From 9403994f56fa9c5487f4d523b25010412ad66416 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 14:35:59 +0200 Subject: [PATCH 1/9] add part about baseline in testing-validation --- .../src/sections/proposed_approach/testing_validation.tex | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/report_thesis/src/sections/proposed_approach/testing_validation.tex b/report_thesis/src/sections/proposed_approach/testing_validation.tex index 154bb436..cce488cf 100644 --- a/report_thesis/src/sections/proposed_approach/testing_validation.tex +++ b/report_thesis/src/sections/proposed_approach/testing_validation.tex @@ -58,6 +58,12 @@ \subsection{Validation and Testing Procedures for Model Evaluation}\label{subsec This necessitates careful dataset partitioning to ensure that the model training process accounts for these challenges, improving the generalizability and robustness of the models. +In Section~\ref{sec:baseline_replica}, we described how we ensured representation of extreme compositions in both the training and testing sets by automatically identifying the $n$ largest and smallest samples by concentration range for each oxide and reserving them for the training set. +We then performed a random split on the remaining dataset, resulting in a final train/test split of 80\%/20\%. +Then we would use a rudimentary procedure to prevent data leakage, ensuring that each target was only present once in the training set. +The baseline did not employ cross-validation, as our goal was to replicate the \gls{moc} model that was presented in \citet{cleggRecalibrationMarsScience2017}. +During experimentation, we discovered that the procedure was insufficient for this work, as it did not sufficiently handle the uneven distribution of extreme values, nor did it support $k$-fold cross-validation, which would additionally have to consider the distribution of extreme values in the folds. + \subsubsection{Dataset Partitioning}\label{subsubsec:dataset_partitioning} To ensure rigorous evaluation of our models and to address the challenges of data leakage and uneven distribution of extreme values, we have implemented a customized k-fold data partitioning procedure. This approach divides the dataset into $k$ folds, which are used to define cross-validation datasets, as well as a training set and a test set. From 436ff855a473fedb5615ff6a76345b5da7417320 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 14:43:28 +0200 Subject: [PATCH 2/9] maybe good tail to testing-validation to ref baseline approach --- report_thesis/src/sections/baseline_replica.tex | 2 +- .../src/sections/proposed_approach/testing_validation.tex | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/report_thesis/src/sections/baseline_replica.tex b/report_thesis/src/sections/baseline_replica.tex index 3b7bab71..4027ca4d 100644 --- a/report_thesis/src/sections/baseline_replica.tex +++ b/report_thesis/src/sections/baseline_replica.tex @@ -34,7 +34,7 @@ \section{Baseline \& Replica}\label{sec:baseline_replica} Following this discovery, we modified the replica to instead use the datasets in the same way as in the \gls{pls1-sm} phase, which yielded results aligning more closely with the original model. Furthermore, our initial replica used a random train/test split for training, in contrast to the original model's manual curation to ensure representation of extreme compositions in both sets. -This difference stemmed from the original authors' application of domain expertize in their dataset curation --- a process we could not directly replicate. +This difference stemmed from the original authors' application of domain expertise in their dataset curation --- a process we could not directly replicate. Nevertheless, we found that automatically identifying extreme compositions and ensuring that they were present in both the training and testing sets brought us closer to the original model. We chose to pull out the $n$ largest and smallest samples by concentration range, for each oxide, and reserve them for the training set. Then we would do a random split on the remaining dataset, such that the final train/test split would be a $80\%/20\%$ split. diff --git a/report_thesis/src/sections/proposed_approach/testing_validation.tex b/report_thesis/src/sections/proposed_approach/testing_validation.tex index cce488cf..d95cabbc 100644 --- a/report_thesis/src/sections/proposed_approach/testing_validation.tex +++ b/report_thesis/src/sections/proposed_approach/testing_validation.tex @@ -60,9 +60,11 @@ \subsection{Validation and Testing Procedures for Model Evaluation}\label{subsec In Section~\ref{sec:baseline_replica}, we described how we ensured representation of extreme compositions in both the training and testing sets by automatically identifying the $n$ largest and smallest samples by concentration range for each oxide and reserving them for the training set. We then performed a random split on the remaining dataset, resulting in a final train/test split of 80\%/20\%. -Then we would use a rudimentary procedure to prevent data leakage, ensuring that each target was only present once in the training set. +In this process, we also employ a rudimentary procedure to prevent data leakage, ensuring that each target was only present once in the training set. The baseline did not employ cross-validation, as our goal was to replicate the \gls{moc} model that was presented in \citet{cleggRecalibrationMarsScience2017}. -During experimentation, we discovered that the procedure was insufficient for this work, as it did not sufficiently handle the uneven distribution of extreme values, nor did it support $k$-fold cross-validation, which would additionally have to consider the distribution of extreme values in the folds. +We note that this procedure is insufficient to support the testing and validation strategy we have laid out above, as it does not support $k$-fold cross-validation. +A random $k$-fold split of the training data would not account for the uneven distribution of extreme values across the folds, and would furthermore cause data leakage between the folds. +Therefore, a more sophisticated procedure is needed to ensure that the data partitioning accounts for these challenges. \subsubsection{Dataset Partitioning}\label{subsubsec:dataset_partitioning} To ensure rigorous evaluation of our models and to address the challenges of data leakage and uneven distribution of extreme values, we have implemented a customized k-fold data partitioning procedure. From 6731da35526d368dfe947af4866ceea90ef2b704 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 15:10:14 +0200 Subject: [PATCH 3/9] add comparison of baseline vs. new test set --- .../eda/compare_old_vs_new_test_sets.ipynb | 186 ++++++++++++++++++ 1 file changed, 186 insertions(+) create mode 100644 baseline/eda/compare_old_vs_new_test_sets.ipynb diff --git a/baseline/eda/compare_old_vs_new_test_sets.ipynb b/baseline/eda/compare_old_vs_new_test_sets.ipynb new file mode 100644 index 00000000..7efb33a2 --- /dev/null +++ b/baseline/eda/compare_old_vs_new_test_sets.ipynb @@ -0,0 +1,186 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "from lib.full_flow_dataloader import load_full_flow_data\n", + "import pandas as pd\n", + "\n", + "train, test = load_full_flow_data()\n", + "full_data = pd.concat([train, test], axis=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "def plot_distribution_comparison(df1, df2, column, labels, colors, bins=30, figsize=(12, 6)):\n", + " \"\"\"\n", + " Plots the distribution comparison of a specified column between two dataframes.\n", + "\n", + " Parameters:\n", + " - df1: First dataframe\n", + " - df2: Second dataframe\n", + " - column: Column name to compare\n", + " - labels: Tuple of labels for the dataframes (label1, label2)\n", + " - colors: Tuple of colors for the histograms (color1, color2)\n", + " - bins: Number of bins for the histogram\n", + " - figsize: Size of the figure\n", + " \"\"\"\n", + " plt.figure(figsize=figsize)\n", + "\n", + " # Determine the range for the x-axis\n", + " min_val = min(df1[column].min(), df2[column].min())\n", + " max_val = max(df1[column].max(), df2[column].max())\n", + "\n", + " # Plot for first dataframe\n", + " plt.subplot(1, 2, 1)\n", + " plt.hist(df1[column], bins=bins, alpha=0.7, label=labels[0], range=(min_val, max_val), color=colors[0])\n", + " plt.title(f'Distribution of {column} in {labels[0]}')\n", + " plt.xlabel(column)\n", + " plt.ylabel('Frequency')\n", + " plt.legend()\n", + "\n", + " # Plot for second dataframe\n", + " plt.subplot(1, 2, 2)\n", + " plt.hist(df2[column], bins=bins, alpha=0.7, label=labels[1], range=(min_val, max_val), color=colors[1])\n", + " plt.title(f'Distribution of {column} in {labels[1]}')\n", + " plt.xlabel(column)\n", + " plt.ylabel('Frequency')\n", + " plt.legend()\n", + "\n", + " plt.tight_layout()\n", + " plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAABKUAAAJOCAYAAABm7rQwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABeeUlEQVR4nO3de3zP9f//8fvbZm8z2xxnW9jWnHKOJOaY1Qg5fkT6YBWqIaSDSqKy8CF0oPr2YckpfUJ8PkiYQyiHUCmnnIo5hM2Gxfb6/eG3t962sff23uv93na7Xi7vy6X36/h4v/aaPbq/n6/Xy2IYhiEAAAAAAADARMVcXQAAAAAAAACKHkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpFEqvv/66LBaLKftq3bq1WrdubXsfHx8vi8WiL774wpT99+/fX6GhoabsK7eSk5P15JNPKjAwUBaLRcOGDXPKds38OTvD7NmzZbFYdOTIEVeXYpqsfkahoaHq37+/awoCAOQ7+jD3Qh92XVHsw4CCgFAKbi/jD0jGq0SJEgoODlZUVJSmT5+uixcvOmU/J06c0Ouvv65du3Y5ZXvO5M615cT48eM1e/ZsPf3005ozZ47++c9/3nadtLQ0BQcHy2KxaMWKFTnaz6VLl/T+++/rwQcfVFBQkHx9fXX33XdrxowZSktLy3KdY8eO6amnnlJoaKisVqsCAgLUpUsXffvtt5mWPXHihB577DHVqFFDvr6+Kl26tO69917FxcXJMIwc1ehsf//dsFgs8vHxUa1atfTmm2/q0qVLLqnJHYWGhmY6Vlm9Zs+e7ZT9jR8/XkuWLHHKtgDAlejD3Lu2nKAPyz8ZvxeTJ0/ONC/jd2f79u0uqOy6nPQ+FotF8fHxed7XpUuX9PrrrztlWyhaPF1dAJBT48aNU1hYmK5evaqEhATFx8dr2LBhmjJlir766ivVq1fPtuyrr76ql156yaHtnzhxQmPHjlVoaKgaNGiQ4/W+/vprh/aTG7eq7eOPP1Z6enq+15AXa9eu1X333acxY8Y4tM7JkycVGhqquXPnqn379rdd57ffftOQIUPUtm1bjRgxQn5+flq1apWeeeYZbd26VXFxcXbLf/vtt3rooYckSU8++aRq1aqlhIQEzZ49Wy1atNC0adM0ZMgQ2/Jnz57V77//rh49eqhKlSq6evWqVq9erf79+2vfvn0aP378Lev75z//qV69eslqteb4OOTEAw88oL59+0q6/m3oxo0bNXr0aO3evVuLFi1y6r6cYd++fSpWzNzvRKZOnark5GTb+//973+aP3++3nnnHZUvX942vVmzZk7Z3/jx49WjRw916dLFKdsDAFejD6MPu52i2odJ0qRJk/T000+rZMmSTt92XsyZM8fu/aeffqrVq1dnmn7XXXfleV+XLl3S2LFjJclu9CJwWwbg5mbNmmVIMrZt25Zp3po1awxvb28jJCTEuHTpUp72s23bNkOSMWvWrBwtn5KSkuX0devWGZKMRYsW5amevNTmbsLCwowOHTo4tE7fvn2Nhg0bGtOmTTN8fHyM5OTkTMuMGTPG+Ps/Y2fOnDF++umnTMtFR0cbkowDBw7Ypp07d84IDAw0KlasaBw8eNBu+UuXLhktWrQwihUrZnz77be3rbVjx46Gj4+Pce3aNUc+olNIMmJiYjJN79Gjh1GsWDHj8uXLptf0dzf/jNzFpEmTDEnG4cOH82X7Pj4+Rr9+/fJl2wBgJvow+jD6sOxJMho0aGBIMiZPnmw371a/O64SExOTb33ZmTNnDEnGmDFj8mX7KLy4fA8F2v3336/Ro0fr6NGj+uyzz2zTs7rGffXq1WrevLlKly6tUqVKqUaNGnr55ZclXb//QOPGjSVJ0dHRmS7lad26terUqaMdO3aoZcuWKlmypG3dm+9lkCEtLU0vv/yyAgMD5ePjo4cffljHjx+3Wya7e+v8fZu3qy2rexmkpKToueeeU+XKlWW1WlWjRg3961//yjS02WKxaPDgwVqyZInq1Kkjq9Wq2rVra+XKlVkf8JucPn1aTzzxhCpWrKgSJUqofv36dt+CZdzX4fDhw/rvf/9rq/121/JfvnxZixcvVq9evdSzZ09dvnxZS5cuvW095cuXV+3atTNN79q1qyTpl19+sU378MMPlZCQoEmTJik8PNxueW9vb8XFxclisWjcuHG33W9oaKguXbqkv/7665bLZXUvg9DQUHXs2FGbNm3SvffeqxIlSujOO+/Up59+etv93krGfSM8PW8MiN24caP+8Y9/qEqVKrJarapcubKGDx+uy5cv262bkJCg6OhoVapUSVarVUFBQercuXOmn9uKFSvUokUL+fj4yNfXVx06dNDPP/9829puPu8zjsu3336rESNGqEKFCvLx8VHXrl115syZTOvndr858dlnn6lRo0by9vZW2bJl1atXr0y/twcOHFD37t0VGBioEiVKqFKlSurVq5cSExMlXf+9SklJsZ1DFouFe2gBKJTow+jD/q6o9mERERG6//77NXHixEw9VVZ+/fVX9ejRQ2XLllWJEiV0zz336KuvvrLNv3Dhgjw8PDR9+nTbtLNnz6pYsWIqV66c3Xn09NNPKzAwMMe1ZiU9PV1Tp05V7dq1VaJECVWsWFGDBg3S+fPn7Zbbvn27oqKiVL58eXl7eyssLEyPP/64JOnIkSOqUKGCJGns2LG2c+3111/PU20oGgilUOBlXBd/q+HbP//8szp27KjU1FSNGzdOkydP1sMPP2y7Xv2uu+6y/dEbOHCg5syZozlz5qhly5a2bfz5559q3769GjRooKlTp6pNmza3rOutt97Sf//7X7344osaOnSoVq9ercjIyBz9sfq7nNT2d4Zh6OGHH9Y777yjdu3aacqUKapRo4aef/55jRgxItPymzZt0jPPPKNevXpp4sSJunLlirp3764///zzlnVdvnxZrVu31pw5c9SnTx9NmjRJ/v7+6t+/v6ZNm2arfc6cOSpfvrwaNGhgqz3jj1Z2vvrqKyUnJ6tXr14KDAxU69atNXfu3JwcriwlJCRIkt1lWsuWLVOJEiXUs2fPLNcJCwtT8+bNtXbt2kw/s8uXL+vs2bM6cuSI4uLiNGvWLDVt2lTe3t65qu/gwYPq0aOHHnjgAU2ePFllypRR//79cxy0XLlyRWfPntXZs2d19OhRzZs3T3FxcXr00UftQqlFixbp0qVLevrpp/Xuu+8qKipK7777ru3Svwzdu3fX4sWLFR0drQ8++EBDhw7VxYsXdezYMdsyc+bMUYcOHVSqVClNmDBBo0eP1t69e9W8efNc30B0yJAh2r17t8aMGaOnn35ay5Yt0+DBg+2WyY/9ZnjrrbfUt29fVatWTVOmTNGwYcO0Zs0atWzZUhcuXJAk/fXXX4qKitLWrVs1ZMgQvf/++xo4cKB+++032zJz5syR1WpVixYtbOf8oEGD8lQbALgr+jB79GGZFfY+TLoexJ46dUozZsy45XI///yz7rvvPv3yyy966aWXNHnyZPn4+KhLly5avHixJKl06dKqU6eONmzYYFtv06ZNslgsOnfunPbu3WubvnHjRrVo0cLBT2xv0KBBev755xUREaFp06YpOjpac+fOVVRUlK5evSrpegD64IMP6siRI3rppZf07rvvqk+fPtq6daskqUKFCrbP3rVrV9u51q1btzzVhiLCpeO0gBzIydBXf39/4+6777a9v3k48TvvvGNIMs6cOZPtNm41NLtVq1aGJGPmzJlZzmvVqpXtfcaw8TvuuMNISkqyTf/8888NSca0adNs00JCQrK8xOfmbd6qtn79+hkhISG290uWLDEkGW+++abdcj169DAsFovdEGlJhpeXl9203bt3G5KMd999N9O+/m7q1KmGJOOzzz6zTfvrr7+Mpk2bGqVKlbL77CEhIQ4NG+/YsaMRERFhe//RRx8Znp6exunTp+2Wy8mlYampqUatWrWMsLAw4+rVq7bppUuXNurXr3/LdYcOHWpIMvbs2WM3PTY21pBke7Vt29Y4duzYbT9Xxrn890vGQkJCDEnGhg0bbNNOnz5tWK1W47nnnrvtNv9ex99fXbp0Ma5cuWK3bFaXVsTGxhoWi8U4evSoYRiGcf78eUOSMWnSpGz3efHiRaN06dLGgAED7KYnJCQY/v7+dtOz+hndfN5nHJfIyEgjPT3dNn348OGGh4eHceHCBYf3ezs3X7535MgRw8PDw3jrrbfslvvxxx8NT09P2/QffvghR5eFcPkegMKCPow+jD4se/rbbRTatGljBAYG2vqtrH532rZta9StW9euR0tPTzeaNWtmVKtWzTYtJibGqFixou39iBEjjJYtWxoBAQHGjBkzDMMwjD///NOwWCx25/Tt3Hz53saNGw1Jxty5c+2WW7lypd30xYsX3/bfAS7fQ24xUgqFQqlSpW759JfSpUtLkpYuXZrrm1FarVZFR0fnePm+ffvK19fX9r5Hjx4KCgrS//73v1ztP6f+97//ycPDQ0OHDrWb/txzz8kwjExPUImMjLQbNl2vXj35+fnpt99+u+1+AgMD1bt3b9u04sWLa+jQoUpOTtb69etzVf+ff/6pVatW2W23e/fuslgs+vzzzx3e3uDBg7V371699957dqOGLl68aPfzyUrG/KSkJLvpvXv31urVqzVv3jw9+uijkuTwN69/V6tWLbtvuSpUqKAaNWrc9meQoXPnzlq9erVWr16tpUuXatSoUVq5cqUeffRRuyHef/8GMSUlRWfPnlWzZs1kGIZ++OEH2zJeXl6Kj4/PNGw7w+rVq3XhwgX17t3bNkLr7Nmz8vDwUJMmTbRu3brcHAYNHDjQ7nKPFi1aKC0tTUePHs3X/UrSl19+qfT0dPXs2dNu24GBgapWrZpt2/7+/pKkVatW8XRDAPj/6MNuoA+zVxT6sAyvv/66EhISNHPmzCznnzt3TmvXrlXPnj118eJFW6/x559/KioqSgcOHNAff/wh6XoPdOrUKe3bt0/S9RFRLVu2VIsWLbRx40ZJ10dPGYaRp5FSixYtkr+/vx544AG7/qdRo0YqVaqUrf/J+B1evny5bfQU4CyEUigUkpOTb/mH7ZFHHlFERISefPJJVaxYUb169dLnn3/uUGN0xx13yMvLK8fLV6tWze69xWJR1apV83yJ0e0cPXpUwcHBmY5HxlM1Mv4HP0OVKlUybaNMmTLZBhJ/30+1atUyPUUtu/3k1MKFC3X16lXdfffdOnjwoA4ePKhz586pSZMmDg8dnzRpkj7++GO98cYbtqe7ZPD19b3tY6wz5t98LENCQhQZGanevXtr7ty5uvPOO3N1SUCG3P4MMlSqVEmRkZGKjIzUww8/rPHjx+vNN9/Ul19+qeXLl9uWO3bsmPr376+yZcuqVKlSqlChglq1aiVJtvshWa1WTZgwQStWrFDFihXVsmVLTZw40Tb0Xrp+TyXp+r1EKlSoYPf6+uuvdfr0aacchzJlykiS7Tjk134ztm0YhqpVq5Zp27/88ott22FhYRoxYoT+7//+T+XLl1dUVJTef/992/EDgKKIPuwG+rAbikoflqFly5Zq06ZNtveWOnjwoAzD0OjRozP1GhlPRszoNzKCpo0bNyolJUU//PCDWrRooZYtW9pCqY0bN8rPz0/169d3qM6/O3DggBITExUQEJCppuTkZFs9rVq1Uvfu3TV27FiVL19enTt31qxZs5SamprrfQMZPG+/CODefv/9dyUmJqpq1arZLuPt7a0NGzZo3bp1+u9//6uVK1dq4cKFuv/++/X111/Lw8PjtvvJ7XXqt3LzTUAzpKWl5agmZ8huP38fYWOmjIYnIiIiy/m//fab7rzzzttuZ/bs2XrxxRf11FNP6dVXX800/6677tIPP/yg1NTUbB8NvGfPHhUvXjxTY3uzHj166OOPP9aGDRsUFRV129pulh8/g7Zt20qSNmzYoE6dOiktLU0PPPCAzp07pxdffFE1a9aUj4+P/vjjD/Xv39/ufwyGDRumTp06acmSJVq1apVGjx6t2NhYrV27Vnfffbdt2Tlz5mR5c82/fxPqiNsdh/zab8a2LRaLVqxYkWUdpUqVsv335MmT1b9/fy1dulRff/21hg4dqtjYWG3dulWVKlXKdQ0AUBDRh+UNfVjh6sPGjBmj1q1b68MPP7SNLsqQ0ceMHDky2zozfo+Cg4MVFhamDRs2KDQ0VIZhqGnTpqpQoYKeffZZHT16VBs3blSzZs0yBZOOSE9PV0BAQLaBY8b9xywWi7744gtt3bpVy5Yt06pVq/T4449r8uTJ2rp1q12fBDiKUAoF3pw5cyTptn+EihUrprZt26pt27aaMmWKxo8fr1deeUXr1q1TZGRkto1JbmWM6shgGIYOHjyoevXq2aaVKVPGdnPkvzt69KjdH3xHagsJCdE333yTaVj0r7/+apvvDCEhIdqzZ4/S09Pt/hjmZT+HDx/W5s2bNXjwYNsIngzp6en65z//qXnz5mXZ3Pzd0qVL9eSTT6pbt256//33s1ymY8eO2rJlixYtWqTHHnss0/wjR45o48aNioyMvG0jnPFtmDuNlrl27Zqk699eS9KPP/6o/fv3Ky4uzu7G5qtXr85y/fDwcD333HN67rnndODAATVo0ECTJ0/WZ599ZrvMICAgQJGRkfn8Sexryq/9hoeHyzAMhYWFqXr16rddvm7duqpbt65effVVbd68WREREZo5c6befPNNSY79zgJAQUYfZo8+rGj3Ya1atVLr1q01YcIEvfbaa3bzMs6p4sWL56iPadGihTZs2KCwsDA1aNBAvr6+ql+/vvz9/bVy5Urt3LlTY8eOzVO94eHh+uabbxQREZGj4Pe+++7Tfffdp7feekvz5s1Tnz59tGDBAj355JP0Psg1Lt9DgbZ27Vq98cYbCgsLU58+fbJd7ty5c5mmNWjQQJJsw059fHwkKcvmJDc+/fRTu2HJX3zxhU6ePKn27dvbpoWHh2vr1q12j7Bdvnx5pkcWO1LbQw89pLS0NL333nt209955x1ZLBa7/efFQw89pISEBC1cuNA27dq1a3r33XdVqlSpTM1MTmR8S/PCCy+oR48edq+ePXuqVatWtx06vmHDBvXq1UstW7bU3Llzs/32aNCgQQoICNDzzz+f6Z4BV65cUXR0tAzDsGsozpw5k+W2PvnkE1ksFjVs2NCRj5uvli1bJkm2Id0Z3wL+/Vs/wzBsT+jJcOnSJV25csVuWnh4uHx9fW2/K1FRUfLz89P48eOzvK9Adscpr/Jzv926dZOHh4fGjh2b6ZtRwzBsT0FKSkqyBX4Z6tatq2LFitkNYffx8XHavyUA4K7owzKjD6MPy7i31EcffWQ3PSAgwDaK6uTJk5nWu/nztWjRQkeOHNHChQttl/MVK1ZMzZo105QpU3T16tU8P3mvZ8+eSktL0xtvvJFp3rVr12zn/Pnz5zP1Rzf/DpcsWVKS836HUXQwUgoFxooVK/Trr7/q2rVrOnXqlNauXavVq1crJCREX331lUqUKJHtuuPGjdOGDRvUoUMHhYSE6PTp0/rggw9UqVIlNW/eXNL1xqR06dKaOXOmfH195ePjoyZNmigsLCxX9ZYtW1bNmzdXdHS0Tp06palTp6pq1aoaMGCAbZknn3xSX3zxhdq1a6eePXvq0KFDdiNRMjhSW6dOndSmTRu98sorOnLkiOrXr6+vv/5aS5cu1bBhwzJtO7cGDhyoDz/8UP3799eOHTsUGhqqL774Qt9++62mTp1625tXZmXu3Llq0KCBKleunOX8hx9+WEOGDNHOnTuzbDyOHj2qhx9+WBaLRT169NCiRYvs5terV8/2DWm5cuX0xRdfqEOHDmrYsKGefPJJ1apVSwkJCZo9e7YOHjyoadOmqVmzZrb133rrLX377bdq166dqlSponPnzuk///mPtm3bpiFDhtzy0oX8tH//fn322WeSrodKW7duVVxcnKpWrWp7VHfNmjUVHh6ukSNH6o8//pCfn5/+85//ZLpfwv79+9W2bVv17NlTtWrVkqenpxYvXqxTp06pV69ekiQ/Pz/NmDFD//znP9WwYUP16tVLFSpU0LFjx/Tf//5XERERmZpxZ8jP/YaHh+vNN9/UqFGjdOTIEXXp0kW+vr46fPiwFi9erIEDB2rkyJFau3atBg8erH/84x+qXr26rl27pjlz5sjDw0Pdu3e3ba9Ro0b65ptvNGXKFNsQ/CZNmjjrUACA6ejD6MPow3KmVatWatWqVZY3m3///ffVvHlz1a1bVwMGDNCdd96pU6dOacuWLfr999+1e/du27IZgdO+ffs0fvx42/SWLVtqxYoVslqtaty4cZ5rHTRokGJjY7Vr1y49+OCDKl68uA4cOKBFixZp2rRp6tGjh+Li4vTBBx+oa9euCg8P18WLF/Xxxx/Lz8/Pdr8wb29v1apVSwsXLlT16tVVtmxZ1alTR3Xq1MlTjSgCTHzSH5ArGY9TzXh5eXkZgYGBxgMPPGBMmzbN7pG3GW5+RO2aNWuMzp07G8HBwYaXl5cRHBxs9O7d29i/f7/dekuXLjVq1apleHp62j36t1WrVkbt2rWzrC+7RxHPnz/fGDVqlBEQEGB4e3sbHTp0MI4ePZpp/cmTJxt33HGHYbVajYiICGP79u2Ztnmr2m5+FLFhGMbFixeN4cOHG8HBwUbx4sWNatWqGZMmTTLS09PtltPfHmP7d9k9Ivlmp06dMqKjo43y5csbXl5eRt26dbN8XHJOHkW8Y8cOQ5IxevTobJc5cuSIIckYPny4YRiZf84Zxz67V1aPqD18+LAxYMAAo0qVKkbx4sWN8uXLGw8//LCxcePGTMt+/fXXRseOHW3H1dfX14iIiDBmzZqV6dhmJbtHEWd1bLI6B7Jy82f08PAwKlWqZAwcONA4deqU3bJ79+41IiMjjVKlShnly5c3BgwYYHv0dMbP7ezZs0ZMTIxRs2ZNw8fHx/D39zeaNGlifP7555n2vW7dOiMqKsrw9/c3SpQoYYSHhxv9+/c3tm/fblsmq8dF33x+Zfe48Yyf57p16xze7+1MmjQp08/CMAzjP//5j9G8eXPDx8fH8PHxMWrWrGnExMQY+/btMwzDMH777Tfj8ccfN8LDw40SJUoYZcuWNdq0aWN88803dtv59ddfjZYtWxre3t6GpBz9PgGAO6IPu3Vt9GH0YVn9DP9+LG7ubw4dOmT07dvXCAwMNIoXL27ccccdRseOHY0vvvgi03YCAgIMSXY93aZNmwxJRosWLW5b381iYmIy9WWGYRgfffSR0ahRI8Pb29vw9fU16tata7zwwgvGiRMnDMMwjJ07dxq9e/c2qlSpYlitViMgIMDo2LFjpt5r8+bNRqNGjQwvL69sf+bAzSyG4aK76AEAAAAAAKDI4p5SAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAEzn6eoC8lt6erpOnDghX19fWSwWV5cDAAAKGMMwdPHiRQUHB6tYsaLxfR79EwAAyIuc9k+FPpQ6ceKEKleu7OoyAABAAXf8+HFVqlTJ1WWYgv4JAAA4w+36p0IfSvn6+kq6fiD8/PxcXA0AAChokpKSVLlyZVtPURTQPwEAgLzIaf9U6EOpjCHnfn5+NFUAACDXitJlbPRPAADAGW7XPxWNGyMAAAAAAADArRBKAQAAAAAAwHSEUgAAAAAAADBdob+nFACgaEtLS9PVq1ddXQbcWPHixeXh4eHqMgAAKNLo2QoWZ/VPhFIAgELJMAwlJCTowoULri4FBUDp0qUVGBhYpG5mDgCAO6BnK7ic0T8RSgEACqWM5iYgIEAlS5YkbECWDMPQpUuXdPr0aUlSUFCQiysCAKBooWcreJzZPxFKAQAKnbS0NFtzU65cOVeXAzfn7e0tSTp9+rQCAgK4lA8AAJPQsxVczuqfuNE5AKDQybgfQcmSJV1cCQqKjHOFe1kAAGAeeraCzRn9E6EUAKDQYvg3copzBQAA1+HvcMHkjJ8boRQAAAAAAABMRygFAADshIaGaurUqbb3FotFS5YscVk9AAAAKJy40TkAoEjp1Mm8fS1b5tjy/fv3V1xcnO192bJl1bhxY02cOFH16tVzcnU5d/LkSZUpUybftt+6dWutX78+2/mtWrVSfHx8rrfdoEEDu5ANAAAUAPEmNm2S1Nqxxi2jb4uNjdVLL71km75kyRJ17dpVhmE4u8JMZs+erejo6Fsuc/jwYYWGhuZq28OGDdOFCxdyV1wOMVIKAAA30q5dO508eVInT57UmjVr5OnpqY4dO7q0psDAQFmt1nzb/pdffmn7zN9//70k6ZtvvrFN+/LLL/Nt3wAAALlVokQJTZgwQefPn3fJ/h955BFbv3Ty5Ek1bdpUAwYMsJtWuXJll9SWU4RSAAC4EavVqsDAQAUGBqpBgwZ66aWXdPz4cZ05c8a2zIsvvqjq1aurZMmSuvPOOzV69Gi7p57s3r1bbdq0ka+vr/z8/NSoUSNt377dNn/Tpk1q0aKFvL29VblyZQ0dOlQpKSnZ1vT3y/eOHDkii8WiL7/8Um3atFHJkiVVv359bdmyxW4dR/ZRtmxZ22euUKGCJKlcuXK2aXv37r3ltj744ANVq1ZNJUqUUMWKFdWjRw9J17/BXL9+vaZNmyaLxSKLxaIjR47k7AcBAABwG5GRkQoMDFRsbOwtl7tVX/Tee++pTp06tmWXLFkii8WimTNn2u3n1VdfzbRdb29vW78UGBgoLy8vlSxZ0va+RIkSGjRokCpUqCA/Pz/df//92r17t2397HrG+Ph4RUdHKzEx0dZDvf7663k8WlkjlAIAwE0lJyfrs88+U9WqVVWuXDnbdF9fX82ePVt79+7VtGnT9PHHH+udd96xze/Tp48qVaqkbdu2aceOHXrppZdUvHhxSdKhQ4fUrl07de/eXXv27NHChQu1adMmDR482KHaXnnlFY0cOVK7du1S9erV1bt3b127ds2p+8jJtrZv366hQ4dq3Lhx2rdvn1auXKmWLVtKkqZNm5bpG0N3/7YQAAAUHB4eHho/frzeffdd/f7771kuc7teplWrVtq7d6/tC8j169erfPnytlsXXL16VVu2bFHr1q0dru8f//iHTp8+rRUrVmjHjh1q2LCh2rZtq3PnzknKvmds1qyZpk6dKj8/P1sPNXLkSMcPUA5wTykAANzI8uXLVapUKUlSSkqKgoKCtHz5chUrduN7pL9/UxYaGqqRI0dqwYIFeuGFFyRJx44d0/PPP6+aNWtKkqpVq2ZbPjY2Vn369NGwYcNs86ZPn65WrVppxowZKlGiRI7qHDlypDp06CBJGjt2rGrXrq2DBw+qZs2aTttHTuo9duyYfHx81LFjR/n6+iokJER33323JMnf39/uG0MAAABn69q1qxo0aKAxY8bok08+yTT/dr1MnTp1VLZsWa1fv149evRQfHy8nnvuOU2bNk2S9P333+vq1atq1qyZQ3Vt2rRJ33//vU6fPm27DcO//vUvLVmyRF988YUGDhx4y57R399fFosl33soRkoBAOBG2rRpo127dmnXrl36/vvvFRUVpfbt2+vo0aO2ZRYuXKiIiAgFBgaqVKlSevXVV3Xs2DHb/BEjRujJJ59UZGSk3n77bR06dMg2b/fu3Zo9e7ZKlSple0VFRSk9PV2HDx/OcZ1/v/F6UFCQJOn06dNO3UdOtvXAAw8oJCREd955p/75z39q7ty5unTpkkP7AAAAyIsJEyYoLi5Ov/zyS6Z5t+tlLBaLWrZsqfj4eF24cEF79+7VM888o9TUVP36669av369GjdurJIlSzpU0+7du5WcnKxy5crZ7fvw4cO23vBWPaNZCKUAAHAjPj4+qlq1qqpWrarGjRvr//7v/5SSkqKPP/5YkrRlyxb16dNHDz30kJYvX64ffvhBr7zyiv766y/bNl5//XX9/PPP6tChg9auXatatWpp8eLFkq5fEjho0CBb8LVr1y7t3r1bBw4cUHh4eI7rzLgcULp+zylJSk9Pd+o+crItX19f7dy5U/Pnz1dQUJBee+011a9fP9+fFONqGzZsUKdOnRQcHGx3z68MhmHotddeU1BQkLy9vRUZGakDBw64plgAAAq5li1bKioqSqNGjco0Lyd9UevWrRUfH6+NGzfq7rvvlp+fny2oWr9+vVq1auVwTcnJyQoKCrLb765du7Rv3z49//zzkm7dM5qFy/cAAHBjFotFxYoV0+XLlyVJmzdvVkhIiF555RXbMn8fRZWhevXqql69uoYPH67evXtr1qxZ6tq1qxo2bKi9e/eqatWq+VazM/eRk215enoqMjJSkZGRGjNmjEqXLq21a9eqW7du8vLyUlpaWp7rcDcpKSmqX7++Hn/8cXXr1i3T/IkTJ2r69OmKi4tTWFiYRo8eraioKO3du9ehyycBAEDOvP3222rQoIFq1KhhNz0nvUyrVq00bNgwLVq0yHbvqNatW+ubb77Rt99+q+eee87heho2bKiEhAR5enoqNDQ02+Wy6xnN6qEYKQUAgBtJTU1VQkKCEhIS9Msvv2jIkCFKTk5Wp06dJF2/1v/YsWNasGCBDh06pOnTp9t9o3X58mUNHjxY8fHxOnr0qL799ltt27ZNd911l6TrT+7bvHmzBg8erF27dunAgQNaunRprm5Cnh1n7uN221q+fLmmT5+uXbt26ejRo/r000+Vnp5uawhDQ0P13Xff6ciRIzp79qxtNFdB1759e7355pvq2rVrpnmGYWjq1Kl69dVX1blzZ9WrV0+ffvqpTpw4kWlEFQAAcI66deuqT58+mj59ut30nPRF9erVU5kyZTRv3jy7UGrJkiVKTU1VRESEw/VERkaqadOm6tKli77++msdOXJEmzdv1iuvvKLt27fftmcMDQ1VcnKy1qxZo7Nnz+bb7REIpQAAcCMrV65UUFCQgoKC1KRJE23bts3uW7OHH35Yw4cP1+DBg9WgQQNt3rxZo0ePtq3v4eGhP//8U3379lX16tXVs2dPtW/fXmPHjpV0velZv3699u/frxYtWujuu+/Wa6+9puDgYKd9Bmfu43bbKl26tL788kvdf//9uuuuuzRz5kzNnz9ftWvXlnT9huweHh6qVauWKlSoYHfvrcLq8OHDSkhIUGRkpG2av7+/mjRpoi1btmS5TmpqqpKSkuxeAADAMePGjcv0BVhO+iKLxaIWLVrIYrGoefPmtvX8/Px0zz33yMfHx+FaLBaL/ve//6lly5aKjo5W9erV1atXLx09elQVK1a8bc/YrFkzPfXUU3rkkUdUoUIFTZw4MQ9H5hZ1GoZh5MuW3URSUpL8/f2VmJgoPz8/V5cDoBD6/wNYcm3ZMufUgRuuXLmiw4cPKywsjEuVkCO3OmfcvZewWCxavHixunTpIun6JZ4RERE6ceKE7Sb0ktSzZ09ZLBYtXLgw0zZef/11WxP6d+76mQG4ifg8NkGtaYKKOnq2gs0Z/RMjpQAAAIq4UaNGKTEx0fY6fvy4q0sCAABFAKEUAABAIRIYGChJOnXqlN30U6dO2ebdzGq1ys/Pz+4FAACQ3wilAAAACpGwsDAFBgZqzZo1tmlJSUn67rvv1LRpUxdWBgAAYM/T1QUAAADAMcnJyTp48KDt/eHDh7Vr1y6VLVtWVapU0bBhw/Tmm2+qWrVqCgsL0+jRoxUcHGy77xQAAIA7IJQCAAAoYLZv3642bdrY3o8YMUKS1K9fP82ePVsvvPCCUlJSNHDgQF24cEHNmzfXypUruYksAABwK4RSAIBC6+ZH8gLZKWjnSuvWrXWrByhbLBaNGzdO48aNM7EqAAByp6D9HcZ1zvi5EUoBAAodLy8vFStWTCdOnFCFChXk5eUli8Xi6rLghgzD0F9//aUzZ86oWLFi8vLycnVJAAAUGfRsBZMz+ydCKQBAoVOsWDGFhYXp5MmTOnHihKvLQQFQsmRJValSRcWK8QwYAADMQs9WsDmjfyKUAgAUSl5eXqpSpYquXbumtLQ0V5cDN+bh4SFPT0++mQUAwAXo2QomZ/VPhFIAgELLYrGoePHiKl68uKtLAQAAQDbo2YouxqgDAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdC4NpTZs2KBOnTopODhYFotFS5YssZtvGIZee+01BQUFydvbW5GRkTpw4IBrigUAAAAAAIDTuDSUSklJUf369fX+++9nOX/ixImaPn26Zs6cqe+++04+Pj6KiorSlStXTK4UAAAAAAAAzuTpyp23b99e7du3z3KeYRiaOnWqXn31VXXu3FmS9Omnn6pixYpasmSJevXqZWapAAAAAAAAcCK3vafU4cOHlZCQoMjISNs0f39/NWnSRFu2bMl2vdTUVCUlJdm9AAAAAAAA4F7cNpRKSEiQJFWsWNFuesWKFW3zshIbGyt/f3/bq3LlyvlaJwAAAAAAABzntqFUbo0aNUqJiYm21/Hjx11dEgAAAAAAAG7itqFUYGCgJOnUqVN200+dOmWblxWr1So/Pz+7FwAAAAAAANyL24ZSYWFhCgwM1Jo1a2zTkpKS9N1336lp06YurAwAAAAAAAB55dKn7yUnJ+vgwYO294cPH9auXbtUtmxZValSRcOGDdObb76patWqKSwsTKNHj1ZwcLC6dOniuqIBAAAAAHkX3ylv67de5pw6ALiMS0Op7du3q02bNrb3I0aMkCT169dPs2fP1gsvvKCUlBQNHDhQFy5cUPPmzbVy5UqVKFHCVSUDAAAAAADACVwaSrVu3VqGYWQ732KxaNy4cRo3bpyJVQEAAAAAACC/ue09pQAAAAAAAFB4EUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTebq6AADo1Clv6y9b5pw6AAAAAADmYaQUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAACFTFpamkaPHq2wsDB5e3srPDxcb7zxhgzDcHVpAAAANtzoHAAAoJCZMGGCZsyYobi4ONWuXVvbt29XdHS0/P39NXToUFeXBwAAIIlQCgAAoNDZvHmzOnfurA4dOkiSQkNDNX/+fH3//fcurgwAAOAGLt8DAAAoZJo1a6Y1a9Zo//79kqTdu3dr06ZNat++fZbLp6amKikpye4FAACQ3xgpBQAAUMi89NJLSkpKUs2aNeXh4aG0tDS99dZb6tOnT5bLx8bGauzYsSZXCQAAijpGSgEAABQyn3/+uebOnat58+Zp586diouL07/+9S/FxcVlufyoUaOUmJhoex0/ftzkigEAQFHESCkAAIBC5vnnn9dLL72kXr16SZLq1q2ro0ePKjY2Vv369cu0vNVqldVqNbtMAABQxDFSCgAAoJC5dOmSihWzb/M8PDyUnp7uoooAAAAyY6QUAABAIdOpUye99dZbqlKlimrXrq0ffvhBU6ZM0eOPP+7q0gAAAGwIpQAAAAqZd999V6NHj9Yzzzyj06dPKzg4WIMGDdJrr73m6tIAAABsCKUAAAAKGV9fX02dOlVTp051dSkAAADZ4p5SAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdG4dSqWlpWn06NEKCwuTt7e3wsPD9cYbb8gwDFeXBgAAAAAAgDzwdHUBtzJhwgTNmDFDcXFxql27trZv367o6Gj5+/tr6NChri4PAAAAAAAAueTWodTmzZvVuXNndejQQZIUGhqq+fPn6/vvv3dxZQAAAAAAAMgLt758r1mzZlqzZo32798vSdq9e7c2bdqk9u3bZ7tOamqqkpKS7F4AAAAAAABwL249Uuqll15SUlKSatasKQ8PD6Wlpemtt95Snz59sl0nNjZWY8eONbFKAJ06uboCAAAAAEBB49YjpT7//HPNnTtX8+bN086dOxUXF6d//etfiouLy3adUaNGKTEx0fY6fvy4iRUDAAAAAAAgJ9x6pNTzzz+vl156Sb169ZIk1a1bV0ePHlVsbKz69euX5TpWq1VWq9XMMgEAAAAAAOAgtx4pdenSJRUrZl+ih4eH0tPTXVQRAAAAAAAAnMGtR0p16tRJb731lqpUqaLatWvrhx9+0JQpU/T444+7ujQAAAAAAADkgVuHUu+++65Gjx6tZ555RqdPn1ZwcLAGDRqk1157zdWlAQAAAAAAIA/cOpTy9fXV1KlTNXXqVFeXAgAAAAAAACdy63tKAQAAAAAAoHAilAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpPF1dAAAAAAAUOfGdXF2B1HqZqysAUMQxUgoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6TxdXQAAuFqnTq6uAAAAAACKHkZKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAFEJ//PGHHnvsMZUrV07e3t6qW7eutm/f7uqyAAAAbDxdXQAAAACc6/z584qIiFCbNm20YsUKVahQQQcOHFCZMmVcXRoAAIANoRQAAEAhM2HCBFWuXFmzZs2yTQsLC3NhRQAAAJlx+R4AAEAh89VXX+mee+7RP/7xDwUEBOjuu+/Wxx9/nO3yqampSkpKsnsBAADkN0IpAACAQua3337TjBkzVK1aNa1atUpPP/20hg4dqri4uCyXj42Nlb+/v+1VuXJlkysGAABFEaEUAABAIZOenq6GDRtq/PjxuvvuuzVw4EANGDBAM2fOzHL5UaNGKTEx0fY6fvy4yRUDAICiiFAKAACgkAkKClKtWrXspt111106duxYlstbrVb5+fnZvQAAAPJbrkKp3377zdl1AAAAFHpm9VARERHat2+f3bT9+/crJCTElP0DAADkRK5CqapVq6pNmzb67LPPdOXKFWfXBAAAUCiZ1UMNHz5cW7du1fjx43Xw4EHNmzdPH330kWJiYvJtnwAAAI7KVSi1c+dO1atXTyNGjFBgYKAGDRqk77//3tm1AQAAFCpm9VCNGzfW4sWLNX/+fNWpU0dvvPGGpk6dqj59+jh9XwAAALmVq1CqQYMGmjZtmk6cOKF///vfOnnypJo3b646depoypQpOnPmjLPrBAAAKPDM7KE6duyoH3/8UVeuXNEvv/yiAQMGOG3bAAAAzpCnG517enqqW7duWrRokSZMmKCDBw9q5MiRqly5svr27auTJ086q04AAIBCgx4KAAAgj6HU9u3b9cwzzygoKEhTpkzRyJEjdejQIa1evVonTpxQ586dnVUnAABAoUEPBQAAIHnmZqUpU6Zo1qxZ2rdvnx566CF9+umneuihh1Ss2PWMKywsTLNnz1ZoaKgzawUAACjQ6KEAAABuyFUoNWPGDD3++OPq37+/goKCslwmICBAn3zySZ6KAwAAKEzooQAAAG7IVSh14MCB2y7j5eWlfv365WbzAAAAhRI9FAAAwA25uqfUrFmztGjRokzTFy1apLi4uDwXBQAAUBjRQwEAANyQq1AqNjZW5cuXzzQ9ICBA48ePz3NRAAAAhRE9FAAAwA25CqWOHTumsLCwTNNDQkJ07NixPBcFAABQGNFDAQAA3JCrUCogIEB79uzJNH337t0qV65cnosCAAAojOihAAAAbshVKNW7d28NHTpU69atU1pamtLS0rR27Vo9++yz6tWrl7NrBAAAKBTooQAAAG7I1dP33njjDR05ckRt27aVp+f1TaSnp6tv377cDwEAACAb9FAAAAA35CqU8vLy0sKFC/XGG29o9+7d8vb2Vt26dRUSEuLs+gAAAAoNeigAAIAbchVKZahevbqqV6/urFoAAACKBHooAACAXIZSaWlpmj17ttasWaPTp08rPT3dbv7atWudUhwAAEBhQg8FAABwQ65CqWeffVazZ89Whw4dVKdOHVksFmfXBQAAUOjQQwEAANyQq1BqwYIF+vzzz/XQQw85u55M/vjjD7344otasWKFLl26pKpVq2rWrFm655578n3fAAAAzmRmDwUAAODucn2j86pVqzq7lkzOnz+viIgItWnTRitWrFCFChV04MABlSlTJt/3DQAA4Gxm9VAAAAAFQbHcrPTcc89p2rRpMgzD2fXYmTBhgipXrqxZs2bp3nvvVVhYmB588EGFh4fn634BAADyg1k9FAAAQEGQq5FSmzZt0rp167RixQrVrl1bxYsXt5v/5ZdfOqW4r776SlFRUfrHP/6h9evX64477tAzzzyjAQMGOGX7AAAAZjKrhwIAACgIchVKlS5dWl27dnV2LZn89ttvmjFjhkaMGKGXX35Z27Zt09ChQ+Xl5aV+/fpluU5qaqpSU1Nt75OSkvK9TgAAgJwwq4cCAAAoCHIVSs2aNcvZdWQpPT1d99xzj8aPHy9Juvvuu/XTTz9p5syZ2YZSsbGxGjt2rCn1AQAAOMKsHgoAAKAgyNU9pSTp2rVr+uabb/Thhx/q4sWLkqQTJ04oOTnZacUFBQWpVq1adtPuuusuHTt2LNt1Ro0apcTERNvr+PHjTqsHAAAgr8zooQAAAAqCXI2UOnr0qNq1a6djx44pNTVVDzzwgHx9fTVhwgSlpqZq5syZTikuIiJC+/bts5u2f/9+hYSEZLuO1WqV1Wp1yv4BAACcyaweCgAAoCDI1UipZ599Vvfcc4/Onz8vb29v2/SuXbtqzZo1Titu+PDh2rp1q8aPH6+DBw9q3rx5+uijjxQTE+O0fQAAAJjFrB4KAACgIMjVSKmNGzdq8+bN8vLyspseGhqqP/74wymFSVLjxo21ePFijRo1SuPGjVNYWJimTp2qPn36OG0fAAAAZjGrhwIAACgIchVKpaenKy0tLdP033//Xb6+vnku6u86duyojh07OnWbAAAArmBmDwUAAODucnX53oMPPqipU6fa3lssFiUnJ2vMmDF66KGHnFUbAABAoUIPBQAAcEOuRkpNnjxZUVFRqlWrlq5cuaJHH31UBw4cUPny5TV//nxn1wgAAFAo0EMBAADckKtQqlKlStq9e7cWLFigPXv2KDk5WU888YT69Oljd9NOAAAA3EAPBQAAcEOuQilJ8vT01GOPPebMWgAAAAo9eigAAIDrchVKffrpp7ec37dv31wVAwAAUJjRQwEAANyQq1Dq2WeftXt/9epVXbp0SV5eXipZsiQNFQAAQBbooQAAAG7I1dP3zp8/b/dKTk7Wvn371Lx5c27SCQAAkA16KAAAgBtyFUplpVq1anr77bczfQMIAACA7NFDAQCAosppoZR0/cadJ06ccOYmAQAACj16KAAAUBTl6p5SX331ld17wzB08uRJvffee4qIiHBKYQAAAIUNPRQAAMANuQqlunTpYvfeYrGoQoUKuv/++zV58mRn1AUAAFDo0EMBAADckKtQKj093dl1AAAAFHr0UAAAADc49Z5SAAAAAAAAQE7kaqTUiBEjcrzslClTcrMLAACAQoceCgAA4IZchVI//PCDfvjhB129elU1atSQJO3fv18eHh5q2LChbTmLxeKcKgEAAAoBeigAAIAbchVKderUSb6+voqLi1OZMmUkSefPn1d0dLRatGih5557zqlFAgAAFAb0UAAAADdYDMMwHF3pjjvu0Ndff63atWvbTf/pp5/04IMP6sSJE04rMK+SkpLk7++vxMRE+fn5ubocoFDq1Mm1+1+2LG/rF/T6AeQvZ/YSBaWHon8CTBDv4gakMGhNEwW4q5z2Erm60XlSUpLOnDmTafqZM2d08eLF3GwSAACg0KOHAgAAuCFXoVTXrl0VHR2tL7/8Ur///rt+//13/ec//9ETTzyhbt26ObtGAACAQoEeCgAA4IZc3VNq5syZGjlypB599FFdvXr1+oY8PfXEE09o0qRJTi0QAACgsKCHAgAAuCFXoVTJkiX1wQcfaNKkSTp06JAkKTw8XD4+Pk4tDgAAoDChhwIAALghV5fvZTh58qROnjypatWqycfHR7m4ZzoAAECRQw8FAACQy1Dqzz//VNu2bVW9enU99NBDOnnypCTpiSee4FHGAAAA2aCHAgAAuCFXodTw4cNVvHhxHTt2TCVLlrRNf+SRR7Ry5UqnFQcAAFCY0EMBAADckKt7Sn399ddatWqVKlWqZDe9WrVqOnr0qFMKAwAAKGzooQAAAG7I1UiplJQUu2/3Mpw7d05WqzXPRQEAABRG9FAAAAA35CqUatGihT799FPbe4vFovT0dE2cOFFt2rRxWnEAAACFCT0UAADADbm6fG/ixIlq27attm/frr/++ksvvPCCfv75Z507d07ffvuts2sEAAAoFOihAAAAbsjVSKk6depo//79at68uTp37qyUlBR169ZNP/zwg8LDw51dIwAAQKFADwUAAHCDwyOlrl69qnbt2mnmzJl65ZVX8qMmAACAQoceCgAAwJ7DI6WKFy+uPXv25EctAAAAhRY9FAAAgL1cXb732GOP6ZNPPnF2LQAAAIUaPRQAAMANubrR+bVr1/Tvf/9b33zzjRo1