You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
privacykit/notebooks/data-analysis.ipynb

215 lines
44 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"df = pd.read_csv('../src/out/risk_xoi.csv')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>group_count</th>\n",
" <th>row_count</th>\n",
" <th>marketer</th>\n",
" <th>prosecutor</th>\n",
" <th>field_count</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>432512</td>\n",
" <td>79080802</td>\n",
" <td>0.005469</td>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>17824004</td>\n",
" <td>79080802</td>\n",
" <td>0.225390</td>\n",
" <td>1</td>\n",
" <td>28</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>43538084</td>\n",
" <td>79080802</td>\n",
" <td>0.550552</td>\n",
" <td>1</td>\n",
" <td>38</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>64042788</td>\n",
" <td>79080802</td>\n",
" <td>0.809840</td>\n",
" <td>1</td>\n",
" <td>46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>6866070</td>\n",
" <td>79080802</td>\n",
" <td>0.086823</td>\n",
" <td>1</td>\n",
" <td>17</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 group_count row_count marketer prosecutor field_count\n",
"0 0 432512 79080802 0.005469 1 10\n",
"1 0 17824004 79080802 0.225390 1 28\n",
"2 0 43538084 79080802 0.550552 1 38\n",
"3 0 64042788 79080802 0.809840 1 46\n",
"4 0 6866070 79080802 0.086823 1 17"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"compiled = df.groupby('field_count')[['field_count','marketer','prosecutor']].mean()\n",
"figure = compiled[['marketer','prosecutor']].plot.line().get_figure()"
]
},
{
"cell_type": "markdown",
"metadata": {
"variables": {
" figure ": "<img src=\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAicAAAG0CAYAAADpSoetAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzs3XmYXHWdP/r3qb2r9z3dnU46K0mALCQQwqbORDKI8efMMDIuZIyKI5L5qRmvGhVyR2dA5wLj3PmhGaMMuIJycQMMYDQiEghJSMKSPeklve/V3dW1nnP/OPU9VdVdy6l96ffrefoRuk91fYOQ/uSzfSVFURQQERER5QlDrg9AREREFIrBCREREeUVBidERESUVxicEBERUV5hcEJERER5hcEJERER5RUGJ0RERJRXGJwQERFRXmFwQkRERHmFwQkRERHlFQYnRERElFdMuT6AHrIso6enB+Xl5ZAkKdfHISIiIh0URcHExASam5thMOjPhxREcNLT04PW1tZcH4OIiIiS0NXVhfnz5+t+viCCk/LycgDqL66ioiLHpyEiIiI9HA4HWltbtZ/jehVEcCJKORUVFQxOiIiICkyiLRlsiCUiIqK8wuCEiIiI8gqDEyIiIsorDE6IiIgorzA4ISIiorzC4ISIiIjyCoMTIiIiyisMToiIiCivMDghIiKivMLghIiIiPJKwsHJiy++iK1bt6K5uRmSJOGXv/xl3NccOHAAV111FaxWK5YuXYpHH300mbMSERHRHJBwcDI1NYU1a9bg4Ycf1vX8xYsXceutt+Jd73oXjh07hs9+9rP4xCc+geeeey7hwxIREVHxS/jiv1tuuQW33HKL7uf37NmDRYsW4cEHHwQArFy5Ei+99BL+4z/+A1u2bEn07dNHUQCvM3fvT0RElE/MdiDBC/oyJeO3Eh88eBCbN28O+9yWLVvw2c9+Nupr3G433G639vcOhyP9B/M6gfua0/99iYiICtGXewBLaa5PASALDbF9fX1obGwM+1xjYyMcDgemp6cjvub+++9HZWWl9tHa2prpYxIREVGeyHjmJBm7du3Czp07tb93OBzpD1DMdjVKJCIiIvXnYp7IeHAyb9489Pf3h32uv78fFRUVKCkpifgaq9UKq9Wa2YNJUt6kr4iIiCgo42WdTZs2Yf/+/WGfe+GFF7Bp06ZMvzUREREVoISDk8nJSRw7dgzHjh0DoI4KHzt2DJ2dnQDUksy2bdu05z/1qU/hwoUL+MIXvoBTp07h29/+Nn72s5/hc5/7XJp+CURERFRMEg5ODh8+jHXr1mHdunUAgJ07d2LdunW49957AQC9vb1aoAIAixYtwjPPPIMXXngBa9aswYMPPojvfe97uR0jJiIiorwlKYqi5PoQ8TgcDlRWVmJ8fBwVFRW5Pg4RERHpkOzPb96tQ0RERHmFwQkREVERUxQFvzrWjbP9E7k+im4MToiIiIrYkY5RfObxY/jb77yMjuGpXB9HFwYnRERERezN7nEAgMPlw6d+dBTTHn+OTxQfgxMiIqIidnZgUvvrk70OfOUXbyDfZ2EYnBARERUxEZz8/dWtMBokPPV6N370SkeOTxUbgxMiIqIidi4QnHzk2oX40l+tAAB87em3caRjNJfHionBCRERUZEannRjZMoDSQKW1JfhEzcuwq1XNsHrV/DpHx/B4IQ710eMiMEJERFRkRIlnfnVJSixGCFJEr5522osbShDv8ONHT85Cp9fzvEpZ2NwQkREVKREcLKsoVz7XJnVhD0fWY9SixGvXhzBN/edytXxomJwQkREVKTOBRavLWsoC/v80oYyPPB3awAAe/90EU+f6Mn62WJhcEJERFSkROZk6YzgBABuubIJ//iOxQCALzx5Iq82yDI4ISIiKlJaWaexPOLX/6+bL8OmxbUwGSQM5FFzrCnXByAiIqL0G3d6tWmcSJkTADAZDfivD63DlNuHhbWl2TxeTAxOiIiIitC5QbVM01xpQ5k1+o/7ujIr6sqs2TqWLizrEBERFaGz/YF+kyglnXzG4ISIiKgIBceII5d08hmDEyIioiIUa1In3zE4ISIiygM+v4wnj1xK20r5aDtOCgGDEyIiojyw54/n8fmfH8eDz59O+XtNuLzoGXcBYOaEiIiIkiDLCh5/rQtAsByTivODUwCA+nIrquyWlL9ftjE4ISIiyrGDF4ZxaXQaANAzNp3y9ztbwCUdgMEJERFRzj0RyJoAQL/DBW+KNwWfK+BJHYDBCRERUU6NO73Y91af9veyAvQF+kWSpU3qFOCOE4DBCRERpYGiKJhy+3J9jIL0q+Pd8PhkrGyqwIIaO4DUSztnB1jWISKiOe5ffvM21n7teZzsdeT6KAVHlHQ+sGE+WqpKAAA948kHJ9Mev9a/wuCEiIjmrJfPD8HrV3C8ayzXRykob3aP460eByxGA96/tgUt1Wpw0j2afHByfnASigLUlFpQm2d35ujF4ISIiFKiKIr2J/XhKU+OT1NYfnZYzZrcfHkjqkstaA5kTrrHku85OVfAm2EFBidERJSSMacXTo8fADA8mV/BiaIouT5CVC6vH798vRsA8IENrQCAliobgNR6TkS/CYMTIiKasy6FlCBGptKzej0d/u2Zt7Hu6y/gXOCHdb557q0+OFw+tFSV4IaldQCgZU5SCk76C3uMGGBwQkREKbo06tT+Op/KOs+c6MWY04u9L17M9VEiEiWd29bPh8EgAYDWENs9Np101ie446Qwx4gBBidERJSi7pA/5edLWcfp8Wl3y/zqeDfGnd4cnyhc14gTfz43DElSgxNBZE6cHj/GpxM/s9vnR/uwurp+WSMzJ0RENEeFl3XyIzi5ELhbBgBcXhk/P9IV4+ns+/mRSwCA65fUoTWw2wQAbGYjakvVu3C6kyjtXByagqwA5TYTGsoLc1IHYHBCREQpmhmc5EMT6oUhNTgJVEvwo1c6IMu5PxcA+GUFTwZKOh+4unXW18U4cU8SEzuh/SaSJKVwytxicEJERCkJ7Tnx+GVM5MGm2AuD6g/p91zZhHKrCe3DTrx0bijHp1L9+dwQesZdqCwx4+ZVjbO+3lwpdp04Z30tnrNF0G8CMDghIqIUzSw/jORB38n5QFnnipZK/G2gp+MHBztyeSTNE4GsyfvXNsNmNs76ujaxk8T9OmIyqZD7TQAGJ0RElILxaS8mXGqmpK5M7ZXIh4kdkTlZUl+Gj1y7EADw+1P9YVmeXBid8uCFt/oBRC7pAEBzYNdJMj0noqxTyDtOAAYnRESUArFmvabUgpZqtbEz102xsqxoDbGL60uxtKEM1y+thawAP3m1M6dn+8Xr3fD4ZVzeXIHLmysjPjM/yRX2Xr+Mi0NiUodlHSIimqNEJqKlqkSbMhmezO0itj6HC9NeP0wGSbvl945r2wCol+y5ff6cne3Xx3sAALdHyZoAyS9i6xiegk9WYLcY0VxpS/6QeYDBCRERJU2UHuZXl6CmND/KOiJrsqDWDrNR/TG3eWUDmiptGJ7y4Nk3enNyLllWcLpP7QkRG2EjEcHJwIQ7oUAq9E6dQp7UARicEBFRCsQYcUtVCWoDPSe5LutcGFJ/SC+uC/ZdmIwGfOiaBQCAH+aoMbY3kNExG6Ww3SYz1ZZaYDWpP577x/VnoYql3wRgcEJERCkQfRHzq/OnrHN+QDTDloZ9/u+vWQCzUcLRzjG82T2es3MtrC3VMjqRSJKkrbG/NKa/gbdYxogBBidERJQC8cNzfrUdNaXqRtKcl3UCTaFL6sMzCPXlVtxyRROA3GRPzg+KjE5pnCdD+070jxMHgxNmToiIaA7TyjrVeVTWCZnUmemOTepYcS7u2xHByRIdwYMYJ9bbFOuXFe37F/qOE4DBCRERJWnS7cNY4Ad8S1hZJ3fBidPj05p0F9fP/iG9YWE1Vswrz8l9OyJompnRiSTRiZ2uESc8PhlWkwHzq6P3sxQKBidERJQU0W9SYTOhwmbWpnVyeb+O2PNRbQ+eJ5QkSdi2qQ1A9u/b0TInETI6M4meE72L2M4OBJfOGQ2FPakDMDghIqIkdYf0mwBAbaDnxOOXMZmj+3WCJZ3o2Yn/tbY56/ftTLi86He4455NSDw4KY619QKDEyIiSkpovwkAlFiMsFvUu2Jy1XeiJztRajVp9+38f0cvZeVcImiqL7eissQc9/nQso6eLNSZwP6UpToCn0LA4ISIiJISOkYsiFLKUI76TvRkTgDguiW1AID2QBko0xIp6QBAU6Ah1uWVMaqjcffEJXU0+oqWyCvxCw2DEyIiSkroAjahtjS3EzvBBWyxgwCR7Unmcr1kaGPEOjMbVpMR9eVqmSzeHTvjTq82Pr2mtSqFU+YPBidERJSUS9rq+uB0SG2Z+gN1ZCr7i9gUJXjhX7xxXRFQDU164PJm/q6d8wP6J3WEZp19J8cujQEAFtbaIzYBFyIGJ0RElJTuUdEQmx9lnT6HC05P+IV/0VSWmLX+mN5x/YvOkiUyOnrLOgDQonPXybFONThZWyRZE4DBCRERJcHl9WsBSGhwkkxZZ3zai35H6gGCduFfjT3menggfEV8vLJJqnx+Ge1DaiCXSOZE78TOsa5RAAxOiIhojhP9JmVWU9j0SU0Swclff/vP+MsH/5jyxtZE+zoSXXSWrEuj0/D41QVpof058eg5n6IoONbFzAkREZH2p/mWqhJIUnDpl+g50Xu/jsPlxYXBKUy6fTjRPZbSmYIbWPWVTvT2dKQqNGgyJLAgTU9w0jnixKjTC4vRgFXNFakdNI8wOCEiooRditBvAiDhm4lDSyonex0pnSkYBOgLTkRPR7aCk0T6TYDQsk70kpfImqxsroDVZEzyhPknqeDk4YcfRltbG2w2GzZu3IhDhw7FfP5b3/oWLrvsMpSUlKC1tRWf+9zn4HJlvgGJiIgyY+YCNiHRsk54cDKR0pkSubsGCJ4902WdZCZ1gNCJInfUiaLXA82w64qopAMkEZw88cQT2LlzJ3bv3o2jR49izZo12LJlCwYGBiI+/5Of/ARf+tKXsHv3bpw8eRLf//738cQTT+DLX/5yyocnIqLciLSADYB2M/Gwzvt1QrMWqWROpj3+mBf+RdJcmaXgJMGMjlBlN6PEHHui6PVA5mTdgjkenDz00EO48847sX37dqxatQp79uyB3W7HI488EvH5l19+Gddffz0+9KEPoa2tDTfffDM++MEPxs22EFFx2vXUCXzm8ddzdjEcpYco67RUhY/savfr+PTdrxManJwbmITbl9zOEXHhX1WUC/8i0Xo6xl0ZvQBQLEhLNHMiSRKaY4wTu31+nOxRA7piaoYFEgxOPB4Pjhw5gs2bNwe/gcGAzZs34+DBgxFfc9111+HIkSNaMHLhwgU8++yzeM973hP1fdxuNxwOR9gHERU+l9ePnx7qwq+O9eRsgyilR/dY5MxJicWo/Wlfz//HoWUdn6zgXOB23UQF+zr0BwDzKm0wSGogNZShpXEjUx7tn0OimRMgdtPu2z0OePwyakotcfe6FJqEgpOhoSH4/X40NjaGfb6xsRF9fX0RX/OhD30IX/va13DDDTfAbDZjyZIleOc73xmzrHP//fejsrJS+2htbU3kmESUp5ye4J+Kp7OwlZMyw+3zazfszuw5AYJ9J3omdsSWWTHEkmzfiXanTpy19aHMRgMaK0RmIjN9kBcCQVNLVQnsFlPCrxfBX6RdLKIZds38yrCJqWKQ8WmdAwcO4L777sO3v/1tHD16FE899RSeeeYZfP3rX4/6ml27dmF8fFz76OrqyvQxiSgLnJ5gmj8bK8MpM3oDP8htZoM2nROqLtB3MqJjS6z4obt+YTWA5PtOtDt1EiydZHrXSbL9JkKsvpjgfpPqJE+XvxIK4+rq6mA0GtHf3x/2+f7+fsybNy/ia+655x7ccccd+MQnPgEAuPLKKzE1NYVPfvKT+MpXvgKDYXZ8ZLVaYbVaEzkaERWA6ZDMSWgWhQrLpdHgnTqR/sQezJzELpWoW2bVZzavbMRr7aNJByepjOse6RjN2JbY8wlOEM0U7IuJEZwUWTMskGDmxGKxYP369di/f7/2OVmWsX//fmzatCnia5xO56wAxGhU65FsiCOaW0JLOdMMTgpW95hoho287bSmVN8iNpENsFuMuG5JHQDg7V5Hwj8bFEXBRVHWSTJzksiuE4fLi2ff6IXPL8d99nyghybeRYTRBMedw8tOI1MedAyr/z+snT/HgxMA2LlzJ/bu3YvHHnsMJ0+exF133YWpqSls374dALBt2zbs2rVLe37r1q34zne+g8cffxwXL17ECy+8gHvuuQdbt27VghQimhtCsyVOlnUK1qUoY8SC3rJO6JbZZY1lMBokjDm96Evwnp1+hxtTHj+MOi78m0nv5XqhvvXCWXz6x0fx3y9eiPusltFJoBcm/HzB4Cl0ouh4IGuyuK4UlXZzxNcWsoS7c26//XYMDg7i3nvvRV9fH9auXYt9+/ZpTbKdnZ1hmZKvfvWrkCQJX/3qV9Hd3Y36+nps3boV//Zv/5a+XwURFYTQbImLmZOC1R1lAZugtyE29PvYzEYsrivF2YFJnOx1oKlS/x00IgBYWGOHxZTYn7ljlU2iOX5JDQyeOnoJn37nkqjNqG6fH12BX2OymZPGChukwETR8JQH9eVqVur1IrxPJ1TircMAduzYgR07dkT82oEDB8LfwGTC7t27sXv37mTeioiKCKd1ikNoz0kkuoOTkMwJAKxqrggEJxP4ixWNsV4a5kIKTactMaZhIlEUBWf71Ymi84NTONk7EfVOm85hJ/yygjKrCQ3lyfVRWkwGNJRb0e9wo2dsWgtOirnfBODdOkSURaHTOmyILVwzg4qZxJbYkTgNsTMzMCub1B/ybyfYFHs+yX4TIJg5GXV6w/79jGZw0g2HK/jc0yd6Ypwr2KSbyqhvy4y+GEVRtLJOsWZOGJwQUdaEjg9zlLgwef0yegMlkNYoZR2xJTZez8mlGUGOCE4SndhJdlIHACpsZpRb1SKCnl0n5/rDl8T95kRP1AbeVCd1hJnjzheHpjA+7YXFZMCKecVzE3EoBidElDVhZR1mTgpS37gLsgJYjAbUlUUuVYiyzlCc+3Vm3s+zsqkcANA+NJXQvx8XUsicACGlHR1NsecCgdD1S2thtxjRNTKN45fGIz6b6qSOdr4ZmRNR0rmiuSLhHptCUZy/KiLKS5zWKXyhtxEbDJFLFaKs4/HJmIoSZPj8sjaVI+7naSi3oa7MAlkBTvfr2xQ77fFrzayJbIcNlcgitrOBzMmVLVXYvFLti3n6eOTSTioZnVjnO6Zd9ld8y9cEBidElDXcc1L4xIV/0caIAcBuMQXv14lS2umfcMMvKzAbpbBm0URLOxeHpqAoiV34N1Osy/VmEnf/LG0ow3tXNwEAnj7RO+viQEVR0lbWiZY5KdZ+E4DBCRFlUWjDIYOTwhSvGVYIlnYiN8WKkk5TZXgGJtHgRFtbX5d806m2iE3HxM7ZQHCyrKEM77isHuU2E/ocLhzuGA17bnDCjUm3DwYJWFCb2qV8wcyJCy6vX/tnw+CEiCgNpj3BjZocJS5M8RawCbVxFrFF2zIr+k50Bycp9puEniFez8mY06Ot21/SUAaryYgtl6tXt8yc2hG9KQtq7LCaUls4Ks43MuXBkY5ReP0K6soscf8/KGQMTogoa6a9IZkTBicFKd4CNkFkTkai7DqJ9n1E5uRU74SuNfbBvo7Ug5N4i9hESae50oaywISPKO3MXGefrpIOAFSUmFBqMWrvA6hZk2K7iTgUgxMiyhpO6xS+S2Oi5yR2qaI2zv060cpDS+rLYDEaMOH2aVmaWIKZk+SbTkXZpG/cBb8cPSA6F2H65vqldai2mzE06cErF0a0z6drUgcAJEnSgrjn3uoDUNwlHYDBCRFlETfEFja/rKB3TEzY6CvrDE9G7jm5FCVzYjYasDTwA/2tntilHUVRtO2wqUzENFbYYDRI8PoVDE5EXxwX7DcpDzvvLVeKxthgaSddkzqCCKCGAmWyta3FO6kDMDghoiyaZuakoPU7XPDJCkwGCY0VtpjPxi3rBDIn8yMEOXqbYnvHXSEX/iUfBBgNEuYFfj2x+k5CJ3VCidLOb9/sg8enlnYupLGsAwSDEwCQJGB1a2Vavm++YnBCRFkTNkrMzEnBET+4m6rUTEMstTHu11EURRvbjdS7orcp9skjlwCkZxlZi45dJyI4WdYYHnBsXFSL+nIrxqe9eOncIJwen/bPKl3BSWimakl9GSpsxXcTcSgGJ0SUNcycFDZtx0lV/NFYrawTYZR4eMoDl1eGJCHi7cOrROakL3pw4vL68ejL7QCAj92wKO554om3JXbKHQw4ls4IOIwGCbeK0s7xXlwcUrMm1XYzqpPcvTLrfCHBSbH3mwAMTogoi8Iv/ot/yRrll5nr5mOpiXG/jvg+DeXWiBkPUdbpGpnGhMsb8fv//HAXRqY8mF9dogUGqYi3iE30kNSVWSIGHFvXqGd4/u1+rVcmXVkT9XwMToiIMiK0IdbllWM8SfkoWhNrJKFlnZkjwfEWuVWXWtBUqQYLp/pmr7H3+WV8908XAAB33rgYJmPqP8rirbCP1m8irGutRktVCSbdPjzy0kUA6Q5Ogj0+DE6IiNLELytw+4IBiccvh+2FoPynNbHGGSMGgmUdt08OC0qB0B0n0b9PrKbYZ9/sQ9fINGpKLfjAhlZ9h49DBCfRxpfPxglODAYJtwYaY0VAtaQhPZM6gFr+WlJfisX1pVgxrzz+CwocgxMiyopIDbBsii0sWuYkzhgxoN6vYzOrP2KGZ5R29KzAj9YUqygK/vuP5wEA/7CpDSWW1LavCvPjZE7EhX+hY8QzbV3dHPb36cycGA0SfvuZm/DcZ29KS6Yo3xX/r5CI8kJoA6xYbMngJDK/rOCj/3MIn//58VwfRSPLSkI9J0DoIrbwplg95SGROXm7N7ys89K5IbzV40CJ2YhtmxbqO7wOTYHgxOHyRexzET0n0TInAHBFSwXaQu7RSWdwAgAWkwHmORCYAAxOiChLRHBSYjZqN