDhScfXX39tdAgiIiIiIha6ZW7O0y2iRERERETEpgyvdIiIiIiI2BPdMjfnqdIhIiIiIiI2ZRfP6RARERERkceXKh0iIiIiImJTSjpERERERMSmlHSIiIiIiIhNKekQERERERGbUtIhIiIiIiI2paRDRERERERsSkmHiIiIiIjYlJIOERERERGxKSUdIiIiIiJiU0o6JFcdPHiQKlWq5Fg/Ecns8uXLVKlShcuXLwNQpUoVDh48aHBUIg+3bds2mjRpgr+/Pz/88AMAycnJPP/88/q+FXmMKOmQXBUQEMCePXtyrJ+IiPyzzZw5k+DgYDZu3EjdunVJSkpi0KBBhIeHGx2aiOQgJR2Sq1xcXChatGiO9RMRkX+2u3fvEhgYSKlSpbh8+TKvvPIKv/76q9FhiUgOU9IhwP+fjrF+/XoaN25MnTp1GD9+PKmpqcyaNYu+ffvy2muvUa9ePQ4dOkRycjLjx48nKCiIoKAg3n77bWJiYizjXbp0iR49ehAQEECzZs1YvHgxkHna1OLFi3nqqaeoUaMG7du358cff3xov2vXrjFw4EDq1atHUFAQ48ePJzk5GYA1a9bQqVMnZs6cSVBQEHXq1GHSpEmYzeZc+MqJPLoH19nHH39M3bp1ee+99/j+++9p06YN/v7+dOjQgUOHDln6p6amMn36dIKDgwkMDOSNN94gOjoagOvXr/PGG29Qt25dqlevzosvvsiRI0eMOjWRbHn66ae5cuUKI0aM4Omnn+bQoUMEBQWxfPnyR3r/2bNn6dixI/7+/jRu3JjZs2db9sXHxzN69GjLz6lRo0aRlJQEQGxsLKNGjaJhw4YEBgYyZMgQYmNjgfs/f55++mnGjBlDYGAg8+fPB2DZsmU8/fTTBAQE0KlTJ37++ecc/mqIPN6UdIiV2bNn8+GHHzJ79my2bNnCrFmzgPtzbp9//nm++OILatasyfTp0zl16hQLFixg8eLFxMXFMXDgQACSkpLo3r07Hh4erFixgtGjR/Phhx+yY8cOq2OdPn2aKVOmMGbMGDZt2kSdOnV48803SU9Pt+qXnJxMly5dSEhI4Msvv+Sjjz5i586dTJkyxdLn2LFjXLhwgaVLlzJq1CgWL17Mvn37bPzVEsmeo0ePsnr1al555RWGDRtGnz59+Oabb3jhhRf473//y6VLlwCYMWMGa9euZeLEiSxfvpxbt24xZswYAN5++23S0tJYtmwZ69atw8fHh9DQUAPPSiTrVq1aRfHixRkxYgSrVq3i1VdfZcSIEbi7uz/S+4cOHYqvry8bNmxgwoQJfPrpp+zatQuAd999lyNHjvDJJ5+waNEijhw5wkcffQRA//79OXPmDHPnzuWzzz4jIiKCd955xzLulStXSE5OZs2aNTz//PNs376d2bNnM2rUKNauXUtgYCCdO3e2JCoi8gjMImazOTIy0ly5cmXz999/b2lbtWqVuX79+uYZM2aYGzZsaGmPj483+/n5mc+ePWtpi42NNVetWtV89uxZ89atW821atUy371712qsnTt3mg8cOGCuXLmy2Ww2m7ds2WKuXr26+eeffzabzWbzvXv3zPv27TOnpKRY9du6davZ39/fHBMTYxlv165d5mrVqpnj4uLMq1evNletWtXqeCEhIeY5c+bk8FdJ5O95cJ3t2rXLbDabzW+//bZ50qRJVn369+9vnjRpkjk9Pd1cr1498+rVqy37wsPDzTNnzjSnp6ebP//8c/Nvv/1m2bd7925z1apVrY4TGRlpNpvN5sqVK5sPHDhg69MTyZannnrK6vv8gUf5vq1du7b5o48+MqelpZnNZrP56NGj5hs3bphjYmLMvr6+Vu8/fPiwefHixeYzZ86YK1eubD5//rxl37lz58yVK1c2R0REWH7+nDt3zrL/3//+t3nx4sVWx37xxRcztYnIH3MyOukR+1K7dm3Ln6tXr87t27eJjo6mVKlSlvbIyEhSUlLo2LGj1XvT09O5ePEikZGRlCtXDk9PT8u+l156CcDqTiTBwcFUrlyZtm3bUq1aNZo3b87LL7+Mk5P1t2VERARly5alQIECVnGmpqZa5v16e3tbHc/T05PU1NS/86UQsZkH11NERASbNm2ymkqSkpJCcHAw0dHRxMTE4OfnZ9lXsWJFBgwYAMC///1vNm7cyNGjR7lw4QKnTp3KVCUUeZy8/vrrVlMIjx07Rq9evZg+fTrLly+nWbNmtGvXjqJFi3LixAnS0tKsrp86depQp04dNm7ciJeXF+XKlbPsq1ChAgUKFOD8+fPkz58fgNKlS1v2R0REMHXqVKZPn25pS0pK4uLFizY8Y5HHi5IOseLs7Gz584MPMA4ODri6ulra09LSAPjqq6/Ily+f1fu9vb1ZtWrVIx3L3d2dlStXcujQIXbs2MGaNWtYunQpa9asseqX8di/j+HB/11cXDL1MWtNh9ipB9/TaWlp/