aiQfHx+7+VOmTHFKcQAAAIUJPRQAAMANDoVSv/32m0JDQ/XTTz+pYcOGkqT9+/fbLWOxWJxXHQAAQCFADwUAAJCZQ6FUtWrVdPLkSa1bt06S9Mgjj2j69OmqWLFivhQHAABQGNBDAQAAZObQPaUMw7B7v2LFCqWkpDi1IAAAgMKGHgoAACCzXN3oPMPNDRYAAABujx4KAADAwcv3LBZLpvsdcP8DqVOnvK2/bJlz6gBQNOX13yCJf4eA/EYPBQAAkJlDoZRhGOrfv7+sVqsk6cqVK3rqqacyPTnmyy+/dF6FAAAABRw9FAAAQGYOhVL9+vWze//YY485tRgAAIDCiB4KAAAgM4dCqVmzZuVXHQAAAIUWPRQAAEBmebrROQAAAAAAAJAbhFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAABAIff222/LYrFo2LBhri4FAADAhlAKAACgENu2bZs+/PBD1atXz9WlAAAA2CGUAgAAKKSSk5PVp08fffzxxypTpoyrywEAALBDKAUAAFBIxcTEqEOHDoqMjHR1KQAAAJl4uroAAAAAON+CBQu0c+dObdu27bbLpqamKjU11fY+KSkpP0sDAACQRCgFAABQ6Bw/flzPPvusVq9erRIlStx2+djYWI0dO9aEyoBCJL6TqytAXn8GrZc5pw4AucblewAAAIXMjh07dPr0aTVs2FCenp7y9PTU+vXrNX36dHl6eiotLc1u+VGjRikxMdH2On78uIsqBwAARQkjpQAAAAqZtm3b6scff7SbFh0drZo1a+rFF1+Uh4eH3Tyr1Sqr1WpmiQAAAIRSAAAAhY2vr6/q1KljN83Hx0flypXLNB0AAMBVuHwPAAAAAAAApmOkFAAAQBEQHx/v6hIAAADsMFIKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGC6AhVKvf3227JYLBo2bJirSwEAAAAAAEAeFJhQatu2bfrwww9Vr149V5cCAAAAAACAPCoQoVRycrL69Omjjz/+WGXKlHF1OQAAAAAAAMijAhFKxcTEqEOHDoqMjLztsqmpqUpKSrJ7AQAAAAAAwL14urqA21mwYIF27typbdu25Wj52NhYjR07Np+rAuBOOnVydQUFX16P4bJlrt1/XuW1fgAAAACOc+uRUsePH9ezzz6ruXPnqkSJEjlaZ9SoUUpMTLS9jh8/ns9VAgAAAAAAwFFuPVJqx44dOn36tBo2bGiblpaWpg0bNui9995TamqqPDw87NaxWq2yWq1mlwoAAAAAAAAHuHUo1bZtW/34449206Kjo1WzZk29+OKLmQIpAAAAAAAAFAxuHUr5+vqqTp06dtN8fHxUrly5TNMBAAAAAABQcLj1PaUAAAAAAABQOLn1SKmsxMfHu7oEAAAAAAAA5BEjpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOk8XV0AAAAAAACmi++Ut/VbL3NOHblV0OsHxEgpAAAAAAAAuAChFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdJ6uLgBA3nXqlLf1ly1zTh0AAAAAAOQUI6UAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAACAQiY2NlaNGzeWr6+vAgIC1KVLF+3bt8/VZQEAANghlAIAAChk1q9fr5iYGG3dulWrV6/W1atX9eCDDyolJcXVpQEAANh4uroAAAAAONfKlSvt3s+ePVsBAQHasWOHWrZs6aKqAAAA7DFSCgAAoJBLTEyUJJUtW9bFlQAAANzASCkAAIBCLD09XcOGDVNERITq1KmT5TKpqalKTU21vU9KSjKrPAAAUIQRSgEAABRiMTEx+umnn7Rp06Zsl4mNjdXYsWNNrApuIb5T3tZvvcw5deRWQa8fBV9ez0FX43cIboDL9wAAAAqpwYMHa/ny5Vq3bp0qVaqU7XKjRo1SYmKi7XX8+HETqwQAAEUVI6UAAAAKGcMwNGTIEC1evFjx8fEKCwu75fJWq1VWq9Wk6gAAAK4jlAIAAChkYmJiNG/ePC1dulS+vr5KSEiQJPn7+8vb29vF1QEAAFzn1pfvxcbGqnHjxvL19VVAQIC6dOmiffv2ubosAAAAtzZjxgwlJiaqdevWCgoKsr0WLlzo6tIAAABs3Hqk1Pr16xUTE6PGjRvr2rVrevnll/Xggw9q79698vHxcXV5AAAAbskwDFeXAAAAcFtuHUqtXLnS7v3s2bMVEBCgHTt2qGXLli6qCgAAAAAAAHnl1qHUzRITEyVJZcuWzXaZ1NRUpaam2t4nJSXle10AAAAAAABwTIEJpdLT0zVs2DBFRESoTp062S4XGxursWPHmlgZXK1Tp7xvY9myvG8DKMqc8XsIAAAAoGhx6xud/11MTIx++uknLViw4JbLjRo1SomJibbX8ePHTaoQAAAAAAAAOVUgRkoNHjxYy5cv14YNG1SpUqVbLmu1WmW1Wk2qDAAAAAAAALnh1qGUYRgaMmSIFi9erPj4eIWFhbm6JAAAAAAAADiBW4dSMTExmjdvnpYuXSpfX18lJCRIkvz9/eXt7e3i6gAAAAAAAJBbbn1PqRkzZigxMVGtW7dWUFCQ7bVw4UJXlwYAAAAAAIA8cOuRUoZhuLoEAAAAAAAA5AO3HikFAAAAAACAwolQCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmM7T1QUAAACgiIrv5Nr9t16Wt/ULev155erPn1cFvX4AKAQYKQUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB33lHIDnfJ4OfsyF99OIK/y+vkLQw2u/hm6+vMXdRz/gs/VP8O8/hvi6r9Drt4/AAAAXIORUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMVyBCqffff1+hoaEqUaKEmjRpou+//97VJQEAALg9eigAAODO3D6UWrhwoUaMGKExY8Zo586dql+/vqKionT69GlXlwYAAOC26KEAAIC7c/tQasqUKRowYICio6NVq1YtzZw5UyVLltS///1vV5cGAADgtuihAACAu3PrUOqvv/7Sjh07FBkZaZtWrFgxRUZGasuWLS6sDAAAwH3RQwEAgILA09UF3MrZs2eVlpamihUr2k2vWLGifv311yzXSU1NVWpqqu19YmKiJCkpKSnf6rx6Nd82nSP5+NFM4erj5w7y+jPkGAJ5U9B/B11df0Hf/+23f30HhmHk746cyNEeyhX9kyQppYD/8lA/gKKsoP+PKPJVTvsntw6lciM2NlZjx47NNL1y5couqMYc/v6urgB5xc8QcK2C/jvo6vqLyv4vXrwof1d/2HxSFPun6wr6z7Og1w+gYOPfINze7fontw6lypcvLw8PD506dcpu+qlTpxQYGJjlOqNGjdKIESNs79PT03Xu3DmVK1dOFovFabUlJSWpcuXKOn78uPz8/Jy23cKMY+Y4jpnjOGaO45g5jmPmuIJ8zAzD0MWLFxUcHOzqUnLM0R7KrP5JKtjngqtwzBzHMXMcx8xxHDPHccwcV1CPWU77J7cOpby8vNSoUSOtWbNGXbp0kXS9SVqzZo0GDx6c5TpWq1VWq9VuWunSpfOtRj8/vwJ1YrgDjpnjOGaO45g5jmPmOI6Z4wrqMStoI6Qc7aHM7p+kgnsuuBLHzHEcM8dxzBzHMXMcx8xxBfGY5aR/cutQSpJGjBihfv366Z577tG9996rqVOnKiUlRdHR0a4uDQAAwG3RQwEAAHfn9qHUI488ojNnzui1115TQkKCGjRooJUrV2a6cScAAABuoIcCAADuzu1DKUkaPHhwtpfruYrVatWYMWMyDXVH9jhmjuOYOY5j5jiOmeM4Zo7jmLkGPVThwDFzHMfMcRwzx3HMHMcxc1xhP2YWoyA93xgAAAAAAACFQjFXFwAAAAAAAICih1AKAAAAAAAApiOUAgAAAAAAgOkIpXLp/fffV2hoqEqUKKEmTZro+++/d3VJbuv111+XxWKxe9WsWdPVZbmVDRs2qFOnTgoODpbFYtGSJUvs5huGoddee01BQUHy9vZWZGSkDhw44Jpi3cTtjln//v0znXft2rVzTbFuIjY2Vo0bN5avr68CAgLUpUsX7du3z26ZK1euKCYmRuXKlVOpUqXUvXt3nTp1ykUVu15Ojlnr1q0znWtPPfWUiyp2vRkzZqhevXry8/OTn5+fmjZtqhUrVtjmc44VbfRPjqGHuj16KMfRQzmG/slx9E+OK8r9E6FULixcuFAjRozQmDFjtHPnTtWvX19RUVE6ffq0q0tzW7Vr19bJkydtr02bNrm6JLeSkpKi+vXr6/33389y/sSJEzV9+nTNnDlT3333nXx8fBQVFaUrV66YXKn7uN0xk6R27drZnXfz5883sUL3s379esXExGjr1q1avXq1rl69qgcffFApKSm2ZYYPH65ly5Zp0aJFWr9+vU6cOKFu3bq5sGrXyskxk6QBAwbYnWsTJ050UcWuV6lSJb399tvasWOHtm/frvvvv1+dO3fWzz//LIlzrCijf8odeqhbo4dyHD2UY+ifHEf/5Lgi3T8ZcNi9995rxMTE2N6npaUZwcHBRmxsrAurcl9jxowx6tev7+oyCgxJxuLFi23v09PTjcDAQGPSpEm2aRcuXDCsVqsxf/58F1Tofm4+ZoZhGP369TM6d+7sknoKitOnTxuSjPXr1xuGcf28Kl68uLFo0SLbMr/88oshydiyZYurynQrNx8zwzCMVq1aGc8++6zriioAypQpY/zf//0f51gRR//kOHoox9BDOY4eynH0T46jf8qdotI/MVLKQX/99Zd27NihyMhI27RixYopMjJSW7ZscWFl7u3AgQMKDg7WnXfeqT59+ujYsWOuLqnAOHz4sBISEuzOOX9/fzVp0oRz7jbi4+MVEBCgGjVq6Omnn9aff/7p6pLcSmJioiSpbNmykqQdO3bo6tWrdudazZo1VaVKFc61/+/mY5Zh7ty5Kl++vOrUqaNRo0bp0qVLrijP7aSlpWnBggVKSUlR06ZNOceKMPqn3KOHyj16qNyjh8oe/ZPj6J8cU9T6J09XF1DQnD17VmlpaapYsaLd9IoVK+rXX391UVXurUmTJpo9e7Zq1KihkydPauzYsWrRooV++ukn+fr6uro8t5eQkCBJWZ5zGfOQWbt27dStWzeFhYXp0KFDevnll9W+fXtt2bJFHh4eri7P5dLT0zVs2DBFRESoTp06kq6fa15eXipdurTdspxr12V1zCTp0UcfVUhIiIKDg7Vnzx69+OKL2rdvn7788ksXVutaP/74o5o2baorV66oVKlSWrx4sWrVqqVdu3ZxjhVR9E+5Qw+VN/RQuUMPlT36J8fRP+VcUe2fCKWQ79q3b2/773r16qlJkyYKCQnR559/rieeeMKFlaEw69Wrl+2/69atq3r16ik8PFzx8fFq27atCytzDzExMfrpp5+4N4kDsjtmAwcOtP133bp1FRQUpLZt2+rQoUMKDw83u0y3UKNGDe3atUuJiYn64osv1K9fP61fv97VZQEFDj0UXIEeKnv0T46jf8q5oto/cfmeg8qXLy8PD49Md7o/deqUAgMDXVRVwVK6dGlVr15dBw8edHUpBULGecU5lzd33nmnypcvz3knafDgwVq+fLnWrVunSpUq2aYHBgbqr7/+0oULF+yW51zL/phlpUmTJpJUpM81Ly8vVa1aVY0aNVJsbKzq16+vadOmcY4VYfRPzkEP5Rh6KOegh7qO/slx9E+OKar9E6GUg7y8vNSoUSOtWbPGNi09PV1r1qxR06ZNXVhZwZGcnKxDhw4pKCjI1aUUCGFhYQoMDLQ755KSkvTdd99xzjng999/159//lmkzzvDMDR48GAtXrxYa9euVVhYmN38Ro0aqXjx4nbn2r59+3Ts2LEie67d7phlZdeuXZJUpM+1m6Wnpys1NZVzrAijf3IOeijH0EM5R1HvoeifHEf/5BxFpX/i8r1cGDFihPr166d77rlH9957r6ZOnaqUlBRFR0e7ujS3NHLkSHXq1EkhISE6ceKExowZIw8PD/Xu3dvVpbmN5ORku28FDh8+rF27dqls2bKqUqWKhg0bpjfffFPVqlVTWFiYRo8ereDgYHXp0sV1RbvYrY5Z2bJlNXbsWHXv3l2BgYE6dOiQXnjhBVWtWlVRUVEurNq1YmJiNG/ePC1dulS+vr62a9D9/f3l7e0tf39/PfHEExoxYoTKli0rPz8/DRkyRE2bNtV9993n4upd43bH7NChQ5o3b54eeughlStXTnv27NHw4cPVsmVL1atXz8XVu8aoUaPUvn17ValSRRcvXtS8efMUHx+vVatWcY4VcfRPjqOHuj16KMfRQzmG/slx9E+OK9L9k2sf/ldwvfvuu0aVKlUMLy8v49577zW2bt3q6pLc1iOPPGIEBQUZXl5exh133GE88sgjxsGDB11dlltZt26dISnTq1+/foZhXH+k8ejRo42KFSsaVqvVaNu2rbFv3z7XFu1itzpmly5dMh588EGjQoUKRvHixY2QkBBjwIABRkJCgqvLdqmsjpckY9asWbZlLl++bDzzzDNGmTJljJIlSxpdu3Y1Tp486bqiXex2x+zYsWNGy5YtjbJlyxpWq9WoWrWq8fzzzxuJiYmuLdyFHn/8cSMkJMTw8vIyKlSoYLRt29b4+uuvbfM5x4o2+ifH0EPdHj2U4+ihHEP/5Dj6J8cV5f7JYhiGkT9xFwAAAAAAAJA17ikFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFoNCJj4+XxWLRhQsXXF0KAABAgUEPBcBshFIACqwtW7bIw8NDHTp0uOVy8fHx6ty5s4KCguTj46MGDRpo7ty5mZY7d+6chg0bppCQEHl5eSk4OFiPP/64jh07ZrfcjBkzVK9ePfn5+cnPz09NmzbVihUrnPrZAAAA8gs9FAB3QSgFoMD65JNPNGTIEG3YsEEnTpzIdrnNmzerXr16+s9//qM9e/YoOjpaffv21fLly23LnDt3Tvfdd5+++eYbzZw5UwcPHtSCBQt08OBBNW7cWL/99ptt2UqVKuntt9/Wjh07tH37dt1///3q3Lmzfv7553z9vAAAAM5ADwXAXVgMwzBcXQQAOCo5OVlBQUHavn27xowZo3r16unll1+WdP1bvTZt2uj8+fMqXbp0lut36NBBFStW1L///W9J0tNPP605c+bo4MGDCgwMtC13+fJlVatWTXXr1r3lN3lly5bVpEmT9MQTTzjvQwIAADgZPRQAd8JIKQAF0ueff66aNWuqRo0aeuyxx/Tvf/9bjmTsiYmJKlu2rCQpPT1dCxYsUJ8+feyaKUny9vbWM888o1WrVuncuXOZtpOWlqYFCxYoJSVFTZs2zduHAgAAyGf0UADcCaEUgALpk08+0WOPPSZJateunRITE7V+/focrfv5559r27Ztio6OliSdOXNGFy5c0F133ZXl8nfddZcMw9DBgwdt03788UeVKlVKVqtVTz31lBYvXqxatWrl8VMBAADkL3ooAO6EUApAgbNv3z59//336t27tyTJ09NTjzzyiD755JPbrrtu3TpFR0fr448/Vu3ate3mOfItYY0aNbRr1y599913evrpp9WvXz/t3bvXsQ8CAABgInooAO7G09UFAICjPvnkE127dk3BwcG2aYZhyGq16r333st2vfXr16tTp05655131LdvX9v0ChUqqHTp0vrll1+yXO+XX36RxWJR1apVbdO8vLxs7xs1aqRt27Zp2rRp+vDDD/P68QAAAPIFPRQAd8NIKQAFyrVr1/Tpp59q8uTJ2rVrl+21e/duBQcHa/78+VmuFx8frw4dOmjChAkaOHCg3bxixYqpZ8+emjdvnhISEuzmXb58WR988IGioqJs90/ISnp6ulJTU/P+AQEAAPIBPRQAd8RIKQAFyvLly3X+/Hk98cQT8vf3t5vXvXt3ffLJJ5o0aZLd9HXr1qljx4569tln1b17d1vT5OXlZWuSxo8frzVr1uiBBx7QxIkTVadOHR0+fFivvvqqrl69qvfff9+2vVGjRql9+/aqUqWKLl68qHnz5ik+Pl6rVq3K508PAACQO/RQANwRI6UAFCiffPKJIiMjMzVT0vWGavv27dqzZ4/d9Li4OF26dEmxsbEKCgqyvbp162Zbply5ctq6davatGmjQYMGKTw8XD179lR4eLi2bdumO++807bs6dOn1bdvX9WoUUNt27bVtm3btGrVKj3wwAP598EBAADygB4KgDuyGI7clQ4AAAAAAABwAkZKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0/0/sJDEI2Asow8AAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAABKUAAAJOCAYAAABm7rQwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABlw0lEQVR4nO3deVwV9f7H8fcB5IAKuLMkKrnvppW5a5KI5lq5ZLlVtmhqpiW3XNCKbHHL0m73JpWVZbmUN80VtdTKBc1KU0PRBFGvgmCiwvz+8Me5ngAFPMwBzuv5eMzjcWfmOzOfM+eQn/s+c2YshmEYAgAAAAAAAEzk5uwCAAAAAAAA4HoIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpQAAAAAAAGA6QikAAAAAAACYjlAKAAAAAAAApiOUAgAAAAAAgOkIpYBrTJ06VRaLxZRjdezYUR07drTNx8TEyGKx6IsvvjDl+EOHDlWNGjVMOVZBpaam6tFHH1VAQIAsFovGjh3r7JIKhZmfu6Iip8+fxWLR1KlTnVIPAMAc9FpFC70WAGcjlEKJFR0dLYvFYpu8vLwUFBSksLAwzZ07V+fPn3fIcU6cOKGpU6cqNjbWIftzpKJcW1688sorio6O1pNPPqmPPvpIDz/8cK5ja9SoYfd+XztdvHgx38dOS0vT9OnT1aRJE5UuXVp+fn5q166dPvzwQxmGYRs3dOjQXI977TR06NCCnIICOXLkSLbj+/r6qlmzZpo3b54yMjJMq6Woy8t7Z7FYFBMTc9PHunDhgqZOneqQfQFAUUCvVbRrywt6rYK5ttf68ssvs63PCsFOnz5tWk3XyqkXzG06cuTITR+vuP8dwLk8nF0AUNimTZumkJAQXb58WYmJiYqJidHYsWM1c+ZMffXVV2rSpIlt7IsvvqiJEyfma/8nTpxQZGSkatSooWbNmuV5uzVr1uTrOAVxvdree+89ZWZmFnoNN2PDhg266667NGXKlDyNb9asmZ599tlsyz09PfN13JMnT6pz58767bffNGDAAI0aNUoXL17Ul19+qSFDhuibb77Rxx9/LHd3dz3++OMKDQ21bRsXF6fJkydrxIgRateunW15zZo1cz1eQT53eTFw4EB169ZNkpScnKxvvvlGTz/9tI4eParXX3/d4ce7WX/99Zc8PMz9Z+mjjz6ym//www+1du3abMvr169/08e6cOGCIiMjJcnum3sAKO7otei1XLXXkq5+/vv27VukrsSqXLlytl7mzTff1PHjxzVr1qxsY29WQf9GAYlQCi4gPDxct99+u20+IiJCGzZs0L333quePXvqt99+k7e3tyTJw8Oj0P9P8YULF1S6dOl8/+PtaKVKlXLq8fMiKSlJDRo0yPP4W265RQ899NBNH3fIkCH67bfftGzZMvXs2dO2fPTo0ZowYYLeeOMN3XbbbXr++efVqlUrtWrVyjZmx44dmjx5slq1apXnWgrrc9e8eXO7Gp566im1bNlSn3zySZEMpby8vEw/5t/fo+3bt2vt2rUO+RwBgKug18oZvVbuSkqv1axZM8XGxmrZsmXq27evw/dfUGXKlMl2bhYvXqyzZ8/S46DI4ed7cEl33323Jk2apKNHj2rRokW25Tn93nzt2rVq27atypUrp7Jly6pu3br6xz/+IenqvQnuuOMOSdKwYcNsl8FGR0dLuno1RKNGjbRz5061b99epUuXtm379/scZMnIyNA//vEPBQQEqEyZMurZs6eOHTtmN6ZGjRo5XqJ87T5vVFtO9zlIS0vTs88+q+DgYFmtVtWtW1dvvPGG3SXU0tWfPI0aNUrLly9Xo0aNZLVa1bBhQ61evTrnE/43SUlJeuSRR+Tv7y8vLy81bdpUH3zwgW191j0f4uLi9J///MdhlxefO3dOY8eOtb2+WrVqacaMGXbfYm7fvl3ffvuthg4datckZYmKilLt2rU1Y8YM/fXXXzdVT5acPnc3e45zYrFY5O/vn60pW7Fihbp3766goCBZrVbVrFlT06dPz/Yzv4MHD+q+++5TQECAvLy8VLVqVQ0YMEDJycl24xYtWqQWLVrI29tbFSpU0IABA7J9hnOr79p7SmWdl0OHDmno0KEqV66c/Pz8NGzYMF24cCHb9gU97o1kZmZq9uzZatiwoby8vOTv76/HH39cZ8+etRu3Y8cOhYWFqVKlSvL29lZISIiGDx8u6epl9FnfREZGRto+09xDC0BJRa9Fr+UKvdaAAQNUp04dTZs2Ldt7mJMffvhBXbt2lZ+fn0qXLq0OHTro+++/t63fu3evLBaLvvrqK9uynTt3ymKxqHnz5nb7Cg8PV8uWLfNca07S09M1ZcoU1apVS1arVcHBwXruueeUnp5uN+5m/kaBG+FKKbishx9+WP/4xz+0Zs0aPfbYYzmO+eWXX3TvvfeqSZMmmjZtmqxWqw4dOmT7x6N+/fqaNm1atkuIW7dubdvHmTNnFB4ergEDBuihhx6Sv7//det6+eWXZbFY9PzzzyspKUmzZ89WaGioYmNjbd8y5kVearuWYRjq2bOnNm7cqEceeUTNmjXTt99+qwkTJujPP//Mdqnvd999p6VLl+qpp56Sj4+P5s6dq/vuu0/x8fGqWLFirnX99ddf6tixow4dOqRRo0YpJCRES5Ys0dChQ3Xu3DmNGTNG9evX10cffaRnnnlGVatWtV0mfqPLiy9fvpztt/ulS5dW6dKldeHCBXXo0EF//vmnHn/8cVWrVk1bt25VRESEEhISNHv2bEnS119/LUkaPHhwjsfw8PDQgw8+qMjISH3//fd2l5M7WkHPcZYLFy7YzkdKSopWrVql1atXKyIiwm5cdHS0ypYtq3Hjxqls2bLasGGDJk+erJSUFNsVVZcuXVJYWJjS09P19NNPKyAgQH/++adWrlypc+fOyc/PT9LVz++kSZPUr18/Pfroozp16pTeeusttW/fXrt371a5cuXyfR769eunkJAQRUVFadeuXfrXv/6lKlWqaMaMGbYxhXHcLI8//riio6M1bNgwjR49WnFxcZo3b552796t77//XqVKlVJSUpK6dOmiypUra+LEiSpXrpyOHDmipUuXSrr62Z0/f76efPJJ9enTx/Zt6rU/aQGAkoZeyx691mxJJavXcnd314svvqjBgwff8GqpDRs2KDw8XC1atNCUKVPk5uamhQsX6u6779aWLVt05513qlGjRipXrpw2b95sC+y2bNkiNzc37dmzRykpKfL19VVmZqa2bt2qESNGFPi1Z2ZmqmfPnvruu+80YsQI1a9fXz///LNmzZql33//XcuXL5fkmL9R4LoMoIRauHChIcn46aefch3j5+dn3Hbbbbb5KVOmGNf+WcyaNcuQZJw6dSrXffz000+GJGPhwoXZ1nXo0MGQZCxYsCDHdR06dLDNb9y40ZBk3HLLLUZKSopt+eeff25IMubMmWNbVr16dWPIkCE33Of1ahsyZIhRvXp12/zy5csNScZLL71kN+7+++83LBaLcejQIdsySYanp6fdsj179hiSjLfeeivbsa41e/ZsQ5KxaNEi27JLly4ZrVq1MsqWLWv32qtXr2507979uvu7dqykbNOUKVMMwzCM6dOnG2XKlDF+//13u+0mTpxouLu7G/Hx8YZhGEbv3r0NScbZs2dzPdbSpUsNScbcuXOzrbveOc/N3z93hnFz5zguLi7HcyHJePLJJ43MzEy78RcuXMi2j8cff9woXbq0cfHiRcMwDGP37t2GJGPJkiW5HvfIkSOGu7u78fLLL9st//nnnw0PDw+75X///GW95qz3yzD+d16GDx9uN65Pnz5GxYoVC3TcGxk5cqTde7FlyxZDkvHxxx/bjVu9erXd8mXLlt3wvzenTp3K9hoBoDij16LXcvVe6/XXXzeuXLli1K5d22jatKmtx8o6XtbnOjMz06hdu7YRFhZm14dduHDBCAkJMe655x7bsu7duxt33nmnbb5v375G3759DXd3d2PVqlWGYRjGrl27DEnGihUr8nwOunfvbvd5/Oijjww3Nzdjy5YtduMWLFhgSDK+//57wzBu/m8UuBF+vgeXVrZs2es+GSbr6ooVK1YU+EaVVqtVw4YNy/P4wYMHy8fHxzZ///33KzAwUN98802Bjp9X33zzjdzd3TV69Gi75c8++6wMw9CqVavsloeGhtrdULJJkyby9fXVH3/8ccPjBAQEaODAgbZlpUqV0ujRo5WamqpNmzYV+DW0bNlSa9eutZuyvoVbsmSJ2rVrp/Lly+v06dO2KTQ0VBkZGdq8ebMk2T4P174Hf5e1LiUlpcC15kVBz3GWESNG2M7Dl19+qZEjR+rdd9/VuHHj7MZd+63w+fPndfr0abVr104XLlzQ/v37Jcl2JdS3336b40/nJGnp0qXKzMxUv3797M5xQECAateurY0bN+br9Wd54okn7ObbtWunM2fO2M5/YR1Xuvq58fPz0z333GO37xYtWqhs2bK2fWf9t2LlypW6fPlygY8HACUNvdb/0GuVvF5L+t/VUnv27LFdXfR3sbGxOnjwoB588EGdOXPGdm7S0tLUuXNnbd682fb5b9eunXbt2qW0tDRJV6/m6tatm5o1a6YtW7ZIunr1lMViUdu2bQv4yq++X/Xr11e9evXs3q+7775bkrL1ODfzNwpcDz/fg0tLTU1VlSpVcl3fv39//etf/9Kjjz6qiRMnqnPnzurbt6/uv/9+ubnlLdO95ZZb8nWjzdq1a9vNWywW1apVyyGPa72eo0ePKigoKFuDkPXUsaNHj9otr1atWrZ9lC9fPtt9dnI6Tu3atbOdv9yOkx+VKlXK9RLvgwcPau/evblelp6UlCTpf03Q+fPnc/3JV16aKUco6DnOUrt2bbvzkfVkmNmzZ2v48OFq3LixpKuXZb/44ovasGFDtuYv635RISEhGjdunGbOnKmPP/5Y7dq1U8+ePfXQQw/ZAquDBw/KMIxsn+EsBb3h69/PQ/ny5SVJZ8+ela+vb6EdV7r6mpKTk3P970TW56ZDhw667777FBkZqVmzZqljx47q3bu3HnzwQVmt1gIfHwCKO3qt/6HXKnm9VpZBgwZp+vTpmjZtmnr37p1t/cGDByVdvcF7bpKTk1W+fHm1a9dOV65c0bZt2xQcHKykpCS1a9dOv/zyi10o1aBBA1WoUCFfdf69pt9+++2G75cj/kaB6yGUgss6fvy4kpOTVatWrVzHeHt7a/Pmzdq4caP+85//aPXq1frss8909913a82aNXJ3d7/hcfJzb4K8yu2RsxkZGXmqyRFyO46Rh5s8OkNmZqbuuecePffcczmur1OnjqSrDdvy5cu1d+9etW/fPsexe/fulaR8Pa2mIArjHHfu3Fnz5s3T5s2b1bhxY507d04dOnSQr6+vpk2bppo1a8rLy0u7du3S888/b/eN2JtvvqmhQ4dqxYoVWrNmjUaPHq2oqCht375dVatWVWZmpiwWi1atWpVj7WXLli1QzTc6D4V13Kx9V6lSRR9//HGO67MaOYvFoi+++ELbt2/X119/rW+//VbDhw/Xm2++qe3bt99UDQBQXNFr3Rx6reLTa2VdLZXVJ/1dVj/1+uuvq1mzZjnuI6tXuP322+Xl5aXNmzerWrVqqlKliurUqaN27drpnXfeUXp6urZs2aI+ffrkq8acamrcuLFmzpyZ4/rg4GBJjvkbBa6HUAou66OPPpIkhYWFXXecm5ubOnfurM6dO2vmzJl65ZVX9MILL2jjxo0KDQ3NtWkpqKxvUrIYhqFDhw7Z3RC5fPnyOnfuXLZtjx49qltvvdU2n5/aqlevrnXr1un8+fN230pl/XyrevXqed7XjY6zd+9eZWZm2n274ujj/F3NmjWVmpp6w5tl3nvvvYqKitKHH36YY6OUkZGhTz75ROXLl1ebNm0KpdbCdOXKFUlXv7mWrj4x5cyZM1q6dKnd642Li8tx+8aNG6tx48Z68cUXtXXrVrVp00YLFizQSy+9pJo1a8owDIWEhNgaTzMU5nFr1qypdevWqU2bNnn6Pz133XWX7rrrLr388sv65JNPNGjQIC1evFiPPvqow/9bAQBFHb2WPXqtq0pqr/XQQw/ppZdeUmRkZLanCmb9RNDX1/eG58fT01N33nmntmzZomrVqtluHN6uXTulp6fr448/1smTJ3MN9PKqZs2a2rNnjzp37nzDz7HZf6NwLVxvB5e0YcMGTZ8+XSEhIRo0aFCu4/773/9mW5b17UbWo1LLlCkjSTk2LgXx4Ycf2t174YsvvlBCQoLCw8Nty2rWrKnt27fr0qVLtmUrV67M9jjj/NTWrVs3ZWRkaN68eXbLZ82aJYvFYnf8m9GtWzclJibqs88+sy27cuWK3nrrLZUtW1YdOnRwyHH+rl+/ftq2bZu+/fbbbOvOnTtnC2tat26t0NBQLVy4UCtXrsw29oUXXtDvv/+u5557rlC+mS1sWU+8adq0qaT/fUN47TeCly5d0jvvvGO3XUpKiu0cZWncuLHc3Nxsfwt9+/aVu7u7IiMjs33DaBiGzpw549gX8/8K87j9+vVTRkaGpk+fnm3dlStXbH9bZ8+ezXbsv/+3onTp0pIc998KACjK6LWyo9cq2b1W1tVSsbGx+uqrr+zWtWjRQjVr1tQbb7xh+2LwWqdOnbKbb9eunX744Qdt3LjRFkpVqlRJ9evXtz19OGt5QfXr109//vmn3nvvvWzr/vrrL9s9rZzxNwrXwpVSKPFWrVql/fv368qVKzp58qQ2bNigtWvXqnr16vrqq6/k5eWV67bTpk3T5s2b1b17d1WvXl1JSUl65513VLVqVduNBWvWrKly5cppwYIF8vHxUZkyZdSyZUuFhIQUqN4KFSqobdu2GjZsmE6ePKnZs2erVq1ado9SfvTRR/XFF1+oa9eu6tevnw4fPqxFixbZ3agxv7X16NFDnTp10gsvvKAjR46oadOmWrNmjVasWKGxY8dm23dBjRgxQu+++66GDh2qnTt3qkaNGvriiy/0/fffa/bs2YV274AJEyboq6++0r333quhQ4eqRYsWSktL088//6wvvvhCR44cUaVKlSRdbVY7d+6sXr166cEHH7R9M7V06VLFxMSof//+mjBhQqHU6Ui7du3SokWLJF29N8P69ev15ZdfqnXr1urSpYukq41h+fLlNWTIEI0ePVoWi0UfffRRtoBlw4YNGjVqlB544AHVqVNHV65c0UcffSR3d3fdd999kq5+3l566SVFREToyJEj6t27t3x8fBQXF6dly5ZpxIgRGj9+vMNfZ2Eet0OHDnr88ccVFRWl2NhYdenSRaVKldLBgwe1ZMkSzZkzR/fff78++OADvfPOO+rTp49q1qyp8+fP67333pOvr6+6desm6erl7w0aNNBnn32mOnXqqEKFCmrUqJEaNWrkyNMBAKaj16LXklyz1/q7rHtLxcbG2i13c3PTv/71L4WHh6thw4YaNmyYbrnlFv3555/auHGjfH19bV8cSlcDp5dfflnHjh2zC5/at2+vd999VzVq1FDVqlVvqtaHH35Yn3/+uZ544glt3LhRbdq0UUZGhvbv36/PP/9c3377rW6//Xan/I3CxZj7sD/APFmPKc6aPD09jYCAAOOee+4x5syZY/c43Cx/f1zs+vXrjV69ehlBQUGGp6enERQUZAwcODDbo25XrFhhNGjQwPDw8LB7HGqHDh2Mhg0b5lhfbo8p/vTTT42IiAijSpUqhre3t9G9e3fj6NGj2bZ/8803jVtuucWwWq1GmzZtjB07dmTb5/Vq+/tjig3DMM6fP28888wzRlBQkFGqVCmjdu3axuuvv2736FrDuPoI3ZEjR2arKbfHJ//dyZMnjWHDhhmVKlUyPD09jcaNG+f4CNn8Pqb4RmPPnz9vREREGLVq1TI8PT2NSpUqGa1btzbeeOMN49KlS9nGTp061WjYsKHh7e1t+Pj4GG3atDGio6OznY9rOfIxxQU9x1mPKb528vDwMG699VZjwoQJxvnz5+3Gf//998Zdd91leHt7G0FBQcZzzz1nfPvtt4YkY+PGjYZhGMYff/xhDB8+3KhZs6bh5eVlVKhQwejUqZOxbt26bMf/8ssvjbZt2xplypQxypQpY9SrV88YOXKkceDAAduYnD5/uuax0teel78/gjjrbzsuLi7fx72RkSNHZnsvDMMw/vnPfxotWrSwfRYaN25sPPfcc8aJEycMw7j6aOaBAwca1apVM6xWq1GlShXj3nvvNXbs2GG3n61btxotWrQwPD09s71eAChu6LWuXxu9VsnvtV5//fVs6679u/h7D7N7926jb9++RsWKFQ2r1WpUr17d6Nevn7F+/Xq7cSkpKYa7u7vh4+NjXLlyxbZ80aJFhiTj4YcfvtFLzqZ79+7ZPo+XLl0yZsyYYTRs2NCwWq1G+fLljRYtWhiRkZFGcnKyYRg3/zcK3IjFMIronfIAAAAAAABQYnFPKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACm83B2AUVRZmamTpw4IR8fH1ksFmeXAwAAiiDDMHT+/HkFBQXJzc11vuejTwIAADeS1z6JUCoHJ06cUHBwsLPLAAAAxcCxY8dUtWpVZ5dhGvokAACQVzfqkwilcuDj4yPp6snz9fV1cjUAAKAoSklJUXBwsK1vcBX0SQAA4Eby2icRSuUg61J0X19fmi0AAHBdrvYTNvokAACQVzfqk1znBggAAAAAAAAoMgilAAAAAAAAYDpCKQAAAAAAAJiOe0oBAFxSZmamLl265OwyUISVKlVK7u7uzi4DAACXkJGRocuXLzu7DOSRo/okQikAgMu5dOmS4uLilJmZ6exSUMSVK1dOAQEBLnczcwAAzGIYhhITE3Xu3Dlnl4J8ckSfRCgFAHAphmEoISFB7u7uCg4Olpsbv2RHdoZh6MKFC0pKSpIkBQYGOrkiAABKpqxAqkqVKipdujRfBBUDjuyTCKUAAC7lypUrunDhgoKCglS6dGlnl4MizNvbW5KUlJSkKlWq8FM+AAAcLCMjwxZIVaxY0dnlIB8c1Sfx9TAAwKVkZGRIkjw9PZ1cCYqDrOCSe1wAAOB4Wf++8kVh8eSIPolQCgDgkrg0HHnB5wQAgMLHv7fFkyPeN0IpAAAAAAAAmI5QCgAA5FmNGjU0e/Zs27zFYtHy5cudVg8AAACKL250DgCApB49zD3e11/nb/zQoUP1wQcf2OYrVKigO+64Q6+99pqaNGni4OryLiEhQeXLly+0/Xfs2FGbNm3KdX2HDh0UExNT4H03a9bMLmQDAABFRIzJzVnH/DVnWb1ZVFSUJk6caFu+fPly9enTR4ZhOLrCbKKjozVs2LDrjomLi1ONGjUKtO+xY8fq3LlzBSsuj7hSCgCAYqJr165KSEhQQkKC1q9fLw8PD917771OrSkgIEBWq7XQ9r906VLba/7xxx8lSevWrbMtW7p0aaEdGwAA4Hq8vLw0Y8YMnT171inH79+/v60nSkhIUKtWrfTYY4/ZLQsODnZKbXlFKAUAQDFhtVoVEBCggIAANWvWTBMnTtSxY8d06tQp25jnn39ederUUenSpXXrrbdq0qRJdk9E2bNnjzp16iQfHx/5+vqqRYsW2rFjh239d999p3bt2snb21vBwcEaPXq00tLScq3p2p/vHTlyRBaLRUuXLlWnTp1UunRpNW3aVNu2bbPbJj/HqFChgu01V65cWZJUsWJF27Jff/31uvt65513VLt2bXl5ecnf31/333+/pKvfbm7atElz5syRxWKRxWLRkSNH8vZGAAAASAoNDVVAQICioqKuO+56vc+8efPUqFEj29jly5fLYrFowYIFdsd58cUXs+3X29vb1hMFBATI09NTpUuXts17eXnp8ccfV+XKleXr66u7775be/bssW2fW18YExOjYcOGKTk52dYnTZ069SbPVs4IpQAAKIZSU1O1aNEi1apVSxUrVrQt9/HxUXR0tH799VfNmTNH7733nmbNmmVbP2jQIFWtWlU//fSTdu7cqYkTJ6pUqVKSpMOHD6tr16667777tHfvXn322Wf67rvvNGrUqHzV9sILL2j8+PGKjY1VnTp1NHDgQF25csWhx8jLvnbs2KHRo0dr2rRpOnDggFavXq327dtLkubMmZPt28Si/k0iAAAoWtzd3fXKK6/orbfe0vHjx3Mcc6N+pUOHDvr1119tXzJu2rRJlSpVst2e4PLly9q2bZs6duyY7/oeeOABJSUladWqVdq5c6eaN2+uzp0767///a+k3PvC1q1ba/bs2fL19bX1SePHj8//CcoD7ikFAEAxsXLlSpUtW1aSlJaWpsDAQK1cuVJubv/7junab9Fq1Kih8ePHa/HixXruueckSfHx8ZowYYLq1asnSapdu7ZtfFRUlAYNGqSxY8fa1s2dO1cdOnTQ/Pnz5eXllac6x48fr+7du0uSIiMj1bBhQx06dEj16tVz2DHyUm98fLzKlCmje++9Vz4+Pqpevbpuu+02SZKfn5/dt4kAAAAF0adPHzVr1kxTpkzRv//972zrb9SvNGrUSBUqVNCmTZt0//33KyYmRs8++6zmzJkjSfrxxx91+fJltW7dOl91fffdd/rxxx+VlJRku9XCG2+8oeXLl+uLL77QiBEjrtsX+vn5yWKxFHqfxJVSAAAUE506dVJsbKxiY2P1448/KiwsTOHh4Tp69KhtzGeffaY2bdooICBAZcuW1Ysvvqj4+Hjb+nHjxunRRx9VaGioXn31VR0+fNi2bs+ePYqOjlbZsmVtU1hYmDIzMxUXF5fnOq+98XpgYKAkKSkpyaHHyMu+7rnnHlWvXl233nqrHn74YX388ce6cOFCvo4BAABwIzNmzNAHH3yg3377Ldu6G/UrFotF7du3V0xMjM6dO6dff/1VTz31lNLT07V//35t2rRJd9xxh0qXLp2vmvbs2aPU1FRVrFjR7thxcXG2/u96faFZCKUAACgmypQpo1q1aqlWrVq644479K9//UtpaWl67733JEnbtm3ToEGD1K1bN61cuVK7d+/WCy+8oEuXLtn2MXXqVP3yyy/q3r27NmzYoAYNGmjZsmWSrv4k8PHHH7cFX7GxsdqzZ48OHjyomjVr5rnOrJ8DSlfvOSVJmZmZDj1GXvbl4+OjXbt26dNPP1VgYKAmT56spk2bFvpTZAAAgGtp3769wsLCFBERkW1dXnqfjh07KiYmRlu2bNFtt90mX19fW1C1adMmdejQId81paamKjAw0O64sbGxOnDggCZMmCDp+n2hWfj5HgAAxZTFYpGbm5v++usvSdLWrVtVvXp1vfDCC7Yx115FlaVOnTqqU6eOnnnmGQ0cOFALFy5Unz591Lx5c/3666+qVatWodXsyGPkZV8eHh4KDQ1VaGiopkyZonLlymnDhg3q27evPD09lZGRcdN1AAAAvPrqq2rWrJnq1q1rtzwv/UqHDh00duxYLVmyxHbvqI4dO2rdunX6/vvv9eyzz+a7nubNmysxMVEeHh6qUaNGruNy6wvN6pO4UgoAgGIiPT1diYmJSkxM1G+//aann35aqamp6tGjh6Sr9wGIj4/X4sWLdfjwYc2dO9fu266//vpLo0aNUkxMjI4eParvv/9eP/30k+rXry/p6pP7tm7dqlGjRik2NlYHDx7UihUrCnQT8tw48hg32tfKlSs1d+5cxcbG6ujRo/rwww+VmZlpaxZr1KihH374QUeOHNHp06dtV3MBAADkV+PGjTVo0CDNnTvXbnleep8mTZqofPny+uSTT+xCqeXLlys9PV1t2rTJdz2hoaFq1aqVevfurTVr1ujIkSPaunWrXnjhBe3YseOGfWGNGjWUmpqq9evX6/Tp04V2CwRCKQAAionVq1crMDBQgYGBatmypX766Se7b9R69uypZ555RqNGjVKzZs20detWTZo0yba9u7u7zpw5o8GDB6tOnTrq16+fwsPDFRkZKelqQ7Rp0yb9/vvvateunW677TZNnjxZQUFBDnsNjjzGjfZVrlw5LV26VHfffbfq16+vBQsW6NNPP1XDhg0lXb0hu7u7uxo0aKDKlSvb3XsLAAAgv6ZNm5btS6689D4Wi0Xt2rWTxWJR27Ztbdv5+vrq9ttvV5kyZfJdi8Vi0TfffKP27dtr2LBhqlOnjgYMGKCjR4/K39//hn1h69at9cQTT6h///6qXLmyXnvttZs4M9ep0zAMo1D2XIylpKTIz89PycnJ8vX1dXY5Rc7/fyFfYF9/7Zg6AKAgLl68qLi4OIWEhOTrSW9wTdf7vLhqv+CqrzvPYm6yUepIowTAddCXFW+O6JO4UgoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCALgkHj6LvPj7Y50BAIDj8e9t8eSI983DAXUAAFBslCpVShaLRadOnVLlypVlsVicXRKKIMMwdOnSJZ06dUpubm7y9PR0dkkAAJQ4np6ecnNz04kTJ1S5cmV5enrSmxUDjuyTCKUAAC7F3d1dVatW1fHjx3XkyBFnl4MirnTp0qpWrZrc3Li4HAAAR3Nzc1NISIgSEhJ04sQJZ5eDfHJEn+TUUGrz5s16/fXXtXPnTiUkJGjZsmXq3bu3bX1uCelrr72mCRMm5Lhu6tSpioyMtFtWt25d7d+/32F1AwCKt7Jly6p27dq6fPmys0tBEebu7i4PDw++sQUAoBB5enqqWrVqunLlijIyMpxdDvLIUX2SU0OptLQ0NW3aVMOHD1ffvn2zrU9ISLCbX7VqlR555BHdd999191vw4YNtW7dOtu8hwcXhAEA7Lm7u8vd3d3ZZQAAALg8i8WiUqVKqVSpUs4uBSZzaloTHh6u8PDwXNcHBATYza9YsUKdOnXSrbfeet39enh4ZNsWAAAAAAAARUexuUHCyZMn9Z///EePPPLIDccePHhQQUFBuvXWWzVo0CDFx8ebUCEAAAAAAADyqtj8ru2DDz6Qj49Pjj/zu1bLli0VHR2tunXrKiEhQZGRkWrXrp327dsnHx+fHLdJT09Xenq6bT4lJcWhtQMAAAAAAMBesQml3n//fQ0aNEheXl7XHXftzwGbNGmili1bqnr16vr8889zvcoqKioq283RAQAAAAAAUHiKxc/3tmzZogMHDujRRx/N97blypVTnTp1dOjQoVzHREREKDk52TYdO3bsZsoFAAAAAADADRSLUOrf//63WrRooaZNm+Z729TUVB0+fFiBgYG5jrFarfL19bWbAAAAAAAAUHicGkqlpqYqNjZWsbGxkqS4uDjFxsba3Zg8JSVFS5YsyfUqqc6dO2vevHm2+fHjx2vTpk06cuSItm7dqj59+sjd3V0DBw4s1NcCAAAAAACAvHPqPaV27NihTp062ebHjRsnSRoyZIiio6MlSYsXL5ZhGLmGSocPH9bp06dt88ePH9fAgQN15swZVa5cWW3bttX27dtVuXLlwnshAAAAAAAAyBenhlIdO3aUYRjXHTNixAiNGDEi1/VHjhyxm1+8eLEjSgMAAAAAAEAhKhb3lAIAAAAAAEDJQigFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAEAJsXnzZvXo0UNBQUGyWCxavnx5tjG//fabevbsKT8/P5UpU0Z33HGH4uPjzS8WAAC4PEIpAACAEiItLU1NmzbV22+/neP6w4cPq23btqpXr55iYmK0d+9eTZo0SV5eXiZXCgAAIHk4uwAAAAA4Rnh4uMLDw3Nd/8ILL6hbt2567bXXbMtq1qxpRmkAAADZcKUUAACAC8jMzNR//vMf1alTR2FhYapSpYpatmyZ40/8AAAAzEAoBQAA4AKSkpKUmpqqV199VV27dtWaNWvUp08f9e3bV5s2bcp1u/T0dKWkpNhNAAAAjsDP9wAAAFxAZmamJKlXr1565plnJEnNmjXT1q1btWDBAnXo0CHH7aKiohQZGWlanQAAwHVwpRQAAIALqFSpkjw8PNSgQQO75fXr17/u0/ciIiKUnJxsm44dO1bYpQIAABfBlVIAAAAuwNPTU3fccYcOHDhgt/z3339X9erVc93OarXKarUWdnkAAMAFEUoBAACUEKmpqTp06JBtPi4uTrGxsapQoYKqVaumCRMmqH///mrfvr06deqk1atX6+uvv1ZMTIzzigYAAC6LUAoAAKCE2LFjhzp16mSbHzdunCRpyJAhio6OVp8+fbRgwQJFRUVp9OjRqlu3rr788ku1bdvWWSUDAAAXRigFAABQQnTs2FGGYVx3zPDhwzV8+HCTKgIAAMgdNzoHAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJjOw9kFwDl69HB2BQAAAAAAwJVxpRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABM59RQavPmzerRo4eCgoJksVi0fPlyu/VDhw6VxWKxm7p27XrD/b799tuqUaOGvLy81LJlS/3444+F9AoAAAAAAABQEE4NpdLS0tS0aVO9/fbbuY7p2rWrEhISbNOnn3563X1+9tlnGjdunKZMmaJdu3apadOmCgsLU1JSkqPLBwAAAAAAQAF5OPPg4eHhCg8Pv+4Yq9WqgICAPO9z5syZeuyxxzRs2DBJ0oIFC/Sf//xH77//viZOnHhT9QIAAAAAAMAxivw9pWJiYlSlShXVrVtXTz75pM6cOZPr2EuXLmnnzp0KDQ21LXNzc1NoaKi2bduW63bp6elKSUmxmwAAAAAAAFB4inQo1bVrV3344Ydav369ZsyYoU2bNik8PFwZGRk5jj99+rQyMjLk7+9vt9zf31+JiYm5HicqKkp+fn62KTg42KGvAwAAAAAAAPaKdCg1YMAA9ezZU40bN1bv3r21cuVK/fTTT4qJiXHocSIiIpScnGybjh075tD9AwAAmOFGD5G51hNPPCGLxaLZs2ebVh8AAMC1inQo9Xe33nqrKlWqpEOHDuW4vlKlSnJ3d9fJkyftlp88efK696WyWq3y9fW1mwAAAIqbvDxERpKWLVum7du3KygoyKTKAAAAsitWodTx48d15swZBQYG5rje09NTLVq00Pr1623LMjMztX79erVq1cqsMgEAAJwiPDxcL730kvr06ZPrmD///FNPP/20Pv74Y5UqVcrE6gAAAOw59el7qampdlc9xcXFKTY2VhUqVFCFChUUGRmp++67TwEBATp8+LCee+451apVS2FhYbZtOnfurD59+mjUqFGSpHHjxmnIkCG6/fbbdeedd2r27NlKS0uzPY0PAADAVWVmZurhhx/WhAkT1LBhwzxtk56ervT0dNs8D4QBAACO4tRQaseOHerUqZNtfty4cZKkIUOGaP78+dq7d68++OADnTt3TkFBQerSpYumT58uq9Vq2+bw4cM6ffq0bb5///46deqUJk+erMTERDVr1kyrV6/OdvNzAAAAVzNjxgx5eHho9OjRed4mKipKkZGRhVgVAABwVU4NpTp27CjDMHJd/+23395wH0eOHMm2bNSoUbYrpwAAACDt3LlTc+bM0a5du2SxWPK8XUREhO2LQ+nqlVI8qRgAADhCsbqnFAAAAApmy5YtSkpKUrVq1eTh4SEPDw8dPXpUzz77rGrUqJHrdjwQBgAAFBanXikFAAAAczz88MMKDQ21WxYWFqaHH36Ye28CAACnIJQCAAAoIa73EJlq1aqpYsWKduNLlSqlgIAA1a1b1+xSAQAACKUAAABKius9RCY6OtpJVQEAAOSMUAoAAKCEuNFDZP4upwfGAAAAmIUbnQMAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0Hs4uAAAAAChSYno4uwIAAFwCV0oBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAFBCbN68WT169FBQUJAsFouWL19uW3f58mU9//zzaty4scqUKaOgoCANHjxYJ06ccF7BAADApRFKAQAAlBBpaWlq2rSp3n777WzrLly4oF27dmnSpEnatWuXli5dqgMHDqhnz55OqBQAAEDycHYBAAAAcIzw8HCFh4fnuM7Pz09r1661WzZv3jzdeeedio+PV7Vq1cwoEQAAwIYrpQAAAFxUcnKyLBaLypUr5+xSAACAC+JKKQAAABd08eJFPf/88xo4cKB8fX1zHZeenq709HTbfEpKihnlAQAAF8CVUgAAAC7m8uXL6tevnwzD0Pz58687NioqSn5+frYpODjYpCoBAEBJ59RQqjCeEDN16lRZLBa7qV69eoX8SgAAAIqHrEDq6NGjWrt27XWvkpKkiIgIJScn26Zjx46ZVCkAACjpnBpKFdYTYho2bKiEhATb9N133xVG+QAAAMVKViB18OBBrVu3ThUrVrzhNlarVb6+vnYTAACAIzj1nlKF9YQYDw8PBQQEOLRWAACAoi41NVWHDh2yzcfFxSk2NlYVKlRQYGCg7r//fu3atUsrV65URkaGEhMTJUkVKlSQp6ens8oGAAAuqljd6DyvT4g5ePCggoKC5OXlpVatWikqKuq6IRY38AQAACXBjh071KlTJ9v8uHHjJElDhgzR1KlT9dVXX0mSmjVrZrfdxo0b1bFjR7PKBAAAkFSMQqm8PiGmZcuWio6OVt26dZWQkKDIyEi1a9dO+/btk4+PT47bREVFKTIysrBKBwAAMEXHjh1lGEau66+3DgAAwGzF4ul7+XlCTHh4uB544AE1adJEYWFh+uabb3Tu3Dl9/vnnuW7DDTwBAAAAAADMVeSvlLr2CTEbNmzI9801y5Urpzp16tjdX+HvrFarrFbrzZYKAAAAAACAPCrSV0oV5Akxf5eamqrDhw8rMDCwECoEAAAAAABAQTg1lEpNTVVsbKxiY2Ml/e8JMfHx8bp8+bLuv/9+7dixQx9//LHtCTGJiYm6dOmSbR+dO3fWvHnzbPPjx4/Xpk2bdOTIEW3dulV9+vSRu7u7Bg4caPbLAwAAAAAAQC6c+vM9Rzwh5vDhwzp9+rRt3fHjxzVw4ECdOXNGlStXVtu2bbV9+3ZVrly5cF8MAAAAAAAA8sypoZQjnhBz5MgRu/nFixffbFkAAAAAAAAoZEX6nlIAAAAAAAAomQilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAoITZv3qwePXooKChIFotFy5cvt1tvGIYmT56swMBAeXt7KzQ0VAcPHnROsQAAwOUVKJT6448/HF0HAACAy3JUb5WWlqamTZvq7bffznH9a6+9prlz52rBggX64YcfVKZMGYWFhenixYsOOT4AAEB+FCiUqlWrljp16qRFixbRxAAAANwkR/VW4eHheumll9SnT59s6wzD0OzZs/Xiiy+qV69eatKkiT788EOdOHEi2xVVAAAAZihQKLVr1y41adJE48aNU0BAgB5//HH9+OOPjq4NAADAJZjRW8XFxSkxMVGhoaG2ZX5+fmrZsqW2bduW63bp6elKSUmxmwAAAByhQKFUs2bNNGfOHJ04cULvv/++EhIS1LZtWzVq1EgzZ87UqVOnHF0nAABAiWVGb5WYmChJ8vf3t1vu7+9vW5eTqKgo+fn52abg4OCbrgUAAEC6yRude3h4qG/fvlqyZIlmzJihQ4cOafz48QoODtbgwYOVkJDgqDoBAABKvKLYW0VERCg5Odk2HTt2zPQaAABAyXRTodSOHTv01FNPKTAwUDNnztT48eN1+PBhrV27VidOnFCvXr0cVScAAECJV5i9VUBAgCTp5MmTdstPnjxpW5cTq9UqX19fuwkAAMARPAqy0cyZM7Vw4UIdOHBA3bp104cffqhu3brJze1qxhUSEqLo6GjVqFHDkbUCAACUSGb0ViEhIQoICND69evVrFkzSVJKSop++OEHPfnkkw54FQAAAPlToFBq/vz5Gj58uIYOHarAwMAcx1SpUkX//ve/b6o4AAAAV+Co3io1NVWHDh2yzcfFxSk2NlYVKlRQtWrVNHbsWL300kuqXbu2QkJCNGnSJAUFBal3796OfDkAAAB5UqBQ6uDBgzcc4+npqSFDhhRk9wAAAC7FUb3Vjh071KlTJ9v8uHHjJElDhgxRdHS0nnvuOaWlpWnEiBE6d+6c2rZtq9WrV8vLy+vmXgAAAEABFCiUWrhwocqWLasHHnjAbvmSJUt04cIFwigAAIB8cFRv1bFjRxmGket6i8WiadOmadq0aTdVLwAAgCMU6EbnUVFRqlSpUrblVapU0SuvvHLTRQEAALgSeisAAOCKChRKxcfHKyQkJNvy6tWrKz4+/qaLAgAAcCX0VgAAwBUVKJSqUqWK9u7dm235nj17VLFixZsuCgAAwJXQWwEAAFdUoFBq4MCBGj16tDZu3KiMjAxlZGRow4YNGjNmjAYMGODoGgEAAEo0eisAAOCKChRKTZ8+XS1btlTnzp3l7e0tb29vdenSRXfffXe+7nuwefNm9ejRQ0FBQbJYLFq+fLndesMwNHnyZAUGBsrb21uhoaF5ejrN22+/rRo1asjLy0stW7bUjz/+mN+XCAAAYBpH9VYAAADFSYFCKU9PT3322Wfav3+/Pv74Yy1dulSHDx/W+++/L09PzzzvJy0tTU2bNtXbb7+d4/rXXntNc+fO1YIFC/TDDz+oTJkyCgsL08WLF3Pd52effaZx48ZpypQp2rVrl5o2baqwsDAlJSXl+3UCAACYwVG9FQAAQHFiMa733GATWSwWLVu2TL1795Z09SqpoKAgPfvssxo/frwkKTk5Wf7+/oqOjs71UvaWLVvqjjvu0Lx58yRJmZmZCg4O1tNPP62JEyfmqZaUlBT5+fkpOTlZvr6+N//iiqAePZx37K+/dt6xAQBwFFfoF3LiEq87xomNUkcaJQBA8ZfXfsGjIDvPyMhQdHS01q9fr6SkJGVmZtqt37BhQ0F2aycuLk6JiYkKDQ21LfPz81PLli21bdu2HEOpS5cuaefOnYqIiLAtc3NzU2hoqLZt23bTNQEAABQGM3orAACAoqZAodSYMWMUHR2t7t27q1GjRrJYLI6uS4mJiZIkf39/u+X+/v62dX93+vRpZWRk5LjN/v37cz1Wenq60tPTbfMpKSkFLRsAACDfzOitAAAAipoChVKLFy/W559/rm7dujm6HqeIiopSZGSks8sAAAAuqqT1VgAAAHlR4Bud16pVy9G12AkICJAknTx50m75yZMnbev+rlKlSnJ3d8/XNpIUERGh5ORk23Ts2LGbrB4AACDvzOitAAAAipoChVLPPvus5syZo8K8R3pISIgCAgK0fv1627KUlBT98MMPatWqVY7beHp6qkWLFnbbZGZmav369bluI0lWq1W+vr52EwAAgFnM6K0AAACKmgL9fO+7777Txo0btWrVKjVs2FClSpWyW7906dI87Sc1NVWHDh2yzcfFxSk2NlYVKlRQtWrVNHbsWL300kuqXbu2QkJCNGnSJAUFBdme0CdJnTt3Vp8+fTRq1ChJ0rhx4zRkyBDdfvvtuvPOOzV79mylpaVp2LBhBXmpAAAAhc5RvRUAAEBxUqBQqly5curTp89NH3zHjh3q1KmTbX7cuHGSpCFDhig6OlrPPfec0tLSNGLECJ07d05t27bV6tWr5eXlZdvm8OHDOn36tG2+f//+OnXqlCZPnqzExEQ1a9ZMq1evznbzcwAAgKLCUb0VAABAcWIxuE48m5SUFPn5+Sk5ObnE/pSvRw/nHfvrr513bAAAHMUV+oWcuMTrjnFio9SRRgkAUPzltV8o0D2lJOnKlStat26d3n33XZ0/f16SdOLECaWmphZ0lwAAAC6L3goAALiaAv187+jRo+ratavi4+OVnp6ue+65Rz4+PpoxY4bS09O1YMECR9cJAABQYtFbAQAAV1SgK6XGjBmj22+/XWfPnpW3t7dteZ8+feyefAcAAIAbo7cCAACuqEBXSm3ZskVbt26Vp6en3fIaNWrozz//dEhhAAAAroLeCgAAuKICXSmVmZmpjIyMbMuPHz8uHx+fmy4KAADAldBbAQAAV1SgUKpLly6aPXu2bd5isSg1NVVTpkxRt27dHFUbAACAS6C3AgAArqhAP9978803FRYWpgYNGujixYt68MEHdfDgQVWqVEmffvqpo2sEAAAo0eitAACAKypQKFW1alXt2bNHixcv1t69e5WamqpHHnlEgwYNsrs5JwAAAG6M3goAALiiAoVSkuTh4aGHHnrIkbUAAAC4LHorAADgagoUSn344YfXXT948OACFQMAAOCK6K0AAIArKlAoNWbMGLv5y5cv68KFC/L09FTp0qVpnAAAAPKB3goAALiiAj197+zZs3ZTamqqDhw4oLZt23IzTgAAgHyitwIAAK6oQKFUTmrXrq1XX3012zd9AAAAyD96KwAAUNI5LJSSrt6g88SJE47cJQAAgMuitwIAACVZge4p9dVXX9nNG4ahhIQEzZs3T23atHFIYQAAAK6C3goAALiiAoVSvXv3tpu3WCyqXLmy7r77br355puOqAsAAMBl0FsBAABXVKBQKjMz09F1AAAAuCx6KwAA4Iocek8pAAAAAAAAIC8KdKXUuHHj8jx25syZBTkEAACAy6C3AgAArqhAodTu3bu1e/duXb58WXXr1pUk/f7773J3d1fz5s1t4ywWi2OqBAAAKMHorQAAgCsqUCjVo0cP+fj46IMPPlD58uUlSWfPntWwYcPUrl07Pfvssw4tEgAAoCSjtwIAAK7IYhiGkd+NbrnlFq1Zs0YNGza0W75v3z516dJFJ06ccFiBzpCSkiI/Pz