From 025dd149df6c3f6f466b7bd85858a9e2e56cdf0b Mon Sep 17 00:00:00 2001
From: "andreas.zimmermann" <andreas.zimmermann@stud.hslu.ch>
Date: Tue, 24 Oct 2023 19:05:03 +0200
Subject: [PATCH] 08A done

---
 .../08A Neural Networks/Neural Networks.ipynb | 692 +++++++++++++++++-
 1 file changed, 655 insertions(+), 37 deletions(-)

diff --git a/notebooks/08A Neural Networks/Neural Networks.ipynb b/notebooks/08A Neural Networks/Neural Networks.ipynb
index da70ba0..240d381 100644
--- a/notebooks/08A Neural Networks/Neural Networks.ipynb	
+++ b/notebooks/08A Neural Networks/Neural Networks.ipynb	
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,19 +50,188 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(499999, 15)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>class</th>\n",
+       "      <th>t0</th>\n",
+       "      <th>t1</th>\n",
+       "      <th>t2</th>\n",
+       "      <th>t3</th>\n",
+       "      <th>t4</th>\n",
+       "      <th>t5</th>\n",
+       "      <th>t6</th>\n",
+       "      <th>t7</th>\n",
+       "      <th>t8</th>\n",
+       "      <th>t9</th>\n",
+       "      <th>t10</th>\n",
+       "      <th>t11</th>\n",
+       "      <th>t12</th>\n",
+       "      <th>t13</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>442326</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>147.785248</td>\n",
+       "      <td>145.541351</td>\n",
+       "      <td>149.439621</td>\n",
+       "      <td>0.753921</td>\n",
+       "      <td>1.431642</td>\n",
+       "      <td>3.517790</td>\n",
+       "      <td>0.491196</td>\n",
+       "      <td>-0.866637</td>\n",
+       "      <td>1.815981</td>\n",
+       "      <td>1.023984</td>\n",
+       "      <td>1.838293</td>\n",
+       "      <td>4.541910</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>220797</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>147.673752</td>\n",
+       "      <td>142.333054</td>\n",
+       "      <td>113.879356</td>\n",
+       "      <td>1.441206</td>\n",
+       "      <td>2.373645</td>\n",
+       "      <td>7.629642</td>\n",
+       "      <td>-1.529135</td>\n",
+       "      <td>-2.501392</td>\n",
+       "      <td>5.557172</td>\n",
+       "      <td>2.065227</td>\n",
+       "      <td>3.417144</td>\n",
+       "      <td>9.101445</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>251879</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>147.543015</td>\n",
+       "      <td>139.968277</td>\n",
+       "      <td>98.095177</td>\n",
+       "      <td>1.845582</td>\n",
+       "      <td>1.914326</td>\n",
+       "      <td>12.611120</td>\n",
+       "      <td>-1.830748</td>\n",
+       "      <td>-1.878371</td>\n",
+       "      <td>8.901849</td>\n",
+       "      <td>2.542774</td>\n",
+       "      <td>2.854787</td>\n",
+       "      <td>15.419715</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>285237</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>147.491776</td>\n",
+       "      <td>142.003952</td>\n",
+       "      <td>123.266624</td>\n",
+       "      <td>1.299123</td>\n",
+       "      <td>2.353261</td>\n",
+       "      <td>11.553779</td>\n",
+       "      <td>-1.523925</td>\n",
+       "      <td>-2.832719</td>\n",
+       "      <td>7.647702</td>\n",
+       "      <td>2.095353</td>\n",
+       "      <td>3.752808</td>\n",
+       "      <td>13.843594</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50676</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>149.468170</td>\n",
+       "      <td>137.266510</td>\n",
+       "      <td>136.136230</td>\n",
+       "      <td>1.000460</td>\n",
+       "      <td>0.780718</td>\n",
+       "      <td>4.431769</td>\n",
+       "      <td>-0.557105</td>\n",
+       "      <td>-0.598855</td>\n",
+       "      <td>2.950278</td>\n",
+       "      <td>1.225681</td>\n",
+       "      <td>1.002184</td>\n",
+       "      <td>5.491724</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        class   t0   t1          t2          t3          t4        t5  \\\n",
+       "442326      0  0.0  1.0  147.785248  145.541351  149.439621  0.753921   \n",
+       "220797      0  0.0  1.0  147.673752  142.333054  113.879356  1.441206   \n",
+       "251879      0  0.0  1.0  147.543015  139.968277   98.095177  1.845582   \n",
+       "285237      0  0.0  1.0  147.491776  142.003952  123.266624  1.299123   \n",
+       "50676       0  0.0  1.0  149.468170  137.266510  136.136230  1.000460   \n",
+       "\n",
+       "              t6         t7        t8        t9       t10       t11       t12  \\\n",
+       "442326  1.431642   3.517790  0.491196 -0.866637  1.815981  1.023984  1.838293   \n",
+       "220797  2.373645   7.629642 -1.529135 -2.501392  5.557172  2.065227  3.417144   \n",
+       "251879  1.914326  12.611120 -1.830748 -1.878371  8.901849  2.542774  2.854787   \n",
+       "285237  2.353261  11.553779 -1.523925 -2.832719  7.647702  2.095353  3.752808   \n",
+       "50676   0.780718   4.431769 -0.557105 -0.598855  2.950278  1.225681  1.002184   \n",
+       "\n",
+       "              t13  \n",
+       "442326   4.541910  \n",
+       "220797   9.101445  \n",
+       "251879  15.419715  \n",
+       "285237  13.843594  \n",
+       "50676    5.491724  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "df = pd.read_csv(\"skin_disease.csv\")\n",
     "df = df.sample(frac=1)\n",
-    "df = df.iloc[0:100000]\n",
+    "print(df.shape)\n",
+    "df = df.iloc[0:100_000]\n",
     "df.head()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -79,13 +248,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {
     "solution2": "hidden",
     "solution2_first": true
    },
    "outputs": [],
-   "source": []
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -106,6 +277,7 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)"
    ]
   },
@@ -118,7 +290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -137,7 +309,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -150,14 +322,71 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {
     "solution2": "hidden",
     "solution2_first": true,
     "tags": []
    },
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"â–¸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"â–¾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MLPClassifier(batch_size=1024, hidden_layer_sizes=(30, 15))</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MLPClassifier</label><div class=\"sk-toggleable__content\"><pre>MLPClassifier(batch_size=1024, hidden_layer_sizes=(30, 15))</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "MLPClassifier(batch_size=1024, hidden_layer_sizes=(30, 15))"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mlp.fit(X_train, y_train)\n",
+    "mlp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mlp.n_layers_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAi4AAAG1CAYAAADeA3/CAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/OQEPoAAAACXBIWXMAAA9hAAAPYQGoP6dpAABYmElEQVR4nO3de1xUdf4/8NdcYWAYLnINxAsGCKJgopJQaEY310ytzTLLUttdk36VVn5z3e92/3rdLb9qGtZma/UttTRts9rddjNF1M1MBQFvgMKAXIbLMANzzu+PYUZHQM9wmQF8PR+PeYBnzjlzzjuSl5/P53w+MlEURRARERH1AnJ3XwARERGRVAwuRERE1GswuBAREVGvweBCREREvQaDCxEREfUaDC5ERETUazC4EBERUa/B4EJERES9BoMLERER9RoMLkTUyiOPPIJHHnnE3ZdBRNQKgwsRERH1GgwuRERE1GswuBBRh+3duxcPPfQQbrrpJowZMwbPPfccLly4YH9fEASsXr0aEyZMwLBhwzBhwgSsXLkSTU1N9n2+/PJLTJ48GcOHD8fYsWOxcOFClJWVXfVz9Xo9XnjhBaSkpCApKQkzZ87Ef/7zHwBAcXExYmJisG3bNodjXnzxRUyYMMH+50ceeQQLFy5EZmYmEhMTMXv2bNxxxx3IzMxs9Xn33nsvfvvb39r//O2332Lq1KlISEjAuHHj8Oqrr6KhocG54hFRhzC4EFGHfP7553j88ccRFhaGVatWYfHixfjPf/6DX//617h48SIAYOPGjfjoo48wf/58bNq0CTNmzEBWVhbWrVsHADh06BCef/55ZGRkYOPGjVi8eDH279+P5557rt3Pra+vx4wZM5CdnY1FixZhzZo18PDwwOOPP44zZ844dQ9fffUVvL29sW7dOsyZMweTJ0/G999/j7q6Ovs+hYWFyM3Nxb333gsA2LlzJ+bPn4/Bgwfjf//3f/HUU09hx44d+N3vfgdRFJ2sIhE5S+nuCyCi3kcQBKxYsQKpqalYuXKlffvIkSNx9913IysrC88//zwOHDiAYcOGYdq0aQCA0aNHQ6PRwMfHB4A1uHh6emLevHlQq9UAAD8/Pxw9ehSiKEImk7X67O3bt6OkpATbt2/H0KFD7Z87ZcoU5OTkICUlRfJ9qFQq/PGPf7R/dmRkJN5++218++23mDJlCgBri5BOp8OECRMgiiJWrFiBtLQ0rFixwn6egQMH4rHHHsP333+P9PR06YUkIqexxYWInHb69GmUl5dj0qRJDtsjIyORlJSEAwcOAADGjBlj70569913UVBQgJkzZ9pbL5KTk2E0GjFp0iSsXLkSBw8eRGpqKp566qk2QwtgDTsRERH20AIAGo0GX3/9Ne6//36n7mPw4MH20AIA/fv3x8iRI7F79277tl27duHOO++EWq3GqVOnUFpaigkTJqC5udn+Sk5Ohlarxd69e536fCJyHoMLETmturoaABAYGNjqvcDAQNTW1gIA5syZg6VLl6KxsRErVqzAPffcg0mTJmH//v0AgKSkJGzYsAH9+/fHe++9h4cffhi33HILNm/efNXP7tevX5fch7e3d6tt9957L3788UdUVVXh6NGjOHv2rD1o2e77j3/8I+Lj4x1edXV10Ov1XXJdRNQ+dhURkdP8/PwAABUVFa3eKy8vh7+/PwBALpfj4YcfxsMPP4yLFy/i+++/x/r167FgwQLs3bsXarUaaWlpSEtLg9FoxP79+/HBBx/g1VdfxYgRIzB8+PBW5/fx8UFxcXGr7YcPH4avry88PT0BABaLxeF9qYNn77rrLrz66qv49ttvcerUKYSHh+Omm24CAOh0OgDA888/j9GjR7c61tfXV9JnEFHHscWFiJw2aNAgBAUF4csvv3TYXlRUhJ9++gkjR44EADz44IN49dVXAQD9+vXD1KlT8fDDD8NgMKCurg7/8z//g2nTpkEURWg0GowfPx4vvPACAOD8+fNtfvaoUaNQVFSE/Px8+zaTyYQFCxbgs88+g1arBQCHJ5Oamprw888/S7o3nU6H8ePH47vvvsPXX3+NyZMn27utBg8ejH79+qG4uBgJCQn2V0hICFauXInjx49L+gwi6ji2uBBRm0pLS/H++++32h4dHY2bb74Zzz77LBYvXoznnnsOkydPRlVVFdasWQNfX1/Mnj0bgHUMy6ZNmxAYGIikpCSUlZXhvffew+jRoxEQEICxY8fivffew4svvojJkyejqakJ7777Lvz8/DB27Ng2r2vq1KnYvHkzfvvb3yIzMxP+/v744IMP0NTUhIceegi+vr5ISkrC5s2bMWDAAPj6+uKDDz5AY2MjvLy8JN375MmTkZmZCYvFYu8mAgCFQoFnnnkGS5cuhUKhwPjx42EwGLB27VqUlZUhPj7e+UITkVNkIp/fI6IrPPLII/YBtleaPn06XnvtNQDA119/jXfeeQcnT56EVqtFWloann32WYSFhQEAmpubsW7dOuzYsQOlpaXw8fHBhAkT8Nxzz9m7k7788kts2rQJp0+fhkwmw0033YSFCxciJiam3esrKyvDsmXL8K9//QuCICAxMRGLFi1CbGwsAODMmTN45ZVXcPDgQWi1WkyfPh2enp749NNP8fe//91+jwDaHE/T1NSE1NRU9O/fH5999lmr93fv3o13330X+fn58PLywsiRI/H//t//u+o1E1HXYHAhIiKiXoNjXIiIiKjXYHAhIiKiXoPBhYiIiHoNBhciIiLqNRhciIiIqNdgcCEiIqJeg8GFiIiIeg2nZ84VBAFr1qzBp59+itraWiQnJ2Pp0qXo379/m/vv2LEDixYtarX9u+++Q0REBAAgIyMDZ8+edXj/vvvuw5tvvuns5QEARFGEIHT99DRyuaxbztvXsE7SsE7SsE7SsE7SsE7SuKNOcrms3VXhL+d0cFm7di22bNmCN998E6GhoVi+fDnmzJmDnTt3OiwPb5OXl4fRo0dj1apVDtsDAgIAWBc+KyoqwjvvvOMwXbZtobSOEAQRlZX1HT6+LUqlHP7+3jAYGtDcLHTpufsS1kka1kka1kka1kka1kkad9UpIMAbCkUXBxez2YxNmzZh4cKFSE9PBwCsXr0aaWlp2LNnDyZNmtTqmJMnTyImJgZBQUFtnrOgoACCICApKYkrqxIREdFVOTXGJTc3F/X19UhJSbFv0+l0iIuLQ05OTpvH5OXlISoqqt1z5uXlITAwkKGFiIiIrsmpFpfS0lIAsC+gZhMcHGx/73I1NTUoKyvDwYMHsWXLFlRVVWH48OFYtGgRBg0aBMAaXLy8vJCZmYnDhw/D398f06ZNw6xZsyCXd3zssFLZteOOFQq5w1dqG+skDeskDeskDeskDeskTU+vk1PBxWg0AkCrsSweHh6oqalptX9+fj4A62DZN954A42NjVi3bh0eeugh7Ny5E4GBgcjPz4fBYMAdd9yB+fPn49ChQ1i+fDlqamrw9NNPd+im5HIZ/P29O3Tsteh0mm45b1/DOknDOknDOknDOknDOknTU+vkVHCxDZg1m80Og2dNJhM0mtY3OGrUKOzbtw/+/v72kcJr1qxBeno6tm3bhnnz5mHjxo0wmUzw8fEBAMTExKCurg7r1q3DggULOtTqIggiDIYGp4+7GoVCDp1OA4PBCIuFg7rawzpJwzpJwzpJwzpJwzpJ46466XQaSa08TgUXWxeRXq9HZGSkfbter0dMTEybx9ieHrLRaDSIiIhAWVkZAGvrzZUtONHR0WhoaEBNTQ38/f2duUS77hoJbbEIHI0uAeskDeskDeskDeskDeskTU+tk1PNGbGxsdBqtcjOzrZvMxgMOH78OJKTk1vt/8knn2DMmDFoaLjU+lFXV4czZ85gyJAhEEUREydOxJo1axyOO3r0KIKCgjocWoiIiKhvciq4qNVqzJw5EytWrMB3332H3NxcPPPMMwgNDUVGRgYsFgvKy8vR2NgIALjlllsgCAKef/555Ofn4+jRo1iwYAECAgIwdepUyGQy3H777cjKysLu3btx7tw5fPLJJ3j33XeRmZnZLTdMREREvZfTE9BlZmaiubkZS5YsQWNjI5KTk5GVlQWVSoXi4mLcdttteOONNzB16lSEhYXh/fffx8qVKzFjxgyIoohx48bhgw8+gIeHBwDgueeeg1arxapVq1BaWoqIiAi89NJLeOCBB7r8ZomIiKh3k4mi2OfmPrZYhG6bObeqqr5H9vn1FKyTNKyTNKyTNKyTNKyTNO6qk3Xm3Gt3BPXMh7SJiIiI2sDgQkRERL0GgwsRERH1GgwuTuiDw4GIiIh6FQYXiQ6fLMeM33+Fn/Ir3H0pRERE1y0GF4nyzlWj3tiEE2cr3X0pRERE1y0GF4lULatNN/EROiIiIrdhcJFIpbAuEtls4TgXIiIid2FwkUjJFhciIiK3Y3CRSNUym18Tl0InIiJyGwYXiWxjXDhNNBERkfswuEikbGlxaWaLCxERkdswuEjEp4qIiIjcj8FFIra4EBERuR+Di0RscSEiInI/BheJ+FQRERGR+zG4SKTkU0VERERux+AikZItLkRERG7H4CIRx7gQERG5H4OLRPYJ6NjiQkRE5DYMLhLZH4du5iKLRERE7sLgIpFtdegmiwBRZHghIiJyBwYXiWxPFQFAs4XBhYiIyB0YXCRSOQQXjnMhIiJyBwYXiWxjXAA+Ek1EROQuDC4SyWUyKFvGuXASOiIiIvdgcHECH4kmIiJyLwYXJygVCgCchI6IiMhdGFycoFbZWlz4VBEREZE7MLg4wT7tP7uKiIiI3ILBxQkqrhBNRETkVk4HF0EQ8NZbbyEtLQ2JiYmYO3cuioqK2t1/x44diImJafUqLi627/PVV1/h7rvvxvDhwzFlyhTs27evY3fTzVS2MS5scSEiInILp4PL2rVrsWXLFrzyyiv4+OOPIQgC5syZA7PZ3Ob+eXl5GD16NH744QeHV1hYGABg//79WLRoER588EFs374dKSkpmDdvHgoLCzt3Z91ApWKLCxERkTs5FVzMZjM2bdqEzMxMpKenIzY2FqtXr0ZpaSn27NnT5jEnT55ETEwMgoKCHF6KltaLjRs3YuLEiZg1axaioqLwwgsvID4+Hn/5y186f3ddjGNciIiI3Mup4JKbm4v6+nqkpKTYt+l0OsTFxSEnJ6fNY/Ly8hAVFdXme4Ig4PDhww7nA4AxY8a0ez53Uik4jwsREZE7KZ3ZubS0FADs3Tw2wcHB9vcuV1NTg7KyMhw8eBBbtmxBVVUVhg8fjkWLFmHQoEEwGAxoaGhAaGiopPM54/JFEbuCQiGHSmltJRLErj9/X6FoCXcKBetzNayTNKyTNKyTNKyTND29Tk4FF6PRCABQq9UO2z08PFBTU9Nq//z8fACAKIp444030NjYiHXr1uGhhx7Czp070dzc3O75TCaTM5fmQC6Xwd/fu8PHt8c2xkWlVnbL+fsSnU7j7kvoFVgnaVgnaVgnaVgnaXpqnZwKLp6engCsY11s3wOAyWSCRtP6BkeNGoV9+/bB398fMpl1nZ81a9YgPT0d27Ztw/33328/3+XaO59UgiDCYGjo8PFtsba4WIOLobYRVVX1XXr+vkKhkEOn08BgMMLCLrV2sU7SsE7SsE7SsE7SuKtOOp1GUiuPU8HF1kWk1+sRGRlp367X6xETE9PmMQEBAQ5/1mg0iIiIQFlZGfz8/ODl5QW9Xu+wj16vR0hIiDOX1kp3PPljG+NiMlv4ZNE1WCwCayQB6yQN6yQN6yQN6yRNT62TUx1YsbGx0Gq1yM7Otm8zGAw4fvw4kpOTW+3/ySefYMyYMWhouNT6UVdXhzNnzmDIkCGQyWQYOXIkDhw44HBcdnY2Ro0a5ey9dDsuskhEROReTgUXtVqNmTNnYsWKFfjuu++Qm5uLZ555BqGhocjIyIDFYkF5eTkaGxsBALfccgsEQcDzzz+P/Px8HD16FAsWLEBAQACmTp0KAJg9ezZ27dqF9957D4WFhVi2bBlOnDiBRx99tOvvtpNsg3O5yCIREZF7OD1kODMzE9OnT8eSJUswY8YMKBQKZGVlQaVS4cKFC0hNTcXu3bsBWLuW3n//fTQ0NGDGjBl47LHH4OPjgw8++AAeHh4AgNTUVLz++uv46KOPcN9992H//v1Yv359u49Qu5NtkUXO40JEROQeMlEU+9xSxxaLgMrKrh08q1TK8bcDRdiyJw/pSeGYdUfbY3qud0qlHP7+3qiqqu+RfaM9BeskDeskDeskDeskjbvqFBDgLWlwbs98SLuHUnKRRSIiIrdicHGCfYwLu4qIiIjcgsHFCWouskhERORWDC5OsM3jwhYXIiIi92BwcQLncSEiInIvBhcn2Ma4sKuIiIjIPRhcnGBrcWFXERERkXswuDjBHlya+9zUN0RERL0Cg4sTOMaFiIjIvRhcnMDgQkRE5F4MLk7gIotERETuxeDiBLa4EBERuReDixP4VBEREZF7Mbg4wd7iwqeKiIiI3ILBxQm2MS6CKMIisNWFiIjI1RhcnKBWXioXW12IiIhcj8HFCarLggvHuRAREbkeg4sTFAo5ZDLr93yyiIiIyPUYXJykUtgG6DK4EBERuRqDi5OUfCSaiIjIbRhcnHRpoUUGFyIiIldjcHGSvavIwqeKiIiIXI3BxUlKBaf9JyIichcGFyexq4iIiMh9GFycxPWKiIiI3IfBxUlKPg5NRETkNgwuTuIYFyIiIvdhcHGSSmmdOpddRURERK7H4OIkdhURERG5D4OLky4NzuU8LkRERK7G4OIkFce4EBERuY3TwUUQBLz11ltIS0tDYmIi5s6di6KiIknH7tixAzExMSguLnbYnpGRgZiYGIfXiy++6OyluYRtrSJ2FREREbme0tkD1q5diy1btuDNN99EaGgoli9fjjlz5mDnzp1Qq9XtHldSUoKXX3651faGhgYUFRXhnXfeQXx8vH27p6ens5fmErYWFw7OJSIicj2nWlzMZjM2bdqEzMxMpKenIzY2FqtXr0ZpaSn27NnT7nGCIGDRokUOwcSmoKAAgiAgKSkJQUFB9pePj4/zd+MCnDmXiIjIfZwKLrm5uaivr0dKSop9m06nQ1xcHHJycto9bv369WhqasKTTz7Z6r28vDwEBgbC19fXmUtxG87jQkRE5D5OdRWVlpYCAMLCwhy2BwcH29+70s8//4xNmzbhs88+Q1lZWav38/Ly4OXlhczMTBw+fBj+/v6YNm0aZs2aBbm8540dtrW4MLgQERG5nlPBxWg0AkCrsSweHh6oqalptX9DQwMWLlyIhQsXYuDAgW0Gl/z8fBgMBtxxxx2YP38+Dh06hOXLl6OmpgZPP/20M5fnwDaItqsoWlpa1CoFAMAiiF3+GX2BrU62r9Q21kka1kka1kka1kmanl4np4KLbcCs2Wx2GDxrMpmg0Wha7f/qq69i0KBBePDBB9s958aNG2EymexjWmJiYlBXV4d169ZhwYIFHWp1kctl8Pf3dvo4KXy0HrYP6bbP6At0utY/D9Qa6yQN6yQN6yQN6yRNT62TU8HF1kWk1+sRGRlp367X6xETE9Nq/61bt0KtViMpKQkAYLFYAACTJk3Cb37zG/zmN7+BWq1u1YITHR2NhoYG1NTUwN/f37k7AiAIIgyGBqePuxqFQg6dToPmJus9NBjNqKqq79LP6AtsdTIYjLCwO61drJM0rJM0rJM0rJM07qqTTqeR1MrjVHCJjY2FVqtFdna2PbgYDAYcP34cM2fObLX/lU8aHTlyBIsWLcKGDRsQHR0NURRx++23Y8qUKXjqqafs+x09ehRBQUEdCi023TXPiq2mTU0C53K5CouF9ZGCdZKGdZKGdZKGdZKmp9bJqeCiVqsxc+ZMrFixAgEBAQgPD8fy5csRGhqKjIwMWCwWVFZWwsfHB56enhgwYIDD8bYBvDfccAP8/PwAALfffjuysrIwePBgDBs2DPv27cO7776Ll156qWvusIvxqSIiIiL3cXoCuszMTDQ3N2PJkiVobGxEcnIysrKyoFKpUFxcjNtuuw1vvPEGpk6dKul8zz33HLRaLVatWoXS0lJERETgpZdewgMPPOD0zbgC53EhIiJyH5koin1utUCLRUBlZdeOP1EqrYNxvz94Fis++gmRIVr89+zRXfoZfYGtTlVV9T2yibGnYJ2kYZ2kYZ2kYZ2kcVedAgK8JY1x6ZnPOvVgl7qK+lzeIyIi6vEYXJxkXx2aaZ2IiMjlGFycZJt0jossEhERuR6Di5M4OJeIiMh9GFycpOLj0ERERG7D4OIkzuNCRETkPgwuTrq0OrSIPvgkORERUY/G4OIk1WUrQrPVhYiIyLUYXJykvGxynKZmtrgQERG5EoOLk5QKmf17trgQERG5FoOLk2QymT28MLgQERG5FoNLB9i6iziXCxERkWsxuHSAirPnEhERuQWDSwdwLhciIiL3YHDpgEsLLfKpIiIiIldicOkALrRIRETkHgwuHaDi4FwiIiK3YHDpAKWSj0MTERG5A4NLB3CFaCIiIvdgcOkAzuNCRETkHgwuHWAPLmxxISIicikGlw6wTUDXzBYXIiIil2Jw6YBLE9BxHhciIiJXYnDpAFXLU0XsKiIiInItBpcO4OBcIiIi92Bw6QD7GBe2uBAREbkUg0sH2Me4sMWFiIjIpRhcOoAT0BEREbkHg0sHcJFFIiIi92Bw6QAuskhEROQeDC4doFRyHhciIiJ3cDq4CIKAt956C2lpaUhMTMTcuXNRVFQk6dgdO3YgJiYGxcXFDtu/+uor3H333Rg+fDimTJmCffv2OXtZLqVUcHVoIiIid3A6uKxduxZbtmzBK6+8go8//hiCIGDOnDkwm81XPa6kpAQvv/xyq+379+/HokWL8OCDD2L79u1ISUnBvHnzUFhY6OyluQy7ioiIiNzDqeBiNpuxadMmZGZmIj09HbGxsVi9ejVKS0uxZ8+edo8TBAGLFi1CfHx8q/c2btyIiRMnYtasWYiKisILL7yA+Ph4/OUvf3H+blyEiywSERG5h1PBJTc3F/X19UhJSbFv0+l0iIuLQ05OTrvHrV+/Hk1NTXjyyScdtguCgMOHDzucDwDGjBlz1fO5GxdZJCIicg+lMzuXlpYCAMLCwhy2BwcH29+70s8//4xNmzbhs88+Q1lZmcN7BoMBDQ0NCA0NlXy+nkDJmXOJiIjcwqngYjQaAQBqtdphu4eHB2pqalrt39DQgIULF2LhwoUYOHBgq+DS2NjY7vlMJpMzl9aKLVx0FUVL95BCIYenWgHA+lRRV39Ob3d5nah9rJM0rJM0rJM0rJM0Pb1OTgUXT09PANaxLrbvAcBkMkGj0bTa/9VXX8WgQYPw4IMPtnk+Dw8P+/ku1975pJLLZfD39+7w8Vej02kQ0HJuQRS77XN6O52u4//9rieskzSskzSskzSskzQ9tU5OBRdbF5Fer0dkZKR9u16vR0xMTKv9t27dCrVajaSkJACAxWIBAEyaNAm/+c1v8OSTT8LLywt6vd7hOL1ej5CQEOfu5DKCIMJgaOjw8W1RKOTQ6TQwGIwwNlhbg0xmC6qq6rv0c3q7y+tkYVdau1gnaVgnaVgnaVgnadxVJ51OI6mVx6ngEhsbC61Wi+zsbHtwMRgMOH78OGbOnNlq/yufNDpy5AgWLVqEDRs2IDo6GjKZDCNHjsSBAwdw//332/fLzs7GqFGjnLm0Vrpr4KzFIkDW8n1Ts8ABuu2wWFgbKVgnaVgnaVgnaVgnaXpqnZwKLmq1GjNnzsSKFSsQEBCA8PBwLF++HKGhocjIyIDFYkFlZSV8fHzg6emJAQMGOBxvG3B7ww03wM/PDwAwe/ZszJs3D3FxcbjllluwdetWnDhxAq+99lrX3GE34CKLRERE7uH0yJvMzExMnz4dS5YswYwZM6BQKJCVlQWVSoULFy4gNTUVu3fvlny+1NRUvP766/joo49w3333Yf/+/Vi/fj2ioqKcvTSXuXyRRVHktP9ERESuIhP74G9ei0VAZWXXjj1RKuXw9/dGVVU9qmtNyPzzvwEAGxal2yekI8c69cQmxp6CdZKGdZKGdZKGdZLGXXUKCPCWNMaFv3E7QHXZI9DsLiIiInIdBpcOUCkuDy59rsGKiIiox2Jw6QC5XAa5zPpsERdaJCIich0Glw5SKluCC7uKiIiIXIbBpYPsj0SzxYWIiMhlGFw6iAstEhERuR6DSwfZWlzYVUREROQ6DC4dpGRXERERkcsxuHSQSskWFyIiIldjcOmgSy0unMeFiIjIVRhcOkilsD4OzcG5RERErsPg0kFKdhURERG5HINLB9m6ijhzLhERkeswuHSQivO4EBERuRyDSwdx5lwiIiLXY3DpICUnoCMiInI5BpcOujTlPx+HJiIichUGlw5ScXAuERGRyzG4dJBSyXlciIiIXI3BpYO4yCIREZHrMbh0EBdZJCIicj0Glw7iU0VERESux+DSQfYJ6NjiQkRE5DIMLh2k4uPQRERELsfg0kHKltWh2VVERETkOgwuHcTBuURERK7H4NJBtq4itrgQERG5DoNLB3GRRSIiItdjcOkgPg5NRETkegwuHXRpkUUGFyIiIldhcOkgLrJIRETkegwuHaTkPC5EREQu53RwEQQBb731FtLS0pCYmIi5c+eiqKio3f2PHTuGRx99FElJSRg7diyWLl2K2tpah30yMjIQExPj8HrxxRedvxsXUnEeFyIiIpdzOrisXbsWW7ZswSuvvIKPP/4YgiBgzpw5MJvNrfatqKjA7NmzER4ejm3btmHt2rU4dOiQQyhpaGhAUVER3nnnHfzwww/210svvdS5O+tmnMeFiIjI9ZwKLmazGZs2bUJmZibS09MRGxuL1atXo7S0FHv27Gm1f0lJCVJTU/Hyyy9j0KBBGDlyJB544AHs3bvXvk9BQQEEQUBSUhKCgoLsLx8fn87fXTeydRVZBBGCyO4iIiIiV3AquOTm5qK+vh4pKSn2bTqdDnFxccjJyWm1/4gRI7Bq1SoolUoAQGFhIb744guMGzfOvk9eXh4CAwPh6+vb0XtwC9vgXICtLkRERK6idGbn0tJSAEBYWJjD9uDgYPt77bnjjjtw5swZhIeHY82aNfbteXl58PLyQmZmJg4fPgx/f39MmzYNs2bNglze8bHDthaRrqJoCSq2rxrZpdKJsq7/vN7qyjpR21gnaVgnaVgnaVgnaXp6nZwKLkajEQCgVqsdtnt4eKCmpuaqx65YsQJGoxHLly/HrFmz8MUXX8Db2xv5+fkwGAy44447MH/+fBw6dAjLly9HTU0Nnn76aSdvx0oul8Hf37tDx16LTqcBAIiXdQ95az3h7+PZLZ/XW9nqRFfHOknDOknDOknDOknTU+vkVHDx9LT+cjabzfbvAcBkMkGjufoNJiQkAADWrFmDW2+9Fd988w2mTJmCjRs3wmQy2ce0xMTEoK6uDuvWrcOCBQs61OoiCCIMhganj7sahUIOnU4Dg8EIS8uTRCqFHE0WARUX64FmS5d+Xm/VVp2oNdZJGtZJGtZJGtZJGnfVSafTSGrlcSq42LqI9Ho9IiMj7dv1ej1iYmJa7X/q1CmcO3cO6enp9m0hISHw8/NDWVkZAGvrzZUtONHR0WhoaEBNTQ38/f2duUS77hp3YrEI9nMrldbg0mhq5jiXK1xeJ2of6yQN6yQN6yQN6yRNT62TU80ZsbGx0Gq1yM7Otm8zGAw4fvw4kpOTW+3/448/IjMzEwaDwb7t3LlzqKqqQlRUFERRxMSJEx3GvADA0aNHERQU1OHQ4iq2uVx64n9YIiKivsip4KJWqzFz5kysWLEC3333HXJzc/HMM88gNDQUGRkZsFgsKC8vR2NjIwBg0qRJ8PPzw6JFi5Cfn4+DBw8iMzMTw4cPx/jx4yGTyXD77bcjKysLu3fvxrlz5/DJJ5/g3XffRWZmZrfccFeyDcjlJHRERESu4VRXEQBkZmaiubkZS5YsQWNjI5KTk5GVlQWVSoXi4mLcdttteOONNzB16lT4+fnhL3/5C958803MmDEDCoUCt912G1588UUoFAoAwHPPPQetVotVq1ahtLQUEREReOmll/DAAw90+c12NfskdAwuRERELiETxb43e5rFIqCysr5Lz6lUyuHv742qqnp719Dv381GSUU9Fj6YiLiBAV36eb1VW3Wi1lgnaVgnaVgnaVgnadxVp4AAb0mDc3vmQ9q9xKWFFvk/ABERkSswuHSCbfbcpuY+12hFRETUIzG4dILS9lQRW1yIiIhcgsGlE9hVRERE5FoMLp1wqauIwYWIiMgVGFw6QcV5XIiIiFyKwaUTOI8LERGRazG4dII9uLCriIiIyCUYXDqBXUVERESuxeDSCSp7iwvncSEiInIFBpdOUCqt87iwxYWIiMg1GFw6gYNziYiIXIvBpRM4jwsREZFrMbh0AmfOJSIici0Gl05giwsREZFrMbh0wqUxLnyqiIiIyBUYXDrB9lQRu4qIiIhcg8GlE1QKBQB2FREREbkKg0snqDiPCxERkUsxuHQC53EhIiJyLQaXTuAii0RERK7F4NIJXGSRiIjItRhcOkHFFhciIiKXYnDpBKW9xYXzuBAREbkCg0snKBWcx4WIiMiVGFw64fKuIlFkqwsREVF3Y3DpBNvgXBGARWBwISIi6m4MLp1gexwa4Oy5RERErsDg0gm2wbkAx7kQERG5AoNLJ8hlMijktgG67CoiIiLqbgwunWR/JLrZ4uYrISIi6vucDi6CIOCtt95CWloaEhMTMXfuXBQVFbW7/7Fjx/Doo48iKSkJY8eOxdKlS1FbW+uwz1dffYW7774bw4cPx5QpU7Bv3z7n78RNbE8WcS4XIiKi7ud0cFm7di22bNmCV155BR9//DEEQcCcOXNgNptb7VtRUYHZs2cjPDwc27Ztw9q1a3Ho0CG8+OKL9n3279+PRYsW4cEHH8T27duRkpKCefPmobCwsHN35iL2uVw4OJeIiKjbORVczGYzNm3ahMzMTKSnpyM2NharV69GaWkp9uzZ02r/kpISpKam4uWXX8agQYMwcuRIPPDAA9i7d699n40bN2LixImYNWsWoqKi8MILLyA+Ph5/+ctfOn93LsAVoomIiFzHqeCSm5uL+vp6pKSk2LfpdDrExcUhJyen1f4jRozAqlWroFQqAQCFhYX44osvMG7cOADWbqfDhw87nA8AxowZ0+b5eiL7QotscSEiIup2Smd2Li0tBQCEhYU5bA8ODra/15477rgDZ86cQXh4ONasWQMAMBgMaGhoQGhoqNPnu5bLH1XuCoqWlhWFwvG8tuAidMNn9kbt1YkcsU7SsE7SsE7SsE7S9PQ6ORVcjEYjAECtVjts9/DwQE1NzVWPXbFiBYxGI5YvX45Zs2bhiy++QGNjY7vnM5lMzlyaA7lcBn9/7w4ffzU6ncbhzxoPFQDA01PVbZ/ZG11ZJ2ob6yQN6yQN6yQN6yRNT62TU8HF09MTgHWsi+17ADCZTNBorn6DCQkJAIA1a9bg1ltvxTfffINbb73Vfr7LSTnf1QiCCIOhocPHt0WhkEOn08BgMMLiMJ7F+jRRdY0RVVX1XfqZvVH7daLLsU7SsE7SsE7SsE7SuKtOOp1GUiuPU8HF1kWk1+sRGRlp367X6xETE9Nq/1OnTuHcuXNIT0+3bwsJCYGfnx/Kysrg5+cHLy8v6PV6h+P0ej1CQkKcubRWuuspH4tFcDi3smUCOpPZwieLLnNlnahtrJM0rJM0rJM0rJM0PbVOTnVgxcbGQqvVIjs7277NYDDg+PHjSE5ObrX/jz/+iMzMTBgMBvu2c+fOoaqqClFRUZDJZBg5ciQOHDjgcFx2djZGjRrl7L24hUqpAAA0Mb0TERF1O6eCi1qtxsyZM7FixQp89913yM3NxTPPPIPQ0FBkZGTAYrGgvLzcPnZl0qRJ8PPzw6JFi5Cfn4+DBw8iMzMTw4cPx/jx4wEAs2fPxq5du/Dee++hsLAQy5Ytw4kTJ/Doo492/d12A9s8LnyqiIiIqPs5PWQ4MzMT06dPx5IlSzBjxgwoFApkZWVBpVLhwoULSE1Nxe7duwEAfn5+9vlYZsyYgfnz5yMuLg5ZWVlQKKwtFampqXj99dfx0Ucf4b777sP+/fuxfv16REVFdeFtdh/bk0Scx4WIiKj7yURR7HNz1VssAioru3agrFIph7+/N6qq6h36/DbtPoEffr6AabcOxj0pA7v0M3uj9upEjlgnaVgnaVgnaVgnadxVp4AAb0mDc3vmQ9q9CCegIyIich0Gl066tMgigwsREVF3Y3DpJPtaRc19rseNiIiox2Fw6ST76tBscSEiIup2DC6dZB/jwuBCRETU7RhcOkll7ypicCEiIupuDC6dpGSLCxERkcswuHSSki0uRERELsPg0kn2riK2uBAREXU7BpdO4gR0RERErsPg0klK+wR0nMeFiIiouzG4dJJSyXlciIiIXIXBpZM4xoWIiMh1GFw6yd5VxDEuRERE3Y7BpZM4cy4REZHrMLh0EudxISIich0Gl06yzZzbzKeKiIiIuh2DSydxcC4REZHrMLh0km2Mi0UQIQhsdSEiIupODC6dpFTI7N9zgC4REVH3YnDpJNvgXIDdRURERN2NwaWTFHIZbG0ufLKIiIioezG4dJJMJuNCi0RERC7C4NIFLi20yOBCRETUnRhcugDnciEiInINBpcuoFJwhWgiIiJXYHDpAlxokYiIyDUYXLoAF1okIiJyDQaXLsCFFomIiFyDwaULXBqcy+BCRETUnRhcuoCKj0MTERG5hNPBRRAEvPXWW0hLS0NiYiLmzp2LoqKidvfPz8/HvHnzMGbMGKSkpCAzMxPnz5+3v2+xWDB8+HDExMQ4vN5+++2O3ZEbcAI6IiIi13A6uKxduxZbtmzBK6+8go8//hiCIGDOnDkwm82t9q2qqsLs2bPh6emJzZs3Y+PGjaisrMScOXNgMpkAAGfOnIHJZMIXX3yBH374wf56/PHHO393LmIf48J5XIiIiLqVU8HFbDZj06ZNyMzMRHp6OmJjY7F69WqUlpZiz549rfb/9ttv0dDQgGXLliE6OhrDhg3D8uXLUVhYiMOHDwMA8vLyoNVqERsbi6CgIPvL29u7a+7QBWwrRHNwLhERUfdyKrjk5uaivr4eKSkp9m06nQ5xcXHIyclptX9KSgrWrl0LT0/PSx8ot36kwWAAYA0uUVFRHbr4nkKl4OBcIiIiV1A6s3NpaSkAICwszGF7cHCw/b3LRUREICIiwmHbhg0b4OnpieTkZADAyZMn0dzcjCeeeAK5ubkICQnBo48+invvvdepG7mS7UmfrqJoCSe2r5dTqxQAAIsgdvnn9jZXqxNdwjpJwzpJwzpJwzpJ09Pr5FRwMRqNAAC1Wu2w3cPDAzU1Ndc8fvPmzfjwww+xZMkSBAQEALAO3hUEAZmZmQgNDcX333+PxYsXo6mpCdOnT3fm8uzkchn8/bunq0mn07TaptV6AAAUKkW3fW5v01adqDXWSRrWSRrWSRrWSZqeWiengouty8dsNjt0/5hMJmg07d+gKIr485//jHXr1uG3v/0tHnnkEft7X375JSwWi31MS2xsLM6fP4+srKwOBxdBEGEwNHTo2PYoFHLodBoYDEZYrugSsjRbAAB19SZUVdV36ef2NlerE13COknDOknDOknDOknjrjrpdBpJrTxOBRdbF5Fer0dkZKR9u16vR0xMTJvHNDU1YfHixfjyyy+xePFiPPbYYw7vXx6AbKKjo7Fjxw5nLq2V7hooa7EIrc4tl1kH55rNrd+7XrVVJ2qNdZKGdZKGdZKGdZKmp9bJqQ6s2NhYaLVaZGdn27cZDAYcP37cPmblSs8//zz+9re/YeXKla1Ci8FgwOjRo7Ft2zaH7UePHsWNN97ozKW5lW11aE5AR0RE1L2canFRq9WYOXMmVqxYgYCAAISHh2P58uUIDQ1FRkYGLBYLKisr4ePjA09PT2zbtg27d+/G888/j9GjR6O8vNx+Lh8fH+h0OowdOxarV69Gv379MGDAAOzZswc7duzAO++80+U3211USuvgXE5AR0RE1L2cCi4AkJmZiebmZixZsgSNjY1ITk5GVlYWVCoViouLcdttt+GNN97A1KlT8eWXXwIAli1bhmXLljmcx7bP66+/jrfffht/+MMfcPHiRURFRdln5u0t7PO4sMWFiIioW8lEUexz071aLAIqK7t2kKxSKYe/vzeqqupb9fn986cSfPC3PCTdGIgF04Z36ef2NlerE13COknDOknDOknDOknjrjoFBHhLGpzbMx/S7mW4yCIREZFrMLh0Adsii0zwRERE3YvBpQso2eJCRETkEgwuXcC+OnRznxsuRERE1KMwuHQBFZ8qIiIicgkGly5gW1iRXUVERETdi8GlC9gG53ICOiIiou7F4NIFbI9Dm5ss6IPT4hAREfUYDC5dINBPA6VChvrGZuirjO6+HCIioj6LwaULeKgUiLrBFwBw/GyVm6+GiIio72Jw6SJDB/oDAE4wuBAREXUbBpcuEjcgAACQe7YKAse5EBERdQsGly4yMMwHHmoF6oxNKNbXuftyiIiI+iQGly6iVMgR098PAHD8DLuLiIiIugODSxcaOoDjXIiIiLoTg0sXsgWXk0XVnP6fiIioGzC4dKGIYC20GhVMTRacvmBw9+UQERH1OQwuXUgukyHW1l3EcS5ERERdjsGli8W1BBdOREdERNT1GFy6mG0iusKSGpiaLG6+GiIior6FwaWLBftp0E/nAYsgIr+42t2XQ0RE1KcwuHQxmUyGoS2z6HKcCxERUddicOkGQznOhYiIqFswuHQD25NF50prUWdscvPVEBER9R0MLt3A38cDYf28IALIO1ft7sshIiLqMxhcuolttegTZyvdfCVERER9B4NLN4nlukVERERdjsGlm8QO8INMBly42ICqWpO7L4eIiKhPYHDpJt6eKgwI8QHA7iIiIqKuwuDSjWyz6LK7iIiIqGswuHSjoZeNcxFF0c1XQ0RE1Ps5HVwEQcBbb72FtLQ0JCYmYu7cuSgqKmp3//z8fMybNw9jxoxBSkoKMjMzcf78eYd9/vrXv+K2227D8OHD8dBDD+H48ePO30kPdGOEH5QKGSoNJuirjO6+HCIiol7P6eCydu1abNmyBa+88go+/vhjCIKAOXPmwGw2t9q3qqoKs2fPhqenJzZv3oyNGzeisrISc+bMgclkHbC6fft2LFu2DE8//TS2bduGiIgIzJ49G5WVvX9ciIdKgagbfAFwFl0iIqKu4FRwMZvN2LRpEzIzM5Geno7Y2FisXr0apaWl2LNnT6v9v/32WzQ0NGDZsmWIjo7GsGHDsHz5chQWFuLw4cMAgPXr12PmzJmYPHkyhgwZgtdffx0ajQaffvpp19yhm3GcCxERUddxKrjk5uaivr4eKSkp9m06nQ5xcXHIyclptX9KSgrWrl0LT0/PSx8ot36kwWDAxYsXcebMGYfzKZVKjBo1qs3z9Ua2cS65Z6sgcJwLERFRpyid2bm0tBQAEBYW5rA9ODjY/t7lIiIiEBER4bBtw4YN8PT0RHJyMi5cuNDu+XJzc525tFaUyq4dd6xQyB2+SnVjfz94qhWoMzbh2JlKJN0Y1KXX1dN0tE7XG9ZJGtZJGtZJGtZJmp5eJ6eCi9FoHWCqVqsdtnt4eKCmpuaax2/evBkffvghlixZgoCAAJw6dard89nGwHSEXC6Dv793h4+/Gp1O4/QxKQlh+MehYrz16c94cupw3JUysOsvrIfpSJ2uR6yTNKyTNKyTNKyTND21Tk4FF1uXj9lsduj+MZlM0Gjav0FRFPHnP/8Z69atw29/+1s88sgjrc53uWud71oEQYTB0NDh49uiUMih02lgMBhhsQhOHfvQxBthNDZh//EyrP3sCPJOX8TDGdFQ9tA02xmdqdP1hHWShnWShnWShnWSxl110uk0klp5nAouti4dvV6PyMhI+3a9Xo+YmJg2j2lqasLixYvx5ZdfYvHixXjsscfaPF9UVJTD+UJCQpy5tFaam7un2BaL4PS5FTIZ5v4qDuFB3tj2/Sl8d6gYJeV1+N19CdBqVN1yne7WkTpdj1gnaVgnaVgnaVgnaXpqnZz6J39sbCy0Wi2ys7Pt2wwGA44fP47k5OQ2j3n++efxt7/9DStXrnQILQDQr18/DBo0yOF8zc3NOHjwYLvn661kMhnuSRmIp6YlwEOtQO65arz8fg6Ky+vcfWlERES9hlPBRa1WY+bMmVixYgW+++475Obm4plnnkFoaCgyMjJgsVhQXl6OxsZGAMC2bduwe/duPPPMMxg9ejTKy8vtL9s+jz/+ON577z1s374dBQUF+K//+i80NjZi+vTpXX+3PUDSjUF46ZGbEOjriYqaRry2+RD+k1/u7ssiIiLqFZweZJGZmYnp06djyZIlmDFjBhQKBbKysqBSqXDhwgWkpqZi9+7dAIAvv/wSALBs2TKkpqY6vGz7PPDAA8jMzMSf/vQnTJs2DSUlJXjvvfcQEBDQhbfZs0QEabH0sWTERvrBZLZgzdaj+OKH0xAEPi5NRER0NTKxDy6iY7EIqKys79JzKpVy+Pt7o6qqvsv6/JotAj7+Lh9/P1wCAIgf6I+5v4qHzlt9jSN7ru6oU1/EOknDOknDOknDOknjrjoFBHhLGpzb9x5r6UWUCjlmZsTgiXuGQq2S49iZKvzhvQPIO8dZdomIiNrC4NIDjEsIw+8fTUZYPy/U1Jmx7KP/YNe+M5xpl4iI6AoMLj1EeKA3lj6ajJT4UIgisPX7U/jzpz+jtqH14pVERETXKwaXHsRDrcCcSUPx2F2xUCnlOHrqIv77vRx2HREREbVwagI66n4ymQy3jLgBg8J0WPv5LyirbMD/bPkPIoK8cfOwMIyJC4G/j4e7L5OIiMgt2OLSQ/UP1mLpo6Nwy4gwKBUyFJfX4//+UYCFa/di5Sc/Yd8vpTCZLe6+TCIiIpdii0sPpvFQ4rG7huL+8UOQk6vHj7+UoqC4BsdOV+LY6Up4qBQYFROEO8dEIjxI6+7LJSIi6nYMLr2At6cK6YnhSE8Mh76qAfuOlWHfL6XQVxux95dS/HisFDcPC8WU1MHo5+t57RMSERH1UgwuvUywvxfuTR2EyeMGorDEgK9zzuFQXjn2Hi1F9nE9JowMx6SbB/bZxRuJiOj6xuDSS8lkMgyJ8MWQiAQUnq/B1n8WIvdcNfbkFOHfP5/HnWMGIGNUf3ioFe6+VCIioi7D4NIHRN3gi0UzkvDL6Up89s9CFOnrsP1fp/D3Q8VIiOoHhVwGuVwGuUxm/V5m/bPOW41xCaHw9mTrDBER9Q4MLn2ETCZDwuB+iB8UgAPHy7DtX6dQUdOIH36+cNXjvvjhNG4fFYGM5P7wYoAhIqIejsGlj5HLZBgbH4pRscE4cKIMlQYTBEGEIIqwtHwVBOv3J85WoaS8Hjv2nsE3B4uRkdwft4+KYIAhIqIei8Glj1Iq5Lh5WNhV9xFEEYfyyrHjh9MoqajHFz+cxp6copYA0x9ens79eIiiiDOlBhw7V43BIVqoJKzySURE5AwGl+uYXCZDcmwwbooJwsFcPXbsPYPzLQHmm5wijBjSD0PCfREV7ouIIC3kclmrczRbBOQVVeOnkxX4qaAcFw0mAICPlwqTxw3CrYk3QMkAQ0REXUQmin1vCWKLRUBlZX2XnlOplMPf3xtVVfVobha69Nw9hSCIOJinxxc/nMaFiw0O73moFRgcpsOQcF8MifCF0dSM/+RX4OfCizCamu37qVVy6Lw9UFFtBACE+GswPT0KI6ODIJO1Dj7Xq+vh56krsE7SsE7SsE7SuKtOAQHeUEj4hy5bXMhOLpdh9NAQjIoJxomzVcgvrkZBSQ0KzxtgMltw4mwVTpxtveCjzkuFEUMCkXRjEIYP6Yd+/bT4/B/52P59IcqqjPjf7b9gSIQvHhg/BEPCfd1wZ0RE1FcwuFArcrkM8YMCED8oAIC1Jaakot4aYlpeCoUcI6L6IenGIAy+QWfvRlIq5VAq5LjtpgiMjg3GV9nnsOfAORQU1+D1zYdwU0wQ7h03CBHBXKKAiIicx+BC1ySXy9A/WIv+wVqMTwqXfJzGQ4mptwzG+KRwfP7vU/jh6AUcyivHobxyRARpkRIfgjFxIQjQcZkCIiKShsGFup2/jwdm3z0Ut4/qjy/2nsZP+RUoLq/Dp/+sw6f/LER0fz+Mjbd2UXGpAurpLlysx/mKeo7bInITBhdymYhgLebfl4D6xiYczNVj/7Ey5BVV42TL6697TmLoQH8MDPVB/2AfRAR5I8Tfq82nmdpiNDVDX2VEebX1pa822v9sbhaQNjwMd42J5Dw11GGGBjPe/Oth1DY04cnJ8RgTF+LuSyK67jC4kMt5e6pwa2I4bk0MR6WhEdknyrD/WBmK9HX45VQlfjlVad9XrZQjPMgbEUFahPXzhkUQUNvQhDrjZa+GJtQamxyebmrLrn1n8Y/DJbhrbCQm3sR1nMh5f91zErUNTQCA7f8+hZtigvi4P5GLMbiQWwXoPHHXmAG4a8wAlJTX4cTZKhSX16FIX4+S8jqYmwWcvlCL0xdqJZ3Px0uFYD8Ngvw1CPLVINhfgyA/DQz1ZnzRMtHe1u9P4ZuDxfjVzQM5zwxJlpOrR06uHnKZDBoPBfRVRvxw9ALSE6WP+yKizmNwoR4jPEiL8KBLTxsJggh9tRHF+joU6etQWtkAD5UCWi8VfDQqaDWqlu/V0Hqp4Outhsaj/R/pkdFByD5ehu3/tq7j9NdvTuLrA+dwb+ogpMSHSu6SouuPod6MzV/nAQDuSRkArUaFj77Lx44fTuPm+FCoVWy9I3IVBhfqseRyGUIDvBAa4IVRscFdcr6UYaFIHhqMf/98ATv2nkZFTSOydp3A1u8LMXpoCMbGh2BAiA8HXZKDD/fkoc7YhIggLX41biBEEdiTcw4XDSb8/XAJ7hwT6e5LJLpusI2crjtKhRzjk8Lx5pMpeGD8EGg1KlTXmbEnpwgvv38Q/7UxG1/8cBqllQ3XPlk7RFFETZ0JDY1XH3dDPd+BE2U4mFcOhVyGJ+4ZCqVCDpVSjsmpgwAAu/efveb4KiLqOmxxoeuWh0qBO8dE4rabIvDL6YvIPl6Gn/IrUFbZgC9+OI0vfjiNAaE+GBHVD77eanjbuqdaXt6eKqhUclysacT5inpcuNjQ8rUe5y82wGhqhgzADUHeuLFlqYQhEX4I8uW8Nb1FTb0ZH+45CcDaRTQg1Mf+3s3DQvG37HO4cLEBXx84hylpg911mUTXFQYXuu6plHIk3RiEpBuDYDQ146f8Cuw/XoZjpytxtrQWZ0vbHxgskwHtrfZle6+kvB4l5fX450/nAQC+3mpE9/dDfFQgPJQyeHso4eOlho+XCj5eKqiUHC/RE4iiiA+/tnYR9Q/WYtLNAx3eV8jluC9tMNZ+/gu+zinChJsioPNSu+diia4jDC5El9F4KJEyLBQpw0JhaDDjYK4eZ0trUWdsQn1jM+ovewzbIogQRUCpsI7FCevnjRsCvRHWzws39PNGSIAGDSYLCoprUFBSjYLiGpwprUVNvdn+hEpbPNQK+GhUUCjkEAURgmj9HOtX6/d+Wg/cmngDUoaFwqObB4YaGsw4dd6A8xX1GBLui+j+ft36eT3FgRN6HDrp2EV0pZtigjAg1AdnS2ux68ezmDHxRjdcKdH1hcGFqB06LzUmjIxo8z1RFNFotqDRbIHOWwWFvO3hYr5KBW6KCcJNMUEAAHOTBWdKa1F43oCyaiMuVhtRU2dGrdGMugZrGDKZLTCZLVe9tpp6Mz74Og9bvy/ELSNuwISREeh3jS6o+sYmnLlQC3OTBRoPpfXlqYSXhxIaDwUUcjmaLQKKy+tQWGJA4fkanCoxQN+y0rfN0AH+mJI2CDdG+F3183qzmnoz/vqNtYto0s0DERni0+Z+MpkM024djFWfHME//lOMjOT+1/zvQESdw+BC1AEymcz+y98ZapUC0f39EDcooNWy8aIowmhqRm3LhHqCIEIuk0Emh/WrDJDB+jX3XDW+O1SE8upGfJV9Dn87cA4jo4Nw+6j+uDHCF6IInK+oR+H5GnsIuXDx6oON1So5BAFotrRexj6snxdC/L1w9NRF+yrh8YMCMCV1EKL62Irfgijig7/los7YhMhgLe5JGXDV/eMHBiA20g+556rxxd7TePzuoS66UqLrk9PBRRAErFmzBp9++ilqa2uRnJyMpUuXon///tc8bt68eRgxYgQWLFjg8F5GRgbOnj3rsO2+++7Dm2++6ezlEfVaMpkMXp4qeHmqcK2J5CNDfDDxpggcKazAtweLceJslX0ByxB/DWrqzWhso9Um2F8DrUYFo6kZDaZmNJosMDVZ9zM3WQOLt6cSg2/wRdQNOgwO12FwmM6+TEJFjRFf/ngWe49ewLHTlTh2uhIJg/thStogDArT2T9HFEU0NQswmpphNFtgsQgI6+fd4+fKKSipwV+/OYmzpbVQyGV4vJ0uostZW12i8NrmQ9h79ALuGhOJsH7eLrpiouuP08Fl7dq12LJlC958802EhoZi+fLlmDNnDnbu3Am1uu2BaWazGUuXLsW///1vjBgxwuG9hoYGFBUV4Z133kF8fLx9u6cnm1uJrkYul9kHFRfr6/DtoSLsO1aGsipr146HWoHBYToMvkGHqHBrEPFpY/CoRRBgNFnsj/QG+nq2O49NoK8Gj90Vi3tSBmDnj2fw49FSHD11EUdPXURYPy97WGk0W2ARHEcte3sqMTyqH0YMCcSwQQE9as2o6joTPv1HIfYdKwUAaDwUePj26Ha7iK4UFe6LxCGB+KmgAtv/dQq/uy+hOy+X2iGIIgqKaxAe5A3vHvTzRV3LqeBiNpuxadMmLFy4EOnp6QCA1atXIy0tDXv27MGkSZNaHXP48GEsXboUjY2N0Ol0rd4vKCiAIAhISkqCr2/fanImcpWIYC0eu2sopt0ahZNF1Qj290J4oLQWDoVcDq1G7tTK3EF+Gjx+91DckzIAX+49gx+PlbbZFSUD4OmhhCCKqG9sxr5jZdh3rAxymQw3RvhixJBAjBjSDwE+njCam+2hx2iyfm9uFiBTKFBV04CGxmaYzBY0NlnHAJmaLDA3WaDzViPQV4NAP08E+noiyFeDfr6ekpZyaLYI+OZgEXbsPQOT2QIZgHHDwzDt1ij4ejv3hNDUWwfjSEEFDuaVY+/RCxgS7osgP02nWpmami04faEWBSU1OHPBAD+tBxKi+iGmvx9n672MKIo4euoiPvvnKRSX18HXW40nJg3FsEH93H1pHVZVa8J3h4px6nwNRgwJRHpiONdXa+FUcMnNzUV9fT1SUlLs23Q6HeLi4pCTk9NmcPn++++RlpaG+fPnY/Lkya3ez8vLQ2BgIEMLURfw8VLjppjOzzIsVYi/F56YFId7UwehrMoITw