{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "--- This is a regression problem ---\n",
      "\n",
      "1. Loading dataset from file...\n",
      "\n",
      "2. Calculating gram matrices. This could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 183 built in 440.4844558238983 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.1} is: \n",
      "[[0.0287062  0.0124634  0.00444444 ... 0.00606061 0.00606061 0.00606061]\n",
      " [0.0124634  0.01108958 0.00333333 ... 0.00454545 0.00454545 0.00454545]\n",
      " [0.00444444 0.00333333 0.0287062  ... 0.00819912 0.00819912 0.00975875]\n",
      " ...\n",
      " [0.00606061 0.00454545 0.00819912 ... 0.02846735 0.02836907 0.02896354]\n",
      " [0.00606061 0.00454545 0.00819912 ... 0.02836907 0.02831424 0.0288712 ]\n",
      " [0.00606061 0.00454545 0.00975875 ... 0.02896354 0.0288712  0.02987915]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f80070a0a58>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 429.7083742618561 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.2} is: \n",
      "[[0.06171557 0.03856471 0.01777778 ... 0.02424242 0.02424242 0.02424242]\n",
      " [0.03856471 0.03579176 0.01333333 ... 0.01818182 0.01818182 0.01818182]\n",
      " [0.01777778 0.01333333 0.06171557 ... 0.02994207 0.02994207 0.03262072]\n",
      " ...\n",
      " [0.02424242 0.01818182 0.02994207 ... 0.07442109 0.07434207 0.07383563]\n",
      " [0.02424242 0.01818182 0.02994207 ... 0.07434207 0.07430377 0.07376068]\n",
      " [0.02424242 0.01818182 0.03262072 ... 0.07383563 0.07376068 0.07366354]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8004fc7e10>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 430.415020942688 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.30000000000000004} is: \n",
      "[[0.09803909 0.07202114 0.04       ... 0.05454545 0.05454545 0.05454545]\n",
      " [0.07202114 0.06853421 0.03       ... 0.04090909 0.04090909 0.04090909]\n",
      " [0.04       0.03       0.09803909 ... 0.06368916 0.06368916 0.06678704]\n",
      " ...\n",
      " [0.05454545 0.04090909 0.06368916 ... 0.12892852 0.12891455 0.12734365]\n",
      " [0.05454545 0.04090909 0.06368916 ... 0.12891455 0.12892664 0.12733207]\n",
      " [0.05454545 0.04090909 0.06678704 ... 0.12734365 0.12733207 0.1261675 ]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8004728668>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 434.5828993320465 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.4} is: \n",
      "[[0.13888889 0.11120616 0.07111111 ... 0.0969697  0.0969697  0.0969697 ]\n",
      " [0.11120616 0.10756609 0.05333333 ... 0.07272727 0.07272727 0.07272727]\n",
      " [0.07111111 0.05333333 0.13888889 ... 0.10909713 0.10909713 0.11216176]\n",
      " ...\n",
      " [0.0969697  0.07272727 0.10909713 ... 0.19178929 0.19182091 0.18963212]\n",
      " [0.0969697  0.07272727 0.10909713 ... 0.19182091 0.19186661 0.18966477]\n",
      " [0.0969697  0.07272727 0.11216176 ... 0.18963212 0.18966477 0.18786824]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f800473f748>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 434.108122587204 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.5} is: \n",
      "[[0.18518519 0.15591398 0.11111111 ... 0.15151515 0.15151515 0.15151515]\n",
      " [0.15591398 0.15254237 0.08333333 ... 0.11363636 0.11363636 0.11363636]\n",
      " [0.11111111 0.08333333 0.18518519 ... 0.16617791 0.16617791 0.16890214]\n",
      " ...\n",
      " [0.15151515 0.11363636 0.16617791 ... 0.26386999 0.26391515 0.26158184]\n",
      " [0.15151515 0.11363636 0.16617791 ... 0.26391515 0.26396688 0.26162729]\n",
      " [0.15151515 0.11363636 0.16890214 ... 0.26158184 0.26162729 0.25964592]]\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQsAAAECCAYAAADpWvKaAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzsvWmwZMl1HvadzHur6r3XPT09OwAOiJUECBGCKAgmRZGiFKIWKgKkJFtByTJJWzIVlqCQQ/4h+YfDsn7phx12OMJWmIpgkHZIpvVDDNKGghQFhgiSImCAoiwQxDIDzNozvcz03u9V1b2Zxz8yT+bJvFmv603PoN8M6kR0v6pb9+Z2cznLd84hZsaOdrSjHd2NzP1uwI52tKM3B+02ix3taEdb0W6z2NGOdrQV7TaLHe1oR1vRbrPY0Y52tBXtNosd7WhHW9F93yyI6E8T0VeI6Gki+nv3uz1vFBHRs0T0BSL6d0T0+XjtISL6FSJ6Kv49f7/beS9ERD9NRJeJ6HfVtWYfKdD/HN/7vyei77p/LX/ttKHPf5+ILsR3/e+I6IfUb/917PNXiOhP3Z9Wvza6r5sFEVkA/wuAPwPgOwD8JSL6jvvZpjeY/hgzf4SZPxq//z0An2Lm9wP4VPz+ZqafAfCnq2ub+vhnALw//vtJAP/oG9TG15t+BtM+A8D/GN/1R5j5XwBAnNs/CuBD8Zn/Na6BNwXdb87iYwCeZuavM/MawM8B+OH73KZvJP0wgJ+Nn38WwI/cx7bcMzHzpwFcrS5v6uMPA/jfOdBnADxIRG/7xrT09aMNfd5EPwzg55h5xczPAHgaYQ28Keh+bxbvAPCC+v5ivPZWJAbwL4not4noJ+O1x5n55fj5IoDH70/T3lDa1Me3+rv/RBSvflqJl2/qPt/vzeKbif4IM38XAvv9N4no+/WPHHD3b2ns/TdDHyP9IwDvBfARAC8D+B/ub3NeH7rfm8UFAE+q798Sr73liJkvxL+XAfw8Avt5SVjv+Pfy/WvhG0ab+viWfffMfImZHTN7AP8YWdR4U/f5fm8WnwPwfiJ6NxHNEJQ/v3if2/S6ExEdENFZ+QzgTwL4XYS+/ni87ccB/ML9aeEbSpv6+IsAfixaRb4bwA0lrrypqdK9/DmEdw2EPv8oEc2J6N0Iyt3/9xvdvtdK3f2snJlHIvoEgF8GYAH8NDN/8X626Q2ixwH8PBEBYcz/KTP/EhF9DsA/I6K/CuA5AH/xPrbxnomI/k8APwDgESJ6EcB/C+Afot3HfwHghxCUfIcA/tNveINfB9rQ5x8goo8giFzPAvjrAMDMXySifwbg9wCMAP4mM7v70e7XQrRzUd/Rjna0Dd1vMWRHO9rRm4R2m8WOdrSjrWi3WexoRzvainabxY52tKOtaLdZ7GhHO9qK3rDN4qTepAoC/U1Duz5/c9Bbpc9vyGbxGr1J3xIDekLa9fmbg94SfX6jOItvdm/SHe3oLUdvFIKz5V33H2y62R4ccHfuPM4tnmAA4NUaw+MHAACO3v6z6w60HgEA64fnoIglYwAU/8rWxwTMbvlUPg1TkNxwrs8FIBaiiEldV/d0d9ogNjP64vtw1rZdpqRcBvoz57H/2JOcOqF+Z6m3apdc645eG5iOqnbWNB5U4RV0G/RYbareoDmm0p/+7HnsPfEkA0C33L4PNDLGvbucbZvaVb3Dok3qkl3dvT3kpveMiw3tigWn96ypmLjIx/aGJpgh/GDUVB7n9eQ4nsw4LXx1eA3D6s5WBd03uHeU434SAOZ7D+IHHvtreOofnAMAmK/v4dxTwLmvHaX7n/4rMywudlg+ucb5z/dFWWdfmG4Gz/9ZwCwNuGfML4cFsHzbGF5Gx3jg9/rJM5oOXm4vqssfA9xe/s2sDLhjzK5akAfW58Nv+xdeG9O2d3m7BfTKxzxoUO/YAzAA9/l5WlHYVBnw83C9v25gHOXNMNJ44MEWWFy+N2Zz78r2G8DVj3jQOO0DqdfJNl4nYHHl3to2v3Z82258uxq7EeXGDYBnjO5mboMZgXEPmN082aKtaXb97vfceq8HdwwaKbQNQH/rZOMxPODT4Sv00n//P239/BslhtzVu46Zf4qZP8rMH+1nB29QM3a0ox29XvRGcRbJmxRhk/hRAH95081mOcI9/QzM178nfB8JD33xJsxzl9I9Z772fgDA7KUeD3/hqHi+v3hjUuYD738bzAB4C1BkBMzYARxOq0e+sDq2A7NLd5rXl+fPw8/ysNGIzHpz3u0f/uL62PI30fzV5Vb3DWcfACm2kjicgNypk2/gxNZ6dZ08T0QLPzNgAs4/NbymdgvNrm3fbzc7gNFsfWTNSTF1HMfWzQnnnhnvrW3Xj28buT31GRPR0HdUtI084DvgzEv32K4bd3++W87hLYEthfcH4MzLJ6v36CE74SwubTfdQhtOVNuWdFJv0uXjHV760T+Mc0+FQXjoizfx1H/Zwz7/vsQ+z64D55726A89XvzbDtr/bf1yCL7Es/wm7aFPLOyZ58JCWbwSFgk54MrfOlTtJRCVLOqtV8+ED7W8O46AV2xnXKV7L3YAASautZufuHmXMcp16s/Xrx+U9da6C1nc4wpkpmw1q7al3wlgF673F2fN9tDIIE9YfuLaxjb7yI8bYnim9FeuAcBLNw7AtYwDTMYXAJw7KvrQUtOk7y/s4eDPvrKxbceRlPvytbMwVumyRLxITbg9+U3/7j1hfCVvKCAADjjzI1deU7uEXrxxBl3nq7bUtIL3Bssre2mAHvhz0/AnrTkltL6zP1GJ8Ke2d3p9w3QWMUjpv9jmXpFbRUdhnrsE+/z70N0h4FB+83jgmUOYwzVe/noZBHt+JG82n577LzHYhLV85kLYgbsjB44n13NPPXhsm2YrTJVQABZXKcjQQvHkO7gYLooS6eKjD23T9QnZ1Xby7/41CqduRZNTubq+d4XDGDAKvYUZAWKPKw88ck+xrOyaJjrZTbS4QVMFLsp2yXzfu8S4OH+surF6sFbE6usMmDXhuKXRaT2feu9ytfPAgdIvcDx4Lvh7i4Z4t3YBQHdIAAPnruYGPb9+4kT19A3dCh9tHy/4vsazEOKesX6gfMN+zsAh4ehbwkJ/5AuAOcxspJzg3AF2GRbG8rG4O1vG+S/ngWmxn6JVNmsATKE+nycnd0GE4Y5hoiLRd4z50+0+zK+VLKFZ96mNFE97Ngwf9ap2RfBRGWlWBD+LokFc1G4R+uj7sJD9LNxrlwQ3A+ZXX9uKXlw7flp2h7ZQOupNRTYcFiVkw/Lhe87PyylnADfPYy6b2OLV7fuwuOHR3ygnNlU6aN8F7oh8+Zubh3dol4BIGmwYbhaaLQrDbZSzi4aS9OgmpXccGoKgbI5cE3kCG55s3mzCRmHXwPrBPBfkd9/l5xeReZnfyB1bPWTKgwsorSqaOzKMxZXpZmFOIMns4N472tGOtqJTwVl0twnv/oVb+Mpf2wcQlJmz60H0eOQL4Z4L/9EA+/z5qMNgjPP4sAfsUThNFq/Irky49hduJ/nv4ssRszHT2ql4zJGc6OWue/BsB3JyKsSLTDj6ketN+fvKpajjiKcBzPpYncJoOH0my0mnMHsx6BT626FeuwonkI2iFlugXwH8I3eX37XuQNr8witnm/eaKDODhqYeQT4DbfhHohf3wJELSsPE8QQThiMOfb9B1veq3aILuXT9DGxXckUT+dsTyATYSnGqunCyH17ZR+L3mbKJdhH+7P3w8SFQCcDla+X4GethDBdzgijoHmT8iRjMNHkfzARjPO68sg8awiTjc0r2UdP1se8OY3X1zn6a133Uv9Q6nhYxEx48OJzMXftL2yu0T8VmYVce5rlLWFx8f7p27umsowAA+/z5pMPYu5xZOtFJkGfYlfDJwI2vn0lltXQas2vVJXkx8dazL7rIzjLYyCbEeOnxc80+FDoOALMbx+sU2FSfozVl/6KAb3y6J7H9CJsFeeDKudemE+nvohPpb7X1CIASR6JoUogoSrfQApIZp3Qo8d4ri+31I3ZNoMPj295pPYza2bo4hg9c02cE5/GP916E0olsAHeZavwcADqi4nYZG7nIesdFec0Z4IHrSqxWwEJSc/LCOuhFzDrXb5eY4GU2ETHw/LkHJtfXR8fjjTSdis1CaPlk2BhmL/XoD32ho9A6jAefLlfhJpOYGbJOAwCOnvCADzqSs88cL4H1t9qyfXfYJQsNEHQebINyLICywm+vVacwv7mddtqsbZpgQJaLvXr3dkXJpCtt7m5H81+lDBzOMGBOpkdo0eJGLURvpu7QNPUj5HO72IbrvuMTAb6abbsLKOvwRgm4qjce33OhBCUfdCCLezOGFHqITbR6yCQdholjNn/1ZPWYgSamUzpBBNBTsVmsHiJc+A/fj/OfD4Px8BeO8OLfdpXVg7F3mfHg0wb84+Xbefr56pRlAi3W8NaDnYE9CjLLwQsBS2BG4PyPPQ+gNOlpNvFrlx4pzJBC+wfXMY55xK318J6wfP4MQNma8c4ffzqx0JrE5CifART3felyW7NemyPPzteJDZV+MBMGp7gnxbaPLrT5lQvnmpwDrYOy7IM/8ZV0zSgtoWeTvvsWyxTv/9KrT8DXp2hkwWsW+PH5Gr0tZ6tnQmdyvaM3MMT4+jOP4/t/8Pea9epnjxvzL10rx5arZ963yPgdXY68p8FZPPtKnmtEjHG0+GN/9sswDVbEx4E24PS5JgPGl27c3Zry9tkRRrb46qVH0/v7gfd86a7PaXpldaYQ8QDg8j/dHmhxKjYLMBWnJJDtzXJ9nJemwD5OKMcEWA46B5d1FmQ9jGV48mAbtfJEQewgwMbnO+NhwFj7cIQVk42zHBzaRJh1pfq4tw7OGyy7wH5zZBM74zEz02177cOinRmHMXZoZkasfXgVNm4A42hhDMN7gjEMF/vWdR7OGcw6h7laaLJZ6NSZC9XWQfrVMWB4wr+yD9ag3jh0apMw5OPm4IrNojcujH1FRIy+0tU4bzC6ElcCAPNuRB/HSG+grc0CnceeLTnIemMYvYUhD0MMG+VKB4O17zAzI/b6IS0Wz4TBWVj1zve7XH5HPi1weWZNHTq1AZvYzz2zLtoi+JMal+KUGGzh4WAwNyP2ugErF99/bL+Mm4zpfjdgZIeu8zBxfPareoU0BkZ+H9jigX6JwZeshW08v4l21pAd7WhHW9Hp4CwoYBpsQ35iaaHCQABIp5pnClyFUi6yCZojTx7ssg2cWKHx4vNj3L31iaPbRSYr7AiMwVk4V+6x3hPIBcUgqfLXfgp4SaeUt6rOPn/2uWxpK/MUbShihZCcJPr6OjaGAKzluqOJ5QdAaL8HBm/hFHzRUmiPYyo+jxtEEWaacBye82/67+DagCCnxiCx746w8sdPVy0qyYnpmODZwDFhNZbPixgi02rpssKnI5fELQ+CAWPpuuLdew+40WLl+0Jk0+0BNHeWaYSN9wQOJ887A1fNUeF8R2/gnIGP70/GQyNpN5GDwZHrJ5zFJvGoRadis6AhKIvEe7S/eAPrlx/H/IiSctIeEc5cGDG7vg46CisjSrA3LcAEK+4eHPxA2AaQzsEL4d7Z7bDwzcj46vMR/WZyOaExcYFdnQVFm1c7ABMOL88Lpdw61nHm5eDJKe39nW95MokvWpcoehBjeGJaAwB3I0xYclFkEmVkFEPQMeCAFR/ktusK9EZglWUibsT7F21Tg26HUNdnH34XyGhdSN6g9IZFG+bY+vp8qhPxlIBKqZ0AruOB8l5tZhGK3/de6PHpc+9rVyrVRJEttDWX4ZyBMYzVYQ+Wxa7HSqDqeCjbivXalqIcob+al4wgOH919n5oqk2l+v3W9xjjsTyawa/DIs4QfWVal3H3hO5yn9r2y+aDEz1QC2ofrgPLo9nEKnNnOW/e36JTsVmAMNHSCiUTaTRjJpIXzQgKTUZhTg0a/zBJZdMnzmOVXoR8Tz9kLkS3TyojR+VvLnI1PtwmbdTK0eL9yN4k3BCiLkXmiF7sLXFS+uJyWwtmSLt3Iy8Gcnm8mmJqHCdmAousrJqgGLeNTUuN2fQjl3/FgpMbLxxiNQYULDijay8EXXf2S6PJdXYK8Sjt1PXpdjOm/fAZm8EUHiOHgtsIi7fkoMKGW7dd7jEBYyNzIW1gyO83zi+Z5wnl67JOY9MmkbrDCHiTBle5LZ2KzYI7xrhfXZuFo0gg3ItXKOMogHzSUgYujQd5V55ftemQ6g+jyWkIJy15BiJ3IAsjndLyx0ZxxnCBwVhcNE2vyNmteKLJZFqb/GI4P5/qEc5BPkdOKdn+I3RZuCMBlNFIIX7GNdte9S3HClC6Ptvg30Y+7KRuaUvuRO8Suh/a/KrJVxueVG/VTh373V8zJZcju1O9KxHQ3QEOb1dOcPUCMZwOj8mYe4K5bRNgjIknGJvupjqx9E6p2lL7VxADtyftis9T9b11jwfoTgcs4sTRc0ZxYvZ2aJuu//DmPN+r290iAsyNbjplxk0PTGmn4NzRjna0FZ0KzgKEJtoRQDJ7kmLbwVlpyfE0CdxfvCEiHoW7lJgJxJxZc80Syy7fYOWYGMmPMrKdxe4szEyMf5C4Dk/lKRGfT+TV0eWlcFZt4CznN+oLoCHNRWAiYgjytGxnW0ZI7d6gAJ1Q67REfE/HOTfpe3XMiLuQccjcZGpD/V3+0XTMXRAhJA0xGcpzR0TSuwCUiEvHqwQgU2JE/kHpi2pOQ1+TdonIouZMBK6DmLLjo1PdlnoL92HFIVdcmxkag71RnpzSqdgs7CHhHf/6EE//x4Gde+D9b4M99Nh/KXuPXvsLtxOEmxZrkACSnIEZO5AH5lejksgB+38qB865UIC2woJcPBQ0kdb6BK7RyqLx6bMhhJkjtWEBT/7gcxOAETPhaxcfDV/i9YfOHmbsvsIXCGhq1rlkuehs/vzqswGIZtYGbDn8NQxzFH0HOoZZGnzgB5+6K+irRZtAX9K+J8/eSRiUGpgk+IfRG3TGNzXwX3/usanYIhgYUUrH5z76J740sSJoi4b+/rtX3oYPPXB8jBBpV9321dihtw5PX34kA+qY4ONiE6XiH/3oV48t3zPhK9cfm1x/z96d1GZd7xgtD51xGL1NVpVUHggzM+Krrz4alI8AbJfnjNZJ/ImPfRUehK/cyPU/vndrUucmq8jIBm/fmwaJ+rmfPmzc3aZTsVkImWU0NQ2iM8i/aZCWj4ArABl0RTmupBy4vfEZtAUAg4ncASVwTW9dWsxEie/AQAhhe7h0LV7YsTCJyqIxJth2xfSpQVNlQJLw7KIbk2lzZh0GCucId/lkSGCyqLeA