8lJyfL19fX2eUUih49nHfsr7923rGlm3/tzq4fAFA0OLJfKE69lSv0SYpxYqPUkUYDAFD85bVfKNCNzlNSUnTq1Klsy0+dOqXz588XZJcAAAAui94KAAC4ogKFUn369NGwYcO0dOlSHT9+XMePH9eXX36pRx55RH379nV0jQAAACUavRUAAHBFBbqn1IIFCzR+/Hg9+OCDunz58tUdeXjokUce0euvv+7QAgEAAEo6eisAAOCKChRKlS5dWu+8845ef/11HT58WJJUs2ZNlSlTxqHFAQAAuAJ6KwAA4IoK9PO9LAkJCUpISFDt2rVVpkwZFeCe6QAAAPh/9FYAAMCVFCiUOnPmjDp37qw6deqoW7duSkhIkCQ98sgjPLIYAAAgn+itAACAKypQKPXMM8+oVKlSio+PV+nSpW3L+/fvr9WrVzusOAAAAFdAbwUAAFxRge4ptWbNGn377beqWrWq3fLatWvr6NGjDikMAADAVdBbAQAAV1SgK6XS0tLsvsXL8t///ldWq/WmiwIAAHAlZvVWGRkZmjRpkkJCQuTt7a2aNWtq+vTp3LsKAAA4RYFCqXbt2unDDz+0zVssFmVmZuq1115Tp06dHFYcAACAKzCrt5oxY4bmz5+vefPm6bffftOMGTP02muv6a233nLYMQAAAPKqQD/fe+2119S5c2ft2LFDly5d0nPPPadffvlF//3vf/X99987ukYAAIASzazeauvWrerVq5e6d+8uSapRo4Y+/fRT/fjjjw47BgAAQF4V6EqpRo0a6ffff1fbtm3Vq1cvpaWlqW/fvtq9e7dq1qzp6BoBAABKNLN6q9atW2v9+vX6/fffJUl79uzRd999p/DwcIcdAwAAIK/yfaXU5cuX1bVrVy1YsEAvvPBCYdQEAADgMszsrSZOnKiUlBTVq1dP7u7uysjI0Msvv6xBgwbluk16errS09Nt8ykpKYVaIwAAcB35DqVKlSqlvXv3FkYtAAAALsfM3urzzz/Xxx9/rE8++UQNGzZUbGysxo4dq6CgIA0ZMiTHbaKiohQZGWlKfQ4T08PZFRTczdbe8WvH1AEAgAkK9PO9hx56SP/+978dXQsAAIBLMqu3mjBhgiZOnKgBAwaocePGevjhh/XMM88oKioq120iIiKUnJxsm44dO1bodQIAANdQoBudX7lyRe+//77WrVunFi1aqEyZMnbrZ86c6ZDiAAAAXIFZvdWFCxfk5mb/naS7u7syMzNz3cZqtcpqtTrk+AAAANfKVyj1xx9/qEaNGtq3b5+aN28uSbYbZWaxWCyOqw4AAKAEM7u36tGjh15++WVVq1ZNDRs21O7duzVz5kwNHz7cYccAAADIq3yFUrVr11ZCQoI2btwoSerfv7/mzp0rf3//QikOAACgJDO7t3rrrbc0adIkPfXUU0pKSlJQUJAef/xxTZ48uVCOBwAAcD35CqUMw7CbX7VqldLS0hxaEAAAgKswu7fy8fHR7NmzNXv27EI7BgAAQF4V6EbnWf7eSAEAAKDg6K0AAIAryVcoZbFYst3XgHtIAQAAFAy9FQAAcGX5/vne0KFDbU9guXjxop544olsT4hZunSp4yoEAAAooeitAACAK8tXKDVkyBC7+YceesihxQAAALgSeisAAODK8hVKLVy4sLDqAAAAcDn0VgAAwJXd1I3OAQAAAAAAgIIglAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpinwoVaNGDVkslmzTyJEjcxwfHR2dbayXl5fJVQMAAAAAAOB6PJxdwI389NNPysjIsM3v27dP99xzjx544IFct/H19dWBAwds8xaLpVBrBAAAAAAAQP4U+VCqcuXKdvOvvvqqatasqQ4dOuS6jcViUUBAQGGXBgAAAAAAgAIq8j/fu9alS5e0aNEiDR8+/LpXP6Wmpqp69eoKDg5Wr1699Msvv5hYJQAAAAAAAG6kWIVSy5cv17lz5zR06NBcx9StW1fvv/++VqxYoUWLFikzM1OtW7fW8ePHc90mPT1dKSkpdhMAAAAAAAAKT7EKpf79738rPDxcQUFBuY5p1aqVBg8erGbNmqlDhw5aunSpKleurHfffTfXbaKiouTn52ebgoODC6N8AAAAAAAA/L9iE0odPXpU69at06OPPpqv7UqVKqXbbrtNhw4dynVMRESEkpOTbdOxY8dutlwAAAAAAABcR5G/0XmWhQsXqkqVKurevXu+tsvIyNDPP/+sbt265TrGarXKarXebIkAAACAc8X0uLntO37tmDoAAMiDYnGlVGZmphYuXKghQ4bIw8M+Rxs8eLAiIiJs89OmTdOaNWv0xx9/aNeuXXrooYd09OjRfF9hBQAAAAAAgMJTLK6UWrduneLj4zV8+PBs6+Lj4+Xm9r9s7ezZs3rssceUmJio8uXLq0WLFtq6dasaNGhgZskAAAAAAAC4jmIRSnXp0kWGYeS4LiYmxm5+1qxZmjVrlglVAQAAAAAAoKCKxc/3AAAAAAAAULIQSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwnYezC0DB9Ojh7AoK7mZr//prx9QBAAAAAACchyulAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAAAAAYDpCKQAAAAAAAJiOUAoAAAAAAACmI5QCAAAAAACA6QilAAAAXMiff/6phx56SBUrVpS3t7caN26sHTt2OLssAADggjycXQAAAADMcfbsWbVp00adOnXSqlWrVLlyZR08eFDly5d3dmkAAMAFEUoBAAC4iBkzZig4OFgLFy60LQsJCXFiRQAAwJXx8z0AAAAX8dVXX+n222/XAw88oCpVqui2227Te++9d91t0tPTlZKSYjcBAAA4AqEUAACAi/jjjz80f/581a5dW99++62efPJJjR49Wh988EGu20RFRcnPz882BQcHm1gxAAAoyQilAAAAXERmZqaaN2+uV155RbfddptGjBihxx57TAsWLMh1m4iICCUnJ9umY8eOmVgxAAAoyQilAAAAXERgYKAaNGhgt6x+/fqKj4/PdRur1SpfX1+7CQAAwBEIpQAAAFxEmzZtdODAAbtlv//+u6pXr+6kigAAgCsjlAIAAHARzzzzjLZv365XXnlFhw4d0ieffKJ//vOfGjlypLNLAwAALohQCgAAwEXccccdWrZsmT799FM1atRI06dP1+zZszVo0CBnlwYAAFyQh7MLAAAAgHnuvfde3Xvvvc4uAwAAgCulAAAAAAAAYD5CKQAAAAAAAJiOUAoAAAAAAACm455STtKjh7MrAAAAAAAAcB6ulAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmI5QCgAAAAAAAKYjlAIAAAAAAIDpPJxdAAAAAIAiIqaHc4/f8WvnHh8AYCqulAIAAAAAAIDpCKUAAAAAAABgOkIpAAAAAAAAmK5Ih1JTp06VxWKxm+rVq3fdbZYsWaJ69erJy8tLjRs31jfffGNStQAAAAAAAMirIh1KSVLDhg2VkJBgm7777rtcx27dulUDBw7UI488ot27d6t3797q3bu39u3bZ2LFAAAAAAAAuJEiH0p5eHgoICDANlWqVCnXsXPmzFHXrl01YcIE1a9fX9OnT1fz5s01b948EysGAAAAAADAjRT5UOrgwYMKCgrSrbfeqkGDBik+Pj7Xsdu2bVNoaKjdsrCwMG3btu26x0hPT1dKSordBAAAAAAAgMLj4ewCrqdly5aKjo5W3bp1lZCQoMjISLVr10779u2Tj49PtvGJiYny9/e3W+bv76/ExMTrHicqKkqRkZEOrR2Fp0eP4n38r792TB0AAAAAABRnRfpKqfDwcD3wwANq0qSJwsLC9M033+jcuXP6/PPPHXqciIgIJScn26Zjx445dP8AAAAAAACwV6SvlPq7cuXKqU6dOjp06FCO6wMCAnTy5Em7ZSdPnlRAQMB192u1WmW1Wh1WJwAAAAAAAK6vSF8p9Xepqak6fPiwAgMDc1zfqlUrrV+/3m7Z2rVr1apVKzPKAwAAAAAAQB4V6VBq/Pjx2rRpk44cOaKtW7eqT58+cnd318CBAyVJgwcPVkREhG38mDFjtHr1ar355pvav3+/pk6dqh07dmjUqFHOegkAAAAAAADIQZH++d7x48c1cOBAnTlzRpUrV1bbtm21fft2Va5cWZIUHx8vN7f/5WqtW7fWJ598ohdffFH/+Mc/VLt2bS1fvlyNGjVy1ksAAAAAAABADop0KLV48eLrro+Jicm27IEHHtADDzxQSBUBAAAAAADAEYr0z/cAAAAAAABQMhFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAuKhXX31VFotFY8eOdXYpAADABRFKAQAAuKCffvpJ7777rpo0aeLsUgAAgIsilAIAAHAxqampGjRokN577z2VL1/e2eUAAAAXRSgFAADgYkaOHKnu3bsrNDTU2aUAAAAX5uHsAgAAAGCexYsXa9euXfrpp5/yND49PV3p6em2+ZSUlMIqDQAAuBiulAIAAHARx44d05gxY/Txxx/Ly8srT9tERUXJz8/PNgUHBxdylQAAwFUQSgEAALiInTt3KikpSc2bN5eHh4c8PDy0adMmzZ07Vx4eHsrIyMi2TUREhJKTk23TsWPHnFA5AAAoifj5HgAAgIvo3Lmzfv75Z7tlw4YNU7169fT888/L3d092zZWq1VWq9WsEgEAgAshlAIAAHARPj4+atSokd2yMmXKqGLFitmWAwAAFDZ+vgcAAAAAAADTcaUUAACAC4uJiXF2CQAAwEVxpRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA0xFKAQAAAAAAwHSEUgAAAAAAADAdoRQAAAAAAABMRygFAAAAAAAA03k4uwAAAADATkwPZ1cAAABMwJVSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMF2RDqWioqJ0xx13yMfHR1WqVFHv3r114MCB624THR0ti8ViN3l5eZlUMQAAAAAAAPKiSIdSmzZt0siRI7V9+3atXbtWly9fVpcuXZSWlnbd7Xx9fZWQkGCbjh49alLFAAAAAAAAyAsPZxdwPatXr7abj46OVpUqVbRz5061b98+1+0sFosCAgIKuzwAAAAAAAAUUJG+UurvkpOTJUkVKlS47rjU1FRVr15dwcHB6tWrl3755Zfrjk9PT1dKSordBAAAAAAAgMJTbEKpzMxMjR07Vm3atFGjRo1yHVe3bl29//77WrFihRYtWqTMzEy1bt1ax48fz3WbqKgo+fn52abg4ODCeAkAAAAAAAD4f8UmlBo5cqT27dunxYsXX3dcq1atNHjwYDVr1kwdOnTQ0qVLVblyZb377ru5bhMREaHk5GTbdOzYMUeXDwAAAAAAgGsU6XtKZRk1apRWrlypzZs3q2rVqvnatlSpUrrtttt06NChXMdYrVZZrdabLRMAAAAAAAB5VKSvlDIMQ6NGjdKyZcu0YcMGhYSE5HsfGRkZ+vnnnxUYGFgIFQIAAAAAAKAgivSVUiNHjtQnn3yiFStWyMfHR4mJiZIkPz8/eXt7S5IGDx6sW265RVFRUZKkadOm6a677lKtWrV07tw5vf766zp69KgeffRRp70OAAAAAAAA2CvSodT8+fMlSR07drRbvnDhQg0dOlSSFB8fLze3/13wdfbsWT322GNKTExU+fLl1aJFC23dulUNGjQwq2wAAAAAAADcQJEOpQzDuOGYmJgYu/lZs2Zp1qxZhVQRAABA8RYVFaWlS5dq//798vb2VuvWrTVjxgzVrVvX2aUBAAAXU6TvKQUAAADH2rRpk0aOHKnt27dr7dq1unz5srp06aK0tDRnlwYAAFxMkb5SCgAAAI61evVqu/no6GhVqVJFO3fuVPv27Z1UFQAAcEWEUgAAAC4sOTlZklShQoUc16enpys9Pd02n5KSYkpdAACg5COUAgAAcFGZmZkaO3as2rRpo0aNGuU4JioqSpGRkSZXBhRQTI+b277j146pAwCQJ9xTCgAAwEWNHDlS+/bt0+LFi3MdExERoeTkZNt07NgxEysEAAAlGVdKAQAAuKBRo0Zp5cqV2rx5s6pWrZrrOKvVKqvVamJlAADAVRBKAQAAuBDDMPT0009r2bJliomJUUhIiLNLAgAALopQCgAAwIWMHDlSn3zyiVasWCEfHx8lJiZKkvz8/OTt7e3k6gAAgCvhnlIAAAAuZP78+UpOTlbHjh0VGBhomz777DNnlwYAAFwMV0oBAAC4EMMwnF0CAACAJK6UAgAAAAAAgBMQSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANN5OLsAAAAAAJAkxfRwdgUAABNxpRQAAAAAAABMx5VSgMl6OPkLwK+/dt6xb/a1O7N2R3D11w8UBH83AAAAJRdXSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0hFIAAAAAAAAwHaEUAAAAAAAATEcoBQAAAAAAANMRSgEAAAAAAMB0xSKUevvtt1WjRg15eXmpZcuW+vHHH687fsmSJapXr568vLzUuHFjffPNNyZVCgAAUPTlt7cCAAAoDEU+lPrss880btw4TZkyRbt27VLTpk0VFhampKSkHMdv3bpVAwcO1COPPKLdu3erd+/e6t27t/bt22dy5QAAAEVPfnsrAACAwlLkQ6mZM2fqscce07Bhw9SgQQMtWLBApUuX1vvvv5/j+Dlz5qhr166aMGGC6tevr+nTp6t58+aaN2+eyZUDAAAUPfntrQAAAApLkQ6lLl26pJ07dyo0NNS2zM3NTaGhodq2bVuO22zbts1uvCSFhYXlOh4AAMBVFKS3AgAAKCwezi7gek6fPq2MjAz5+/vbLff399f+/ftz3CYxMTHH8YmJibkeJz09Xenp6bb55ORkSVJKSkpBS7+hy5cLbdfAdRXix/qGbvZz78zaHcHVXz9QEEX57yarTzAMo/AO4mAF6a2c0ScpjUYJTsI/tgDgEHntk4p0KGWWqKgoRUZGZlseHBzshGqAwuXn5+wKCq441+4Irv76gYIw4+/m/Pnz8ivBf6D0SXAtJfdvGQCc4UZ9UpEOpSpVqiR3d3edPHnSbvnJkycVEBCQ4zYBAQH5Gi9JERERGjdunG0+MzNT//3vf1WxYkVZLJabeAX/k5KSouDgYB07dky+vr4O2SfyjvPvPJx75+L8Oxfn33nMOPeGYej8+fMKCgoqlP0XhoL0VvRJJR/n33k4987F+Xcuzr/zFKU+qUiHUp6enmrRooXWr1+v3r17S7raCK1fv16jRo3KcZtWrVpp/fr1Gjt2rG3Z2rVr1apVq1yPY7VaZbVa7ZaVK1fuZsvPka+vL39wTsT5dx7OvXNx/p2L8+88hX3ui9sVUgXpreiTXAfn33k4987F+Xcuzr/zFIU+qUiHUpI0btw4DRkyRLfffrvuvPNOzZ49W2lpaRo2bJgkafDgwbrlllsUFRUlSRozZow6dOigN998U927d9fixYu1Y8cO/fOf/3TmywAAACgSbtRbAQAAmKXIh1L9+/fXqVOnNHnyZCUmJqpZs2ZavXq17Qad8fHxcnP730MEW7durU8++UQvvvii/vGPf6h27dpavny5GjVq5KyXAAAAUGTcqLcCAAAwS5EPpSRp1KhRuV5SHhMTk23ZAw88oAceeKCQq8ofq9WqKVOmZLv8Hebg/DsP5965OP/Oxfl3Hs799V2vt3IG3i/n4vw7D+feuTj/zsX5d56idO4tRnF6jjEAAAAAAABKBLcbDwEAAAAAAAAci1AKAAAAAAAApiOUAgAAAAAAgOkIpUzw9ttvq0aNGvLy8lLLli31448/OrukEmnz5s3q0aOHgoKCZLFYtHz5crv1hmFo8uTJCgwMlLe3t0JDQ3Xw4EHnFFsCRUVF6Y477pCPj4+qVKmi3r1768CBA3ZjLl68qJEjR6pixYoqW7as7rvvPp08edJJFZcc8+fPV5MmTeTr6ytfX1+1atVKq1atsq3nvJvr1VdflcVi0dixY23LeA8Kz9SpU2WxWOymevXq2dZz7os++iRz0Cc5F32S89AnFS30SeYqDn0SoVQh++yzzzRu3DhNmTJFu3btUtOmTRUWFqakpCRnl1bipKWlqWnTpnr77bdzXP/aa69p7ty5WrBggX744QeVKVNGYWFhunjxosmVlkybNm3SyJEjtX37dq1du1aXL19Wly5dlJaWZhvzzDPP6Ouvv9aSJUu0adMmnThxQn379nVi1SVD1apV9eqrr2rnzp3asWOH7r77bvXq1Uu//PKLJM67mX766Se9++67atKkid1y3oPC1bBhQyUkJNim7777zraOc1+00SeZhz7JueiTnIc+qeigT3KOIt8nGShUd955pzFy5EjbfEZGhhEUFGRERUU5saqST5KxbNky23xmZqYREBBgvP7667Zl586dM6xWq/Hpp586ocKSLykpyZBkbNq0yTCMq+e7VKlSxpIlS2xjfvvtN0OSsW3bNmeVWWKVL1/e+Ne//sV5N9H58+eN2rVrG2vXrjU6dOhgjBkzxjAMPvuFbcqUKUbTpk1zXMe5L/rok5yDPsn56JOciz7JfPRJzlEc+iSulCpEly5d0s6dOxUaGmpb5ubmptDQUG3bts2JlbmeuLg4JSYm2r0Xfn5+atmyJe9FIUlOTpYkVahQQZK0c+dOXb582e49qFevnqpVq8Z74EAZGRlavHix0tLS1KpVK867iUaOHKnu3bvbnWuJz74ZDh48qKCgIN16660aNGiQ4uPjJXHuizr6pKKDPsl89EnOQZ/kPPRJzlPU+yQP047kgk6fPq2MjAz5+/vbLff399f+/fudVJVrSkxMlKQc34usdXCczMxMjR07Vm3atFGjRo0kXX0PPD09Va5cObuxvAeO8fPPP6tVq1a6ePGiypYtq2XLlqlBgwaKjY3lvJtg8eLF2rVrl3766ads6/jsF66WLVsqOjpadevWVUJCgiIjI9WuXTvt27ePc1/E0ScVHfRJ5qJPMh99knPRJzlPceiTCKUAONzIkSO1b98+u98ro3DVrVtXsbGxSk5O1hdffKEhQ4Zo06ZNzi7LJRw7dkxjxozR2rVr5eXl5exyXE54eLjtfzdp0kQtW7ZU9erV9fnnn8vb29uJlQFAzuiTzEef5Dz0Sc5VHPokfr5XiCpVqiR3d/dsd68/efKkAgICnFSVa8o637wXhW/UqFFauXKlNm7cqKpVq9qWBwQE6NKlSzp37pzdeN4Dx/D09FStWrXUokULRUVFqWnTppozZw7n3QQ7d+5UUlKSmjdvLg8PD3l4eGjTpk2aO3euPDw85O/vz3tgonLlyqlOnTo6dOgQn/8ijj6p6KBPMg99knPQJzkPfVLRUhT7JEKpQuTp6akWLVpo/fr1tmWZmZlav369WrVq5cTKXE9ISIgCAgLs3ouUlBT98MMPvBcOYhiGRo0apWXLlmnDhg0KCQmxW9+iRQuVKlXK7j04cOCA4uPjeQ8KQWZmptLT0znvJujcubN+/vlnxcbG2qbbb79dgwYNsv1v3gPzpKam6vDhwwoMDOTzX8TRJxUd9EmFjz6paKFPMg99UtFSJPsk026p7qIWL15sWK1WIzo62vj111+NESNGGOXKlTMSExOdXVqJc/78eWP37t3G7t27DUnGzJkzjd27dxtHjx41DMMwXn31VaNcuXLGihUrjL179xq9evUyQkJCjL/++svJlZcMTz75pOHn52fExMQYCQkJtunChQu2MU888YRRrVo1Y8OGDcaOHTuMVq1aGa1atXJi1SXDxIkTjU2bNhlxcXHG3r17jYkTJxoWi8VYs2aNYRicd2e49qkyhsF7UJieffZZIyYmxoiLizO+//57IzQ01KhUqZKRlJRkGAbnvqijTzIPfZJz0Sc5D31S0UOfZJ7i0CcRSpngrbfeMqpVq2Z4enoad955p7F9+3Znl1Qibdy40ZCUbRoyZIhhGFcfdzxp0iTD39/fsFqtRufOnY0DBw44t+gSJKdzL8lYuHChbcxff/1lPPXUU0b58uWN0qVLG3369DESEhKcV3QJMXz4cKN69eqGp6enUblyZaNz5862RsswOO/O8Pdmi/eg8PTv398IDAw0PD09jVtuucXo37+/cejQIdt6zn3RR59kDvok56JPch76pKKHPsk8xaFPshiGYZh3XRYAAAAAAADAPaUAAAAAAADgBIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAFzG0KFDZbFYsk2HDh3K0/Zbt25Vt27dVL58eXl5ealx48aaOXOmMjIyJEnR0dE57v/a6ciRI4X4CgEAAAqGPgmAMxBKAXApXbt2VUJCgt0UEhJyw+2WLVumDh06qGrVqtq4caP279+vMWPG6KWXXtKAAQNkGIb69+9vt99WrVrpscces1sWHBxswqsEAADIP/okAGbzcHYBAGAmq9WqgICAbMtXrFihyMhI/frrrwoKCtKQIUP0wgsvyMPDQ2lpaXrsscfUs2dP/fOf/7Rt8+ijj8rf3189e/bU559/rv79+8vb29u23tPTU6VLl87xeAAAAEUNfRIAs3GlFACXt2XLFg0ePFhjxozRr7/+qnfffVfR0dF6+eWXJUlr1qzRmTNnNH78+Gzb9ujRQ3Xq1NGnn35qdtkAAACFjj4JQGHiSikALmXlypUqW7asbT48PFxnz57VxIkTNWTIEEnSrbfequnTp+u5557TlClT9Pvvv0uS6tevn+M+69WrZxsDAABQXNEnATAboRQAl9KpUyfNnz/fNl+mTBk1adJE33//ve0bP0nKyMjQxYsXdeHCBdsywzBMrRUAAMBM9EkAzEYoBcCllClTRrVq1bJblpqaqsjISPXt2zfbeC8vL9WpU0eS9Ntvv6l169bZxvz2229q0KBB4RQMAABgEvokAGYjlALg8po3b64DBw5ka8KydOnSRRUqVNCbb76Zrdn66quvdPDgQU2fPt2MUgEAAExFnwSgMBFKAXB5kydP1r333qtq1arp/vvvl5ubm/bs2aN9+/bppZdeUpkyZfTuu+9qwIABGjFihEaNGiVfX1+tX79eEyZM0P33369+/fo5+2UAAAA4HH0SgMLE0/cAuLywsDCtXLlSa9as0R133KG77rpLs2bNUvXq1W1j7r//fm3cuFHx8fFq166d6tatq1mzZumFF17Q4sWLZbFYnPgKAAAACgd9EoDCZDG4Ix0AAAAAAABMxpVSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdIRSAAAAAAAAMB2hFAAAAAAAAExHKAUAAAAAAADTEUoBAAAAAADAdP8HUbKcBdQhJtEAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAABKUAAAJOCAYAAABm7rQwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABZu0lEQVR4nO3debyXc/4//udpO22n00KbUk1lUNmXD2mhTJKIjyETqrHNR1G2IYZkS7ZJlsLMJzthLDEfRlLZqYixZa+Gkq0VR865fn/49f46WtTpdL3Pcr/fbu/bzfW6tuf7Ou/TeXq8ryUnSZIkAAAAACBFVbJdAAAAAACVj1AKAAAAgNQJpQAAAABInVAKAAAAgNQJpQAAAABInVAKAAAAgNQJpQAAAABInVAKAAAAgNQJpQAAAABInVCKSu3CCy+MnJycVPbVvXv36N69e2Z6+vTpkZOTEw888EAq+x80aFC0bt06lX2V1IoVK+L444+Ppk2bRk5OTgwfPjzbJZXIJ598Ejk5OXHrrbdmu5TUrP48T58+PTNWHj5zAKRDz1W26LmAskIoRYVx6623Rk5OTuZVs2bNaN68efTq1SvGjRsXy5cvL5X9fPbZZ3HhhRfGnDlzSmV7paks17YhLrvssrj11lvjf/7nf+KOO+6IY445Zp3Ltm7dOg466KA1xu+4446oWrVqHHDAAfH999/HV199FVdeeWV07do1ttxyy6hfv37813/9V0yaNGmd237rrbfi6KOPjq222ipyc3OjefPmMWDAgHjrrbdK5X2WRPfu3Yt9vmvUqBFt2rSJE088MRYsWJC1usqaQYMGFTtO63oNGjSoVPZ39913x9ixY0tlWwDlhZ6rbNe2IfRc67a65+rbt+8a81aHYFdddVUWKvvJL3vCdb0uvPDCUtnfjTfeKPRjs6qW7QKgtF100UXRpk2bWLVqVSxatCimT58ew4cPj2uuuSYmT54cO+ywQ2bZv/zlL3HOOeds1PY/++yzGDVqVLRu3Tp22mmnDV7vySef3Kj9lMT6arvllluiqKhos9ewKZ5++un4r//6rxg5cmSJ1r/rrrti0KBB0bNnz3j44YejZs2a8dRTT8V5550XBx54YPzlL3+JatWqxT/+8Y/o379/vP322zFq1Khi23jwwQfjqKOOioYNG8Zxxx0Xbdq0iU8++ST+/ve/xwMPPBD33ntvHHrooeuto1WrVvHdd99F9erVS/Q+1qVFixYxevToiIj44Ycf4u23344JEybEv/71r3jnnXeidu3apbq/TZWNz9xJJ50UPXv2zEx//PHHccEFF8SJJ54YXbp0yYy3bdu2VPZ39913x5tvvlluv2EG2BR6Lj1XRe25IiIee+yxmD17duy6666lvu1Ncd5558Xxxx+fmZ45c2aMGzcuzj333Nhuu+0y4z///dsUN954Y2yxxRal9oUe/JJQigqnd+/esdtuu2WmR4wYEU8//XQcdNBBcfDBB8c777wTtWrVioiIatWqRbVqm/fX4Ntvv43atWtHjRo1Nut+fs3m+GNd2hYvXhzbb799ida99957Y+DAgbHffvvFI488EjVr1oyIiA4dOsT7778frVq1yix78sknR8+ePWPMmDHx5z//OerUqRMRER9++GEcc8wx8Zvf/CaeeeaZ2HLLLTPrDBs2LLp06RLHHHNMvPHGG/Gb3/xmnbWs/ta4tOXn58fRRx9dbKxNmzYxdOjQeP7552P//fcv9X1uimx85vbaa6/Ya6+9MtOzZs2KCy64IPbaa681jh0Am0bPtXZ6rvLfc2299daxfPnyGDVqVEyePLnUt78pftnv1axZM8aNGxf7779/sctWobxw+R6Vwn777Rfnn39+zJs3L+68887M+NrubzBlypTYZ599on79+lG3bt347W9/G+eee25E/HRPgt133z0iIgYPHpw5PXb1Ka3du3ePjh07xuzZs6Nr165Ru3btzLq/vL/BaoWFhXHuuedG06ZNo06dOnHwwQevcTlW69at1/rtxM+3+Wu1re3+BitXrowzzjgjWrZsGbm5ufHb3/42rrrqqkiSpNhyOTk5MXTo0Hj44YejY8eOkZubGx06dIgnnnhi7Qf8FxYvXhzHHXdcNGnSJGrWrBk77rhj3HbbbZn5q+/18PHHH8c///nPTO2ffPLJBm3/vvvui6OPPjq6d+8ekydPLtactGnTplhztPr99OvXLwoKCuKjjz7KjF955ZXx7bffxs0331ysOYqI2GKLLeKmm26KlStXxhVXXLHeetZ2f4NBgwZF3bp149NPP41+/fpF3bp1Y8stt4wzzzwzCgsLN+h9rk3Tpk0jIoo1+vPmzYuTTz45fvvb30atWrWiUaNG8fvf/36N47lq1aoYNWpUtG/fPmrWrBmNGjWKffbZJ6ZMmVJsuXfffTcOP/zwaNiwYdSsWTN22223DWrQfvmZ+/kp7zfffHO0bds2cnNzY/fdd4+ZM2eusX5J97shXn755TjggAMiPz8/ateuHd26dYvnn3++2DLLly+P4cOHR+vWrSM3NzcaN24c+++/f7z66qsR8dPv3z//+c+YN29e5jNb1u8hArC56bn0XL98P+Wx58rLy4vTTjstHn300czf/fVZsmRJDB8+PPPzbdeuXYwZM6bYGXO77LJLHHbYYcXW69SpU+Tk5MQbb7yRGZs0aVLk5OTEO++8s0G1rsvjjz8eXbp0iTp16kReXl706dNnjcsiFy1aFIMHD44WLVpEbm5uNGvWLA455JDM56F169bx1ltvxYwZMzKfFcEXpc2ZUlQaxxxzTJx77rnx5JNPxgknnLDWZd5666046KCDYocddoiLLroocnNz44MPPsj8z+p2220XF1100RqXA+29996ZbXz11VfRu3fv6N+/fxx99NHRpEmT9dZ16aWXRk5OTpx99tmxePHiGDt2bPTs2TPmzJmT+XZxQ2xIbT+XJEkcfPDBMW3atDjuuONip512in/9619x1llnxaeffhp//etfiy3/3HPPxYMPPhgnn3xy5OXlxbhx4+K///u/Y/78+dGoUaN11vXdd99F9+7d44MPPoihQ4dGmzZt4v77749BgwbFkiVLYtiwYbHddtvFHXfcEaeddlq0aNEizjjjjIiINZqUtfnHP/4RAwYMiK5du8ajjz66wcds0aJFEfFT47Pao48+Gq1bty52mdfPde3aNVq3bh3//Oc/N2gfv1RYWBi9evWKPffcM6666qp46qmn4uqrr462bdvG//zP/2zQ+l9++WVE/BQovfPOOzFy5Mho165ddO7cObPczJkz44UXXoj+/ftHixYt4pNPPonx48dH9+7d4+23385c5nfhhRfG6NGj4/jjj4899tgjli1bFrNmzYpXX3018y3cW2+9FZ07d46tttoqzjnnnKhTp07cd9990a9fv/jHP/7xq6fVr83dd98dy5cvj5NOOilycnLiiiuuiMMOOyw++uijzLfLm2O/qz399NPRu3fv2HXXXWPkyJFRpUqVmDhxYuy3337x7LPPxh577BEREX/605/igQceiKFDh8b2228fX331VTz33HPxzjvvxC677BLnnXdeLF26NP7zn/9kfl/q1q1b4roAKgo9V3F6rvLXc0X8dMbWX//617jwwgvX+6XYt99+G926dYtPP/00TjrppNh6663jhRdeiBEjRsTChQsz957s0qVL3HPPPZn1vv7663jrrbeiSpUq8eyzz2Yut3v22Wdjyy23LHYp3sa64447YuDAgdGrV68YM2ZMfPvttzF+/PjYZ5994rXXXsuEpv/93/8db731VpxyyinRunXrWLx4cUyZMiXmz58frVu3jrFjx8Ypp5wSdevWjfPOOy8i4ld/z2CjJVBBTJw4MYmIZObMmetcJj8/P9l5550z0yNHjkx+/mvw17/+NYmI5IsvvljnNmbOnJlERDJx4sQ15nXr1i2JiGTChAlrndetW7fM9LRp05KISLbaaqtk2bJlmfH77rsviYjk2muvzYy1atUqGThw4K9uc321DRw4MGnVqlVm+uGHH04iIrnkkkuKLXf44YcnOTk5yQcffJAZi4ikRo0axcZef/31JCKS6667bo19/dzYsWOTiEjuvPPOzNgPP/yQ7LXXXkndunWLvfdWrVolffr0We/2fr5s8+bNk2rVqiXdu3dPVq5cuUHrJUmSfPXVV0njxo2TLl26ZMaWLFmSRERyyCGHrHfdgw8+OImIYnX/0scff7zGz2HgwIFJRCQXXXRRsWV33nnnZNddd/3Vmld/tn752m677ZKPPvqo2LLffvvtGuu/+OKLSUQkt99+e2Zsxx13/NXj3aNHj6RTp07J999/nxkrKipK9t5776R9+/aZsdWf52nTphV7zz//zK0+Lo0aNUq+/vrrzPgjjzySRETy6KOPbvR+f80vfyeKioqS9u3bJ7169UqKiooyy3377bdJmzZtkv333z8zlp+fnwwZMmS92+/Tp0+x9whQGei59Fwbqrz2XB06dEiSJElGjRqVREQye/bsYvu78sorM8tffPHFSZ06dZL33nuv2HbOOeecpGrVqsn8+fOTJEmS+++/P4mI5O23306SJEkmT56c5ObmJgcffHBy5JFHZtbbYYcdkkMPPfRX61xt9XZX92DLly9P6tevn5xwwgnFllu0aFGSn5+fGf/mm2/WeC9r06FDh2KffShtLt+jUqlbt+56nwhTv379iIh45JFHSnyDytzc3Bg8ePAGL3/sscdGXl5eZvrwww+PZs2axf/93/+VaP8b6v/+7/+iatWqceqppxYbP+OMMyJJknj88ceLjffs2bPYzaF32GGHqFevXrFTsde1n6ZNm8ZRRx2VGatevXqceuqpsWLFipgxY0aJ38PXX38dP/74Y7Ro0WKDv60rKiqKAQMGxJIlS+K6667LjK/+XPz8Z7E2q+cvW7asRDX/6U9/KjbdpUuXXz2Gq7Vu3TqmTJkSU6ZMiccffzzGjh0bS5cujd69e8cXX3yRWe7nx2LVqlXx1VdfRbt27aJ+/frFTkGvX79+vPXWW/H++++vdX9ff/11PP3003HEEUfE8uXL48svv4wvv/wyvvrqq+jVq1e8//778emnn27M24+IiCOPPDIaNGiQmV79Lenq47C59hsRMWfOnHj//ffjD3/4Q3z11VeZba9cuTJ69OgRzzzzTOZ3v379+vHyyy/HZ599VqJ9AVRmeq7/R89V/nqu1YYNGxYNGjRY4ybtP3f//fdHly5dokGDBpm+4ssvv4yePXtGYWFhPPPMM5n9R0Rm+tlnn43dd9899t9//3j22Wcj4qfLAN988811nkG2IaZMmRJLliyJo446qlg9VatWjT333DOmTZsWET/1izVq1Ijp06fHN998U+L9waYSSlGprFixYr1/AI888sjo3LlzHH/88dGkSZPo379/3HfffRvVLG211VYbdYPN9u3bF5vOycmJdu3abfC1/SU1b968aN68+RrHY/WpwvPmzSs2vvXWW6+xjQYNGvzqH7F58+ZF+/bto0qV4v/crGs/G6NHjx7xP//zP3HnnXdu8NPPTjnllHjiiSfib3/7W+y4446Z8dXH4dceY72hjdTa1KxZc43T4zfkGK5Wp06d6NmzZ/Ts2TMOOOCAGDZsWEyePDnmzp0bl19+eWa57777Li644ILMfQ222GKL2HLLLWPJkiWxdOnSzHIXXXRRLFmyJLbZZpvo1KlTnHXWWcXuafDBBx9EkiRx/vnnx5ZbblnstfppPYsXL97o4/DLz9LqgGr1cdhc+42ITAA3cODANbb9t7/9LQoKCjLH6Iorrog333wzWrZsGXvssUdceOGFG93MAlRWeq7/R89V/nqu1fLz82P48OExefLkeO2119a6zPvvvx9PPPHEGn3F6qcBr+5ZmjRpEu3bt88EUM8++2x06dIlunbtGp999ll89NFH8fzzz0dRUdEmhVKre5399ttvjZqefPLJTD25ubkxZsyYePzxx6NJkybRtWvXuOKKKzKXW0Ja3FOKSuM///lPLF26NNq1a7fOZWrVqhXPPPNMTJs2Lf75z3/GE088EZMmTYr99tsvnnzyyahateqv7mdj7kmwoX55Y9DVCgsLN6im0rCu/SS/uEFn2q6//vr45ptvYty4cdGgQYO48MIL17nsqFGj4sYbb4zLL788jjnmmGLz8vPzo1mzZsVCmbV54403Yquttop69eptdK2b42e16667Rn5+fuZbt4ifmsCJEyfG8OHDY6+99or8/PzIycmJ/v37F2v2u3btGh9++GE88sgj8eSTT8bf/va3+Otf/xoTJkyI448/PrPsmWeeGb169Vrr/tf3+7Quv/ZZ2lz7/fm2r7zyynU+Xnz1faGOOOKI6NKlSzz00EPx5JNPxpVXXhljxoyJBx98MHr37l2i/QNUBnquTaPn+klZ6blW31tq1KhRmftD/VxRUVHsv//+8ec//3mt62+zzTaZ/95nn31i6tSp8d1338Xs2bPjggsuiI4dO0b9+vXj2WefjXfeeSfq1q0bO++8c4nrXd3r3HHHHZkH4vzczx+OM3z48Ojbt288/PDD8a9//SvOP//8GD16dDz99NObVANsDKEUlcYdd9wREbHO/8ldrUqVKtGjR4/o0aNHXHPNNXHZZZfFeeedF9OmTYuePXuus1kpqV9eOpUkSXzwwQeZmx1G/PTNzpIlS9ZYd968ecUek7sxtbVq1SqeeuqpWL58ebFvoN59993M/NLQqlWreOONN6KoqKjYN3eltZ8qVarE7bffHkuXLo1Ro0ZFw4YN1zg9PiLihhtuiAsvvDCGDx8eZ5999lq3ddBBB8Utt9wSzz33XOyzzz5rzH/22Wfjk08+iZNOOmmTai5thYWFsWLFisz0Aw88EAMHDoyrr746M/b999+v9TPUsGHDGDx4cAwePDhWrFgRXbt2jQsvvDCOP/74zGerevXqmW/70rA597v6coh69ept0LabNWsWJ598cpx88smxePHi2GWXXeLSSy/NhFKl/e8BQEWg5ypOz7Wm8tRzrT5b6sILL4yBAweuMb9t27axYsWKDeorunTpEhMnTox77703CgsLY++9944qVarEPvvskwml9t57700K1Vb3Oo0bN96gmtq2bRtnnHFGnHHGGfH+++/HTjvtFFdffXXm6Zl6HTY3l+9RKTz99NNx8cUXR5s2bWLAgAHrXO7rr79eY2z12RQFBQUR8dMlVBGx1oalJG6//fZipy8/8MADsXDhwmJnYrRt2zZeeuml+OGHHzJjjz322BqPMd6Y2g488MAoLCyM66+/vtj4X//618jJySm1M0EOPPDAWLRoUUyaNCkz9uOPP8Z1110XdevWjW7dum3yPqpXrx4PPPBAdO7cOYYPH55phlebNGlSnHrqqTFgwIC45ppr1rmds846K2rVqhUnnXRSfPXVV8Xmff311/GnP/0pateuHWedddYm11xapk2bFitWrCh2WnzVqlXX+Db1uuuuW+MxyL98j3Xr1o127dplPuuNGzeO7t27x0033RQLFy5cY98/v49Vadqc+911112jbdu2cdVVVxUL8n657cLCwmKXOq6uq3nz5pnjE/HT79wvlwOozPRca9Jzram89VzDhw+P+vXrx0UXXbTGvCOOOCJefPHF+Ne//rXGvCVLlsSPP/6YmV59Wd6YMWNihx12iPz8/Mz41KlTY9asWZt06V7ET2FwvXr14rLLLotVq1atMX91r/Ptt9/G999/X2xe27ZtIy8vb41ep7R+B2FtnClFhfP444/Hu+++Gz/++GN8/vnn8fTTT8eUKVOiVatWMXny5KhZs+Y6173ooovimWeeiT59+kSrVq1i8eLFceONN0aLFi0y3+K0bds26tevHxMmTIi8vLyoU6dO7LnnntGmTZsS1duwYcPYZ599YvDgwfH555/H2LFjo127dsUeoXz88cfHAw88EAcccEAcccQR8eGHH8add95Z7CaYG1tb3759Y999943zzjsvPvnkk9hxxx3jySefjEceeSSGDx++xrZL6sQTT4ybbropBg0aFLNnz47WrVvHAw88EM8//3yMHTu2RPcJWJvatWvHP//5z+jWrVv88Y9/jPz8/Dj44IPjlVdeiWOPPTYaNWoUPXr0iLvuuqvYenvvvXfmm8/27dvHbbfdFgMGDIhOnTrFcccdF23atIlPPvkk/v73v8eXX34Z99xzT6kdm421dOnSzLdWP/74Y8ydOzfGjx8ftWrVinPOOSez3EEHHRR33HFH5Ofnx/bbbx8vvvhiPPXUU2s8Rnr77beP7t27x6677hoNGzaMWbNmxQMPPBBDhw7NLHPDDTfEPvvsE506dYoTTjghfvOb38Tnn38eL774YvznP/+J119/fbO818213ypVqsTf/va36N27d3To0CEGDx4cW221VXz66acxbdq0qFevXjz66KOxfPnyaNGiRRx++OGx4447Rt26deOpp56KmTNnFjsDbdddd41JkybF6aefHrvvvnvUrVs3+vbtW1qHAaBM03PpuSpqz/VL+fn5MWzYsLXe8Pyss86KyZMnx0EHHRSDBg2KXXfdNVauXBn//ve/44EHHohPPvkktthii4j46fYDTZs2jblz58Ypp5yS2UbXrl0zZ5VtaihVr169GD9+fBxzzDGxyy67RP/+/WPLLbeM+fPnxz//+c/o3LlzXH/99fHee+9Fjx494ogjjojtt98+qlWrFg899FB8/vnn0b9//8z2dt111xg/fnxccskl0a5du2jcuHHst99+m1QjFJOtx/5BaVv9eOLVrxo1aiRNmzZN9t9//+Taa69d6+Nkf/l44qlTpyaHHHJI0rx586RGjRpJ8+bNk6OOOmqNR7w+8sgjyfbbb59Uq1at2GNof/4I2V9a1+OJ77nnnmTEiBFJ48aNk1q1aiV9+vRJ5s2bt8b6V199dbLVVlslubm5SefOnZNZs2atsc311fbLxxMnyU+PjD3ttNOS5s2bJ9WrV0/at2+fXHnllUlRUVGx5SIiGTJkyBo1reuxyb/0+eefJ4MHD0622GKLpEaNGkmnTp3W+gjljX088dqWXbRoUdKuXbukZs2aybRp09b4XPzytbY63njjjeSoo45KmjVrllSvXj1p2rRpctRRRyX//ve/N6i2dT2euE6dOmss+8vP4LqsfvT16ldOTk7SsGHD5OCDD848pni1b775JnO869atm/Tq1St599131/h5XXLJJckee+yR1K9fP6lVq1ay7bbbJpdeemnyww8/FNvehx9+mBx77LFJ06ZNk+rVqydbbbVVctBBByUPPPBAZpnVn+fVjyNe/Z5//plb22OUV4uIZOTIkRu931+zrkd2v/baa8lhhx2WNGrUKMnNzU1atWqVHHHEEcnUqVOTJEmSgoKC5Kyzzkp23HHHJC8vL6lTp06y4447JjfeeGOx7axYsSL5wx/+kNSvXz+JiDV+xwAqIj3X+mvTc5X/nmttn61vvvkmyc/PX2svs3z58mTEiBFJu3btkho1aiRbbLFFsvfeeydXXXXVGn3V73//+yQikkmTJmXGfvjhh6R27dpJjRo1ku++++5Xa/y5+++/f40eLEl++tz36tUryc/PT2rWrJm0bds2GTRoUDJr1qwkSZLkyy+/TIYMGZJsu+22SZ06dZL8/Pxkzz33TO67775i21m0aFHSp0+fJC8vL4mINX4PYFPlJEmW75gHAAAAQKXjnlIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqqmW7gM2tqKgoPvvss8jLy4ucnJxslwMAlHNJksTy5cujefPmUaVKxfh+T78EAJSmDe2XKnwo9dlnn0XLli2zXQYAUMEsWLAgWrRoke0ySoV+CQDYHH6tX6rwoVReXl5E/HQg6tWrl+VqAIDybtmyZdGyZctMj1ER6JcAgNK0of1ShQ+lVp+CXq9ePU0WAFBqKtJlbvolAGBz+LV+qWLcCAEAAACAckUoBQAAAEDqhFIAAAAApK7C31MKAH6usLAwVq1ale0yKMOqV68eVatWzXYZAFCp6NHKl9Lql4RSAFQKSZLEokWLYsmSJdkuhXKgfv360bRp0wp1M3MAKIv0aOVXafRLQikAKoXVzU7jxo2jdu3awgbWKkmS+Pbbb2Px4sUREdGsWbMsVwQAFZserfwpzX5JKAVAhVdYWJhpdho1apTtcijjatWqFRERixcvjsaNG7uUDwA2Ez1a+VVa/ZIbnQNQ4a2+P0Ht2rWzXAnlxerPintbAMDmo0cr30qjXxJKAVBpOB2cDeWzAgDp8Xe3fCqNn5tQCgAAAIDUCaUAgF/VunXrGDt2bGY6JycnHn744azVAwBA+edG5wBUan37pru/Rx/duOUHDRoUt912W2a6YcOGsfvuu8cVV1wRO+ywQylXt+EWLlwYDRo02Gzb7969e8yYMWOd87t16xbTp08v8bZ32mmnYiEbAFDGTE+5Seu+cU3a6h5t9OjRcc4552TGH3744Tj00EMjSZLSrnANt956awwePHi9y3z88cfRunXrEm17+PDhsWTJkpIVt4GcKQUAZdwBBxwQCxcujIULF8bUqVOjWrVqcdBBB2W1pqZNm0Zubu5m2/6DDz6Yec+vvPJKREQ89dRTmbEHH3xws+0bAGBD1KxZM8aMGRPffPNNVvZ/5JFHZnqjhQsXxl577RUnnHBCsbGWLVtmpbYNJZQCgDIuNzc3mjZtGk2bNo2ddtopzjnnnFiwYEF88cUXmWXOPvvs2GabbaJ27drxm9/8Js4///xiT0J5/fXXY9999428vLyoV69e7LrrrjFr1qzM/Oeeey66dOkStWrVipYtW8app54aK1euXGdNP79875NPPomcnJx48MEHY999943atWvHjjvuGC+++GKxdTZmHw0bNsy85y233DIiIho1apQZe/vtt9e7rRtvvDHat28fNWvWjCZNmsThhx8eET99qzljxoy49tprIycnJ3JycuKTTz7ZsB8EAMDP9OzZM5o2bRqjR49e73Lr64Guv/766NixY2bZhx9+OHJycmLChAnF9vOXv/xlje3WqlUr0xs1bdo0atSoEbVr185M16xZM0466aTYcssto169erHffvvF66+/nll/Xf3h9OnTY/DgwbF06dJMv3ThhRdu4tFaO6EUAJQjK1asiDvvvDPatWsXjRo1yozn5eXFrbfeGm+//XZce+21ccstt8Rf//rXzPwBAwZEixYtYubMmTF79uw455xzonr16hER8eGHH8YBBxwQ//3f/x1vvPFGTJo0KZ577rkYOnToRtV23nnnxZlnnhlz5syJbbbZJo466qj48ccfS3UfG7KtWbNmxamnnhoXXXRRzJ07N5544ono2rVrRERce+21a3yLWNa/QQQAyqaqVavGZZddFtddd1385z//Wesyv9a3dOvWLd5+++3Ml40zZsyILbbYInObglWrVsWLL74Y3bt33+j6fv/738fixYvj8ccfj9mzZ8cuu+wSPXr0iK+//joi1t0f7r333jF27NioV69epl8688wzN/4AbQD3lAKAMu6xxx6LunXrRkTEypUro1mzZvHYY49FlSr/77uln3971rp16zjzzDPj3nvvjT//+c8RETF//vw466yzYtttt42IiPbt22eWHz16dAwYMCCGDx+emTdu3Ljo1q1bjB8/PmrWrLlBdZ555pnRp0+fiIgYNWpUdOjQIT744IPYdtttS20fG1Lv/Pnzo06dOnHQQQdFXl5etGrVKnbeeeeIiMjPzy/2LSIAwKY49NBDY6eddoqRI0fG3//+9zXm/1rf0rFjx2jYsGHMmDEjDj/88Jg+fXqcccYZce2110ZExCuvvBKrVq2Kvffee6Pqeu655+KVV16JxYsXZ265cNVVV8XDDz8cDzzwQJx44onr7Q/z8/MjJydns/dLzpQCgDJu3333jTlz5sScOXPilVdeiV69ekXv3r1j3rx5mWUmTZoUnTt3jqZNm0bdunXjL3/5S8yfPz8z//TTT4/jjz8+evbsGZdffnl8+OGHmXmvv/563HrrrVG3bt3Mq1evXlFUVBQff/zxBtf58xuvN2vWLCIiFi9eXKr72JBt7b///tGqVav4zW9+E8ccc0zcdddd8e23327UPgAANtSYMWPitttui3feeWeNeb/Wt+Tk5ETXrl1j+vTpsWTJknj77bfj5JNPjoKCgnj33XdjxowZsfvuu0ft2rU3qqbXX389VqxYEY0aNSq2748//jjTB66vP0yLUAoAyrg6depEu3btol27drH77rvH3/72t1i5cmXccsstERHx4osvxoABA+LAAw+Mxx57LF577bU477zz4ocffshs48ILL4y33nor+vTpE08//XRsv/328dBDD0XET5cEnnTSSZnga86cOfH666/H+++/H23btt3gOldfDhjx0z2nIiKKiopKdR8bsq28vLx49dVX45577olmzZrFBRdcEDvuuONmf3oMAFA5de3aNXr16hUjRoxYY96G9EDdu3eP6dOnx7PPPhs777xz1KtXLxNUzZgxI7p167bRNa1YsSKaNWtWbL9z5syJuXPnxllnnRUR6+8P0+LyPQAoZ3JycqJKlSrx3XffRUTECy+8EK1atYrzzjsvs8zPz6JabZtttoltttkmTjvttDjqqKNi4sSJceihh8Yuu+wSb7/9drRr126z1Vya+9iQbVWrVi169uwZPXv2jJEjR0b9+vXj6aefjsMOOyxq1KgRhYWFm1wHAMBql19+eey0007x29/+ttj4hvQt3bp1i+HDh8f999+fuXdU9+7d46mnnornn38+zjjjjI2uZ5dddolFixZFtWrVonXr1utcbl39YVr9kjOlAKCMKygoiEWLFsWiRYvinXfeiVNOOSVWrFgRffv2jYifrv+fP39+3HvvvfHhhx/GuHHjin3L9d1338XQoUNj+vTpMW/evHj++edj5syZsd1220XET0/ue+GFF2Lo0KExZ86ceP/99+ORRx4p0U3I16U09/Fr23rsscdi3LhxMWfOnJg3b17cfvvtUVRUlGkSW7duHS+//HJ88skn8eWXX2bO5gIAKKlOnTrFgAEDYty4ccXGN6QH2mGHHaJBgwZx9913FwulHn744SgoKIjOnTtvdD09e/aMvfbaK/r16xdPPvlkfPLJJ/HCCy/EeeedF7NmzfrV/rB169axYsWKmDp1anz55Zeb7VYIQikAKOOeeOKJaNasWTRr1iz23HPPmDlzZrFv0g4++OA47bTTYujQobHTTjvFCy+8EOeff35m/apVq8ZXX30Vxx57bGyzzTZxxBFHRO/evWPUqFER8VMjNGPGjHjvvfeiS5cusfPOO8cFF1wQzZs3L7X3UJr7+LVt1a9fPx588MHYb7/9YrvttosJEybEPffcEx06dIiIn27IXrVq1dh+++1jyy23LHbvLQCAkrrooovW+LJrQ3qgnJyc6NKlS+Tk5MQ+++yTWa9evXqx2267RZ06dTa6lpycnPi///u/6Nq1awwePDi22Wab6N+/f8ybNy+aNGnyq/3h3nvvHX/605/iyCOPjC233DKuuOKKTTgy66kzSZJks2y5jFi2bFnk5+fH0qVLo169eptlH///F9Ul9uijpVMHAGv3/fffx8cffxxt2rTZqKe8UXmt7zOTRm+RtlTe0/RNbJgiIrprmgAqEj1a+VYa/ZIzpQAAAABInVAKAAAAgNQJpQAAAABInVAKAAAAgNQJpQAAAABInVAKgErjl4/ohXXxWQGA9Pi7Wz6Vxs+tWinUAQBlWo0aNaJKlSrx2WefxZZbbhk1atSInJycbJdFGZQkSfzwww/xxRdfRJUqVaJGjRrZLgkAKiw9WvlUmv2SUAqACq9KlSrRpk2bWLhwYXz22WfZLodyoHbt2rH11ltHlSpOKgeAzUWPVr6VRr8klAKgUqhRo0ZsvfXW8eOPP0ZhYWG2y6EMq1q1alSrVs03tQCQAj1a+VRa/ZJQCoBKIycnJ6pXrx7Vq1fPdikAAPz/9GiVl3PSAQAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1AmlAAAAAEidUAoAAACA1GU1lHrmmWeib9++0bx588jJyYmHH344M2/VqlVx9tlnR6dOnaJOnTrRvHnzOPbYY+Ozzz7LXsEAAAAAlIqshlIrV66MHXfcMW644YY15n377bfx6quvxvnnnx+vvvpqPPjggzF37tw4+OCDs1ApAAAAAKWpWjZ33rt37+jdu/da5+Xn58eUKVOKjV1//fWxxx57xPz582PrrbdOo0QAAAAANoOshlIba+nSpZGTkxP169df5zIFBQVRUFCQmV62bFkKlQEAAACwMcrNjc6///77OPvss+Ooo46KevXqrXO50aNHR35+fubVsmXLFKsEAAAAYEOUi1Bq1apVccQRR0SSJDF+/Pj1LjtixIhYunRp5rVgwYKUqgQAAABgQ5X5y/dWB1Lz5s2Lp59+er1nSUVE5ObmRm5ubkrVAQAAAFASZTqUWh1Ivf/++zFt2rRo1KhRtksCAAAAoBRkNZRasWJFfPDBB5npjz/+OObMmRMNGzaMZs2axeGHHx6vvvpqPPbYY1FYWBiLFi2KiIiGDRtGjRo1slU2AAAAAJsoq6HUrFmzYt99981Mn3766RERMXDgwLjwwgtj8uTJERGx0047FVtv2rRp0b1797TKBAAAAKCUZTWU6t69eyRJss7565sHAAAAQPlVLp6+BwAAAEDFIpQCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCACjHCgsL4/zzz482bdpErVq1om3btnHxxRd7ijEAUOZVy3YBAACU3JgxY2L8+PFx2223RYcOHWLWrFkxePDgyM/Pj1NPPTXb5QEArJNQCgCgHHvhhRfikEMOiT59+kREROvWreOee+6JV155JcuVAQCsn8v3AADKsb333jumTp0a7733XkREvP766/Hcc89F7969s1wZAMD6OVMKAKAcO+ecc2LZsmWx7bbbRtWqVaOwsDAuvfTSGDBgwDrXKSgoiIKCgsz0smXL0igVAKAYZ0oBAJRj9913X9x1111x9913x6uvvhq33XZbXHXVVXHbbbetc53Ro0dHfn5+5tWyZcsUKwYA+IlQCgCgHDvrrLPinHPOif79+0enTp3imGOOidNOOy1Gjx69znVGjBgRS5cuzbwWLFiQYsUAAD9x+R4AQDn27bffRpUqxb9nrFq1ahQVFa1zndzc3MjNzd3cpQEArJdQCgCgHOvbt29ceumlsfXWW0eHDh3itddei2uuuSb++Mc/Zrs0AID1EkoBAJRj1113XZx//vlx8sknx+LFi6N58+Zx0kknxQUXXJDt0gAA1ksoBQBQjuXl5cXYsWNj7Nix2S4FAGCjuNE5AAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKmrls2dP/PMM3HllVfG7NmzY+HChfHQQw9Fv379MvOTJImRI0fGLbfcEkuWLInOnTvH+PHjo3379tkrGgCA7Jjed9PW7/5o6dQBAJSKrJ4ptXLlythxxx3jhhtuWOv8K664IsaNGxcTJkyIl19+OerUqRO9evWK77//PuVKAQAAAChNWT1Tqnfv3tG7d++1zkuSJMaOHRt/+ctf4pBDDomIiNtvvz2aNGkSDz/8cPTv3z/NUgEAAAAoRWX2nlIff/xxLFq0KHr27JkZy8/Pjz333DNefPHFda5XUFAQy5YtK/YCAAAAoGwps6HUokWLIiKiSZMmxcabNGmSmbc2o0ePjvz8/MyrZcuWm7VOAAAAADZemQ2lSmrEiBGxdOnSzGvBggXZLgkAAACAXyizoVTTpk0jIuLzzz8vNv75559n5q1Nbm5u1KtXr9gLAAAAgLKlzIZSbdq0iaZNm8bUqVMzY8uWLYuXX3459tprryxWBgAAAMCmyurT91asWBEffPBBZvrjjz+OOXPmRMOGDWPrrbeO4cOHxyWXXBLt27ePNm3axPnnnx/NmzePfv36Za9oAAAAADZZVkOpWbNmxb777puZPv300yMiYuDAgXHrrbfGn//851i5cmWceOKJsWTJkthnn33iiSeeiJo1a2arZAAAAABKQVZDqe7du0eSJOucn5OTExdddFFcdNFFKVYFAAAAwOZWZu8pBQAAAEDFJZQCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQAAAABSJ5QCAAAAIHVCKQCAcu7TTz+No48+Oho1ahS1atWKTp06xaxZs7JdFgDAelXLdgEAAJTcN998E507d4599903Hn/88dhyyy3j/fffjwYNGmS7NACA9RJKAQCUY2PGjImWLVvGxIkTM2Nt2rTJYkUAABvG5XsAAOXY5MmTY7fddovf//730bhx49h5553jlltuWe86BQUFsWzZsmIvAIC0OVMKAKAc++ijj2L8+PFx+umnx7nnnhszZ86MU089NWrUqBEDBw5c6zqjR4+OUaNGpVxpGTC976at3/3R0qmjpDa1/ojsvwcA+BlnSgEAlGNFRUWxyy67xGWXXRY777xznHjiiXHCCSfEhAkT1rnOiBEjYunSpZnXggULUqwYAOAnQikAgHKsWbNmsf322xcb22677WL+/PnrXCc3Nzfq1atX7AUAkDahFABAOda5c+eYO3dusbH33nsvWrVqlaWKAAA2jFAKAKAcO+200+Kll16Kyy67LD744IO4++674+abb44hQ4ZkuzQAgPUSSgEAlGO77757PPTQQ3HPPfdEx44d4+KLL46xY8fGgAEDsl0aAMB6efoeAEA5d9BBB8VBBx2U7TIAADaKM6UAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUlelQqrCwMM4///xo06ZN1KpVK9q2bRsXX3xxJEmS7dIAAAAA2ATVsl3A+owZMybGjx8ft912W3To0CFmzZoVgwcPjvz8/Dj11FOzXR4AAAAAJVSmQ6kXXnghDjnkkOjTp09ERLRu3TruueeeeOWVV7JcGQAAAACbokxfvrf33nvH1KlT47333ouIiNdffz2ee+656N279zrXKSgoiGXLlhV7AQAAAFC2lOkzpc4555xYtmxZbLvttlG1atUoLCyMSy+9NAYMGLDOdUaPHh2jRo1KscpN17fvpm/j0Uc3fRsAAAAAaSnTZ0rdd999cdddd8Xdd98dr776atx2221x1VVXxW233bbOdUaMGBFLly7NvBYsWJBixQAAAABsiDJ9ptRZZ50V55xzTvTv3z8iIjp16hTz5s2L0aNHx8CBA9e6Tm5ubuTm5qZZJgAAAAAbqUyfKfXtt99GlSrFS6xatWoUFRVlqSIAAAAASkOZPlOqb9++cemll8bWW28dHTp0iNdeey2uueaa+OMf/5jt0gAAAADYBGU6lLruuuvi/PPPj5NPPjkWL14czZs3j5NOOikuuOCCbJcGAAAAwCYo06FUXl5ejB07NsaOHZvtUgAAAAAoRWX6nlIAAAAAVExCKQAAAABSJ5QCAAAAIHUlCqU++uij0q4DAKDS0VMBAJVZiUKpdu3axb777ht33nlnfP/996VdEwBApaCnAgAqsxKFUq+++mrssMMOcfrpp0fTpk3jpJNOildeeaW0awMAqND0VABAZVaiUGqnnXaKa6+9Nj777LP43//931i4cGHss88+0bFjx7jmmmviiy++KO06AQAqHD0VAFCZbdKNzqtVqxaHHXZY3H///TFmzJj44IMP4swzz4yWLVvGscceGwsXLiytOgEAKiw9FQBQGW1SKDVr1