8FNGrr2B9PtQIeagXkMhksgoDCEgOOFFTgSOFFnK+oR15RNfKKqvF//yjo8uuSAfDz8UA/nSf8tGr4aj3gp1XDT+sB35avFTWN+OTvBShrmWhw8A06PHx7tEOXlzMigrQYGx+CfcfKkLXrBADrZIehARqHJ878fTygUsrtE9mpFHIoW76amwUUltSgoLgG+SXVOFtai2aLY8vVt4eKoVLKERPph4TB/ZAwuB/Cg7qma8pktqC0sgEXKutRerEBpZUNuGhohChe+dj/pT8o5HKH+1EqZPb78vfxwOihIQgJ8OqS62tLYUkNPv1nIU4WVdu31dSbseqTI8hI7o9pt0ZBpew9c62eKTVgT04Rck7o7a2WueeqsWvfWdwxuj8mjIxwemxdX+PU3ZeWWptRw8LCHLYHBwfb37vSM888c9Vz5uXlwcvLC5mZmTh8+DD8/f0xbdo0zJo1C/J2ntQgop4l0E+DQD9Nu+8r5HJE9/dDdH8/3D9+CMqrjfi58CKOFFQg91wVmi0iZDK0hB4FPD2U0KiV8PJUwkfrAQWsK4V7qBXwVCugVingqVJApZSjus6MizWNKK8xoqKmERXVRpibBVTVmlBVa7rmteu81bg/PQopw0Ih7+RSDzMmRkOtUuD0eQMuVDagqVlAcXk9isvrO3xOnbcaN4b7YvANOpRVGXH01EVU1ZrsK6l/hHwE+2kwIjoIPholfL3VCNB5IsDHAwE6T4fH5ZuaLaiqNaHSYEJlbaP9e31VAy5UNqDScO16OWv7v09j8A06pMSHYvTQ4Da7KzvifEU9tn5fiP/kVwCwhsSJN0Xg9uT+2LXvDP5+uAR7copw4mwV5k2OR3ig8+HuYk2jfTB6fnE1FHIZ+gdr0T/EB/2DtYgM1sLfx6PTS4QIgoifCiqwJ6fIIYBF9/dDwuAA/OvIeZRXN2Lr96fwt+xzmDiqPyaOiui27jBBFFFvbEJNnQnGRmvLZ1OzAHOzBU3Ngr0b2l1LozgVXIxGa9/5lWNZPDw8UFNT06ELyM/Ph8FgwB133IH58+fj0KFDWL58OWpqavD000936JwAoOzihK1oaXZWcCXhq2KdpLne6xQW6I2wQG/cMSYS5mYLRMH6VNOVfxEqFHLodBoYDEZY2njaqS2iKMJQb0Z5dSMqaxtRXWdCTa0ZVXUmVNeZUF1rQnWdGc0WAeNHRmBK2qAu+xesn48HnpgUB8D6l//F6kaUVNTjvO11sR619WY0Way/CJqaBTRbBIdWlfAgb0RH+OHG/r64McIPwf4ah7qIooiSinr8XHARPxdWIO9cNfTVRnxz4Fyb1+StsS5AWttgRm1D0zXvwcdLhbB+LfMRBXoj0NfT/nPq8F9HBkAEmgURzZfdi7nla1NL69HRUxdx6rwBp84b8PF3+Rge1Q/jEsKQGB0ItcTJFgVRRF1DE6pqrf8Nc07o8e+fz0MUrRM9pg2/AffdMtj+KPpjdw/FiBsD8e7O4yjS1+Hl93Pw0O3RuD3Z+hBJe//fVdeacOJsFY6fqcSJs1XQVxlb7VNWZcTBvHKH+kYGaxEZokVkS6C5Icj7qvcmiCIqqo0o0tfhXFkd9h69YP8shVyGMXEhuGNMpL31b9K4gdj/Sxl27D2NCxetM3vvybEGmNFDQ+CnVcPHS92hbknbFAhnL9TibJl1ws1zZXX2Qfvtefr+4S5t3b2cTBTbm/ezta+//hqZmZk4cuSIw+DZp59+GmazGevWrbvq8RMmTMB9993n8FSR2WyGyWSCj8+lQXAbNmzAunXrcOjQoQ61uoiiyEXyiOiqetLfE4IgotkiQAScnlDQaGrGz/nlOFVSg/Jqo7X1qdqIimpjm2soqVUKBPl5op+vxt5SFhLghf7BPggP1kLn5Niea6kyNOJfP5XgH4eKUFh86R+4nmoF/H084aFWwENlbUW79L0cjWYLKmsacdHQiCpDY6vB3gAwdlgoHrlrKCJD2+7eqzI04k8f/weH86yTPY6JD8Wj98Shps6E0ovWZTpKWwJlaUU96oyOwU4ul+HG/n4YPiQQw4cEQhSB0+cNOH2+BqfP16BIXwehjeuSy2UID/LGwDBfDAzToX+IFpU1jTh9wYCzFww4W2qA0eQYDLQaFe5MGYhJqYPQz7ft1kuLIOLHI+fxybd5rWb0lssAndYD/j4e8PfxhJ+PB7QaFUSgjYksAXOzBecu1OJcmaFVd+Tl1CoFPFRyqJSX/tsE6Dzx1P2JCO7GLsCrceqfGbYuIr1ej8jIS6uh6vV6xMTEdOgC1Gp1qxac6OhoNDQ0oKamBv7+/k6fUxBEGAwdXyCvLR35l9/1iHWShnWS5nqsU0f+5hoa6Ycxw8Ja1amhsRmVhkbU1Jvh46WCf8svs/YCm8XchCrztVtlnHVLQihuSQhFSXkd9h4txY+/XEClwYQLF6V3oclg7Tbz8/FAsL8Gd46JtE+CWFXV/nkypydgz4Ei/N/f85F9rBTZx9oe1mD7jMhQH8QN9EfcwABE9/dr1Ro3MNgb4xOtvwvNzRacL6/HubI6nCurtbag6OtQb2xCUVkdisrq8O+fStr8LKVChhsCvdE/WIvo/n64eViYdfCtIFz1foYN9EPcE6NxOK8cX2efw/mL9ahraIIgWluMqmtNOA1Du8e3xctTiYGhPhgQ6oMBIT4YFO6LIZEBMDaY2gxmVuJVr7MjdDqNpFZop4JLbGwstFotsrOz7cHFYDDg+PHjmDlzptMXKYoibr/9dkyZMgVPPfWUffvRo0cRFBTUodBiY5vUq6tZLEK3nbsvYZ2kYZ2kYZ2kubJOaqUcoQFeCL3sX8YWi4jLB9e6Uoi/F6beMhhT0gbhfEW9dR6hZuvTYU3NQsuTYtaxFGqlAv4+HvBrGVit81a3elJM6s/ExJsiEB3hi/e+ykWRvg6BOk8E+XkiyN8LwX4aBPlpEOJv/XrlkztX+ww5ZIgI0iIiSIubh4UCsP5eq64zo7i8DsX6OhSV1+HCxQb4easREWzdNyJYixB/TYfvBwAShwQicUggAOuUBrUNTTDUm1FTb7Z/bWhstk5cKZNBLrtsIkuZDAq5DMH+XhgQokW/K6ZAUCrlUKsUqG/pBuxpnAouarUaM2fOxIoVKxAQEIDw8HAsX74coaGhyMjIgMViQWVlJXx8fCTNwyKTyXD77bcjKysLgwcPxrBhw7Bv3z68++67eOmllzp8U0RE1HPJZdZf+K4UGeKDV+aMgc7XC4aahm77hSyTyVq6azyQMNg1j2Mr5PKWgOfhks9zN6dHpGVmZqK5uRlLlixBY2MjkpOTkZWVBZVKheLiYtx222144403MHXqVEnne+6556DVarFq1SqUlpYiIiICL730Eh544AGnb4aIiOhqFD189ma6NqcG5/YWFouAysqu7XtTKuWt1pah1lgnaVgnaVgnaVgnaVgnadxVp4AAb0ljXK7PZzGJiIioV2JwISIiol6DwYWIiIh6DQYXIiIi6jUYXIiIiKjXYHAhIiKiXoPBhYiIiHoNBhciIiLqNRhciIiIqNdgcCEiIqJeg8GFiIiIeg0GFyIiIuo1+uQii6IoQhC6/rYUCjksFi7MdS2skzSskzSskzSskzSskzTuqJNcLoNMdu3Vu/tkcCEiIqK+iV1FRERE1GswuBAREVGvweBCREREvQaDCxEREfUaDC5ERETUazC4EBERUa/B4EJERES9BoMLERER9RoMLkRERNRrMLgQERFRr8HgQkRERL0GgwsRERH1GgwuEgiCgLfeegtpaWlITEzE3LlzUVRU5O7L6lHeeecdPPLIIw7bTpw4gZkzZyIxMRETJkzABx984Karc5/q6mosXboUt9xyC0aOHIkZM2bg4MGD9vf37duHqVOnYsSIEbjzzjuxa9cuN16t+1y8eBGLFi3C2LFjkZSUhHnz5qGwsND+Pn+WWjt9+jSSkpKwbds2+zbWyaqsrAwxMTGtXrZasU6XfP7557j77ruRkJCAe+65B1999ZX9veLiYjz55JMYOXIkUlNT8ac//QkWi8WNV9tCpGt6++23xTFjxoj/+Mc/xBMnToiPP/64mJGRIZpMJndfWo/w4YcfirGxseLMmTPt2yorK8UxY8aIixcvFgsKCsTPPvtMTEhIED/77DM3XqnrzZ49W5w0aZKYk5Mjnjp1SvzjH/8oDh8+XCwsLBQLCgrEhIQEcdWqVWJBQYH47rvvinFxceKPP/7o7st2uV//+tfi/fffLx45ckQsKCgQFyxYIKampooNDQ38WWqD2WwWp06dKkZHR4tbt24VRZH/z13un//8p5iQkCCWlZWJer3e/jIajazTZT7//HMxLi5O/PDDD8WzZ8+Ka9euFWNjY8XDhw+LZrNZzMjIEOfNmyfm5eWJ33zzjTh69Gjxz3/+s7svW2RwuQaTySQmJSWJf/3rX+3bampqxOHDh4s7d+5045W5X2lpqfjkk0+KiYmJ4p133ukQXNavXy+mpqaKTU1N9m0rV64UMzIy3HGpbnHmzBkxOjpaPHjwoH2bIAjixIkTxT/96U/i73//e3H69OkOxzz77LPi448/7upLdavq6mrx2WefFfPy8uzbTpw4IUZHR4tHjhzhz1IbVq5cKc6aNcshuLBOl2zYsEH81a9+1eZ7rJOVIAji+PHjxTfffNNh++OPPy6uX79e3Llzpzhs2DCxurra/t7HH38sjhw50u3/aGdX0TXk5uaivr4eKSkp9m06nQ5xcXHIyclx45W537Fjx6BSqbBjxw6MGDHC4b2DBw9i9OjRUCqV9m1jx47FmTNnUFFR4epLdQt/f39s2LABCQkJ9m0ymQwymQwGgwEHDx50+LkCrDU6dOgQRFF09eW6ja+vL1auXIno6GgAQGVlJd5//32EhoZiyJAh/Fm6Qk5ODj755BO8+eabDttZp0vy8vIQFRXV5nusk9Xp06dRUlKCX/3qVw7bs7Ky8OSTT+LgwYOIj4+Hr6+v/b2xY8eirq4OJ06ccPXlOmBwuYbS0lIAQFhYmMP24OBg+3vXqwkTJuDtt99G//79W71XWlqK0NBQh23BwcEAgAsXLrjk+txNp9Ph1ltvhVqttm/7+uuvcfbsWaSlpbVbI6PRiKqqKldfbo/w+9//HikpKdi1axdee+01eHl58WfpMgaDAc8//zyWLFnS6u8k1umSkydPorKyEg8//DBuvvlmzJgxA//6178AsE42p0+fBgA0NDTgiSeeQEpKCu6//378/e9/B9Cz68Tgcg1GoxEAHH75AICHhwdMJpM7LqlXaGxsbLNmAK7buh0+fBiLFy9GRkYG0tPT26yR7c9ms9kdl+h2jz76KLZu3YpJkyZh/vz5OHbsGH+WLvPf//3fSEpKavWvZID/z9k0Nzfj1KlTqKmpwYIFC7BhwwYkJiZi3rx52LdvH+vUoq6uDgDwwgsvYNKkSdi0aRPGjRuH3/3udz2+Tspr73J98/T0BGD9RWL7HrD+h9NoNO66rB7P09Oz1S9f2w+7l5eXOy7Jrb799lssXLgQI0eOxIoVKwBY/xK4ska2P1+vP1tDhgwBALz22ms4cuQIPvzwQ/4stfj8889x8OBB7Ny5s833WScrpVKJ7OxsKBQK+9/Zw4YNQ35+PrKyslinFiqVCgDwxBNP4L777gMADB06FMePH8d7773Xo+vEFpdrsDXH6vV6h+16vR4hISHuuKReITQ0tM2aAbju6vbhhx9iwYIFGD9+PNavX2//V0tYWFibNfLy8oKPj487LtUtKisrsWvXLjQ3N9u3yeVyDBkyBHq9nj9LLbZu3YqLFy8iPT0dSUlJSEpKAgD84Q9/wJw5c1iny3h7ezv8QxMAbrzxRpSVlbFOLWz3ahtbZjNkyBAUFxf36DoxuFxDbGwstFotsrOz7dsMBgOOHz+O5ORkN15Zz5acnIxDhw45PPO/f/9+DBo0CP369XPjlbnWli1b8Morr+Dhhx/GqlWrHJpeR40ahQMHDjjsv3//fowcORJy+fXzv2ZFRQWeffZZ7Nu3z76tqakJx48fR1RUFH+WWqxYsQK7d+/G559/bn8BQGZmJl577TXWqUV+fj5Gjhzp8Hc2APzyyy8YMmQI69QiPj4e3t7eOHLkiMP2kydPIjIyEsnJyTh+/Li9Swmw1snb2xuxsbGuvlxHbn2mqZdYtWqVOHr0aPHbb791mMfFbDa7+9J6jBdeeMHhceiKigoxOTlZfOGFF8T8/Hxx69atYkJCgrht2zY3XqVrnTp1SoyPjxfnz5/vMJeEXq8XDQaDePLkSTE+Pl5cvny5WFBQIGZlZV2387jMmTNHzMjIEA8cOCDm5eWJzz77rJicnCyWlJTwZ+kqLn8cmnWyslgs4rRp08S7775bzMnJEQsKCsTXX39dHDZsmJiXl8c6XeZ///d/xaSkJHHnzp0O87js379fbGxsFCdOnCg+8cQT4okTJ+zzuLz99tvuvmzO4yJFc3OzuGzZMnHs2LFiYmKiOHfuXLGoqMjdl9WjXBlcRFEUjxw5Ij7wwAPisGHDxPHjx4ubN29209W5x7p168To6Og2Xy+88IIoiqL4/fffi5MmTRKHDRsm3nnnneKuXbvcfNXuYTAYxD/84Q/iuHHjxOHDh4uPP/64ePLkSfv71/vPUnsuDy6iyDrZlJeXiy+++KI4btw4MSEhQfz1r38t5uTk2N9nnS7ZtGmTOGHCBDE+Pl6cPHmy+M0339jfO3PmjDh79mwxISFBTE1NFf/0pz+JFovFjVdrJRPF62jCCCIiIurVrp+OdCIiIur1GFyIiIio12BwISIiol6DwYWIiIh6DQYXIiIi6jUYXIiIiKjXYHAhIiKiXoPBhYiIiHoNBhciIiLqNRhciIiIqNdgcCEiIqJeg8GFiIiIeo3/DyeDQ1PtaBlkAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plot_costs(mlp.loss_curve_)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -178,6 +407,7 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "mlp.fit(X_train, y_train)\n",
     "plot_costs(mlp.loss_curve_)"
    ]
@@ -191,7 +421,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {
     "solution2": "hidden",
     "solution2_first": true
@@ -200,9 +430,10 @@
    "source": [
     "def relu(x):\n",
     "    ### START YOUR CODE ###\n",
-    "    \n",
-    "    ### END YOUR CODE ###\n",
-    "    pass"
+    "    # return x if x > 0 else 0 # Funktioniert nicht, weil X ein Dataframe ist\n",
+    "    # return np.max(0, x) # np.max braucht integers\n",
+    "    return np.maximum(0, x)\n",
+    "    ### END YOUR CODE ###"
    ]
   },
   {
@@ -224,13 +455,14 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "def relu(x):\n",
     "    return np.maximum(0, x)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {
     "solution2": "hidden",
     "solution2_first": true
@@ -239,7 +471,7 @@
    "source": [
     "def sigmoid(x):\n",
     "    ### START YOUR CODE ###\n",
-    "    \n",
+    "    return 1/(1+np.exp(-x))\n",
     "    ### END YOUR CODE ###\n",
     "    pass"
    ]
@@ -263,6 +495,7 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "def sigmoid(x):\n",
     "    return 1/(1+np.exp(-x))"
    ]
@@ -299,9 +532,21 @@
     "*Click on the dots to display the solution*"
    ]
   },
+  {
+   "attachments": {
+    "image.png": {
+     "image/png": "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"
+    }
+   },
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "![image.png](attachment:image.png)"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {
     "jupyter": {
      "source_hidden": true
@@ -311,6 +556,7 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "def predict(mlp, X):\n",
     "    # define the first activations, e.g. inputs\n",
     "    A = X\n",
@@ -340,17 +586,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {
     "solution2": "hidden",
     "solution2_first": true
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Are the outputs the same: True\n"
+     ]
+    }
+   ],
    "source": [
-    "# y_pred_scikit = ...\n",
-    "# y_pred_own = ...\n",
+    "y_pred_scikit = mlp.predict(X_test)\n",
+    "y_pred_own = predict(mlp, X_test)\n",
     "\n",
-    "# print('Are the outputs the same: %s' % ... )"
+    "print('Are the outputs the same: %s' % (y_pred_own == y_pred_scikit).all())"
    ]
   },
   {
@@ -372,6 +626,7 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "y_pred_scikit = mlp.predict(X_test)\n",
     "y_pred_own = predict(mlp, X_test.values)\n",
     "\n",
@@ -387,13 +642,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {
     "solution2": "hidden",
     "solution2_first": true
    },
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.93585\tF1 Score: 0.6722023505365355\n"
+     ]
+    }
+   ],
+   "source": [
+    "acc = accuracy_score(y_test, y_pred_own)\n",
+    "f1 = f1_score(y_test, y_pred_own)\n",
+    "print(f\"Accuracy: {acc}\\tF1 Score: {f1}\")"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -414,6 +681,7 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "y_pred = predict(mlp, X_test.values)\n",