Pe//yUkJMRqv5ubW6bkO6P09HS6d+/OnTt3aNOmDU8//TQpKSn079/flmGLGGrChAkkJiZatfXs2ZPWrVuzdetWtm/fTpcuXRg3bhzVq1f/w3Ee9vMC7l+PD36mAJl+7o0YMYIGDRpYvSfjL7tE5M9pTYdYOXPmjOXPp06dolixYhQsWNCqzxNPPIGjoyMxMTGUKVOGMmXK4OnpyaRJk7h16xZly5bl0qVLJCQkWN7z/vvvM378eKtxjh07xrx586hfvz7Dhw9n8+bNJCUlZVoMW65cOS5evGi1UD0sLAwnJyf+X3v3HhLVtsBx/GtOaShGJSSYqWlOSlCRZpH0GiscPL0oI6JoilIKwl5aYRHZRGQP7KFmEVr0joxqskjNgtLeoVBGb7OwSOhhb6PzR7e5Z65563baHm78Pn+utVh7rwV7ht+sNWt36tTp1w1epJkFBwdTU1PjfI4CAwPZu3cvZ86cwcfHh7Zt21JVVeVsf+PGDfr378+tW7e4ePEieXl5JCUlMXDgQJ4+fQoobMvvq0OHDi7Pyvv371m+fDmtWrXCZrOxY8cOEhISOHHihPN76q/PT1FREaNGjSI4OJiXL19y9+5dZ93t27epr693Wf34q+DgYGpra12un5OTw7Vr14wetshvQ6FDXNjtdiorKzl37hyZmZlMmDChURtvb2/Gjh3L0qVLOX/+PLdv3yYlJYUHDx7QsWNHYmJi8PX1ZcmSJdy5c4fi4mL27NlDTEyMSz+enp5s2rSJ/fv3U1NTg8Ph4M2bN41eCtivXz8CAgJISUnh5s2blJeXk56eTnx8PD4+PobOh4iRJk+ezLFjx9i+fTvV1dXk5eWRl5dHUFAQABMnTiQzM5Py8nJu3bqF3W6nR48etGnThhYtWuBwOHj06BHHjx93Hvrw9VQ3kd+dh4cHV65cIT09nbt371JZWcmlS5eIiIjA29ubkSNHYrfbqaiooLKyknXr1tGnTx9CQkLo378/qampVFRUUFFRQWpqKlFRUYSFhX3zWjabjfz8fA4dOkR1dTUZGRkUFhYSEhLSzKMW+f+l0CEurFYriYmJzJkzh7FjxzJ9+vRvtluwYAF9+/Zl1qxZJCQkYDKZyM3Nxd3dHZPJRFZWFk+fPmXUqFHY7XZSUlIYOHCgSx/h4eHO00bi4uLIyckhIyOj0Ye4u7s7WVlZACQkJDBnzhwsFgvLli0zZA5EmkuPHj1YtWoVu3btwmq1sm/fPtasWUNUVBTwZevI0KFDSU5OZvz48fj5+ZGeno6fnx9Lly5ly5YtxMfHk5ubS1paGiaTievXr//DoxJpPuvWrePt27eMGTOGqVOnEhkZyYwZMwBYtGgRXbt2xWazMW3aNKKjo5k9ezbwZfU9ICCAyZMnM3XqVLp06cKmTZuavI7VamX27NmsX7+e+Ph4ysrKyM7Odv5AICLf5/ZZa/HCl/cHWCwWiouLXf48JyIiIiLyd2mlQ0REREREDKXQISIiIiIihtL2KhERERERMZRWOkRERERExFAKHSIiIiIiYiiFDhERERERMZRCh4iIiIiIGEqhQ0REREREDKXQISLyi5nNZsxmM48fP25Ut3v3bsxmMxs2bPihvurq6igsLGyy/uDBgwwePPin71VERKQ5KHSIiBigZcuWlJSUNCovKirCzc3th/tZvXo1p0+fbrLearVy4MCBn7pHERGR5qLQISJigMjIyEaho76+nqtXrxIREfHD/XzvVUqenp60a9fup+5RRESkuSh0iIgYwGKxcOHCBerr651lpaWlREZG4uXl5dJ2z549DB48mJ49ezJx4kRu3rwJwIYNGygoKKCgoMC5hcpsNpOZmUl0dDRJSUmNtldVVFQwfvx4unfvzrBhw3A4HAB8/PiRtLQ0oqOj6dmzJ0lJSTx58sToaRAREQEUOkREDBEWFkaHDh04c+aMs+zkyZPExsa6tCspKWHjxo0sXryYgoICevXqxaRJk3jx4gVTpkwhLi6OuLg4ly1Up06dYvfu3cybN8+lr7q6OqZMmUJ4eDgFBQUkJiaSmppKVVUVO3fu5OLFi2zbto0DBw7w+vVrVqxYYewkiIiI/ItCh4iIQSwWi3OL1YcPHzh79iwWi8WlzdatW0lMTGTQoEEEBQWRnJyMv78/hw8fxsvLC09Pz0ZbqMaNG0fnzp0JDQ116cvhcNCmTRvS0tLo3Lkzo0ePZu7cubx7946amho8PDzw9/cnJCSElStXMn36dOMnQUREBDD90zcgIvK7slgszJo1i4aGBsrKyggLC6N9+/Yube7cuUNGRgZr1651lr1//5779+832a+/v/83y+/du0dERAQtWvz79ySbzQaAl5cXDoeDmJgYevfuTWxsLKNHj/4boxMREflxCh0iIgbp1asXAJcvX6aoqIghQ4Y0avPp0ycWLVpE3759Xcq9vb2b7NfDw+Ob5SZT0x/pXbp0