933 lines
235 KiB
Plaintext
933 lines
235 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Support Vector Machines"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## IRIS data set\n",
|
|
"> - **label**: species \n",
|
|
"> - **features**: sepal_length, sepal_width, petal_length, petal_width"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>sepal_length</th>\n",
|
|
" <th>sepal_width</th>\n",
|
|
" <th>petal_length</th>\n",
|
|
" <th>petal_width</th>\n",
|
|
" <th>species</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>5.1</td>\n",
|
|
" <td>3.5</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>4.9</td>\n",
|
|
" <td>3.0</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>4.7</td>\n",
|
|
" <td>3.2</td>\n",
|
|
" <td>1.3</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>4.6</td>\n",
|
|
" <td>3.1</td>\n",
|
|
" <td>1.5</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>5.0</td>\n",
|
|
" <td>3.6</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" sepal_length sepal_width petal_length petal_width species\n",
|
|
"0 5.1 3.5 1.4 0.2 setosa\n",
|
|
"1 4.9 3.0 1.4 0.2 setosa\n",
|
|
"2 4.7 3.2 1.3 0.2 setosa\n",
|
|
"3 4.6 3.1 1.5 0.2 setosa\n",
|
|
"4 5.0 3.6 1.4 0.2 setosa"
|
|
]
|
|
},
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"import seaborn as sns\n",
|
|
"iris = sns.load_dataset('iris')\n",
|
|
"iris.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"scrolled": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>sepal_length</th>\n",
|
|
" <th>sepal_width</th>\n",
|
|
" <th>petal_length</th>\n",
|
|
" <th>petal_width</th>\n",
|
|
" <th>species</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>5.1</td>\n",
|
|
" <td>3.5</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>4.9</td>\n",
|
|
" <td>3.0</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>4.7</td>\n",
|
|
" <td>3.2</td>\n",
|
|
" <td>1.3</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>4.6</td>\n",
|
|
" <td>3.1</td>\n",
|
|
" <td>1.5</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>5.0</td>\n",
|
|
" <td>3.6</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>setosa</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" sepal_length sepal_width petal_length petal_width species\n",
|
|
"0 5.1 3.5 1.4 0.2 setosa\n",
|
|
"1 4.9 3.0 1.4 0.2 setosa\n",
|
|
"2 4.7 3.2 1.3 0.2 setosa\n",
|
|
"3 4.6 3.1 1.5 0.2 setosa\n",
|
|
"4 5.0 3.6 1.4 0.2 setosa"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# Make it binary\n",
|
|
"data=iris[iris['species']!='virginica']\n",
|
|
"data.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"(100, 2)\n",
|
|
"(100,)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"X = data[['sepal_width','petal_width']]\n",
|
|
"y = data['species']\n",
|
|
"print(X.shape)\n",
|
|
"print(y.shape)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"scrolled": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"(75, 2)\n",
|
|
"(25, 2)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=2)\n",
|
|
"print(Xtrain.shape)\n",
|
|
"print(Xtest.shape)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Estimation"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style>#sk-container-id-1 {color: black;background-color: white;}#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: \"▸\";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: \"▾\";}#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>SVC(C=10, kernel='linear')</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\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(C=10, kernel='linear')</pre></div></div></div></div></div>"
|
|
],
|
|
"text/plain": [
|
|
"SVC(C=10, kernel='linear')"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.svm import SVC\n",
|
|
"\n",
|
|
"svc1 = SVC(kernel='linear',C=10)\n",
|
|
"svc1.fit(Xtrain,ytrain)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array(['versicolor', 'setosa', 'versicolor', 'setosa', 'setosa', 'setosa',\n",
|
|
" 'setosa', 'setosa', 'setosa', 'setosa'], dtype=object)"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"ypred = svc1.predict(Xtest)\n",
|
|
"ypred[:10]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([[2.3, 0.3],\n",
|
|
" [3.5, 0.6],\n",
|
|
" [2.7, 1. ]])"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"svc1.support_vectors_"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([[16, 0],\n",
|
|
" [ 0, 9]])"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.metrics import confusion_matrix\n",
|
|
"confusion_matrix(ytest,ypred)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Data Visualization"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0,\n",
|
|
" 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
|
|
" 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0,\n",
|
|
" 0, 0, 1, 1, 0, 0, 1, 0, 0])"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.preprocessing import LabelEncoder\n",
|
|
"y1 = LabelEncoder().fit_transform(ytrain)\n",
|
|
"y1"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/root/.local/share/virtualenvs/app-4PlAip0Q/lib/python3.11/site-packages/sklearn/base.py:450: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Create grid to evaluate model\n",
|
|
"\n",
|
|
"import numpy as np\n",
|
|
"xx = np.linspace(2, 5, 100) #(100,)\n",
|
|
"yy = np.linspace(0, 2, 100) #(100,)\n",
|
|
"YY, XX = np.meshgrid(yy, xx) #(100,100) and (100,100) Replicate the data\n",
|
|
"\n",
|
|
"xy = np.vstack([XX.ravel(), YY.ravel()]).T # (10000,2)\n",
|
|
"Z = svc1.decision_function(xy).reshape(XX.shape) #(100,100)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"import matplotlib.pyplot as plt\n",
|
|
"%matplotlib inline\n",
|
|
"\n",
|
|
"plt.scatter(Xtrain['sepal_width'], Xtrain['petal_width'], c=y1, \n",
|
|
" s=30, cmap=plt.cm.Paired)\n",
|
|
"\n",
|
|
"# plot the decision function\n",
|
|
"ax = plt.gca()\n",
|
|
"\n",
|
|
"# plot decision boundary and margins\n",
|
|
"ax.contour(XX, YY, Z, colors='k', levels=[-1, 0, 1], alpha=0.5,\n",
|
|
" linestyles=['--', '-', '--'])\n",
|
|
"\n",
|
|
"# plot support vectors\n",
|
|
"ax.scatter(svc1.support_vectors_[:, 0], svc1.support_vectors_[:, 1], s=100,\n",
|
|
" linewidth=1, facecolors='none', edgecolors='k');"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Nonlinear Kernel"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 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-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 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-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 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-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 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-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(degree=2, gamma='auto', kernel='poly')</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-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(degree=2, gamma='auto', kernel='poly')</pre></div></div></div></div></div>"
|
|
],
|
|
"text/plain": [
|
|
"SVC(degree=2, gamma='auto', kernel='poly')"
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.svm import SVC\n",
|
|
"svc2 = SVC(kernel='poly', degree=2, gamma='auto')\n",
|
|
"svc2.fit(Xtrain, ytrain)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"ypred = svc2.predict(Xtest)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([[16, 0],\n",
|
|
" [ 0, 9]])"
|
|
]
|
|
},
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.metrics import confusion_matrix\n",
|
|
"\n",
|
|
"confusion_matrix(ytest, ypred)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/root/.local/share/virtualenvs/app-4PlAip0Q/lib/python3.11/site-packages/sklearn/base.py:450: UserWarning: X does not have valid feature names, but SVC was fitted with feature names\n",
|
|
" warnings.warn(\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAGiCAYAAAAba+fDAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAACD7klEQVR4nO3dd3zU9eE/8NfnduZlX3bIZoQ9AgiKCga0WuqmDlBQ62i11AH9tVKqFuuq1oVWEW2rKM6voDhQQAVBQcoQQhZJCLns3CWX5Nbn8/sj3sccubskkHl5PR+Pe0A+K+/78CH3ynsKkiRJICIiIvITioEuABEREVFvYrghIiIiv8JwQ0RERH6F4YaIiIj8CsMNERER+RWGGyIiIvIrDDdERETkVxhuiIiIyK8w3BAREZFfYbghIiIiv9KjcLNmzRpMnToVISEhiImJwcKFC5Gfn9/leRs3bsTIkSOh0+kwduxYfPTRR277JUnC/fffj7i4OAQEBGDu3LkoKCjo2TshIiIiQg/Dzfbt23H77bfj22+/xWeffQa73Y4LLrgAFovF6zk7d+7EokWLsHTpUvzwww9YuHAhFi5ciEOHDsnHPPLII/jnP/+JtWvXYvfu3QgKCkJeXh7a2tpO/50RERHRsCScycKZNTU1iImJwfbt23H22Wd7POaqq66CxWLBpk2b5G3Tp0/HhAkTsHbtWkiShPj4ePzhD3/A3XffDQAwmUwwGAxYv349rr766tMtHhEREQ1DqjM52WQyAQAiIiK8HrNr1y4sX77cbVteXh7ef/99AEBJSQmMRiPmzp0r79fr9cjNzcWuXbs8hhur1Qqr1Sp/LYoi6uvrERkZCUEQzuQtERERUT+RJAlNTU2Ij4+HQtF73YBPO9yIooi77roLZ511FnJycrweZzQaYTAY3LYZDAYYjUZ5v2ubt2NOtWbNGqxevfp0i05ERESDSHl5ORITE3vteqcdbm6//XYcOnQIX3/9da8VprtWrlzpVhtkMpmQnJyM8vJyhIaG9nt5iIiIqOfMZjOSkpIQEhLSq9c9rXBzxx13YNOmTdixY0eXSSs2NhZVVVVu26qqqhAbGyvvd22Li4tzO2bChAker6nVaqHVajttDw0NZbghIiIaYnq7S0mPGrgkScIdd9yB9957D1988QVSU1O7PGfGjBnYunWr27bPPvsMM2bMAACkpqYiNjbW7Riz2Yzdu3fLxxARERF1V49qbm6//Xa8/vrr+OCDDxASEiL3idHr9QgICAAAXH/99UhISMCaNWsAAHfeeSfOOeccPP7447jooouwYcMGfP/993jxxRcBtKe1u+66Cw8++CAyMzORmpqKP//5z4iPj8fChQt78a0SERHRcNCjcPP8888DAObMmeO2/ZVXXsGSJUsAAGVlZW49nmfOnInXX38df/rTn/DHP/4RmZmZeP/99906Id97772wWCy4+eab0djYiFmzZmHLli3Q6XSn+baIiIhouDqjeW4GC7PZDL1eD5PJxD43REREQ0RffX5zbSkiIiLyKww3RERE5FcYboiIiMivMNwQERGRX2G4ISIiIr/CcENERER+heGGiIiI/ArDDREREfkVhhsiIiLyKww3RERE5FcYboiIiMivMNwQERGRX2G4ISIiIr/CcENERER+heGGiIiI/ArDDREREfkVhhsiIiLyKww3RERE5FcYboiIiMivMNwQERGRX2G4ISIiIr/CcENERER+heGGiIiI/ArDDREREfkVhhsiIiLyK6qBLgAR9T5TWT5KtvwbtUe+g1KlQdy0eRgxbxF0YdEDXTQioj7HcEPkZyp2fYS9z9wDQRAgiU4AQNMHxSj57A3MWvUfhCSkD3AJiYj6FpuliPyI1VSHfc/dB0iiHGwAAKIIR0sT9j59NyRJGrgCEhH1A4YbIj9StuM9SKLocZ8kOmEuOwpTyeF+LhURUf9iuCHyI5bKEgiC7//WzSdL+qk0REQDg+GGyI9oQsIB+G52aj+GiMh/MdwQ+ZHEsy5x72tzCk1IBKLG5PZjiYiI+h/DDZEfCU3Owoi5izrvEAQAAsbe8CcoVOp+LxcRUX/iUHAiPzN2yZ8QFJeCok3r0NZQDQDQp47ByMt/C8OEswe4dEREfU+Q/GBcqNlshl6vh8lkQmho6EAXh2hQkEQn2hqqoVBpoNVHDnRxiIg66avP7x43S+3YsQMXX3wx4uPjIQgC3n//fZ/HL1myBIIgdHqNGTNGPuYvf/lLp/0jR47s8Zshop8JCiUCIuMYbIho2OlxuLFYLBg/fjyeffbZbh3/1FNPobKyUn6Vl5cjIiICV1xxhdtxY8aMcTvu66+/7mnRiIiIiHre52bBggVYsGBBt4/X6/XQ6/Xy1++//z4aGhpwww03uBdEpUJsbGxPi0NERETkpt9HS7388suYO3cuUlJS3LYXFBQgPj4eaWlpuOaaa1BWVub1GlarFWaz2e1FREREBPRzuDl58iQ+/vhjLFu2zG17bm4u1q9fjy1btuD5559HSUkJZs+ejaamJo/XWbNmjVwjpNfrkZSU1B/FJyIioiHgjEZLCYKA9957DwsXLuzW8WvWrMHjjz+OkydPQqPReD2usbERKSkpeOKJJ7B06dJO+61WK6xWq/y12WxGUlISR0sRERENIX01Wqrf5rmRJAnr1q3Ddddd5zPYAEBYWBiysrJQWFjocb9Wq4VWq+2LYhIREdEQ12/NUtu3b0dhYaHHmphTNTc3o6ioCHFxcf1QMiIiIvInPa65aW5udqtRKSkpwf79+xEREYHk5GSsXLkSFRUVeO2119zOe/nll5Gbm4ucnJxO17z77rtx8cUXIyUlBSdPnsSqVaugVCqxaJGHaeSJhoCmiiI0lhyGUqNDdM5MqAODB7pIRETDRo/Dzffff49zzz1X/nr58uUAgMWLF2P9+vWorKzsNNLJZDLhnXfewVNPPeXxmidOnMCiRYtQV1eH6OhozJo1C99++y2io6N7WjyiAdVmqsW+Z+5B7eFv5W0KjQ7Zl96GjIuXQRCEASwdEdHwwOUXiHqJ6LBh28rLYKks8bgy95hr7kP6RUv6v2BERIPUoFl+gYg8q9zzGZorCj0GGwDIf+85OG1Wj/uIiKj3MNwQ9RLjvm0QFN7/SzlamtBQsL//CkRENEwx3BD1EtFhR1etvKLD1k+lISIavhhuiHpJRNYEn/sFpQr61M6jBYmIqHcx3BD1kqSzfwWVLgjw1DQlKJB09kJoQ8P7v2BERMMMww1RL9EE6zFj5UtQB4QAaK+pEZTtsy3EjDsLOdf/cSCLR0Q0bPTb8gtEw0F4xnjMe/oLVOzajMbi9kn84qZdgIisiZzjhoion3CeGyIiIhoQnOeGiIiIqBsYboiIiMivMNwQERGRX2G4ISIiIr/CcENERER+heGGiIiI/ArDDREREfkVhhsiIiLyK5yhmIj6hOn4ERR9/CpqD+2CoFAidvJ5SJ1/HYJjUwa6aETk5xhuiKjXndzzKfb+czkAQBKdAIDjn29A2bZ3MOOP6xCRNXEgi0dEfo7NUkTUq+wtTfjhufsgSaIcbID2kOO02/D9P5e7bSci6m0MN0TUqyp2bobTbgU8LVsniWirN6L6wDf9XzAiGjYYboioV1mqyiAolN4PEAS0VJX3X4GIaNhhuCGiXqUJjYAkit4PkCRo9BH9VyAiGnYYboioVyXO/IXP/SpdEAwT5/RLWYhoeGK4IaJeFRAZi5FX/Lb9C0H4eYfQ/uNm7JI/QaUNGICSEdFwwaHgRNTrshb+BgFR8Sj44EU0VxQBAMLTxyLr0ttgmHD2AJeOiPwdww0R9YmkWZcg8ayLYbeYISiUUAcGD3SRiGiYYLghoj4jCAI0wfqBLgYRDTPsc0NERER+heGGiIiI/ArDDREREfkVhhsiIiLyKww3RERE5FcYboiIiMivMNwQERGRX+E8N71AdDpQc3AnWmtPQhceg5jxs6BQaQa6WD3WZqpF9f++hmi3ISJzAkKTswa6SD0mSRIaCv8Hc1n+T2sYnQN1YEiPrmFvaULV/h1wtDYjNCkL4ZkTIHRcRqAbGksOo7H4MJRaHQzjZ0MTEt6j89tMdSj8v3/BaqpFWMY4pF5wLRSKnv0uYi4/hoaC/RBUGsSMnwWdPqpH5xMRDVWCJElST07YsWMHHn30UezduxeVlZV47733sHDhQq/Hb9u2Deeee26n7ZWVlYiNjZW/fvbZZ/Hoo4/CaDRi/PjxePrppzFt2rRulclsNkOv18NkMiE0NLQnb+eM1R7ejb3P3gNrY428TR0chom3PITYyef1a1lOlyQ6cfi/j6Lkk/9AEp3y9sjR0zDlt09Aq48cwNJ1n6WqDN/9406Yy47K2xRqDUZe/juk/+LGLgOKJEko+mg9jr71FES7Vd4empyNKXc+ieC4EV2WobW+Ct8/dScaCv4nbxOUKmRechOyL/9tt0LS3mfvRcU3H7ptE5QqTLrjMSTk5nV5vtVcj71P/wG1h7/9+XyFEiMuuAY5194LQaHs8hpERP2hrz6/e9wsZbFYMH78eDz77LM9Oi8/Px+VlZXyKyYmRt735ptvYvny5Vi1ahX27duH8ePHIy8vD9XV1T0tXr8ylx/Dt3+/GVZTndt2e7MJ3/3jt6jL3zdAJeuZHzf8A8Ufv+oWbACg/uhe7FqzrNP2wcje0oRv/nodmk4UuG0X7Tb8+MZjKN36ZpfXKP1iI3787yNuwQYAmk4U4psHroe9pcnn+U6bFTsfuB6NRYfctktOB4699zwKPnixyzIcfG1Np2Djusbep34PU+lRD2d1OE504tuHl6HuyHedtpds+Td+fOPxLstARDTU9TjcLFiwAA8++CB+9atf9ei8mJgYxMbGyq+OVexPPPEEbrrpJtxwww0YPXo01q5di8DAQKxbt66nxetXhZvWtX/wS+IpeyQAAgo+eGEgitUjtmYTire85nGfJDphLjuKqh929HOpeq78qw/Q1ljjNYjlv/MsRKfD6/mS6ET+O8943Wc11aJ8+3s+y3ByzyewVJV5LUPhh/+Cw9rq9XxRFHH88zd8fAcJB1/9m88yVP/vK5iOH/FSBgnFn/wHtuZGn9cgIhrq+q1D8YQJExAXF4d58+bhm2++kbfbbDbs3bsXc+fO/blQCgXmzp2LXbt2ebyW1WqF2Wx2ew0E494vvH6QSaIT1f/7GpJ4avAZXGp/3A3JYfe6X1CqULV/ez+W6PRU7fuyPVN6YTXVoqn8mNf95vICt6bFTiQJxn1f+ixD9Q/bAcH7fylHqwUNBfu97m8s/J/PfwsAaCw64HN/1Q/bISi9NztJDjtqD+/2eQ0ioqGuz8NNXFwc1q5di3feeQfvvPMOkpKSMGfOHOzb195kU1tbC6fTCYPB4HaewWCA0Wj0eM01a9ZAr9fLr6SkpL5+Gx512VwjiZA61eoMLl2/BwmSjxqPwaK9VsZ39zHR6f29Sj72/XyM7/vQfn3fZfD1fUS772DTfoHuXL+LvkVD4N+TiOhM9Hm4yc7Oxi233ILJkydj5syZWLduHWbOnIl//OMfp33NlStXwmQyya/y8vJeLHH3RY2a5r1zpqBAeMZ4KJSDe0BaRNYkn7UNkuhE5Mgp/Vii0xM1eprP96EKCEJoUqbX/SGJGVAFBHv/BoICkaNzfZYhctQUn9lGUKkRlp7jdX9E9gSf7wEAguPTuijDVN/hRRAQkT3J5zWIiIa6AZnnZtq0aSgsLAQAREVFQalUoqqqyu2Yqqoqt9FUHWm1WoSGhrq9BkLGL2703uwkici45Kb+LdBpCIgwIGHmRR4/VAWFErrwGMRPXzAAJeuZlPOuhFKr8xIOBKTNvx5Kjc7r+UqNFmkLFsNjrYeggFKjxYjzr/RZhqTZv4Q6WO858AoCUs67AprgMK/nK1SaLkfYjf713T73x+XmQRcR67kMCgUSZlyIgMg4n9cgIhrqBiTc7N+/H3Fx7T9gNRoNJk+ejK1bt8r7RVHE1q1bMWPGjIEoXrdFjpqKCTc/CEGpAgThpz8VEBQKjLn2PsRNOX+gi9gt45f+BTHjzgLQHmiEn2qbdOHRmPHHdVBqtANZvG7RhUVj+n3/gjqwvfZFUKrkD/ikc36FrEtv6/Ia2ZfeiuQ5l7af3+E+qAODMf2+F6ELj/F1OtSBIZj5x5flOW06liFu6jyMuea+Lssw5a6noE8d47l8l/9W/nfyRqnWYOYf10EXYfi5DD/1wYnOmYHxy1Z3WQYioqGux/PcNDc3y7UuEydOxBNPPIFzzz0XERERSE5OxsqVK1FRUYHXXmsfgfPkk08iNTUVY8aMQVtbG1566SU8/fTT+PTTT3H++e0f/m+++SYWL16MF154AdOmTcOTTz6Jt956C0ePHu3UF8eTgZznBmifV+TENx+itaYCunADEmdd3OUH4WAjSRIaiw7A+P0XcNqtiMiaiNjJ50GhUg900XrEYW3FyW+3wFx2FKqAYMRPn4/QRO/NUZ40nShExbcf/zSJXzbiZyyAShvQ7fOddhsq93yKxuJDUGp1iJs6D2FeAos31Qd3oeCDF2BvMSMkIR1jFt0DXUT3nynRYYdx35eoP/YDFCo1Yiefh/CM8T2ejJCIqC/11ed3j8ONt0n5Fi9ejPXr12PJkiU4fvw4tm3bBgB45JFH8OKLL6KiogKBgYEYN24c7r///k7XeOaZZ+RJ/CZMmIB//vOfyM313cfBZaDDDREREfXcoAk3gxHDDRER0dAzaGYoJiIiIhrMGG6IiIjIrzDcEBERkV9huCEiIiK/wnBDREREfoXhhoiIiPwKww0RERH5lcG9qiMNK611lSj66FVU7PoITmsrwtPHIW3B9TBMPKffytBmqkXxx6/hxNcfwtHaDH3KSKTOvw5xU+d1e3bfY+89j6KPX4W92QQICoSmZGP8jasQnjG+W+fbmhtRvOU/KP/qfdibTQhJSEPqBdci4axfdLsMtT/uQdHmV1B/bB8EpRrx0+Yh7cIlCI5N6db5RERDGSfxo0GhqaIIX//lGjhamyGJTgDt6ztJohMjr7wTWQt/0+dlaKmpwFerFsFmrpfLAIUCEEWkX3QDxlxzb5fX2PXwTag58LXHfdP+8GyXC2O2mWrx9apfo6W2AnAtyiooAElE8jmXYfzND3QZcI5/vgEH1q2W71/7JZRQqDWY+adXEZ4+tsv3QUTUHziJH/m1/S/+2S3YAJD/fvStp2AuP9bnZTi4/kH3YAPIAaNo8yuoO7rX5/nGvV94DTYAsPeZe7osw4+vP4bW2pM/BxsAkNr/Xrb9HVTt2+bz/NY6Iw688sBPp7nfS6fdin3P3gs/+H2GiMgnhhsacM0nS9BQ8IN7qOhAUChR9uXbfVqGtoZqVO3f7rMMpV9u9HmN/Hef87nfaW2B0Uc4cbRaULFzs88yHN/6ps/vUb7jPcBbxY4owmI8joaC/T6vQUQ01DHc0IBrqanwuV8SnV0ec6Za64yAjxoNSXTCYizzeY22huouv4+p5JD38xtrIDkdvstQVerz+i01JyB4TTc/HVN9wnchiYiGOIYbGnDasCif+wWFEtqw6AEvQ0CEwecxmuCwLr9PUNwI7+eHhLf3r/FeCARExPq8fnfukza8b+8lEdFAY7ihAReanI2QpEyvH+yS6ETS2Qv7tAyBUfGIHDkFgsJHGc75lc9rpF+4xOd+QaVG/PQLve7XBOsRO/lcCAql5wMkEclzLvP5PZJm/9JrsxYEAbpwA6JGTfV5DSKioY7hhgacIAgYv3Q1FCrVKR/s7c0rKXOvRkTmhD4vx9glf4ZSE+AxXMTPWICY8bN9np8859L2kObt+tf/Pyi8hCeXMdfcC3VgSOcyCAJixs9G/PT5Ps8PjktF1q9ulc+RT1coIQgKTLj5Ae/hiYjIT3AoOA0aptKjOPbuczDu/QKS6ERQbArSL7oBKedd2e35Xc5U88kS5L/7HE7u3gLJ6UBAVDzSFlyPtLxruxUKRFHE/rUrULHrY7n/jDY8GjnXrEDCTO+1Nh211FQg/93nUPHNJogOG7ThMUi74BqkX7QECpWmy/MlScKJbz5E4Ycvo6n8mByMsn51a7+ERCKi7uqrz2+GGxp0RKcDktMBhVrbb6HmVO1Dp21QanSnXQZbcyMUGh1UGt2AlcFpa2uf40alPq3ziYj6Ul99fnOGYhp0FEoVoBzYR1NQKKHSBpzRNbrTwbivy6A8zWBFRDSUsc8NERER+RWGGyIiIvIrDDdERETkVxhuiIiIyK8w3BAREZFfYbghIiIiv8JwQ0RERH6F89wMEjWHv0Xp529CdDqQMH1Bt2ez7U0ttSdR9cN2iA4bIjInICx9XL9PotfWUA3jvi/htLYiLC0HEdmTe1QG0eFA8Sevoe7oXqgDQ5B5yU0ISUjvURnKd36Ew68+CKfNipCEdMz443qoAwO7fb4kSajP34fG4oNQagMQO+lc6MJjelQGIiI6fZyheIDZms3Y/sdfobX2pNt2VWAIZv/1TYTEp/Z5GUSHHQdffQilX7wFSGhfk0gSEZY+DtOWP90vH8ySKOLHNx5H8cfrIYmSXIaQpCxMW/4MggxJXV7DuG8bvvvHb+VlD1wiRk7FzD+t73JdJ7vdjk+WTYFot3XalzTncky8+YEuy2CpPoHvnrgD5rL89oVAJQmCQkBq3nUYc829XhfmJCIajhobGxEeHs7lFzwZyuHm87vmoaX6hMd9Sm0gFrz8XZcfymfq4GtrUPLJv4FTHgVBoURQ3AjMefj99lmD+1D+u88i/+1nOm0XFErowmNw7mObfc7Wa6kqx9bleZ3eg0vslLmYtvxpn2X4aOlUOFqbve6f8vt/In7qPK/7nbY2fHH3RWirr/K4MnfWpbdh5OW/9VkGIiJ/ZbVaUVVVBaPRCKPRiKqqKpSWluKhhx7i8gv+pO7oXq/BBgCc1haUbPk30i9c3GdlsJobcPyz1z2GAkl0ormiCFX7vkScjw/1M+Voa0Hhh+s87pNEJ1rrKnFy10dInnOZ12sc+vcar8EGAIx7t8LR1gKVznPzUktdlc9gAwA/PLcC8a94vw8VOz/qVAPXUdHmV5Dxixuh0gX5/D5EREOZJElwOp1QqdojRlVVFTZs2ICGhoZOxzqdnX8R7A0MNwOo9MuNXR5TsWtzn4abuqPfdWrG6UhQqlC9/6s+DTeNRQfhtLZ4P0BQoGr/Vz7DTX3+Pt/fRJJQ+d3nSJp9icfdP/73kS7L6bOMAKoPfP1TU5To5fxWNBT8D9FjZ3b5vYiIhgK73Y6amhq5Jsb15+TJkzFvXvvnRkhIiBxsQkNDERsbC4PBgNjYWAQFBeHhhx/u9XIx3AwgSfT8Ieh2TF+3GnZVBkmC5OXDurd0fX3Ja2BwO6arIzw0FbmIoveA122S1GU5/KAVmIiGIUmS4HA4oFarAQCtra1Yt24d6urqIHr4HKmqqpL/HhgYiBtuuAHR0dEIPGVwhtls7pPyMtwMoKTZF6Pimw99HhM76dw+LUNE9iQICoXXoCWJTkSNmd6nZQhLy4FCrYVot3o+QAKixuT6vIY+NQe1h3b6PCZ28vle942+6g8w7vnU5/kKtdbn/sjR03By9xYf52sQnj7W5zWIiAaa0+l0q41x1cikpKTgqquuAgDodDo0NTVBFEUEBga61cbExsYiKirK7ZopKSn9+h4YbgZQzLjZ0IZFw9pY43G/QqVB5iU392kZdOExSJq9EGU73u9UOyIolNBFGBA37YI+LYM6MASpF1yDoo9e8dCpWQF1cBgSZ/3S5zVyrluJbfdd7HV/1Jjp0AR776wWHJfsO2AByFnyZ59lSJp1CfLfeRb25sbOtUSCgBHzfg110NDq8E5E/s1ms0Gj0QBor5156aWXUFlZ2WVtjCAIuPbaa6HX6xEcHNzv04Z0heFmgJ3z4Nv4csUvYW9udNuuUGtw1qr/QqHq+3+isTf8GfbWZlTu+RSCQgkIAiSnA4ExiZh+34tQqjV9XoZRV90FW1M9yne83z5cWlBAcjqgC49B7r0vQB0Y7PP80KQMTLjlb9j/4v/rFJBCkjIx/b5/dVmGvOd34uObpnpsAouZeA5GnOu9zw8AqAKCMPNPr2D3329Ba10lBKUKkERIoojEWZdg9NXLuywDEVFfcDgcqK2tdesXU1VVheDgYNx6660A2gOLJEkQRRE6nU6uiXH9GR0d7XbNxMTEgXgr3cKh4INE+VcfoGzbu5BEJ2InnYu0i27o8yHgpzKV5aNq7xdw2q2IyJyImPGz+31eluaTJTi551M4ba0IS82BYdKcHg1Dd7RZcOStf6Kx6CBUgUHI/MVNiBozrUdlOLLxaRRtfgWS0wFtWBRmrfoPAqPiu32+6HSgat82NJYcglITgLip8xCSkNajMhARnQ5JktDa2urWt+XNN99Efn6+x9oYlUqFlStXQqlUAgCMRiMCAgIQGhraL7UxffX5zXBDREQ0BLlGKrlqYVwvu92OP/7xj3I4efvtt3Ho0CEEBATAYDC4vWJiYuROwgOhrz6/e9zmsWPHDjz66KPYu3cvKisr8d5772HhwoVej3/33Xfx/PPPY//+/bBarRgzZgz+8pe/IC8vTz7mL3/5C1avXu12XnZ2No4ePdrT4hEREfkVSZJgMpmg1+vlwLJp0ybs3bvX4whMQRBgMpkQFhYGADjvvPMwb968fquNGQx6HG4sFgvGjx+PG2+8EZdeemmXx+/YsQPz5s3D3/72N4SFheGVV17BxRdfjN27d2PixInycWPGjMHnn3/+c8H6oa8JERHRYNLW1ibXwFRXV8t/Wq1W/OEPf0BISAiA9uHVkiS5jVRy1cRER0e71cZEREQM1NsZMD1OEAsWLMCCBQu6ffyTTz7p9vXf/vY3fPDBB/jwww/dwo1KpUJsbGy3rmm1WmG1/jyqpa/GyRMREfUFp9OJuro6hIeHy0Fk27Zt2LZtm8fjlUol6uvr5XAzbdo0TJ06dVCOVBoM+r16RBRFNDU1dUqSBQUFiI+Ph06nw4wZM7BmzRokJyd7vMaaNWs6NWMRERENNpIkwWw2d6qJqa2thdPpxJIlSzBixAgAkJuR9Hq9W02MwWBAZGSk3OkXAIKDfY8gHe76Pdw89thjaG5uxpVXXilvy83Nxfr165GdnY3KykqsXr0as2fPxqFDh+SU2tHKlSuxfPnPw2rNZjOSkrpeNZqIiKivtLa2orq6GpGRkXL42LdvHz780PNkrVqtFhaLRf569OjRGDlyJHQ6Xb+U15/1a7h5/fXXsXr1anzwwQeIiYmRt3ds5ho3bhxyc3ORkpKCt956C0uXLu10Ha1WC63W92yxREREfcHhcKCmpgbV1dVutTGuLhKXXHIJJk2aBACIjo6GQqFAVFSUXAvjqpHp2EEYgDyZHp25fgs3GzZswLJly7Bx40bMnTvX57FhYWHIyspCYWFhP5WOiIjInSiKaGhoQFVVFSIjI2EwGAAApaWl+Pe//+3xHL1e7zaCKTExEf/v//0/tyYl6nv9Em7eeOMN3HjjjdiwYQMuuuiiLo9vbm5GUVERrrvuun4oHRERDXc2mw2lpaVybUx1dTVqamrgcLQvqjtr1iw53BgMBnnOmJiYGLfXqU1K/T0ZK7Xrcbhpbm52q1EpKSnB/v37ERERgeTkZKxcuRIVFRV47bXXALQ3RS1evBhPPfUUcnNzYTQaAQABAQHQ6/UAgLvvvhsXX3wxUlJScPLkSaxatQpKpRKLFi3qjfdI/UASRZRtfwfFW/6D5pPFUAeGIunshUj/xQ3Q6aO6vgAAS1U5Cj98CRXffgynrQ1hqWOQfuESxOfmdX3yIHJyz6co2rweppLDUGi0SMidj4xLliHI4LmDPBH1H4vFIoeX8PBwZGVlAQBaWlrw3//+t9PxarUa0dHRbh14g4KCcO+993KU0iDW4xmKt23bhnPP7bxS9eLFi7F+/XosWbIEx48fl4ezzZkzB9u3b/d6PABcffXV2LFjB+rq6hAdHY1Zs2bhoYceQnp6erfKxBmKB5Ykitj3/H2o+GYTIAjy2k6CQgmtPgqz/7oBAZG+h/mbyvLxzepr4bS2/rzopKAAJBGZC2/BqCvv6uN30TuObvwnjr33PKBQAD9NdS4olFBqdDjr/n9DP2LUAJeQaPhwOBzYv3+/W21MS0uLvH/06NHy4BZJkvCvf/0L4eHhbvPFhIeHs/alD3H5BR8YbgZW5Xef47t//NbjPkGhRNy0CzDld0/4vMaOP10B0/EfIXlY+wQAzvnbu4M+GJjK8rF9xULPOxUK6JNH4py/vdOvZSLyd1arFTU1NXIH3+DgYJx11lkA2vvMPPTQQ3A6nfLxgiAgLCwMBoMBqampyM3NHaiiEwbR8gtEpyr98m0ICoXHYCKJTlTu+RR2ixnqIM8PbtOJQjQWH/J6fUGhRNm2dzB2yZ96rcx9oXzbOxAUyp9rnjoSRZiO/whz+TGEJmX1f+GI/MjWrVthNBpRXV0Nk8nkti8uLk4ONwqFApMmTYJarZb7xJw6ey/5J4YbOmMtNSe81rgA7QGnrbHWa7hprav0eX1JdHZ5zGDQUlfpOdh00FpbyXBD5IPNZkNtba1cE1NTUwOVSuU2N9qRI0dQW1srfx0cHCwHl/j4eLfrdWcQC/kfhhs6YwGRcWiuLJH7mJxKUCig1Ud6PV8XbvB5fUGhhC7C9zGDQUC4wXvNzU+Gwvsg6g8Oh8NtDcEPP/wQxcXFaGxs7LQYpFarhSRJcgfemTNnQhRFREdHIyYmBgEBAf1adhr8GG7ojKWcdwVqDnztcZ+gUCJ28nnQBOu9nh+anIXQlFEwl+UDkuemreRzLuu18vaVpHN+hZJPO4+2AAAoFAhNzERocnb/FopogFmtVtTW1sq1MK6X3W7HPffcIx9nNpvR0NAAoH00kiu4REdHIzo62u2argnyiLxhuKEzFjdlLuKmXYDKPZ/9tOXn0VLq4DCMufa+Lq8x4aYH8M0D10G02zqNlkq7cAnC0sb0Uel7T1jqGKT/4kYUbVrXadSYQqXB+Jse4NBR8lutra2oq6tDYmKivO2dd97BwYMHvZ5jsVgQFBQEADj77LNx1llnITo6Wt5GdLo4Wop6heh04PjnG1Cy5d+wVJVBpQtC0tkLkXHxsi6Hgbs0VRSj4IMXcHL3JxDtNoQmZyP9oiVInHXJkAkFkiSh4ptNKProFZiOH4VCrUZ87nxk/vJmhCR0b2oDosHMYrGgqqpK7hfj+rO5uRkAsGLFCnkiu48//hi7d+9GSEiIvPyAqyYmOjoagYGBA/lWaBDgUHAfGG4GF0kUIZzBvBCSJAGSdEbXGAwkUQQEYcgEMyIXSZLQ2Ngoh5cpU6bI6x5t2rQJ33//vcfz9Ho9rrvuOkRFtU/cabFYoFAo2CeGvOJQcBoyzjSUCILQ3qwzxA31cEbDx8mTJ1FQUCCHmdraWnnZAQAYMWKEPAopJiYGERERcu1LVFSU/OepCxqzeYkGCsMNEZGfa21tlUOL6zVv3jy5huX48eP48ssv3c5RKpWIjIxEdHS026KP06ZNw7Rp0/q1/EQ9xXBDROQHJEmCJEnyUgGFhYX46quvUFtbC4vF0un4cePGyeEmKSkJEyZMkGtgoqKiuOwADWkMN0REQ4hrkru6ujq3mpi6ujpcfvnlGDlyJADAbrejtLRUPi80NFQOLqdOdpeUlISkpKR+fy9EfYXhhohokJEkCSaTCbW1tYiMjER4eDgAID8/H2+88YbX82pqauRwk5SUhEsvvRRRUVGIjIzs1B+GaKC1tbWhuLi4T67NcENENIBaWlpQUFCAuro6uTamvr4edrsdAHDBBRdg5syZAICwsDAA7R11XbUwkZGR8t9d+4H2JQnGjRvX32+HyCNJklBbW4sTJ06gvLwcJ06cQE1NDdra2vrk+zHcEBH1IafTifr6ejm81NXVISMjA6NHjwYAmEwmvPfee53OUyqViIiIcFuiIDo6Gvfddx+HVtOgZ7VaceLECbcw4ynIuGolexvDDRHRGZIkCXa7XZ4LxmQyYdOmTaitrfW4VpJSqZTDTWRkJEaMGCHXwrhqYsLCwjp16OWcMTQYSZKEuro6OcSUl5ejpqam03OvVqsRHx8v9/FKTEyE0+nEffd1PYt9TzHc+AmnzYrK7z+HxVgKrT4S8bl50ASH9ega1Qe+QvEn/4VotyFm/CykLVjC0RJEP5EkCc3NzW61MK6/19fXY9KkSbjwwgsBtC/0WFBQIJ+r0Wjk0BIZGYmUlBS3fUuWLOnvt0N02qxWKyoqKuQwc+LECbS2tnY6Ljw8HImJiXKQMRgMbtMKAO2T+PUFzlDsB6oPfoO9//wD7BYTBKUKkuiEoFRhzK/vQdr867o839bSjO0rf4XWmhNu2xVqDWb88RVEZnOROhoeJElCS0uLHFgCAwORlZUFoL1vzCOPPOL13MzMTFxzzTXy1/v370dYWBgiIyMRHBzMmappSDq1VubEiROorq7uVCujUqmQkJDgFmaCg4O7vD5nKCaPmiqKsefR2yA62zsfSs72WUUlhx2HXvsbdGHRiJ8+3+c1vl51dadgAwCi3YadDy7Ggn/thkrHNWDI/zidTmzfvl0OM/X19bBarfL+zMxMOdwEBgYiMDAQWq0WkZGRiIiIkJuRIiMjodfr3a49YcKE/nwrRL2iY18ZX7UyYWFhcohJSkryWCszkBhuhrjiLa+1r6LtqQJOEJD/3vOIy83z+lujubwQzRVFXq8vOR048tZTGHv9yt4qMlGfkyQJTU1NcmDp+IqOjsZll10GoL0Py+7du90CjSAI0Ov1iIiIcFvhGgDuvvtuNtWS3+huX5mOtTKuMNOdWpmBxHAzxFXv39EebjyRJDSVH4PdYvLa/6Zs+ztdf4//fQWA4YYGF6fTicbGRjQ0NECSJGRmZsr7HnvsMY+z8rrOcxEEAbNmzYJKpUJERAQiIiIQHh7uNkKpIwYbGsr8pVamOxhuiGhI2L17N6qrq1FfX4+GhgaYTCb5N8yYmBi3cBMSEoLW1laEhYXJocUVXCIjI92uO3v27H59H0T9wdu8Mv5QK9MdDDdDXMyEs1H25duea28EAaFJWT5HTSWfcxmKP1rv+3uM5w9/6huiKMJkMqGhoaHTS61W44YbbpCP3bdvH6qqqtzOV6vVCA8PR0xMjNv26667DgEBAaxpoWGjra2tU62Mt3llOgaZoVgr0x0MN0Nc2vzrUb79PUiS2LnfjSQh61e3+jw/NCkDwQkZaK4o9LhfUKow6so7e6u4NMxIkgSLxSI3H9lsNkyePFne/+KLL8JoNHo8V6PRQJIkub/YxIkT0draivDwcLkWxtsopKCgoL55Q0SDgCRJqKmp6VQrcyrXvDI9HcHkDxhuhriQhDTk3vM8vn96OezNJghKJSSnCEGlwphr7kV8bl6X1zj7gQ3YtmIhWqo7DwWf+f/Wc6QUeSVJEmw2m9u6RV9//TXKysrQ0NCAxsZGeRkBoD2wTJo0SQ4ker0etbW1CAsLk5uQwsPD5VdH06dP7583RTTItLa2dqqV6dgJ3sXVCd4VZmJiYvyyVqY7OM+Nn3DabTB+/zksVWXQhET8NImfvusTO6g+8A1KPv0vnDYrDBPORur861itTwDaF2R0zbZ76gsAVqxYIQeWN954A/n5+fK5giAgJCREDiy/+MUv5A67VqsVGo2Gc8AQ/UQURVRXV7stXVBXV9fpOI1GI8/26wo0Q7HGkvPckE9KtQYJMy48o2vEjDsLMePO6qUS0VDgmnW3sbERJpNJ/rO5uRlXXnmlHDo+//xzt8Byqra2NnlZgEmTJiErK0uujdHr9V5HH3GlahruLBaLW41MRUUFbDZbp+MiIyPdmpdiYmL4y6cPDDdEfsxms8FkMsFsNsNkMmHixIlyYPnwww+xf/9+t6HRHXUMLLGxsbBYLG6BxfX3sLAwqNVq+bzs7Oy+f2NEQ5DT6URVVZVbmKmvr+90nFardZvtNyEhAYGB7B7QEww3REOUw+FAU1MTwsLC5MDy/fff49ixY3KYOXUOi1GjRsmBRalUwul0QqFQIDQ0FHq9Xg4ter3e7bfCc889F+eee27/vTkiP9DU1OTWvFRZWenWB80lOjrara9MVFQUa2XOEMMN0SBXWlqK8vJymM1mt1dzczMA4L777pMDS3V1NY4dO+Z2vlarlYOL3W6Xj501axbOOusshISE8Acp0RlyOByorKx0q5UxmUydjtPpdHKQSUxMREJCAld67wMMN0QDoKGhAbW1tWhqaoLZbJb/dP39jjvukKuhDx8+jD179ni8jkqlQnNzs/zDccyYMYiJiZHDTGhoKHQ6ncdzh2vne6IzJUkSTCaTW5CprKzs1MQrCAIMBoNbmImMjGQH+n7gV+GmqqoKISEhw/LBkSQJ1dXVMJlMCAoKQmxs7JAcAmi1WlFVVQWbzYbIyMhOw4EHM6vVKnfGbWpq6vRatGiRHFh27drlNbAA7dXZrmOTk5NhtVoRGhrq9tLr9QgICHB73lNSUpCSktK3b5RomLHZbHKtjGteGVfNaUdBQUGdamU0Gs0AlJj8KtxkZWUhMzMTt956K5YsWTKkPhhPV1NTE/7zn//gueeew6FDh+Tt8fHxuPnmm3HTTTchPj5+AEvYPYcPH8bzzz+P1157DU1NTfL2OXPm4LbbbsPChQvdOq32F6fTiebmZjQ3N8Nisch/b2pqQnNzMy6++GI5hHzxxRfYvXu312t1DCxRUVGIjY1FSEgIQkJC5MDi+nvHJQJycnKQk5PTt2+UiAD8vJhkRUWFXCtTVVUFURTdjlMoFIiNjXXrK9Ox/xsNLL+a5+Y///kPNm/ejLfffhsBAQHYuHEjLrjggoEuXp/ZuXMnFi5ciLq6Ovzyl7/EokWLEB0djebmZmzatAn/+c9/YLPZ8OKLL2LJkiUDXVyPRFHEihUr8Oijj8JgMGDZsmU4++yzoVarUVpainXr1uGrr77CmDFjsHnz5l6plXA4HHJQsVgsbn9vbm7GhRdeKIeQLVu24Ntvv/V6rd/85jeIjY0F0D553TfffIOQkBAEBwfLwcX1Sk1NZds60SDT1tbmFmS8LSYZEhIij1xKSkpCXFzcgPzC5W/6ap4bvwo3rptTVVWFG2+8EZ9++ik++ugjzJs3r1/KIYkihDPomClJEiBJ3brG7t27ce6552LKlCn473//i6SkJACA6HBA8dOcIiaTCXfffTdeeuklvPzyy7jxxhtPu2x9QZIk3HnnnXjmmWfw97//HXfeeac85X7H+7Bv3z5cfvnlcDgc+Pbbbz3WRFksFpjNZlgsFrS0tLj9abFYcMkll8gTXH3yySfYtWuX13KdGli++OILBAcHy6+goCA5wIwePVqezrzjUgFENPiIoigvW+B6eVq2QKVSIT4+Xg4yiYmJ7KPWRxhufHDdnHdunI4xF16L9ItuAFQa/PKXv8TOnTtRVlaGkJCQPvnejrYWFG1+Bcc/3wCrqRbq4DCknHcFMi9eBnVQ9/6h6gv2o+D9F1D9v68gSSIisiYi85KbYJg4x+PxNpsNaWlpSElJweeffw6l5MTep3+PmgM7Aam96lQ/YjQm3vp3hCSm47bbbsNLL72Eo0ePIj09vZfe+Zn74IMPsHDhQjz//PP4zW9+A/OJQhx7/wUY93wK0WGDM3IEgiblIXTUdJSXl+PWW29FYmIili9fjtbWVixatEj+z/Dpp59i586dXr/XqYHlyy+/RFBQkBxWXK/g4GDk5OTIz4trqDRDC9HQ09zc7FYr422CPNdikq4g46+LSQ5Ggybc7NixA48++ij27t2LyspKvPfee1i4cKHPc7Zt24bly5fj8OHDSEpKwp/+9KdOzSTPPvssHn30URiNRowfPx5PP/00pk2b1q0yuW7OG5dnIlCjhn7EKJz159dgrK3HiBEj8PTTT+PWW30vIHk6HNZW7HxwMRqLD8uhAgAEhQJBsSMw6y+vd7kEgnHvl/juH3cAEH5e2VuhAEQROYv/H9Lyru10zltvvYWrrroKBw8exMiMVHz22/Ngt5g7X1yhwDkPvQNNTAoSEhKwdOlSPProo2fylrvkcDhgtVrR1tYmv1JSUuQZao8cOYKioiK0tbVh1apVsFqt+N3vfof6ihIUfLIBF2eFIfCnnmA/GC04WtOC8IwJiBk/C//73//w/vvv4/bbb0dUVBRuueUWxMXFAWjvoLtz504EBgbKQcX198DAQIwcOVKuYRFFEYIgMLAQ+RGHwwGj0ehWK+NaHqQjrVbrtmxBQkLCkFy2wF8MmuUXLBYLxo8fjxtvvBGXXnppl8eXlJTgoosuwm9+8xv897//xdatW7Fs2TLExcUhL699Ucc333wTy5cvx9q1a5Gbm4snn3wSeXl5yM/PR0xMTM8KKIkwHT+Ckk/+g8xf3oxLLrkEzz33HH7zm9/0+odZyaf/RWPxoU6rcUuiCIvxOAr+70WM+fU9Xs8XHTbsf+GPkEQJQIfOaj91XDv874cRn5sHXVi023nPPfcczj77bOTk5GDfc/d6DjY/Xef7p36P85/4GDfeeCPWrVuHv/71r279PiRJgsPhkOc/cd2j6upq1NXVwWazwWq1yn+6/r5gwQJ56vwvv/wSe/fuRVtbGxwOR6di3HXXXQgLCwMAnDhxAt9//z1qa2vx448/4le/+hXq6+tx/JuPIYoOWO0OBP4UhPQaJQxBGmhrjmBk4q8wffot+PLLL9HY2Ig777zTrcP4jBkzMGPGDK/3uiPO6UI0tPVkKHbHCfISExM5Qd4w0eNws2DBAixYsKDbx69duxapqal4/PHHAbTPkPr111/jH//4hxxunnjiCdx000244YYb5HM2b96MdevWYcWKFZ2u6fqQdTGb2z/c/2dsQZBagQC1AoFfvIXMX96MSy+9FNdddx327dsnr3GjVCrll1qtRkREhHyttrY2AO0fgK7mCG/NEqVfbOwUbFwkUUTZl29j9KK73c6VJEl+VXz/JSymBkiQoFH+/J+txe6EQ5QgQsS+D/+D5HOvgNPphNPphMPhwK5du/DII48AAPZu3YzGplaIkgSnhPbzRAkOSYJTBKaJJbC1NOPSSy/F448/joceeggxMTGw2Wyw2+2w2WxwVd51nAxu9+7d2Lt3r9d/1zlz5sjhxm63dxoWqdFoEBAQAJ1O5zbKIC0tDSqVCl988QUA4P7774e6tRH7DvwXmrgIaFU/36u0CB3SInQQFEqkKOswbv7tWLhwIY4ePYrMzEyvZSMi/2K1WnHy5Em3MGOxWDodFxgY2GkoNtcvG576fCj4rl27MHfuXLdteXl5uOuuuwC09x/Zu3cvVq5cKe9XKBSYO3eu106fa9aswerVqzttL6hrgVqpgF6nQnZjeycxvb69Wej111/32O8mPDwcd955p/z1q6++isrKSo/fV6/X4/e//7389UffH0WNucXjsWqFgIWjAMlph6DS4D//+Q+KiorQsRWwoeggqn+sg0IArsqJkrd/V9GMk002QFAg/N1NiCn6eZZLp9MJm80mv6/CajPKGjv37HeZHB+E1rqTcs3JyZMnvS5iaLPZ5HDjWqRNq9VCq9VCo9HIf+p0OrcfGLm5uRg3bpy8XavVev3NKD09Henp6Th8+DDUajUmTJiA6v99Bb3O+6MoiU601VcBaP836DhUnIj8iyRJbp1+KyoqUF1djVN7UCiVSreh2AkJCQgPD2dzMwHoh3BjNBphMBjcthkMBpjNZrS2tqKhoQFOp9PjMUePHvV4zZUrV2L58uXy12azGUlJSciKDIRKKSBApUBAZHtfjIaGBgA/1xg4HA65FsTpdHZajOzUuQx87VMEhMLR2AKgc+2NAAGakHAoVBr53FP/c6oDgwFIkCT3/4xqpQC1UgGFIEAfFY2wsDAolUqoVCooFApoNBp5sTWDPgiQRCgVApSCAKUAKBQCVIqf/i4ICIpOQH3pDwCAyy+/HDk5OdBoNNBoNFCr1fKfHQPJzJkzMXPmTK/3oiPXbLg9ERoaKtf4uP6tvBEUSgREtY+Qamho4KgFIj/ScVXsiooKVFRUuNXMu4SFhckhJjExEXFxcV5/USMakk+Gq3bgVONiAxGoVgKCgJTzrwIAbNy4ERMnTsTtt9/erWvfcsstEEVRfkmS5DGYAMB1N9+Gw28+6blpSqFAyvlXyl9efvnlbh1ZBUEARCe++H0BbE0NbqfOTGr/8BaUKlzw+HPQhka47d+4cSPefvttLF++HOdecjnKt73j9f2EJGZCpQvCxo0bERUVhfPPP39QVNOeddZZAIC3334bS5YsQVj6WJhKDkPyEC4l0Ynkcy5FS0sLNm3ahGXLlvV3cYmoF5za6beiokL+BbQjjUaD+Ph4t1qZvhrxSv6pz8NNbGwsqqqq3LZVVVUhNDQUAQEBct8XT8e4hu72iCAgImsiUuf9GsePH8fmzZvx4osvdvt0V1+b7sj55VI0/7gTdfl73QOOoEBochYyL75J3uRtufqpv30Uux/5DSBJ8mgpQaGEJIoYd+OqTsEGAG677TZcdtll+OGHHzB2yZ9QtW8bbOa6TscJShWm3PUULBYL1q9fj9tuu21QBBugvXkqLy8Pzz77LBYvXowJNz2Ir1dfA6e1tdOosayFv4F+xCisW7cOjY2NuOWWWwa28ETUJUmS0NDQ4DYU22g0euz0GxUV5RZkYmJi2OmXzsgZzXMjCEKXQ8Hvu+8+fPTRRzh48KC87de//jXq6+uxZcsWAO19NqZNm4ann34aQHsTTnJyMu644w6PHYpP5RpK9sGt52H0hdcg9YJr4JCA+fPn4+DBgygtLe2zoX5OmxUln72O0q1vorW2EtqwKKScdwXS5l8Hla5739N0/AgKN62Dcd8XkEQRUaOmIuMXSxE1Jtfj8Q6HA5mZmYiIiMD27duhUymw/4X/h8q9WyE57ICgQETWREz8zRoERCdgyZIlePPNN3Hs2LFBte7Qxx9/jAsvvBCPP/44li9fDktVOYo2r0PFro/gtLUhLDUHaRcuRvy0C1BSUoLp06cjNzcX//d//zfQRSeiU3Sc6df1Z0tL5z6JQUFBctNSYmIi4uPjvS7uSv5v0Mxz09zcjMLCQgDAxIkT8cQTT+Dcc89FREQEkpOTsXLlSlRUVOC1114D0D4UPCcnB7fffjtuvPFGfPHFF/jd736HzZs3uw0FX7x4MV544QVMmzYNTz75JN566y0cPXq0U18cT069OaWlpbjhhhuwc+dOfPbZZ5g9e3ZP78ugt3//fpx99tnIzs7Gf//7X2RlZXU6prq6GnfddRfeeOMNvP7661i0aNEAlNS3FStW4O9//zvuv/9+3HvvvZ1CqCRJ+Prrr7Fo0SIEBARg586diI6O9nI1IuoPoiiiqqrKLcjU1tZ2Ok6pVCIuLs4tzHD9JeqotrYW0dHRAz/Pzffff49zzz1X/trVsXfx4sVYv349KisrUVZWJu9PTU3F5s2b8fvf/x5PPfUUEhMT8dJLL8nBBgCuuuoq1NTU4P7774fRaMSECROwZcuWbgWbjjZs2IBNmzZh06ZNiIiI8NtgAwATJkzA9u3bcfHFFyM7Oxvz5s3DokWLEBMTg6amJmzatAkbN26EUqnEW2+9hSuuuGKgi+zRmjVrEBQUhFWrVuGpp57CkiVLMHv2bGi1Whw/fhzr1q3DDz/8gClTpuD//u//GGyI+pkkSTCbzW7NS5WVlbDb7Z2OjYiIkINMQkICYmNj2emX3DidTlRUVKC4uBglJSVyZUlv86vlFwBg/PjxuP322/HrX/96WMw62dbWho0bN+LZZ591W5E6PT1dXh294wrTg1VJSQlefPFFvPTSS/JvgIIg4KKLLsJtt92GvLw8tsET9QPXnDIdm5g8Tb+g0+mQkJDgFmaGw89c6rm2tjb88MMPKC4uRmlpqdsSGFarFQ8//PDAN0sNRq5wU1FR4XFRxeHCYrHAZDIhKCgIoaGhQ7LqVxRFNDY2wmazISwsjG3xRH2o40KSrjBTU1PTaXSoQqGAwWBwa16KjIwckj9jqO81NDSgra1NXh6ntbUVjzzyiPxcBQYGIjU1FampqYiKikJqaurAN0sNZq61g4Yr15pKQ5lCoXCbMZqIek/H5qWKigqcPHnS40KSer2+05wyarV6AEpMQ4HFYkFJSQmKi4tRXFyMxsZGJCcn48YbbwQABAQEIDc3F6GhoUhLS4PBYJCDsWuFgd7mV+GGiIja2Ww2eckC1+R4nj5IXAtJdmxe4pwy1B3bt2/HkSNHYDQa3bYrFAoolUpIkiSHmPnz5/dr2RhuiIiGOFEUUV1dLYcYb81LgiC4NS8lJCRwIUnqkqsT8IkTJ9xmrq+srJSDjcFgQFpaGtLS0pCcnDzgc6ox3BARDSGnjl5yNS95Gr0UGhraqXlJo9EMQKlpKJEkCdXV1XIzU8dOwKNGjUJ4eDiA9jnqcnJykJqaOui6RDDcEBENYh1XxHbVzHgaveRqXnKFGTYv0en44Ycf8Pnnn3dadd3VCdjhcMjbUlNT+7t43cZwQ0Q0SDidTrl5yRVmamtruxy9lJCQgMjISDYvUbe1tLTg+PHjKC4uxsSJE5GQkACgvfOvxWKBWq3GiBEjkJqa2qkT8FDAcENENAA6rr3kelVWVrr9ZuwSFhbmFmQ4eol6ym63o6ysTG5qMhqNcmh2LYkBtNfG3HDDDUhMTIRSqRzIIp8Rhhsion7Q0tLiFmQqKio8rr106uR48fHxw36aCzoztbW1eP755zstWhoTE4O0tDSkp6fL27Ra7aBag/B0MdwQEfUyu90Oo9Ho1rzU0NDQ6TilUonY2Fi3IMPJ8eh0SJKEuro6uWYmLCxMHn4dEREBtVqN4OBgpKWlyRPo+XOfLIYbIqIzIIoiamtr3WpkqqqqIIpip2OjoqLkWpmEhAQYDAauvUSnrbm5WQ4zxcXFbvMY6fV65OXlQRAEKBQK3HHHHQgKCho2wZn/q4iIukmSJJhMJnntJV+z/AYHB7sFmfj4eAQEBAxAqclfOBwOtzD86quvoqamRv5apVIhKSlJnm+mo+HWtMlwQ0TkRWtrqxxgXE1Mpw6RBQCNRiPP8ut6DdX13Wjw6LiCdnFxMaqqqnDPPffIASc9PR1qtVoOM0lJSexo/hOGGyIiuPeTcb3q6+s7HadQKBAbG+sWZjjLL/WW+vp6HDt2DMXFxTh+/HinWsGTJ08iOTkZAORmJ+qM4YaIhh3Xatgdg0x1dbXHfjKRkZFys1JiYiIMBgN/O6ZeYzabodVq5eUKjhw5gs8++0zeHxgYKHcCTktLk2cHBsBg4wPDDRH5Ndd8Mh37yVRWVnpcroD9ZKivtbW1obS0VG5qqqmpwaWXXopx48YBaG9qKi4uRnp6+pCcPG+wYLghIr/S1NTUqcNva2trp+NcyxW4amTi4+PZT4b6RHNzM7777jsUFxejoqLCrYZQEAS35s/Y2Fhcd911A1FMv8JwQ0RDVltbG06ePOkWZjoOh3XpOJ+Mq0YmKiqKQYZ6nSRJqKmpgcPhQHx8vLx9+/bt8t8jIyPlTsAjRoxg7WAfYLghoiGhY4dfV5ipq6vrdJwgCIiOjnbr8GswGIb0VPI0uDU1NbnNN9PU1IS0tDRcf/31ANqbO2fOnImoqCikpaUhLCxsYAs8DDDcENGg41pA0hViTp486bXDb3h4uFuQiYuLg0ajGYBS03CzdetWHD161G2uGaB9vhm1Wg1JkuTawQsuuGAgijhsMdwQ0YByTRvfsUbGaDR6XEAyODhYDjKuPwMDAweg1DSciKIoP5+5ubny9srKStTU1EAQBMTFxcmdgJOSkjjz9ADj3SeifuOa4bdjkKmsrITVau10rE6ncwsy7PBL/eXUdZpKSkrkZ3TUqFEIDQ0FAMycOROTJk1Camoq+80MMgw3RNRnOo5ccnX89bQStlqtljv8ugJNREQEgwz1u/379+PLL7+EyWRy2x4QEIC0tDS3KQROXeKABg+GGyLqFS0tLZ2CTFNTU6fjlEolDAaDW61MdHQ0Z/ilfmW321FWVobi4mKMGzcOBoMBQHt/GZPJBKVSieTkZLmpKTY2ls/oEMJwQ0Q91tbWhsrKSrcw09jY2Ok418iljk1LXAmbBoIkSTAajSguLkZRURHKysrkfl06nU4ON+np6bj22muRkpLCmaiHMP6EISKfrFYrjEajXBtz8uRJj0OwAfelCuLj4xEXF8cPCBpwtbW1WLduXacm0dDQUKSlpSEhIUHeFhAQgIyMjP4uIvUyhhsiktlsNjnIuGpmamtrIUlSp2PDwsI6BRmdTjcApSZqZ7VaUVJSguLiYoSEhGD27NkA2qcLcDgc0Gg0GDFihNzUxIkc/RfDDdEw5XA4OtXI1NTUeAwyoaGhnYIMh2DTQHMN0S4qKkJxcTFOnDghz4UUGRkphxulUolly5YhMjKSkzkOEww3RMOAw+GQJ8VzvbxNiudaPLJjkAkODh6AUhP59uKLL8JoNLpti4iIkGtmOk6iFxMTMxBFpAHCcEPkZzoGGVfTUnV1NZxOZ6djg4KC5BDjeoWEhAxAqYk8a21tRUlJCYqKilBRUYGbb75ZHrWUkJAAk8kkr9OUnp7OpQ0IAMMN0ZB2ao1MZWWl1yATGBjoVhvDSfFoMHI6nSgvL5ebmk6ePOnWVFpRUYGkpCQAwLx583DRRRdxiDZ1wnBDNEQ4HA5UVVXJtTFdBRlXgHGFGb1ezyBDg44kSZAkSQ4oX3/9Nb788ku3Y6Kjo5Geno709HTExsbK29mBnbxhuCEahFxB5tSmJU99ZDoGGdefDDI0mLW0tMjzzRQVFWH+/PkYPXo0gPZZf/fs2SM3M6WlpcnLHRB1F8MN0QCz2+2dgkxNTY3HIBMQENCpaYlBhgY7p9MpzwZcVFSEyspKt6am4uJiOdwkJibi7rvv5jNNZ4ThhqgfnTqPTGVlJWpra73WyHQMMWxaoqFCkiTYbDZotVoA7WuMvfrqq27HGAwGuakpOTlZ3s7nm3rDaYWbZ599Fo8++iiMRiPGjx+Pp59+GtOmTfN47Jw5c7B9+/ZO2y+88EJs3rwZALBkyZJOD35eXh62bNlyOsUjGhTa2to6BZm6ujqP88gEBwcjLi7OLciwsy8NJac2NcXFxWHRokUA2id8TElJQVhYmNzUxOkFqC/1ONy8+eabWL58OdauXYvc3Fw8+eSTyMvLQ35+vsd5BN59913YbDb567q6OowfPx5XXHGF23Hz58/HK6+8In/tSvxEQ0FLS4scYFyv+vp6j8eGhIR0qpEJDg5mkKEhp7S0FIWFhR6bmpxOJ0RRlDsK33DDDQNVTBqGehxunnjiCdx0003yg7p27Vps3rwZ69atw4oVKzodHxER4fb1hg0bEBgY2CncaLVat17wRIORJEloamqSA4zRaERlZSVMJpPH48PCwuQaGdeLv7HSUCRJEhobGxEeHi5v+/LLL3H8+HH561ObmjhEmwZKj8KNzWbD3r17sXLlSnmbQqHA3LlzsWvXrm5d4+WXX8bVV1+NoKAgt+3btm1DTEwMwsPDcd555+HBBx9EZGSkx2tYrVZYrVb5a7PZ3JO3QdQtkiShoaHBLcRUVlbCYrF4PD4yMtItxMTGxnKJAhrSWltb3ZqazGYz7rnnHvm5HjNmDEJDQ+WmJk4ASYNFj8JNbW0tnE6nvDS8i8FgwNGjR7s8f8+ePTh06BBefvllt+3z58/HpZdeitTUVBQVFeGPf/wjFixYgF27dnlcB2TNmjVYvXp1T4pO5JMoiqipqZFDjOvPjiHaRaFQICoqqlOQYVMq+YOamhocPHgQRUVFnSbQU6lUqKqqQmpqKgBg6tSpmDp16kAVlcirfh0t9fLLL2Ps2LGdOh9fffXV8t/Hjh2LcePGIT09Hdu2bcP555/f6TorV67E8uXL5a/NZrM8YyVRV1xDrzsGmaqqKjgcjk7HqlQqGAwGxMbGykEmJiYGarV6AEpO1Pvq6+uh1Wrl2vSKigrs2LFD3h8TEyM3NaWkpPDZpyGhR+EmKioKSqUSVVVVbturqqq67C9jsViwYcMG/PWvf+3y+7iWoi8sLPQYbrRaLX9Lpm5paWmB0Wh0CzK1tbUeRyxpNBq5FsYVZFzPPJG/sFqt8lpNRUVFqK+vR15eHmbMmAGg/edvTk6OHGg4gR4NRT0KNxqNBpMnT8bWrVuxcOFCAO3V+Vu3bsUdd9zh89yNGzfCarXi2muv7fL7nDhxAnV1dYiLi+tJ8WgYkyQJJpPJLcQYjUavHX2DgoLcgkxsbCwiIiI4Yon8UltbG/bs2YOioiKUl5e7zaukUCjQ1NQkfx0aGorLL798IIpJ1Gt63Cy1fPlyLF68GFOmTMG0adPw5JNPwmKxyKOnrr/+eiQkJGDNmjVu57388stYuHBhp07Czc3NWL16NS677DLExsaiqKgI9957LzIyMpCXl3cGb438ldPpRG1tbacg09bW5vH48PDwTkGGQ6/Jn5nNZjQ3NyM+Ph4AoFQqsWPHDrnpNTIyUq6ZGTFiBGvCye/0ONxcddVVqKmpwf333w+j0YgJEyZgy5YtcifjsrKyTsP/8vPz8fXXX+PTTz/tdD2lUokDBw7g1VdfRWNjI+Lj43HBBRfggQce4H84kifCc/WLMRqNXheLVCqViI6OdgsxBoOBi+uR37Pb7SgrK5PnnKmurobBYMCtt94KAFCr1Zg1axaCg4ORnp7uNpybyB8JkqfOB0OM2WyGXq+HyWRi+/AQ5ZpDo2OIMRqNaGxs9Hi8a16kjkEmOjqa/WNoWNm3bx8OHz6M0tJStw7xgiAgISEBS5YsgUrFVXZo8Oqrz28+9dTv7Ha7POy6Y5jxNOwaAPR6vRxkXK+wsDA2K9Gw0traipKSEowaNUp+9ktLS1FUVASgfebrjIwMec4ZzrFEwxnDDfUZSZLQ3NwsBxhXiPE2Wqljs5LrZTAYEBAQMAClJxpYoiiioqICRUVFKCwsREVFBSRJwm9+8xt5dOqECRMQGxuLjIwMREVFMfAT/YThhnqFw+FATU2NHGJcQaalpcXj8YGBgXJ4cQUZDrsmap9nZufOnSgqKurUST46Otrt/1Rqaqo8oR4R/YzhhnrEtbZSxxBTVVWF2tpat+GlLoIgICoqSg4xrj85Womo/ZeC0tJShIaGIjo6GkD7MjeHDx8GAOh0OnlUU3p6OvR6/UAWl2jIYLghr+x2O6qrqzsFmdbWVo/HBwQEwGAwyC9XJ1/OaErUTpIk1NXVobCwEIWFhSgtLYXdbsf06dMxf/58AEBSUhLmzJmD9PR0JCQkcPFJotPAcEPyApEdA0x1dTXq6+s99o1RKBSIjIyUA0xMTAxiY2MREhLC2hgiD+x2Oz755BMUFhZ2GgEYGhrqNl2BSqXCnDlz+reARH6G4WaYaW5uRnV1tVwj4/q73W73eHxQUJBbbYzBYEB0dDSHlxJ5IUmSPI3BqFGjALQHloKCAphMJiiVSqSkpCAjIwMZGRmIjo7mLwVEvYyfUH7KZrPJHXw7BhmLxeLxeJVKhejoaLcQExMTg+Dg4H4uOdHQY7FYUFxcLDc3WSwWBAQEIDs7GwqFAoIgYN68edBqtUhJSYFGoxnoIhP5NYabIc61FIGrBsb1amho8Hi8IAgIDw9HTEyMW4iJiIhg2z5RD+3btw979+7FyZMn3ZpwNRoNkpOT0dbWJs83k5OTM1DFJBp2GG6GCFEUUV9fj+rqatTU1Mghpq6uzuMoJQAIDg6WQ4zrz6ioKP7WSHQazGYzioqKMHr0aHlpGJPJhIqKCgCQ55tJT09HcnIypzUgGkAMN4OMKIpoaGiQA4zrz9raWo/rKQHtw0VjYmLkZqWYmBjExMRwhlKiM+B0OuX1mgoLC1FVVQWgfVTgyJEjAbTXxoSHhyM9PR0hISEDWVwi6oDhZoCIoojGxkY5wHR8dVwjpiO1Wi2HGFeAiYmJ4Sglol5UXV2NrVu3oqSkBDabTd4uCALi4+Pdmm+jo6Pl+WmIaPBguOljTqdTronp+KqtrfUaYlyde10hxvUn11Oi4aatrQ3Hjh1Dc3MzQkJCkJWVJTcJ9QbXJHoajQZJSUkA2v//5efnA2hv2nU1NaWnp7M2lGiIYLjpJXa7HXV1dXJwcYWY+vp6r81JHUNMx1d4eDg799KwVlRUhOeffx7r1q1z6xwfHR2NZcuW4ZZbbkFKSsppXbu+vl5uaiopKYHdbsfIkSNx9dVXAwAiIiJw4YUXIikpCbGxsfyFgmgIYrjpodbWVjnAuF41NTVobGz0OOEd0D5yIioqyi3AxMTEQK/XM8QQneLll1/GLbfcAr1ej6VLl+JXv/oV9Ho96uvr8fbbb+PZZ5/F448/jldffVUOJF2RJAmffvop8vPzUV9f77YvJCQEYWFhbtumTZvWW2+HiAYAw40HoijCZDK5BRjXy9s8MUB7R8NTQ0x0dDRCQ0P52x9RN7zyyityzcw//vEPBAQEwClKsDtFjFQqMHv2bDz00EO49dZb8etf/xoqlQqXX355p+vU1dWhsrJSHn4tCAIqKipQX18PhUKB5ORkZGRkIDMzEzExMfz/SeRnhnW4aWtrQ11dHerq6uTw4vraW38YANDr9YiKipJf0dHRiIqKQlBQEH9IEp2miooK3HLLLbjpppvw/PPPo80hYndpPY43tECUAKVCQFpEIMbGheLVV1+Fw+HA4sWLcd555yEkJATHjx9HQUEBCgsLUV9fD0EQkJ6ejoCAAADA7Nmz4XA4kJaW1qv9doho8BEkb20pQ4jZbIZer4fJZEJoaKjbPleHXldocQWZuro6NDc3e72mUqlEZGSkW4hxvThPDFHvW7VqFZ544glUVFRAExCET/Kr0Wp3ouMPKAFAsFaFC7Ji0Fhfi4SEBFx55ZUYNWqU2y8kSqUSycnJuOiiixAVFdXv74WIusfX5/eZ8KuaG9fQzY5BprGx0eskd0D7aIioqCi3IBMZGYmwsDD2hyHqJw6HA//6179w3XXXITQ0FHtPNHYKNg67HTWVJxAeGY38mgCMjYvB3LlzsWXLFmRkZCAsLAyZmZnIyMhAamoqa2eIhjG/CjcbNmzw+ANNo9EgMjISkZGRiIiIkANMZGSk22q8RDQwKisrUVlZiV/84hcAgJI6CyQAzeZGGMtKYCw7jpqTZXA6nJhw1rkIDwvF2Dg9rrjiCmzZsgXXX3890tLS2CxMRAD8LNxEREQgMTHRLchERkZykjuiQa6lpQVAe01qU3Mzvv/qCxjLj6Op0X2NtMDg9lmAbY722ljXBHqBgYH8P05EMr8KN7fcckuvttkRUd9rbGyUw01NTQ20Gg3Kjh6E1e6AQqFAZGw8YpNTEZucitDwSAiCgCCtSj4eaO/kT0Tk4lfhhogGP6fTifLychQUFKCgoADV1dWIjY3F6NGj8cYbb+Cyyy7DhXnzYLSpEJ2QBI22c9NxVlQwAOCNN97AjBkzOHMwEblhuCGifnH48GEcPnwYRUVFsFqt8naFQgGtVotbbrkFy5cvx4kTJ7DoornYVlSD6mZbp+skhOqQHhWE/Px8fP755/j3v//dn2+DiIYAvx8KTkT9TxRFVFZWIj4+Xu4L8+677+LAgQMAgKCgIHkSPddcNGazGWlpacjJycGWLVug1mhRUm9BUa0FLXYngjQqZEQFYUREIFosFpx77rkwGo0oKCjgwACiIYpDwYloUGttbUVhYaE8kV5LSwtuvfVWGAwGAMD48eMRERGBzMxMt9DjEhoaig8++ADz5s3D3Llz8cILL2DMmDHI+KkJymX//v1YunQpCgoKsH37dgYbIuqE4YaITpvJZMKBAwdQUFCA8vJyt/XVdDod6uvr5XDjWlnbl7POOgtffvklLrvsMuTk5OCcc86R15ZqaGjAxo0bsWvXLqSmpuKrr77C+PHj+/T9EdHQxHBDRN1ms9ngcDjkDry1tbXYunWrvD8mJgZZWVnIzMxEUlLSaU2EmZubi+LiYrz//vt47rnncM8998But0Oj0eDss8/Ge++9h1/84hdQqfjji4g8Y58bIvKpoaEBx44dQ0FBAY4fP46pU6ciLy8PQPvMwu+88w7S09ORmZnZJ0OyJUmSww0R+Rf2uSGifiFJkrwI5bFjx1BbW+u2v6qqSv67SqXCVVdd1aflEQSBwYaIeoThhohgt9uhVqvlr9999100NTUBaB+qnZycjMzMTGRlZXEhSiIa9BhuiIYhSZJQVVWFY8eO4dixY2hsbMTy5cuhUCggCALGjx+P5uZmeag2RyQR0VDCcEM0TNjtdpSUlMiBxmw2u+13zRQMAHPnzh2IIhIR9QqGGyI/JkmSPJ/Mjh078NVXX8n71Go10tLS5NFN7IxPRP6C4YbIj0iShIqKCrl25rzzzkNWVhYAIDMzEwcPHpTDzIgRI9z62RAR+YueT0IB4Nlnn8WIESOg0+mQm5uLPXv2eD12/fr1EATB7XVq+70kSbj//vsRFxeHgIAAzJ07FwUFBadTNKJhx2q14scff8T777+Pxx57DC+99BJ27NgBo9GI/Px8+bikpCTceeeduPDCC5GZmclgQ0R+q8c1N2+++SaWL1+OtWvXIjc3F08++STy8vKQn5+PmJgYj+eEhoa6/ZA9ddr1Rx55BP/85z/x6quvIjU1FX/+85+Rl5eHH3/8kR0ZiXwwm8146qmn4HQ65W1arRYZGRlyDY3Lqf/viIj8VY/DzRNPPIGbbroJN9xwAwBg7dq12Lx5M9atW4cVK1Z4PEcQBLmj4qkkScKTTz6JP/3pT/jlL38JAHjttddgMBjw/vvv4+qrr+5pEYn8jiiKqKioQH5+PiRJwrx58wAAISEh8sR52dnZyMrKQnJyMpRK5UAWl4hoQPUo3NhsNuzduxcrV66UtykUCsydOxe7du3yel5zczNSUlIgiiImTZqEv/3tbxgzZgwAoKSkBEaj0W10hl6vR25uLnbt2uUx3FitVlitVvnrU0d9EPkDq9WKoqIiuf9MS0sLgPaamfPOOw9KpRKCIOCmm25CQEDAAJeWiGjw6FG4qa2thdPplBfCczEYDDh69KjHc7Kzs7Fu3TqMGzcOJpMJjz32GGbOnInDhw8jMTERRqNRvsap13TtO9WaNWuwevXqnhSdaEj55JNPsGfPHrfmJp1OJ0+k13HVFAYbIiJ3fT5aasaMGZgxY4b89cyZMzFq1Ci88MILeOCBB07rmitXrsTy5cvlr81mM5KSks64rET9rePoppkzZ8p9zAICAuB0OhEZGYmsrCxkZ2cjOTn5tBaiJCIabnoUbqKioqBUKt3WlgHa15rx1qfmVGq1GhMnTkRhYSEAyOdVVVUhLi7O7ZoTJkzweA2tVgutVtuTohMNGna7HcXFxcjPz8exY8fQ3NwMoH1F7ZycHADAxIkTMXr0aC51QER0Gnr0a6BGo8HkyZOxdetWeZsoiti6datb7YwvTqcTBw8elINMamoqYmNj3a5pNpuxe/fubl+TaCioqanBG2+8gb///e944403sG/fPjQ3N0Or1WLMmDFuk+iFhIQw2BARnaYeN0stX74cixcvxpQpUzBt2jQ8+eSTsFgs8uip66+/HgkJCVizZg0A4K9//SumT5+OjIwMNDY24tFHH0VpaSmWLVsGoH0k1V133YUHH3wQmZmZ8lDw+Ph4LFy4sPfeKVE/kiQJNTU1cDqdcpDXaDTylAhhYWHIzs5GdnY2UlJSOLqJiKgX9TjcXHXVVaipqcH9998Po9GICRMmYMuWLXKH4LKyMrd+AQ0NDbjppptgNBoRHh6OyZMnY+fOnRg9erR8zL333guLxYKbb74ZjY2NmDVrFrZs2cI5bmhIcTqdKCsrQ35+PvLz89HQ0IDMzExcc801ANpHAf7iF79AYmIiDAYD550hIuojgtRx2MUQZTabodfrYTKZuD4O9bsjR47gyJEjOHbsGNra2uTtKpUKmZmZuPLKKxlkiIg86KvPb64tRdRDLS0tCAwMlL/es2cPSkpKAACBgYFyc1NaWho0Gs1AFZOIaNhiuCHqgiRJqK6uRn5+Po4ePYrKykr84Q9/QHBwMABg0qRJiIuLQ3Z2NpKSkjhcm4hogDHcEHkgiqLcf+bo0aNoaGiQ9wmCgBMnTmDkyJEAgLFjx2Ls2LEDVVQiIjoFww2RBwcPHsR7770nf61SqZCWloaRI0ciKytLrrUhIqLBh+GGhjWLxYJjx47h6NGjSE9Px7Rp0wAAmZmZCAoKQmZmJrKzs5Gens7+M0REQwTDDQ07DQ0NOHr0KI4ePYqysjJ5nabW1lY53AQGBuLuu+/mKCcioiGI4YaGDUmS8PLLL+PEiRNu22NjYzFy5Ei5D40Lg82ZE0UR9a12CIKAcJ2Kna3PgEOU0GZ3QqNSQKPkfTwTVocTdqeEALUSSgX/n/sjhhvyS6Ioory8HOXl5Zg1axaA9rASFBQEhUKB5ORkOdCEhYUNbGH9kCiK+LasAWUNrXBNpKUQgMyoYExKDBvIog05NoeI/1WaUFJngfOnm5mo12F8vB6hOvXAFm6IqbPYsP9kI6qbbQAAtVJAZlQwcmJDGXL8DCfxI7/hcDhQUlKCI0eOID8/HxaLBQBw5513Ijw8HABQX18PnU7nNk8N9b7PjlWj1mLzuC8lPAAzR0T2c4mGJrtTxGfHqmFuc6DjD2oBgEopIC8rBiEMON1Sa7Fia0ENJAk49UPPEKLFnPQoKFhb2+84iR+RF+Xl5fj2229RUFAAm+3nD1SdTofs7GyIoihvi4iIGIgiDivVTW1egw0AlDa0YmK8AwEa/vjpSlGdBaY2R6ftEgCHU8KBSjPOSmVQ7I695Y0QvfwqX9VkRYWpDUlhAf1bKOoz/OlCQ05LSwskSUJQUBAAoKmpCYcPHwYAhIaGIjs7G6NGjeKClAPkcFVTt46ZkhTeD6UZ2orrLF73SQDKG1vhECWo2KTiU5PVgfpWu9f9AoCSegvDjR9huKEhwWw2y2s4lZaW4pxzzsGcOXMAABkZGZg9ezZGjhyJ+Ph4dgQeYDaH2OUxbd04hgBrF/epvQZHhErBEO9LV8+khK7vNQ0tDDc0aNXV1cmBpqKiotM+F41Gg/PPP7+/i0dehOpUPn9LBoDwAPYT6Q69Tg1rs7VTHxEXtVKARsWRU10J0ighoHNfGxcB7c8t+Q/+a9Kg5HQ68a9//UteZVsQBCQlJWHUqFEYNWoURzgNYuPj9Tje0Op1vwBgVAxneO6OzOhgVDVbPe4TAGREBbMTbDfo1EokhQWgvLHVY8CR0D6Sj/wHww0NKEmScPLkSRw5cgSVlZW49tprIQgClEolRo0aBbPZjFGjRmHkyJFc8mCICNSokBMbgkNGz31vclPCOd9NNyXqdciICkJhraVTzUNkkAY5sSEDVbQhZ3JiGBpa7Wiy/txB23VPx8frERHIGcj9CcMN9TtJklBeXo4ff/wRR44cgclkkvdVVVUhNjYWAHDJJZew/8wQNTZOj8hADfafNMFsdUAAEB6gweREPSKDtANdvCFDEARMSQxDfKgOBbUWNLXZoVMrkRYRhBERgZybpQd0aiXysmNQVGfB8foW2J0iwgM1yIoORkwwn0l/w3BD/erQoUPYsmULmpub5W0ajQaZmZkYPXq021BtBpuhLV4fgHg9R5+cKUEQkKAPQALv5RlTKxUYGROCkTGs8fJ3DDfUZ5xOJ0pKShAeHo7IyPa5OAICAtDc3CzPQTNq1Cikp6dDrWYHUyIi6h0MN9SrnE4niouLcfjwYeTn56O1tRUzZsxAXl4eAGDEiBG49tprkZqayjloiIioTzDc0BkTRREFBQX48ccfkZ+fL49wAoCgoCBotT+3ZyuVSmRkZAxEMYmIaJhguKHTIkmS3CdGEARs2rQJTU3to2NCQkIwatQojB49GsnJyRwZQ0RE/YrhhrrNbrejsLAQP/74I06ePInbb78dCoWifUTHlCloaWnBmDFjkJSUxM7AREQ0YBhuBpgoivj888+xfv16lJaWQhRFxMXFYdGiRVi4cOGAd7R1OBwoLCyU+9B0XJiyvLwcKSkpAIBzzjlnoIpIRETkhuFmAG3atAm///3vUVhYiJycHEyaNAkKhQJHjx7FlVdeibi4OKxevRo33XTTgJTv4MGD2LRpE6zWn2dI1ev1GD16NMaMGYOEhIQBKRcREZEvDDcDZP369Vi6dCkuuOACvPLKKzjrrLPcmnIOHjyIxx57DDfffDPKy8vx17/+tU/L43A4UFRUBL1eL0+iFx4eDqvV2inQsMmJiIgGM4abAbBjxw4sW7YMy5Ytw/PPPw8IAsobW3HS3AZJAmKCtRg1ZgxeffVVjB49GitWrEBGRgauv/76Xi2Hax6aQ4cO4ejRo2hra8OkSZNwySWXAAASEhKwbNkyBpoesjlEFNdbUN9ih0ohIDEsAHEh2mF3Dx2iiNKGVlQ3WSEIQHyoDolhAT1aC+lEYysOV5nRZhcRoFZibFwI4kKH1mR2DlHEgZNmVJja1zWKDtJiYmIodCr++CXqK4IkSd4WSh0yzGYz9Ho9TCYTQkNDB7o4XcrLy0NtbS12794NuyTgi4IaeYp6oH2tE51KgfMyohGqU+GKK67A/v37cezYsTMeeSRJEkpKSnD48GEcOXIELS0t8r6QkBBMnjwZc+bMOaPvMZxVN1mxvbgWDlFy+/eMDtLgnPQoqJXDY+SYqdWOLwpr0OYQ3e5DqFaFczOjEaj2PceRKIrYWliLWout0764EC3mZET3fqH7QEOLDZ8eq4bo4afs7NRIJIYNraBG1Nv66vN7ePykHUQKCgrw6aef4ne/+x1UKhW+LqmTF3KT8PPCeFaHiC+LaiAB+P3vf4+ioiJ89tlnvVKGTZs2Ye/evWhpaUFQUBCmTp2KJUuW4Pe//z2DzRmwOpxysAHc/z1rLTZ8X944UEXrV6IkYVtRLawOEYD7fWiyOvBNSV2X19hXYfIYbACgssmKA5Umj/sGm88LajwGGwD4qqQODlHs3wIRDROsF+1n7777LoKDg3HllVeivsXm9Qe4BKDVLuJEYytmzpyJkSNH4u2335Zn+u2Ka7XtQ4cOoaioCDfffDNUKpU8bLuurg5jxozBiBEjOA9NLymua5GDzakkAKUNLZiQoEdAF7UWQ12FqRUtdqfHfRLag159i83nKszFdRaf3+NYdTPGxenPpJh97ni9xevz4HLgpBmTEsP6p0BEwwjDTT+rqalBXFwcAgICcKK22eexgtD+QZAcHoi0tDRUV1d3ef3q6mocPHgQhw4dQkNDg7y9qKgI2dnZAICZM2ee2Zsgj+paPAdVFwlAQ6vd78NNrcUGQQB8NXjXWbyHG4cowtlFY7m9i9AwGFSY27o8prrZ2uUxRNRzDDf9TK1Ww+Fob4ZSdtWxUgJUivZj7HY7AgMDvR5aWlqKzZs3uwUgtVqN7Oxs5OTkID09/cwLTz4pBAECfm6C8UQ5DPoUKxWC75sAQKHwfiP8pR5R1Y2O00of94GITh/DTT/LyMhAaWkpTpw4gXhDnM8PQwlAYlgA2trasG/fPixbtkze19TUBJvNJq+2HRgYiOrqaiiVSmRmZiInJwdZWVnQaLxX/VPvSgrTobShxet+jVJAVJDW635/kagPwGFjk9f9AtpHTnmjUCgQoFag1e69P0qodvD/6BoZE4zieu/PAwBkRAX1U2mIhhd/+SVpyLjiiisQGBiIf/3rX9CplciOCfZ6bEKoDhGBGmzcuBF1dXX49a9/jX379uHVV1/FE088gS+++EI+Njo6GldeeSXuueceXH311cjJyWGw6WcJ+gCEB6jh7XfxcXH6YfGbekSgBol67+ElKzq4y6a5SQlhvvcnDu7+NgCgD9AgItD7DOM6lQKpEQw3RH2BQ8EHwG233Ya3334bP/zwA+Lj43Gw0oyj1U1yPwMBQGpEICYnhaPJ1IgpU6YgMDAQV155JZzOnztqpqWl4brrrht286cMZlaHiN1l9agw/dzfQq0UMC5Oj8yooGHzb+UUJew90YDiuha5ZlIpANkxIRgbF9qtuW4Kapqx90SjW82mQgCmJYcPmVDgbUh7sEaJC7IN0Kr4+yUNb331+c1wMwAqKyuRm5uLkJAQbNmyBUlJSbA7RVQ3WyFJQGSQBgFqJUwmE6ZPn47i4mLceOONMBgMMBgMGDt2LHJychAWFjbQb4W8sNgc8iR+McHaYVFj40mb3Sl3MI4O1kLTw3l+RFFEcX0LmqwO6APUGBEWMCRH97XYHCistUCSgOSIAIQHsFaVCBhk89w8++yzGDFiBHQ6HXJzc7Fnzx6vx/7rX//C7NmzER4ejvDwcMydO7fT8UuWLIEgCG6v+fPnn07RhoS4uDh89tlnsFgsGDt2LO666y4UFRyD1FSHQ99uR2V5Kf7yl79g1KhROHHiBG6++WZcfvnluPXWW3Hrrbdi1qxZDDaDXJBGhaSwAMSF6oZtsAEAnVqJxLAAJOgDehxsgPb+NxlRwZiYEIa0iKAhGWwAIFCjwrh4PcYn6BlsiPpBj3vlvfnmm1i+fDnWrl2L3NxcPPnkk8jLy0N+fj5iYmI6Hb9t2zYsWrQIM2fOhE6nw9///ndccMEFOHz4sNvCi/Pnz8crr7wif63V+nfHy+zsbOzZswcPPfQQXnnlFTz11FNQqVRQKBSw2WwICgrCddddh7vuugtZWVnDpjmDiIjoTPW4WSo3NxdTp07FM888A6C92jgpKQm//e1vsWLFii7PdzqdCA8PxzPPPCOvlbRkyRI0Njbi/fff7/k7wNBrlmpra8OBAwdw4MABnDhxAg6HA8eOHUNzczOio6MxefJkLFmyZEi8FyIiotPVV5/fPaq5sdls2Lt3L1auXClvUygUmDt3Lnbt2tWta7S0tMButyMiIsJt+7Zt2xATE4Pw8HCcd955ePDBB+VhzqeyWq2wWn+e/MpsNvfkbQw4q9WKjz76CAAgCAJGjhyJK6+8EiNHjuQIJyIiojPUo3BTW1sLp9MJg8Hgtt1gMODo0aPdusZ9992H+Ph4zJ07V942f/58XHrppUhNTUVRURH++Mc/YsGCBdi1axeUys5DRtesWYPVq1f3pOgDQpIkHD9+HAcOHIDdbsfll18OANDr9Zg6dSoiIyORk5OD4GDvw8GJiIioZ/p1JqyHH34YGzZswLZt26DT/TwPxtVXXy3/fezYsRg3bhzS09Oxbds2nH/++Z2us3LlSixfvlz+2mw2IykpqW8L3wO1tbX43//+hwMHDsBkal/gT6FQoLm5WQ4yF1100UAWkYiIyG/1KNxERUVBqVSiqqrKbXtVVRViY2N9nvvYY4/h4Ycfxueff45x48b5PDYtLQ1RUVEoLCz0GG60Wu2g7HB85MgRfP3116ioqJC36XQ6jBkzBuPGjUNQ0NCYm4OIiGgo61G40Wg0mDx5MrZu3YqFCxcC+GmSqq1bcccdd3g975FHHsFDDz2ETz75BFOmTOny+5w4cQJ1dXWIi4vrSfH6ndPphCiKUKvbZyG1WCyoqKhoH76akYHx48cjOzsbKtXgnyqeiIjIX/T4U3f58uVYvHgxpkyZgmnTpuHJJ5+ExWLBDTfcAAC4/vrrkZCQgDVr1gAA/v73v+P+++/H66+/jhEjRsBoNAIAgoODERwcjObmZqxevRqXXXYZYmNjUVRUhHvvvRcZGRnIy8vrxbfaOyRJQmVlJfbv34+DBw/ivPPOw9SpUwEAY8aMgcPhwNixY1lLM8S12BywOyUEaZRQncb8LK02J06YWqBVKZEQqvXYd6zLa9idsDlEBGqUUJ9GGWwOEbUWK5QKAdFBmtOaI8ZVhgCN8rTmqbE5nSirb4VCISAlTHda98HqcKLNLkKnVp7WjL4OUUR1U/sAhJgQLVSncR+arQ40ttoRqlMhVOd9SQVvJElCs80JSZIQrFV1a4ZmfyRJElrsTjic7fdhOM8BRX2rx+HmqquuQk1NDe6//34YjUZMmDABW7ZskTsZl5WVuf0Qff7552Gz2eTOtC6rVq3CX/7yFyiVShw4cACvvvoqGhsbER8fjwsuuAAPPPDAoGp6ampqwsGDB7F//363lbcLCgrkcBMQEIDp06cPVBGpF1Q3W7G/ohF1LXYA7as2p0cGYXx8aLc+FNtsTmzJr0Krw33RxxHhgZgxIsLLWe7qWmz44UQjan6asl8htC/HMSEhrFsBwyGK2FFUh6rmn0cUKoT2NZ0mdrFmk4up1Y59FY0w/hQKBAFICQvAxIQw6LpYFwpor9X85FgNTG0OedvuMiAmWIPzMzvPh+VJk9WBH040osLcvpSFgPaFZCcl6BGo6fpHlyiK+LasAaUNrW7bk8MDMCM5vFthr85iw1cltW6LeGpVCswcEYHYEO/rZ3V0vL4FBypNsNic8vmjYkIwMiZ4WM1fVWluw/6TJjS2tv/fUikEZEYHY2xsKEMO9Touv9AFSZLw5ptv4tixYxDF9h9wKpUKo0aNwvjx45GWljZkZ00ld9VNVnxRWNNplXYBQFSQBudlRvv8jdvpdOLtA5XwtpZ1kl6HWWlRPstQ32LDZ8eqIUnuq8ULAPQBaszLioGqiw+CDw9Xotnm9LgvPSIQ01J8hyxzmx2f5FfDKUqdyhCsVeGC7JguQ9a7B0/C6vB8J/Q6FS4c5buPnsXmwCdHq2Fzip3KoFMrkJdt6HLxzS8KatwCXkcxwVqcnxnt83xTqw0fHa32un9uZjSig33/Anbsp/WxPMmKCsLkpHCf5/uLClMrdhTXedwXH6rD2WmRwyro0c8G1fIL/kySJNTW1spfC4IASZLkyQovvvhi3H333bjsssuQkZHBYONH9lY0dgo2QHvIqLHYcKKx1cPen31fYfIabACg3NTmtvCpJ/srTJ2CjasMja12HK+3+Dz/eL3Fa7ABgKL6Fti8hA6XA5XmTsHGVYYmqwOFNc0+zy+pt3gNNgBganPA1Grzuh8AfjQ2dQo2rjK02UXkVzf5PN/UavMabID2GrqGFt9l2F3W2MX+Bp/77U4R+0+avO4/VmtBk9Xhdb+/kCTJa8ADgJPmNlQ1ef+3Ijod/GT+icViwbfffou1a9fimWeeQUPDzz+4zjvvPPz2t7/F0qVLMXnyZLdh7OQfmtrscnW5N8frW3zuL2/wHX4A4KDR+4dym92Jqmarx4DlUtJFGfKrfQcPAMiv8V4GpyjhRGPrGZXhYGXXk2ruPeH9Q1+SJJQ0tHgtg9SNMhzycZ9dDlf5Pqaui/DTZHXItbmeVJja4BS930kBQGmD7/fhD+pb7HKTnCcCgOPD4D5Q/xrWw3hEUURRURF++OEH5Ofny79Vq1QqVFZWIjy8vcr41EkLyf/YnF23zlqdvms8nN1o4W2xe/8hb+/i+gB81oh09xptPq7hEDvXlpzK1tV98PGB7uLrXkrduEZX77Or+9TdY7oiwvtviF2VURDQZS2aP+jqeZG6cQxRTw3bcFNZWYk33njDbemG+Ph4TJw4ETk5OQgICBjA0lF/C9YqIaBzc5CLACAswPcoGa1K4dbx1JOEUO+1fgGa9tEj3j7Yu1OGUJ0aTT5+SwaAmCDvS3yolQpolQqv4UMAoO9itFCIVoU2h+9aj8hA79dQCAKCNUqfzWtdjViKCNT4bJZqP8b3NZQC4CvzCoDPTuZd3SdR6voYfxCq8/0x051niqinhk2zlN1ud+tLExkZiba2NgQGBmL69Om49dZbcfPNN2Pq1KkMNsOQVqVESngAvHVplABkRPoe3j+pi5FIAoCUCO/XUP00MstXGbKifS/VMSFB73O/UvBdBoUgIDPa+/7ulGF6SpjP/QAwuYtydvU9utqfExfSZRnGxvnuvDgiPNDn/ni97+bp6GANQrQqr/+eKoWA5HD//1kTpFEhLlTn87lO7+L/FlFP+X24MRqN2Lx5Mx5//HG89dZbcA0O02g0WLJkCZYvX4758+ez6YkwKTG802+Zrh/IkxPDEB7oe1HT5PBAxAR7P2Z2queFYDsaFxeKiFO+j6sMY+NCEdPF6JxQnRqjY7x/sJ+d7nu0FgCMNoTCEOL+fVxlyI4OQkIXH+rBWg3SI70HgwnxoV3Od5MZHYzEn76P63u7/kyNCERqhO/goVIoMC0pzOv+qUlhXQ7tn5IUhmCN53LqfhoO7osgCJiVGtlpjiIB7UPzZ3vY56+mJYcj8JR76fr3zE0OR7B22DYiUB/xy6HgVqsVBw8exL59+3Dy5En5uPDwcCxdupQLVZJXDlHE8foWHK9vgd0pITxQjczoYER2EWw6OlrdhENGM+w/tWnodSqcNSIC+oDuXcMpSihtaJFHHekD1MiKCu5y2HFHJ02t+F+lGeY2OwRBQEyQFpMTwxDSRROBiyhJKGtoRUm9Ba12J0J1amREBcEQrO32kN3Segv2VZjkPj5BGiWmJYd3e34YSZJwwtSGojoLWmwOBGtVSI8MQnyorttlqLPYsK+iUR4ZFR6owaQEPSKDuncvRVHE4aomFNZaYHOKUCsUSI0MxPi40G6PlGyzO1FYZ0GFqRWSBBhCtMiMCh52H+h2p4jiOgvKGlvhcEqIDNIgKzq4y6ZW8m99NRTc78JNfn4+Pv30U9jtP03CplRi1KhRmDRpElJTUzmXAhER0SDRV+HG7351CA8Ph91uR3R0NCZNmoTx48cjMNB3FTYRERH5D78LN2lpaVi6dCkSExNZS0NERDQM+V24USgUSEpKGuhiEBER0QAZHl31iYiIaNhguCEiIiK/wnBDREREfoXhhoiIiPwKww0RERH5Fb8bLUU00FrtThTXWVDfYoNSoUBSWAAS9Dooujk1gSRJqGq2orS+BVan2D47cGTQsJvRtjc4nCKON7TA2NS+iGZsiBYp4YHDZtmD3tRsdaCozgJTmx0apQIjIgJ7NGM1UX/yuxmKe3OGQ6KeqjS34aviWnk1addK4xGBapybHg2NyveHqihJ+KakDidMbfK5rj+nJYdzgcEeMLfZ8UVhTaeV2nUqBc7PjO5yZXH6WXGdBbvLGjo9kwl6Hc4aEQmlggGHTk9ffX7z1xeiXtJqd7oFG6D9AwAAGlrs+K68octrHDaaccLU5nau6889ZQ2o/2mNJPJNkiTsKK5D2ynBBgCsDhHbi2vhB7/X9YuGFht2l7U/u6c+kxWmNhw2mgekXES+MNwQ9ZLiOotbsOlIAlDW2IpWu9Pr+U5RQn5Ns9f9AoBjPvbTz4xNVjRZHfD0zyEBaLY6UflTUxX5dqymGb7qZY7VNsMpMijS4MJwQ9RLGlrtXR/jo+alxe6UVxL3REL7KtfUtfoWm88PZOGnY6hrdS02jyHRxe6UYLE5+q08RN3BcEPUS5SC4PMDFQBUPjqydqffgop9G7pFpRB8fiBL4L3sLpWi648J3ksabBhuiHpJUliAzw9UrUqBqCCN1/2BaiUiAn13ck0O5wr33ZEYFtD1MfqujyEgOdz3fYoIUCNQw5F8NLgw3BD1kni9DpGBGq+1N+Pj9V0OBx8fr/e4XQAQqFFytFQ3BWlUyIzyfq84tL770iKDEKRRen2ux3l5ZokGEsMNUS9RCALOzYhCcniA2weBVqXo9jDu2BAdzkmLRJBG6bbdEKLFvMyuh5LTzyYlhmGMIcStuU+pEDDaEILJSWEDV7AhRqNUYG5mDGJDtG7bgzRKnJ0WibhQ3QCVjMg7znND1Ada7U40ttqhVAiICtJ0ewI/F0mSUN9ib5/ET6tiLcMZsDtF1P3UeTgyUMMJ/M5As9UBs9UBrVKBiEA1J/CjM9ZXn9/8iUnUBwLUSgSolV0f6IUgCIj00T+Huk+tVCA2hLULvSGYQZuGCP4KQ0RERH6F4YaIiIj8CsMNERER+RWGGyIiIvIrDDdERETkVxhuiIiIyK8w3BAREZFfYbghIiIiv8JwQ0RERH7ltMLNs88+ixEjRkCn0yE3Nxd79uzxefzGjRsxcuRI6HQ6jB07Fh999JHbfkmScP/99yMuLg4BAQGYO3cuCgoKTqdoRERENMz1ONy8+eabWL58OVatWoV9+/Zh/PjxyMvLQ3V1tcfjd+7ciUWLFmHp0qX44YcfsHDhQixcuBCHDh2Sj3nkkUfwz3/+E2vXrsXu3bsRFBSEvLw8tLW1nf47IyIiomGpxwtn5ubmYurUqXjmmWcAAKIoIikpCb/97W+xYsWKTsdfddVVsFgs2LRpk7xt+vTpmDBhAtauXQtJkhAfH48//OEPuPvuuwEAJpMJBoMB69evx9VXX93pmlarFVarVf7aZDIhOTkZ5eXlXDiTiIhoiDCbzUhKSkJjYyP0en3vXVjqAavVKimVSum9995z23799ddLl1xyicdzkpKSpH/84x9u2+6//35p3LhxkiRJUlFRkQRA+uGHH9yOOfvss6Xf/e53Hq+5atUqCQBffPHFF1988eUHr6Kiop7EkS71aHnX2tpaOJ1OGAwGt+0GgwFHjx71eI7RaPR4vNFolPe7tnk75lQrV67E8uXL5a8bGxuRkpKCsrKy3k1+w5ArRbMW7MzxXvYO3sfew3vZe3gve4er5SUiIqJXrzsk167XarXQarWdtuv1ej5kvSQ0NJT3spfwXvYO3sfew3vZe3gve4dC0buDt3t0taioKCiVSlRVVbltr6qqQmxsrMdzYmNjfR7v+rMn1yQiIiLypkfhRqPRYPLkydi6dau8TRRFbN26FTNmzPB4zowZM9yOB4DPPvtMPj41NRWxsbFux5jNZuzevdvrNYmIiIi86XGz1PLly7F48WJMmTIF06ZNw5NPPgmLxYIbbrgBAHD99dcjISEBa9asAQDceeedOOecc/D444/joosuwoYNG/D999/jxRdfBAAIgoC77roLDz74IDIzM5Gamoo///nPiI+Px8KFC7tVJq1Wi1WrVnlsqqKe4b3sPbyXvYP3sffwXvYe3sve0Vf3scdDwQHgmWeewaOPPgqj0YgJEybgn//8J3JzcwEAc+bMwYgRI7B+/Xr5+I0bN+JPf/oTjh8/jszMTDzyyCO48MIL5f2SJGHVqlV48cUX0djYiFmzZuG5555DVlbWmb9DIiIiGlZOK9wQERERDVZcW4qIiIj8CsMNERER+RWGGyIiIvIrDDdERETkV4ZEuFmzZg2mTp2KkJAQxMTEYOHChcjPz+/yvI0bN2LkyJHQ6XQYO3YsPvroo34o7eB1Ovdx/fr1EATB7aXT6fqpxIPX888/j3Hjxsmzk86YMQMff/yxz3P4PHrW03vJZ7J7Hn74YXmqDV/4XHatO/eSz6Vnf/nLXzrdl5EjR/o8pzeeySERbrZv347bb78d3377LT777DPY7XZccMEFsFgsXs/ZuXMnFi1ahKVLl+KHH37AwoULsXDhQhw6dKgfSz64nM59BNqnF6+srJRfpaWl/VTiwSsxMREPP/ww9u7di++//x7nnXcefvnLX+Lw4cMej+fz6F1P7yXAZ7Ir3333HV544QWMGzfO53F8LrvW3XsJ8Ln0ZsyYMW735euvv/Z6bK89k726DGc/qa6ulgBI27dv93rMlVdeKV100UVu23Jzc6Vbbrmlr4s3ZHTnPr7yyiuSXq/vv0INYeHh4dJLL73kcR+fx57xdS/5TPrW1NQkZWZmSp999pl0zjnnSHfeeafXY/lc+taTe8nn0rNVq1ZJ48eP7/bxvfVMDomam1OZTCYA8LmK6K5duzB37ly3bXl5edi1a1eflm0o6c59BIDm5makpKQgKSmpy9+ohyOn04kNGzbAYrF4XTKEz2P3dOdeAnwmfbn99ttx0UUXdXrePOFz6VtP7iXA59KbgoICxMfHIy0tDddccw3Kysq8Httbz+SQWxVcFEXcddddOOuss5CTk+P1OKPRCIPB4LbNYDDAaDT2dRGHhO7ex+zsbKxbtw7jxo2DyWTCY489hpkzZ+Lw4cNITEzsxxIPPgcPHsSMGTPQ1taG4OBgvPfeexg9erTHY/k8+taTe8ln0rsNGzZg3759+O6777p1PJ9L73p6L/lcepabm4v169cjOzsblZWVWL16NWbPno1Dhw4hJCSk0/G99UwOuXBz++2349ChQz7b7Khr3b2PM2bMcPsNeubMmRg1ahReeOEFPPDAA31dzEEtOzsb+/fvh8lkwttvv43Fixdj+/btXj+Uybue3Es+k56Vl5fjzjvvxGeffcaOrGfodO4ln0vPFixYIP993LhxyM3NRUpKCt566y0sXbq0z77vkAo3d9xxBzZt2oQdO3Z0mYRjY2NRVVXltq2qqgqxsbF9WcQhoSf38VRqtRoTJ05EYWFhH5Vu6NBoNMjIyAAATJ48Gd999x2eeuopvPDCC52O5fPoW0/u5an4TLbbu3cvqqurMWnSJHmb0+nEjh078Mwzz8BqtUKpVLqdw+fSs9O5l6fic+lZWFgYsrKyvN6X3nomh0SfG0mScMcdd+C9997DF198gdTU1C7PmTFjBrZu3eq27bPPPvPZju/vTuc+nsrpdOLgwYOIi4vrgxIObaIowmq1etzH57FnfN3LU/GZbHf++efj4MGD2L9/v/yaMmUKrrnmGuzfv9/jhzGfS89O516eis+lZ83NzSgqKvJ6X3rtmexR9+MBcuutt0p6vV7atm2bVFlZKb9aWlrkY6677jppxYoV8tfffPONpFKppMcee0w6cuSItGrVKkmtVksHDx4ciLcwKJzOfVy9erX0ySefSEVFRdLevXulq6++WtLpdNLhw4cH4i0MGitWrJC2b98ulZSUSAcOHJBWrFghCYIgffrpp5Ik8XnsiZ7eSz6T3XfqCB8+l6evq3vJ59KzP/zhD9K2bdukkpIS6ZtvvpHmzp0rRUVFSdXV1ZIk9d0zOSTCDQCPr1deeUU+5pxzzpEWL17sdt5bb70lZWVlSRqNRhozZoy0efPm/i34IHM69/Guu+6SkpOTJY1GIxkMBunCCy+U9u3b1/+FH2RuvPFGKSUlRdJoNFJ0dLR0/vnnyx/GksTnsSd6ei/5THbfqR/IfC5PX1f3ks+lZ1dddZUUFxcnaTQaKSEhQbrqqqukwsJCeX9fPZOCJElSz+p6iIiIiAavIdHnhoiIiKi7GG6IiIjIrzDcEBERkV9huCEiIiK/wnBDREREfoXhhoiIiPwKww0RERH5FYYbIiIi8isMN0RERORXGG6IiIjIrzDcEBERkV/5/4WgJRpqgRkaAAAAAElFTkSuQmCC\n",
|
|
"text/plain": [
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"%matplotlib inline\n",
|
|
"\n",
|
|
"plt.scatter(Xtrain['sepal_width'], Xtrain['petal_width'], c=y1, \n",
|
|
" s=30, cmap=plt.cm.Paired)\n",
|
|
"\n",
|
|
"# plot the decision function\n",
|
|
"ax = plt.gca()\n",
|
|
"\n",
|
|
"# create grid to evaluate model\n",
|
|
"xx = np.linspace(2, 5, 100)\n",
|
|
"yy = np.linspace(0, 2, 100)\n",
|
|
"YY, XX = np.meshgrid(yy, xx)\n",
|
|
"xy = np.vstack([XX.ravel(), YY.ravel()]).T\n",
|
|
"Z = svc2.decision_function(xy).reshape(XX.shape)\n",
|
|
"\n",
|
|
"# plot decision boundary and margins\n",
|
|
"ax.contour(XX, YY, Z, colors='k', levels=[-1, 0, 1], alpha=0.5,\n",
|
|
" linestyles=['--', '-', '--'])\n",
|
|
"\n",
|
|
"# plot support vectors\n",
|
|
"ax.scatter(svc2.support_vectors_[:, 0], svc2.support_vectors_[:, 1], s=100,\n",
|
|
" linewidth=1, facecolors='none', edgecolors='k')\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Activity 1\n",
|
|
"> Use the simulation data below to create linear classifier. \n",
|
|
"> Plot the figure like above. "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import matplotlib.pyplot as plt\n",
|
|
"%matplotlib inline"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# from sklearn.datasets.samples_generator import make_blobs\n",
|
|
"from sklearn.datasets import make_blobs\n",
|
|
"\n",
|
|
"X, y = make_blobs(n_samples=50, centers=2,\n",
|
|
" random_state=0, cluster_std=0.60)\n",
|
|
"\n",
|
|
"# plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 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-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 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-3 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-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 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-3 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-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 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-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 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-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 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-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(C=10, kernel='linear')</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-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(C=10, kernel='linear')</pre></div></div></div></div></div>"
|
|
],
|
|
"text/plain": [
|
|
"SVC(C=10, kernel='linear')"
|
|
]
|
|
},
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=2)\n",
|
|
"\n",
|
|
"from sklearn.svm import SVC\n",
|
|
"svc3 = SVC(kernel='linear',C=10)\n",
|
|
"svc3.fit(Xtrain,ytrain)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 19,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"3.1851579396666305"
|
|
]
|
|
},
|
|
"execution_count": 19,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"Xtrain[:,0].max()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([1, 0, 1, 0, 1, 1, 0, 1, 0, 1])"
|
|
]
|
|
},
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"ypred = svc3.predict(Xtest)\n",
|
|
"ypred[:10]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 21,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([[2.33812285, 3.43116792],\n",
|
|
" [0.44359863, 3.11530945],\n",
|
|
" [2.06156753, 1.96918596]])"
|
|
]
|
|
},
|
|
"execution_count": 21,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"svc3.support_vectors_"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 22,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"%matplotlib inline\n",
|
|
"\n",
|
|
"plt.scatter(Xtrain[:,0], Xtrain[:,1], c=ytrain, \n",
|
|
" s=30, cmap='coolwarm')\n",
|
|
"\n",
|
|
"# plot the decision function\n",
|
|
"ax = plt.gca()\n",
|
|
"\n",
|
|
"# create grid to evaluate model\n",
|
|
"xx = np.linspace(-1, 4, 50)\n",
|
|
"yy = np.linspace(-1, 5, 50)\n",
|
|
"YY, XX = np.meshgrid(yy, xx)\n",
|
|
"xy = np.vstack([XX.ravel(), YY.ravel()]).T\n",
|
|
"Z = svc3.decision_function(xy).reshape(XX.shape)\n",
|
|
"\n",
|
|
"# plot decision boundary and margins\n",
|
|
"ax.contour(XX, YY, Z, colors='k', levels=[-1, 0, 1], alpha=0.5,\n",
|
|
" linestyles=['--', '-', '--'])\n",
|
|
"# plot support vectors\n",
|
|
"ax.scatter(svc3.support_vectors_[:, 0], svc3.support_vectors_[:, 1], s=100,\n",
|
|
" linewidth=1, facecolors='none', edgecolors='k');"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Activity 2\n",
|
|
"> Use the simulation data below to create nonlinear classifier. \n",
|
|
"> Plot the figure like above. "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 23,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"<matplotlib.collections.PathCollection at 0x7fd4205ca890>"
|
|
]
|
|
},
|
|
"execution_count": 23,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"# from sklearn.datasets.samples_generator import make_circles\n",
|
|
"from sklearn.datasets import make_circles\n",
|
|
"\n",
|
|
"X, y = make_circles(100, factor=.1, noise=.1)\n",
|
|
"plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 24,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 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-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 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-4 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-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 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-4 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-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 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-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 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-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 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-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(C=10, degree=2, kernel='poly')</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-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(C=10, degree=2, kernel='poly')</pre></div></div></div></div></div>"
|
|
],
|
|
"text/plain": [
|
|
"SVC(C=10, degree=2, kernel='poly')"
|
|
]
|
|
},
|
|
"execution_count": 24,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, random_state=2)\n",
|
|
"\n",
|
|
"from sklearn.svm import SVC\n",
|
|
"svc4 = SVC(kernel='poly',degree=2,gamma='scale',C=10)\n",
|
|
"svc4.fit(Xtrain,ytrain)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 25,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([1, 1, 1, 1, 1, 0, 1, 1, 0, 1])"
|
|
]
|
|
},
|
|
"execution_count": 25,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"ypred = svc4.predict(Xtest)\n",
|
|
"ypred[:10]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 26,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([[ 0.75791515, -0.00889201],\n",
|
|
" [-0.19369049, 0.76432475],\n",
|
|
" [ 0.12312965, -0.2271171 ]])"
|
|
]
|
|
},
|
|
"execution_count": 26,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"svc4.support_vectors_"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 27,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"<matplotlib.collections.PathCollection at 0x7fd42063a110>"
|
|
]
|
|
},
|
|
"execution_count": 27,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAjoAAAGiCAYAAADulWxzAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAACPx0lEQVR4nO3dd3yT9fYH8M+TpE333qWTAmW2bMreU6DqRXABDlQUvV68DtTrVq7+XPcqigqKiCDKBQeyt+xZZim0lO5B90qbJnl+fxzSUGi6aPIk6Xm/Xnm1TZ4k34bQ5+T7Pd9zBFEURTDGGGOM2SCZ1ANgjDHGGDMVDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrNMGujs27cPU6dORVBQEARBwK+//tro8Xv27IEgCLdccnNzTTlMxhhjjNkokwY6lZWViImJwZIlS1p0v6SkJOTk5NRd/Pz8TDRCxhhjjNkyhSkffNKkSZg0aVKL7+fn5wcPD4+2HxBjjDHG2hWTBjqtFRsbi5qaGvTo0QNvvPEGhgwZYvTYmpoa1NTU1P2s0+lQVFQEb29vCIJgjuEyxhhj7DaJoojy8nIEBQVBJmu7BSeLCnQCAwOxdOlS9OvXDzU1NVi2bBlGjhyJI0eOoE+fPg3eZ/HixXjzzTfNPFLGGGOMmUJGRgY6dOjQZo8niKIottmjNfZEgoANGzYgPj6+RfcbMWIEQkND8cMPPzR4+80zOqWlpQgNDUVGRgbc3NxuZ8iMMcYYM5OysjKEhISgpKQE7u7ubfa4FjWj05ABAwZg//79Rm9XKpVQKpW3XO/m5saBDmOMMWZl2jrtxOLr6CQkJCAwMFDqYTDGGGPMCpl0RqeiogLJycl1P6empiIhIQFeXl4IDQ3FokWLkJWVhZUrVwIAPv30U0RERKB79+6orq7GsmXLsGvXLmzbts2Uw2SMMcaYjTJpoHP8+HGMGjWq7ueFCxcCAObMmYMVK1YgJycH6enpdber1Wo899xzyMrKgpOTE3r16oUdO3bUewzGGGOMseYyWzKyuZSVlcHd3R2lpaWco8MYY4xZCVOdvy0+R4cxxhhjrLU40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrMUUg+AMdY+lVdosHlXLs5cKIVCLsOQAd4YOdgHdnb8+Ysx1nY40GGMmd2FS2VY+NoZVFZpAQCCAOzYl4/vQ5zwn3dj4O1pL/EIGWO2gj86McbMqrpai3++cRZVKi1EERBFQKej2zKyVHjj/xKlHSBjzKZwoMMYM6sdf+WjrFxTF9zcSKsTcepsCa6kVZp/YIwxm8SBDmPMrC5eroBCLjR6TFJyuZlGwxizdZyjwxgzK6VSBrHJY+RmGUtbq67WYuuePOzafw1VKi26d3bDnZODEBbiJPXQGGu3ONBhjJnVyME+WPtrptHb7e1lGNDb04wjahvFJWosWJSAtEwVBIFyjy4ll2P9n1l4dWE0xo/0l3qIjLVLvHTFGDOrHtFuiOvnBZmR1as594TCxdn6PoN9sOQSMrNVACjIAQCtDtCJwDufXEROXrWEo2Os/eJAhzFmVoIg4J2XuuGO8YGQ35Cr4+wkx5MPRWL2PaESjq518gtqsP9IIbQNJFjr/b41x3wDYozVsb6PTYwxq6dUyvHCgs547MEIXEwuh51CQI9oN6vNzUnLqKybxWmITgfeScaYREw6o7Nv3z5MnToVQUFBEAQBv/76a5P32bNnD/r06QOlUomoqCisWLHClENkjEnIw90Og/p6oW+Mp9UGOQDg3MRSm1wGuDhZ7+/HmDUzaaBTWVmJmJgYLFmypFnHp6amYsqUKRg1ahQSEhLw7LPP4tFHH8XWrVtNOUzGGLst0VGuCPBTGr1dqwPGjvAz44gYY3omXbqaNGkSJk2a1Ozjly5dioiICHz00UcAgK5du2L//v345JNPMGHChAbvU1NTg5qamrqfy8rKbm/QjDHWQjKZgGcejcLL752v23FVd5sA9OnlgYF9vKQbIGPtmEUlIx86dAhjx46td92ECRNw6NAho/dZvHgx3N3d6y4hISGmHiZjjN1ieJwP3v9XD4R2MNTMUdrLcPfUYLz/rx6QGdtmxhgzKYtKRs7NzYW/f/1aE/7+/igrK4NKpYKjo+Mt91m0aBEWLlxY93NZWRkHO4wxSQwZ4I3B/b2Qka1CdbUWHYKc4ORo/bk5Wq0Ida0ODkoZBIEDNmZdLCrQaQ2lUgml0vjaOGOMmZMgCAgNto1KyLn51fjupzRs35MPda0OXp52uGtKMO67KwT2dha1IMCYURYV6AQEBCAvL6/edXl5eXBzc2twNocxxphp5ORVY95zJ1FeXltXH6iouBbLf7yKhLMl+PCNnlAoONhhls+i3qVxcXHYuXNnveu2b9+OuLg4iUbEmHnlXavGtj152L43H0XFaqmHw9qxL1dcqRfk6IkicPx0CbbvzZdmYIy1kElndCoqKpCcnFz3c2pqKhISEuDl5YXQ0FAsWrQIWVlZWLlyJQDgiSeewOeff44XXngBDz/8MHbt2oWff/4Zf/75pymHyZjkVNVafPD5JezYl1+3Y0cuEzBtYiCeebQj7HiZgJlRZZUGew8WGK30LAjAxm05mDQmwLwDY6wVTPrX8/jx4+jduzd69+4NAFi4cCF69+6N1157DQCQk5OD9PT0uuMjIiLw559/Yvv27YiJicFHH32EZcuWGd1azpiteP2DROz8K7/etmStTsSvm7Px0ZeXpRsYa5fKyjXQ6oyXehZF4Fohzzgy62DSGZ2RI0dCbKQuekNVj0eOHIlTp06ZcFSMWZak5HIcPFbY4G2iCPy5IxdzZ4UhwM/BzCNj7ZWnux3s7QSoaxv++y2TAcGBnDfJrAPPhzMmsYPHCiFv5H+iKAKHTxSZb0Cs3XNwkGP8KH+j70udDoifFGjeQTHWShzoMCaxWo1ISQ9GCAJQW9tIW2zGTOCJ2ZEIDHDEjXUO9W/TiaP8MWyQjzQDY6yFLGp7OWPtUc+ubtBqG8+H6NnN3Ywjsg3lFRps35uHrNxqeHnYYdwIf/j5cM2t5vJwt8M3H/XB/zZm4c8duSgrr0VoByfcPSUY40f6caVnZjUEsbEkGitUVlYGd3d3lJaWws3NTerhMNYkrVbEg08dQ1aO6pZdLnIZ0D3aDV+831uawVmp3Qeu4Z2PL0Jdq4NcJkAnioAIPPpAOGbfEyb18BhjDTDV+ZuXrhiTmFwu4MM3esL/erKxXC5ALqdPy+Ghznjnpe5SDs/qJCWX4/UPLkCt1kEUAY1WhE4H6ETg6x+uYtuevKYfhDFmM3jpijELEBTgiNVf9se+w4U4eaYEMhkwqK8XBvbxqgt6WPP8/FsmBAjQ4dbJakEAfvglHeNH+jdwT8aYLeJAhzELoVDIMHqoL0YP9ZV6KFbt+OkSozVgRBFITa9CRaUGLs7854+x9oCXrhhjNqU5SbKcSMtY+8GBDmPMpgwd6A25kUBGJgN6RLvByVFu5lExxqTCc7eMtUOVVRps2Z2HIyeKIIpA3xgPTB4TADdXO6mHdtvumR6MTTtyIWooCflGOh3w0L2864qx9oS3lzPWzqRnVmHBy6dRVKyGIFDeiiAALs4K/PfdGHSKdJF6iLftzNki/HvxSVReK4OTVgU7rRp2TvaY+eJYQyLytm1AeTmg0QBaLV30L4abGzB9uuEBd+8GKioAOzu6ODgAjo6AkxPg7AyEhEjzi96kulqL3QeuITWjCq7OCowe5ovgAG7VwKyDqc7fPKPDmJXTakVkZFcBAEKCnBrdpSWKIha9ew6lperrP6Pua2WVBs+/eRbrlg+EQmHhq9oqFVBYSMFJ2A0zNN98AxQVoZdKhVVRIrJdqlFWUQtHBzk69ImA3Y27rS5eBIqMtNbwuanqb2IikJ/f8LGursBzzxl+/vVXoLSUgiUPD8DLC/D2pouj6YKOk2dL8PK751BRqYVCTrWDvlqZipnxHbDg4UgIjVTfZsyWcaDDmJUSRRHrN2Vj5dp0FBZT4OLjZY/Z94TizslBDZ7YTp4pQVqmqsHH0+mAgiI19h8pxMghFrTz6+pVIDcXuHYNKCigS2Ul3RYYCDz+uOHYmhoKggDIFHJ06OJHMy6OjrcGL0OHAmo1IJcbLvrXzN6+/rGDBtHsT20t3aemBqiqoudycqp/bEYGBWEN8fYGnn7a8HNZGY1Pfns5Q7n51fjnG2frWoVobqi0vfbXTPh622NWvGXMOjFmbhzoMGalvl2Thu/WpNW7rqBIjY+XJqOkrBYP3xt+y30uXamATIZbclf0FHIBl1MrGgx0MjMzcf78eahUKnh6emLAgAFwbMsZiqoqIDOTgpjeN1SC/v33hmde3NwA95taY9x1F6BQAC4uFNw0NovRp0/zx9aSY6dPB0pKKIgpLqagp7CQAqWbX6+VK+mYgABa/goNpa+urs1/PgAbNmVDo9HBWCLCj//LwN+mdoCCazKxdogDHcasUEFRDb5fm2b09u9/Skf8xCB4edafmXB0kBsNcgBAJ4pwdDDMLoiiiO3bt2PJkiXYuHEjdDfc2cvLCw899BCefPJJREZGtuwXEEUgLw9IS6PgJivLEMw4OACxsYYgJSqKggRfX7r4+NDMyM2zLgAQFNSycZhCaChdbqZWUzCnp9VS3o9WS79/VhZw+DDd5ukJdOsGjBvXrKc8nlDc6L9rcUktsrJVCAtxMn4QYzaKAx3GrNDegwVGP70DFLDsPngNd08Jrnf9sEE++GRpstGCejodMOr6bI5Go8FTTz2Fr7/+GjExMVi6dCnGjx8PR0dH5Obm4ocffsC3336LL7/8Ej/99BOmTp1qfEDiTR3a16wBLl269TgfH6BDB1oi0gcykycbf1xrYm9fPziTy4EXX6QZncxMWvLKyKAAsLjYsDwH0Ou3axcQEQGEh9M++RvImjFTI+Md9ayd4kCHMStUXqmBTCYY7XoukwmoqNDccr23pz3uu7sDfvglo8H7TZ8YiOBAR4iiiKeeegrLly/H8uXL8dBDD0EQBFwrrEF5hQZRUd3wf//3f3jjjTcwe/Zs3HXXXdi8eTPGjh1reLCqKuDKFeDyZSA1FXjySZqtASi35upVw1JNhw40G2PCZF2LJAiUrOzlBfTqRdfV1FDgc2PuT04O8NdfdHFyArp0oRmfiAhAocCQAd64eLncaPAb4Kfk3Ves3eJAhzErFBHqbDTIAWgnVkSoc4O3PfZgBJydFFi1LgMVlRQMOTnKMXN6B8ydRTuYduzYga+//hrLli3Dww8/jPNJZfh8eQrOJpYBAOztBEwaE4D5cyPx008/4Y477sDs2bORduIE7FJSaEdTVhbqnXmvXKGTMwAMHgyMGHHLzAQDoFQCHTvWv87OjvKWkpIogDx1ii5KJRAdjfje/fDzbwpUVGoaXMJ6+N5wrgbN2i2uo8OYFdJodLj74SMoLlXfcmKTyQAvD3us+3ZQo8mnNWodLqWUQ6cDOnd0qZebEx8fj9TUVCQkJCDxcjmeeikBWm39AnwyGdApwgVffNAbl5LO48FevbB6xgx00wczAODvTzk2UVE0e3Obu4vaPZ2O8poSE+lSXk7Xz56NFJkfXnnvPLKyqwCZDKII2NvJ8PjsCMyM7yDtuC1YZZUGv27OxqYdeSgtr0V4iBPuviMYIwf78JZ8M+M6OoyxOgqFDItf7Y5nXz2D6hptXQAikwEODnIsfqV7kztslPYy9Ozqfsv1WVlZ+OOPP/DFF19AEAQs+fZK/SBHFOFVU4TI8lQUlPpg+54g3DG+JwLj4nDkxAl0mzYNiI4GOnemnVGs7chktFwVEQFMmkQ5PUlJQEQEOgoCVi8dgOSl61CWeBU1Mf0Qc88guLgppR61xSorr8WTLyYgLbOqbvLxTHkpEs6VYvrEQPzzyU4c7NgADnQYs1LdOrth9dL++G1zDg6foB1Lg/p6YfqkQPh4tf7klpiYCJ1Oh3HjxqGgqAanz5cCAJxrKxBVloKO5VfgUVMCAMh2DsaW3TG4Y3wgBk+ahH999hkeeuCB2/7dWDMIwi07vGQC0Lk6A/CuBDL3At+cBPr1o4tzw0uZ7dnS71ORkVVVb4VVH9D/tiUHcf29MHSAT8N3ZlaDAx3GrJiPlxKP3B+OR+4Pb7PHVF0vuOfk5ITKSi0iyq6gc1kygqqyIVw/I2hlcmQ4hyDZLRKK8loAgKOjI8qqq9tsHKwVBAF47DHg5Eng2DFa2tq9m5KYe/akIone3lKP0iJUV2uxZVcutEa25ctkwG+bczjQsQEc6DDG6vH09AQAZGdno2s3X/SsvAyfymwAQI5TAJLdopDmEgq1XAm5TMDocOqNlZOTU3dfJiEXF2D4cGDIEODCBarNk5VFyctyOXDHHVKP0CIUlqihrjWeoqrTARlZDVcRZ9aFAx3GbtPJsyX4aUMGzl0sg72dDKOG+mLm9A4I8HOQemgto9UCFy9iwMWLCPH2xg8//IBPPukD3zuGI2H7RVxyiUK5ff2KvVqdiDsnB6G2thZr1qxBfHy8NGNnt5LLaRanZ0/K5TlwgIIfPX2vMD8/6cZ4k6wcFX7dnI2Ll8vh5KTAqCG+GD3MF/Z2bb87z83FDjIBMFJSCoIAeHvatfnzMvPjXVeM3Yb/bczCJ18lQy5D3RS4XAY4Osrx+eJYREVYQSfwykrg+HG6XN/F82VyMhZt3IiMjAzI5Y74+6tnkHi5vK7buVxO58jHZ0fgwRmh+PnnnzFz5kycOXMGPXv2lPgXYs2ydi2VAejdGxg9mmaCJLTzr3y89eFFiKDEd/17LSrCGf99NwZurm0fdLz87jnsP1potKr0or93wZSxAW3+vKxhpjp/c6DDWCtl56ow87GjDRZpk8mAyDBnfPefvpa7a6OggJY1EhIAzfXigi4uQN++SPf1RbdBgzB69GisW7cOEBTYsTcfW3fTFtyOYc64c0oQekS7IykpCUOHDkW/fv2wefNmSX8l1kw6HbBuHS1tAVSxecgQqm9kZ/5ZjJy8asx67GiDFbtlMqrW/eYL3Rq45+3JyK7CYwtPoUqlqZerIxOAnt3c8enbvWBngtkk1jAOdJqJAx1mLt+sSsUPv6Q32mNo+Sd90CWqZQ0azaK6GvjwQ0OAExREHbq7d6+rdbN582ZMnz4dw4YNw0cffYTY2Nh6D6FWq7F+/Xo8/fTT8PX1xV9//QVvTnS1LhkZwNatVIkZoHIAY8fScpcZA/SvVl7Bj//LMPp/SSYDNqyIg7dnA/3NblNmtgrLV1/Frv3XoNWKcHNV4M7JQZg9IxRKJdd9Mieuo8OYhcnObXqHUXZetWUEOqIIXLtmyMdwcKCTWVUVfYoPDb3lxDZp0iRs27YNDz74IHr37o24uDiMHz8eTk5OyMnJwU8//YTc3FxMmjQJq1atgpeXlwS/GLstISHAI48A588DO3ZQ1/X166kBab9+ZhvG5SuVjTeb1QFX0ytNEuh0CHLE6//sikV/7wKVSgsXZwXkDdSgysxWIeF8CeQyAf1iPeHrzfWJrAUHOoy1kpen/fVlKeOTol4ebf+HuUVEkXpK7dlDFXXnz6dqxQAwdWqTLRhGjhyJ1NRUbNy4EV9++SW+/vprqFQqeHh44K677sL8+fPRo0cPk/8azIQEAejRg4o8Hj4MnD0LxMSYdQjOTnLIZGg02HF2Mu3pyt5O1mDSc2WVBu9+chH7DhfWXScTgCnjArDwiU68tGUFONBhrJUmjfbH2l8zG7xNEAB/XyV6dpVw+TQtjTpep6XRz3I5kJ1tCHSa2WdKoVAgPj6ed1TZOoWC6uwMHmx4b+h0wKZNwIABJt2dNXqYH3b+dc3o7QF+SnTuaP5kaVEU8cp753HybEm963UisHF7LnQ6Slhmlo1DUcZaKSrCBTOnBwOov+ojk1H38Bef7iJNI8XcXGDVKuC77yjIUSjoRPX3v9MOG8Yac2MAfOwY7cb76ivg0CEYbY9+m4YM8EbPrm5GY++nH+koyf+lC5fKcfx0SYMzTaIIbNqZi9x8LpJp6TjQYew2LHikI15c0BkdAh0BAAKAAb298MX7segfK0HxPI0G+OEHIDmZTlj9+gHPPANMnsx9p1jLde1KPcu0WkpaXrOG8rramEIu4KM3e+GOcQFQKAwBTXCAA957uTtGDPZt8+dsjoPHChvM19ETReDIySIzjoi1Bu+6YqwNiKIIlUoLhZF1fpNSq2lLsH5a6cgR2k0zejTACcLsdokicOIEsGULBdLu7sDf/kaJzCZQVlGL9EwVHB1kiAxzlrQ8w9Lvr2DNhkxotQ2fJgUAzz4RhbunBJt3YDbKVOdvntFhrA0IggAnJ4V5gxxRpBo4//0vFX7TGzCATkQc5LC2IAg0M/joo9Qnq7SUlkVPnjTJ07m52KFHtBs6hrtIXoMqpru70SAHoG0IMd3czTcg1ioc6DBmjTIzgW++AX79FaiooDwKPUstUMisW0AANQzt0YMS24OCpB6RyQ3o7YWwDo6QN3CmlMuAvjEe1lH9vJ3jpSvGrIlKRfVOTpygn5VKYMQImsVR8CZKZgaiCBQV1e+CLoo2G2Dn5lfjH/86g4xsVV2+jlYrolsXV/zfaz3h7sb9sNoKFwxkrL1LSgJ+/516UwFAbCxVsZW4R5HF0ekoIKyupq8qFVBbSwm1Wi3lmWi1dKxcrt8mR9/b21MxxRsv9vY2exJvFUGoH+RkZgIbNwL33GOTy6UBfg5Y9UV/HDpeiFNnSyCTCYjr54XePT0kX1pjzcOBDrMIoiiitIzaEbi7KfgPSENkMgpyfHyo2F9YmNQjkkZVFXXeLiykSr5lZfUv1W283VehoB1rbm6UiOvmBnh4AL6+9G/h5NS2z2dNRBHYvJlKGixbBsyaRVW2bYxcLmDoQB8MHegj9VBYK/DSFZPcjn35WPFTGq5m0LbVyDBnzJ0VhtFDpdlSajFEkU7mPjf8cb1wgbb7todlKo0GyM+nIoc5OdTCoqCg+dublUrA0dEwKyOX0+sml9f184JOR7M7+q+1tYbZoOpqw8xPY5ydqZheQADQoQNd3NzazyxQRQVtO8/Kotd31iwgKkrqUTErxE09m4kDHeuy9tdMfLY8BYJgqEWm//7Zx6Lwt6ntdNtmcTHw22/0SfnJJ22/Bo4o0uxMWhptjc/KoiDHWE8Ad3daPvH0NMy2uLkBrq60lOfg0OzKz42OSaOhE7l+tqi0lL4WFVHQVVLS8H1dXSngCQsDOnakYNWWA5/aWuqGnpR0W8FOanolTp4tgQCgX6wnQoPb8WxZO8SBTjNxoGM9SkprMX3OIaPbN+0UAn77IQ5uLu0o2U8Uadvu1q1UH8feHpgxA+jUSeqRtS19QuuVK9SLKz0dKC+/9TgnJyAwkHb4+PnRcpGXF70ulkCtpoBHP/OUkQHk5d0aoLm5UcCjvzg6SjNeU9JqgV9+oVIHLQx2Kqs0ePP/EnHweFFdPCiKwMjBPnjlH9FwdOAu4u0BJyMzm7P7wDXodMbjbI1GxJ4DBZg2IdCMo7pVZZUGVSotPN3toFCYsCJDeTnN4iQn089hYUB8PM1a2IKaGiA1lX6/lBSatbqRfstyaCjNhgQFWf4SkL09jTMoiJLDAZrd0Ac9qak0S1VWBpw6RReZDIiIALp1o8rDtpLjI5dTUL5uHZCYSCUPmhnovLr4Ak6coffDjR+99x0ugPjJRby7qLspRszaCQ50mGRKStWQyQSjMzoyuYCSUrWZR2WQnFqBpStTceR4EUQALs5y3Dk5CHNnhUNp38YBT3IysGEDJRsrFMCYMcDAgbe//CI1lYqWMy5coODmxpwXuZyq60ZEUFAXHEwVnq2dnR39PmFh1CSztpZmrFJS6N85P5++T0kB/vyTgoGYGOoeLrfymQu5nIpVHjwIxMU16y6Jl8pwLKG4wdt0OmDvwQKkZVQhLMRGAkJmdhzoMMl0CHJqtOqoVisiRKI1+ksp5Zj/QgJqNTroR1hRqcWP6zJw/mI5Pn67FxSN9MBpsaQkCnICAoC776YlGmtVXU2f6C9coKWpG4MbLy86sUdFAeHhlrMEZUp2doYlq/HjacnuwgXg3DnKwbp0iS4uLkCfPkDfvpSDZK3kcmDYsPrXVVUZnbk6cqoYchmgNZKOJQjAkVNFHOiwVuNAh0lmeJwPXF0UqKjU3NIUWRAAN1cFhg7wbvjOJvbfZSmo1ehuSbXQicDJsyXYe/Aaxgzza7snnDCBlmni4qxzR5VORzMUp09TjoZGY7jN35+Wabp1s+4Arq14edFMz9ChtJPs7FnKy6qoAPbtA/76i3bWDRgAREZa9tJdU0QR2LYNOH+eWkg0kHeh0+mLDRr/0NPYEjdjTbHCv6jMVijtZXjrxW544a2z0GnFuk90chkgl8vw9ovdYGfuBpkArhXWIOFcqdHbZTJg047c2wt0Ll6koGDGDHpAheLWT8HWoLCQcjHOnDEUMgQooOnZk4IbH649YpSvLzVfHTGCZvWOHaO8nqQkugQFAcOHA126WGfAo1bTcl1ZGbB6NfDQQ7Tt/wZ9enrg29VpRh9CFOkYxlqLAx0mqf6xnvj+v/3w8+9ZOHyiEAAwuL83ZkwLRkiQNFPVJWW1jd6u0wHFJY0fY5QoAnv2AHv30s8JCbRcYU1EEbh8GTh61JA4DVA9mZ49gV69aKeUNZ6YpSKXG2a9Cgoo4Dl5kpKaf/qJXs9Ro2j3nTW9rkolcP/91JctN5eS7WfMqPc7xHR3R3QnF1xOqYT2ppkbmQyI7eGBzh1dzT1yZkN4ezm7LTqdiK178rBhUzayslXwcLfHlHEBuHNykNVuCS2rqMXUB4xve5fLBIwe5ovX/9m1ZQ9cXQ2sX0/5GAAlG48fbz0JqDU1dPI9etSwY0oQ6OTbty/l3VjL72INqqqAQ4eAI0doZgSg5O2JEylx25pkZlLHc62WEu1vmr0sKlbj+bfOIim5ol4/qV7d3PDvV3vAzdUGktRZk7iOTjNxoGM+Op2Itz5KxI59124p+Ncx3BmfL46Fi7N1Thq+/VEitu/LN1qvbsm/YxHTvQUJo9eu0SfzwkJappo6lXbaWIPycjrZHj9uaK/g4AD07g3072+T/Y0sSmUl7WI6epR2cAG0lX3MGCpMaC1OnAD++IP+QNx//y1bz0VRxKmzJThxhgoGDujjhZ5d3bgdTDvCgU4zcaBjPtv25OGtjy42eJtMBsyY1gFPP9LRzKNqGyWltXjyxVPIyFYBIqVJ6neGzJ0ZikcfiGj+gyUnAz//TJ/K3d2BmTMp98LSFRcD+/fT8pp+55SPDyVM9+zZPnZMWZLycmDnTvr3AOj1HzkSGDTIesoQ/PEHBTwODsAzz9hODSHWJkx1/jbL/44lS5YgPDwcDg4OGDhwII4ePWr02BUrVkAQhHoXBwcHcwyTtdCGTdmQGfmwpdMBf2zNgUZjZErEwnm422HZx33w1MOR6BjhDH9fJQb188bHb/ZsWZAD0B9zUaTt1I89ZvlBTmkpdUn/7DM6KWm1VMTv3nuBp56iZSoOcszP1ZUKSM6bRwUV1Wra0fTNNzRjaA0mTaIdZdOmcZDDzMbk6wpr167FwoULsXTpUgwcOBCffvopJkyYgKSkJPj5Nbxrxc3NDUlJSXU/89SlZcrKVaGxXZ9VKi3KKzTw9LDOk6KTkwKz4kMwKz7k9h4oKIh2m/j7W3YOS2UlbW0+dswwgxMVRfkU7bVTuiUKDgYeeYRmdrZto4anX30FjBtHW9It+e+lQgHcd5/Uo2DtjMkDnY8//hjz5s3DQw89BABYunQp/vzzT3z77bd46aWXGryPIAgICAgw9dDYbfLysEdRsfHdR3YKAc5WmqNzW2praYp+4EBD0qglz+LU1AAHDgCHDxuSXsPDadtzaKikQ2NGCALlSEVFGdqGbN5Mie7Tp1tPE9iKCvr/YkFtTsoqapGTWw03VzsE+vNqgi0w6VlIrVbjxIkTWLRoUd11MpkMY8eOxaFDh4zer6KiAmFhYdDpdOjTpw/ee+89dO/ecK+Tmpoa1NTU1P1cVlbWdr8Aa9Qd4wLxn6+TGyzzJZcJGDvCD/YS1MGRlEpF9UIyMqjH0dNPW24BQFGkWj47dtAJB6CAbMwY6y9U1164ulJi7/Hj1Ag2JQX48kuqrt2K7uFmlZYGrF1LQc4jj0ieZ1RWXov/LkvBjr350FzfcdmtsyuemdcRPaKtuFI1M22OTkFBAbRaLfz9/etd7+/vj9zc3Abv06VLF3z77bf47bffsGrVKuh0OgwePBiZmZkNHr948WK4u7vXXUJCbnOZgTXb1PEB6NrZ9Za/T3IZ4O6mwKP3h0syLslUVAArVlCQ4+AA3HWX5QY52dnA8uXAr7/SuL29KUl63jxqVcBBjvUQBNr99sQTVG9HpQJ+/JFm6Cx5r4mXFyXzZWVRoCah6motnnopAdv25NUFOQBw8XI5nl50Gucu8gdoa2ZxH7fj4uIwe/ZsxMbGYsSIEVi/fj18fX3x1VdfNXj8okWLUFpaWnfJyMgw84jbL6VSjv+8G4P77w6p20ZuZydg4pgALPukL/x929G0b0kJ8O23QF4e9Sx6+GHLzGupqqJE42++odom9vaU2/Hkk9RJmwMc6+XjQzMjffpQgLNlCzUNvbHXmCVxdaXZQ4B2k5WXSzaUzbvykJpe1WDLF61OxNLvr0gzMNYmTPpx08fHB3K5HHl5efWuz8vLa3YOjp2dHXr37o3kGyuw3kCpVEJ5U0lxZj6ODnI8PjsSj94fgSqVFo4OMigUFhc/m1ZBAbByJZW59/AAZs+2vNoyokhtGrZupWAHoDo+Y8daVy0W1jh9jSZfX0pUPn6cmojecw/NMlqavn0pqToriwKzGTMkGcbW3Xn1aoHdSKcDEs6VoqhYDS9P69xY0d6Z9Ixkb2+Pvn37YufOnXXX6XQ67Ny5E3Fxcc16DK1Wi7NnzyIwMNBUw2RtQC4X4OqiaH9BDkCNGMvK6OTy8MOWF+SUllLe0IYNFOT4+dE477yTgxxbJAhU62jWLJqxu3KFqhLr87AsiUxGgZlMRo0/r16VZBjlFbc2Fr5ZpUrT+AHMYpn8rLRw4UJ88803+P7775GYmIj58+ejsrKybhfW7Nmz6yUrv/XWW9i2bRuuXLmCkydP4oEHHkBaWhoeffRRUw+VsdaZOpW29c6da1m7XUSR6uB88QX1ppLLaang8cd5N1V70KULBbQuLrSk+t13FJBbmoAAmtkBKDFegryizh1dIDdWFAyAo4MMft68cmCtTJ4pOXPmTFy7dg2vvfYacnNzERsbiy1bttQlKKenp0N2QzZrcXEx5s2bh9zcXHh6eqJv3744ePAgunXrZuqhMtZ8lZVU8EwQADs7YPJkqUdUX0UF5eLo+2p16EDbjn19pR0XM6+AAAp2Vq6k9iPff081nVxcpB5ZfcOH09Kqry+g0dD/KTO6a0oQtu/Nb/A2mQyYNiEQSqUF18BijeIWEIy1VEEB7a7q04c6SltaAu+lS1RbpbKScjZGj7auNgGs7ZWU0IxOaSkFE3PnUrd5S6JSAY6Okj396vUZ+OK7K5DLKX9bJqP8nJju7vjojZ5wsNImxdaEe101Ewc6zKT0u6vKygyfli2lHYJGQ1P/hw/TzwEBtMXdSAVy1s4UFxuWrzp0AObMMfvMiaW7eLkcGzZn48rVSni422HCKH+MHOzTPnMPJcCBTjNxoMNMpqKCgpyiItrK+9BDlvOpuLiYGofm5NDPgwbRjipLrePDpFFQQPWTVCogOpp2Y1naTF9+PnDunGXOljKTsuqmnoxZPZUK+OEHCnL0W8gtJci5dIl6HeXkUN7QffcBEydykMNu5eNDzVkVCuDiRdrSbUnUamDZMtrJeIVr17C2wYEOY03RaIA1a2jniqsrBTmWMFsoisDevbR1vLqaliOeeIK6QzNmTGgoLWkKAnD0KO3MsxT29pT7BgD790s7FmYzONBhrCnJyUB6OhVce+ABy6iTo1YDv/wC7N5NP/fvT0tplhCAMcvXrZuhKvHmzbRcZCni4mg5LTXVssbFrBYHOow1JToa+NvfKJ/hpr5tkigtpVyhCxeoNs706cCUKfQ9Y801ZAg1/tRogP/9j75aAnd3w6ykxD2wmG3gQIcxY27M0+/Rgzp6Sy0nh3IYcnMpR2jOHKB3b6lHxayRIADx8fQ+ysujlhGWon9/+nr6NM1eMnYbONBhrCGpqRRQSNho8Bb6Uv7l5bRlfN48rnDMbo+LC7UCAShfx0hPQbOLjKQl4poamrlk7DZwoMPYzYqLKf8lK8tyEiLPnwd+/JE+3UZEUP0eDw+pR8VsQVQUMHAgfb9xo2XMoAgCEBtLyf+W2n2dWQ3ef8qsTlauChu35SA1vQquzgqMG+GHfrGekDXSq6bZamuBtWup+WVQENWikdqxY8CmTbSU1r07fQLnreOsLY0ZQ9vNS0qAPXuA8eOlHhElJQ8bxrV02G3jv5bMqmzemYvF/0kCBCrPLpcBm3flYXB/L7y7qDvs7G5jklIUgT/+MOS/zJolfeXY/fup2jFAeQuTJllegTdm/eztgTvuoFnDQ4eAmBjpE++l/r/HbAb/xWRWIzm1Au/9Jwk6kYIcANBe/3roeBGWr756e09w/Dg1FpTJgBkzpN+qfWOQM2IENQ7lIIeZSqdOtO1cFA3vO0ug01FFZ8Zaif9qMqux/s9sGFudEkW6vUata92D5+QYqsSOHQuEh7fucdrKoUOGk82YMVwOn5nH2LEUTF++DGRkSD0aSrz/8ENg6VJaVmasFTjQYVbj3MWyuhmchlSptMjJU7Xuwe3tqatzly6UGyClI0eArVvp+1GjKE+BMXPw8qIkYMBQjFJKLi60hKXRAFevSj0aZqU40GFWw8mx6YJ4DspWFs3z9gYeeYQSfaWcOTl+nCrVAsDw4bRkxZg5DR9OxSevXJE+uBAE2hUG0CwTY63AgQ6zGqOH+RqNQQQB6BTpjAA/h5Y9aHW14Xs7O2rzIJULF4A//6Tvhw6l2RzGzM3Dw1CE8uBBSYcCwBDopKZKOw5mtTjQYVbjjrEBCPR3gPymd60++Jk/p4WVi0tKgP/8B9i1S/paHenpwPr1lGzUvz/l5XBODpNKXBy9/y5dAgoLpR2LvijmtWuAqpVL06xd40CHWQ0nJwW+eD8W/XvXb6oZ4OeAf7/aAwP6tKDZpigCv/1GfzhTU6UNKgoLqTu6RkM5QpMmcZDTUjU1QGYmkJJCl7Q0IDubmkIWFVlGETxr4u1Nu7AAqpgsJWdnwMeHvreEBGlmdbiODrMqPl5KfPhGT+TmVyM9swquLgp0iXJtebHAo0cpwLGzo7wcqbZtV1UBq1ZRwBUcTM1DeQt5faJI1arz8mib8bVr9HXoUNoODdCuuRUrjD/GkCHAuHH0vUpFuVCBgUBYGNdrMWbgQJrRSUgARo8GlErpxhIaSv/m6emGhp+MNRMHOswqBfg5tDwfR6+kBNi5k74fN452mkhBq6VWE8XFgKcncN99fNK9UWEhVem9erXhnmO5uYZAx9GRckuUSpoNq62lGTKNhr739DTc79o1w7+/XA6EhFBvpchIqobNgSaJjKSZncJCqpocEyPdWHr0oK7mltBYl1kdDnRY+yKKhn4+YWGGLslS2LKFZpXs7YF776Up+vZKFGlZQi6nmS2AAo6zZ+l7uZwq9fr4UBkAHx8KSvT8/YFnn2388fXs7YGePWl2oLSUAqmrVylXy8UFmDqVlhDbO0EAevWibeZnzkgb6OgDUcZagQMd1r6cOUMdmhUKYNo06XJhTp6kHlaCANx9N3Ujb29EkfJqzp4FEhNp1qZLFwr6AJqhGTeOAp/g4Nub7brx3zkggF5zUaT8nStXKOC8cgWoqKCZA73KSpolaq+9xXr2pEBH/9q4uEg9IsZarJ3+72XtVm0tfaIfNoym5aWQm0tNOgHaQt7eZg90OgpsDh6kDvF6Dg50IhVFCkwEgXJrTEUQ6D3g7U0ze1otzewEBBiO2b6drps8uX3mhnh5UZCZlQUkJQF9+0o3ltJS+r/j6yvdcjOzShzosPalXz86YUm1TKRWA+vWUe5I587ts+rxmjWG4m8KBXVk796dliaknDmRy4GOHQ0/63S0vFVSAqxeDURHAxMn0kxTe9K5MwU6V65IG+hs2kTB1pQpHOiwFuFAh7U/Ujbr3LKFdo+4ugLx8e1jG7lGQ/k2+iTfrl3pxDlgAM2kWGpukkwGPPEEsHcv9R67eJG2ro8YQXVm5K2swm1tIiMNy1f62TYp6BPKi4uleX5mtTjQYbZPFIE//qCdG1ImNJ4/T7k5ggDcdRfg5CTdWMxBFIFz52iH0/DhQJ8+dH1MDOV+WMMOM3t7yhOKiaGq1Wlp1Gz17Flg5sz2MbMQFER5SioVLR0FBkozDg50WCtxoMNs38WLFGCcPQv84x/SBBjl5RRsAbRcFRFh/jGYU14eLTWkpdHPJ05QWwFBoJkQM8+GlJ44h4Jd1M7AZ+xQuPfu1rIH8PMD5s6lZPZt2+jfU9dIh1lbIpfTDsVLlyhfSapAR79kWFIizfObSEWlBifOlKC2VodunV0RFOAo9ZBsDgc6rMVEUUR2bjU0GhHBgQ5QKCy47ohWS5/AAWDwYGmCHFEEfv+d+moFBQEjR5p/DOai1QJ//QXs20eBgJ0dBXb6lgJmVltcihP3PI3CPUdQ1zvk5Y/gM24I+qz5D+zcXZv/YIJAMzuRkVToUV+ttz3o0IECnZwc6cag3/FVWSndGNqQKIpY8VMafliXAbXaEDQPH+SNRX+PhqsLn57bCr+SrEV2/pWPb1ZdRWY29Zxxd7PDrPgOuP/ukJZXJzaHkyep4JmzMwU6Ujh9mpJv5XJpqzCbWkEB9evKzqafu3al5N0bt2ubUNnZJKR8+A3yft8FUaOB15C+qMkvRMWFZDpAaziZFO46jFP3PYsBfy5v+RO5utJFLyWFgll980lbpJ/FkTLQ0edyVVVJmyvURlb8lIblq9NuuX7/0UL8882z+PL9WMv8m2qFONBhzbZxWw7+/dmleteVltXiq5WpyM5T4cUFFrZNWq2mRFKAEkilKGFfWQls3UrfjxpFW2NtVWUlnQgdHWlnTI8eZnvqgj2HceyOeRC1WogaatBasPuw0eUlUavFtW37UXb6Itxiolv/xHl5wE8/0fPMmEE7s2yRPtApKKD/V/b25h+DfjZWo6ExSNmS4jZVVmnww7qG+3bpdMD5i2U4llCMgS3p38eMstGPlqyt1dRo8dnyFKO3/7E1F1fSLGxK+ehRKnLm5SXdttgdOyiJMyBAuhklcwkLoyKM8+ebNcgRtVqcnvsCdLWauiAHQNM5NDIZru08cHtP7uNDdZC0WprNkrrTt6m4uBhqHBUUSDMGe3uqZzRtmtXPip44XVJvuepmcrmAvw7b6HtJAtb9bmFmc+RkMSqrtEZvl8sEbN+bZ8YRNaGmhgrSATSbI8VW4Kws4NQp+n7KFKv/43yLykqqL1NUZLiud2+zb98v2HUI1Vl50iQHy+W0gy48nGYZ1q+noMcWWcKupwEDaPeeNezYa0Stpun3qrq2nSS7m4GN/eVlplJeqWn0dkEAyisaP8as7Ozo01+XLrSV2dxE0VD9OCaGGkfakoICYNkySlDdsKF+LykzU6W3Mm9Ep4PP6DaYZZPJKPfKwYGCW/1yqa3RBzo2tutJCt06N/5hQKsV0TNawnpfNoYDHdYsEaGN71bS6kSEh1hQ4TeZjJZP7r1XmpmU06fppKdUUh0WW5KdDSxfbui6Pn26pImhDsEt7xMmyOXwGTcE7rFd22YQ7u7UDBSgXWf6hGxbYgkzOllZ1KtOpZJuDG0g0N8Bw+N8GvzTJJMBHm52GDuiHfa/MxEOdFizdO3kiqgI57odujcSBMDeXoYJo/zNPzBLVFtLnbABKpRnS40QMzOBlSvpRBMcDDz6qOTbrH3GDoEywKfJYEuQy+u2mHuPGoQ+a/7TtgPp3p2Ca1E0LFnaEv1Os4oK6cbwv/8Bq1ZJlyfUhhY906VuZkcuFyCX0/vXzcUOH7/VE44O7aTythnwrivWLIIg4K0XuuGplxJQUlZbt1IhlwEymYC3X+xmGXUfRJH+EEZFUQKyFLtDjh0DysroU/7AgeZ/flPJygJ++IHyn0JDgfvvt4idLzKFAr2WLcbx+PmAKELU58jIZYBWh64fvASvYf1QsOsQBAHwGTME7n26m2YwY8bQzqvuJnp8KTk40NfqaunGoM/DsvKt5QDg6qLAF+/H4nhCMf46Ugh1rQ49o90wdrgfHDjIaVMWcGZi1iK0gxNWfdEfv2/NwV+HC6Cu1aFPTw/cNSUYHYIspJrn5ctU1yQry9BywJyqq2npAqDt5FI2qWxLokidvGtqKPH2vvukCSKN8JswHIP3rUHyB18j/8/dELVaeA6MRcd/Pgr/qWMAAB79zJCr5elpWOKxNY7X/49LuWyk/4RlA4EOQB8SB/TxwgDeRm5SNvJXmJmLu5sdHpwRigdnhEo9lIYdPkxf+/aVZrbh8GE6Efj5Ab16mf/5TUUQgHvuob5V48dbVJCj59G/F/r98jnE6ydDQeqToU5HgaGjhXwIuF2WNKNjazsYmUlxoMNsR2EhdVgWBOqKbW5qNdXuAWhLu639MXZyMiTctgFtjRqlx85AV1sL99husPNsXgVlUaeDrlYDubLhYEvyAAegvmpbttAyVhu+ZpLSl2iQssdXbS19tfLt5cy8bOwvMWvXTpygr506GRoAmlNCApWn9/Sk9ge2YM8ew+vaRkRRROp/VmBnyFAcGnU/joyfix0hQ3Hu2behrVEbvV/5hWScvH8hNrv0xBaXntjddTzSvloD0RKbazo7U52hCxdsr/mnVKUERJFmyADD7BJjzcAzOsw21NYadrr062f+59fpgEOH6PvBg21jNicxkQIdAPD3p8aOjdDWqJG9+ndkrvoV6mvFcO3eCWHz74P38AH1jkv5v2+Q9MpH9a7T1aiR9uWPqM7MRb91S2557JLjZ3F4zIPQqdV11Y+rUtJxbsEbKNh1CNHv/RNOkSFtNpsjiiIK9xxG7vpt0Kqq4d63B4Lvnw47t2buoAsPpxmwqiogPZ1+tnb611aqQEetNjy3BSTBM+vBgQ6zDUlJlBvj7i5Nc8VLl6i+iJMTEBtr/udvaxUV1HEdoM7jTQQ5mopKHJnwEEqOngZkAqATUXk5FTnrNqPTq0+h8+vPAABqyypw+e3PG34QnYi833ag5NgZePSvn990bsEb0NbU1GvMqT/p5a7fitz1W+ES3RFd3l2IgGljW/c763+Xyiocv3M+CncfhqBQABCRuXIDkv71Cfr//jW8BjcjyV0mo/fhmTPA1au2EehInQgsl1P7h/Jy20nyZ2ZhAx87GQMtF/XsSbM5UsymHD9OX22gPD0A2mGlUlEzx7FNBw5Jr32KkhNn6QcdnRD1My+X31mCgt2HkLNhGw4OnwVddY3RxxEUcuT8b0u96youpqD0xLn6QU4DKpKu4MTdTyF77Z9Njrcx5595C4X7jl7/Ha73zxJFaMorcWzqPKiLSpr3QAEB9PXatdsaj8VQX19WlCoRXaGg/18jRtjMritmHhzoMNsQHAzcfTcwbJj5n7u4mKq1AtI1D21LV69SZWdBoETaJvqEaVXVyPj2F6OBiKCQ48zjr+LkPU+jIjG58ecWBGgr629frs7Jb964r884nF/4LnT6pNUWqskvRNbq3xv+XXQ6aMorkbny1+Y9mL5Tva0EOvrdVpwfw6wMz/8xdrv0ybpRUdZfQ0WnM/To6tsXCApq8i7V2fm3BCc3EjVaqFIzrz9+4/kdYq0G17bvx6ExD8KlSyRUmTkov3C52cMHAHV+IYr+Og6f0XEtuh8AlJ48V78D+s0EoPjwSQBzm34wfcXowkJ6Xa09b0ufCCxVfkxBAS1beXnREjVjzcSBDrN+J07QjI6/v/mntHU6mv0ApClQ2NbS0oD8fKr9MmZMs+5i5+HapkOoSklHVUo6iq4vH7VGbUlZq+4nM7JlvY4gg7y5J3oPD2roqlAAGo1F1h5qkaoq+ipVXaATJyjhf9AgYOJEacbArBIHOsy6VVQAGzfSssXChYCbmTv+pqfTp0wHB6BzZ/M+tylERACPP07Lcc08odl7e8Jn7BAU7j4EsYk8GnNx6dq6hHTPuD5QuLtCU1re8AFaLfynNS8AhCBQV3NbUVpKX839f0yvqIi+entL8/zMaln5XCpr95KSKMgJDpbmD/DZ6wm43brZzk6QwED6fVogevHzEOztcUvXV7kccidHwEwTbYJCDq9h/eDatWOr7i93UKLzvxY0/NhyOVx7dWl+oGNr9IGOmZeNdDodysvLoc2/nqvFgQ5rIRv5y8zaraQk+hodbf7n1mqpIBxAO76smSjSrppW5l+4x3bF4L1rkPjSByjcRfWEZA5KdJh9J1y6RuHCP95py9EaZR/gi5jvPmjyuNIT55Dx/XpU5+TDKSwYIQ/9Da7dOwEAwp+ZA51Wi8tvfw5tRVXdfXzGD0Xst/+GrCW76srKqOSALQTBZdeXA80Q6Gi1WmzZsgVffPEFtm7dCp1Wi1cABPr6QuHsjJmPPQZ3ztNhzSSIolTVn0yjrKwM7u7uKC0thZtUU6zMPDQa4P33qVjgE08YtvOaS2oq8P33VAX3ueesO9k0JwdYvpwCtmnTbivXqSavALXFpXDoEACFizO0NWocGT8HxUcSmtwifjtkDkqMzdgPO4+G/9+LoojstX/iwnPvQZ1fWHe9IJdD1GrR+a1n0WnR/LrrNZVVKNx9GNqqarj36Q7nqLCWDUgUgXfeoYD4H/+w7gRaUQQ++IBKDjz+OM36mUhKSgqmTZuGCxcuoG/fvnjggQcQ5uiI8E2bkJiSgtmJiXB0csJ3332Hv/3tbyYbh1REUURmjgpVVVp0CHKEs5MNBMnNZKrzd/t5BZntycigIMfFhRKRzU2/pTwqyrqDHIDaV2g09HreZkK30t8HSn+fup/lSnsM3PwtLr/3Ja4u+aHeLElbEeRyhD56j9EgBwASX3gfqZ9+d8v1opZ2WV167VO49YqG/5RRAACFsxP87xjd+kGpVBTkAPQetWYVFfT7yGSGbfMmkJqaiiFDhsDNzQ2HDh3CoEGD6IYzZ4CcHPSePh0jJ07EwoULcc8992DVqlW47777TDYeczt6sgiff5uCK2n0f8TeTsDksYF48qFIODk2XuaBGWeWv85LlixBeHg4HBwcMHDgQBw92vhuil9++QXR0dFwcHBAz549sUm/3ZWxG6Wk0NeOHaUpIHb5+rbnTp3M/9xtSas15BrFxJjkKeROjoh+ZyHGXzuG2FUfwTEsuN7tyiC/ph9EJqNcn5vygAS5HHbeHuj4z3lG71p86FSDQU79QcqQ+ul3qLiYgqL9x1Gdldf0mBpTfj2h2dm5yVpEFk+fH+PlZbJlOFEUcffdd8PV1RX79+/HwIEDsWNfPua/cAqvPLMTv/yRiR2XZHB188Pq1asxe/ZszJ07F5cvt6z8gKU6crII/3zjLFLTDR8E1LUift+ajedePwONxjIS/a2RyQOdtWvXYuHChXj99ddx8uRJxMTEYMKECcjPb7gI2MGDB3HvvffikUcewalTpxAfH4/4+HicO3fO1ENl1iYtjb5GRpr/ucvL6Y+/IEjz/G0pNZW2Dru4UNBoQjKFAsEz78Coyzsx5OAv6L/xG4xK2oExV/ag8+tPQ3HDjIzc2QmC/fWTqiDAd/xQ9P9jGfynjTUEtoIA75EDMeTAz3AINj6rl/HdulsTpW+m1aFw31Hs7TkZh0bdj50RI3As/nGoMnNb98uWlNBX17bdfi+JvOtBn18zAtJW2rdvH06dOoWlS5fC19cXH3x+CW/8XyLOJ5UhQRmJTc6DsPSEM+Y9dxKl5RosXboUbm5u+PLLL002JnMRRRH//SYZIm5tJabTAWcTy/DXkcIG78uaZvIcnYEDB6J///74/HPqb6PT6RASEoKnn34aL7300i3Hz5w5E5WVldi4cWPddYMGDUJsbCyWLl16y/E1NTWoqTGUlC8rK0NISAjn6LQHGg2QnU1T6eau7XHhAvDzz5QX9MQT5n3utrZ7N7B3L/Xoio+vd1Nlchqyf/oD6oISOHeOQPB9UxtdHrpd2ho1KhJTIFPI4dK1I3TqWlRn58PO0w32Xh6oSsvCsemPo+L8ZZrhEUVAFBE06w70WrYYciN1cA5PmFuXJN0SgkIOZaAfhh3bAHvvFhaDbOR1tTpr11KT13HjgCFDTPIUM2fOxOnTp5GYmIgDxwrx0tvnGzxOLgMmjvbHor9H48UXX8TXX3+NrKwsODk5mWRcpiaKInb+lY83/u+i0WNkMmDoQB+893J3M47M/EyVo2PSGR21Wo0TJ05g7A29cmQyGcaOHYtDhxr+o3Po0KF6xwPAhAkTjB6/ePFiuLu7111CQkLa7hdglk2hAEJDpSlglpFBX23h/ZZ5vWrxDY07RVFE4ksfYE/X8bj8zhdI+3oNzj/7NnaEDkPeHztNNhS50h7usV3h2qMzBLkcckcHOHcMhb2XB3S1tTgyYS4qk67QwTpd3cff7J834fyzxnd2OXYIhKBo+fKRqNGiOisPaV//1PJfRv8eaaIhqsUTRbO833fv3o2ZM2dCEAT8tjnHaNqbVgds25OPKpUWs2bNQklJCRISEkw2LlPKzlXh0YUnGw1yAHqrV1S0rq0JM3GgU1BQAK1WC/+bEkX9/f2Rm9vwdHBubm6Ljl+0aBFKS0vrLhn6/5CMmZKtBDqi2GCgk7Z0Na58tJwO0Woh1moAUYSuugYn7nkG5Rea6FllAnm/7UBVSnrDLRp0OmSuWIeavIIG79th7l2Nt3ZojE6H7NW/t/g+yMq6/uRWHuiUlFAyslzerJYgrVVWVgaf620zMrNV0F1PSQmuzETX4kS4qUvrjq3ViCgqVtcdX1bWskrYVSotEs6V4PT5UtSopcl9qarSYMGi00i+UtHksXIZEBVh5QntErLyrSKAUqmEm5tbvQtrB7ZvB/7805AkaU46HW3HBqz/JFZbC/TvT8sr1/MvRJ0OKR980/DxoghAxNXPV5ptiHoFOw9BaCQRVtRoUfTXsQZv8xraD6GPzWr1c9eWVbb8TuPHU/6WCfNazOLqVfoaFGTSekDOzs4ov57A7eNtD9n1NKwupZcQl38Y4eVpdcfKBMDdza4uwHFp5q42jVbEVytTMe3Bg1iw6DSeeikB02cfxKp16TB3pZXNu/NwraCmWRUXdCIwfaLpgkxbZ9JAx8fHB3K5HHl59Xcv5OXlIcBIzZOAgIAWHc9uX22tDiWltdBoraik0pkzwLFjhkaD5lRURDuV7O2tv4mnvT0wdizlkFxfK6jOzkd1Zo7Ru4gaLQpake/SGrXFpcha/TvSvlqDmvzWJ2MKgoAen7+BXl+/C5duUform3tnuMd2bdkTymTUFHX2bOsvPaAvo2DiRPX+/fvj999p5mzK2EDoREAQdQiqovdithPV7pHLgKEDveHqosDvv/8OBwcHdO/evNyVj764hFW/pKO6xhBdVFRqsfT7VHz9w9W2/YWacPBoYZMVw2Uyepu++HRnhIVYZw6SJTDp/0B7e3v07dsXO3ca1vR1Oh127tyJuLiGOwvHxcXVOx4Atm/fbvR41nr5BTV479OLGH/PftzxwEFMvu8AlnybgsoqjdRDa1xlJe16EgRp6ufoA3FfX2m2tZtYc3JZWlQduBVEUcTlxV9iR8hQJMx5HucWvIG833dA1Bh/bwoKObyGDzB+uyAg5KG/YcTpP9Hrm/du3d5ifDCoTE6DprLt6/9YPJ3OUMYhqnX9w5pr/vz5OHLkCOV1DvdF3xgP+NUUwF6rRo1ciUIHb8hlApydFXjyoY7QarVYunQp7r33Xng24wNHelYV/tiWC2P/6qv/l4HiEnXb/lKN0GjEJt+Cwwb64PvP+uGOcaYr0NgemPyjxsKFC/HNN9/g+++/R2JiIubPn4/Kyko89NBDAIDZs2dj0aJFdcf//e9/x5YtW/DRRx/h4sWLeOONN3D8+HEsWNBw/xnWOvkFNXh04Uls3Z2PWg39b6uq0mLtb5l4+uXTUFW3Mp/BHPT5Wl5e0nSE1i+XWfuSBEC5FyUltIPtOqW/D1x7djEexMll8I8fZ9JhXf1sJS699il0Nc088cgEhDw8A0q/5vVByly5vkUzLZXJabi6ZFXzDr58GTh61NDt25qlpwPV1dTGwoT5OQBwxx13IDw8HAsWLEBtbQ3+7/WemBenhYODHNlOQZDbyTFupB+WfdwHHYIc8c477yA9PR1PPfVUsx5/78GCRv/JtToR+824hTu2h3vd8lxDHB1keHVhNCLDnM02Jltl8kBn5syZ+PDDD/Haa68hNjYWCQkJ2LJlS13CcXp6OnJyDNPkgwcPxurVq/H1118jJiYG69atw6+//ooePXqYeqjtyvLVV1FaqoZWV/8jhU4HXL5Sgd+2ZEs0sma4do2+SjGbAxi6KPv4NH6cNTh1Cvj0U8p3uk4QBHR+45mGZzzkcihcnBH+hOmq0erUalx+d0mTxwlyeV2wEnz/dHT/5JVmP0d1Vh7qsl2bNSgd0r9pxs4rUaT8sU2bgOPHm//4lkrfy61TJ5Mvwcnlcvz88884c+YMJk6ciKLCfEwMLsW9d3bAy59Nxo5fhuLVf0TD21OGV199FW+88Qbeffdd9O3bt1mPX6XSQtbIDKwgwKwf8KZNDIK9UtZgsCMIwN+mBsPRwcoLTVoIs7SAWLBggdEZmT179txy3YwZMzBjxgwTj6r90mh02LYnz3gSnAhs3J6LWfEWuqOo8PqnLqm6GJuxuaHJ6ZNLtfX/wAdMG4teyxbjwsJ3oSkz7ApxiuiAPmv+02hxvttVevICaotKGz3GI643AqaOhszeHn5TRrW4D5VTxzBUpWW1qPdWTc61pg+6eJFm/JRKSvK2ZlotoC/Uaqamtf3798f27dsxbdo09AgJwdIuXdArJgaV42pQcegANm/ejGXLluHatWv497//jRdeeKHZj925o0ujeYiiCHSKNN/OJm9Pe3z0Rk+8+PY5VFRqoZALEAFotSLGjfDDI/dHmG0sto57XbVDVdVa1NY28h8eQHGJBdds0Ac6Xl7SPH/p9ZOwLezw07cmaCD3JWTOXQi6ZzLyN+9FbWEJnLtEwGtYfwgmzksStU1/qlZl5KDDnLubvVR1s9B5M1GwfX+L7tNkmwpRpAKBADBwoDT1ndrSlSu0/ObsbNbq34MHD8bly5fx+wcfIPPrr/Hn+fNYsXo1AMDNzQ1z587FE088ga5dW5YgPmygN3y87FFUor5lMk8uA0KCnRDbw7wfXmK6e2DDijjs3JePy6kVcHJUYPQwX3TireRtigOddsjZUQEXZzkqKhs+oQgC0CHQgv9I63MfpJjREUVDDyNbmtExkuQrd3RA4F0TzDggQLBr+s9STWYu9g+8C0P2N976wZiA+HEInDkFOWv/bPpgAJAJCGtqe3piIuWP2dsD+maU1uzMGfrao4fZd455enpizuLF0L32GtIvXMDTggBHR0eEh4fDsZUBpEIhw/+93hPPvHIaFZUaiCL9rRNFwMvTHv9+tYfJg/iGODrIccd4TjY2JQ502iG5XMD0iUFYsyGjwTQFUQTiJ1vwf7wnnqD6L1I0SlSrDcs8Vlpyvh59HyZ9XyYTqErLgvpaERzDgqH0bXoWTm2k6N/NanKvIfHF99F71cctHpMgCAi8a3zzAh2ZDB4DeiH8qQeNH6NWA1u20Pdxcdb/3qiqMuTnmKjRa3PIHB0R3rcvwtvo8TpFumDtNwOweUceTpwphkwQMKifF8aP9Ofu4DaMA512as7MMJw4U4Kk5PK6nFOZQIWpxgzzxYSREiX6NpeJtzcbpa/bI5OZtHia2fj60tfCQkrObcNP7qUnz+P8P95B8cGTdIVchoD48ej+yStwCDS+DGTv17wkb1GjRc7/tqLHknLYube8caauuukdXXIXJ0Qtmo+IBQ9C7uhg/MB9+yh3y8MDGDq0xWOxOAkJFNAHBZl8t1WDqqsBh0Ze79vg5mKHmfEdMDPeyot9smazgb/UrDWcHOX4/L0Y/LEtBxu356KwWI0OgY64c3IQxo3wg6yxfY/tmT7QcXCwjRo67u4UNNbWAsXFzV4OLD1xDmnfrEVF0hUo/X3Q4cF4+E0aAeF6oFR25iIOjrwPOvUNwYRWh7zftqP0xFkMO7oBdp4NL/15DOgFp46hqErNoMi7EaJGg2vb/oLHgBg4hQU373e+zr1P00Xmun34MkIfacbGiL59KQm5b1/pgvC2IoqGHWP9+knz/MuX0weJO++0jTIOTFIc6LRjDg5yzJjWATOmWdEnm/R0SvgMCQFGjjT/8+sDHSnq95iCINBreeUKvbbNCHQuL/4Sl177FIJCTv2j5HLk/m8L/O4Yhb4/fwaZnR2SXv8Uorr2ll1NokYLVXoO0r5ag6iXGu76LggCei59G0cnPwJR13TxylP3/QMA4DWsP3r89zW49ujcjF8ccInuCO8xg1G098itfbDkMti5uSJo1pRmPRY8PYH7TLfl3qySk6mEglJJ+TnmlpVFJSQUCttI+GeSs/La5KzdKS2lSq1paU0fa0q2MJujF3g9Hys1tclDC3YdwqXXPgUAQ3BwPWcp/889SPnga2gqq5C/aY/x3VM6HbJ+/K3R5/EZOQiD966BW+9uzfoVAKD44EkcGD4LFZea/j30eq/8EM6daUcR1eURAEGAwsUZ/f/4BgrnRnJtRJECRFtz8CB97dNHmoBeP5vUvbvJlq9Y+8IzOsy66GdUlEppnl8f4Ji5AaBJdekCHDgAJCXR7qtGco+ufr7SMJNzM1HE1SWrEPLwjCaXnGpLypsclkf/Xhh6aB2Oz1iA/D92NXm8qNVCp6pG8uIvEfvdB0aPUxeVIOuHX1F2+iLkrs7o/ukrqLlWhPyNuyHW1sIzrg86PBhvdGmtzr59wO7dwJAhwDjTVoo2m6wsCnhlMml2jqlUhto9UiybMZvEgQ6zLlIHOnq2FOiEhNASQVkZtS9opD5J6cnzDQc516mvFUHU6WDv6wX1taKGD5LL4dbMJpmCXI6+P3+Gk/f9A3kbtjV5vKjRIvvnTYhZ/u+6fKEbXdtxACfufgpaVTUEOd2e9sUq+N0xCn3W/Adyh2a+ry5epCAHMCR02wL9bE7PntKUT0hIoGDb3x/oYEVL6syi8dIVsy765FapcmT0W9qbUdTOaggC0KsXfX/gQKNBnMKtiUJmggA7NxeEP/WA8eU9rRbhCxrZqn0TmUIB125RzaqvAwCiuha62ltze6qz8nD8zvnQVlcDoghRo60L2vI37cHFlz9s3oDS04F16+j7/v2B2Njm3c/S5eUZtpQPHmz+59fpqEcYQK+rLS0PM0lxoMOsS91eeIneuvqcgepqaZ7fVAYNot1CmZk0q2NE8H3TjL72glwO34nDoXB1Qcfn58F30gi64frMib4retQrT8JvwvAWDc+5UzjEBoKXWwchwCkiBHLlrYFw+rK10NXWNrysphOR/s1a1N7Q7qJBWVnA6tU069C5MzBxYjN/AyuwYwf9/+reXZo+csnJtPPP0dEQeDPWBjjQYdZFX+FQqk97+kBHo6Et2bbCxYXaFshkhu7sDQh7/F44hgTWBS11ZDIIdnJ0efNZ+tHeHv3Xf4G+65bAf8poeAyMRdB90zB430/o8sbfWzy8gOljIWvmslL4M3MavL7o4MlGe1vpqmtQfjbJ+ANnZAArV1KQGxoKzJghTdFKU7h6lQJcmQwYPVqaMXTqBNx7LzB+vO3samQWgXN0mHWROjdGqaSTgU5HJzxrr5lyoyFDaKdNIz3E7DzdMXjfGpx75i3k/b6z7t/DvW93dP/kX3C/YZeUIJcjYPpYBEwfe1vDEkUR555+C7rqGuMHyWWAVoegWXcg/Mn7Gz7E0cFQFfP64xZDiwpoYQ8B3lA0nqNTUEA5YuHhtJXcVv7t9R3XAaoDJFWzXEGgxHjG2hgHOsy6REdT4mygRC0qBIGaHJaXU/Kua8sr8losR8dmNaJ0CPJHv3VLUJ17DVVXMqD09YJzp3CTDav4wAlkrfrV6O2C0h4B08Yi5KG74TN2iNF+Rf7TxiD/z92oFnXYK5Zjk64EKTAETy6CAo+s/AbzXZ5El4ZOuL17U2uHyEjbCXIA4PRpWpKztwdGjJBmDE3s9mPsdvDSFbMuISG0xBIaKt0YPD3pqwn7Q0kuNxf4/Xc02AztOocAX3gN7mPSIAcAMlf9dutS2Q3EGjU6PvcIfMcNbbQpY/C9U5HTwQtPaK/ic10evAQFXpIF4gN5CN6RdcCDk+7Aqh9/RHR0NN577z2qA7R/v6GJK0AzDrYU5FRXG2ZzRoygJUxzy8kBPv6YEuEZMwEOoRlrKQ8P2nlTXCz1SExDraZclKoq+l2HtyxxuM2HU1DU6JZ2AKi5Vtjk41y6mooXSi7C19UNi6vcEChQHojc3RXR7z6H8MfvxcfV1XjvvffwziuvoOvx47izVy/g/Hng0UdtJx/nRnv3ApWVtFwlVcf1PXvovZaXJ83zM5vHgY6Nu5RSjt+35iAjWwUfT3tMHBOAfjEejX7ytWgqlaE8vBTNBgHDjE6RkTox1s7eHpgwAdiwAdi1ixKwBwy4rYdUZeQg/ZufUHzoFGSODgiYPg7B994BuVPTS2XOHUONFymsOyas0ccQRRGzZs1CUHAwDhw4AFlmPq58vBz5W/dBnVeIxOfeQ+mxM+j08pN464EHMOLYMfy1YQP6+Poi7K67bDPIycsDjhyh7ydNkuZ3zMykQpWCIN2yGbN5HOjYsBVr07Bs1VXI5QK0WhFyGbB1Tz7GDPPFa891hVxuhcHO5cvA+vWUJzF7tjRj0DcZtOVPoL160fLVoUPApk0UYA4f3qrdbvlb9+HE3U9Bp9HQridBwLXNe5Hy4TeI2/kDHIIa38oc8vAMXPnkuwZvExRyeMY1vXy2b98+nDlzBjt27ICbqytOvfMacv63tS6ZWlejRs6qDdD+vA49Zk/C6AEDsP/ECSy+dg1LbXGrs05nWJrs2hWIijL/GG5Mgo6JkS4Jmtk8ztGxUUdOFmHZqqsAAK2W/pjrd9bu2n8NP/+eKdHIbpOzM32trJRuDPpE6Lw82yoceCNBoG2++sapu3cDW7e2eNeburAYJ2Y8Dd2NDT6vP4bqaiYSHnqxycdw6RKJbh+9TMO6MVdHLoOdtydili1u8jG+/PJLdOnSBaNHj0b+pj3IWbel3u+iELUIqS2Ca1UJ8rfthzB4MNxfeAHfbtyIPFsMaA8coARkBwdg8mRpxnDpEvWsUyiAUaOkGQNrFzjQsVE//56lr9N2C1EEfv4tE7om+hFZJKfrTRalDHQ8PekEodHQMpqtEgQKdPRF8Q4fNjRcbKbMlRugq6lpMEASNVoU7jrUrCacEU/PRtzuH+E/dQyUQX5w7hSOTovmY/jJ3+EUGdLk/Q8fPoz4+HgIgoCM79ZRA88baCCDDgLUooBLqaWo7tUb8X/7G2pra3Hq1Knm/8LWIC+P8mIAWrKSYuegTkcFCgHKDZKi3QRrN3jpykYlJZc3VhsN1wrVqKjSwM3FynaQ6Gd0qqroj6UUFZIFgWZ1UlMpxyAgwPxjMKdBg2jb+dmztMW6BcpOXwQEGQDjM1/lZy7CpXNEk4/lNbQfvIa2rtFjRUUF3K+fTFWZuZBpauEpqlAoOEEUqGN5DlyhgQwiBNTkFsA9nGbuysubbkBqNWprgf/9j2Yiu3SRrgJxZiZQWEjvq6FDpRkDazd4RsdGOTk2nlgoCIDSzgr/+V1cKGlSp6M6NlIJD6evqU3PRtiEmBjg/vsNtU5qaym/oomZNYWrc5OJ7032z2oDbm5uKCoqAgoKEKSsRYRQCk9RBQ8YWnnUCnIKemQyOHQIQGFhYd19bca2bVT52sUFmDpVugrjoaHAE08A8fGGauOMmYgVnulYc4wb4Wd0skMuA4YM8IZSaYU7SWQy2vIMSLu9O+L6DMSVK9JXazaXG0+K+/dTnsfnnwMnThh9DQLvmQxRY7xHlZ2nO7xGDGzrkdYniojv0wc1K1ZA99//IjDcD4JWC5VgB9VNk9qCQg7/qaOh9PXCL7/8AgcHB/Tv39+04zOXxETg2DH6/s47pamZcyM/P66EzMyCAx0b9bc7guHpbn9Lno5MBsjlMjxyX3ij9y8qViM9qwo1NRaYbKvf3i1loBMcTNuwVSrandTeREXRkp1KBfzxB/Dll9R5WqWqd5jX0H7wmzKSWi80IHrx8w024Gwzogh8/z2e8/SEV0EBkpOT4ThxDHQPzkam4IZquaHlgyCXw97PG90/fgVarRZLly7FvffeC69GWmJYjdJS2mUFUKuPjh2lGce1a7a9W5FZJA50bJSnhz2W/l9v9Iv1rHd9VIQLPlscg06RDX+au3CpDAsWJWDa7EO474ljmHL/Qfznm2Soqi0o4ImNBaZMMcyqSEEuNzx/UiONIG1VSAjw2GOUqKxU0nLIpk3ARx9R4HOdIAjos/YzRCyYDZmjYYnCITgAMd+9j9BHZrTtuIqLgRuThwUBcHJCUEgIKjt3xqz9+5E3ejS6rPgYsT98BI++PSB3doQy0A+RCx/GsKMb4BASiOeffx4ZGRl4+umn23Z8UqitBdaupSA0KEi6pp06HdVm+uorajvBmJkIomhb8+5lZWVwd3dHaWmpba2t34bc/Grk5lfD090eYSFORo+7cKkMT72UAK1WrFf5XyYDunV2w2fvxcDOGvN6TOX0afrD7eMDPPWUdPkOUlOpgDNngJMn6dN6bCzlXgB0cjtzBoiIgEYmR/m5y5A5KOHWq8stO59aTBSpDcfVq7RN+epVQ1uOBQvo3wWgpFelEulFRRg0aBCcnJywevVqDGigCGJRURFeeeUVLF26FJ999hkWLFhwe2OUmijSe/TMGUr8ffxxw9KvuR08SDlCDg707yP10hmzOKY6f/Ouq3YgwM8BAX5NJ/x9tizlliAHoHPVuYtl2LX/GiaMary4W7sSHU3JuQUF1K9HqkrNUnN0pP5jAwYA2dk0w6OXkwP8+isAQOHtDc/gYCoMl6ijLuk+PrQEaIwoUkuK6mp6Hv2xZ8/SSfPmHVEyGSW6qtWG664Xogt1ccGBAwdwxx13YODAgejfvz9mz56N4OBgqFQq7NixA2vWrIFOp8PXX3+NefPmtcGLI7EDByjIkcmAe+6RLsgpKqIq2wBV3eYgBwBQo9bhz+052Lg9F0XFanQIcsSdk4MwaogvZEaWe1nLcaDDAAD5BTU4m2h8F5NMALbszrOcQCcnh3JjoqOb1XHbJJRKev5z5+hk0l4DHT1BoNylG9XWAh06UHG6wkK63GjKFECf7JucTHkkCgVtf66upoBFP+k8cyZV8QXomPJyOoEHB9MuuPBwWlJrJHCKiIjA6dOnsWnTJnzxxRd45plnoJ/UDgsLw2uvvYaHH34Y/v4W8j6/HRcvAjt30veTJkm31CuK9O+q0VBF89hYacZhYVTVWjz76mlcSCoHBHqZikrUSDhXioOjCvHKs9Ec7LQRDnQYAKCsvLbR23UiUFra+DFmtX49JTY6OlKwIZXYWAp0EhIo96Gx2Yn2KDycGmJWV9Py0rVrhoCnsNCQWA7QMcZKBsjl9Wdv9I/r59fi11yhUGDatGmYNm0a1Go1SktL4ejoCGfnprfCW43MTKqXI4pAv36GYFIKR47QsqK9vbRb2i3Myp/TkHi5HCIAXI/l9bPpW3fnY2AfL4wfaQMBtwXgQIcBAAL9HaBQCNBoGk7ZkssERIY7m3lUjQgNpZNmerq0gU7HjrQ0UlhIOTu2shW5rTk40Fbim7cT35gi2LEjJThrNBTYODjQrJmDA/184wnS0ZFmim6Tvb09fH19b/txLEpREbBmDc2mdeokXYsHgJLD9RWQx4+vH9i2Y1qtiA2bcm5JE9CTCcD6P7M50GkjnFnKAADOTgpMGOVvtPaOVicifpIFLc2EhtLXjAxpxyEIhs7eR460n5o6beXm4CUoiP5t9bk8Li60TMWzAM1TWQn8+CN9DQwEZsyQpnq4nocHBThduwJ9+0o3DgtTqdKgotJ4fSmdCGRkVZlxRLaNAx1WZ8HDHRERSrM2+vOKvsP547Mj0CPagnax6QOd7Oz6iadSiI2lmYeCAmpUyJgUVCrghx9odtHDA7jvPumXUvUfBO65h4PVGzgq5bBTNP56eHrwMnhb4UCH1XF1UeCr/+uNfz7ZCT2i3RDWwQmjhvjgi/dj8eCMUKmHV5+HB120Wlr/l5JSaViy2r2bZ3WY+alUwMqVlKDv4gI8+KA0zTr1srIo50qPg5x67OxkGDvCz2jjZUEApoyz8R56ZsQ5OqweBwc54icFWdYyVUMEgfIPjh0DLl8GOneWdjyDB1Nl4Nxc2u2i3x3EmKlVVwOrVtFORGdnYM6cui31kigtpfE4OACzZ3NejhGP3BeOQ8eLUF5eW68Bs0wGRIQ6Y/pEC/8bbEV4RodZr6go+moJjTWdnKjLN0CzOsayDBlrSzU1FFRkZdF7cM4cQMrkaq0WWLeOZpgcHaWdVbJwAX4OWPZxH4wZ7leXIuDoIMff7gjGkn/HNtmYmTUfV0Zm1kutpiAnIkL6XASAPll/+il9nTYN6NNH6hExW1ZVRYnHWVkUVMyZQ/3HpLRpE81sOjhQFWaezWmWmhotKqq0cHNRtOvq86Y6f7ffV5RZP3t72q5sCUEOQH/cR4yg77dvp50vjJlCaSnw7beGmZzZs6UPck6fpiAHoO7oHOQ0m1Iph7enfbsOckyJX1VmG0TRMpKABw40dPXeskXq0TBbdO0asHw57fJzdwceeoi2kkspK8vQzHXEiFvrJTEmIQ50mPU7cAD44gtKBJaaTEbLVoJA/Zh4uzlrS+npNJNTVka5OA8/LG1Ojt727VTosXNnYORIqUfDWD0c6DCLptGKUNc2kdibnU2fchMSzDKmJgUFGRKTf/sNqKiQdjzMNpw7R1vIVSqqCv3QQzSjYwnuuQfo3Ru4+27eSs4sDgc6zCKdTyrD82+exag792H0XX9h7jPHsX1vfsMH9+5NXxMSpC8eqDd6NODvT3k6GzZYxrIas06iSDv51q2jWZPoaEo8dnKSemQGTk7A9On1O9czZiE40GEW5+jJIjz5YgKOnCyqiw9SrlbizQ8T8e2aq7feoWNHwMuLttqeO2fWsRplZwf87W/UviAlBTh0SOoRMWukVgM//wzs3Us/x8XR7ImdnbTjEkVg82bgxAlpx8FYM3CgwyyKViti8X+ToNOJ9UrR6AOeb1enITNbVf9OgkAdmgHa9WEpsye+vsDEifT9zp3S9+Vi1qWwEFi2DEhMpKam8fHAhAnS9q7SO3iQertt3AjkG5lpZcxCWMD/GMYMTp0rwbVCtdFYRS4DNu9qIOm4d2/6lJubC1y5YtpBtkTfvkC3blRI7aefqLM0Y025eBH4+msKIlxcgLlzqaeaJThxgpKPAWrY6ecn7XgYawIHOsyiFBY1kWMjCA0f4+ho6I78119tP7DWEgT6JB4URPk6q1ZxfR1mnEZDS0I//URLsaGhVHgvJETqkZFz52gWBwCGDKGlNMYsHAc6zKIE+Dk0ersoigj0N3JMXBzQvTt9yrQk9vbUSdrDg2Z01qwBamulHhWzNIWFVB/nyBH6OS6Oko4tpY3C5cvA+vW0NNyvHzB2rNQjYqxZuKknsyi9urmhQ6ADsvOqG24XJQKTxhipAOvuDsyYYdLxtZqLC/DAA3Qiy8ykT+z33kvJyqx9E0VaDtq6lQJgJyeaBZS6Ue2NiouBtWuph1vPnsCUKVa7jfzE6WKs2ZCJ0xdKoZALGB7ng/vuDEFYiAXtYmNtimd0mEURBAH/eq4r7O1kdY3uAMrNAYB/PNEJfj7N3MJqaY01fXwouLG3p51Ya9fSUgVrv8rKaIZv40YKciIigCeesKwgB6B2DsOH09b2+HirDXI2bMrG3189g2OniqBSaVFeocGWXXl4+NkTOJtYKvXwmIlwU09mkTKyq7D210zsOVCAWo0Ovbq54947O6BPr2b0z6mspLojBQU09W9pf5SvXqVmjLW1QKdOlrFdmJmXKFLdp61bqQmsXE5LQYMGWdb7VRTrj0ens4xdX61wrbAGdz98uMHPPzIZ4O/rgLVfD4BMZkGvfztjqvM3z5szixQS5IR/PtkZ/3yyFZ9sdTpqMFhbSy0YLK3vTng45eysXk15Dz/8QDM9jo5Sj4yZQ0kJzeAkJ9PPwcFUbM/Sdi8lJ1P9p5kzDY1zrTTIAYDNO423iNHpgJy8apw+X4rePT3MNyhmFiZ91xYVFeH++++Hm5sbPDw88Mgjj6CiiXL4I0eOhCAI9S5PPPGEKYfJbI2rKzXXBOgTsyUuD0VEAA8+SB3P09OpXkphodSjYqak1VJftiVLKIhQKIBx44BHHrG8IOfCBVpSS0mhMUuksFiNqxmVqFJpb/uxcvNrIDQxW5abX33bz8Msj0lndO6//37k5ORg+/btqK2txUMPPYTHHnsMq1evbvR+8+bNw1tvvVX3s5MllTpn1mHYMJrVKSqi7eajRkk9oluFhlK/ojVrDMXh7rmHgiBmW5KTqZt9QQH9HB4OTJ0KeHtLOqwGJSRQjzZRpF2Mw4ebfQgXk8vx+fIUJJyjvBl7exkmjwnA/LkRcHZq3WnLx9seTWVq+HjZt+qxmWUz2YxOYmIitmzZgmXLlmHgwIEYOnQoPvvsM/z000/Izs5u9L5OTk4ICAiou3CuDWsxpRKYNIm+37+fmn5aIn9/4NFHqUmjSkXLWMePW051Z3Z7iotph92qVRTkODtTMu+cOZYZ5Bw+DPz6K73/+vShJp1yuVmHcPFyOZ58IQFnLhiSg9VqHX7fmo1nXj6NGnXrNhlMHOUP0chdBQHw9rRvXg4gszomC3QOHToEDw8P9NOX5gcwduxYyGQyHNHXiTDixx9/hI+PD3r06IFFixahqqrK6LE1NTUoKyurd2EMANC1K+1e0WopJ8JSgwcXFzrx9ehByQIbN1K9kmqeRrdaKhWwYwctU128SLktcXHA009ThWNLSjgG6P/Gjh006wTQWKdOlSQnZ8l3KdBodbckDet0QFJKBbbtzmvV4wYFOOLRB8IB1H/5ZTJAJhPw8rNd6u30ZLbDZEtXubm58Ltp3VmhUMDLywu5ucaTwu677z6EhYUhKCgIZ86cwYsvvoikpCSsX7++weMXL16MN998s03HzmyEIACTJwOpqfRpuriYmn9aIjs7+vQcGEh9sc6epdyd+HheyrImajXNihw8aAhUIyNpdtHXV9qxNaaykpasAGD0aFr6lSAYKypW49RZ49u8BQHYsjsPUycEturx58wMQ4cgR6xen4Gk5ArIZMDgft6YPTMU3TrzyoGtanGg89JLL+H9999v9JjExMRWD+ixxx6r+75nz54IDAzEmDFjkJKSgo4dO95y/KJFi7Bw4cK6n8vKyhBiKeXSmfQ8PGjXSGAgLRtYMkGgsvphYTSjU1QErFxJn65Hj+bigpZMo6Elx7/+MrT48Penf7fOnS1vBudmLi60E/DaNSAmRrJhlFc0vnFAFIHSsturKj5mmB/GDPODRitCJoC3k7cDLf7L+dxzz2Hu3LmNHhMZGYmAgADk39TVVqPRoKioCAEBRirbNmDg9d0zycnJDQY6SqUSSmUzC8ix9ikqSuoRtEyHDlQ0butWqph78CBtk586lYIgZjlqa4GTJ2lnkn7Z3MuLkt979LDsAKewkGY59f8/goLoIiE/XyWU9jKjeThyuYCO4W3zgUXBy1TtRosDHV9fX/g2Ywo2Li4OJSUlOHHiBPpeb7a4a9cu6HS6uuClORKuT6cGBrZuqpKxei5coGUsCXaStIi9PQU2nTsDf/xBY/7uOyq/P3Ystbtg0qmqAo4epYs+h9DNDRg5kmZEzJzA22IpKcC6dTQT9dBDkgc4eo4OckwZF4BfN2c3WNhPqxVx1xTLGCuzHiabC+/atSsmTpyIefPmYenSpaitrcWCBQswa9YsBF3/T5WVlYUxY8Zg5cqVGDBgAFJSUrB69WpMnjwZ3t7eOHPmDP7xj39g+PDh6NWrl6mGytqLrCzg55/pe29v2jpr6bp0oW3oO3fS7M7Zs5TcOmQIXbiisnkVFFBwc+qUoTGrpyf9W8TGWv7yoijSDOGOHfR9cDAFaBbkidkRuHCpHBcvl0MQaJhyuQCtVsSjD4QjpruH1ENkVsakLSCKioqwYMEC/PHHH5DJZLj77rvx3//+Fy4uLgCAq1evIiIiArt378bIkSORkZGBBx54AOfOnUNlZSVCQkJw55134tVXX232FnNuAcEatW0b/aG3t6dt3ZZWqK0xOTm0KyYtjX52caGk0b59Lf8Ea810OqpgffQozYToBQZSgNOtm3VUDFargd9/B86do59796bmnBb43qlR67B9bx627MpDWXktIsOccefkYMR055lMW2aq8zf3umLti05HNU2uXKFcinnzrKv1gijS8tv27dRKAKBP5MOG0YnLAk9aVqu8nIpOHj9ueK0FgZYTBw6k3XCWnINzI309n7w8CsomTQL69bOe8bN2gQOdZuJAxzZdSavEn9tzkJNfAx8ve0weG4DoKNfWPVhVFfD113TyiogAHnjA8nMqbqbV0vLJvn2GJFgXF2DAACr0dn3WlLWQWk1Lg6dPUzCs//Po6Eiva79+tFRlbfbtA3btovfFPffQcihjFoYDnWbiQMf2fL82Dd+sugq5TIBOFCGT0Xr9jKnBeGZexyb71zQoNxf49ls6scXEUL0aa/x0q9EYdv2UXq8/IpNRscT+/WmXljX+Xuak0dCS1IULQGIivSf0QkNppqxHD+vOh9LpaNl28GCLy8lhTI8DnWbiQMe2HDxWiBfeOmf09pee6Yw7xrVyR15yMnUQHzqUtgNbc0Cg1QLnzwPHjgEZGYbrfX0NJ2r+/2BQW0v//hcu0Nb9mhrDbV5eFPz26mWdszcA1cP56y9g2jRezmRWgwOdZuJAx7Y88/JpJJwvaXCrqSAAYR2csOqL/q1/gsJCy+w5dDtycymv5MwZw+yEINDsTvfuNNvT3pa2RJH+rVNSKMC5etWwawqgILBbN3p9OnSw3qBXFGlJc/Nm+v2GDqVyBIxZAVOdvznUZxYtMbm8wSAHoL/pVzOqUFurg51dK3e93BjkqNW0u8Yatp03JiAAuOMOYNw42o5+5gy1k7h6lS6bNtG24o4d6RIcbH05Sk0RRcrBSk+nXWopKYalPT0PDwpuunWj18Bagxu98nKquXTpEv0cGQkMGiTtmBizABzoMIumtJdBpdIavV0uF9qmEZ9GQ7ux0tPphGELJwilkpJn+/Wjk/6FC3TJzDRc9u6l4yIigPBwms0ICLC+5Q61mnYUZWfT0l1aGv073kgup1mtjh2pGrCfn/UHN3rnzgF//knNROVyaj0RF2cd294BlJTWYuP2HCScK4VcLiCunxfGj/SHk6ONBeBMElb214y1N2OG+eLXTdnQNjCrI5cJGD7Ix2ivGlW1FtcKauDqooCnh33jTySX04k+PZ1q1YginShshYcHJaIOHky7tFJSDBeVinYaXbxIx8rlVCNGH/T4+QE+PlR7SGo6Hc3MFBRQHkpuLtUXKii4tTu9/vcIC6N/27Awy/gd2tpff1FBSYB+3zvvtKr6UOeTyrDwtTOoUmkhihR7HjhaiB9+Scfni2MR6O8g9RCZleMcHWbRcvOrMfeZ46hSaestYckEQKGQ4euPeiMqon6+SUWlBku/T8WmnblQX++Z0y/GA0893BGdIhvJTRFFYM8emuUAJO3ibDY6HQULKSk0w5ORYWhpcDMPDwp4PD0pp+XGi5MT4OBwe6+VTkcdv1Uqmo0pK6t/KSqii8ZI40dXVzrRBwdTUBMcbN07pZqrpAT46iuq7TNsmFUtQ9bUaHHXw4dRXqG5ZYlaLgOiIl2w7OM+rdtZyawOJyM3Ewc6tudKWiXe+08SLl42LEVEhDrhxac7o0d0/UqpNTVaPPHCKaRcrawfGMkAO4UMSz/sjU4RLQh2+vSh6rFWdPK4LfrcFv3SVl4ezZzoO3I3RhBoGczBgS4KBb1uMhld5HIKZrRaCla0WrrU1FBwc+POp8YoFLQzyseHZi6CgijAcW1lXSVrU1QEJCXVn3GsrqbX3Mps3pWLdz9JavSYrz/qjW6d+W95e8DJyKzdigxzxrKP++BKWiVy86vh42WPTpEuDX7K27wrD5ev3HpS1umAWo0OS1dcwUdvNtI3TRBoq7mzM+1cOXmSTv7Tp7flr2S5BIFmbDw9qYGoXlUVLQ8VFFAgdPNsi1pNr1N1NV1uh1JJu8JunDFydaUx+fhQQ1MryT1pU1ottS/Zu5cCxYAAyq0CrDLIAYDLKRVQyAVotMY/b19KqeBAh90WDnSY1YgMc0ZkmHOjx2zemVfXCPBmOh1w9GQxSstq4e7WxJLGgAG0VLNxI+W1tHdOTlQ8z1hFXY3GMDOjD3Y0GnrR9bM4Op1hZkd/USgob8bRkS4ODu0ziGlKairtlrt2jX6OjLSJDvaOjvIG/6/eiBOS2e3iQIfZlNKy2kb/cIqgHJ4mAx2Aeho980z9HUjl5e1niaQlFAq6ODceiLIWKi6misaJifSzszMwYQLNttlA3sqoIb74fm260dvt7ATE9bOxOlfM7PijE7MpHcOdIW/kXe2glMHHqwU7b24Mcq5eBT79FNi/v+EpI8bakk4H/PADBTkyGc0yLlhAFZttIMgBgKgIF4wb4Wf015k7MwyuLvx5nN0efgcxm3LXlCDsPVTQ4G0yGXDH+EAola2cCk9KoiWYHTso6LnzTp7BYG1Lq6UgRp/APXIkNRidMMGqtoy3xCvPdoGvjxLrN2ahuoZ2ELi5KjB3ZhhmTAuWeHTMFvCuK2Z1CovV+GNbDs5eKIWdnQzDBvlg7DDfugDmm1Wp+H5tOuRyav6pz9np1tkVn74T0/o1f315/U2bKP/E1RW4+26q0cLY7RBFmrnZuRMYMoR2++mvB2xmBqcxVVUaXE6thFwuoEtHl9ZXO2dWi7eXNxMHOrbt5NkSvPDmWahrddDpUBfEdAh0wOeLY+Hjraw7bsOmbKSmVcLdzQ6Txvhj/Eh/2LfFH8+8POCXX2gHkiDQNt9Ro9pHzRbWtkQRuHKFApzsbLouMBB47LF2EdwwdiMOdJqJAx3bVVGpwV0PHYaqWntrEVyZgF7d3fDZe7HmGYxaTdvPT52in++5h3omMdYcokhFGvfuNXSbt7enoHnwYNpiz1g7w3V0WLu3dU8eqoz0vdLqRJw6W4rU9EpEhJohb8benmrrdO1KuTtduxpu09exZ8yYbduAQ4foe4UC6N+fOo1zzhdjbY4DHWY1LqdU1OXdGD3mSoV5Ah29zp3poqdSAStXUp5F9+4c8DCi0wG1tYaZmm7dgOPHqeHqkCFUIJExZhIc6DCr4diMJGLJi4vt309NJtetA44cAcaPB0JCpB0Tk45aTcubhw4B0dHAxIl0fUgIsHAhFUlkjJkUp7UzqzF6qG+jszlOjnL0i/E044gaMHKkITE5IwNYvpyCnuJiacfFzKukhMoQfPwx5XKVlFB3+BsbsHGQw5hZ8IwOsxo9ot0wdIA3DhwrbLBe37wHwuHgIPGMjp0dMGIEbQ/etQtISADOnaOtw3FxwNix0o6PmVZaGs3eJCUZtoZ7e9O/fUwMt7dgTAIc6DCrIQgC3nqpG75ccQW/bc6GupZOJJ4ednj0/nBMnxgk8Qhv4OpKycoDB1Li6ZUrze/OzazX5cs0cwNQP6oBA4AuXThXizEJ8fZyZpUqKjVIuVoBhUKGLlGuUMgt+ESi30rs72/ok5WVRZ3RhwwBvLykHR9rOZ0OSE6mGbvevYFOnej6khLgwAEKcHx9pRwhY1aHt5czdgMXZwViuntIPYzmEQQgKqr+dX/9RZ/8T56kk+SgQUBEBH/yt2SiSMUiz54FzpyhBq8ABT36QMfDA5gyRbIhMsZuxYEOY1IYPJj6Gl2+DFy6RBc/P1rq6tmT6vQwyyCKtJvuzBng2jXD9U5O1GCzd2/pxsYYaxIHOoxJITQUuP9+oLCQtqEnJAD5+cAff9B25EcflXqE7ZcoAqWlNDsD0CxbYiIFOQoFzd706kX1k+QSJ78zxprEgQ5r93Lzq3H4RBG0WhEx3d0RFWHG4m3e3sDkycDo0RTgHD9ev5WEWk2zCd2704wPL22Zhk5H5QCSkmhJsbQUeP55wMGBbh86lJLJu3Y1XMcYswoc6LB2S12rw4dLLmHzrry6rg2iCPTp5YG3X+wGdzczNul0cKAtyIMG1a+1cvEisG8fXby96UTbrRs1fuSg5/aUl9PSYXIy7YqrrjbcplAAubmGzvTcx4wxq8W7rli79e//JuHPHbkNNAgFukS54qsPe0OQOphISwMOHqRdWxqN4XoPD1o6GTIEcHeXbHhWpaKClpr0hfqOHwc2bjTc7uRESePR0fSV86QYMyvedcVYG8ovqMGmBoIcANDqgAuXynHyTAn6Sl1pOSyMLjU1NPtw4QJ9LSkBjh4Fhg83HJueTgnOwcF8ktbpgIICIDOTtvKnpdHPkyZRwjdAwUxICH2NiqJZMi7ox5jN4UCHtUsnThdD18hcplwu4PCJIukDHT2lEujRgy61tTTDk5dXvxnk3r10vUwGBARQwnNICAU+7u7tY6mrpAT47TcgO/vWAo2CQLfreXgAjzxixsG1jiiKSE2vQnlFLUKCnODl2c6DWMZaiAMd1i5pG4tyrtM14xhJ2NnR8kp0dP3rXV0BNzegrIxO9NnZwOHDdJuXF/DMM4ZjCwspSNJ307YGOh0FKgUFhkteHgV0EybQMU5ONHuj09GsVlAQ0KEDBXyhoVbXX+r46WJ8+lUyrmZUAQBkAjBisC8Wzo+CpzsHPIw1Bwc6rF2KbaLYoFYronfPxo+xOPHxlE1dVkbLWBkZdMnPN2yV1vv+ezrO1ZWSnL286Bg3N/rZ3B3XRZFmYCoqgMpKmpXSj0GnA5YupeBMq731vjcuN9nbA3/7G/0Ovr5WvRR18mwJFr52pt7yqk4E9h26hpSrFVj+aV84St3bjTErwIEOa5c6BDlieJwP9h8pqLfJCaBk5OBAR8T185ZmcLdDEGiZqmdPugAUHKhUhmM0GkPAUF5Ol6tXDbdHRABz5hh+/vJLChgcHWnGxN6eLnZ2gI8PNavUO3mSAhNBoOfQXzQaGteNxfV+/JECm6oq+npjEBMeDsydS9/LZDR+rZZ2Q3l70/P6+NCW+8DA+q+BjeyQ+vK7K4CIW/LItDogI0uFLbvycOdkC+rvxpiF4kCHtVuvPtsFryzW4lhCMeTXe2VptSI6BDvhozd61l1n9eTy+rk8CgXViFGpaJakqIi+lpXR5cbAQaejGSFjmzM7dqwf6Gzdarx5aWho/UAnJ4cCnBsplTRWfU8wvVmzKMhyd7fqWZrmyi+oQeLlcuMHCMD2vRzoMNYcHOiwdsvJSYFP3u6FxEtlOHC0EFqdiJjuHhjQ2xMymY0EOY1xdKT8lQ4djB8jCFSluaqKLioVFTGsraXLzQ1Ju3Sh60WRAhK5nAIruZxmYm40bRo9vpMT4OxMFzsjtYuCg2/vd7UyVSpNo7eLIlBR2cAyHmPsFhzosHava2c3dO3MNZcaJAgtCzLuuqv5x3bu3PLxXFdQVIP/bczG7v35qFbr0DPaHTOmBaNXN9uoKRTo5wBHBxlU1boGb5fLBXTtZMYK3oxZMQ50GGNWJT2zCvNfTEB5RW1dftW+w9ew+8A1/PPJToifFAStVsSxhGJkZqvg4W6HIQO8rSpxV6mUY/rEIPz8W2aDZRC0WhF3Tmlfs1yMtRYHOowxq/LOJxdRcUOQAxjymD/68jI83e3wn29SkF9QU9fWw9FBjr8/1hF3jAts+EEt0LwHwpGcWoHjp0sgk1G6lPz614XzOyE6yrXpB2GMcQsIxpj1uJJWidkLjhu9XSYz9Cy7eTcdAPz71e4YOtDHhCNsW1qtiIPHCrF9bz5Ky2sRGeaMaRMCERHqLPXQGGtz3AKCMdbuZWarGr29oeBGTxCAb1enWVWgI5cLGDbIB8MGNW/MV9Iq8ef2HOTm18DH2x6TxwSgC8/8sHaOAx3GmNXw9Gh9R3lRBC5dqUBJaS083M3Ymd5MVvyUhmU/XoVcJkAnipDJBPxvYzZmxnfAgocjpW9Qy5hEONBhjFmN7l3cEOCnRN61GqOlfZpiqtYeJaW12PlXPgqL1Qjyd8Doob5wcjLPn9j9Rwqw7MerAAztTbRa+rr210xERThj0ugAs4yFMUvDgQ5jzOyOJRTjl98zkZRcAScnOcaP8MNdU4Lh7tb4TItMJuD5pzrjhTfPQRTEW5aqQoMdkZVbXXeSv1mHIMfbmhUy5n9/ZuGzZSnQakXIZQI0WhGffpOMf/0jGiMG+7b5891szYbMuoTlmwkC8NP6TA50WLtl+yVGGWMW5fu1afjHv87gyIkiFBarkZGlwnc/pWHu308g71p1k/cf2McLny2OQe8eHnXX+fko8cy8jnjrRWr/YGyV5sEZoW2+hPPX4QJ8sjQZGo0IUQQ014Osmhod/vX+BVxMbqTCcRtJSi43mp8kikBKWqXR4I8xW8eBDmPMbJKSy/HNqqsAqGeTnk4HFBXV4KMvLzfrcXp1c8d/3o3BtrVD8MeqOKxbPhD3TOuAqAgXvPtyNyjtZRAAKORC3U6sh+8Lw+Qx/m3+O638OR0NFdIWRUAQBPy0IaPNn/Nm9naN/ylXKIT20DmDsQbx0hVjzGz+2JYDuVxocHZBqwMOHivCtcIa+Horm/V4Tk4KON103dABPvhtZRx27MtHRhYVDBw3wg/+vg5t8BvUV6PWNdqTSqsVcexUcZs/781GD/PDH1uz6wWPenIZMCLOh5ORWbvFgQ5jzGzSs1RNLqFk51Y3O9AxxtlJgekTTd/wslmxgxkCjHvv6oBte/NQXa2tt4QlEwC5QoY5M8NMPgbGLBVPZjLGzMbb067JJRRPK9r6bW8nQ69ubkZ/J7kcGNzfq+Eb21BwgCO++HcsoiLq978KC3HCf9+NQWQYFxhk7RfP6DDGzGbCqABs33utwdtkMiAqwgWhHW5ejLJsc2eGYeHrZ2+5XhAoR2dWfCPd4dtQVIQLvv20L1KuViA3vwa+3vboFOnCS1as3TPZjM67776LwYMHw8nJCR4eHs26jyiKeO211xAYGAhHR0eMHTsWly83LzmRMWb5BvT2vJ4vUv96mQxQyGVY+EQnaQZ2Gwb08cKr/4iGgwP9OdXP7ri5KPDBv3qgY7h5u4x3DHfBkAHe6NzRlYMcxmDCXlevv/46PDw8kJmZieXLl6OkpKTJ+7z//vtYvHgxvv/+e0REROBf//oXzp49iwsXLsDBoXmJhNzrijHLptGKWLM+A7/8kYmi4loIAOL6eeHRB8LRuaP1tiuoUmnx1+GCuoKBQwZ4w66J3VCMMQNTnb9N3tRzxYoVePbZZ5sMdERRRFBQEJ577jn885//BACUlpbC398fK1aswKxZs5r1fBzoMGYdtFoRZeW1UCrlcHKUSz0cxpjETHX+tpiPG6mpqcjNzcXYsWPrrnN3d8fAgQNx6NAho/erqalBWVlZvQtjzPLJ5QI8Pew5yGGMmZTFBDq5ubkAAH//+gW9/P39625ryOLFi+Hu7l53CQkJMek4GWOMMWY9WhTovPTSSxAEodHLxYsXTTXWBi1atAilpaV1l4wM01chZYwxxph1aNH28ueeew5z585t9JjIyMhWDSQggBrO5eXlITAwsO76vLw8xMbGGr2fUqmEUnl7xcUYY4wxZptaFOj4+vrC19c0nXgjIiIQEBCAnTt31gU2ZWVlOHLkCObPn2+S52SMMcaYbTNZjk56ejoSEhKQnp4OrVaLhIQEJCQkoKKiou6Y6OhobNiwAQAV1nr22Wfxzjvv4Pfff8fZs2cxe/ZsBAUFIT4+3lTDZIwxxpgNM1ll5Ndeew3ff/993c+9e/cGAOzevRsjR44EACQlJaG0tLTumBdeeAGVlZV47LHHUFJSgqFDh2LLli3NrqHDGGOMMXYjk9fRMTeuo8MYY4xZH5uvo8MYY4wx1tY40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2iwMdxhhjjNksDnQYY4wxZrM40GGMMcaYzeJAhzHGGGM2y2SBzrvvvovBgwfDyckJHh4ezbrP3LlzIQhCvcvEiRNNNUTGGGOM2TiFqR5YrVZjxowZiIuLw/Lly5t9v4kTJ+K7776r+1mpVJpieIwxxhhrB0wW6Lz55psAgBUrVrTofkqlEgEBAc0+vqamBjU1NXU/l5aWAgDKyspa9LyMMcYYk47+vC2KYps+rskCndbas2cP/Pz84OnpidGjR+Odd96Bt7e30eMXL15cF1TdKCQkxJTDZIwxxpgJFBYWwt3dvc0eTxDbOnS6yYoVK/Dss8+ipKSkyWN/+uknODk5ISIiAikpKXj55Zfh4uKCQ4cOQS6XN3ifm2d0SkpKEBYWhvT09DZ9odqjsrIyhISEICMjA25ublIPx6rxa9k2+HVsO/xath1+LdtGaWkpQkNDUVxc3Ozc3uZo0YzOSy+9hPfff7/RYxITExEdHd2qwcyaNavu+549e6JXr17o2LEj9uzZgzFjxjR4H6VS2WAej7u7O7/h2oibmxu/lm2EX8u2wa9j2+HXsu3wa9k2ZLK23SfVokDnueeew9y5cxs9JjIy8nbGc8tj+fj4IDk52WigwxhjjDFmTIsCHV9fX/j6+ppqLLfIzMxEYWEhAgMDzfacjDHGGLMdJqujk56ejoSEBKSnp0Or1SIhIQEJCQmoqKioOyY6OhobNmwAAFRUVOD555/H4cOHcfXqVezcuRPTp09HVFQUJkyY0OznVSqVeP3113lbehvg17Lt8GvZNvh1bDv8WrYdfi3bhqleR5MlI8+dOxfff//9Ldfv3r0bI0eOpCcXBHz33XeYO3cuVCoV4uPjcerUKZSUlCAoKAjjx4/H22+/DX9/f1MMkTHGGGM2zuS7rhhjjDHGpMK9rhhjjDFmszjQYYwxxpjN4kCHMcYYYzaLAx3GGGOM2SybCHTeffddDB48GE5OTs0uGz137lwIglDvMnHiRNMO1Aq05rUURRGvvfYaAgMD4ejoiLFjx+Ly5cumHaiFKyoqwv333w83Nzd4eHjgkUceqVdaoSEjR4685T35xBNPmGnElmPJkiUIDw+Hg4MDBg4ciKNHjzZ6/C+//ILo6Gg4ODigZ8+e2LRpk5lGavla8lquWLHilvefg4ODGUdrmfbt24epU6ciKCgIgiDg119/bfI+e/bsQZ8+faBUKhEVFdXi5ta2qqWv5Z49e255TwqCgNzc3BY9r00EOmq1GjNmzMD8+fNbdL+JEyciJyen7rJmzRoTjdB6tOa1/OCDD/Df//4XS5cuxZEjR+Ds7IwJEyagurrahCO1bPfffz/Onz+P7du3Y+PGjdi3bx8ee+yxJu83b968eu/JDz74wAyjtRxr167FwoUL8frrr+PkyZOIiYnBhAkTkJ+f3+DxBw8exL333otHHnkEp06dQnx8POLj43Hu3Dkzj9zytPS1BKiFwY3vv7S0NDOO2DJVVlYiJiYGS5YsadbxqampmDJlCkaNGoWEhAQ8++yzePTRR7F161YTj9TytfS11EtKSqr3vvTz82vZE4s25LvvvhPd3d2bdeycOXPE6dOnm3Q81qy5r6VOpxMDAgLE//u//6u7rqSkRFQqleKaNWtMOELLdeHCBRGAeOzYsbrrNm/eLAqCIGZlZRm934gRI8S///3vZhih5RowYID41FNP1f2s1WrFoKAgcfHixQ0ef88994hTpkypd93AgQPFxx9/3KTjtAYtfS1b8vezvQIgbtiwodFjXnjhBbF79+71rps5c6Y4YcIEE47M+jTntdy9e7cIQCwuLr6t57KJGZ3W2rNnD/z8/NClSxfMnz8fhYWFUg/J6qSmpiI3Nxdjx46tu87d3R0DBw7EoUOHJByZdA4dOgQPDw/069ev7rqxY8dCJpPhyJEjjd73xx9/hI+PD3r06IFFixahqqrK1MO1GGq1GidOnKj3XpLJZBg7dqzR99KhQ4fqHQ8AEyZMaLfvPb3WvJYAVagPCwtDSEgIpk+fjvPnz5tjuDaF35NtLzY2FoGBgRg3bhwOHDjQ4vu3qNeVLZk4cSLuuusuREREICUlBS+//DImTZqEQ4cOQS6XSz08q6FfK725erW/v3+L11FtRW5u7i1TqwqFAl5eXo2+Jvfddx/CwsIQFBSEM2fO4MUXX0RSUhLWr19v6iFbhIKCAmi12gbfSxcvXmzwPrm5ufzea0BrXssuXbrg22+/Ra9evVBaWooPP/wQgwcPxvnz59GhQwdzDNsmGHtPlpWVQaVSwdHRUaKRWZ/AwEAsXboU/fr1Q01NDZYtW4aRI0fiyJEj6NOnT7Mfx2IDnZdeegnvv/9+o8ckJiYiOjq6VY8/a9asuu979uyJXr16oWPHjtizZ4/NdUo39WvZXjT3dWytG3N4evbsicDAQIwZMwYpKSno2LFjqx+XseaIi4tDXFxc3c+DBw9G165d8dVXX+Htt9+WcGSsverSpQu6dOlS9/PgwYORkpKCTz75BD/88EOzH8diA53nnnsOc+fObfSYyMjINnu+yMhI+Pj4IDk52eYCHVO+lgEBAQCAvLy8el3m8/LyEBsb26rHtFTNfR0DAgJuSfjUaDQoKiqqe72aY+DAgQCA5OTkdhHo+Pj4QC6XIy8vr971eXl5Rl+3gICAFh3fXrTmtbyZnZ0devfujeTkZFMM0WYZe0+6ubnxbE4bGDBgAPbv39+i+1hsoOPr6wtfX1+zPV9mZiYKCwvrnaxthSlfy4iICAQEBGDnzp11gU1ZWRmOHDnS4l1wlq65r2NcXBxKSkpw4sQJ9O3bFwCwa9cu6HS6uuClORISEgDAJt+TDbG3t0ffvn2xc+dOxMfHAwB0Oh127tyJBQsWNHifuLg47Ny5E88++2zdddu3b683M9Eetea1vJlWq8XZs2cxefJkE47U9sTFxd1S4oDfk20nISGh5X8TbyuV2UKkpaWJp06dEt98803RxcVFPHXqlHjq1CmxvLy87pguXbqI69evF0VRFMvLy8V//vOf4qFDh8TU1FRxx44dYp8+fcROnTqJ1dXVUv0aFqGlr6UoiuK///1v0cPDQ/ztt9/EM2fOiNOnTxcjIiJElUolxa9gESZOnCj27t1bPHLkiLh//36xU6dO4r333lt3e2ZmptilSxfxyJEjoiiKYnJysvjWW2+Jx48fF1NTU8XffvtNjIyMFIcPHy7VryCJn376SVQqleKKFSvECxcuiI899pjo4eEh5ubmiqIoig8++KD40ksv1R1/4MABUaFQiB9++KGYmJgovv7666KdnZ149uxZqX4Fi9HS1/LNN98Ut27dKqakpIgnTpwQZ82aJTo4OIjnz5+X6lewCOXl5XV/BwGIH3/8sXjq1CkxLS1NFEVRfOmll8QHH3yw7vgrV66ITk5O4vPPPy8mJiaKS5YsEeVyubhlyxapfgWL0dLX8pNPPhF//fVX8fLly+LZs2fFv//976JMJhN37NjRoue1iUBnzpw5IoBbLrt37647BoD43XffiaIoilVVVeL48eNFX19f0c7OTgwLCxPnzZtX9wegPWvpaymKtMX8X//6l+jv7y8qlUpxzJgxYlJSkvkHb0EKCwvFe++9V3RxcRHd3NzEhx56qF6wmJqaWu91TU9PF4cPHy56eXmJSqVSjIqKEp9//nmxtLRUot9AOp999pkYGhoq2tvbiwMGDBAPHz5cd9uIESPEOXPm1Dv+559/Fjt37iza29uL3bt3F//8808zj9hyteS1fPbZZ+uO9ff3FydPniyePHlSglFbFv0W55sv+tduzpw54ogRI265T2xsrGhvby9GRkbW+3vZnrX0tXz//ffFjh07ig4ODqKXl5c4cuRIcdeuXS1+XkEURfG25pEYY4wxxixUu66jwxhjjDHbxoEOY4wxxmwWBzqMMcYYs1kc6DDGGGPMZnGgwxhjjDGbxYEOY4wxxmwWBzqMMcYYs1kc6DDGGGPMZnGgwxhjjDGbxYEOY4wxxmwWBzqMMcYYs1n/D2R+K96kRfIoAAAAAElFTkSuQmCC\n",
|
|
"text/plain": [
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"%matplotlib inline\n",
|
|
"\n",
|
|
"plt.scatter(Xtrain[:,0], Xtrain[:,1], c=ytrain, \n",
|
|
" s=30, cmap='coolwarm')\n",
|
|
"\n",
|
|
"# plot the decision function\n",
|
|
"ax = plt.gca()\n",
|
|
"\n",
|
|
"# create grid to evaluate model\n",
|
|
"xx = np.linspace(-1.5, 1.5, 100)\n",
|
|
"yy = np.linspace(-1.5, 1.5, 100)\n",
|
|
"YY, XX = np.meshgrid(yy, xx)\n",
|
|
"xy = np.vstack([XX.ravel(), YY.ravel()]).T\n",
|
|
"Z = svc4.decision_function(xy).reshape(XX.shape)\n",
|
|
"\n",
|
|
"# plot decision boundary and margins\n",
|
|
"ax.contour(XX, YY, Z, colors='red', levels=[-1, 0, 1], alpha=0.5,\n",
|
|
" linestyles=['--', '-', '--'])\n",
|
|
"\n",
|
|
"# plot support vectors\n",
|
|
"ax.scatter(svc4.support_vectors_[:, 0], svc4.support_vectors_[:, 1], s=100,\n",
|
|
" linewidth=1, facecolors='none', edgecolors='k')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.11.0"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|