     "\n",
     "accuracy = accuracy_score(y_test, y_pred)\n",
@@ -433,7 +701,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -449,9 +717,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " dense (Dense)               (None, 30)                450       \n",
+      "                                                                 \n",
+      " dense_1 (Dense)             (None, 15)                465       \n",
+      "                                                                 \n",
+      " dense_2 (Dense)             (None, 1)                 16        \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 931 (3.64 KB)\n",
+      "Trainable params: 931 (3.64 KB)\n",
+      "Non-trainable params: 0 (0.00 Byte)\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
    "source": [
     "dataset_dim = X_train.shape[1]\n",
     "\n",
@@ -471,9 +761,316 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/150\n",
+      "59/59 [==============================] - 1s 8ms/step - loss: 0.5559 - accuracy: 0.8773\n",
+      "Epoch 2/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.3478 - accuracy: 0.8983\n",
+      "Epoch 3/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.2905 - accuracy: 0.9024\n",
+      "Epoch 4/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.2471 - accuracy: 0.9088\n",
+      "Epoch 5/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.2201 - accuracy: 0.9153\n",
+      "Epoch 6/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.2045 - accuracy: 0.9181\n",
+      "Epoch 7/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1956 - accuracy: 0.9216\n",
+      "Epoch 8/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1919 - accuracy: 0.9229\n",
+      "Epoch 9/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1879 - accuracy: 0.9247\n",
+      "Epoch 10/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1852 - accuracy: 0.9261\n",
+      "Epoch 11/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1831 - accuracy: 0.9269\n",
+      "Epoch 12/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1821 - accuracy: 0.9270\n",
+      "Epoch 13/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1805 - accuracy: 0.9283\n",
+      "Epoch 14/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1768 - accuracy: 0.9304\n",
+      "Epoch 15/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1748 - accuracy: 0.9312\n",
+      "Epoch 16/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1717 - accuracy: 0.9315\n",
+      "Epoch 17/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1711 - accuracy: 0.9323\n",
+      "Epoch 18/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1680 - accuracy: 0.9339\n",
+      "Epoch 19/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1654 - accuracy: 0.9349\n",
+      "Epoch 20/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1635 - accuracy: 0.9370\n",
+      "Epoch 21/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1601 - accuracy: 0.9376\n",
+      "Epoch 22/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1571 - accuracy: 0.9387\n",
+      "Epoch 23/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1558 - accuracy: 0.9390\n",
+      "Epoch 24/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1537 - accuracy: 0.9395\n",
+      "Epoch 25/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1519 - accuracy: 0.9406\n",
+      "Epoch 26/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1532 - accuracy: 0.9391\n",
+      "Epoch 27/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1521 - accuracy: 0.9393\n",
+      "Epoch 28/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1491 - accuracy: 0.9409\n",
+      "Epoch 29/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1503 - accuracy: 0.9408\n",
+      "Epoch 30/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1505 - accuracy: 0.9398\n",
+      "Epoch 31/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1479 - accuracy: 0.9411\n",
+      "Epoch 32/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1471 - accuracy: 0.9409\n",
+      "Epoch 33/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1477 - accuracy: 0.9411\n",
+      "Epoch 34/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1458 - accuracy: 0.9416\n",
+      "Epoch 35/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1454 - accuracy: 0.9418\n",
+      "Epoch 36/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1457 - accuracy: 0.9419\n",
+      "Epoch 37/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1465 - accuracy: 0.9417\n",
+      "Epoch 38/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1447 - accuracy: 0.9415\n",
+      "Epoch 39/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1443 - accuracy: 0.9420\n",
+      "Epoch 40/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1452 - accuracy: 0.9416\n",
+      "Epoch 41/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1448 - accuracy: 0.9411\n",
+      "Epoch 42/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1459 - accuracy: 0.9410\n",
+      "Epoch 43/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1475 - accuracy: 0.9407\n",
+      "Epoch 44/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1429 - accuracy: 0.9427\n",
+      "Epoch 45/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1431 - accuracy: 0.9421\n",
+      "Epoch 46/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1442 - accuracy: 0.9415\n",
+      "Epoch 47/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1422 - accuracy: 0.9424\n",
+      "Epoch 48/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1427 - accuracy: 0.9426\n",
+      "Epoch 49/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1430 - accuracy: 0.9423\n",
+      "Epoch 50/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1419 - accuracy: 0.9431\n",
+      "Epoch 51/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1411 - accuracy: 0.9432\n",
+      "Epoch 52/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1425 - accuracy: 0.9425\n",
+      "Epoch 53/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1406 - accuracy: 0.9436\n",
+      "Epoch 54/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1451 - accuracy: 0.9414\n",
+      "Epoch 55/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1445 - accuracy: 0.9412\n",
+      "Epoch 56/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1442 - accuracy: 0.9415\n",
+      "Epoch 57/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1413 - accuracy: 0.9432\n",
+      "Epoch 58/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1400 - accuracy: 0.9431\n",
+      "Epoch 59/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1410 - accuracy: 0.9429\n",
+      "Epoch 60/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1405 - accuracy: 0.9430\n",
+      "Epoch 61/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1414 - accuracy: 0.9422\n",
+      "Epoch 62/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1395 - accuracy: 0.9433\n",
+      "Epoch 63/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1434 - accuracy: 0.9427\n",
+      "Epoch 64/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1410 - accuracy: 0.9432\n",
+      "Epoch 65/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1394 - accuracy: 0.9436\n",
+      "Epoch 66/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1396 - accuracy: 0.9434\n",
+      "Epoch 67/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1399 - accuracy: 0.9439\n",
+      "Epoch 68/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1413 - accuracy: 0.9432\n",
+      "Epoch 69/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1405 - accuracy: 0.9435\n",
+      "Epoch 70/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1435 - accuracy: 0.9424\n",
+      "Epoch 71/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1394 - accuracy: 0.9434\n",
+      "Epoch 72/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1386 - accuracy: 0.9444\n",
+      "Epoch 73/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1399 - accuracy: 0.9440\n",
+      "Epoch 74/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1383 - accuracy: 0.9440\n",
+      "Epoch 75/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1381 - accuracy: 0.9442\n",
+      "Epoch 76/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1389 - accuracy: 0.9440\n",
+      "Epoch 77/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1402 - accuracy: 0.9440\n",
+      "Epoch 78/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1382 - accuracy: 0.9442\n",
+      "Epoch 79/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1378 - accuracy: 0.9441\n",
+      "Epoch 80/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1403 - accuracy: 0.9426\n",
+      "Epoch 81/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1372 - accuracy: 0.9441\n",
+      "Epoch 82/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1364 - accuracy: 0.9440\n",
+      "Epoch 83/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1369 - accuracy: 0.9442\n",
+      "Epoch 84/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1373 - accuracy: 0.9438\n",
+      "Epoch 85/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1358 - accuracy: 0.9438\n",
+      "Epoch 86/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1365 - accuracy: 0.9439\n",
+      "Epoch 87/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1377 - accuracy: 0.9444\n",
+      "Epoch 88/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1372 - accuracy: 0.9431\n",
+      "Epoch 89/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1365 - accuracy: 0.9445\n",
+      "Epoch 90/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1357 - accuracy: 0.9443\n",
+      "Epoch 91/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1377 - accuracy: 0.9437\n",
+      "Epoch 92/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1361 - accuracy: 0.9436\n",
+      "Epoch 93/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1354 - accuracy: 0.9439\n",