/B4X7nGgLyAAv2QSC+irs75pamMEs60GSgFtsJTeLGo0Klme6n98ZB2TBSv82QQAM+ST6XOIQCtruABN6fZpM3hnQv9kUcoCXXQD+j73K5zk8XCJdWnQV0+uAFHJGGrEqYzBfpfBUdJ2x9TcLFK7I6pzzw6Ydw5D3CRkXhJxYdnZs2sMbNEbl+o66NZFfeE9tM21Ixuc647ieObN5biDpaZTtVlIsFkfI1w19Xdd0Gr7OMkSjqJxvxMUndYwU1j8tQbbOVN6DnLgJLRDELjERwBhgia0nr6uMAR6Qcn1NXHCGRAyDiJZLXwUftJfpN/J3x3HAcjGYYvrzhv4Ddpz5s3YB3k2NIVCOeqklIXAlbgI4qloI3u3wnTYaM7SeA4g4zs8lzgIIX1Sr71FxwGRq9Gmy4iOHEcLFzkLBgJnAUCq0ziOkWwDL2IKDIh8XhcL0GbMS/y9Y5M+t2g92oTQJcrcROYsQtsCXiTjMI7cFN+xabPwTDh0s+kh8aYTQ9aM/uINzC+/DUBYpGeeMwlXAQQ3c8Fd2KN5ocs4eCF4ECarh+MgekQYuI1abrukpIEebgZX43XEItBIhYx35nmCcRzkybh+yANffuGJcuKLBv5WxEdEufDVK4vwWy2nyrOWs2xvkXAQBy/GTWNE4XUqsrLvwuffefTJpiu5No0Z9XvCcdzq27uwIxATnrt8UMm6So+i8Cap3xXtvdhPVAnkK/1EfO6zZ9/VxHTUIe2IgPW1Ba5eqrwm6/3O0xR7AgSNv2V0r/RJL2EY6MZgivRxLn16nnEcLXOk94RBe2kSg53BC/RQiTuJY5bM8yocQX0PWQ96dZZ8igZZ33Geyud/Rd8OZsLqziy9h6/Ro+GAq+dYg9gTDh5YTvp0c/3r7QcatLOG7GhHO9qKTgVnIbR8Wzg+zdhh8QqjO1IyZsRdHD3ho/do3LU5IDOJkRKxkPBWUUdhl3HXPiunDmPvYmRHU6yKUqnc3+EsgqgTkQ+7fHoBCeHZ3Y5Q6L2oh7hu2ie4PqUbn3vBa/jMxSetOzK34TfhIVTbfAJiZb2NvW2aVh8/D6iy2fUK4Sksi3zWdTWov9n4LYp0NWdxeNS1+6CHLX4nR7A37hJ7QbdL1xWvz68qQB2rMY1z6fYNhWb0NO2HYdBtFdndA5gxzKGOl6ca33rXNRFjds3kkIMbbju8sYjyqskWsaPtz3rDwO24HjR5t30Zp2qzqOGCzYGTRS2oXbkXSAPBaYahNGHFr4wcmKYw2ep5G6HWxZqWAuoIWNIeRposrEWQYuLKm0Z2mlCfkzk0tjv1S5cl/0w1MWuWNJksuWTPW5tYLJNbidTq9yD1t1jexl4km24d/GYyjsdsFkw8Na/X/ajFJbktxcCkco7pOmLbm2VLsaZ890zhPYtIXLe5rIRbKPbQJwOwOgzqJnB810RhHKRBm1DPTWIAljfC9Leh07VZREsAW8SQdtNbuOciRBuAFFG7gINzNHuKfwUQZEyEU1Z0AJs2/xDtOsjlE3i3pngCBfh1LtCuVdYvtVmkCaDxE2qBpL5wnlDybCpDbPuTU5nKBeimi4NGQnORd6FSs958um1DZti8WaT3KfUPZjOmo+JmyE/DGNS7WH6Hrevh+SLvh16MQDSBRWpwFmy5wCpQiKUEq6JXtfagYxixANQckDEeihks5t3ahDmjHCO3jQQvFfmVLeH1dYPvQqdis1ifA176obfhgRjb5JEvrHDlbx3iuacezLkdyWF2DTj7jMH5H3s+YQE8E776/BNBgSTQVQYWDy3RdQ7OmaTM3Ltok7LwIx8PlW0K6PL5F5+E98FPIinhmPCuR65nD05Es6ezuEAPh00jhlb/4x//7RRbQShYTaKGPJrT6s+fvfStAADnA5bDR0yHxmQMzuJDD17HTCGERAO/Vhr9hR3Sb2JJ+L0LTzQnLq+CWPPnv++3TmROq+k3r7xnWna0DNRm1g+evYa5VX2I5sRgzQj3jmxgwPj1Z96Ln/j+zxxbt7bOWJJ4J9lq8/nr78SojmOxZKXgN2dzUCVtOpV7jlyP/++Vd6R7rPE4Wvf4K+/5XNEOsUS4ONIWnD6nZ+M1C8a/vfnOZNnSZl/t2fvug1cxeoN/c/ndqb1/+Z2fi2X5iZl3MjZscMPtwVXz/KcO2sm0WrRTcO5oRzvaik4FZwEOyV65kSzLCE5GOf4QcQEQgolaCrFlc0BmCoBmLeAmE8QSpsxRzCNw6cj1RdQgotAu5mBSBMIJs9eVvPDcjjGSU9QXxLo64zCPJ7+O2iS2/H2zxioO/9yM6bNwTM5bGAIcA1rUFgT3wg4JlGUo4ArGCnCzsOPEDm9jNOravu4dgV2IgNVHnrhGG8p1xwaW/OSUCv32kxBzY8QZ1JzFnh2wZ/N4alBW4iwk+pX12Ldlyklb1bPkDj052BpnwR0WNGJhR4ycOVLPgduScTyjyg+RwMpYJ0DgJENbQ0Rv1xnMzZDesR7/IXIxPTkMbJvo1LkZcNCtMA57sS1jmocmcRseZ+0SS+oxty7NkQOzgkEFyoqLxMCnzwBSX4ZK0dEKB7iJTslmIfoGJfuxEt6AidB3bCc5bCjy7zj/A40WvGu5mCLewkJtK1MnE4gbShhVhp6Uof+c/m56RvfBUxkWUK4bcA6EI2NSD4pSfOoxkE1BA52cmvQtMa4On4dmD/Imp78DZVg8TxQX5nRzmGyEzGmjkOcteSy5gyGPzrgUOKYV/9TU8yCVH/pm4Sf3U2yrvi5igYUvrk3mBoW/ev7ZxjuQ75aCa0J67/HZUEa4b82qHD3f4gFpan3Om26zMAw/qzohp5BE0q4clETGE4QmMwqNv/gAOJcjSOu4FjK5j6Is79kUgWaDlUU2G3k5wJ1hVugsgIh6HCiwI7Gu0Vvc5nkzTiQAHGKWPjuYAmEp/fes/sbnPYdJejjOMEbORZ/YWmehF4ToLNxomwhOHkNchYCq3CCd+ln7c9E/g7GSbpkDCrVGD94ZZ0kur+HZtc7CjQa33KJZp+gnBrZpUWmSU/32MC90FoK89dFEcHPM5bfg3keux1JF27LGYzV0OPTZ5FpzDnJN6zCArLMYyOLmsEhjc+T6hs7C4obbw+gNlmOXNpRbfi/+muvcpLvYpLO4m65D0+nYLEAJqTihlkVkoiqub6AmZ8FiHtQ7fFpo05NKlyf1dsYXkGgjIlEyaebTXp+QQHgxKewbfJqkFh4e29vBROGWOYsNp6P6vTipiNvMVrxYL7YWbYpY3VKOtgL7yr1dXRcHES7dIwpImm4C9fsyUTxqXZf3YRr45k3jaCKsVhayTVxZIALiSa85CC265Wu++s3ECZ9FpihyoP3OZL7o994SfTZxryAkMbK8/GbjLI5pbzH3tGlTy79iM6vK2dawtFH0YDrW7NWsrCGG6O+tTcEQZ9Nm6vDda72bQ1BmV/OEnmRTk+8bxDW9KdR+INvKu0S8QQxpLf7I8sv7VYtRizybNva8GSvdQfqt1GXUpN9Xy9lOczy5PHm2Nf5TJ7kW1RG2J6Ku1Nt4RXIgCYewyZK1ITLBiWhnDdnRjna0FZ0OzgKAmwFnLoSdeHbpDm69egazFVJ074NnO5x90aG/5fC1S48Uz9LVWWAu1KE9Pn02qBE4OIUBAcItOIvPv/hkeFZElGrnXV1bJPFDM29fu/b2MhRZDBd3cCGykdF686vv+LZYfi64leuy/nznRpSba9ZdMxwMfOHiWTSdplzVNgDJ8xPA/GLbkWwxBJ3QJ89/qLiuT1jNzdVen5JwAAAgAElEQVR5KeTzzZt7k7LrvgtdeOmhMh+scIgFWx2+9y/M8XMHf7BZtq6jlYdWrt+4eVC+j+q+L/MTZVt0GxA5/FcUJJwAGoF/go/lS433fVyMTCLG9Zv7qb7aiU7o8/zOEIn88iJNjZ9x39MscxPduLM3medXl/926+dPx2ZBG6CrHN3VUSI6CzdoUte1F+ZIQMwLmiNlIUK4OWnFmx6V9XW9yAcqg+JyWGQ05nYCpQt8HR1brjWjZRcBW6u/cUxCPdR0L9bxL9PvRMn1XSJs1d2V9jtvTuS2XFN4N42F0WKPByqjebXulY1qJKzHe5uufjA5aFKjWj9oi45qQnw/7AidQnAyhfe9HsvJu7XoGu91o8nxWTa1fQw+IWbMbVsNJxuPYbCTd/Omc1EHGJOUEKKMjBBw8lTAubX7b1pgkjmMYjRrDnj8tLjFsMEZk6F3/3iLagPnxRrLp7FckCFscg57JhtXQH9Op0zKbqZSDBQo0cKFnRLnAr2ZWAZGyhNaV6PqLIwaMl5juRBSEdEPZlR5KXKWM55wRd4TWn4Gzc0imj4nG3Mdjm7SKnXFoUgb2XxKtVMvAkm7wCMhg3W4fBcAMKoNvjokGAiHgjooJLr36BrWn8bm2NqAvCf4Mb//Qj+pDggeTTyUKF0fnJ0s9uPSNfih4bhzAmz/KdksqIhtCCC8HUbC4rNBcQpR7RhFyAFiEELhif9F4looc7nycqjiIKQGB0yVpp6CWKS0RaEOho+GblnzxnB0+ql6mhiX7NTDxqXPKc0gAylmRLVhiVMQ12KITJBUbv49RR3vppy+PMsAjPEwW2iy7IZ1O5hus8K6rtRyW2vWEgEsitSBd6P6EAAA6jhzFkAap7RpdGVsDelIWpC+TCzMcd121je7rJnBTUvSGMB0Prdzw7gS+/COBPwHFFG7WriRSV195VodCt54/+T5re/c0Y529E1Np4SzaLkfhz8+xaSsxBA5OSDsorIrKT1G7e2Y9lUF4QbCrtlUQmkxh0LkrILVj0dyAnyJ/oSR9SK6uHiKaTa+YBkLTgeZq9A5LiIXRa3zqvCqzCxruu7bp5yIZ56pGIdW6kSdpWxCrMQvfaq3xBCteyoaU5Yn7a7Hs5XlS65rziJlCHOUO0PxflblKOVwUTTni7XFlnyZbjHUPxUBdPukjSLOsTPgyCVsSgIUEhHlNJkAmqH6NgXsJeKQZOjNLoaYJeHxz6/w3A8FlOHy/HlgHLG4Spg/He45+pHreOnxc+gOO+wfXE/ZzAdnQ0pBR1hcjOhHF6JwS3DdL78QtNx82EEsA+965DoAYK8bYIhxZ5gV2bu/du3tQZk5IllkyAF/8vv/HW6PGb24ZweM3uJzF58EISudPvy2l1LAXB18VpCnCzsktOWBXeOOC2V+7plvBQD4tQV1HuxM+Cvp7WYOPBh8/Ht/G/smB5gV68ShQlbqLNuCVP3cK986sWQAwHLs4LzBRx69UASu3WQNaSEcAeBXnv32yUJxzmAYbMr+zT7EO/1LH/ks5pTlT4GW90omHXwHSx7/8tIH8T2PPDOpT/uorHyHuRkDMEthQm6Pc5zpVviNK+/F4RDGgZmwGroQiDgu1J94z2dTuT2Nk/4d+hl+58Y70/fOOKx9hw+euVgAnqRNE98QtQsKfmXfrPFbV9+DK0cHAEIgZxnrFKOVGH/pWz6HgS0+e+PdaT5955kLEdqe32Pt3ZrGkS2e7K9iXVkS/v7BNOL