9a6PCzrRHJxaBIHTg/iySOXMBplT0i29U+44PHLMEjAvMrYO04E7X6dqciZk0g7TgQRnJzuc4Rtbd0TyJrcfnVr2iZhAKDMakJliTqe2zvuCvuay+tHx7A6gbMsRnAiSRLeG8ieWIyGor77JtMYnBBRVjgD9+rYLUbYA6l4p5cTO5F0DDu1v47UEJoLB04PAlCDBr1/eheL2GaVdQIjybEyJ221pbCZDXB5ZbQHAoM3Lo3jz+eGYTRI+MSNqY8Pz9QS5Xbi9uEpyApQbjOhvtwa83v8zVUtKDEbsXFxzZwov2QK/8kRUVaIpsgSixG2QOaEu04iCw9O9N3Om2nPnFAvnBNNn3rURFjENuHywuFSg9JYPSdGg4TL5oU3xe55Uc2avG9Ns66m3EQ1R7mdONhvUhb3sr3F9WV48Qvvwnfv2JD2880lDE6IKCtEIGK3BMs6DE4i6xwJCU56c585GZ504+XzQwCQ0E6RWm2FfbDnRPzgr7KbURq42TeaVSFNsR3DU/ht4Ebef3zHYv2HT0BLlF0n8caIZ6ovt6atUXeuiv1vBhFRmmg9JxYTENh7wYbYyMKCkzzInOx7qw+yojZ8LqzVPx5bWzb7ZuLuBCZ+guPEE/juixcgK8A7L6vHikBGJd2iZU7ORbjwjzKLwQkRZYXTKxpiDSI2YXAShWi+BIAz/ZPwy0rcu2wy6dlAxuLWK5vjPBkuUs+JnjFiQQQnr3eO4qVAcPupdyxJ6AyJED0wqWZOKHUs6xBRVkx7REOsSUt5z1zORerIbldIQ+a01x+WScm2oUk3Dp4fBpBYSQcILetEyJzomGQRy8ZGnV54fDLWtlZh46KahM6QiOCW2OC0js8v48IQg5NsY3BCRFkR2hArpnVczJzM0udwweOTYTJI2gV4p+LczptJ+95USzqr51diQW1iTaiirBManFxKIHNSbjOjtSb43KfesSRuQ2oqxJn6HC5te3HniBNev4ISs1HXmSk9GJwQUVaI4MRu5rROLGJSZ351CS5vFrfz5q4pVpvSSeJyPZE5GZp0a/frJLrIbWWgv2RxXSnevaox4TMkor7MCrNRgl9W0D+hNvGKtfVLGkphyGFpba5hcEJEWSGyJGF7ThiczNI5ovabLKgtxYqQRWS5MDDhwqsX1ZLOe5IITkTPSej9OsGeE31ZmPeva0G51YQv3bIi4303BoOEpsrwvhM2w+YGG2KJKCucIdM6fllNmbOsM5vInCyoKcHKQM9FrhaxPRco6axprUJrTeJ7RewWI6wmA9w+GSNTHhgNEgYDGQk9PSeAGhQlExglq7nKhs4R56zghP0m2cXMCRFlhTPC+npmTmYTza8La0pxWSA46Rh2Ysqd/W26zwSmdN6bZHAgSRLqQsaJxVr4ErMR1XZzeg6ZZiKjI+7/YXCSGwxOiCgrgtM6RnXXCThKHIkIThbU2lFbZtXWpZ/uz272RC3pjAAAbrlyXtLfJzhO7A6b1MlkY2sqQhexybLC4CRHGJwQUVaETuuUmNXfehiczCbKOgsDkzFinPZ0lks7+97sg6IA6xZUpbQqPnSFffdY4E6dPJ56CY4TT6NnfBrTXj/MRgkLkyhrUfIYnBBRVkyHNMSKPSec1gk37vRifNoLAFgQ+GG4MkfjxE+nMKUTKvRm4kR2nORK6JZYMamzqK6Ul/hlGRtiiSgrQu/W8fgNYZ8jVUdgUqe+3Ap7oPQlMifZHCfud7jwWrso6aQYnISUdcQa+3zOnIjAqXt0Guf6OamTKwxOiCgrRFnHZjbCaODdOpEEJ3WCJYTLQso6iqJkpVfjt2/0QlGAqxZUpRxI1JQGG2IT3XGSC82BUeIpjx9HO0cBAEvYb5J1zFMRUVYEyzombc9JsWdOfH45oV9jcFInGJwsbSiD0SBhfNqLPocr2kvTSkzp3Lo6sbt0IgldYZ/IvTq5UmIxan0yL51Tb2JexuAk6xicEFFWOEOmdbQNsUWeOfnUj45i0zf2Y2BCX1DRORyc1BGsJiOW1Ks3AZ+z5/2/AAAgAElEQVTqzXxpp2/chcMdasbgPSlM6Qii52Rwwo2+wChxPvecAMHgacKl/jvLSZ3sY3BCRFkxHTatU/x7TmRZwYtnBjHm9OLlc8O6XiN6ThbOuMPmsnlijX3mm2J/+6Za0tmwsFrblpoKkYU42z8Jn6zAZJDQUG5L+ftmUnNV8HwGSW2IpexicEJEWTEdYX19MW+I7XO44AlcHnf80piu12iZk5rwH4bZHCfW7tJZnZ6trLWBnhPxz6KpypbxNfSpag4pOy2osWuZPsoeNsQSUcZ5/TK8frUJtsRshCHQ1Dnt9WetyTPbRHMrABzvih+cuH1+9AZ6SmZmTlY2BdbYZ7is0zs+jcMdo5Ak4JYr0hScBMo6wnydd+rkUmhPzFJO6uQEMydElHGh5ZuSkJ4Tv6xof6IuNl0jweDkrR4HvHF+nV0j01AUNbMkmkiFFYGyzvnBSbh9mck2vd3jwD//7DgA4OqFNZhXmZ7Si7hfR8j3fhNgZnDCfpNcYOaEiDJO9JsYDRIsRoOWOQEAl0eG1VR8aXPRPwKot/Ke6Z/A5c2VUZ8XwcyCGvusTFJTpQ3lNhMmXD6cH5jCquaKtJ2zfWgKD71wBr850QNFUf8/+uRNi9P2/SVJQm2pBT2iGTaPJ3WE0LIOJ3Vyg5kTIso4bVLHbIQkSTAbDTAZgqWdYhRa1gGAE5fG4zwfuRkWUH/ArwxkT073p6cptt/hwpd/8QY2P/RH/Pq4Gpi8d3UTXvjcTdi8qjEt7yHUhJR2CiFzEhacNDI4yQVmTogo40QAItbWi7+ecPm0wKXYiJ0lS+pLcX5wCicujeGD1yyI+nyH2HFSG3kyZEVTOQ61j6h9J+uSP9e404tvHziHR19uh9unlpreeVk9Pn/zZbiiJXpmJxWiKRYA5hdA5qSuzIIFNXZMun3cDpsjDE6IKONCx4iFErManBRr5kQEJ1vXNONbvzuLY12xMyedEbbDhlqhjROn1hR75w8P41DgtuENC6vxhb9agWsW1aT0PeMJ7aEphMyJJEl45n/fAL+shP07S9nD4ISIMk67kdgcnjkBinNL7Pi0F2NO9QK/965Wg5Mz/ROY9vij/rALZk4iBydijX0qFwBOuX1aYLJ32wZsXtmQlUkpsetEkpCW3SnZUG4z5/oIcxp7Togo45whl/4JJUW8JVZkQerKLFhSX4r6civ8soK3eyNnT2RZCVldH7msI4KTgQk3RgIX6CXq/OBk4FxWvHtVY9ZGuGvL1LJOQ7kVFhN/7FB8/LeEiDJu2itW1weTtcWcOemcMXmzZr7ay3E8SmlnYMINj0+G0SChqSryCG+Z1aSVfE4luSn23IAanCxtyO7GU7HrpBAmdSg/MDghooyb9qiNlzN7ToDizJwE19CrQcDq+VUAgBNRNsWKSZ2WqhKYjdF/W14xL7VlbGe14CS7EyjvvKwe1y+txcduWJTV96XCxZ4TIso4MZET2nNSzDcTz2xuXS0yJ1HGieP1mwgr5pXj+bf7U8+c1Gc3OGkot+HHn7g2q+9JhY2ZEyLKuOkIPSfFfDNxaFkHCGZOLg5NYXzaO/v5OJM6woqmwK6TJCd2zgeCk2WNHI+l/MbghIgyzhlhz4kIVIrxZmKxgE1kQmpKLVrg8UaE7EkimRMAON0/Ab+sJHQmt8+vvQ9XslO+Y3BCRBkXKXMiSjzFdjOxxyejd3waALAgJNgIlnZm9510BnpOZt5GPNPC2lLYzAa4vLLWp6JX+5ATfllBudWEhnJr/BcQ5RCDEyLKuGBwEmxzsxVp5uTSqBOyogZf9WXBIGBNjKbYmWWgaIwGCcsDJZlTCZZ2RL/JkoayorwFmooLgxMiyjhR1rGFNsSa1UCl2HpOZo4RC6ujjBM7XF6MBha2LYhT1gFCJnaSDE54kR0VAgYnRJRx0+Liv7C7ddTfflxFljnRgpMZgcYVLZUwSECfw4UBhyv4fMjCtjJr/AFKscY+0U2xZwfUYIb9JlQIkgpOHn74YbS1tcFms2Hjxo04dOhQzOfHxsZw9913o6mpCVarFcuXL8ezzz6b1IGJqPDE2hCb72Wd35/qx+3/fVALIuLRmmFnlGhKrSbtErnQkeIOnZM6QqqZEwYnVAgSDk6eeOIJ7Ny5E7t378bRo0exZs0abNmyBQMDAxGf93g8ePe734329nY8+eSTOH36NPbu3YuWlpaUD09EhSHy3TqFUdb5yaudePXiCJ480qXr+WiZEyBY2gntO5m5sC0esca+c8SJSbe+G539soILQ+r7MDihQpBwcPLQQw/hzjvvxPbt27Fq1Srs2bMHdrsdjzzySMTnH3nkEYyMjOCXv/wlrr/+erS1teEd73gH1qxZk/LhiagwiImcsPX1BbLnZGhSvcfm9a7I211nirWzZHWr2hQbmjnRu+NEqC2zatM2Z/r1ZU8ujTrh8cmwmgyYX63vfYhyKaHgxOPx4MiRI9i8eXPwGxgM2Lx5Mw4ePBjxNb/+9a+xadMm3H333WhsbMQVV1yB++67D35/9N+Q3G43HA5H2AcRFS4tc2IJ/pZTKBtihybdAIDjXWOQ4+wWUZSQC/wiZELWhGROFEX9XnondUKJZWxvdkfeODvT2X61pLO4vgxGAyd1KP8lFJwMDQ3B7/ejsbEx7PONjY3o6+uL+JoLFy7gySefhN/vx7PPPot77rkHDz74IP71X/816vvcf//9qKys1D5aW1sTOSYR5ZlgWSdklLhAMifDgcyJw+XTSiPRDE66Me31wyBFvuRuxbwKWIwGjDm9WlAyc2GbHlctUDMwh9tHdT1/bpD9JlRYMj6tI8syGhoa8N3vfhfr16/H7bffjq985SvYs2dP1Nfs2rUL4+Pj2kdXl75aLxHlp8jTOvmfOXF6fGHB07E4pR1RommqLIHFNPu3V4vJgJXNatbj+KXxqAvb4rmmrQYA8Fr7iJaBiSVXd+oQJSuh4KSurg5GoxH9/f1hn+/v78e8efMivqapqQnLly+H0Rj8TWnlypXo6+uDx+OJ+Bqr1YqKioqwDyIqTIqiaHtO7BHW1+dz5kRkTYTXO2NnKvRkQbTSTteYtrDNbglf2BbP2gVVMBkk9I67cGl0Ou7z2o6TRgYnVBgSCk4sFgvWr1+P/fv3a5+TZRn79+/Hpk2bIr7m+uuvx7lz5yDLsva5M2fOoKmpCRaLJcljE1GhcPtkiD/cl0QYJc7nzInoNxHiZU703JEjLgE8fmlMe37mwrZ47BYTLm9Rg5zDHSMxn1UUhWPEVHASLuvs3LkTe/fuxWOPPYaTJ0/irrvuwtTUFLZv3w4A2LZtG3bt2qU9f9ddd2FkZASf+cxncObMGTzzzDO47777cPfdd6fvV0FEeSs0+AgdJQ7tOYnXaJorYlJHTMec6puIGUx1BYKN1hjNrSJz8ma3AxcHxZ06iU/QXNNWDQA4dDF2Nqff4cak2wejQUKbznFlolyLv45whttvvx2Dg4O499570dfXh7Vr12Lfvn1ak2xnZycMhmDM09raiueeew6f+9znsHr1arS0tOAzn/kMvvjFL6bvV0FEeUuUdCxGA0zG2dM6gJpdCc2q5IvhQObk8uYKSL0O9DvceKN7HNcsqon4vLiMb2GMC/wW15ehzGrCpNuH359S90MlE5xsaKvB3j9dxOH22JkTkTVZWGOP2AdDlI8SDk4AYMeOHdixY0fErx04cGDW5zZt2oRXXnklmbciogInmmFnBh+h9+xMe/35GZxMqZmTujIr1rZW4bm3+nGsazRqcNKpo6xjNEi4oqUCr1wYwcvnh+I+H82GhWrm5OzAJEanPKgujVwmP8e19VSAGEYTUUZFWl0PqD+krYE/yTs9+jadZpvoOakts2JtqxoMROs7mXL7tDJQvMkbcUOxqGYtSKLcUltmxZJ69XWHO6KXds6y34QKEIMTIsqoaW0B2+zMiPicK08ndsS0Tl2ZBesCu0Ve74wcnIisSZXdjAqbOeb3FU2xwsx7ePQSGZzXYpR22AxLhYjBCRFlVKQxYiHfL/8bnlIzJ3VlVlwZuFW4d9yF/pBbhYVoF/5Fsqa1Uvtro0FCS/XshW16XB3Yd3LoYvTg5DwXsFEBYnBCRBk1HeHSPyHfF7ENTaiZk9oyC0qtJixvVC/di5Q96Qxc4KenRNNSVYLaQI9Ic5UNZmNyvxWL4OTN7vGI/wxHpzxaqWkJF7BRAWFwQkQZFbxXZ3b/fb5f/icyJ7Wl6iixVtrpmt3jEbwjJ34WRJIk7YbiWJM98cyvLsG8Cht8shLxTGJtfUtVCUqtSc0/EOUEgxMiyihtdX2kzEkeL2LzywpGpoI9JwCwTjTFRsicBMs6+oKNjYtrAQArm8qTPqMkSdgQ2HcS6Z4d0W+yhCUdKjAMpYkoo6JN6wAhZZ08zJyMOT3aNI0Y010byJy80T0On18O29uiZU50jgV/7PpFaCi34i9XNsZ/OIZrFtXg6RO9EZtieacOFSpmTogoo0TgEXFaJ4/LOmLHSbXdrPWELAksUHN6/DjTP6k96/PL6A7ccaN3Z4nFZMDfXDUflSWxJ3viEX0nRztG4fPLYV87yzt1qEAxOCGijIrVEGvP44bYoYngjhPBaJC0SZvQfSe94y74ZAUWkwGN5basnnN5YznKbSZMefw42TsR9rXzHCOmAsXghIgySldZJx+Dk0DmpHbG5tW1rWpp51hIA6roN2mtLoHBoP8Cv3QwGiRtW+yhkNLOlNuH7jE1m8OyDhUaBidElFGxpnXECntnPpZ1JoM7TkKJTbGh48TBtfW5uVhvQ6C0E3rPzoXApYK1pZaoq+2J8hWDEyLKqGlvYFonQuYkn8s6YjtsbVnkzMm5wUlMuLwAgI6R5G8XTofQTbGKonbxnuWdOlTAGJwQUUbFXF9vzt/19aHbYUPVl1sxv7oEigKcuDQOAOgcFjtOchOcrJ5fCYvJgKFJDy4OqYES19ZTIWNwQkQZ5YzREGvL4/X1Q1EyJ0Awe/J6p9p3ou04SeJ24XSwmoxYE1jqJvadMDihQsbghIgyajrG3Tr2QB9KPo4SazcSl1pnfW3dguANxYqioGskt8EJEHLPTqDvRGyHXdaQ/JI3olxhcEJEGeWMeSux+ltQXpZ1JsO3w4YKTuyMYdTpxYRb7auZX5374ORw+wg8PlnL5jBzQoWIwQkRZdS0Nkoc6W4d9XP5WNYR0zq1ZbMzJ5c3V8BslDA06cGfzw0BAOZV2LQyVS5ctbAakgS0DzvxWvsI/LKCMqsJjRWzz0+U7xicEFFGxSrr5Ouek2mPH1OBM0XqObGZjVjVVAEA+NWxHgD619ZnSmWJGSvmqWf66aFOAOqdOpKU3b0rROnA4ISIMsoZuPgvUkNsvq6vF5M6FpMB5VFu8xWlnT+eGQAALMzRpE6oqwOXAD73Vh8AYBlLOlSgGJwQUcbIsgKXV73vJVLPSb7uORGTOnWllqiZB3EJoNev7hXJ1RhxKNF3Is7EfhMqVAxOiChjQjMikco6tnzNnMToNxHEplgh12UdIBicCFxbT4WKwQkRZUxoo6vNVDg9J9G2w4Zqq7Wjyh68UThXq+tDzau0obWmRPt7Zk6oUDE4IaKMESPCJWZjxAvx7IHMiccvw+eXs3q2WIamou84ESRJ0vpOgPwo6wDB7InFZEBrnpyJKFEMTogoY2LtOJn5eZcvf4ITbcdJeewL80RwUm41oToki5JLIjhZUl8GY5ZvSCZKFwYnRJQxsSZ1AMBqMkD0m4pn84HYDlsXI3MCANctqQMAXN5SkTcju3+9rgUf3rgAX7plRa6PQpS0yDNyRERpEFzAFjk4kSQJJWYjnB4/XJ78y5zE6jkB1NuAf/jxa7CoLvf9JoLNbMS//fWVuT4GUUoYnBBRxjjjBCcAtOAknyZ2hnRM6wg3LqvP9HGI5hyWdYgoY0TAEa3nJPRr+VTWGZ4KZE5KY2dOiCgzGJwQUcaIsk60npPQr8XLnCiKgh+90oGjnaPpO2AEsqxgJBCc1JfzXhqiXGBwQkQZI7IhkS79E/TuOjl+aRxf/eWb2P4/r2U0yzI+7YVfVjesVtuZOSHKBQYnRJQxTj1lHZ2Zk0ujTgBq8PDkkUtpOuFsot+kssQMi4m/RRLlAv/LI6KMiTetA+jPnAxOuLW//v5LF7XsRroN6ZzUIaLMYXBCRBkzHWcJGxBy+V+czElocNIx7MQLb/el4YSziRuJ4+04IaLMYXBCRBnj9MZviNUu/4uTORmYCJZbAGDvny6m44iz6N1xQkSZw+CEiDJGV1lHZ8+JyJx88qbFsBgNONIxmpHJHXEjcZ2OHSdElBkMTogoY7T19TGmdewJ9pysaq7A+9Y2AwC+96cL6Thm+Pswc0KUcwxOiChjtA2xadhzMhjIaNSXWXHnjYsBAPve7EPXiDMdR9UMJ7Adlogyg8EJEWWMnrKOTdsQGz048cuKFjQ0VFhx2bxy3LS8HrKiTu6kk9gOW8ftsEQ5w+CEiDJGZENssaZ1dGROhqfckBXAIAG1gSmaO29cBAD42eEujDu96ToyMydEeYDBCRFlzLSesk4gcHHFyJyIfpOaUiuMBgkAcMPSOqyYVw6nx48fH+pI15G1aZ069pwQ5QyDEyLKmOCtxNEbYsUocayyjghOQu+6kSQJnwj0njz2cjs8Pjnl87q8fky41SZeZk6IcofBCRFlTHBaJ9YSNjVwiVXWiRScAMD71jSjscKKfocbvznek+pxtX4Ts1FChS16QEVEmcXghIgyRgQcevacuGIFJ6IZdkZwYjEZ8A/XtQEA9v7pAhQltZX2Wr9JqRWSJKX0vYgoeQxOiCgjvH4ZXr8aLOi5WydWWWfAETlzAgAfvmYh7BYjTvVN4KVzQ6kcmdthifIEgxMiyojQMo0txT0noTtOZqq0m/GBDa0AUl9pP8TtsER5gcEJEWWEmNQxSIDVFP23Gj23EkfrORE+dv0iGCTgxTOD+MHB9qTLO6LnhJkTotxicEJEGRE6qROrfyP0VuJoQcVQnOBkQa0d2za1AQDu/dVb+OefH4+7Dj/W+zBzQpRbDE6IKCP0TOoAwZKPX1a0HpWZxI3EMxtiQ+3eugpfec9KGA0Snjrajb/5zsvoHE5stb2WOeF2WKKcYnBCRBnh0jGpAwR7ToDIpR2nx4fJwO6RaJkTQN17cudNi/HDj1+D2lILTvY6sPX/vIQ/nB7QfeYhboclygsMTogoI0RZpyRGMyygjgObAltfIzXFDk2o2Qyb2YAya/zdI9ctqcPT//sGrGmtwvi0Fx979DX85+/OQpbj96FwOyxRfmBwQkQZoQUncTInQOyJncFJFwA1a6J390hTZQl+9o/X4kMbF0BRgP/43Rnc+YPDcLhi38EzPMWeE6J8wOCEiDJCz43EQnDXiW/W17RJnQQDBqvJiPv++kr8+22rYTEZsP/UAO5/9mTU5xVF4Z4TojzB4ISIMiJY1olfitEu/4uQOQk2w9qSOscHNrTiOx++CgDw2zf74PNHvoNnfNoLX6D0U8OGWKKcYnBCRBmhZ3W9UBLj8r94O070eMfyelTZzRhzenG4YzTiM0OBrEm5zQSrKf6ZiShzGJwQFTGnx4fRwHhstk2LUeI4DbFA7EVs6QhOTEYD/mJFAwDghbf7Iz4zzO2wRHmDwQlREXv/w3/Gux48gO6x6ay/d9oaYtMQnADAzavmAQCef7sv4rI3seOEkzpEuZdUcPLwww+jra0NNpsNGzduxKFDh3S97vHHH4ckSXj/+9+fzNsSUQKcHh/O9E9izOnFQ8+fycH7J17WiZg5iXGvTiJuWl4Hq8mArpFpnO6fmPX10BuJiSi3Eg5OnnjiCezcuRO7d+/G0aNHsWbNGmzZsgUDA7EXHbW3t+Pzn/88brzxxqQPS0T6ickTAHjq9Ut4u8eR1fdPZlonUuZE3EjcUJFa0GC3mHDjsjoAwPNvzS7tDHJShyhvJBycPPTQQ7jzzjuxfft2rFq1Cnv27IHdbscjjzwS9TV+vx8f/vCH8S//8i9YvHhxSgcmIn1GQnpNFAW4/7fRx2gzQQQaJRYd0zpRyjqyrGhbW1Mt6wDAu1c1AojcdzLM7bBEeSOh4MTj8eDIkSPYvHlz8BsYDNi8eTMOHjwY9XVf+9rX0NDQgI9//OO63sftdsPhcIR9EFFixEKxxgorzEYJfzo7hBfPDGbt/fVuiAVCLv+bUdYZCxnvTUe55S9XNkKSgDe6x9Ezow+H22GJ8kdCwcnQ0BD8fj8aGxvDPt/Y2Ii+vr6Ir3nppZfw/e9/H3v37tX9Pvfffz8qKyu1j9bW1kSOSUQIjsaumFeBO65tAwDc/9tT8OtY454O0151WkdPWccWJTgRzbDVdjMsptT79+vKrFi/oBoA8LuT4dkTboclyh8ZndaZmJjAHXfcgb1796Kurk7363bt2oXx8XHto6urK4OnJCpOoqxTW2bBP/3FUpTbTDjZ68AvX+/OyvsnM63j9EYOTpJdwBbJzZerf7ia2XeibYflAjainEsoOKmrq4PRaER/f/h/1P39/Zg3b96s58+fP4/29nZs3boVJpMJJpMJP/jBD/DrX/8aJpMJ58+fj/g+VqsVFRUVYR9ElJjg9IkF1aUW3P2upQCAB58/HXETa7ol0hArnnHNyJwMTATv1UmXdwdGil+5MIzx6eBdO4PsOSHKGwkFJxaLBevXr8f+/fu1z8myjP3792PTpk2znl+xYgXeeOMNHDt2TPt43/veh3e96104duwYyzVEGTSsZU7UH7Yfva4NzZU29Iy78D9/bs/4+yc1Shwlc5LO4GRRXSmWNZTBJys4cFqdMnT7/JhwqWUo9pwQ5V7CZZ2dO3di7969eOyxx3Dy5EncddddmJqawvbt2wEA27Ztw65duwAANpsNV1xxRdhHVVUVysvLccUVV8Bi4W8CRJkiyhTinhib2YjPb7kMAPDtP5wLm+bJBBFo2HQ0xNqirK/PRHACBKd2ng9M7Yh/FiaDhAqbOa3vRUSJSzg4uf322/HAAw/g3nvvxdq1a3Hs2DHs27dPa5Lt7OxEb29v2g9KRIkZibDx9P1rW7CqqQITbh/+6/dnM/r+wbJO/FFi8cyszEmaFrDNdPPlamnnwKkBuH3+sNuIDQYpre9FRImL/7tGBDt27MCOHTsifu3AgQMxX/voo48m85ZElKBIG08NBglffs9KfOT7r+JHr3Tgo9e1YWFtadrfW1EUOD36p3VKLOqfk2b2wmgNsSkuYJtpdUslGsqtGJhw4+D5Ye3z3A5LlB94tw5REVIUBUNT4WUd4YZldbhpeT28fgX//tzpjLy/2ydDTCzrm9ZR/5w0s6wzMJGZzInBIIUtZBvmdliivMLghKgITXn88PhkAJF/4O66ZQUkCXjmRC+OdY2l/f1D95WkcitxpnpOgPBtsYO8kZgorzA4ISpCoqRTYjZG7PlY2VSB969tAQA8dfRS2t9f9I6YjRLMxvi/zUSa1nH7/NqobyaCk01LalFmNWFgwo3fn1KndrjjhCg/MDghKkLDU/HLFJtXqpmDw+2jCX//r/ziDVy5+zl0Djsjfj2R1fVA5PX1YsOtxWhAZUn6J2isJiPecVk9AODQxREA3HFClC8YnBAVIT3bTje0qWvcT/U5MOHyRn1uJq9fxi9e78aE24ffvhl5Mi+RSR0gOEo87fVDUdRmldCSjiRlZoLm5lXhV3FwxwlRfmBwQlSERqbibzttrLBhQY0dsgK83qm/7+SN7nEtM3LwwnDEZxKZ1AHCm2ZdXrVXZsChboety0BJR3jnZQ0whYwOs+eEKD8wOCEqQkM674nZsFDNnhxuH9H9vV+9EHz2tYsj8PnlWc+IO3L0TOoA4eUf0XeSqR0noSpLzNi0pFb7e07rEOUHBidERUjbDhvnh+2GthoAwGsJ9J28ejGYLZny+PFG9/isZ1wJ9pwYDZJ267AWnGRwUifUu0NKO+w5IcoPDE6IipAo69TFWSp2daDv5PWuUXgjZEBm8vllrYF2Ya0dAPDKhdlZl0RuJBaCTbFqSSibwYnRIMFmNnBahyhPMDghKkLDURawzbSkvgxVdjNcXhlv9zjift+3ex2YdPtQbjPhjmsXAojcdyLKOnp7ToCQcWKPGiRp22EzHJw0VZbg+/+wAd/bdrWue4CIKPMYnBAVIb0bTw0GCesXqNmT13T0nYh+k2vaanD90joAar/KzKzLtNYQq/+GjBLt8j/1tQNZypwAamPsDcvqMv4+RKQPgxOiIjQ8NftenWhE34mefSei32Tj4hpc1liOarsZTo8fJy6F950kU9bRtsRmueeEiPIPgxOiIqMoinYjsZ7pE9F3crhjRNsxEolfVrRlZRsX1cJgkLBxkTrp8sqM0o4IMPQ2xIY+6wrsOsnGtA4R5ScGJ0RFxuHywetXg4x4PScAcOX8SlhMBgxNetAeZeMroC5rc7h8KLOacHlzBQBoY7izghNPEj0nFlHW8cPh8ml3AzFzQjT3MDghKjLiXp0yq0lXg6fVZMSa+ZUAYvediH6T9QurYQrcl3PtYjU4Odw+qgUTQJJlnZAtsaKkU2HT92sgouLC4ISoyCRS0hHWL1T7To7E6DsR2ZGNi2u0zy1vLENNqQXTXj9OXApumdUyJ4mUdULu1xmYULfDMmtCNDcxOCEqMmI7rJ6SjiD6Tl7riJw5kWUFh9qD/SaCJEm4NhCsHDwfLO04k5jWCb38j82wRHMbgxOiIqNlTnRM6gjrA2vsLwxOaWWhUGcGJjDm9KLEbMTqQAlI2BQo7bwSsjl2OsH19UD45X/B4MSm+/VEVDwYnBAVGRFcJHLDbpXdguWNZQCAwx2zSzui32RDWzXMxvDfNkL7Ttw+NSiZTnB9feizTo+fkzpEcxyDE6Iio3c77EzBfSezSzvafpNFNbO+trShDHVlVrh9Mo4Fbjd2JjGtI6b0fUIAACAASURBVJ51ef0YdAS2w1YwOCGaixicEBWZYa0hNrEf7NoNxTMyJ4oSst9kce2s14X2nYh7dpKZ1gkr6zBzQjSnMTghKjIj2nbYxDInVwcyJ292j2tlGQA4PziJoUkPrCbDrH4TQZR2Dl4YAhDsOUlofX3InhM2xBLNbQxOiIqM3nt1ZppfXYLGCiu8fgXHQ8aCRTbkqgXVsJoiZ0LEMrajnWNwef1JLWELK+swOCGa0xicEBWZZEaJAbU8E6nv5FWtpDO730RYXFeK+nIrPD4ZRztHtcxJIgvUREOsw+XDiFP9NTA4IZqbGJwQFRFZVjAa+MFel0S/xtULxQ3Fat+Joih4VSxfWzS730SQJEkbKT5welD7fGLr69USUPeoE4oCGA0SauyJBVhEVBwYnBAVkfFpL/yyeq9OdRI/2EXm5GjHKPyygvZhJwYm3LAYDVi3oCrma0Vp5/enBrTPJTNKLDI/dWUWGAxSQucnouKgv1uNiPKemNSpsJlgMSX+Z48V88pRajFiwu3Dmf4JHO9Se0/WtlbFLdGIpthzA5MAAJvZkFBwMTOQYUmHaO5i5oSoiAQXsCX3g91kNOAqMVLcPqKr30Roq7VjXkVwo2sikzrA7LFjjhETzV0MToiKyEiSC9hCbQhcAniofVRXv4kQuu8ESKykA0QITpg5IZqzGJwQFZGhJG4knklcAviHUwPoGXfBZJBw1cLY/SaC6DsBElvABswOZhp4rw7RnMXghKiIiLJOTQKX/s20dkEVjAYJk271ZuHV8yt1l2iuDdkgm8ikTqTnmTkhmrsYnBAVEVHWSeTSv5nsFhMub67Q/j7SyvpoFtTY0VypZjwSLetYTQZIIf2zDE6I5i4GJ0RFRNsOm0LPCRDsOwEiX/YXjSRJuDZQ2kk0cyJJUlhAw+CEaO5icEJURIYD9+rUpDjpIvpOjIbg1li93r2yEQCwsLY04fcNC044rUM0Z3HPCVEREZmTuhQzJzcur8ea1iqsnV+JMmtiv0381RXz8PQ/3YDljeUJv6+NmRMiAoMToqKijRKn0HMCAGVWE3519/VJvVaSJFzREvn24nhEKajUYkRpgkERERUPlnWIioRfVrQL82pTmNbJJTF+zKwJ0dzG4ISoSIw6PVDUa3VQbTfn9jBJEmUdBidEcxuDE6IiIUo61XYzTMbC/E9blHW4gI1obivM38GIaJahwAK22gKecilh5oSIwOCEqGik416dXKuwqeWoxgpmTojmMrbDExUJbYw4xUmdXPr4jYtQYjHitvXzc30UIsohBidERWK4CDInyxvL8X+/7/JcH4OIcoxlHaIiIS79K9QxYiIigcEJUZEohrIOERHA4ISoaAQbYpk5IaLCxuCEqEgMTYlRYmZOiKiwMTghKhIic1JbwA2xREQAgxOiouD1yxhzegEU9hI2IiKAwQlRURgNXPhnkICqksK8V4eISGBwQlQExKROTakFBoOU49MQEaWGwQlRERDBCXecEFExYHBCVASGA5M6hbwdlohIYHBCVAS0zAnHiImoCDA4ISoCHCMmomLC4ISoCAxrC9jYc0JEhY/BCVGee+C507j2vv24MDgZ9ZnQaR0iokKXVHDy8MMPo62tDTabDRs3bsShQ4eiPrt3717ceOONqK6uRnV1NTZv3hzzeSIKGphw4b9fPI8+hwuPvtwe9bnhKV76R0TFI+Hg5IknnsDOnTuxe/duHD16FGvWrMGWLVswMDAQ8fkDBw7ggx/8IP7whz/g4MGDaG1txc0334zu7u6UD09U7H76ahe8fgUA8KtjPXB5/RGfG55kWYeIikfCwclDDz2EO++8E9u3b8eqVauwZ88e2O12PPLIIxGf//GPf4xPf/rTWLt2LVasWIHvfe97kGUZ+/fvT/nwRMXM45Pxo1c7AABGg4TxaS9+d7I/4rPDUyzrEFHxSCg48Xg8OHLkCDZv3hz8BgYDNm/ejIMHD+r6Hk6nE16vFzU1NVGfcbvdcDgcYR9Ec82zb/RicMKNhnIrPnHjIgDAzw5fmvWc2+fHhMsHAKjjEjYiKgIJBSdDQ0Pw+/1obGwM+3xjYyP6+vp0fY8vfvGLaG5uDgtwZrr//vtRWVmpfbS2tiZyTKKi8D+BHpOPXLsQH7x6AQDgT2cH0Ts+Hfbc6JR64Z/JIKGixJTVMxIRZUJWp3W+8Y1v4PHHH8cvfvEL2Gy2qM/t2rUL4+Pj2kdXV1cWT0mUe693juJ41xgsRgM+eM0CtNWV4pq2GigK8NTR8H6tocngdlhJ4r06RFT4EgpO6urqYDQa0d8fXvfu7+/HvHnzYr72gQcewDe+8Q08//zzWL16dcxnrVYrKioqwj6I5hIxmbN1TTPqy9VSzW0b5gMAfn64C4qiaM9qC9jYDEtERSKh4MRisWD9+vVhzayiuXXTpk1RX/fv//7v+PrXv459+/Zhw4YNyZ+WaA7od7jwzIleAMBHr2vTPn/rlU2wW4xoH3bicMeo9nltARubYYmoSCRc1tm5cyf27t2Lxx57DCdPnsRdd92FqakpbN++HQCwbds27Nq1S3v+m9/8Ju655x488sgjaGtrQ19fH/r6+jA5GX2hFNFc9uNXOuCTFWxYWI0r51dqny+1mvCeK5sAqNkTgffqEFGxSTg4uf322/HAAw/g3nvvxdq1a3Hs2DHs27dPa5Lt7OxEb2+v9vx3vvMdeDwe3HbbbWhqatI+HnjggfT9KoiKhNvnx49f7QQAbL9+0ayv/916tbTzzIleOD3qhA7HiImo2CTV2r9jxw7s2LEj4tcOHDgQ9vft7e3JvAXRnPT08V4MT3nQVGnDzZc3zvr6NYtqsLDWjo5hJ559ow+3rZ+vLWCrY88JERUJ3q1DlCcURcH/vHwRgDo+bDbO/s9TkiTcdlWwMRYINsQyc0JExYLBCVGeONIxije7HbCa1PHhaP52/XxIEvDqxRF0DjsxJHpOGJwQUZFgcEKUJ8TStfevbYmZBWmuKsENS+sAAE8e6eIoMREVHQYnRHmgd3wa+95Utyz/Q8j4cDS3BRpjnzxySVvCxswJERUL7romygM/PNgBv6xg46IarGqOv3Rwy+XzUG4zoWfcpX2Oo8REVCyYOSHKsWmPHz89FH18OBKb2Yj3rWnW/t5iNKDMyj9rEFFxYHBClGP//eJ5jDq9aK0pweaVDbpf93cbghdi1pbxXh0iKh4MTohyqGdsGnv+eB4A8MW/WgFThPHhaNbMr8SyhjIAHCMmouLC4IQoh7657xRcXhnXtNXg1sBqer0kScLtV6vZk5aqkkwcj4goJ1ikpoLk9Pjwdo8D014/3F4ZLl/4//plBa01JVjeWI6FtaUwGvKv5HGkYxS/OtYDSQLu3boqqbLMP1zXBrPRgJuW12fghEREucHghArSR773Ko52jul61mIyYEl9GZY3lmF5YzmWN5Zj4+IaVNjMGT5ldLKs4Gu/eQuAel/OFS2VcV4Rmdlo0DV6TERUSBicUMFxenx4vUsNTC5rLIfNYoTVZIDNHPxfAGgfmsLZgQm4vDJO9jpwstehfY95FTb84u7r0FSZm3LIL17vxvFL4yizmvD5LZfl5AxERPmKwQkVnLP9k1AUoK7Mguc+d1PMZ2VZwaXRaZzpn8Dp/gmc7Z/AKxdG0Odw4c4fHMbP/nET7Jbs/mcw5fbhm/tOAQDuftdSNJTbsvr+RET5jsEJFZzTfRMAgMvmlcd91mCQsKDWjgW1dmxepd7y2zXixPsf/jPe7Hbg8z8/jv/zwatgyGJPyncOnMfAhBsLauz42A1tWXtfIqJCwWkdKjinRHDSGH+TaiStNXbsuWM9zEYJz77Rh2/tP5vO48XUNeLEd/90AQDw5feshNVkzNp7ExEVCgYnVHBO96u9Iyt0ZE6iubqtBvf99ZUAgP93/1n85nhPWs4Wzzd+ewoen4xrF9dgy+WNWXlPIqJCw+CECk4iZZ1Y/m5DKz5502IAwOd/fhzHu/RN/yTr1QvDeOaNXhgk4N73Xs6NrkREUTA4oYIyNOnG0KQHkgQsayxL+ft98a9W4C9WNMDtk3HnDw6jL+QivXTyywq+9vTbAIDbr16g63I/IqK5isEJFRSRNVlQY0/LlI3RIOE//34tljeWYWDCjU/+8DCmPf6IzzpcXlwYnITXLyf8Pr94vRtv9ThQbjXhn29enuqxiYiKGqd1qKAEm2FTK+mEKreZ8b1tV+N/PfwSTlwaxz/99CiuWliNnrFp9Iy50DM2je7RaUy4fQCArWua8V8fXKf7+yuKgu+/dBEAcNe7lqCuzJq2sxMRFSMGJ1RQTvel3gwbyYJaO/Z8ZD0+/L1X8buTA/jdyYGozz59ogefv3k5FtaW6vreRzvHcLLXAavJgA9dsyBdRyYiKloMTqigBJth09+zsXFxLf7z79fh8dc6UV9mRXNVCVqqS9T/rbKhqbIEd//kKA6cHsRjL3fg3q2rdH3fH73SAUDNuFTZeXswEVE8DE6oYMiygjP9kwBSn9SJ5tbVTbh1dfTbgT96XRsOnB7Ezw93YefNy1Fmjf2f0MiUB8+c6AUAfOTahWk9KxFRsWJwQgWjc8SJaa8fFpMBbbX2nJzhpmX1WFxXigtDU3jq6CVs29QW8/mfH+6Cxy/jypZKrJmf3OV+RIVIURT4fD74/ZEbzKk4GI1GmEymtK9GYHBCBeN0v1rSWdZQBpMxN4NmBoOEj17fhnt/9RYefbkdH9m4MOrqe1lW8ONXOwEAH7l2Afea0Jzh8XjQ29sLp9OZ66NQFtjtdjQ1NcFiSV/ZmsEJFYx0LV9L1d9cNR//z77TuDA4hRfPDuKdlzVEfO7Fs4PoHHGi3GbC1jXNWT4lUW7IsoyLFy/CaDSiubkZFouFgXmRUhQFHo8Hg4ODuHjxIpYtWwaDIT1/cGRwQgVDBCfpntRJVJnVhL/b0IpH/nwRj77cHjU4+dEratbktvXzs37zMVGueDweyLKM1tZW2O25Kb9S9pSUlMBsNqOjowMejwc2W3puWecSNgIAeHwyZFlJ+/d99o1e7D/Zn5bvdSowRpyJSZ1Ebdu0EJIEHDg9iAuDk7O+3j02jd+fUn/dH97IRliae9L1J2jKf5n4/5r/9hC6RpzY8K8vYOfPjqX1+57qc+DTPz6KT/7wCAYn3Cl9L5fXj/ZhtX6d68wJALTVleIvAhmTHxzsmPX1n77aCVkBNi2uxdKG1NfsExHNJQxOCE8d7YbD5cMzb/TC6fGl7fs+9rL6Q9svK/hditmTcwOT8MsKquxmNJTnx4bVj17fBkCdyJlwebXPe3wyHn+tCwBwxyZmTej/b+/Ow5q68v+Bvy8hgbAGUPZdcANFBcG4UsXBtnbEbs48tmDH0dZKK1VrbX8quGJtqXu11p+o7Vi3jtrqiEUqtCoKuKIgIqJQFVCUfQkk5/tH5GpkMVE0wXxez5NHcu+59558gsmHc849hxCiKUpOCA5eUM7D0SBnyLh2r13OWV7TgL1nbvDPD10seqrz5Tw0bb2uDK4b7NUJXrZmqJbJsSvjL377oYtFuFNVD1tzI4zsaafFGhJCdJW7uztWrFih7WroLEpO9Ny1O9X8ejUAkHq1tF3Ou+tUIWob5Hwrx7Erd1DxUOuCpppuI9b2nToP4zgOEwa6AwC2pF7jx+w0zQj7j0BXCLV0yzMh5MWWnJwMjuNQVlam7ao8E/TJqecOXlC2aIgMlb8KqXlPn5woFIwfhxEV0hVetmZokDMcudT6ejWPc0lHbiN+1Ov9nGBubIjrpTVIvlyC3OJKnMy/C4EBh38Gumi7eoQQHSOTybRdBRVNk+XpGkpO9FzC/S6dfw/2AABk3ihXGT/xJJIvl6Dgbg0sjA0R1tcRo3zs71/rybt2ntWCf0/LRGSIf/RXJiHxx67xrSYjutvCwVKszaoRohMYY6iRNWrlwZhmdyAGBwfjo48+QlRUFKysrGBnZ4fvv/8e1dXVeO+992Bubg4vLy8cPHgQACCXyzFx4kR4eHhALBajW7duWLlypco5J0yYgLCwMCxevBiOjo7o1q1bi9feuHEjJBIJkpKSACjni4mNjeXP7efnh927dwMArl27hpdeegkAYGVlpWzFnTDhsccBD1pcDh48CH9/fxgZGeHo0aMaxel5oMkX9NiNslqc+6scHKcc3Hkg8xaul9Yg/dpdDO/+5GMlmgbCvh3gAhORIUb52mPNkStIzrmNWpkcYpFAo/OV1chQXKG826ernW4lJwAQLnXHxqP5+DP3Dj9mhwbCEqJU2yBHz3mHtHLtrAWhGs8xtGXLFsyaNQtpaWnYsWMHpkyZgj179mDs2LH44osvsHz5crz77rsoKCiAUCiEs7Mzdu3aBRsbGxw/fhyTJ0+Gg4MD3n77bf6cSUlJsLCwQGJiYovXXLZsGZYtW4bffvsNgYGBAIDY2Fj8+OOPWL9+Pby9vfHHH3/gnXfeQefOnTF48GD8/PPPeOONN5CTkwMLCwuIxeLHHjds2DD+mrNnz8bXX38NT09PWFlZaRraZ46SEz3W1JLR380atubGkHra4HppDVLzSp84Obl6uwopl2+D4x58Qfs4WsBJIsaNslr8kXsbofdbUtTV1KXjJBHD3Fj4RPV6llysTRDSww6JWcWobZDD3cYEg7p00na1CCFPwM/PD3PmzAEAfP7551i6dCk6deqESZMmAQDmzZuHdevW4fz58xgwYADmz5/PH+vh4YHU1FTs3LlTJTkxNTXFxo0bW5ze/bPPPsMPP/yAlJQU+Pj4AADq6+uxZMkSHD58GFKpFADg6emJo0eP4rvvvsOwYcNgbW0NALC1tYVEIlH7uCYLFizAyJEj2y1u7Y2SEz3W1KUzyleZLEi72GB7euFTDYr94X63xkvdbOFmYwpAOXA01Mcem47l49DFIo2TE12ZGbYt7w1yR2LWg0nXWltvhxB9IxYKkLUgVGvX1lTv3r35nwUCAWxsbNCrVy9+m52d8g+3khLlGLq1a9di06ZNKCgoQG1tLWQyGfr06aNyzl69erWYmMTFxaG6uhoZGRnw9PTkt1+5cgU1NTXNkgeZTIa+ffu2WndNjgsICGj1PLqAkhM9VVJZh4zryi4IPjnxtAEAXLxZgfKaBliaaNZKUV3fiN33b6kNf6RbY5SvMjk5nFWMBrlCo7tYdHUw7MOknjYY4t0J10tr8FaAs7arQ4jO4DiuQy3fIBSqfu5xHKeyrWkqA4VCge3bt2PmzJmIi4uDVCqFubk5vvrqK5w8eVLlHKampi1ea8iQIThw4AB27tyJ2bNn89urqpSzTh84cABOTk4qxxgZtT7PkybHtVYnXdFxfmNIuzp0sRiMAX4uEjhKlH2VthbG6NLZFHm3q3EyvxR/07CF479nbqCyvhEenUwx1Luzyj5/Nyt0MhPhTpUMJ66WYsgj+9uSw09br7vJCcdx+GFikLarQQh5jo4dO4aBAwfiww8/5Lfl5eWpfXxgYCAiIyMxatQoGBoaYubMmQCAnj17wsjICAUFBSpdMQ9raomRy+X8NnWO6ygoOdFTTV06L/uqJiDSLjbIu12N43maJSeMMWw9fg0A8O6A5t0aAgMOI3va46e0AiRcKFI7OWGM4XKx8q+B7jqwpg4hhDTx9vbG1q1bcejQIXh4eOCHH35Aeno6PDw81D7HwIED8b///Q8vv/wyDA0NERUVBXNzc8ycOROffPIJFAoFBg8ejPLychw7dgwWFhaIiIiAm5sbOI7D/v378corr0AsFqt1XEdBtxLroXvVMpy4ehdAC8mJp3Ig5wkNx52k5pUit6QKJiIB3mylW6Op++jQxWLI1Vxk8EZZLarqGyEUcPDsrNvNkIQQ/fL+++/j9ddfx7hx4xAUFITS0lKVVhR1DR48GAcOHMCcOXOwevVqAMDChQsxd+5cxMbGokePHhg1ahQOHDjAJz5OTk6YP38+Zs+eDTs7O0RGRqp1XEfBMU1vBNeCiooKWFpaory8HBYW9Nfz09qZXohZP59HDwcLHJw2RGVfaVU9/BcdBgCcmhMCGzP11rF5/4cMHLpYjHcGuGJRWK8Wy8gaFfBflIjKukbs/kCKAHfrx543KbsYE7dkoLu9ORKihqpVF0KI9tTV1SE/Px8eHh4wNjbWdnXIc9DWe/6k39/UcqKHmtbSecW3ebeNjZkRf1fMyfy7ap3vRlktf6dKhNS91XIiQwOM6K5cyVfdtXY6wmBYQggh7YuSEz1TUdeAo1fuAABe7tXymJIB9+/aOZ53R61z/njiOhQMGNjFBt6PmSStqWsn4WKRWrM35lByQggheoeSEz3ze3YJGuQMXrZm8LJt+Qtf2kWZnKizzk5dgxzb0woAABH3F8Fry9CunWEsNEDh3Vpk3ap4bPmOMMcJIYSQ9kXJiZ452MpdOg8b4GEDjgPyblejpKKuzfP9fPov3KtpgJNEzHfZtMVEZIhhXZV36hx6zFo