+      "Epoch 94/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1353 - accuracy: 0.9442\n",
+      "Epoch 95/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1348 - accuracy: 0.9450\n",
+      "Epoch 96/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1350 - accuracy: 0.9441\n",
+      "Epoch 97/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1346 - accuracy: 0.9440\n",
+      "Epoch 98/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1356 - accuracy: 0.9440\n",
+      "Epoch 99/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1339 - accuracy: 0.9443\n",
+      "Epoch 100/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1343 - accuracy: 0.9442\n",
+      "Epoch 101/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1350 - accuracy: 0.9446\n",
+      "Epoch 102/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1342 - accuracy: 0.9439\n",
+      "Epoch 103/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1362 - accuracy: 0.9437\n",
+      "Epoch 104/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1345 - accuracy: 0.9451\n",
+      "Epoch 105/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1343 - accuracy: 0.9448\n",
+      "Epoch 106/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1344 - accuracy: 0.9446\n",
+      "Epoch 107/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1357 - accuracy: 0.9444\n",
+      "Epoch 108/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1358 - accuracy: 0.9437\n",
+      "Epoch 109/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1335 - accuracy: 0.9441\n",
+      "Epoch 110/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1334 - accuracy: 0.9447\n",
+      "Epoch 111/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1356 - accuracy: 0.9435\n",
+      "Epoch 112/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1334 - accuracy: 0.9453\n",
+      "Epoch 113/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1352 - accuracy: 0.9447\n",
+      "Epoch 114/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1350 - accuracy: 0.9446\n",
+      "Epoch 115/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1347 - accuracy: 0.9449\n",
+      "Epoch 116/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1322 - accuracy: 0.9451\n",
+      "Epoch 117/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1314 - accuracy: 0.9458\n",
+      "Epoch 118/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1328 - accuracy: 0.9449\n",
+      "Epoch 119/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1329 - accuracy: 0.9446\n",
+      "Epoch 120/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1330 - accuracy: 0.9451\n",
+      "Epoch 121/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1327 - accuracy: 0.9453\n",
+      "Epoch 122/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1320 - accuracy: 0.9451\n",
+      "Epoch 123/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1344 - accuracy: 0.9455\n",
+      "Epoch 124/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1316 - accuracy: 0.9460\n",
+      "Epoch 125/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1319 - accuracy: 0.9449\n",
+      "Epoch 126/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1330 - accuracy: 0.9448\n",
+      "Epoch 127/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1318 - accuracy: 0.9457\n",
+      "Epoch 128/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1311 - accuracy: 0.9463\n",
+      "Epoch 129/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1330 - accuracy: 0.9444\n",
+      "Epoch 130/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1314 - accuracy: 0.9455\n",
+      "Epoch 131/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1304 - accuracy: 0.9467\n",
+      "Epoch 132/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1334 - accuracy: 0.9451\n",
+      "Epoch 133/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1314 - accuracy: 0.9452\n",
+      "Epoch 134/150\n",
+      "59/59 [==============================] - 0s 4ms/step - loss: 0.1316 - accuracy: 0.9452\n",
+      "Epoch 135/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1321 - accuracy: 0.9463\n",
+      "Epoch 136/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1320 - accuracy: 0.9457\n",
+      "Epoch 137/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1324 - accuracy: 0.9460\n",
+      "Epoch 138/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1306 - accuracy: 0.9459\n",
+      "Epoch 139/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1298 - accuracy: 0.9461\n",
+      "Epoch 140/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1302 - accuracy: 0.9460\n",
+      "Epoch 141/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1312 - accuracy: 0.9461\n",
+      "Epoch 142/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1318 - accuracy: 0.9456\n",
+      "Epoch 143/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1312 - accuracy: 0.9459\n",
+      "Epoch 144/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1312 - accuracy: 0.9460\n",
+      "Epoch 145/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1328 - accuracy: 0.9456\n",
+      "Epoch 146/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1337 - accuracy: 0.9452\n",
+      "Epoch 147/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1311 - accuracy: 0.9464\n",
+      "Epoch 148/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1316 - accuracy: 0.9456\n",
+      "Epoch 149/150\n",
+      "59/59 [==============================] - 0s 3ms/step - loss: 0.1339 - accuracy: 0.9446\n",
+      "Epoch 150/150\n",
+      "59/59 [==============================] - 0s 2ms/step - loss: 0.1298 - accuracy: 0.9464\n"
+     ]
+    }
+   ],
    "source": [
     "adam = tf.keras.optimizers.Adam()\n",
     "model.compile(optimizer=adam, loss='binary_crossentropy', metrics=['accuracy'])\n",
@@ -490,9 +1087,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 22,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiYAAAG1CAYAAADN1D82AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/OQEPoAAAACXBIWXMAAA9hAAAPYQGoP6dpAABFSElEQVR4nO3deXiU9b3//9cs2ZPJShYIARRJ2AnIVgGB9qCtHLTUtqLQqkU91sp1VED5leM5VttaQW2RoraCVqzV73HH4lFxa6uCLK5A2LcAWSDLkGWSWe7fH0mGbEAmJLknmefjunIB99wz83nPJJMXn+22GIZhCAAAIAhYzW4AAABAA4IJAAAIGgQTAAAQNAgmAAAgaBBMAABA0CCYAACAoEEwAQAAQYNgAgAAggbBBAAABA2CCRBi5s2bp3nz5pndDABoFcEEAAAEDYIJAAAIGgQTAK36+OOPde2112rMmDEaP3687rrrLh0/ftx/u8/n06OPPqrp06dr2LBhmj59uh5++GG53W7/OW+++aZmzZqlESNGaMKECVq4cKEKCwvP+rxFRUW6++67NXHiROXm5mru3Ln6/PPPJUn5+fnKzs7WK6+80uQ+99xzj6ZPn+7/97x587Rw4UItWLBAo0aN0g033KDLLrtMCxYsaPF8V155pW699Vb/vzds2KDZs2dr+PDhuuSSS/TAAw+oqqoqsBcPQLsRTAC08Nprr+nGG29URkaGHnnkES1ZskSff/65fvzjH+vkyZOSpD//+c/629/+pttuu01r1qzRnDlztHr1aj3++OOSpK1bt2rx4sWaMWOG/vznP2vJkiXauHGj7rrrrjM+b2VlpebMmaNNmzZp0aJFWrlypSIiInTjjTfq4MGDAdXw1ltvKSYmRo8//rjmz5+vWbNm6aOPPlJFRYX/nH379ikvL09XXnmlJGndunW67bbbdMEFF+iPf/yjfvGLX+iNN97Qz3/+c3EhdqBr2M1uAIDg4vP5tHz5ck2aNEkPP/yw//jo0aP1ve99T6tXr9bixYv12WefadiwYfrBD34gSRo3bpyioqIUFxcnqS6YREZG6uabb1Z4eLgkKSEhQV9//bUMw5DFYmnx3K+++qqOHj2qV199VYMHD/Y/71VXXaXNmzdr4sSJba4jLCxM9913n/+5s7Ky9Nhjj2nDhg266qqrJNX16DgcDk2fPl2GYWj58uWaPHmyli9f7n+c/v376/rrr9dHH32kqVOntv2FBNAu9JgAaOLAgQMqLi7WzJkzmxzPyspSbm6uPvvsM0nS+PHj/cM9Tz31lPbu3au5c+f6ex/Gjh2r6upqzZw5Uw8//LC2bNmiSZMm6Re/+EWroUSqCzOZmZn+UCJJUVFRevvtt/XDH/4woDouuOACfyiRpL59+2r06NFav369/9jf//53XX755QoPD9f+/ftVUFCg6dOny+Px+L/Gjh2r2NhYffzxxwE9P4D2IZgAaKKsrEySlJKS0uK2lJQUnTp1SpI0f/583XvvvXK5XFq+fLmuuOIKzZw5Uxs3bpQk5ebm6k9/+pP69u2rp59+Wtddd52mTJmitWvXnvW5k5OTO6SOmJiYFseuvPJKffLJJyotLdXXX3+tQ4cO+YNUQ9333Xefhg4d2uSroqJCRUVFHdIuAGfHUA6AJhISEiRJJ06caHFbcXGxEhMTJUlWq1XXXXedrrvuOp08eVIfffSRnnjiCd1+++36+OOPFR4ersmTJ2vy5Mmqrq7Wxo0b9eyzz+qBBx7QyJEjNWLEiBaPHxcXp/z8/BbHt23bpvj4eEVGRkqSvF5vk9vbOjn1u9/9rh544AFt2LBB+/fvV58+fTRmzBhJksPhkCQtXrxY48aNa3Hf+Pj4Nj0HgPNDjwmAJgYMGKBevXrpzTffbHL8yJEj+uKLLzR69GhJ0jXXXKMHHnhAkpScnKzZs2fruuuuk9PpVEVFhX73u9/pBz/4gQzDUFRUlKZNm6a7775bknTs2LFWn/viiy/WkSNHtGfPHv+xmpoa3X777XrppZcUGxsrSU1W9rjdbn311Vdtqs3hcGjatGl677339Pbbb2vWrFn+YaULLrhAycnJys/P1/Dhw/1faWlpevjhh7Vjx442PQeA80OPCRCCCgoK9Mwzz7Q4PmjQIH3rW9/SnXfeqSVLluiuu+7SrFmzVFpaqpUrVyo+Pl433HCDpLo5JGvWrFFKSopyc3NVWFiop59+WuPGjVNSUpImTJigp59+Wvfcc49mzZolt9utp556SgkJCZowYUKr7Zo9e7bWrl2rW2+9VQsWLFBiYqKeffZZud1uXXvttYqPj1dubq7Wrl2rfv36KT4+Xs8++6xcLpeio6PbVPusWbO0YMECeb1e/zCOJNlsNt1xxx269957ZbPZNG3aNDmdTq1atUqFhYUaOnRo4C80gIBZDNbAASFl3rx5/gmszV199dX69a9/LUl6++239eSTT2r37t2KjY3V5MmTdeeddyojI0OS5PF49Pjjj+uNN95QQUGB4uLiNH36dN11113+4Z4333xTa9as0YEDB2SxWDRmzBgtXLhQ2dnZZ2xfYWGhHnroIf3jH/+Qz+fTqFGjtGjRIuXk5EiSDh48qPvvv19btmxRbGysrr76akVGRup///d/9f777/trlNTqfBa3261Jkyapb9++eumll1rcvn79ej311FPas2ePoqOjNXr0aP3nf/7nWdsMoOMQTAAAQNBgjgkAAAgaBBMAABA0CCYAACBoEEwAAEDQIJgAAICgQTABAABBg2ACAACCRrfb+dUwDPl8nbP1itVq6bTHDlahVnOo1SuFXs2hVq8UejWHWr1S96/ZarWc8arizXW7YOLzGSopqezwx7XbrUpMjJHTWSWPx9fhjx+MQq3mUKtXCr2aQ61eKfRqDrV6pZ5Rc1JSjGy2tgUThnIAAEDQIJgAAICgQTABAABBg2ACAACCBsEEAAAEDYIJAAAIGgQTAAAQNAgmAAAgaBBMAABA0CCYAACAoEEwAQAAQYNgAgAAggbBBAAABA2CST3DMGQY3feS0gAA9AR2sxsQDAzD0P1/2arICLsWXTPK7OYAABCyCCaSatxe7c0vlyTVenyyWSwmtwgAgNDEUI4km/X0y+D1MpwDAIBZCCaSbLbTPSRen8/ElgAAENoIJpKsFosaRm+8PnpMAAAwC8Gkns1al0wYygEAwDwEk3oN80wYygEAwDwEk3oN80wYygEAwDwEk3r+oRyCCQAApiGY1GOOCQAA5iOY1GOOCQAA5iOY1PPPMaHHBAAA0xBM6jHHBAAA8xFM6hFMAAAwH8Gkns3GHBMAAMxGMKlHjwkAAOYjmNRjuTAAAOYjmNSjxwQAAPMRTOr555h4mWMCAIBZCCb16DEBAMB8BJN6BBMAAMxHMKnH1YUBADAfwaQe18oBAMB8BJN6LBcGAMB8BJN6zDEBAMB8BJN6LBcGAMB8BJN6VnpMAAAwHcGknp1gAgCA6Qgm9VguDACA+Qgm9fzLhZljAgCAaQgm9ZhjAgCA+Qgm9ZhjAgCA+Qgm9fxzTNhgDQAA0xBM6p3ekp5gAgCAWQgm9U7PMWHyKwAAZiGY1LOzXBgAANMRTOpxET8AAMxHMKnHcmEAAMxHMKln909+ZY4JAABmIZjUY7kwAADmCziY+Hw+rVixQpMnT9aoUaN000036ciRI2c8/4033lB2dnaLr/z8/PNqeEezMZQDAIDp7IHeYdWqVXr++ef14IMPKj09XcuWLdP8+fO1bt06hYeHtzh/165dGjdunB555JEmx5OSktrf6k7AHBMAAMwXUI9JbW2t1qxZowULFmjq1KnKycnRo48+qoKCAr3zzjut3mf37t3Kzs5Wr169mnzZbLYOKaCj2G3MMQEAwGwBBZO8vDxVVlZq4sSJ/mMOh0NDhgzR5s2bW73Prl27dOGFF55fK7sAy4UBADBfQEM5BQUFkqSMjIwmx1NTU/23NVZeXq7CwkJt2bJFzz//vEpLSzVixAgtWrRIAwYMaH+j7R0/Z9dur+vB8RlGpzx+MLLV9xI1/NnThVq9UujVHGr1SqFXc6jVK4VezQEFk+rqaklqMZckIiJC5eXlLc7fs2ePJMkwDP32t7+Vy+XS448/rmuvvVbr1q1TSkpKwA22Wi1KTIwJ+