oaSkhNLSUkpLS1m7di1Hjx5l586d/9NpWiIiIj9DoUNExCAmk4kBAwZQUlLCqVOnvrmdKTg4mNraWgIDA51lCxcuJDY2FovFgpub23dPsPoqKCiI06dP8/nzZ2eQSE5Oplu3bvj6+tKqVSusVitxcXFcu3aNcePGUVdXh6+v768ZsIiISBP0nw4REQNZLBb2799P+/btCQgIaFRvs9nIz8/n0KFDVFdXk5GRQWFhISEhIQC0bt2aR48e/dBJU3/88QfPnz9n1apV3L9/n4MHD1JcXEy/fv149eoVdrudsrIyHj58yJEjR/Dz86Nt27a/fMwiIiL/SSsdIiIGiomJoaGhodGpVV9ZrVaePXvG+vXrefbsGaGhoWRnZxMUFATAiBEjmDlzJsOHD6e8vPy/XsvHx4fNmzezYsUKduzYQUBAAGvWrCE8PByz2UxtbS3z58/nxYsXdOvWjezsbNzd3X/1kEVERBpx+/yj6/YiIiIiIiI/QdurRERERETEUAodIiIiIiJiKIUOERERERExlEKHiIiIiIgYSqFDREREREQMpdAhIiIiIiKGUugQERERERFDKXSIiIiIiIihFDpERERERMRQCh0iIiIiImIohQ4RERERETHUn9lxcZMrKSd2AAAAAElFTkSuQmCC"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot classification report\n",
+    "plot_classification_report(cr_v5)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T16:26:19.522283200Z",
+     "start_time": "2024-06-08T16:26:19.336932800Z"
+    }
+   },
+   "id": "a5685db72a4db790"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<Figure size 1000x600 with 1 Axes>",
+      "image/png": "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"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Accuracy comparison\n",
+    "accuracies = [acc_v1, acc_v2, acc_v3, acc_v4, acc_v5]\n",
+    "models = ['Neural Network V1', 'Neural Network V2', 'Neural Network V3', 'Neural Network V4', 'Neural Network V5']\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(10, 6))\n",
+    "sns.barplot(x=models, y=accuracies, hue=models, ax=ax)\n",
+    "\n",
+    "# Add labels\n",
+    "for i, v in enumerate(accuracies):\n",
+    "    ax.text(i, v + 0.01, str(round(v, 2)), ha='center', va='bottom')\n",
+    "\n",
+    "ax.set_title('Accuracy comparison')\n",
+    "ax.set_xlabel('Model')\n",
+    "ax.set_ylabel('Accuracy')\n",
+    "\n",
+    "plt.show()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T18:14:36.782522200Z",
+     "start_time": "2024-06-08T18:14:36.623693300Z"
+    }
+   },
+   "id": "822f2e6732f1a75d"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "0.9824561403508771"
+     },
+     "execution_count": 89,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "acc_v4"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-06-08T18:14:27.106543Z",
+     "start_time": "2024-06-08T18:14:27.067155600Z"
+    }
+   },
+   "id": "e85c80a8f36fd6a7"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "aa65d038e747f33"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}