7skYF8m4r79TRxWnrCSGEPBuUnOiR6vpGJOfcBvCge6UlliZC+DgqBy61NVvs3WoZvjqUAwCYONgDhmpOrPZw105brt6pQqOCwdzIEE4SWkSPEEL0BSUneiQ55zbqGxVwtTZBT4e2R003zRbbVtdO7P+yUVbTgO725s1mhG3L8O52MDTgcLm4im8ZaUlTl05Xe3N+VkZCCCEvPkpO9MjDXTqP+7Lnx5200nKSln8Xu04pp6pfPLaX2q0mAGApFmKgl3I+lbbu2qE7dQghRD9RcqIn6hrkOHJJuVBVW106Tfq7W0NgwOF6aQ1ultWq7GuQKzBnbyYA4J+BLvB303y57VAf5eJZhy4Wt1qGBsMSQoh+ouRET/yZewfVMjkcLI3h5yx5bHlzYyF6OVkCaN618/+P5uNycRWsTUX4bFT3J6rPyJ524DjgXGEZErOKUVpV36wMfxsxDYYlhBC9Qmvr6IErJVVY8r9sAECoj32zdW9aI+1ig7OFZUi9Woo3/JVT0hfercGKw5cBAP/vlR6QmDRfBlwdtubGCHCzQvq1e5i0NeP+NiP0cLBADwcLeNma4cb9FhtaU4cQQvQLJScvuMNZxYjacRZV9Y1wsDTGxMHqr68g9bTBuuQ8pOaVgjEGjuMw/9eLqGtQIMjDGq/3c3r8SdoQ/ZoPvk2+gqybFbhWWoOSynqUVN5GyuXbfBl7C2NYmgjbOAshhJC2TJgwAWVlZdi7d6+2q6I2Sk5eUAoFw5ojV/BNorKVI9DDGt+O74dOaq6VAwAB7lYQCjjcKKtF4d1aXCqqwOHsEggFHBaP9X3qO2h8nSzx7Xh/AMrbnC8VVSL7VgX/yL9TjX8EujzVNQgh5FmRyWQQiZ6s9bgjep6vl8acvICq6hvx4X9O84lJuNQN//l3kEaJCaCcMK2Pi3J8StKlYsT8chEAMHmoZ6uzyz4pUyND+LtZ4Z0Bblg8thf+++EgnJn3N0SFdG3X6xBCnjPGAFm1dh4armsbHByMyMhIREZGwtLSEp06dcLcuXP5pTbc3d2xcOFChIeHw8LCApMnTwYAZGZmYvjw4RCLxbCxscHkyZNRVfVgmoTk5GQEBgbC1NQUEokEgwYNwvXr1/n9+/btQ79+/WBsbAxPT0/Mnz8fjY2N/P6ysjK8//77sLOzg7GxMXx9fbF//34AQExMDPr06aPyOlasWAF3d3d+/5YtW7Bv3z5wHAeO45CcnKxWvSdMmICwsDAsXrwYjo6O6Natm0bxfBrUcvKCuV5ajUlbM3C5uAoigQEWjPHBPwJdn/h8Uk8bpF+7h6UHL6G+UQFnKzEiX/JuxxoTQl5oDTXAEkftXPuLm4DIVKNDtmzZgokTJyItLQ0ZGRmYPHkyXF1dMWnSJADA119/jXnz5iE6OhoAUF1djdDQUEilUqSnp6OkpAT//ve/ERkZic2bN6OxsRFhYWGYNGkSfvrpJ8hkMqSlpfEtz3/++SfCw8OxatUqDBkyBHl5eXzSEx0dDYVCgZdffhmVlZX48ccf0aVLF2RlZUEgEKj1embOnIns7GxUVFQgPj4eAGBtbf3YejdJSkqChYUFEhMTNYrj03qi5GTt2rX46quvUFRUBD8/P6xevRqBgYGtlt+1axfmzp2La9euwdvbG19++SVeeeWVJ640UVUja8T10hpcuFGOhfuzUFHXCFtzI6x7x/+JbvN92IAuNlj1+xXUNyoAAAvH+EIsUu8/BSGEdDQuLi5Yvnw5OI5Dt27dkJmZieXLl/PJyfDhwzFjxgy+/Pfff4+6ujps3boVpqbKRGjNmjV47bXX8OWXX0IoFKK8vByjR49Gly5dAAA9evTgj58/fz5mz56NiIgIAICnpycWLlyIWbNmITo6GocPH0ZaWhqys7PRtWtXvoy6zMzMIBaLUV9fD3v7B9NIbNmypc1629kpp3swNTXFxo0bn3v3lcbJyY4dOzB9+nSsX78eQUFBWLFiBUJDQ5GTkwNb2+Zrqxw/fhz//Oc/ERsbi9GjR2Pbtm0ICwvD6dOn4evr2y4vQlc1yBW4VVaHv8pqcONeLf66V4sbZbW4WVYLBWMwFRlCLBI8+NdIABORIYyFAgg4wMCAgwHHQWDAwYADDDgODMCtsjpcv1uNgtIaXCutwZ1HbsPt4yLBd+/6w87C+KlfQz9XK4gMDSBrVGCUjz1eUmP9HEII4QlNlC0Y2rq2hgYMGKAynk4qlSIuLg5yuRwAEBAQoFI+Ozsbfn5+/Bc8AAwaNAgKhQI5OTkYOnQoJkyYgNDQUIwcORIhISF4++234eDgAAA4d+4cjh07hsWLF/PHy+Vy1NXVoaamBmfPnoWzszOfmLSXx9W7KTnp1auXVsbVaJycfPPNN5g0aRLee+89AMD69etx4MABbNq0CbNnz25WfuXKlRg1ahQ+/fRTAMDChQuRmJiINWvWYP369U9Z/adz8WY57lTJUFXXiKr6BlTWNaKqvlH5ei23GAAAEw5JREFUb10jqmSNEAkMIBYJYCIUwMTIECYiAUxEAoiFAjAGlNXKUFbTgLLaBpTXNPDP71bLUFxRB4VmXZ5PTGIihJu1CQZ6dUJUiDeMDNundcNYKMCEge74M/cOov/es13OSQjRIxyncdeKLnv4y1xd8fHx+Pjjj5GQkIAdO3Zgzpw5SExMxIABA1BVVYX58+fj9ddfb3acsbExxOK21xUzMDDgx8Q0aWho0LiOrXmS19seNEpOZDIZTp06hc8//5zfZmBggJCQEKSmprZ4TGpqKqZPn66yLTQ0tM1bmurr61Ff/6A1oKKiQpNqqm32z5nIvFH+TM7dRGRoAGeJGE5WYjhbieF0/2dDAwPUyBpRI5OjRiZHdX3Tz42obVBAwRgUCgYFY5ArAMYY5IyBMcDOwghuNqZwtTaBu40pXG1MYCl+drfbfvFKj8cXIoSQF8DJkydVnp84cQLe3t6tjvHo0aMHNm/ejOrqav6L/NixYzAwMFAZQNq3b1/07dsXn3/+OaRSKbZt24YBAwagX79+yMnJgZeXV4vn7927N/766y9cvny5xdaTzp07o6ioiJ/uAQDOnj2rUkYkEvEtP5rWW1s0Sk7u3LkDuVzON/c0sbOzw6VLl1o8pqioqMXyRUWtr6kSGxuL+fPna1K1J+Jlawa5gsHM2BDmRoYwMzaEmZEhzI2FMDdWtpI0yhmfNDQlErUNyp85ABITESzFQkhMhJCIhbAybXougqPEGJ1MjdSe9IwQQoh2FRQUYPr06Xj//fdx+vRprF69GnFxca2WHz9+PKKjoxEREYGYmBjcvn0bH330Ed59913Y2dkhPz8fGzZswN///nc4OjoiJycHubm5CA8PBwDMmzcPo0ePhqurK958800YGBjg3LlzuHDhAhYtWoRhw4Zh6NCheOONN/DNN9/Ay8sLly5dAsdxGDVqFIKDg3H79m0sW7YMb775JhISEnDw4EFYWDyYvNLd3R2HDh1CTk4ObGxsYGlp+dh6ax3TwI0bNxgAdvz4cZXtn376KQsMDGzxGKFQyLZt26aybe3atczW1rbV69TV1bHy8nL+UVhYyACw8vJyTapLCCHkOautrWVZWVmstrZW21XR2LBhw9iHH37IPvjgA2ZhYcGsrKzYF198wRQKBWOMMTc3N7Z8+fJmx50/f5699NJLzNjYmFlbW7NJkyaxyspKxhhjRUVFLCwsjDk4ODCRSMTc3NzYvHnzmFwu549PSEhgAwcOZGKxmFlYWLDAwEC2YcMGfn9paSl77733mI2NDTM2Nma+vr5s//79/P5169YxFxcXZmpqysLDw9nixYuZm5sbv7+kpISNHDmSmZmZMQDsyJEjj603Y4xFRESwMWPGPDZubb3n5eXlT/T9zTGm/o3gMpkMJiYm2L17N8LCwvjtERERKCsrw759+5od4+rqiunTpyMqKorfFh0djb179+LcuXNqXbeiogKWlpYoLy9XyQYJIYTolrq6OuTn58PDwwPGxk8/KP95Cg4ORp8+fbBixQptV6VDaes9f9Lvb40mYROJRPD390dSUhK/TaFQICkpCVKptMVjpFKpSnkASExMbLU8IYQQQvSbxnfrTJ8+HREREQgICEBgYCBWrFiB6upq/u6d8PBwODk5ITY2FgAwbdo0DBs2DHFxcXj11Vexfft2ZGRkYMOGDe37SgghhBDyQtA4ORk3bhxu376NefPmoaioCH369EFCQgI/gKagoAAGBg8aZAYOHIht27Zhzpw5+OKLL+Dt7Y29e/e+8HOcEEII6ViapnUn2qfRmBNtoTEnhBDSMXTkMSfkyWh9zAkhhBCijg7wdy9pJ8/ivabkhBBCSLsRCpUTQtbU1Gi5JuR5aXqvm9779kCrEhNCCGk3AoEAEokEJSUlAAATExOVtWrIi4MxhpqaGpSUlEAikai9UrI6KDkhhBDSrppWv21KUMiLTSKRqKx43B4oOSGEENKuOI6Dg4MDbG1t23UROqJ7hEJhu7aYNKHkhBBCyDMhEAieyRcXefHRgFhCCCGE6BRKTgghhBCiUyg5IYQQQohO6RBjTpomeKmoqNByTQghhBCirqbvbU0nausQyUllZSUAwMXFRcs1IYQQQoimKisrYWlpqXb5DrG2jkKhwM2bN2Fubt5sMp+Kigq4uLigsLCQ1t1pA8VJPRQn9VCc1ENxUg/FST0dMU6MMVRWVsLR0VFlUeDH6RAtJwYGBnB2dm6zjIWFRYd5s7SJ4qQeipN6KE7qoTiph+Kkno4WJ01aTJrQgFhCCCGE6BRKTgghhBCiUwQxMTEx2q7E0xIIBAgODoahYYfopdIaipN6KE7qoTiph+KkHoqTevQlTh1iQCwhhBBC9Ad16xBCCCFEp1ByQgghhBCdQskJIYQQQnQKJSeEEEII0SkdPjlZu3Yt3N3dYWxsjKCgIKSlpWm7Slr1xx9/4LXXXoOjoyM4jsPevXtV9jPGMG/ePDg4OEAsFiMkJAS5ublaqq32xMbGon///jA3N4etrS3CwsKQk5OjUqaurg5Tp06FjY0NzMzM8MYbb6C4uFhLNdaOdevWoXfv3vykT1KpFAcPHuT3U4yaW7p0KTiOQ1RUFL+N4gTExMSA4ziVR/fu3fn9FKMHbty4gXfeeQc2NjYQi8Xo1asXMjIy+P368DneoZOTHTt2YPr06YiOjsbp06fh5+eH0NBQlJSUaLtqWlNdXQ0/Pz+sXbu2xf3Lli3DqlWrsH79epw8eRKmpqYIDQ1FXV3dc66pdqWkpGDq1Kk4ceIEEhMT0dDQgL/97W+orq7my3zyySf49ddfsWvXLqSkpODmzZt4/fXXtVjr58/Z2RlLly7FqVOnkJGRgeHDh2PMmDG4ePEiAIrRo9LT0/Hdd9+hd+/eKtspTko+Pj64desW/zh69Ci/j2KkdO/ePQwaNAhCoRAHDx5EVlYW4uLiYGVlxZfRi89x1oEFBgayqVOn8s/lcjlzdHRksbGxWqyV7gDA9uzZwz9XKBTM3t6effXVV/y2srIyZmRkxH766SdtVFFnlJSUMAAsJSWFMaaMi1AoZLt27eLLZGdnMwAsNTVVW9XUCVZWVmzjxo0Uo0dUVlYyb29vlpiYyIYNG8amTZvGGKPfpSbR0dHMz8+vxX0Uowc+++wzNnjw4Fb368vneIdtOZHJZDh16hRCQkL4bQYGBggJCUFqaqoWa6a78vPzUVRUpBIzS0tLBAUF6X3MysvLAQDW1tYAgFOnTqGhoUElVt27d4erq6vexkoul2P79u2orq6GVCqlGD1i6tSpePXVV1XiAdDv0sNyc3Ph6OgIT09PjB8/HgUFBQAoRg/75ZdfEBAQgLfeegu2trbo27cvvv/+e36/vnyOd9jk5M6dO5DL5bCzs1PZbmdnh6KiIi3VSrc1xYVipkqhUCAqKgqDBg2Cr68vAGWsRCIRJBKJSll9jFVmZibMzMxgZGSEDz74AHv27EHPnj0pRg/Zvn07Tp8+jdjY2Gb7KE5KQUFB2Lx5MxISErBu3Trk5+djyJAhqKyspBg95OrVq1i3bh28vb1x6NAhTJkyBR9//DG2bNkCQH8+x1/s+W8JUcPUqVNx4cIFlf5v8kC3bt1w9uxZlJeXY/fu3YiIiEBKSoq2q6UzCgsLMW3aNCQmJsLY2Fjb1dFZL7/8Mv9z7969ERQUBDc3N+zcuRNisViLNdMtCoUCAQEBWLJkCQCgb9++uHDhAtavX4+IiAgt1+756bAtJ506dYJAIGg2mru4uBj29vZaqpVua4oLxeyByMhI7N+/H0eOHIGzszO/3d7eHjKZDGVlZSrl9TFWIpEIXl5e8Pf3R2xsLPz8/LBy5UqK0X2nTp1CSUkJ+vXrB0NDQxgaGiIlJQWrVq2CoaEh7OzsKE4tkEgk6Nq1K65cuUK/Sw9xcHBAz549Vbb16NGD7wLTl8/xDpuciEQi+Pv7Iykpid+mUCiQlJQEqVSqxZrpLg8PD9jb26vErKKiAidPntS7mDHGEBkZiT179uD333+Hh4eHyn5/f38IhUKVWOXk5KCgoEDvYvUohUKB+vp6itF9I0aMQGZmJs6ePcs/AgICMH78eP5nilNzVVVVyMvLg4ODA/0uPWTQoEHNpjW4fPky3NzcAOjR57i2R+Q+je3btzMjIyO2efNmlpWVxSZPnswkEgkrKirSdtW0prKykp05c4adOXOGAWDffPMNO3PmDLt+/TpjjLGlS5cyiUTC9u3bx86fP8/GjBnDPDw8WG1trZZr/nxNmTKFWVpasuTkZHbr1i3+UVNTw5f54IMPmKurK/v9999ZRkYGk0qlTCqVarHWz9/s2bNZSkoKy8/PZ+fPn2ezZ89mHMex3377jTFGMWrNw3frMEZxYoyxGTNmsOTkZJafn8+OHTvGQkJCWKdOnVhJSQljjGLUJC0tjRkaGrLFixez3Nxc9p///IeZmJiwH3/8kS+jD5/jHTo5YYyx1atXM1dXVyYSiVhgYCA7ceKEtqukVUeOHGEAmj0iIiIYY8rb0ObOncvs7OyYkZERGzFiBMvJydFupbWgpRgBYPHx8XyZ2tpa9uGHHzIrKytmYmLCxo4dy27duqW9SmvBv/71L+bm5sZEIhHr3LkzGzFiBJ+YMEYxas2jyQnFibFx48YxBwcHJhKJmJOTExs3bhy7cuUKv59i9MCvv/7KfH19mZGREevevTvbsGGDyn59+BznGGNMO202hBBCCCHNddgxJ4QQQgh5MVFyQgghhBCdQskJIYQQQnQKJSeEEEII0SmUnBBCCCFEp1ByQgghhBCdQskJIYQQQnQKJSeEEEII0SmUnBCiZxhjmDx5MqytrcFxHCQSCaKiotQ+fvPmzc2Wtn9UTEwM+vTp87RVJYToKUNtV4AQ8nwlJCRg8+bNSE5OhqenJwwMDGjJegAcx2HPnj0ICwvTdlUI0XuUnBCiZ5pWgh04cKC2q0IIIS2ibh1C9MiECRPw0UcfoaCgABzHwd3dHcHBwSrdOvX19Zg5cyacnJxgamqKoKAgJCcnt3nepUuXws7ODubm5pg4cSLq6uo0qtemTZvg4+MDIyMjODg4IDIykt9XUFCAMWPGwMzMDBYWFnj77bdRXFys8poebe2IiopCcHAw/zw4OBgff/wxZs2aBWtra9jb2yMmJobf7+7uDgAYO3YsHxdCiPZQckKIHlm5ciUWLFgAZ2dn3Lp1C+np6c3KREZGIjU1Fdu3b8f58+fx1ltvYdSoUcjNzW3xnDt37kRMTAyWLFmCjIwMODg44Ntvv1W7TuvWrcPUqVMxefJkZGZm4pdffoGXlxcAQKFQYMyYMbh79y5SUlKQmJiIq1evYty4cRq/9i1btsDU1BQnT57EsmXLsGDBAiQmJgIAH4f4+PhW40IIeX6oW4cQPWJpaQlzc3MIBALY29s3219QUID4+HgUFBTA0dERADBz5kwkJCQgPj4eS5YsaXbMihUrMHHiREycOBEAsGjRIhw+fFjt1pNFixZhxowZmDZtGr+tf//+AICkpCRkZmYiPz8fLi4uAICtW7fCx8cH6enpfDl19O7dG9HR0QAAb29vrFmzBklJSRg5ciQ6d+4MAJBIJC3GhRDyfFHLCSGEl5mZCblcjq5du8LMzIx/pKSkIC8vr8VjsrOzERQUpLJNKpWqdb2SkhLcvHkTI0aMaPXcLi4ufGICAD179oREIkF2draar0qpd+/eKs8dHBxQUlKi0TkIIc8HtZwQQnhVVVUQCAQ4deoUBAKByj4zM7N2v1573CVkYGAAxpjKtoaGhmblhEKhynOO46BQKJ76+oSQ9kctJ4QQXt++fSGXy1FSUgIvLy+VR2vdHT169MDJkydVtp04cUKt65mbm8Pd3R1JSUmtnruwsBCFhYX8tqysLJSVlaFnz54AgM6dO+PWrVsqx509e1at6z9MKBRCLpdrfBwhpP1RckII4XXt2hXjx49HeHg4/vvf/yI/Px9paWmIjY3FgQMHWjxm2rRp2LRpE+Lj43H58mVER0fj4sWLal8zJiYGcXFxWLVqFXJzc3H69GmsXr0aABASEoJevXph/PjxOH36NNLS0hAeHo5hw4YhICAAADB8+HBkZGRg69atyM3NRXR0NC5cuKDxa29KkoqKinDv3j2NjyeEtB9KTgghKuLj4xEeHo4ZM2agW7duCAsLQ3p6OlxdXVssP27cOMydOxezZs2Cv78/rl+/jilTpqh9vYiICKxYsQLffvstfHx8MHr0aP7OII7jsG/fPlhZWWHo0KEICQmBp6cnduzYwR8fGhrKX79///6orKxEeHi4xq87Li4OiYmJcHFxQd++fTU+nhDSfjj2aGctIYQQQogWUcsJIYQQQnQKJSeEkGfq4VuSH338+eef2q4eIUQHUbcOIeSZunLlSqv7nJycaNFBQkgzlJwQQgghRKdQtw4hhBBCdAolJ4QQQgjRKZScEEIIIUSnUHJCCCGEEJ1CyQkhhBBCdAolJ4QQQgjRKZScEEIIIUSn/B/HwIDUzLl+1QAAAABJRU5ErkJggg==\n\"/>"
}
},
"source": [
"# Dataset Used\n",
"---\n",
"\n",
"We performed joins against all the tables from all-of-us and truncated records while randomly selecting on record per every join. As a result we have roughly a dataset of about **80 million** records and about **5000** distinct patients.\n",
"\n",
"## Expriment Design\n",
"---\n",
"\n",
"We compute both marketer and prosecutor risk computation while randomly selecting the number of attributes out of **111**. This selection is between ***2*** and **111** attributes. The number of maximum number of attributes that can be computed at any time is **64** : limitations of Google's Big-query. We performed **500** runs.\n",
"\n",
"## Results\n",
"---\n",
"\n",
"The results show the prosecutor risk is unchanging perhaps as an artifact of the number of runs **500** or the dataset curation: The joins we performed. The prosecutor risk shows there is at least one record that vulnerable.\n",
"\n",
"The marketer risk seems to increase as the number of randomly selected attributes increases as a general trend. \n",
"\n",
"{{ figure }} \n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.15rc1"
},
"varInspector": {
"cols": {
"lenName": 16,
"lenType": 16,
"lenVar": 40
},
"kernels_config": {
"python": {
"delete_cmd_postfix": "",
"delete_cmd_prefix": "del ",
"library": "var_list.py",
"varRefreshCmd": "print(var_dic_list())"
},
"r": {
"delete_cmd_postfix": ") ",
"delete_cmd_prefix": "rm(",
"library": "var_list.r",
"varRefreshCmd": "cat(var_dic_list()) "
}
},
"types_to_exclude": [
"module",
"function",
"builtin_function_or_method",
"instance",
"_Feature"
],
"window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 2
}