H7n4ih1SZIMQ53y+MHM4YgyuwldKtTqlUKv5lCrVwq9mkOtXil0ag4omERGRkqqm2vS8HdJqqmpUVRUyxfs4osv1qeffqrExERZLHVDJStXrtTUqVP1yiuv6Oabbw64wT6fIaezKuD7nUuNq1aS5PZ4VVpa2eGPH4xsNqscjig5ndXyenv+3JpQq1cKvZpDrV4p9GoOtXqlnlGzwxHV5h6fgIJJwxBOUVGRsrKy/MeLioqUnZ3d6n2ar76JiopSZmamCgsLA3nqJjyejn9jLA2P7TU65fGDmdfrC6maQ61eKfRqDrV6pdCrOdTqlUKn5oAGrHJychQbG6tNmzb5jzmdTu3YsUNjx45tcf6LL76o8ePHq6rqdA9HRUWFDh48qIEDB55Hsztew3JhH8uFAQAwTUDBJDw8XHPnztXy5cv13nvvKS8vT3fccYfS09M1Y8YMeb1eFRcXy+Wqm68xZcoU+Xw+LV68WHv27NHXX3+t22+/XUlJSZo9e3anFNReDV1MHoIJAACmCXiK74IFC3T11Vdr6dKlmjNnjmw2m1avXq2wsDAdP35ckyZN0vr16yXVDf0888wzqqqq0pw5c3T99dcrLi5Ozz77rCIiIjq8mPNh9y8X7vndZAAABKuAd3612WxatGiRFi1a1OK2zMxM7dq1q8mxoUOHas2aNe1vYRdhS3oAAMwXGoui24A5JgAAmI9gUu/0lvSGDINwAgCAGQgm9RqGciSGcwAAMAvBpJ61UTBhOAcAAHMQTOrZbPSYAABgNoJJPbv19EtBMAEAwBwEk3pWq0X1l/NhLxMAAExCMGmEvUwAADAXwaQRW6MlwwAAoOsRTBqx02MCAICpCCaN0GMCAIC5CCaN2LiQHwAApiKYNEKPCQAA5iKYNGK3MccEAAAzEUwasXGFYQAATEUwacQ/lMMcEwAATEEwaaRhW3qGcgAAMAfBpJGGC/l5CCYAAJiCYNIIc0wAADAXwaQRlgsDAGAugkkj/uXCTH4FAMAUBJNGbEx+BQDAVASTRmxssAYAgKkIJo3YmWMCAICpCCaNcBE/AADMRTBppGGOCcuFAQAwB8GkEeaYAABgLoJJIw1zTNj5FQAAcxBMGrGxjwkAAKYimDTi35LeoMcEAAAzEEwa8S8X9hJMAAAwA8GkEf9yYeaYAABgCoJJI1zEDwAAcxFMGrHTYwIAgKkIJo34e0xYlQMAgCkIJo3Y2WANAABTEUwasbIlPQAApiKYNNLQY8LOrwAAmINg0ghzTAAAMBfBpBH2MQEAwFwEk0YahnKYYwIAgDkIJo3YrGywBgCAmQgmjdiZYwIAgKkIJo1YG+aYcHVhAABMQTBpxL/BGlcXBgDAFASTRriIHwAA5iKYNMKW9AAAmItg0gircgAAMBfBpBGbf44Jq3IAADADwaQROz0mAACYimDSiI2dXwEAMBXBpBGulQMAgLkIJo34d371MccEAAAzEEwa8e9jwgZrAACYgmDSCEM5AACYi2DSiK3RBmsG18sBAKDLEUwaaZhjIkk+ggkAAF2OYNJIw1COxDwTAADMQDBpxNaox4R5JgAAdD2CSSP2xj0mBBMAALocwaQRK8EEAABTEUwasVgs/nkmbEsPAEDXI5g049/LhCsMAwDQ5QgmzTTeywQAAHQtgkkzNmvdS+IhmAAA0OUIJs0wxwQAAPMQTJo5fb0c5pgAANDVAg4mPp9PK1as0OTJkzVq1CjddNNNOnLkSJvu+8Ybbyg7O1v5+fkBN7SrcIVhAADME3AwWbVqlZ5//nndf//9euGFF+Tz+TR//nzV1tae9X5Hjx7Vr371q3Y3tKtYucIwAACmCSiY1NbWas2aNVqwYIGmTp2qnJwcPfrooyooKNA777xzxvv5fD4tWrRIQ4cOPe8GdzY7wQQAANMEFEzy8vJUWVmpiRMn+o85HA4NGTJEmzdvPuP9nnjiCbndbt1yyy3tb2kXOb1cmDkmAAB0NXsgJxcUFEiSMjIymhxPTU3139bcV199pTVr1uill15SYWFhO5vZlN3e8XN2G+aW2P0X8rN0yvMEk4aaG1+8sCcLtXql0Ks51OqVQq/mUKtXCr2aAwom1dXVkqTw8PAmxyMiIlReXt7i/KqqKi1cuFALFy5U//79OySYWK0WJSbGnPfjnElYmE2SFBUd3qnPE0wcjiizm9ClQq1eKfRqDrV6pdCrOdTqlUKn5oCCSWRkpKS6uSYNf5ekmpoaRUW1fMEeeOABDRgwQNdcc815NvM0n8+Q01nVYY/XwGaz1r3pRt3cknJntUpLKzv8eYJJQ81OZ3VIbMEfavVKoVdzqNUrhV7NoVav1DNqdjii2tzjE1AwaRjCKSoqUlZWlv94UVGRsrOzW5z/8ssvKzw8XLm5uZIkr9crSZo5c6b+4z/+Q//xH/8RyNP7eTyd98Y07GNS6/Z26vMEE6/XFzK1SqFXrxR6NYdavVLo1Rxq9UqhU3NAwSQnJ0exsbHatGmTP5g4nU7t2LFDc+fObXF+85U6X375pRYtWqQ//elPGjRo0Hk0u/M0bEnPPiYAAHS9gIJJeHi45s6dq+XLlyspKUl9+vTRsmXLlJ6erhkzZsjr9aqkpERxcXGKjIxUv379mty/YYJs7969lZCQ0GFFdCQrW9IDAGCagKf4LliwQFdffbWWLl2qOXPmyGazafXq1QoLC9Px48c1adIkrV+/vjPa2iXsXF0YAADTBNRjIkk2m02LFi3SokWLWtyWmZmpXbt2nfG+48ePP+vtwcDGBmsAAJgmNBZFB4At6QEAMA/BpBn/5Fd2fgUAoMsRTJrxzzFhVQ4AAF2OYNIMc0wAADAPwaQZ5pgAAGAegkkzDVvmMscEAICuRzBpxm5ljgkAAGYhmDTDUA4AAOYhmDRjY0t6AABMQzBpxs4cEwAATEMwacbGHBMAAExDMGnGP8fEIJgAANDVCCbN2Nj5FQAA0xBMmrH7r5VDMAEAoKsRTJo5PceEya8AAHQ1gkkzzDEBAMA8BJNm/FvSM8cEAIAuRzBpxs7OrwAAmIZg0szpLemZYwIAQFcjmDTTsFyYLekBAOh6BJNmbFbmmAAAYBaCSTPMMQEAwDwEk2asBBMAAExDMGnGvyU9k18BAOhyBJNmbGxJDwCAaQgmzZzekp5gAgBAVyOYNHN6KIdgAgBAVyOYNGNj8isAAKYhmDRj988xYfIrAABdjWDSjJU5JgAAmIZg0gxb0gMAYB6CSTMNc0wMEU4AAOhqBJNm7LbTLwnzTAAA6FoEk2Ya5phIrMwBAKCrEUyaCbNb1RBNatz0mAAA0JUIJs1YLRZFRdglSVUut8mtAQAgtBBMWhEdWRdMKl0ek1sCAEBoIZi0IiYyTJJUWU2PCQAAXYlg0oqGHpMqekwAAOhSBJNWxPiHcugxAQCgKxFMWhFdP5RDjwkAAF2LYNKKmCgmvwIAYAaCSSti/D0mDOUAANCVCCatYLkwAADmIJi0gh4TAADMQTBpBT0mAACYg2DSCpYLAwBgDoJJK1guDACAOQgmrWjoMan1+OT2cIVhAAC6CsGkFVERdlnq/84EWAAAug7BpBVWi4UJsAAAmIBgcgZcyA8AgK5HMDmDhgmwrMwBAKDrEEzOgCXDAAB0PYLJGZzuMWEoBwCArkIwOYMY5pgAANDlCCZnEM1QDgAAXY5gcgYx7P4KAECXI5icAUM5AAB0PYLJGcSwXBgAgC5HMDkDNlgDAKDrEUzOoKHHpIIeEwAAugzB5AzoMQEAoOsRTM6gYfKr2+OT2+M1uTUAAIQGgskZREbYZan/O7u/AgDQNQgmZ2C1WBptskYwAQCgKwQcTHw+n1asWKHJkydr1KhRuummm3TkyJEznr99+3b99Kc/VW5uriZMmKB7771Xp06dOq9Gd5XTm6wxARYAgK4QcDBZtWqVnn/+ed1///164YUX5PP5NH/+fNXW1rY498SJE7rhhhvUp08fvfLKK1q1apW2bt2qe+65p0Ma39noMQEAoGsFFExqa2u1Zs0aLViwQFOnTlVOTo4effRRFRQU6J133mlx/tGjRzVp0iT96le/0oABAzR69Gj96Ec/0scff9xhBXSm07u/0mMCAEBXCCiY5OXlqbKyUhMnTvQfczgcGjJkiDZv3tzi/JEjR+qRRx6R3V73C37fvn16/fXXdckll5xns7tGdMPur9X0mAAA0BXsgZxcUFAgScrIyGhyPDU11X/bmVx22WU6ePCg+vTpo5UrVwbYTHPEcIVhAAC6VEDBpLq6WpIUHh7e5HhERITKy8vPet/ly5erurpay5Yt009+8hO9/vrriomJCbC5dez2jl9MZLNZm/wpSbHRdXW6ar2d8pxma63mnizU6pVCr+ZQq1cKvZpDrV4p9GoOKJhERkZKqptr0vB3SaqpqVFUVNRZ7zt8+HBJ0sqVK3XppZfq3Xff1VVXXRVgcyWr1aLExPYFmrZwOE7XkZIYLUly+4xOfU6zNa45FIRavVLo1Rxq9UqhV3Oo1SuFTs0BBZOGIZyioiJlZWX5jxcVFSk7O7vF+fv379fhw4c1depU/7G0tDQlJCSosLCwXQ32+Qw5nVXtuu/Z2GxWORxRcjqr5fX6JEkWw5AklTpdKi2t7PDnNFtrNfdkoVavFHo1h1q9UujVHGr1Sj2jZocjqs09PgEFk5ycHMXGxmrTpk3+YOJ0OrVjxw7NnTu3xfmffPKJHnroIf3rX/+Sw+GQJB0+fFilpaW68MILA3nqJjyezntjvF6f//Gjwm2SpIpqd6c+p9ka1xwKQq1eKfRqDrV6pdCrOdTqlUKn5oAGrMLDwzV37lwtX75c7733nvLy8nTHHXcoPT1dM2bMkNfrVXFxsVwulyRp5syZSkhI0KJFi7Rnzx5t2bJFCxYs0IgRIzRt2rROKagjxXAhPwAAulTAM2kWLFigq6++WkuXLtWcOXNks9m0evVqhYWF6fjx45o0aZLWr18vSUpISNBf/vIXSdKcOXN02223aciQIVq9erVsNlvHVtIJ/MuFWZUDAECXCGgoR5JsNpsWLVqkRYsWtbgtMzNTu3btanJswIABevLJJ9vfQhP5lwuzjwkAAF0iNNYetVNDj4nH61Ot22tyawAA6PkIJmcRFWGT1WKRVDcBFgAAdC6CyVlYLBbFRdf1mpyqIpgAANDZCCbn4Iip2/3VWdXy6skAAKBjEUzOwR9MKgkmAAB0NoLJOTjqh3IIJgAAdD6CyTkwlAMAQNchmJwDQzkAAHQdgsk5OKIJJgAAdBWCyTmcHsphuTAAAJ2NYHIO9JgAANB1CCbn0NBjcqrKLZ9hmNwaAAB6NoLJOTTs/OozDFWyLT0AAJ2KYHIOdpvVf5VhhnMAAOhcBJM2YMkwAABdg2DSBv4JsKzMAQCgUxFM2oAeEwAAugbBpA1O95gQTAAA6EwEkzZwxHAhPwAAugLBpA0YygEAoGsQTNqAoRwAALoGwaQNTveYsCoHAIDORDBpg9MX8quVwbb0AAB0GoJJGzQM5bg9PrlqvSa3BgCAnotg0gYR4TZFhNkkMc8EAIDORDBpI5YMAwDQ+QgmbeRfmcMEWAAAOg3BpI0aT4AFAACdg2DSRmyyBgBA5yOYtFEcm6wBANDpCCZtFE+PCQAAnY5g0kYM5QAA0PkIJm3kiK5fLlzFqhwAADoLwaSN6DEBAKDzEUzaqCGYVNd45PawLT0AAJ2BYNJG0RF22W0WSVJ5Bb0mAAB0BoJJG1ksFqXER0mSisqqTW4NAAA9E8EkAKmJ9cGklGACAEBnIJgEIC0xWpJUWFplcksAAOiZCCYBoMcEAIDORTAJQBrBBACATkUwCUBqUt1QTlFZtXyGYXJrAADoeQgmAUh2RMhmtcjt8ansVI3ZzQEAoMchmATAZrUqJT5SklTIcA4AAB2OYBKgtIbhHFbmAADQ4QgmAUpNqJsAS48JAAAdj2ASIJYMAwDQeQgmAWIoBwCAzkMwCVDjHhOWDAMA0LEIJgFKdkTKarGo1uPjKsMAAHQwgkmA7DarUhLqlgwznAMAQMcimLRDw3AOK3MAAOhYBJN2SEvgKsMAAHQGgkk7sGQYAIDOQTBph7Sk+qGcEoIJAAAdiWDSDqmJDVcZrpLBkmEAADoMwaQdUuLrlwy7fSrlKsMAAHQYgkk72G1W9U6JkSTtO+Y0uTUAAPQcBJN2yslKkCTlHS41tyEAAPQgBJN2yq4PJrsPl5naDgAAehKCSTsN6psgSTp6olKnqtiaHgCAjkAwaae46HD1qZ9nsvtImbmNAQCghyCYnIdB9cM5uxjOAQCgQxBMzkN2/XDOLnpMAADoEAST89AQTPKLKlRR7Ta3MQAA9AAEk/MQHxuh9KRoGZL20GsCAMB5I5icp4b9TBjOAQDg/AUcTHw+n1asWKHJkydr1KhRuummm3TkyJEznr9nzx7dfPPNGj9+vCZOnKgFCxbo2LFj59XoYMIEWAAAOk7AwWTVqlV6/vnndf/99+uFF16Qz+fT/PnzVVvbci+P0tJS3XDDDYqMjNTatWv15z//WSUlJZo/f75qanrGNWay+yZKkg4XnVKli3kmAACcj4CCSW1trdasWaMFCxZo6tSpysnJ0aOPPqqCggK98847Lc7fsGGDqqqq9NBDD2nQoEEaNmyYli1bpn379mnbtm0dVoSZEuMi1KdXjAxD+uSbArObAwBAtxZQMMnLy1NlZaUmTpzoP+ZwODRkyBBt3ry5xfkTJ07UqlWrFBkZefoJrXVP6XT2nIvfTc/tI0l6b2u+fIZhcmsAAOi+AgomBQV1PQIZGRlNjqempvpvaywzM1MTJkxocuxPf/qTIiMjNXbs2EDbGrQmDktXVIRdRaXV+nrfSbObAwBAt2UP5OTq6mpJUnh4eJPjERERKi8vP+f9165dq+eee05Lly5VUlJSIE/dhN3e8YuJbDZrkz8DEWsP19Tc3npr42G9ty1fY3JSO7p5neJ8au6OQq1eKfRqDrV6pdCrOdTqlUKv5oCCScOQTG1tbZPhmZqaGkVFRZ3xfoZh6A9/+IMef/xx3XrrrZo3b147mytZrRYlJsa0+/7n4nCcuY6zmT19kP5v02F9s79EFbU+9U2L6+CWdZ721txdhVq9UujVHGr1SqFXc6jVK4VOzQEFk4YhnKKiImVlZfmPFxUVKTs7u9X7uN1uLVmyRG+++aaWLFmi66+/vv2tleTzGXI6q87rMVpjs1nlcETJ6ayW1+sL+P4RVin3ol7atrtYL723W9d/N6fD29jRzrfm7ibU6pVCr+ZQq1cKvZpDrV6pZ9TscES1uccnoGCSk5Oj2NhYbdq0yR9MnE6nduzYoblz57Z6n8WLF+vdd9/Vww8/rCuuuCKQpzsjj6fz3hiv19fux//2mExt212sf311TDPG9lVqQvdIt+dTc3cUavVKoVdzqNUrhV7NoVavFDo1BzRgFR4errlz52r58uV67733lJeXpzvuuEPp6emaMWOGvF6viouL5XK5JEmvvPKK1q9frzvuuEPjxo1TcXGx/6vhnJ4kJytBAzLiVOv26Xd/3aaCko7v2QEAoCcLeCbNggULdPXVV2vp0qWaM2eObDabVq9erbCwMB0/flyTJk3S+vXrJUlvvvmmJOmhhx7SpEmTmnw1nNOTWCwW3f6DEeqdEqPSUzX63V+36diJSrObBQBAt2ExjO618YbX61NJScf/srfbrUpMjFFpaeV5d5U5K2u1/IXPlV9cqbjoMC2+drT6pHTehN326siau4NQq1cKvZpDrV4p9GoOtXqlnlFzUlJMm+eYhMbaoy7miAnX4mtHKystVqeq3Fr+wucqLGVYBwCAcyGYdJLYqDAtvCZXfXrFqLyiVsv/9rlOlFeb3SwAAIIawaQTNYSTtKRonXTWaNnfPtfhwlNmNwsAgKBFMOlk8THhWnTNKPVKiFRxmUv3/2WL1n1yUF5f9xwnBACgMxFMukCSI1K//MnFGj2ol7w+Q6/+Y79+s3abDhb0nAsZAgDQEQgmXcQRHa7bvj9M82cOVlSEXQeOO3X/M1u0+u87VHqqxuzmAQAQFALa+RXnx2Kx6FvDMjS4X5Je+nCfPt1eoI+/LtDG7YW6oLdD2VkJGtwvSdlZCbJaLGY3FwCALkcwMUFiXIRu+vch+vaYTL3w/h7tzS/XnvqvNz85pJT4SE3N7aNJIzLkiA4/9wMCANBDEExMdEFvh5ZcN1pFZdXadbhMuw6X6su9J3Wi3KWXPtynN/51QDfPGqrRg3qZ3VQAALoEwcRkFotFaYnRSkuM1pSRvVXj9uqznYV6f+tRHSo8pcdf+0a3zBqqi3NSzW4qAACdjsmvQSYizKbJI3pr6U/HaOLQNHl9hp54fbs+21lodtMAAOh0BJMgZbNa9bMrhuiS4enyGYaefGO7nl6/k91jAQA9GkM5QcxqteiG7w1WuN2mDz4/qn9+dVyffFOgySN76+pLL1B0ZJjZTQQAoEPRYxLkrBaL5l2Wrf9v3hgN6Z8or8/Qh58f1f1/2aKjJzr+KssAAJiJYNJNDOwTr4XX5GrxnFwlOyJUWFqtB57doi15RTIMw+zmAQDQIRjK6WZy+iXqv64fqyde+0Z5h8u06rVvFBVhU+/kGGWlx+mKCf2U5Ig0u5kAALQLPSbdkCM6XHddM0qXj8uSzWpRdY1X+4459cG2o7rvmc3adbjU7CYCANAu9Jh0UzarVT+aPlCzL71ABSVVOlpcqbc2HtLhogot+9sX+vG3B+o7YzJlYWt7AEA3Qo9JN2e3WZXZK1bjh6RpybwxmjA0TT7D0N827NHKV75WeWWt2U0EAKDNCCY9SESYTTfNHKJrvn2RbFaLPt9zQv/11CZtySsyu2kAALQJwaSHsVgsmjG2r/7rpxcrs1esKqrdWvXaN3ro+W3MPQEABD2CSQ+VlRane6+/WFdM7Ceb1aK8w2X63fOf63d/3abjJ9n/BAAQnAgmPZjdZtUPLr1QD94yUVNz+8hmtWjXkTL9Zu1W7ckvM7t5AAC0QDAJAcnxkfrJZdl68JaJuqC3Q5Uuj5a/8IW27mLuCQAguBBMQkhyfKQWzcnVqIEpcnt8WvHSV3r1w73sHAsACBoEkxATEWbTbbOH6dJRvWUY0pp12/XHV7+Rq9ZjdtMAACCYhCKb1aqfXJateZdly2a16LMdhbr/L1v0+Z5iuT0+s5sHAAhh7PwaoiwWi/5tbF8Nu6iXfvvMZzp+skqPvfy1oiJsGjWwl2aM7at+6XFmNxMAEGLoMQlxQwYk61fzx+s7F2cqITZc1TVefbq9QPc9s1l/XrddJ8tdZjcRABBC6DGBEmIjdO13Bumab1+kfUfL9cG2o9q4o1Cfbi/U5rxiXTqqt2aM7ateCVEyDEP5xZXKO1SqXolRGtwvURFhNrNLAAD0EAQT+FktFl2UmaCLMhM0Y1xf/b/39yrvcJne25qv97fla+SFKTpeUqXCkir/few2q3KyEvTdCf00uF+iia0HAPQEBBO0qn+6Q4vm5GrnoVL936bD+uZAib7Ye0JSXRjJzkpQwckqnXS69M2BEm0/WKKrL71Ql4/PksVikWEYOnaySs7KWrlqPXJ7fLooM0GJcREmVwYACGYEE5yRxWLRkP5JGtI/SYcLT2nb7mKlJ0Vr5MAURUXYZRiGjp+s0lubDunjrwv0vx/u0/7jTvVKiNKWvCKdaDY/JSLcph9NG6hLR/WW1WIxqSoAQDAjmKBNstLilJXWdJWOxWJR75QY3fi9wbqgd7yef3e3tu4q9t8ebrcqJSFKEWE2uWo9On6ySmvf3qXNOws1e8qF6pcepzB73fxrwzB0qtqtmEi7bFbmZANAqCKY4LxZLBZNy+2jvr1i9cL7e5QSH6mLs1M1/IJkRYTXTYz1GYbe25qvlz/cp7zDZfrNc1tlt1nULy1OHp+hwpIquWq9io8N12VjszQ1t7ciw8/87WkYhsoqahUVYTvreWdTXePRp9sL9NEXx2QY0p0/HqmEWIaaAMBMFqOb7Ufu9fpUUtLxV8e1261KTIxRaWmlPCGyyZgZNReWVumVj/Zr56FSVVS7z3heTKRdowamKMkRqSRHhCwWiyqr3aqoduvoiUodLDglZ2WtIsJsmjwyQ5eNzVJyfGSLxzlZ7pKr1qOEuAg5YsJlCw/TJ1/k66t9J7Ulr0iuWq//3AEZcbr72tEKN2mVkdvjVZi9Y5871L6vQ61eKfRqDrV6pZ5Rc1JSjGy2tvWG02OCLpWWGK1brxomwzBUVFatA8edCrfblJ4UrSRHhDbvLNL6jYdUWFqtj78pOOfj1bi92rAlXx9sO6qLMuOVGBephNhwlVXUaPeRMp101vjPDbdb5fb61DiKpydF65Lh6fq/TYd14PgprVm/U7fMGipLozkwXp9P+4465fb6NDgrUVZrx86PMQxDf9uwRxu25is2KkypiVHqlRClhNhwxcdEKCU+UiMHpviHvQCgJyOYwBQWi0VpidFKS4xucnzyyN66ZHiGvtx3QkeLK1XidKnkVF24iI0KU0xkmFISIjUgw6G+qbHak1+mtzYe1s5Dpco7XNbieawWi6IibKp0eVRb/z+NzF4xGtI/SSMHpignK0EWi0UD+8Rr+Qtf6LOdRYqKsCsjOUY1tR7lF1dq+4ESVdXUXUuod0qMrpo0QKOze8nnM1TidKmsorauN8flltVi0eB+iUpytOy9keS/YGLj4PP2Z0e0YWu+JKmivldo/zFnk/v1S4/TrVcOVWqz16s9jhZX6LV/HtCQAUm6dGTvDglahaVVeumDfbqwT7wuG9e3SX0AEAiGcur1hK6yQPWkmo8UVehI0SmVV9T6555c1DdBF/Z2KDLcrlq3V6eq3UrrFSd5va3W+48vj+mZt/JaffzYqDB5fYaq6wNKdIRd1TUenemHJ7NXjIYNSFb/jDj1S4uTzWqp37SuQMVlLk0cmqaZ3+qvQwWntOq1byRJP5x2oYYNSFZRaZWKy1wqr6xReWWtvt53UpUuj6IibLrhu4N1cU5qm14Tt8en8qpaDeqfLKezWh6PT8dPVup3f90mZ1XdMNqAjDj95LKcgC4/UOlyK9xu8/fgbN1VrDXrd6i6pm5Y7KrJAzTrkgFtfryO1JO+p9sq1GoOtXqlnlFzIEM5BJN6PeGND1So1dyWev/x5TF9seeEIsJtigizKSE2XMMvSNaADIdctR69s/mI3t1yxP9LOMxuVWJchL83p8pV19vRlh8qm9Uii8Uij9en6aP76Lp/G9RqT0OJ06UnXt+uvUfLJUlZabEam5OqIf2TdKSoQjsOluhgwSnFRYcpJT5KcVFhOlx4SvuPn5LH61OfXjH690sGqG+vGD30t89VXlGrtKRoOStrVF3jlcUiTRiSphljs84YUKpcHm3dVaRPvinQriNlstss6psap8S4CG3bXbcSKy0xSoWl1ZKkH08fqMvGZbXhVTg7Z2Wt7DaLoiPDznhO6akauT1epSZGh9z3tMTPcSjoCTUTTNqhJ7zxgQq1mjuq3iqXR8Vl1UqMi1BcdFiLMHGqqlbfHCjR7iNlOlx4SkeKKuXx+pSTlaCJw9LVKz5Kf994SNsPlEiSRlyYrNt/MPysy6Q9Xp9e/ed+vb3piHwB/MhaLPLPqWn4e2avGC2akyuvz9AL7+3RZzuL/OdflBmvJEekf0ipYcJx40nCrbl8XJZmX3qB3tp4SK/+84Ak6dujMzWkf6L6Zzh0tLhCn+0s0hd7TyguOkyXjuqjScPTWwQOwzBUUFKlL/ee1NZdRdp3zCm7zaqpo3rrexP7NVk15fH69PZnh/X6vw7K5zP04+kDdfmELCUlxYbM97TEz3Eo6Ak1E0zaoSe88YEKtZrNqtfr86mm1qfoyKZTuvbml+tAgVNTRvT2L6s+F2dVrbbtLtaWvLpf2n17xWpI/0QNzIxXdY1XJ8qrVV5Rq94pMbooM14pCVH659cFeuXDvapyeZSRHK27rx0tR0y4/zEPHHfq3c1HtDmvSF7fmT8OMpKj9a1h6ZowJF1ew9D+o+U6eqJS2VkJGjYgWVJdsHj5o/1av/HQOWsJD7Pqoj7xiokKU3RkmEqcLu0/5jzjaq0wu1WjB/VSakKUEuIi9NEXR3W4sKLJOROHpuvO68aouqrmvN7jE2XVKiytVkp8pJLjI2U/xwdqdU1dWO3TK6bL9+Hh57jn6wk1E0zaoSe88YEKtZpDrV7pdM35x8v0+e5iDRuQrNio1odFSk/VaPPOQhmqn2gcFabYRl8xkfY2TWo1DEOb84q0/UCJ9h936lhxpWKjw3Rxdqouzu6lgtJqvb8tX0eLW/85ttusuigzXmOye2n0oF46eqJSr//zgH8oq7GYSLuu+fZFqnJ59P8+2Cuvz1CvxCjl9E1Q/wyHEmLDVXqqRiXOGpWcctX96XTJbrNq3OBUfWtYulITo1Vd49HR4krtPFyqbbuKdajwlP85rBaLUuIj1adXjPqmxqpvaqwu6B2vxLgIuT0+fbAtX29+ekgV1W4lOyI0fXSmJo/sfcbXuaOF2vd1qNUr9YyaCSbt0BPe+ECFWs2hVq8UHDW7PV7ZrNYmq38Mw9D+Y04VllapstqjSpdbMVFhurB3vLLSYlv0UBiGobzDZdp/rFwny1066axRsiNCV04aoPj64Z3dR8r0+GvfqLyyNqD21S0vb3ofi0VKTYhS6aka/2qu5pIdkfIZhkrrV41ZLRb/MJvNalFGcrR6p8QoPSlakeF2hdmtigy3KTEuQsnxkUqIrQs2rhqP3F6f4mMi/L1qJ8qqtf1gifKLKzW0f5JGDExu9TIOhmHI5fYqMyNB5eVV8nh8Olnu0hsfH9Cn2wvVOyVal43N0tjBqWfs9al1e/XVvpPatrtYzqpaeTw+eX2Gcvol6oqJ/VrdwLC6xqMPPj+q+JhwTRya3uS9PVRwSuWVNYqOrAuzDX+eq9eprYLhe7qr9YSaCSbt0BPe+ECFWs2hVq8UejW7vT7ll1Try11F2ptfpkqXR0lxEUqKq9uoL9FR9/eSUy598nWBth8o8U9UToyLUFZqrHIH9dKogSlyxIT7dxguOFmp/OJKHSmu0KGCU8ovrvDP3UmIDddVky/QuMGp2pxXpA1b8nWkqOKMbTybqAi7IsNt/rDToHdKjP7t4kyF2a06Ue7SiTKXjp2s1LETlXLVehUVYVdWWqwSYiO0dVeRPN6mH+uJcRHqnx6niDBb/QaChjxeQ65ar3YcLDnjHKLEuAhd8+2LdHF2L1ksFvl8hv751TG9+o/9/pVdmb1i9eNvD5TPZ+jvnx7S7iNlrT5WeJhVF/aO19wZg5SRHNOu10dq/Xva5zP08dfHVVhare9OyFLMWSZLd0fn83NcU+tVeJj1rL2dR09UKi4qrMkQb0cjmLRDqH2AS6FXc6jVK4VezYHWW3qqRifLXUpPjg5o6KW6xqMDx52qdHk04sJkRTTaLdgwDJ0od+nYibrgUFxWrRq3T26PV9W1XpU4XTpZ7vL3xITZrbLbLP6VXlJd78uFfRxKT4rWll1FTW5ri5ysBF3xrf46cMypDVvz5TxHL1KyI1LjhqQqs1eswmxWuWq9WvfJARWX1V2IMzK8LtD4fIZ/DlBqQpQqqt3+PX4a2G0W9U6OUVWNR1UuT4tl9XabVd+fMkCXjc1q0tPi9fm042Cpjp+sksfrq/8y5K3/02a1KDY6TPGx4crKSFB8lE1xUWE6VHhKa9/epQPHT9XXEqGb/n2oBvVNaNKuEqdL2w+WqKyiVoOzEnVBb0eLPXwMw9COg6U6WODUyAtTlJka2+K1MgxD//jymD7+ukDjh6RpysjeAW1+aBiGvD4joB6kQL6vXbUebc4r0u7DZdpztFxFpdXK7BWjn10xpMWqu/KKGr34wV5t3F6o2KgwLZk7+rxC49kQTNoh1D7ApdCrOdTqlUKv5u5Sr2HU9VbUhZK6D2tXrUclzhpVVLuV2SvWP6xT5fLooy+OanNe3eZ/yfGRSomPVEZyjHonRys9JUYur/TVrkIdO1GpnH6JGtIv0f8/ZLfHp2/2n1R5Va1qar2qdXtlsVhks1lkt1o1IMOhC/s4WvyPutbt1VubDuvvnx6Sx3v6tYyOsGvWpAGaPrqPXLVevfGvA/rg86Oy2SyaOqqPLhuXpcS406unfEbd/j+lp2r0/z7Yq2/2161GS02M0kWZ8RqQ4VCJs0Yff3Nc5RWBDcM13k8oKsKmmMgwnSh3yWKRpozsLZvVImeV2x8SG4uNCtOwAUkakOFQVlqsatw+rfvkgPYdPb25YXbfBE0fk6lhA5IUFWFXjdurtW/v0ieNdqVOckTosnFZio0MU3WtR5XVbhWXu3SirFolp2pks1oUZqsbyqyodqu8slZuj0+D+yXqsnFZGn5B0ll7MwzDUFllrZwur3YfPKnjJ6sUGxWmjOTo+mHCulDsqvXq028K9PE3x1sNsjarRTO/1V9jc1J1orxahwpO6f8+O9zk3MS4CC2ZO1op8VEBvQ9tQTBph+7ygdaRQq3mUKtXCr2aQ61eqfNrrq7xyFn/y9Tt9Sk9KVpREU3nnZRX1CjMbmux8qw5wzD0r6+P64X39rT6yzM2KkyD+yUqPKwusNmt1roAZbPK4/X5l7GXnKrRseJK/5yeCUPT9KNpAxURZtPz7+5u9XIWFkn9MxxKckRo58HSFj09DcLsVg3sE69dh8uazBkakOGomyR9olIWizR5RG99vf9ki2G3QPVOiVHuRSm6oLdD/dMdqnHX9aoVl1Vr95Ey5R0uC/g50hKjNHZwqgb2SVB6UpRe+mi/tuQVtXrugIw4zZ5yoZ7fsFvHT1YpLTFK98wdo/gOHtYhmLQDH2g9v+ZQq1cKvZpDrV6pe9Zc6XJrz5FyHTju1IECpyLsNk0YmqaRA1POOcTRUG9R8SnlF1UozG5VelLTSzVs212s7QdLFBNpV1x0uJLiIpWdleAfrvN4fdqbX65d9XsNHSo8peoajyaP6K3vjs9SfGyESpwuffjFUW3aUegf0pIkR3SYbrlymAb3S5Tb49WHnx/T1t3Fstssigq3KyrCrpT4SPVKiFKSo67nyO31yes1FBMVpviYcPl8hj74/Kj+8eWxc+4RJNUFo75pcXXX0Yqv22fo+MkqFZZWNXnPL8pM0PTRfTRkQFKTydKGYeiznUV68f09ctV61Sshyn8NrknDM2S1WlTidOm3z23TSadLQ/sn6q5rcs/9RgaAYNIO3fGH+3yFWs2hVq8UejWHWr1S6NXcWfUahnHGIZUTZdXacahUzspaXTI8o8lQ1fmocnm0ZVeR9h0t1/5jTh07UanwcFvdhG1HpAZkxCk7K1E5/RKVnuo475pbu1ZXY4UlVfr9S1+pf3qcbpk1tN3P0xquLgwAQADONs8jJSFKUxI6ft5FdKRdU0b21pSRvSXV9eQ0XKqiMXsHXVn8XPsQpSVF6zc3jTf9IpwEEwAAgkBH7fVyPswOJZJk/qsAAABQj2ACAACCBsEEAAAEDYIJAAAIGgQTAAAQNAgmAAAgaBBMAABA0CCYAACAoEEwAQAAQYNgAgAAggbBBAAABA2CCQAACBoEEwAAEDQshmEYZjciEIZhyOfrnCbbbFZ5vb5OeexgFWo1h1q9UujVHGr1SqFXc6jVK3X/mq1WS5uvXNztggkAAOi5GMoBAABBg2ACAACCBsEEAAAEDYIJAAAIGgQTAAAQNAgmAAAgaBBMAABA0CCYAACAoEEwAQAAQYNgAgAAggbBBAAABA2CCQAACBohH0x8Pp9WrFihyZMna9SoUbrpppt05MgRs5vVYcrKynTvvfdqypQpGj16tObMmaMtW7b4b//00081e/ZsjRw5Updffrn+/ve/m9jajnfgwAHl5ubqlVde8R/buXOn5s6dq1GjRmn69Ol69tlnTWxhx3nttdf0ve99T8OHD9cVV1yht956y39bfn6+brnlFo0ePVqTJk3S73//e3m9XhNbe348Ho/+8Ic/aNq0acrNzdV1112nL774wn97T3uPn3zySc2bN6/JsXPV2J0/21qr9/3339cPfvAD5ebmavr06frd734nl8vlv72mpkb33XefJk6cqNzcXN11110qKSnp6qa3W2s1N7Z06VJNnz69ybHu/B6flRHiHnvsMWP8+PHGBx98YOzcudO48cYbjRkzZhg1NTVmN61D3HDDDcbMmTONzZs3G/v37zfuu+8+Y8SIEca+ffuMvXv3GsOHDzceeeQRY+/evcZTTz1lDBkyxPjkk0/MbnaHqK2tNWbPnm0MGjTIePnllw3DMIySkhJj/PjxxpIlS4y9e/caL730kjF8+HDjpZdeMrm15+e1114zhgwZYjz33HPGoUOHjFWrVhk5OTnGtm3bjNraWmPGjBnGzTffbOzatct49913jXHjxhl/+MMfzG52u61YscK45JJLjH/+85/GwYMHjV/+8pfGmDFjjMLCwh73Hj/33HNGTk6OMXfuXP+xttTYXT/bWqt38+bNxuDBg43HH3/cOHDggPHhhx8aU6ZMMe655x7/Offcc4/xne98x9i8ebPx5ZdfGldddZVx3XXXmVFCwFqrubF3333XGDRokDFt2rQmx7vre3wuIR1MampqjNzcXOOvf/2r/1h5ebkxYsQIY926dSa2rGMcPHjQGDRokLFlyxb/MZ/PZ3znO98xfv/73xv/9V//ZVx99dVN7nPnnXcaN954Y1c3tVM8/PDDxk9+8pMmweSJJ54wJk2aZLjd7ibnzZgxw6xmnjefz2dMmzbNePDBB5scv/HGG40nnnjCWLdunTFs2DCjrKzMf9sLL7xgjB49utt+gM2aNcv47W9/6//3qVOnjEGDBhlvv/12j3mPCwoKjFtuucUYNWqUcfnllzf5pXWuGrvjZ9vZ6r3rrruM66+/vsn5r776qjF06FCjpqbGKCgoMHJycowPP/zQf/v+/fuNQYMGGdu2beuyGgJ1tpobFBYWGhMmTDDmzp3bJJh0x/e4rUJ6KCcvL0+VlZWaOHGi/5jD4dCQIUO0efNmE1vWMRITE/WnP/1Jw4cP9x+zWCyyWCxyOp3asmVLk9olacKECdq6dasMw+jq5naozZs368UXX9SDDz7Y5PiWLVs0btw42e12/7EJEybo4MGDOnHiRFc3s0McOHBAR48e1b//+783Ob569Wrdcsst2rJli4YOHar4+Hj/bRMmTFBFRYV27tzZ1c3tEMnJyfrggw+Un58vr9erF198UeHh4crJyekx7/H27dsVFhamN954QyNHjmxy27lq7I6fbWer98Ybb9Tdd9/d5JjVapXb7VZFRYW2bt0qqe41aDBgwAClpaUFbb3S2WuWJMMwdM899+jKK6/UuHHjmtzWHd/jtgrpYFJQUCBJysjIaHI8NTXVf1t35nA4dOmllyo8PNx/7O2339ahQ4c0efJkFRQUKD09vcl9UlNTVV1drdLS0q5ubodxOp1avHixli5d2uK9PVPNknT8+PEua2NHOnDggCSpqqpKP/vZzzRx4kT98Ic/1Pvvvy+pZ9b8y1/+UmFhYfr2t7+t4cOH69FHH9WKFSuUlZXVY+qdPn26HnvsMfXt27fFbeeqsTt+tp2t3iFDhignJ8f/b7fbrWeeeUbDhg1TUlKSCgsLlZiYqIiIiCb3C+Z6pbPXLEnPPPOMiouLdeedd7a4rTu+x20V0sGkurpakpr84pakiIgI1dTUmNGkTrVt2zYtWbJEM2bM0NSpU+VyuVrU3vDv2tpaM5rYIf7nf/5Hubm5LXoQJLVac8OHWXd9zysqKiRJd999t2bOnKk1a9bokksu0c9//nN9+umnPbLmvXv3Ki4uTn/84x/14osvavbs2Vq4cKF27tzZI+tt7lw19uTPNo/Ho8WLF2vPnj367//+b0l1n+XNa5W6d715eXlauXKlli1b1mptPfk9tp/7lJ4rMjJSUt0v4Ya/S3U/2FFRUWY1q1Ns2LBBCxcu1OjRo7V8+XJJdd/AzQNIw7+7a/2vvfaatmzZonXr1rV6e2RkZIuaG36Io6OjO719nSEsLEyS9LOf/Uzf//73JUmDBw/Wjh079PTTT/e4mo8fP6677rpLzzzzjC6++GJJ0vDhw7V371499thjPa7e1pyrxp762VZRUaH//M//1GeffaaVK1dqxIgRklp/PaTuW29NTY0WLlyoW2+9tUlPUWM99T2WQrzHpKELrKioqMnxoqIipaWlmdGkTvHcc8/p9ttv17Rp0/TEE0/4/2eVkZHRau3R0dGKi4szo6nn7eWXX9bJkyc1depU5ebmKjc3V5L03//935o/f77S09NbrVlSt33PG9o9aNCgJscHDhyo/Pz8Hlfzl19+Kbfb3WTulCSNHDlShw4d6nH1tuZcNfbEz7aioiL/svDVq1fr0ksv9d+Wnp6usrKyFuGku9b75Zdfas+ePVq5cqX/c+zJJ5/UsWPHlJubqy1btvTI97hBSPeY5OTkKDY2Vps2bVJWVpakuvkJO3bs0Ny5c01uXcd4/vnndf/992vevHn65S9/KYvF4r/t4osv1meffdbk/I0bN2r06NGyWrtnZl2+fHmTvQ0kacaMGVqwYIFmzZql119/XS+88IK8Xq9sNpukupoHDBig5ORkM5p83oYOHaqYmBh9+eWX/h4ESdq9e7eysrI0duxYvfbaa6qoqFBsbKykuppjYmLO+L+xYNYwt2LXrl3+/zFLdfX2799fI0eO7HHvcXNjx449a41xcXE96rOtvLxcP/3pT1VRUaG//vWvys7ObnL7mDFj5PP5tHXrVv9k0AMHDqiwsFBjx441o8nnZcSIEXrnnXeaHFu7dq3eeecdrV27VmlpabJarT3qPW7C7GVBZnvkkUeMcePGGRs2bGiyDry2ttbspp23/fv3G0OHDjVuu+02o6ioqMmX0+k0du/ebQwdOtRYtmyZsXfvXmP16tU9ah+TBo2XC584ccIYO3ascffddxt79uwxXn75ZWP48OHGK6+8YnIrz88f//hHIzc311i3bl2TfUw2btxouFwu4zvf+Y7xs5/9zNi5c6d/H5PHHnvM7Ga3i9frNebMmWNcfvnlxqeffmocOHDAePTRR43BgwcbX3zxRY98j+++++4mS0nbUmN3/mxrXu/dd99tDB061Pj0009bfJZ5PB7DMOq2Opg+fbqxceNG/z4mZ9oXJBg1r7m5FStWtNjHpDu/x2cT0j0mkrRgwQJ5PB4tXbpULpdLY8eO1erVq/3j9t3Z22+/LbfbrXfffVfvvvtuk9u+//3v68EHH9SqVau0bNky/eUvf1FmZqaWLVvWYglxT5KcnKynnnpKv/71r/X9739fvXr10uLFi/1zM7qrn//854qKitKjjz6qwsJCXXjhhXrsscc0fvx4SdJTTz2l++67Tz/60Y8UHx+va6+9Vj//+c9NbnX7WK1WPf744/r973+vJUuWqLy8XIMGDdIzzzzjX3LZE9/jxtryfdxTPtu8Xq/Wr18vt9utn/70py1uf++995SZman7779fv/nNb/SLX/xCkjRlyhQtXbq0q5vbpXrKe9ycxTC6+YYVAACgx+ieEwkAAECPRDABAABBg2ACAACCBsEEAAAEDYIJAAAIGgQTAAAQNAgmAAAgaBBMAABA0CCYAACAoEEwAQAAQYNgAgAAggbBBAAABI3/HzKlRPbu8sAQAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "plot_costs(history.history[\"loss\"])"
    ]
@@ -506,9 +1114,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1250/1250 [==============================] - 2s 2ms/step\n",
+      "Accuracy: 0.9464\n",
+      "F1: 0.7014\n"
+     ]
+    }
+   ],
    "source": [
     "y_pred = model.predict(X_test)\n",
     "y_pred = np.array(y_pred > 0.5, dtype=int).squeeze()\n",
@@ -558,7 +1176,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.12"
+   "version": "3.11.6"
   }
  },
  "nbformat": 4,
-- 
GitLab