qw4+eSTo1mzZnHNNdfEmWeeGR9++GFMmTIlPvvsszjkkENKq04AgApLTwUAVEbVSrLSNddcExMnToy5c+fGgQceGLfffnsceOCBUaXKTxlXmzZt4tZbb43WrVuXZq0AABWKngoAqMxKFEqNHz8+/vjHP8agQYOiWbNma12mcePG8fe//32TigMAqMj0VABAZVaiUOr999//1WVq1KgRAwcOLMnmAQAqBT0VAFCZleieUhMnToz7779/jfH7778/brvttk0uCgCgMtBTAQCVWYlCqdGjR8cWW2yxxnjjxo3jsssu2+SiAAAqAz0VAFCZlSiUmj9/frRp02aN8VatWsX8+fM3uSgAgMpATwUAVGYlCqUaN24cb7zxxhrjr7/+ejRq1GiTiwIAqAz0VABAZVaiUOqoo46KU089NaZNmxaFhYVRWFgYTz/9dAwbNiz69+9f2jUCAFRIeioAoDIr0dP3Lr744vjkk0+iR48eUa3aT5soKiqKY4891v0PAAA2kJ4KAKjMShRK1ahRIyZNmhQXX3xxvP7661GrVq3o1KlTtGrVqrTrAwCosPRUAEBlVqJQarVtttkmttlmm9KqBQCgUtJTAQCVUYlCqcLCwrj11ltj6tSpsXjx4igqKio2/+mnny6V4gAAKjI9FQBQmZUolBo2bFjceuut0adPn+jYsWPk5OSUdl0AABWengoAqMxKFErde++9cd9998WBBx5Y2vUAAFQaeipI2fS+m76N7o9u+jYAiIiIKiVZqUaNGtGuXbvSrgUAoFLRUwEAlVmJQqkzzjgjrr322kiSpLTrAQCoNPRUAEBlVqLL95577rmYNm1aPP7449GhQ4eoXr16sfkPPvhgqRQHAFCR6akAgMqsRKFU/fr149BDDy3tWgAAKhU9FQBQmZUolJo4cWJp1wEAUOnoqQCAyqxE95SKiPjxxx/jqaeeiptuuimWL18eERGfffZZrFixotSKAwCo6PRUAEBlVaIzpebNmxcHHHBAzJ8/PwoKCmL//fePvLy8GDNmTBQUFMSECRNKu04AgApHTwUAVGYlCqWGDRsWu+22W7z++uvRqFGjzPihhx4aJ5xwQqkVB1Qufftu2vqPPlo6dQCkRU8FAFRmJQqlnn322XjhhReiRo0axcZbt24dn376aakUBgBQ0empAIDKrET3lCoqKorCwsI1xv/zn/9EXl7eJhcFAFAZ6KkAgMqsRKHU7373uxg7dmxmOicnJ1asWBEjR46MAw88sLRqAwCo0PRUAEBlVqLL966++uro1atXbL/99vH999/HH/7wh3j//fdjiy22iHvuuae0awQAqJD0VABAZVaiUKpFixbx+uuvx7333htvvPFGrFixIo477rgYMGBA1KpVq7RrBACokPRUAEBlVqJQKiKiWrVqcfTRR5dmLQAAlY6eCgCorEoUSt1+++3rnX/ssceWqBgAgMpETwUAVGYlCqWGDRtWbHrVqlXx7bffRo0aNaJ27doaKACADaCnAgAqsxI9fe+bb74p9lqxYkXMnTs39tlnHzflBADYQHoqAKAyK1EotTbt27ePyy+/fI1v/AAA2HB6KgCgsii1UCripxt1fvbZZ6W5SQCASkdPBQBUBiW6p9TkyZOLTSdJEgsXLozrr78+OnfuXCqFAQBUdHoqAKAyK1Eo1a9fv2LTOTk5seWWW8Z+++0XV199dWnUBQBQ4empAIDKrEShVFFRUWnXAQBQ6eipAIDKrFTvKQUAAAAAG6JEZ0qdfvrpG7zsNddcU5JdAABUeHoqAKAyK1Eo9dprr8Vrr70Wq1atit/+9rcREfHee+9F1apVY5dddsksl5OTUzpVAgBUQHoqAKAyK1Eo1bdv38jLy4vbbrstGjRoEBER33zzTQwePDi6dOkSZ5xxRqkWCQBQEempAIDKrET3lLr66qtj9OjRmeYpIqJBgwZxySWXeFIMAMAG0lMBAJVZiUKpZcuWxRdffLHG+BdffBHLly/f5KIAACoDPRUAUJmVKJQ69NBDY/DgwfHggw/Gf/7zn/jPf/4T//jHP+K4446Lww47rLRrBACokPRUAEBlVqJ7Sk2YMCHOPPPM+MMf/hCrVq36aUPVqsVxxx0XV155ZakWCABQUempAIDKrEShVO3atePGG2+MK6+8Mj788MOIiGjbtm3UqVOnVIsDAKjI9FQAQGVWosv3Vlu4cGEsXLgw2rdvH3Xq1IkkSUqrLgCASkNPBQBURiUKpb766qvo0aNHbLPNNnHggQfGwoULIyLiuOOO8+hiAIANpKcCACqzEoVSp512WlSvXj3mz58ftWvXzowfeeSR8cQTT5RacQAAFZmeCgCozEp0T6knn3wy/vWvf0WLFi2Kjbdv3z7mzZtXKoUBAFR0eioAoDIr0ZlSK1euLPZt3mpff/115ObmbnJRAACVgZ4KAKjMShRKdenSJW6//fbMdE5OThQVFcUVV1wR++67b6kVBwBQkempAIDKrESX711xxRXRo0ePmDVrVvzwww/x5z//Od566634+uuv4/nnny/tGgEAKiQ9FQBQmZXoTKmOHTvGe++9F/vss08ccsghsXLlyjjssMPitddei7Zt25Z2jQAAFZKeCgCozDb6TKlVq1bFAQccEBMmTIjzzjtvc9QEAFDh6akAgMpuo8+Uql69erzxxhubo5a1+vTTT+Poo4+ORo0aRa1ataJTp04xa9as1PYPALA5pN1TAQCUNSW6fO/oo4+Ov//976Vdyxq++eab6Ny5c1SvXj0ef/zxePvtt+Pqq6+OBg0abPZ9AwBsbmn1VAAAZVGJbnT+448/xv/+7//GU089FbvuumvUqVOn2PxrrrmmVIobM2ZMtGzZMiZOnJgZa9OmTalsGwAg29LqqQAAyqKNCqU++uijaN26dbz55puxyy67RETEe++9V2yZnJycUitu8uTJ0atXr/j9738fM2bMiK222ipOPvnkOOGEE9a5TkFBQRQUFGSmly1bVmr1AACUhrR7KgCAsmijQqn27dvHwoULY9q0aRERceSRR8a4ceOiSZMmm6W4jz76KMaPHx+nn356nHvuuTFz5sw49dRTo0aNGjFw4MC1rjN69OgYNWrUZqmHdevbN7v7f/TR7O4fADZG2j0VAEBZtFH3lEqSpNj0448/HitXrizVgn6uqKgodtlll7jsssti5513jhNPPDFOOOGEmDBhwjrXGTFiRCxdujTzWrBgwWarDwCgJNLuqQAAyqIS3eh8tV82VKWtWbNmsf322xcb22677WL+/PnrXCc3Nzfq1atX7AUAUJZt7p4KAKAs2qhQKicnZ437G2zO+x107tw55s6dW2zsvffei1atWm22fQIAbG5p91QAAGXRRt1TKkmSGDRoUOTm5kZExPfffx9/+tOf1nhSzIMPPlgqxZ122mmx9957x2WXXRZHHHFEvPLKK3HzzTfHzTffXCrbBwDIhs3ZU11++eUxYsSIGDZsWIwdO7Y0ygUA2Cw2KpT65c3Fjz766FIt5pd23333eOihh2LEiBFx0UUXRZs2bWLs2LExYMCAzbpfAIDNaXP1VDNnzoybbropdthhh1LZHgDA5rRRodTEiRM3Vx3rdNBBB8VBBx2U+n4BADaXzdFTrVixIgYMGBC33HJLXHLJJaW+fQCA0rZJNzoHAKBsGDJkSPTp0yd69uz5q8sWFBTEsmXLir0AANK2UWdKAQBQ9tx7773x6quvxsyZMzdo+dGjR8eoUaM2c1UV0PS+2a5g01WE95Btm3oMuz9avvcPUIqcKQUAUI4tWLAghg0bFnfddVfUrFlzg9YZMWJELF26NPNasGDBZq4SAGBNzpQCACjHZs+eHYsXL45ddtklM1ZYWBjPPPNMXH/99VFQUBBVq1Yttk5ubm7myX8AANkilAIAKMd69OgR//73v4uNDR48OLbddts4++yz1wikAADKCqEUAEA5lpeXFx07diw2VqdOnWjUqNEa4wAAZYl7SgEAAACQOmdKAQBUMNOnT892CQAAv8qZUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqEUgAAAACkTigFAAAAQOqqZbsASkffvpu2/qOPlk4dVG6b+jnM9v79HgAAAKTHmVIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqhFIAAAAApE4oBQAAAEDqqmW7AAAAgEpjet9sVwBQZjhTCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASF25CqUuv/zyyMnJieHDh2e7FAAAAAA2QbkJpWbOnBk33XRT7LDDDtkuBQAAAIBNVC5CqRUrVsSAAQPilltuiQYNGmS7HAAAAAA2UbkIpYYMGRJ9+vSJnj17ZrsUAAAAAEpBtWwX8GvuvffeePXVV2PmzJkbtHxBQUEUFBRkppctW7a5SgMAAACghMp0KLVgwYIYNmxYTJkyJWrWrLlB64wePTpGjRq1mSujrOnbN9sVRDz66Katv6nvYVP3DwAAAGkq05fvzZ49OxYvXhy77LJLVKtWLapVqxYzZsyIcePGRbVq1aKwsHCNdUaMGBFLly7NvBYsWJCFygEAAABYnzJ9plSPHj3i3//+d7GxwYMHx7bbbhtnn312VK1adY11cnNzIzc3N60SAQAAACiBMh1K5eXlRceOHYuN1alTJxo1arTGOAAAAADlR5m+fA8AAACAiqlMnym1NtOnT892CQAAAABsImdKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQCUc6NHj47dd9898vLyonHjxtGvX7+YO3dutssCAFivatkuACg7+vbNdgUAlMSMGTNiyJAhsfvuu8ePP/4Y5557bvzud7+Lt99+O+rUqZPt8gAA1kooBQBQzj3xxBPFpm+99dZo3LhxzJ49O7p27ZqlqgAA1s/lewAAFczSpUsjIqJhw4ZZrgQAYN2cKQUAUIEUFRXF8OHDo3PnztGxY8e1LlNQUBAFBQWZ6WXLlqVVHgBAhjOlAAAqkCFDhsSbb74Z99577zqXGT16dOTn52deLVu2TLFCAICfCKUAACqIoUOHxmOPPRbTpk2LFi1arHO5ESNGxNKlSzOvBQsWpFglAMBPXL4HAFDOJUkSp5xySjz00EMxffr0aNOmzXqXz83Njdzc3JSqAwBYO6EUAEA5N2TIkLj77rvjkUceiby8vFi0aFFEROTn50etWrWyXB0AwNq5fA8AoJwbP358LF26NLp37x7NmjXLvCZNmpTt0gAA1smZUgAA5VySJNkuAQBgozlTCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASJ1QCgAAAIDUCaUAAAAASF2ZDqVGjx4du+++e+Tl5UXjxo2jX79+MXfu3GyXBQAAAMAmKtOh1IwZM2LIkCHx0ksvxZQpU2LVqlXxu9/9LlauXJnt0gAAAADYBNWyXcD6PPHEE8Wmb7311mjcuHHMnj07unbtmqWqAAAAANhUZfpMqV9aunRpREQ0bNgwy5UAAAAAsCnK9JlSP1dUVBTDhw+Pzp07R8eOHde5XEFBQRQUFGSmly1blkZ5AAAAAGyEchNKDRkyJN5888147rnn1rvc6NGjY9SoUSlVVXH07ZvtCthUfoYAAACUJ+Xi8r2hQ4fGY489FtOmTYsWLVqsd9kRI0bE0qVLM68FCxakVCUAAAAAG6pMnymVJEmccsop8dBDD8X06dOjTZs2v7pObm5u5ObmplAdAAAAACVVpkOpIUOGxN133x2PPPJI5OXlxaJFiyIiIj8/P2rVqpXl6gAAAAAoqTJ9+d748eNj6dKl0b1792jWrFnmNWnSpGyXBgAAAMAmKNNnSiVJku0SAAAAANgMyvSZUgAAAABUTEIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFJXLdsFAAAAkJLpfTd9G90f3fRtAIQzpQAAAADIAqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKkTSgEAAACQOqEUAAAAAKmrlu0CoKLo2zfbFcCmfw4ffbR06mDTVPafY2n8e1rejwEAQGXgTCkAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUieUAgAAACB1QikAAAAAUlcuQqkbbrghWrduHTVr1ow999wzXnnllWyXBABQpuiXAIDypsyHUpMmTYrTTz89Ro4cGa+++mrsuOOO0atXr1i8eHG2SwMAKBP0SwBAeVTmQ6lrrrkmTjjhhBg8eHBsv/32MWHChKhdu3b87//+b7ZLAwAoE/RLAEB5VKZDqR9++CFmz54dPXv2zIxVqVIlevbsGS+++GIWKwMAKBv0SwBAeVUt2wWsz5dffhmFhYXRpEmTYuNNmjSJd999d63rFBQUREFBQWZ66dKlERGxbNmyzVbnqlWbbdNAijbjPxOp2dR/jyrCMagIKvvPsTT+rm7OY7C6p0iSZPPtZCOUl34pVmqYoMIo739ogM1uQ/ulMh1KlcTo0aNj1KhRa4y3bNkyC9UA5Ul+frYryD7HoGLwc0znGCxfvjzyy+nB1i8Bm6Z8/tsHpO/X+qUyHUptscUWUbVq1fj888+LjX/++efRtGnTta4zYsSIOP300zPTRUVF8fXXX0ejRo0iJyen1GtctmxZtGzZMhYsWBD16tUr9e2zdo57djju6XPMs8Nxz47yctyTJInly5dH8+bNs11KROiXWDfHPTsc9/Q55tnhuGdHeTnuG9ovlelQqkaNGrHrrrvG1KlTo1+/fhHxU9M0derUGDp06FrXyc3Njdzc3GJj9evX38yVRtSrV69MfyAqKsc9Oxz39Dnm2eG4Z0d5OO5l6Qwp/RK/xnHPDsc9fY55djju2VEejvuG9EtlOpSKiDj99NNj4MCBsdtuu8Uee+wRY8eOjZUrV8bgwYOzXRoAQJmgXwIAyqMyH0odeeSR8cUXX8QFF1wQixYtip122imeeOKJNW7mCQBQWemXAIDyqMyHUhERQ4cOXefp59mWm5sbI0eOXOMUeDYvxz07HPf0OebZ4bhnh+O+afRL/JLjnh2Oe/oc8+xw3LOjoh33nKSsPM8YAAAAgEqjSrYLAAAAAKDyEUoBAAAAkDqhFAAAAACpE0ptohtuuCFat24dNWvWjD333DNeeeWVbJdUoY0ePTp23333yMvLi8aNG0e/fv1i7ty52S6rUrn88ssjJycnhg8fnu1SKrxPP/00jj766GjUqFHUqlUrOnXqFLNmzcp2WRVaYWFhnH/++dGmTZuoVatWtG3bNi6++OJw+8XS9cwzz0Tfvn2jefPmkZOTEw8//HCx+UmSxAUXXBDNmjWLWrVqRc+ePeP999/PTrGUCv1SuvRL2adfSo9+KX36pXRUln5JKLUJJk2aFKeffnqMHDkyXn311dhxxx2jV69esXjx4myXVmHNmDEjhgwZEi+99FJMmTIlVq1aFb/73e9i5cqV2S6tUpg5c2bcdNNNscMOO2S7lArvm2++ic6dO0f16tXj8ccfj7fffjuuvvrqaNCgQbZLq9DGjBkT48ePj+uvvz7eeeedGDNmTFxxxRVx3XXXZbu0CmXlypWx4447xg033LDW+VdccUWMGzcuJkyYEC+//HLUqVMnevXqFd9//33KlVIa9Evp0y9ll34pPfql7NAvpaPS9EsJJbbHHnskQ4YMyUwXFhYmzZs3T0aPHp3FqiqXxYsXJxGRzJgxI9ulVHjLly9P2rdvn0yZMiXp1q1bMmzYsGyXVKGdffbZyT777JPtMiqdPn36JH/84x+LjR122GHJgAEDslRRxRcRyUMPPZSZLioqSpo2bZpceeWVmbElS5Ykubm5yT333JOFCtlU+qXs0y+lR7+ULv1SduiX0leR+yVnSpXQDz/8ELNnz46ePXtmxqpUqRI9e/aMF198MYuVVS5Lly6NiIiGDRtmuZKKb8iQIdGnT59in3k2n8mTJ8duu+0Wv//976Nx48ax8847xy233JLtsiq8vffeO6ZOnRrvvfdeRES8/vrr8dxzz0Xv3r2zXFnl8fHHH8eiRYuK/VuTn58fe+65p7+v5ZB+qWzQL6VHv5Qu/VJ26JeyryL1S9WyXUB59eWXX0ZhYWE0adKk2HiTJk3i3XffzVJVlUtRUVEMHz48OnfuHB07dsx2ORXavffeG6+++mrMnDkz26VUGh999FGMHz8+Tj/99Dj33HNj5syZceqpp0aNGjVi4MCB2S6vwjrnnHNi2bJlse2220bVqlWjsLAwLr300hgwYEC2S6s0Fi1aFBGx1r+vq+dRfuiXsk+/lB79Uvr0S9mhX8q+itQvCaUot4YMGRJvvvlmPPfcc9kupUJbsGBBDBs2LKZMmRI1a9bMdjmVRlFRUey2225x2WWXRUTEzjvvHG+++WZMmDBBk7UZ3XfffXHXXXfF3XffHR06dIg5c+bE8OHDo3nz5o47UC7pl9KhX8oO/VJ26JcoTS7fK6EtttgiqlatGp9//nmx8c8//zyaNm2apaoqj6FDh8Zjjz0W06ZNixYtWmS7nApt9uzZsXjx4thll12iWrVqUa1atZgxY0aMGzcuqlWrFoWFhdkusUJq1qxZbL/99sXGtttuu5g/f36WKqoczjrrrDjnnHOif//+0alTpzjmmGPitNNOi9GjR2e7tEpj9d9Qf18rBv1SdumX0qNfyg79Unbol7KvIvVLQqkSqlGjRuy6664xderUzFhRUVFMnTo19tprryxWVrElSRJDhw6Nhx56KJ5++ulo06ZNtkuq8Hr06BH//ve/Y86cOZnXbrvtFgMGDIg5c+ZE1apVs11ihdS5c+c1Ht/93nvvRatWrbJUUeXw7bffRpUqxf80Vq1aNYqKirJUUeXTpk2baNq0abG/r8uWLYuXX37Z39dySL+UHfql9OmXskO/lB36peyrSP2Sy/c2wemnnx4DBw6M3XbbLfbYY48YO3ZsrFy5MgYPHpzt0iqsIUOGxN133x2PPPJI5OXlZa6Xzc/Pj1q1amW5uoopLy9vjXtQ1KlTJxo1auTeFJvRaaedFnvvvXdcdtllccQRR8Qrr7wSN998c9x8883ZLq1C69u3b1x66aWx9dZbR4cOHeK1116La665Jv74xz9mu7QKZcWKFfHBBx9kpj/++OOYM2dONGzYMLbeeusYPnx4XHLJJdG+ffto06ZNnH/++dG8efPo169f9oqmxPRL6dMvpU+/lB36pezQL6Wj0vRL2X78X3l33XXXJVtvvXVSo0aNZI899kheeumlbJdUoUXEWl8TJ07MdmmVikccp+PRRx9NOnbsmOTm5ibbbrttcvPNN2e7pApv2bJlybBhw5Ktt946qVmzZvKb3/wmOe+885KCgoJsl1ahTJs2ba3/lg8cODBJkp8ec3z++ecnTZo0SXJzc5MePXokc+fOzW7RbBL9Urr0S2WDfikd+qX06ZfSUVn6pZwkSZI0QzAAAAAAcE8pAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIAAAAgdUIpAAAAAFInlAIqpEGDBkW/fv2KjT3wwANRs2bNuPrqq2P06NGx++67R15eXjRu3Dj69esXc+fOXWM7L7zwQhx44IHRoEGDqFmzZnTq1CmuueaaKCwsTOmdAABsPnomIJuEUkCl8Le//S0GDBgQ48ePjzPOOCNmzJgRQ4YMiZdeeimmTJkSq1atit/97nexcuXKzDoPPfRQdOvWLVq0aBHTpk2Ld999N4YNGxaXXHJJ9O/fP5IkyeI7AgAofXomIE05iX8hgApo0KBBsWTJknj44YfjiiuuiJEjR8bdd98dhx566FqX/+KLL6Jx48YxY8aM6Nq1a6xcuTJatWoV3bp1i3/84x/Fln300Ufj4IMPjnvvvTeOPPLINN4OAMBmoWcCssmZUkCFdvbZZ8fFF18cjz322Dqbq4iIpUuXRkREw4YNIyLiySefjK+++irOPPPMNZbt27dvbLPNNnHPPfdsnqIBAFKmZwKyoVq2CwDYXB5//PF45JFHYurUqbHffvutc7mioqIYPnx4dO7cOTp27BgREe+9915ERGy33XZrXWfbbbfNLAMAUJ7pmYBscaYUUGHtsMMO0bp16xg5cmSsWLFincsNGTIk3nzzzbj33nvXmOcKZwCgotMzAdkilAIqrK222iqmT58en376aRxwwAGxfPnyNZYZOnRoPPbYYzFt2rRo0aJFZnybbbaJiIh33nlnrdt+5513MssAAJRneiYgW4RSQIXWqlWrmDFjRixatKhYk5UkSQwdOjQeeuihePrpp6NNmzbF1vvd734XDRs2jKuvvnqNbU6ePDnef//9OOqoo1J5DwAAm5ueCcgGoRRQ4bVs2TKmT58eixcvjl69esWyZctiyJAhceedd8bdd98deXl5sWjRoli0aFF89913ERFRp06duOmmm+KRRx6JE088Md5444345JNP4u9//3sMGjQoDj/88DjiiCOy/M4AAEqPnglIW07i4l+gAvr5441X+/TTT2PfffeNRo0axUsvvbTW9SZOnBiDBg3KTD/77LNx6aWXxosvvhjff/99tG/fPgYPHhzDhw+PqlWrbuZ3AQCweemZgGwSSgEAAACQOpfvAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqRNKAQAAAJA6oRQAAAAAqfv/ANjAdw6gDmzyAAAAAElFTkSuQmCC", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "from lib.cross_validation import custom_kfold_cross_validation_new\n", + "from lib.reproduction import major_oxides\n", + "\n", + "for oxide in major_oxides:\n", + " folds, train_new, test_new = custom_kfold_cross_validation_new(\n", + " data=full_data, k=5, group_by=\"Sample Name\", target=oxide, random_state=42\n", + " )\n", + "\n", + " test_unique = test.drop_duplicates(subset='Sample Name')\n", + " test_new_unique = test_new.drop_duplicates(subset='Sample Name')\n", + " \n", + " plot_distribution_comparison(test_unique, test_new_unique, oxide, labels=('Baseline Test', 'New Test'), colors=('blue', 'orange'))\n" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "venv", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.2" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} From 2c961d76e4593aa76e2e754162b8e1d34761f74d Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 15:53:23 +0200 Subject: [PATCH 4/9] cite github --- .../src/sections/experiments/stacking_ensemble.tex | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/report_thesis/src/sections/experiments/stacking_ensemble.tex b/report_thesis/src/sections/experiments/stacking_ensemble.tex index fd9c34d8..decff7ee 100644 --- a/report_thesis/src/sections/experiments/stacking_ensemble.tex +++ b/report_thesis/src/sections/experiments/stacking_ensemble.tex @@ -72,6 +72,13 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} The 1:1 plot in Figure~\ref{fig:elasticnet_one_to_one} shows the near-constant predictions for \ce{TiO2} when using a \gls{enet} meta-learner, and Figure~\ref{fig:enetalpha01_one_to_one} shows the improved predictions with \texttt{alpha} = 0.1. This leads us to conclude that the meta-learner's choice significantly impacts the \gls{rmsecv} and prediction outcomes. +The stacking approach demonstrated significant improvements in prediction accuracy compared to the baseline described in Section~\ref{sec:baseline_replica}, validating the efficacy of our methodology. +We measured this improvement using \gls{rmsep}, which provides the fairest comparison between the baseline and the stacking approach. +As mentioned, \gls{rmsep} evaluates the model's performance on the test set. +In Section~\ref{sec:baseline_replica}, we described how the baseline test set was constructed by sorting extreme concentration values into the training set, and then performing a random split. +As noted in Section~\ref{subsec:validation_testing_procedures}, required a more sophisticated procedure to support the testing and validation strategy in this work. +Despite the differences in test set construction, the test sets remained similar in composition\footnote{The analysis of this can be found on our GitHub repository: \url{https://github.com/chhoumann/thesis-chemcam}}, which allowed us to use \gls{rmsep} as a fair comparison metric. + The stacking approach demonstrated significant improvements in prediction accuracy as compared to the baseline we described in Section~\ref{subsec:baseline_results}, validating the efficacy of our methodology. We measured this by \gls{rmsep}, as it provides the fairest comparison between the baseline and the stacking approach. However, it is important to note that some evaluation metrics are worse in the stacking approach than in certain individual configurations. From 81f3d886a324b01c140a23c99fa2fef6271f58a3 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 15:56:04 +0200 Subject: [PATCH 5/9] expand on why it's suitable to devise a new method for data partitining vs. old method --- .../src/sections/proposed_approach/testing_validation.tex | 1 + 1 file changed, 1 insertion(+) diff --git a/report_thesis/src/sections/proposed_approach/testing_validation.tex b/report_thesis/src/sections/proposed_approach/testing_validation.tex index d95cabbc..23564774 100644 --- a/report_thesis/src/sections/proposed_approach/testing_validation.tex +++ b/report_thesis/src/sections/proposed_approach/testing_validation.tex @@ -64,6 +64,7 @@ \subsection{Validation and Testing Procedures for Model Evaluation}\label{subsec The baseline did not employ cross-validation, as our goal was to replicate the \gls{moc} model that was presented in \citet{cleggRecalibrationMarsScience2017}. We note that this procedure is insufficient to support the testing and validation strategy we have laid out above, as it does not support $k$-fold cross-validation. A random $k$-fold split of the training data would not account for the uneven distribution of extreme values across the folds, and would furthermore cause data leakage between the folds. +Moreover, the procedure failed to consider the concentration of each oxide individually, instead aggregating concentrations across all oxides. This represents a significant limitation, as it attempts to generate a uniform test set for each oxide, thereby neglecting the unique distribution characteristics of individual oxides. Therefore, a more sophisticated procedure is needed to ensure that the data partitioning accounts for these challenges. \subsubsection{Dataset Partitioning}\label{subsubsec:dataset_partitioning} From 963ec359ae8f169af1fe4d534b44f6eaac975827 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 15:58:00 +0200 Subject: [PATCH 6/9] remove duplicate text --- report_thesis/src/sections/experiments/stacking_ensemble.tex | 2 -- 1 file changed, 2 deletions(-) diff --git a/report_thesis/src/sections/experiments/stacking_ensemble.tex b/report_thesis/src/sections/experiments/stacking_ensemble.tex index decff7ee..41f0f0dc 100644 --- a/report_thesis/src/sections/experiments/stacking_ensemble.tex +++ b/report_thesis/src/sections/experiments/stacking_ensemble.tex @@ -79,8 +79,6 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} As noted in Section~\ref{subsec:validation_testing_procedures}, required a more sophisticated procedure to support the testing and validation strategy in this work. Despite the differences in test set construction, the test sets remained similar in composition\footnote{The analysis of this can be found on our GitHub repository: \url{https://github.com/chhoumann/thesis-chemcam}}, which allowed us to use \gls{rmsep} as a fair comparison metric. -The stacking approach demonstrated significant improvements in prediction accuracy as compared to the baseline we described in Section~\ref{subsec:baseline_results}, validating the efficacy of our methodology. -We measured this by \gls{rmsep}, as it provides the fairest comparison between the baseline and the stacking approach. However, it is important to note that some evaluation metrics are worse in the stacking approach than in certain individual configurations. We believe that further tuning, particularly of the meta-learner's hyperparameters, could substantially improve these results. From a8ff43dc6419ebe8c40e889ff32135b631ee4b19 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 16:05:12 +0200 Subject: [PATCH 7/9] wip --- .../experiments/stacking_ensemble.tex | 35 +++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/report_thesis/src/sections/experiments/stacking_ensemble.tex b/report_thesis/src/sections/experiments/stacking_ensemble.tex index 41f0f0dc..68cb1fde 100644 --- a/report_thesis/src/sections/experiments/stacking_ensemble.tex +++ b/report_thesis/src/sections/experiments/stacking_ensemble.tex @@ -176,6 +176,41 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} \label{fig:elasticnet_one_to_one} \end{figure*} + +\begin{table} +\centering +\caption{Comparison of \gls{rmsep} values for the \gls{moc} (replica) model and various stacking ensemble models.} +\resizebox{0.45\textwidth}{!}{ +\begin{tabular}{lccccc} +\toprule +Oxide & \gls{moc} (replica) & \gls{enet} ($\alpha = 1$) & \gls{enet} ($\alpha = 0.1$) & \gls{svr} \\ +\midrule +\ce{SiO2} & 5.61 & 3.588 & 3.598 & \textbf{3.473} \\ +\ce{TiO2} & 0.61 & 0.571 & \textbf{0.319} & 0.340 \\ +\ce{Al2O3} & 2.47 & \textbf{1.656} & 1.658 & 1.729 \\ +\ce{FeO_T} & 1.82 & 1.794 & 1.841 & \textbf{1.693} \\ +\ce{MgO} & 1.56 & \textbf{0.711} & 0.768 & 0.819 \\ +\ce{CaO} & 2.09 & \textbf{1.636} & 1.647 & 1.594 \\ +\ce{Na2O} & 1.33 & 0.470 & 0.442 & \textbf{0.369} \\ +\ce{K2O} & 1.91 & \textbf{0.476} & 0.494 & 0.511 \\ +\bottomrule +\end{tabular} +} +\label{tab:stacking_ensemble_vs_moc} +\end{table} + +Table~\ref{tab:stacking_ensemble_vs_moc} compares the \gls{rmsep} values of different oxides for the \gls{moc} (replica) model with three stacking ensemble models: \gls{enet} with $\alpha = 1$, \gls{enet} with $\alpha = 0.1$, and \gls{svr}. + +Overall, the stacking ensemble models tend to produce lower \gls{rmsep} values compared to the \gls{moc} (replica) model. Notably, \ce{SiO2}, \ce{TiO2}, \ce{Na2O}, and \ce{K2O} show significant improvements across all stacking ensemble models. For instance, the \gls{rmsep} for \ce{SiO2} is reduced from 5.61 (\gls{moc} (replica)) to around 3.588-3.598 (\gls{enet} with $\alpha = 1$) and further to 3.473 (\gls{svr}). Similarly, \ce{TiO2} shows a reduction from 0.61 (\gls{moc} (replica)) to 0.319-0.340 (\gls{enet} with $\alpha = 1$). + +The improvements are consistent across most oxides, with \gls{enet} and \gls{svr} models both outperforming the \gls{moc} (replica) model. This suggests that the ensemble approach, particularly with these meta-learners, enhances prediction accuracy for the oxides tested. + + + + + + + \begin{figure*} \centering \resizebox{0.75\textwidth}{!}{ From 88dc53dde6d987193911fea6637b2ffcfee8bfcf Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 19:09:37 +0200 Subject: [PATCH 8/9] analyze! --- .../experiments/stacking_ensemble.tex | 32 +++++++++---------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/report_thesis/src/sections/experiments/stacking_ensemble.tex b/report_thesis/src/sections/experiments/stacking_ensemble.tex index f43f173b..5aa618ac 100644 --- a/report_thesis/src/sections/experiments/stacking_ensemble.tex +++ b/report_thesis/src/sections/experiments/stacking_ensemble.tex @@ -84,7 +84,7 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} \begin{table} \centering -\caption{Stacking ensemble results using the \gls{enet} model as the meta-learner with default hyperparameters.} +\caption{Stacking ensemble results using the \gls{enet} model as the meta-learner with $\alpha = 1$.} \begin{tabular}{lcccc} \toprule Oxide & \gls{rmsep} & STDDEV & \gls{rmsecv} & Std. Dev. CV \\ @@ -185,14 +185,14 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} \toprule Oxide & \gls{moc} (replica) & \gls{enet} ($\alpha = 1$) & \gls{enet} ($\alpha = 0.1$) & \gls{svr} \\ \midrule -\ce{SiO2} & 5.61 & 3.588 & 3.598 & \textbf{3.473} \\ -\ce{TiO2} & 0.61 & 0.571 & \textbf{0.319} & 0.340 \\ -\ce{Al2O3} & 2.47 & \textbf{1.656} & 1.658 & 1.729 \\ -\ce{FeO_T} & 1.82 & 1.794 & 1.841 & \textbf{1.693} \\ -\ce{MgO} & 1.56 & \textbf{0.711} & 0.768 & 0.819 \\ -\ce{CaO} & 2.09 & \textbf{1.636} & 1.647 & 1.594 \\ -\ce{Na2O} & 1.33 & 0.470 & 0.442 & \textbf{0.369} \\ -\ce{K2O} & 1.91 & \textbf{0.476} & 0.494 & 0.511 \\ +\ce{SiO2} & 5.61 & 3.59 & 3.60 & \textbf{3.47} \\ +\ce{TiO2} & 0.61 & 0.57 & \textbf{0.32} & 0.34 \\ +\ce{Al2O3} & 2.47 & \textbf{1.66} & 1.66 & 1.73 \\ +\ce{FeO_T} & 1.82 & 1.79 & 1.84 & \textbf{1.69} \\ +\ce{MgO} & 1.56 & \textbf{0.71} & 0.77 & 0.82 \\ +\ce{CaO} & 2.09 & \textbf{1.64} & 1.65 & 1.59 \\ +\ce{Na2O} & 1.33 & 0.47 & 0.44 & \textbf{0.37} \\ +\ce{K2O} & 1.91 & \textbf{0.48} & 0.49 & 0.51 \\ \bottomrule \end{tabular} } @@ -201,15 +201,13 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} Table~\ref{tab:stacking_ensemble_vs_moc} compares the \gls{rmsep} values of different oxides for the \gls{moc} (replica) model with three stacking ensemble models: \gls{enet} with $\alpha = 1$, \gls{enet} with $\alpha = 0.1$, and \gls{svr}. -Overall, the stacking ensemble models tend to produce lower \gls{rmsep} values compared to the \gls{moc} (replica) model. Notably, \ce{SiO2}, \ce{TiO2}, \ce{Na2O}, and \ce{K2O} show significant improvements across all stacking ensemble models. For instance, the \gls{rmsep} for \ce{SiO2} is reduced from 5.61 (\gls{moc} (replica)) to around 3.588-3.598 (\gls{enet} with $\alpha = 1$) and further to 3.473 (\gls{svr}). Similarly, \ce{TiO2} shows a reduction from 0.61 (\gls{moc} (replica)) to 0.319-0.340 (\gls{enet} with $\alpha = 1$). - -The improvements are consistent across most oxides, with \gls{enet} and \gls{svr} models both outperforming the \gls{moc} (replica) model. This suggests that the ensemble approach, particularly with these meta-learners, enhances prediction accuracy for the oxides tested. - - - - - +Overall, the stacking ensemble models tend to produce lower \gls{rmsep} values compared to the \gls{moc} (replica) model. +Notably, \ce{SiO2}, \ce{TiO2}, \ce{Na2O}, and \ce{K2O} show large improvements across all stacking ensemble models. +For instance, the \gls{rmsep} for \ce{SiO2} is reduced from 5.61 (\gls{moc} (replica)) to around 3.59 (\gls{enet} with $\alpha = 1$) and further to 3.47 (\gls{svr}). +Similarly, \ce{TiO2} shows a reduction from 0.61 (\gls{moc} (replica)) to 0.32 (\gls{enet} with $\alpha = 0.1$). +The improvements are consistent across most oxides, with \gls{enet} and \gls{svr} models both outperforming the \gls{moc} (replica) model. +This shows that the ensemble approach, particularly with these meta-learners, enhances prediction accuracy for the oxides we tested. \begin{figure*} \centering From 88b034dcb39ee5129a9bb65bff118d9ae4561679 Mon Sep 17 00:00:00 2001 From: Christian Bager Bach Houmann Date: Wed, 12 Jun 2024 19:12:43 +0200 Subject: [PATCH 9/9] tail --- .../experiments/stacking_ensemble.tex | 21 ++++++++----------- 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/report_thesis/src/sections/experiments/stacking_ensemble.tex b/report_thesis/src/sections/experiments/stacking_ensemble.tex index 5aa618ac..95ff0f1b 100644 --- a/report_thesis/src/sections/experiments/stacking_ensemble.tex +++ b/report_thesis/src/sections/experiments/stacking_ensemble.tex @@ -72,13 +72,21 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} The 1:1 plot in Figure~\ref{fig:elasticnet_one_to_one} shows the near-constant predictions for \ce{TiO2} when using a \gls{enet} meta-learner, and Figure~\ref{fig:enetalpha01_one_to_one} shows the improved predictions with \texttt{alpha} = 0.1. This leads us to conclude that the meta-learner's choice significantly impacts the \gls{rmsecv} and prediction outcomes. -The stacking approach demonstrated significant improvements in prediction accuracy compared to the baseline described in Section~\ref{sec:baseline_replica}, validating the efficacy of our methodology. +The stacking approach demonstrated strong improvements in prediction accuracy compared to the baseline described in Section~\ref{sec:baseline_replica}, validating the efficacy of our methodology. We measured this improvement using \gls{rmsep}, which provides the fairest comparison between the baseline and the stacking approach. As mentioned, \gls{rmsep} evaluates the model's performance on the test set. In Section~\ref{sec:baseline_replica}, we described how the baseline test set was constructed by sorting extreme concentration values into the training set, and then performing a random split. As noted in Section~\ref{subsec:validation_testing_procedures}, required a more sophisticated procedure to support the testing and validation strategy in this work. Despite the differences in test set construction, the test sets remained similar in composition\footnote{The analysis of this can be found on our GitHub repository: \url{https://github.com/chhoumann/thesis-chemcam}}, which allowed us to use \gls{rmsep} as a fair comparison metric. +Table~\ref{tab:stacking_ensemble_vs_moc} compares the \gls{rmsep} values of different oxides for the \gls{moc} (replica) model with three stacking ensemble models: \gls{enet} with $\alpha = 1$, \gls{enet} with $\alpha = 0.1$, and \gls{svr}. +Overall, the stacking ensemble models tend to produce lower \gls{rmsep} values compared to the \gls{moc} (replica) model. +Notably, \ce{SiO2}, \ce{TiO2}, \ce{Na2O}, and \ce{K2O} show large improvements across all stacking ensemble models. +For instance, the \gls{rmsep} for \ce{SiO2} is reduced from 5.61 (\gls{moc} (replica)) to around 3.59 (\gls{enet} with $\alpha = 1$) and further to 3.47 (\gls{svr}). +Similarly, \ce{TiO2} shows a reduction from 0.61 (\gls{moc} (replica)) to 0.32 (\gls{enet} with $\alpha = 0.1$). +The improvements are consistent across most oxides, with \gls{enet} and \gls{svr} models both outperforming the \gls{moc} (replica) model. +This shows that the ensemble approach, particularly with these meta-learners, enhances prediction accuracy for the oxides we tested. +The results presented above indicate a strong performance from the stacking ensemble approach. However, it is important to note that some evaluation metrics are worse in the stacking approach than in certain individual configurations. We believe that further tuning, particularly of the meta-learner's hyperparameters, could substantially improve these results. @@ -176,7 +184,6 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} \label{fig:elasticnet_one_to_one} \end{figure*} - \begin{table} \centering \caption{Comparison of \gls{rmsep} values for the \gls{moc} (replica) model and various stacking ensemble models.} @@ -199,16 +206,6 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results} \label{tab:stacking_ensemble_vs_moc} \end{table} -Table~\ref{tab:stacking_ensemble_vs_moc} compares the \gls{rmsep} values of different oxides for the \gls{moc} (replica) model with three stacking ensemble models: \gls{enet} with $\alpha = 1$, \gls{enet} with $\alpha = 0.1$, and \gls{svr}. - -Overall, the stacking ensemble models tend to produce lower \gls{rmsep} values compared to the \gls{moc} (replica) model. -Notably, \ce{SiO2}, \ce{TiO2}, \ce{Na2O}, and \ce{K2O} show large improvements across all stacking ensemble models. -For instance, the \gls{rmsep} for \ce{SiO2} is reduced from 5.61 (\gls{moc} (replica)) to around 3.59 (\gls{enet} with $\alpha = 1$) and further to 3.47 (\gls{svr}). -Similarly, \ce{TiO2} shows a reduction from 0.61 (\gls{moc} (replica)) to 0.32 (\gls{enet} with $\alpha = 0.1$). - -The improvements are consistent across most oxides, with \gls{enet} and \gls{svr} models both outperforming the \gls{moc} (replica) model. -This shows that the ensemble approach, particularly with these meta-learners, enhances prediction accuracy for the oxides we tested. - \begin{figure*} \centering \resizebox{0.75\textwidth}{!}{