3JjoVm4WQ24uAmVk3gXdr+LdWdAmcm/TpHk+LFFxXK0DjyV5DttfOlsFqR4oWGMo6Ck+4Pc4KcM2R6wOU14nCNFy/Gxy7/ixw7KSRdwRmE6HsJp16PBpgNAlOXpev23aIvHGkhMzHJCP2XEKwgc2grI7aqQB0SoWkbPThVBfHpnB6HgMtb0DJnTcFHDu1T214a99h5bsCOSsJgR0CVFo285CWISgIpQQNJ9do0eRQBsKhOigMeYxscduVsH4BSaWAvcZPuADZhAdjcWecTSw9hMw5EDFuuwUcSjj/Dbc3gbe3nPuAsFmcNcvJBniSxMhvWZ1FSxt9P+iksSGI2ixseVO7zHuJQ3EcncQzsaY38j28Uf1t0d2g5t8M9JbdLHa0ox29vnSqxBCzimzXCOj4FcU96zJWBRDjVTiaxHhM7J/JYoT8lbgEKR4FqpPKRpu9SjJEYOzZIcn/QIiHMXJICBMUVuFmiTeh/RF0vImFqnehYjqIaY8dgWzwqSDLYAGW2RBWXsfLANrRkrROQ+JoSBKemtYA4M3GGBPyGQh+FZ1xTTFEMrzVlBIxAeDYzt64QmcBlHEzAOVJanwRbyK3L+tULDzmJoyrjpQFhFgVM+vguhyjwkffH9FV6XgZPbmJL8eSOyxUPBMDxsge+3ZdtFlEt8EonYWxhYggeo19s8ZeN+Cwi7E1VLwM43L0rH2zwsBdEe/ijF0WsTtCv44RQ+xyEs/izedIFill4zKYYhzkHhu04inhjaecB1Wb58X9WJcjeAzKyXTEi29wtlBwggFJc58UERwWfJnpKQQe4fQvXF9H2RkMGMoTdK0W7Tomv+nIxxBvZeZ1ZgSdhcJZcGyXTmIDILmF6wUsG4QhTpPEcXt6hLECBjYwSi7etFl4UNObNFh5aHKNPaVNQnQZg7fFgSCLTC8qcVn3TEUSoNy+vFmsfJ+uFYmdvMURejifkwR5ZfmRZT4U7utmoiwcfFeMuSEObuO+L3QvtYLTkYlu8lQ865lgyRf6Moq/MeksY4SBOwxsw/yLfVv5fqKzkDprr2DHsZ11+IAT6CxOxWZhh+APMrsac5IysPdih4OLHvNr4eS5cin4inR3CMvnz2ApyE5HOPNyUIbOJIy+A7528VEYyccZEwB1tw0kafIFejjUJSCXgdJGAgRfDxoB45AAV+SBz118soByCzrwztW98Ow6/Pa7y7cnCK/GVkt4ftP5YA4DYCyn6/0LUWk5hojUkmtVwGm+Z9BI+PUn3otOAYzEPDiqzGrWZJdqQRneuLlfmD5lXbt1UKZ+5s5Cpc3L74i5NPtKv2san6+SFAGAJ9gxW+lk9H71/LelqE9AthLXVksC8PIr5/DK7YOi2JqDcc7ASn5Z3aZ4/dblM8mvh5hSQigBr31y/zvTM7aRy3VwFtfuZN8XImAcDZ659nAJ/orvQjYma/zEvCqbRWcdrr16Fhxjt2Z/HmRTLjF+sf8wRm9w+eaZ9F6+On80BeBhtbHo8tM4MuHRg9uTPl0fvoxt6VRsFkJF9OfWhicWD7WoEyqzKEj+Mqbw1qp8ivdRXciGNtbf5UVR+aMOmpMhFBm1WcAOpP6qAo7KTq6vyTO6LmRMgb5u1G/hb+hvjdHQ9VDVj4AJ0GW04czS/glIsP7Ajd/U9zrIcd3Pjc+qIaxFLZL/VBsSklW/h0ibXP7rsZFxKZ8FPMqxn7SHAp/Vco0pUMmNjkpdslEY4mQ4NOoevT05Pj5h9jZ0qjaL9fnQ5f6WgRmQwuIDSBzA+jzDrgi8lhMCsEuAPCdIc9hQsv5AThC3x2kDIb2TE8KJo16QWSM5r8nhRz7gKDQgyYvjVeQoRD/i7/SYpC8E0mnhVfpCH3UuQE6IRCNAJoCAyGTfE/hwTZvaWmHsAGDQsPT4mzvagCeOJ9pwOMPY8gSVzwCOS1/YL2m6WfjMKaXnARyty6RBLfxH+s7A4Z12pKzUR4/sD6MBUI5ABjB3bHKYCwCnVDEA4OZSeZS2ymdK2c5T34hxa9grN7I4ZrXXqR4u4aKM8cCdDiaG9c+uCVz4IF0/ChyNhg0Mg+AwdBs3t11zcUKbTK0t2llDdrSjHW1Fp4KzGM4CF3/gIexfCN8f/uIaNz9xExcffQhGTh+zxuwGYX6V8c4ffzopIz0TfudbngwKNDndPeGhs4eYdQ6jsyFJMUJKQTYMuyb88Y//NoAcwk2iSAv96ju+DS56YIqszhyQmRqYI0jM312+PVhD7oT2/tj3/CZ6cpMI2aKAmtM4QfgBwK+8/AEAmW2Uk1U4iVk3hrwhD18srRZRoaUtNQcRiRmil4c2f4a+tRlfYbXs4ZnwNz786VKz34hOJZ9bEat++V0fmiA+R28weDuJtPXhBy8UfQhlE3oVVm+IFqRffPb34e984FNokYHE4OwierNs05JnWNAav3b9A4WSVEB7Mpf+wAMvpN/0GIii89DN8Vuvvjv1TZC/f/2dn56Ml7QnlDWmz0JiveppxL+59X7cGQNXI303YAzq1P99By9hYIt/deUDqb3/2dt/IwbtbUda1+RhcNMtiojfAPDfzW4f+5ymU7FZgAEa24oKyUJFJpswDXEK3772dupq7Am99ZiLeTV5X3KSqXMqgBEWPgXXrUPhsafkPeo9YWZcQmYCyOZRG0WcWFdPDvPYeIHjOlASPRZmSJ/37QqHLkyWlOJg7AoXcSFCYCn37IC9Btxb017aLFglN/Iwxk9FFmsBF0LTy0Ip4oeSwSzy8GvuMKMxpQQAMjtrwEUMzfA6MjseBjVYOPbsUJh3gYbplGws02PfTE2nmiwzepL0C1pWDONdb0wjh/QEEgc0wON9CtGfgiirBbZQSZE6ExI+LcxQbFCyeGcppYLHjFzTdLowa+ybNY5I0hKo9BHJuuNx1h5h6Xss7JA24X1awQrcWxTVlQUkBzPuAIsJ3PvNlwrgjaaGEmkS57DaKDYp8HI8yKxkmgijyC9BT1oL3vhy6tPh9UY+bozBqUmsKI2JX4e1NxWu47ggv62Yki2yKmpzGmc14Sf3V+UM6nq9iQkeoYjdOmmnr/7K5uYn98jvQZHoizbaqImXDdpWn6f1nuxdp4C9lV9ITRPUaQwbXNAWSn2h07FZMDYhmMtAMxtIlEXZOzBrqCcvorJa1DkfimY1Lluqg7b6gKOgqcVaXmQrSGxwMCuDy0peiFA3FYPiq7a0gsfK9fpazS2Jtl5TC2Ke2keSOyRHmbLEMY1N7Bvy73WovU3z2VK5yPRilTEZ4veQn2NaULFI2aeNom6rpc3vWUdcT2UVjkl5w8nPcIHnyM9xrNvAIb9fV7n7mpQ3ZBq1XOak3rRMulYePrr9ANAOkY/YFnvs5nI32ik4d7SjHW1Fp4OzaNjmhSZZn1v3qHJSedF0VSA45WZGKY9y9lCUE0WwBTUNvkTijfKds24DCLK3JL4VjsKBknLPs0ksssiZjs3GwK61Pd6DJqy051y+fA/jYVIbwpg0kgwx0ktI4oUatzA2JrUz/RVZmU2RSHjShgY5NQby3YPQQ4ffIAy+i0jLRlkKaemEu1FtCeUS1hFB2WpPfj+Vt201Hg7Zq1c4vTDmRqGEPVxk9X16LvBghRKSYv8peN8W4xLnZOZEIw9XtX/NthDdpI0tCrzWFJV6EkbjnjYLInoWwC2EKHQjM3+UiB4C8H8BeBeAZwH8RWa+dnxBAHcbOhmV++xz4JEAm84ZyVIAX7WxDM6AyIbs4zo4b4zLKS9CtONiDanzepDJQBxjGGtvCzdhQ4y17+Bd3FwiXmJgC/hSLNDWkKXv0+dDN0+ftVsyq79Cck1bPYC2NcQoNjX304AqDAAAeGcipLqHp1JcCuNsMJBNnzdZQzwIo4KZ6z4llGGcsHUfQtlta8joTZH5q+x7VuIFhejUGgIP3BnnhTUkLb7Y3duuzEgmpK0hS5f7NrLBynVYejXmTWuInVpDOOh8nA8xSGQ+ytwqrCFscMvtYWCLpeuTEvyQ5zB8b9aQb7SL+h9j5o8w80fj978H4FPM/H4An4rfX1f6RromvxF0Ly7f25a/TR0tZWedGOfYeu7BTfv1GAODqZn02Pu3mDd373NDDwbRXU11Dynn6gnauW27agvM3TLJ1cmMTkpvhBjywwB+IH7+WQD/GsDfPfYJD5iBgb28y8kpZCOybTRl6D1tOjUmhvYXLL0nzDqHRTeGhMDaR8MErk3Me2K6O8RsYg1hnppOF3YoWMGFHYM5sgt7tI91zWkM5lGUp7OcQvt2lRyf9s06RbgSb9px6AvTqbC9Yjo9sOtmRCu9CA+6YGrU/eqtgzW5PKGh84ALZssFRZNvFVRFzJIDd1iYIXqEZgUnEDaBWTQvpnEygUPQplMAONOtqmhfHoPvykhZFLATvXWF6VQrheVUXTJjQUOh4PQwsD5cl/GQtonpVMyV5+xhHicVCUwUtRZceAh30X9k36wm1hAHOhZnIVnOFzTgjF0lLmsWTfmGODn0GWKcNUfoyWG/y9HPDsxqa6/TNYdIZZN2nGADudfNggH8Swqz4H9j5p8C8Dgzvxx/vwjg8buWQtlZK12SBdpnDIUWQ0bOL5JFL5HGiTE6izXF0GTJ54SCsMk5QfEKWQzxVG5WyY8i+Q4ENnEihrguxDckpLpEDAFQmPFE3Fj5vmBfBw4uzNrhSBl3ks5Crk3EkCgWFGKI0qZrMcR5JWLHv84RvDeF5yW4dH1PXpQwZVQxRb6K5iR1AiUc3YNw6BoRsdigV20Yolw+OluMFyCZwvP34P1JkxN06XvAhDFbVfoB8UoFgFt+0bQwyAI89LOibyNzEEO4T+0o0iZWXqeaUrJkMinaWhgrixG2EB0tMQ79HEvugxgS27bkMB5Wme02h9UL4lKNszhOp1TTvW4Wf4SZLxDRYwB+hYgKFzZmZtpg2CeinwTwkwBgzz94j83Y0Y529EbTPW0WzHwh/r1MRD8P4GMALhHR25j5ZSJ6G4DLG579KQA/BQDzJ59kUyE45RQSBxuyNYJTWN3IrpMWQ4DOOsxs3GeVcw5MqEbEEAmWIpYQ7SkYxBADjvcyBwh1KYYM6MjD2Bj8xmYEpwRT0QhOQWpq9vuMXSYlV3L2cRaWGC6OiogNcmoedKsCkSgcgD4RJViMZjVFDJkgODsL54AFDUl8AjK7LH0Cwom5oCFq42PfYnkduQKKH6ibiCEGjDN2VQScsQhxN3pyqR8r38OQx6xzOKjQniJuSPssPHpy6GmcgLIOzKoInuPZpJgjMhfO2aP0uyBUNRnyEzFk9CaJA/WYySk+IxesMUpFKKLJPq3wQLfE7TgvBPWrY6v05HDWLtF7F+Zb/O2A1hGTosRFVYdWQIdxbcDOT6B3es2bBREdADDMfCt+/pMA/gGAXwTw4wD+Yfz7C3cvDPDdBjFkFsUQRwVwSwe7TWKIzcz16CwG4hCgNmUka4shIu97WBVkJrplG1+IIXfcLAXXFRq9CfEo1IY1sMWhm09eRrKA+FnxWfQXWgyRBajFELl25LIGXZCJo7eTADF1dO/BWXg/hYaPowF7gyX3OQ5DpZRbkwo2TF07YC9b+CpDV9NciWgFUAeEWHR0QBeJlLUebWK7E9V6F7YhMC/3RdtFfLnt5mne6MAyMhe2s4bkNnTeY+U63PHzEqkb9Sjy3MBdYXYFgDXFIEomtCtb5+J74hAMGAhjesstMHAQgcd4ctzhGSxzsWFKnaI3kWY5DtakqRiyvY3jXjiLxwH8fIyK1AH4p8z8S0T0OQD/jIj+KoDnAPzFe6ijhKNuq4sRFOSWt59Ebms/v3nAW/4T+jf9/LbuwlT5gYTn69Mc6XutxJJwcsDxaF+NO6nxKGWevZJqc9ym8Z20NUbJMsqPImA5ZPzK+1vafccUObINSMYTvGtZeAlbUfdrw+jV79U2QvTpezeNj7Q1cW8RW6PfZ2jjtOxNuouaTmIfIb6XLLivE82ffJK//S/8HcxuhLY89MVbeOpv97AvLIrckg9+FZjfdHj1x+6kiEjeG9y5eBBg4VqRaRnchUhTB89F785bQVwxI8N8/FUASGy/U/gGALhy+YGAz1A5ScEEszeGBLvCbVgP9hQiXFGOR/HQ915M7KKGcIuyr7euGUnp5VfPxX5RcJ6Tv06JY45gOw9TRMoKYpI+1W2X6x9jHk/38r7CxyP7sqwC5/bkRy8kBVpNuh+1k5uINc9fPT8xyTITnNPeu+HevncpLqc0RYRRo8QbAnDruXP4jt//3KRN2oFOFlK9Oa5jyMQLN86la55zJCtpw1ylR2xFyhqdwbUrZ1XlDIwGv//bnq/aFJSXOoVCvbHItY4cXrh5PkUy09HPtMVq0Y9w3uDSpXNp7n3Xe59rHgT1uMj1G+u9ScSuf/s3/g/c/urFrXaWHdx7Rzva0VZ0OuDehjGxoomMHsXI/jbBuLzr6ohBJAl4JOAvGGYdIbieUnQkiaBFDLiI6nTeVm7gCu1JyFnMEZ71axsiiUtNMRO4kdiOsS7HVLiZp7YKqnFQ8rcyQ+YM5tFcTKotiG74BLjRpEhg0raQOjBfKmIwxnIllmdNEhVscBbDpuy8iuQUn2Qr8xodGuvm8FmnHyQC1msLo7IwC3fUyjZuBuBoLHUWm5IB1xyBIcbgLZbrvuBkQvkEH3UWrfekr3tPwFCNuaNpu1DiXY6jI/RYDl3qw2q0BeOXyvQmiCVrk1wjbg/HR/aq6dZqPlFsfyNNp68PMcEM9bXwR66zKR3qdEAamHB/8lD1CFnUbfAETahZQvJDyXEMQ2U1SCm1wVOGkTNCKkHtSm6j1cRwKNfkCZwmnJ548pyCcVvKkZx1bI5i8UhRUV1AVrHb2idFQ7WVcjZlA7PczqIeNyG7IVXAtkTEkyzskvdVbx7MgLWcxEl9r1GwfXlubVHAwFtUx/6or3edK8SmUHbG0WgLhN5UZIGNZJQSHWmD3jRmm0QCTT1xIZJ2jXqJGJ31MJ6KzPM6tsbdyIOw6MaJzuauCa0UnY7Nghi+dhOQSR6v2xWKpLRFktx4neVFGgTOAgAUmEswPME3JHIWvHmSTTkLgJ2BTozMUkf0DdHAsZZTWCtepl4CrDkLfcqqhRbaQfDau6zFWSgpM0USH9sOcuSRkvwevyRz/zSZYhFKX3Ob62TKRAEIxg3Fn1d9SFHIHZLDVc3V1O1otc17KlIrlkmUw32j2mhJc2Was3B6zAHEMRsq/USd9rHmNuT7gJBGUfvRTDiLOJccx/rj+Iifyra0HLu2A+GWdDo2C1YBadO18EeQv8dyFqJs1Dk3zGbOAjgBZ6HK38hZkDqxW5zFtFsFZ1HoG1VQ23Ym7rj4THn6yWbhYRLbYJKCNdvfWQIU1+X6IFrpoK7NwLnxc7+B+9AntW6z5iyErOVSwXmMGDJYZMVrtYHWGzBVnsrMQUlcJ0AK92/mLOqFdRxnIYJbKzJ5awOT+3viot6W+AMExadh5ADTUAmJqk1oE82sm4g3b07Oom6JcBYRZ2GPcjRm0a4DKDw9eaZe9pFJFhJT6CwQcBZRT1BpKjLJJqFXskHIZq5OF3aB8xBdgGx6Ovq2bESaEfCcv+vPnHJFoNyopL7YBz+YkrNIBedr3igPVtG2S36UimgIc39ZJehtWTxaMTxTnZ7AlWUpfOEc9jBeH9ZdGTKQpmEE5bsZCHeGKTx8E+n3Kos16EiEs5j2Q+eD2aSzoLXi1ihY2w63bFerX8yE5bpH17l0fdIXRkrijCGHBbgzzDZyeC2T+Z3V9P6CQ78L7awhO9rRjrai08FZMKFC8qajQXALbAENPus6CVKDkFPEAzQqMaTLOAvhWjhCvcEBDg6Up3tBcrJrBacHaObA41TB6XuOjmShwFk3NhnCluhRKDitUnAaJe8LBx4VnGbmpgpOLoOjaDHExxwivg+w+VqKMAiy+9y6Zn6Jbem62QPZUqZMCk4tOgLoZ+PWCs6jnnHQl5OkhedoXRdg3I354lgFp86f2xRDvMF6piwQxODRYL9fv2YFpyHGzfk8Y25UG2oFp/OEwz6H5zvo11tbXTwIq3k3udtsEVxK6HRsFi0FZyQxqfaVglOzjKKRy6ZTwCxNkPsbYoiYCDVNXmhayZWCczDAmFcbR1GHxgAekjYGtnE7Baf+TYshInJovUwSQ9YWbKeLmtW4sFVlxXK7sZ3rlMbQ58EbrFQe2JYy8bjJ7z2hGfasJYYMFk5tvCmhkV548bsZpibKk9J63RWLoxZDStNuWwyBNj1TUGzfa7uW6z6DDF024+q5MrjYVjVeR2O/0YTdosN1PzWdnkAMORWbhVkRHvnCGs99PAzUcPYB+HGF/WshTwgA8I+8givnHoJZW5ydrzGLMt7oLFZ8AHLA7Fqc5CPwgR98KsUb+J1HnwQA+KUNi84RPvTgdQBIodUPx1kx0F+4eDbgN0bKSi0PfPx7fzv5EgBI2cR//Yn3gijn99B5PXS+DPHROLDr/LlbRV8Pwq/ffC+AgKMQtCaZoKMAAkfh1xb/yR/4TPJf0OVrV2idoVyuf/od72u+g9UYTp3vfvTZlJ29VtaJ6XLwFr1xTXj6J9cfmpzsozcYhg4mPu99yMf61z7wG7kPjfwk+vsnH/9O/NFHnirKrQPCrHyfnNC0r8Ytt8C+XeHX5t+W9B7MhOUY/FuEo/jP3/UbuWzlWyLBiJc8w2dvvKeqs8NHzz1buLaLU1+dF6YO2CwpB35z/324sjwDAJjbMY37Wm3aP/b234KDwW8++f5Uxh888+wkT4q2gGlXgzV3eEd/dfLO/qu9G9iWTsVmISRpBmnkIk+IJjOgzAkCBDFBnUhMBMktovOKJJHCU/JalbwfY/Q+TQvEcBYBRCkGwr5Z4zZnVnRuRozeFDBdAEVej1b4eR24Zs8O2SlMwdgNMbyhkOBZWVnY+iIvCaAch1QzdPAd8XbtY39rzsAZg9Eb7NnsdVpr2ZPXKQXP0JbfS1dZHHL5PictJhm7IQXaSfep/CRAmOTiDVznGJlGpmLMzVB4D3sOsTv3zRoLOySOMoT/Cz3so9jVCq4DKD8LHxZzqj/es2/WRZuz12lMDEUj1tw1ubN9E7yHZSMWr9YQ0TtvQPtmhYE7dJTFzwOzQk+uCAC0ySekZ4cDWsNV5o8TRRrb+s4d7WhH39R0qjiL10wbxORtSPIzTByQtC2fps80m7EBW7FdOzwmnolNoKwL0/gAACAASURBVFg8bbRLtISYa8TeTDkxTpDcpig75Qzh4vfJqX4P8TiLMqomWfiU86MV4/JupHOnaOxLkfu5MQ76tN6Ua0PmjW5HSDjEKBIT6d9VewSd0Up4NclHQh5DrZTWofwSh2dTm2suw5BPv78WOl2bhUJabiJKGmxh0VoLasNXRthVOD8Xkv2ohXCXxT5NKuMxwkwmnE4CVCQDQr6mk9uEezI8Ow0C8cYBKZPeTDebXH7Zv1Yfpf22moBGiRnF5ATDqzpEt9BK7CQWB1LfdR2pbQiafr24iqxn1eYwXWQ+jWWZMCgnBNLerLU4VgewSf5JUdyyVG7GRo1ZETwXIR1ACtZLDFukeI+bEUyae825osIipnpU3yYJlYCUrqFOEeBj8OA6uvdJ6HRtFhppuYE4RnlKGuq4+MubNnwlxMWXTYwh9uZm7X5dnoSPT5NOkJEKZAMEmfi4vB6hHJPKGJMzk9RJ+W9hpcnl60AnPgZbKfOGxAFVp6R25y66mODvJsciVXk9vAreMrCNp1SpTJO8J/V5L5BqVt/1c+mzTADVNKdycuQAuibWX8YIlZiWUAtTdBYhyE2OHSHvh3XfdcUqopQDwbGF42leFs+Ucr8KrTkoGnXsUocybsUaQYfhYhmt96Lzhsj4+gATzu2NuVumOWimuUgkCM9rpVO1WbAE5+1MEaBXk+9zThAAKS8IOaSFRBwGXbJkJ5Od4Qjp45yfIZ42EmItkaOIAFUwZY8U/s5XG8joSu6ilb9DW0MMcu4PCc7qmVI8CvbBKYx91HD7PJnYmSIg8CZrSB0QGMAkoY2QKPtC8NipGa62hkiA4Uk5bspljb70kBVriM5RcjdryOhNEclKPyO0irlYamuIKHeXrscq+lNwtXkAKPKSbLKGrJQ/xgodVr4Lkc6Q32VtDRnIbrSGOISAvfJelq5vWkMO/TwcKpyjud1yeyeyhtzh2eSdnYTTOFWbxetJr2tukS0245PoKk6cM+OEfblb+cfhJE5Km6KAbUOtXBv3Sq93ecBmi0FLZDgpbdK7tHRPJx3j10OPVLThdS1tRzva0VuWThVnQTGStxmmOAuddEgSCAFISYQYCmcRMQmCsxDUnncUtkdHyZ69sGNkCauQbBHGTUbhLDjY6w+RHYf2zRor38GaoHQdIqxaJwEqnHviiXHQrdJppKNOSyg8zxFfARNxFjkEHFsqkhiFOgJbq0UPHV08JTEyLoHVNHkOrtJnulUCc02SDEVsykAqyZASHwCg79yEqyPH8D5HLvdxPHtyOFDYhlRPASYLSYY644skQLnfStyICZJqBScQIqjvdzkyu/M5d6iAsvZVlO6exhwEV6wizEVEdYkKftYsizYLfL9OMlQrax1CZPCDbo2bEb+x3+U5oxWcB2aFgR06cgnv8qA9nIghUmed0nBgiwfNYTPZ0bZ0ujaLpAE75qbWbxs46jDYDRmdy3u2TutGx5tN70X0aYkG27oPH8cC12a/lplu8oy2UMRNqLaS1PXqz8dB2o8jbYGQdxJTArfvP6l4pu6nQoTIpucWpb43fg7zR49N3KjIJFOnJc6fk4UkLOZgvWmYtU8qqn4D6FRtFsX4bJpn1Rim24iPeUiepWRuqM2ZybSWQlJxXq13KbY1acUGDyi5lLLyTqMM9d+W7kPcqeVzCrJbmTJrjXAru9am9sr10jSYNwXPJpUnJlPHtsiJUi+2MmZIyWFR4/RP7T6mfWX/pv0VrqLe8DbqBjaZpRXmo6UE1GUmbEWrjEZ5m9pft0n/tWAMKE3fwlXoerxqU2lVCu/HVXPhJNv5qdos/DxOps4EnwjVr5RHZM4pJwiAlBeEnDIxxpeyjhaGdMJZDhYRRpH/YU0ctNAabOSCk1CytACAL60FQPANGNgmK4DUJXk9as2+zuuhP4tlRKJwsw+BbNgRHExyEPMu+ItIXhKgnR4RQBI9gNIa4nyOPC3kYozH225e/FZHfArDEOqXnB6aRmdSfNN8zcJ7SrE9xdtzyT3q9aLTD+jv21hDJBu9toboxE7LMVtDPBMGH0298Z3d8bMkQkxylCBYl4r3Rx5Hrsctv1cCsyKXOBVDqNjAxaR6Z5wnGPqS8jzUqRLv+NA3SW8IADfdInEyLolMUVyn7MkMBPHkutmfmE6/0VnUd7SjHX0T0KngLMwIzF9dor+eczL0F2fYu8JYXAvH+guvnEW/InS3Ca9cOBdiWACAI+xfDLbn2c1wiRzjS5cfjzEADNytmED2dgCw0Ej4vQtPhGvR8cnFaOHCwcwv9jBjcN1OOiEPfO6Vb032byCEYnNMuHFzP4SvOwq/fYa+FZ2ZhnHTeUP0ZzlZ3Mv7YUwGAluGGcPfLjrZ+Z7RjYRPv+N9RQDbdJopHIU4jQEZX3Hh2rlmpKthHeIz/pp7XxHXgTCNJsYIJ1fL/HrtpXOTa2CECFPKexcA/tXDH0wOfZpaoemeeeVhfNL9vo33ASEsgATP1RzP0dhj3o149tLDcBKdmwk8Rm40tuuXzn7nsW1Ye4sLt88V9yyHDpePzlZm1DA2rvF+heQd9NbhmVcfwvIwcIHGcvo9YVOI8Qvzj2D0Fl+/8XBSFL94+GAh7uq21jSyxdv2bkxQvtfHl5v3t+hUbBZCRkLlRcRTMyxCjOcA5Ulah0BI5RHDa7i03Mh54ptoxSjuA0L8BYoRtpXqoqUgZIguoVSgSfCZHGCHUyBYaxiS2cAazikFK7Bm0lFkUGWO8tdQ0unPXaqfiyRKQRVTxsqUmKCGOI9NNQmlvFEsG9EzVn7PDZDxju2WRE0J753Lby0yfX2MdRDxJPlRrd/xhtA1IOfWBLmejE8xUjm9tPze9TPBBV/AaeHayKYslxjWhLqK+J3gjIKN5dZJiwwFuHxobx4TivOQCCDOG0dPHp6CqCuldPEw0G2SA6hWmBsOZdRB9E9Cp2qz4GoyNXVPVN+8mTZF2C7q5FAoM02kN6lft2PTzs0cXNjzdwVJB0+vcQl/TikFy/1qQse1pYYMF9BhyCLJvIKO7MwRVq5TGxZ5R+rvXMLZm4GD5DM3riPDpVt9aH2fZPVqlUcUohDoJsi46/kg7WLKiswChk6TU7huLyGPQ9FuKu+Vz0WgHXk2RiiTNsg8ZOSAzqhg5q33g8a1yVii7NNJgWSnarOo6XUCGb6u9HogQ1+rZ+omOmmb6rD8k9+rsn1jI31N7dByzGmhmqNUVGNIjrMibV2d4mJaeVfvdW5s4jZz0OjXjuo8nQrO48brjZ5oavKcZLPaFhNRRLNGuTCpdfEe6V6wCCe591430dezrNNK9Ubweh8ad6N7xW6czs1iRzva0amjUyWGjAeR7ZsZ0MjQinITYdDDGQatDTjyVeQIdgDgs2J0AriLilM/j0CVDuBVtPm7oFRMEbvjbr8YQo5U8rkg4pBXQ2eiXiO6Qa9jZvWozV4tewxWLCyxPYzkVTp0PuU+GTqb8BUmQt7JAZJNjTxBos8ZhHatxg6uyBPKhbUFqGTweF1ydTR1OcS4vZw3M5vLZxnXTdYQWtOUzfIhPaVAQOT9HI09BpoibFvBcpkJ14/2Nt4HBIyHwO41d7IeLTrbY1h2OeCtR87/Ei/dHDKOo2VhGL3BnVXGrggQ69pyr0SHIoxRitht/CR7ubyDznisljN4mY+jScryFHyZGNdW+/AgrEebFK5XlwcbI5zXNHqDmR0n72w8gXPaqdosZDIxxQXCDfnKILxo+Sl+1osaiMojb4LiUZszxGoRgUPsTHwxVIoAKhBPVjSJT4Fqj3yPVpl0mQlwVcx9rQhzlExjziEn5pGNKVp9BPiXDDpRGcZAsTGoJiYalIuzU4uOY1sKIgaY4JzJKQO1zpKRfWw8pbgiNVE1DqkvTGkzl7F33rR52wa3zBw2g6LcerPwBsw8iViWxslRkSBKMtiJKlGbN5txRLl0tedYz+hscX82nWYFZw1UM5T1CD6C/0LFsftEeY4TYYyxLLw34GQON/JIbtOk1bHt3mB9wnSHNZ2KzWI8AC597AEsLofv558asPzENVx54BF0h3IcDehvERavMj74E18pYit89uF3hSxly3ivIzx59g7m3YjBWTx3+QAAMLtuwRYwa+DPf99vAUBRjqZPnv8QnDcYnUknrWfCRx69gDtjPl327ICBDT5zJ5xKQ7SX/40Pf7oIqCu08j0M+RTxGQAWNCTE4P/92IdDOREz4KKZUjKFza3D4A2++9FnC6cm8TXQcTTOdMFJy4BxO6IYf829rzCryYl4ezmHcwZ/9zt/OTkqtZCU9eea/vlj31V8N8RYO1vEC5G6//BDX0/ObqE+nsDGBw7Bgf/J+g/hv/m2/6dZZ763Sw5dGsG59DMszBq/+o7vwJFCtR65Ho4JfWR1vu/Br6bfQkDicoEf+jn+9eLb0/eOPG4OC3ziHZ9KKFrd9nV8vzNy6XNNM3L4tXd8ANfGgK+RyOoWPqFFDTH+0JmvY+AOn5x9OI3jf/HEr0aIe4kSbtEaFkvfJxSt0O/1t5v3t+hUbBZgwDjGRLPHSImDSALXRBKbuyMCGR9O5pRFPeSfTKAlEQMoW8tkwHtyMGA4Kp2lAKTkOMLtMxP27Lpg3fbsAOO7iNcARuVR2ZObLDgJ9qKjWi/MkLNoxzYMCMly6xSw1nisnMXcjJMo3J5KE96cxtQnMb311iU2ubB6GA/m0G7dNg0l15+1V6Ymo/AQ0pbOeKx9CRc3xFhU0b1lE+sp9zrAtwNOoY4EDkxjTS5omDqEGeCA1pibUUXVIhh0AGXv0eCxGto+IzeJPuVhEojMxn4uXfDA1aHuxJcmlQWXruW+hu8LGrBvV7g5hsNGonWHeiUGqMeBWWHpOaQKEM/l5GHLqo2b4mN4WOMnXqftLDJt2ik4d7SjHW1Fp4OzOCG1bMW19Lyt+e1u5qRtzVst06l2RwaQBMrk1szlvW7D3t1CjdaQZgnQWiIMp67k8nxTOUml6FFzWslVnKbXhMuYRnjiiSCdvSlLqLK4duu6Bw6Bb1tqOx3VXP+VshOlcT/+XW6MWK44gtq7NHm5bnFCl17CQdm+CfdgkL1ytZfppn6k+jeY3S0z/FvC61Qh2GqiDWOQQ9wH7TFLOcU9yozRKiRSGWE6g2aAUrvMjMki1aHhBKpbtq9eqNWEQV5wx4W2L9B/1UKXKNytsGvJzTy2uQZcCenrdcRtD4lunUFK9WbXijmxaXEKpNui7aZeupfrzWRaXr0piBig9Styn1XXUxh+cNoAJtG9hShfa7nw1+2RcAE26YXC59ZhEMZgusG37htie3VQnDr9gw7i3EoFYCeHxPZiyOnYLI4BIml0riYt/yU04qZtUhfSuEcvMh19G6hAVALjRY54FYL35gjftSlAy/qTekV+3kIabAVrabW/JpGdE9y7+G0KIZ48XwWA1Z8lkK3ct23UJWm/A02iR0nZeWMiSMrWevJLVHNNOuJ10Y8YHbtesB6UFJm6fNvod4geoTft6bh7NgDlYLxAONU3cY1hDJSJe8N8yTqJDNmufYla99dtm7Zje97idGwWJ6QwWEEplUyCk3umfgfNstTCb9Emu3XNGEuqQ91GR8FqkBVleWNpLfBNE6qZUkD5CxhwXLxln2XitXwcWvsmc2iDK9juvIDlAZ1DRG8mspjyRrph7FhydpTRtUEmbQ51ioDWG0oBXZAXex2FQvf9bvOhjj/SSgmo40VImS7Z8zdH26rbEvxHzMaDwuuNlNU72NAPVx1yrd8dpv4u2/MVp2WzYEzC/qeTXYnJMg6a9RcxhGI5Qp0JcRudN8eKIZJIF9GkVoshRTOPEUPEe1WLIZJLIosZJoGQQkCUnDh3TR3A7TyhpgGi6o0rrAaiXddu673JZkQthrRicBICjkJHmZIoTLJR9Kk/JpoDW3oNbcor9RhZJKLUb90HSbyj41nKdUs8WYi5vEAuRvPSYoglD8vRXG0crJcJldsmC1+3pacRJlkjIqCNXDKzSv2d8cnakdq7QQzR828GhzVF6wfq6FcheZCYOXvj0MPBUbCEiPXGEKNPomy2iDVpA1e9s4bsaEc7et3pdHAWhEnG9KRgFE4MmUHQegLH1NRZjD5kBfegY3UWkulJaFudRbo/tiWEist1eTYpA7hm33NWrxztOSSgieHzNrgd1zqLwdvEpcipMrAtwGUDhcjYXvWLsRn56T2VYggBWmwyyG0PY2UmbK30XY+hV2Mi3wOGpNRZuFosQc7m5ZgmcriOASrtcfCFziJlamMTQgqiatsGncXA3URUHNhO3v3oDdawmOkDeoPOQo/VmkRUzRnTZAwQLVupXm8xwGLgbqKzGMiUOAsFtiszoIX6Nc7CkAe32I0NdDo2CwaoQh+lxapwVXoeCbs9srKGCCfIlRgigQ8aitSUz9PPKvEisnWeYAWGHkFLOghLZ1yQ00UMMaUYUgdzFXZ1YYYEL17QMBFD9ELrKzFEsoMJ2ywaeInrKJRAW+q6jQCnelOyxOAohpRh7X3SUczUS1rQgAFlwN66jynoj48pH8XnRNIGkCvS/hmEAC/FmPkgEljiQkwAptajdUR7FqZMclhyj55GzE0W/YTF12JI3T9HagFj+u574zAzDjNU4hQYTpmMe3LBVaASVRx5zOCjKFyKQj25dBhY8rE9Bh1lsGGfRBZOuppBiX6FSMIIbaroJJ6op2OzwGbOQgtKuq+tWABpvgoHIFyAHo9qbGquolbO1SJgnbPSM0XupjTbaO27oOqEs6gX9TpyFkBWqN4NEzDliKbXck5Sm+rzTNGfpaxHB2cplG6cv6/T+jUYYGP/ptRSqIpCU9PAFmt10gnWZEZj8psIuU5D4GU9ZiExsymQkYnTIRmRqLBFCJ471OOAUlG9VpzKOsRfT2MdNk1K6N2gVA7fgwVG/HCk3swJmfi5VGCHvsqJX7dnUHMCMJGrCPcJ95g2aM7PFcrY6rMDYV3Bvd98nAUwiT/iq8UHnDwYTq2M3Hzf9hiB7esuFYUAChBOkfm6EHWOtyRoqsPd19d1FvUW13TXPigciGAtQtuE9a2sJVVbNvkppHZWOAuN3TDVdcEUFO2rQWeNbgmXUeMstIJTt6fV/xKEVrehVN6elJrYkajgnF5vg+x0u+6W+HiKa9kpOHe0ox29znRqOIv6IM3oy3ztpId9rYzcfF9LSXdCNqZBCeeg2NlUfqHYy3XVYshxXEBKqycKtQrDISLPJFeEwqAcV74ArVpYgIRtOEbBeTfSrLngUcSjtQaDteNNlmJIuw5TtLWl4NxEtRii76/F1Rx677VxGGW9DY2/ak9zvm4pTnzTgbLeiEzZ0zruTQwpyqqgx28EHZdlexNQ6CTiyDYo020pYQoaYshJMoWfRAyR8ltw743lbyGG1G35RtD9EkNOx2ZBgFsQ9q5ErfS1NV66cQC7Jvg+dubFPexdYixueHzp1SeKfJrr6/PAmsi79YSvP/cYyDLYE/ZeDLri/iYAA5gB+M0r7wGAIry9Xjw3b+6BPYE9YTBxmJjwK89+O8ZRKdqsh/eE8fmDAFxahpf1y+/6UHNi6ZNJPnfkMEYF2fNXz4f7YtYujmZTH93vr5s9eE/45PpD6Gx+8SlSlgoQ03dZ/SjXm3k9ANCaQJ7wzx/7rszVFGbJ45GuQl965fGyXOKUhLjOgfpzR38QvSknr2dKeTGAELTFEOPCcw/jZx/83uLeuj0DG9iGnmpgg548vnz9sRLhGjOSSX1fv/VwLlvNBXlm8BYvXDmvOhfyzfxM/33NBay5jU3cjyGPp28+WgQqauWK/fc33oHRGzx96ZGkdO/rzRL/f3tvG2tJcp6HPW9V9znn3jszu9xPcne5K9L8FLmEAlKKncSU7EiIRQuQ/cewgsCRrURCIMGyYwRxfgQOYBjQjwRBACM2FMeRFThWCESBBWvh0ORaWtGWFDKSSVv8MrVLandJ7c7uzNyZufee091Vb35UvVVvVfe599w7s7tnl+cFZu45fbqrqqurq956P55nvVbnQbjR7Y2QsV7uf3ny/CnZjsliwnUqkOiCZ8EzVr5zoI0uSieRcZyRj+ARQxKD+yr1eQyD4GqlIGIMUyunnBzHDXsqeEcBRFQmGpUdeDZypJ0cGyKgycwOiZ6uMR7ehZgQPVCMAbwPHpmEpGVdQJ2q0KCEh6I+Jt8LpCbD4wWFMsJVzc8h/aQNlzVmQ4HVEF8+vaVy3hT3JvwXo/ZyxWYv/UfrjYsiYsgN1+d76F2YcCxl2z8DGKqtjS5P84CUMRCqXYbhjRhP1fG0EEgUKQOYxrNoyaMhj5Wwn5uciSvb08CZ4uAjj41R7vmxdpiTzEp6BjNp8D/PZntn4NzJTnaykWyHZgGsn+LizHluEwLLv7PnzrOIiOq2bHL+lBqrj59GBgPk+I7892I2FFnFy4OnX7O+vToCU86diAY9o3/W3UuK9VCrYiDiWd/O9Wnw0+tgEWg5kXNTl39WPVPj6zxkwx4xi7kaL3V9k1nWp5V7Fwz0tbz1NYu7aKgsiq22AadJrVa/4XLKOLpT/o475cI4z/UXah/Op3pfpJ475eeYbsP5DKivxXg7U7Mgor8P4EcAvMzMH47H7gPwfwL4LgDfAPDnmPk6ERGA/wnAJwAcA/hxZv6dM1tB6xWANKGKpoCw2ghmpSBrSzkAwhQYjZNwlDNaGYlDSFYUMfhwjMQcDdbqu3MmGD51joAnwEcbS6xr8CZQ6amwXzkubcw5Gk1yZ2bo+/yvRtkuypFm0pgKgJzsbYFBkKulv0Zb3dBPnbN5v16do92FEsJdi6sMxYCCEaj+rstR0ft/F21X8JQAbFN7qhdo8HZkr5DjQEbDljaIHUfQ33VejYbuT1GVzhbo3mAGewQw4g2N2fnaOH4doXc2u89j+Uxc8JYuXRsMxc6A4vOR/qj7a0o8GyxdM3pm55lSNtmG/AKAvw3gF9Wxvw7gM8z8c0T01+P3/xrADwN4b/z37wL4O/Hv6UIcMsRP1CEx8gRQapgBkOzrYPVXNy1j26pbd9FX7Snnl3ikSUcexOBNkV8mJYg6XJIHA31vA22AVM1hUrKDtHM88KakSPjSg1TIoUk8InEyUrkqIEbfN3Ca34MQAYbVIC8+x3I7M6ltmR4AEzrfoNtgEVunmns1kddSq/wnXVt4PrT3R19DxKCBcDzUaBWnta+Ke3ANll07ybMhWeu3u4z8PXVvvbPwXX5Wnhg8mALt/SJy3LfZqDnxu/T14A3cYIJBHcAtxXOyidzqFqNJ6zyu6jMnC2Z+hoi+qzr8owB+IH7+BwB+DWGy+FEAv8jMDOC3iOheInoHM5/O68408oaIJHgGFaeitwDMFDQJpXmE5YkT4Y/OGZGkvjroae0ej/OLipgMpWMOjPHBBk9SfnY7TqnU8sLo/XLhEVDcHDIBBG9IPNcEd7AxDla7TjFeJeRFNMQZAt5yPllrLBYgP8b21FJ4Q8y0O3Bqe6YJobU01sGa8XMovThBU2HDmNk1gyRKOYG50XHtag7Hc5sBFG5cPYnptpMugwAwY2am27UuA1QfM8RorTs1SM4iorITg0z4BwBzK/giE5rLhMybYayRvg7h3g+rCeAPAYhz/VEAz6vzXojHdrKTnbzJ5Y69IczMdAGrFhH9JICfBAB7371T0a2hfNEmHMqkMr3/Fa1ClyFBWrXGEf/VWAvrG8rFZ/YmrfKhyBDYY1L5sdxoiKlX6bQCFD5wVV7xedwO5vDZe1NtkTixsKW6TF6tfR2DIu2V6z0AX8H1qdUv8GyoPpt4YILoVWtMa6EJvUHODg0eFs8AqxuT71TZYybLO2VrFGI9xlsc/Vfv970bbyNd9ewRNb6zKACnQ9VzX5b2kSy63wZvwnmctcyztrq1dM6OnsV5sk4vqlm8RETvAID4N3KJ4UUA71TnPRaPjYSZf56ZP8bMH7OXDi7YjNdfzmWtX6fO11mgE+fVrtNN2yHbgHHg2MW8N1M5KomKoPpX17dZXfnf1H2cR9Z5AC7iGdjkmrvJgn6R+xXZ1FNypx6Si2oWvwLgPwXwc/HvP1bHf4aIfgnBsHl4pr0CgOkI932lxx98IibuzA7g3AkWh4GuEADaP3MVVxcPoDk2eHjeYd6E/VrvLG7gCsgT2usxytEBH/vBL6M1LtAbXv4uAMDxSROiF3uDD16+DiAyihHjaJgVlvQXv3Uf0AdvSrJ9eMKPfc9vFzO61PH0294HIBjtAOAj976Y6AV1GrfQC15qVjh2wTB2ya5w7GfwTPj24RUAQNdZWMtwjmAto+/Co2pnA/re4j/7wGdPpUcEMpCKhU/0iJ++/4OTe+iTIVjb/737ni1AcwSFKUQbRpBkUKJf1OA3FoxfOvnoaK0avMFJ16KJNgfRfn72/U+PWMZqakT5/skrH8OPPPjF4twaTfzYz7Ew/Qhw6JZbYN+s8Cn74UR+7JlwMrTwTMnm8Jef+HS6ZgpKf+ln+I2H36fO8TjxM3z8yldTn+s8HOlzTU+pr3UIjGT/fPZBfOskPPf9Jve9RPgaMH7i7c/AscFnHvpQKuPjl78So1ZVtGq0TdXt77nBI831kZ3pL85vYFPZxHX6jxCMmQ8Q0QsA/gbCJPFJIvoJAN8E8Ofi6U8huE2/juA6/YsbtwQ5tNs4HtEVAgiuz4HQWlcA04phUYd1mxhGK/SGAKDpDcU4FCYLj4FNEeZMhsGGyu0NB0pAR7nD5zQAJhjEdHP3bI990wGYxnyQ3wBg366y6i9GSWNgrQdHY6KsOtZ6uMFM0gw6DvSIMnAPTOYRlfE0M8PkZNGTBUxoi5QrBDoC+JMniwBQk2ADkV/qVrVVizU+GTMBD0PhJVpMTHjF4OcADdgYj319P5hOkAtUgiUeRM8WB6bDnu3R+Qx+M8TckNZm+kKRltzYgGsyF6mc42Cwb1YF12nC/4io3Avq02d9jx4GBC03JAAAIABJREFU+7TCnu2S8XYen0+JT8I4oA4d2YLe8IA6GAqAwRnhfHqz0LPFAQ0J/Su3Y3NtYxNvyI+t+ek/nDiXAfz0xrXvZCc7edPI9oR7n1M23X/VdHNry3sNou5eS1lLe/cGRfqdxqZW17UujXoqFX4dQdPrIZsifr2Rskm/3y3ZrslCR1quOWVybFMMRqguMhElOWleyjOiuSxK453kuU+/RNNwZ9mmPMqEFEBgTEPPATlb0oNySEgVDFao9lN1YJor9Ty0gqktsuWRrEl4gEoWdQNfcIxogJip2JUyu3Rcbw2jJ+I5M53V2476WQi3iPSHLluew1TbNL5G7ofcn8kewWP8DekDuVbqAud7ClRCPoEJybVCA6ljWzJ/SAYSThm/XGJwFHgeaWxNTx49LMyEHeY8sl2ThdwvrQ9DZSqRntJB7SIFIBD9I6qA5EGkdB4Q6f1YNWKNu6+OeJNEIIlx0i6xGvFIM4b1PkPNC8S846zfSKh3/kzpMzgYHJPtRAVY6VWwYBFTE8lpbG0alh5UXqNRpjxF1CnO5QuiFaW2RkyO+Dn3zUSbFCqVwbp7qKMPSyoAxxT25OoaKVvAksX9WgAUi+tUI5RD0U0gM58VE7JXDG4JqNci0Q9If8XpokDqishgfQQjrikoeq9CwEkAfE3sezV2q2g8gfqvMTSmGOvOK1s1WeiwbEL5vmqGMoH5B5AZxyrNQpjChLEMwKmahWZ6ChVxXMEpr+QUWb58Du9tycFxiEDQLsQaqh8AWmQKg9YMaBUjWVg9XKFZGMMJz0JWZmNCuzTjWbgfnwy7uW2RkYxKRu6pZDEiBjisriOWMDawhIIiwKCsP2khCo8BapUkVa/EUViUGkDQCEyxUnsEhrIpwF7RIOSlnEV2r0AdkDUeMQoKgxiABLKjYzNqzSIDLkfov0qzEIYzSx4tyj4zasIy8AXDmb5XuTetWQg+hkYSF2OqPrelIYER1yJUA1raifPOI1s1WWwk59hir7VXcBk/YOEL9e9uiikG/innkPBz3N36p+5nc3tPVplrjcoSwytVuwiBn1D1AYxiP9bWW8SgTG9P9G+nnVNSMa6Pe8ltz1ues1R2ua5mQRf6wszVUlI/5PLH0IL6xR9tTdaMIN3WcsLLn8c+p/PL9lpudrKTnWyVbJVmIZMvx62wXgiSCmszNSGQw6qnbBay7xvZLCinpg/ewlMI2TVM8FIpU94Hqb99lSYt9gZGaQsQekHDJs3qHpkgpqcmrTYr3waavmhjASSDlFSqetyneko2CyHoEWNcTZEXiGlyHASQ4wtGqcrSbkXEE0iKJmIy2Kb9ei06dFmHUY9gBaINRPbYGqFcGwLlHjwTlj4HNoUV2BarascWhj0sSmKncE8Nem8Lm4W0Z1C2CSeDkFDYLNLv6p5XPlBQCuOZ9I20SVMF1nSIYsNYclvQIko6vSdGL+jt4HQP2mbRcwNHvghTX2ez6NiiZ5PKvIhs1WSxqTdkBCZzl2wWRTDMht4QCd2uvSFSpvaG9L5R2x21J6ZAQwfyhc1Ch3yL2k6EZLPQTOFyfzXZUPYkaFV3/RZAU+nl8mPQFeWJp6UBiAFTQDb86mcjNRKw1mZRECVFu4u2jXhl1xjRF6YtQ5CempE3xMTPtTcEyPk062wWOYcmBLotuZ20WYjtQO5BbBYysbQI9gY9PsM9NsH0OeENkbEbyuRkgyjP9SVVIwBoBnrKz9BFwOU72eZuxWRBQ0D0Bu0BANycgOczmjcAvHTjUkD7bhjPPvcw0MSH5gh7z7fB8HkUDhkH/Jur74A1YV/dXQ8hvuQITAzyhN947o+Ec60HEeCGEuehfX4OM4TU+bTd9MCnXvpgsXqKkezbr0TU7FjEr3zjw8mYphOqZGVrrUuANLPGoYuI4be+GcoxPdDZYPTtLWD6MNJOWobpCb/68JPFxCSik6006Kwcf+6V+9emzjMD/7D73pSerSdsRrZ/OKZos8gvmmgfL37z/vFM7wk0UErfF2/JJ698rGijyBQk4VdeeQh/d/X9o3O1DN6gMX4UM7NyDVrr8M2X7wvPWe63j+kBMZz/77UfV20Yt2vwFs8eZgRw6cffO3zHyGistczG+BQtqq+V6NFnX7kfq2XQmhLsAHECaU59AcLvHz6Qvv/ujXeOJsB13o6BLR7bvzECx7naPzV5/pRsxWTh9oBXn9zH4mq4kXueG3Dwp1/BH84fQnsYjUSNAx0HuoCP/9CXsGdDuPTKN3jmnvdgcITj29FL4QgfunIT+02HpWtx7aUQd28PW7AJL+KPf/y3AITwZgvGLbcotIBfOvgouqHBMFg0jeQ0EP7YA8/h5pBBRy7ZFVa+wSu3D0DEOD4Kv/2XH/hMCk/W+RPHPqD57JtVUqsPTIclt3BM+OS93wsg5GpI3klDHkd9uLeDtsPJ0OL7H/i3KWRcVhgHg9sut+0eexx/53T8V92H0ZBHjX9w42QPgzP4b9/3T8ow8gnj2VRuiMg/uPffH7+svsHx0KaQZpm4fuTBLxYh3FKXDtde+hYtOfzd1ffj5979f+E0WXKDhVrlRW7yHFdohace/AhuRzQlB4OjYQ4PwiyGcH/ini+kaxamH21Djvwcn57n3IyWHK71B/irb/9nSrMI8RGOKZEUt/DoUW79ZELZNwOefuh9eKG7DwBw2S7j7x6rOD4MGH/y0pew5Ba/3Hw0TQ4/+8CvwVJpeOzjrVsCnHapxntYVobWz7a3Tu1TLTsD5052spONZDdZVCLBXNsi5wmi2aZ2v5ZykSjEO4lcFLmbrGwi6zAzt1G2YhuyTfJ60dCtoxSs5TwGqdeTQg/Y/B7uRNYFHOnPm0wEm7b1NArFqdD5/NvF+uJux/VYmv7u+c5CvYFtmSx4jfOBUxTt6FFMvkS1q1NEf5WozCg6Au6sl42rPWdRBU1jDk0N0pwfkD0j4HLgFEhequAUyansKxJU5nh8DznoLEdwEjFM1awp8JXEERpfyJzjYhN5cc1Spi3uYgBdm/RWWfLDi2qr3A67NplMt0//lftM53H2GqVktonho4PQam/IqO2U8UrLe4jfSdsPGD1XbVIuP0NlSr0O5NPHas+W2Cu0FUJKMcDI0GwxjoI9j2zHZPEayWngsxcVPeBSHWesDtm1WYb7ZjfuZm7NM9uG8URxsXLKiEbPZjIy0FQDvJaL1F+Duawb3LkNZRyIJMKNX7YKIwLrPq9fgetnX/42Pr6JBnTay5siROnujI+63PNf9xaW8+z3N02FHiWSrUnKmlJZg6+7jEsAyr2wlFfHA2zUtrv0OEPwEY2O1aJtJHfTXqL7Y92LK8fPesb6vCKxak1fnaaqS6LcJF8K08j+oPvxIlsASVIsxspdsHFIuedhTgPe4pPFTnayk7sn27ENIWASqJgA38SAJk+IH2PIssCjmRQCnTbinEPCO28znF4MMybOKepLbmA5hNOagk8yZrlWK/zKNwkbEQgq7Mq3cM5Efo9wvJdykffMOrx5yZziLCxyopFeOWr0af155dvJ7cJKhUQfJwxOxnGML+idhTfj1XFwob90iLIFqxT0vMJ5GHQcckYLjZaBvtqyACqEWdlhDHGKOUn1xfiEmYrU7NiipwaDN1hyOVzrepbchjgNLhnfQ+Rl6G9h8ZK0cMeU+v7Iz4uI1JQ2n8ZKW7CiDWSx8g2WOt6E89ZIazW1tqa3Jcd+ptIALMABe0LaZRD6Sur3MbLzyJtsI0F+TlMiod5dpR+cR7vYjskC2ZA5Ph5fWoWxqfefhjyMCca91Gec09gb9nkSUfbPnObrEviMDspaB2M/N0MxYASTUSLvBALCks8p4ioUuKcwABbUJzxEST92E9uPdXvUllwB2Gvh4cjEfA6f6pD+ShmQJmCT+gqL0RoGc0jvngrKatV9OPhpjEqEF77eE69DCl+YEoMzhDSXQVkh14PRGI+FDmVW14g4UArKyiHnPh1vKcMGODIwnmNaP6f+knr1/aWtBJkRBmdrZmjJoy0yX2NuSBWUZSsDuWXCImKpJugCBWsg9A0GnJ7J3AzpnAX5UVCWX2vjcWjJw1SBdHcVg/N1kdfIGzJp4FzjDdETxdpmMp1q4NSvn0Z30gZOjZQkRrGWhrD6UelJkL9kygkk1Osxyvfg8h50jsd5vCG1xoKU95Hvo/AWFPc9nuDO4w0BmyI3xMaclNrrUN8jgIg3URo4LXFa7VszwAgWCY8NnBpHYyo3ZPLZQ9C5xp4Oz7kNnrnoLznHrukvWcCkXeIN0eNtyhtymlhwMamdV7ZjsgDWgj2kcUaoOju7H0kmAKVZ5OQw9dD19Uozqa3hWkqUKoqDo0rWim5TQ+WsVyc1aaNajcGgYdympH5N6kGWoO9QHUP5EsjLXHe3TCL1RKFfmnTfJP20ZhJQWwCR8LlOBKtchrGuAlavAsip21y3V44ZVM8hvdTSthKiDigT1cL5ooWoib+aoKfcpzH7JGUb2+qz1BsM3qjK9IU7Xx8LSWN5wjIAZhTKSGez4GQg/c1tGnttXg/6wp3sZCffYbI9msUmdhY1CcoqXLirKg0iYA6q+VBfL8Y6BTS7tmmyzaAAqqs1AHGnrRONIanFV2WcJVM11GS6p7ZjQ0PW2GU67qeA/egKQqCaHKiW80SXavBfx+bMa7MhMeBYFMFtyMbFSfevOlaMFRpzcWg8i/pep5CqTmvrabYC0Tim2uVgYBSvpRPm7PR7XVb1/U2PwWkAXxI2hS4lwM2jodFRykr3TMkj4dnAOVN6QwCshgYGjKVrgCF7Q8iPvSFLbpI3RNRF2XqYyl5we5gnVjGRwVsMzqR2hnJnSTfUqd1LDntm67kAc5HPXUxbN5SxFjTmgkwst9xi0rouXo+ie8mn4ydDC2v8yHDbDQEYZulnWd+sxrONrFoOlD0PyegZPvds0Lty8lvnDbnlFgXcnOBp6u1AzwHKZuUa3OTKe1IR90ibwCjateQW8MBtt8DtIZch3hDxIN30OWN3SW2eLGKfH/s5jtT1rXE4Gma4xS2s2CdUp4nnQbwQ+qUX75UnwqHbT96QYwSPzApt7hsGbvg9LLnFiWvRURj7t2L2rp4c1y08PUz0iJQWjvPE5mzHZOEBUxm6Of4nOA5sOAVAGuKUVuyYsjdEXKQu4AQsIhVcoh+kWA5lwuIFDenB6RVsyhvCTLjUrIoOvmRXOEELa8P0I96QBXUjdqwuIkyF3/v0UmrmMMF36L0NmowPBk550aSsfbvKjGdxH1trFpdiurNeBedNALOtJ4vGRqo90+GAMluaRlzStoiWBvTcjFb9dl2Uo8vAP/J336xwoJjZMjhwtlMII1lrHa5Q6Cc9Sen7tuD4PLmYLOCBy6bDvungbEbKWvkWICSv0oFZpUl3QX2hVUn7Dpr8rFpyWNkGBzQoYyRnD1K8riWPlk3BBiaenwMacMkucej2Yv/3yUahF5PLZomWHfZsn57ngfEjA6eL9qjCjgGg52APWhaT8/kinLdispDxNr8eGj670eHb1y/DdIQ43nF8dR9XrgOL64wvX38Ye214wKuhweq4BTsDczt0BDng6y8/gLZ1AY/ildDp82sENgTTA5+/8TgAYGEHNMbhdj8vLM2HNw/gewMeCNRk7eazV/8IlkPutpl1cN7g1suXghvuKLTh1298IFEj6m3C0RDqOWhWmffUrhLOwouHAfxm2bVomtB+az26LpR7OF+g6xr8+vx9WNjsGjXEQTNQWs9+06W6l0M4/o2X7g90jjVU3rIBHOHpR787uQclZ0G2WuLe673F3AwBz0JtFyx5fOXGQyMjWu9NuJ/oXnZxUv+U/XDigw315Ulbyuh9cAV/8+X78NSDHynKFS+BvMyCfdGaoZgsbrsF9k2HL9x8LGkWgzc4jhghQl+opYmgRlqO3BxfePURVT/jqGvx1KUPj4yjAVYvo7cLlH99r/umwxdvP4ZvJ67TMHk25INWHJ/DsZ9h5Rt87urjqW+e2ns/JPcn9TVnzVS3vxcNuoKFPHSfHd37OtmKyYINUN0DjPVwCMA4AAAHaFS1InjJGcADPJOXGhgi8pQbbKYYiLEY5ANyEAAMHPzZA1sYFcxDxCAb5mhK6EWE477Fqs+NdY0JyFlDSPgSr5/EYtQoRjpGY6Ui0TrfFPtJ4TeVf7Idks9H/Qx93LJIPIZnwsrl8nUfyXHXG5ChkWaBwQCOcOJnheakvTTW6+AyG8FvSpuF50yUpJ3UU8jeN/tF4h6VvhK0q9QsHxDP3WDShKrP17LyTYAF9LPCDnV7mMNZg9vDPG3zNGeI9NO1/iBdo3lv5fcT1+J4lWkgjPFY9S1uu0XpfSHhBCknCy36nMN+kQCBuvicBsrEyA15XOsPsHINTro29d+14dLI5b8u7L5ni1tuUSCpAfk92ER23pCd7GQnG8lWaBYAwIZAfrx/4hTCTSAuV+l8UvidxWthQvg3c/AiJxtl1Cy01IlBpUUcZbQYCVYlVddHXMnYjrr8KanrdGqlS7fFVAL1ooz5SMzrHGw3HmXbnDfp+lRuxNocbVXVBrdom94RU97v97AxfT4fk3N10QyMtRhVjx/15fiY3G9tjHNcaj6eKbC0sU9xFLocjYNZekHEkKk0u4lEq5rRi2Jfakay0FhTlj+Z9Ba2drU3LV1XJBrS5PPVjHdnedRcZGOr+3Bzi8W2TBZxG2KzrSu9HC5qfeTKaE5RwRkIhk1G0pPYMLwjABbeEZroDZHriaEg4dv4txwY0olkcuQdEWPVN6luuc4zgXoCU94qdd4miHktUo/+TeeaaDBgCffVk4b34fNyaAqVUrYh+lixZ43HeaDQufUocQTyhBPXwtzBsHDeYKjyasRGIWuBDPiToR2pxcyUAIOlPCIG96bwREyJB4UQ7onjK98mG4XI4MPmwcfnebvP5U+B4Ha+QRe3oESMgQz63hbbI20/0G7WdV6HlW9wu5+nl301UALz1RPOrX6BgQ26waZ341bEVT0roE/u4eawNxqT58kW3o7J4hRZF19gRyumOqFaOaeM81PgqWcKh+uUglOsnLqeOs28rlfXOVV/4gllAsC5DhlIXMbeyfepVdlQvh6xvDCzjdvnmIpOF8Jm+QzElzIer49NJb3Vn4s2rzle94XUcZrotut26eOF5jaqV0++btSOqSQ/cAkpUHPKAgDolFgcpZmFenm6T6JWI+Nh4/JVW4ImM70obiLbMVkwYCqDtLyQKU1ggSqRjOVSJN4Q0Ryiu5GIQQbw0XXKkVuEKa8cs1ixp+mXm33OzWAmNNYVHdyYYIhl0UAiRXgTE7ZCe1UwUxxLMzOk+IPGuPTZCBenDytIFXOTPrfWoZ2gGtDS2swBkgaT5dBfjHKyMACD0ZIvOF8lE1Q+A5kKYErsBLQ/MUXO1rKdM+MKT4RMmjqnZ4iUjmSzu7yor/IE1N4BIGTozk2P1uYJwDMljUIMqsnVjmBU9BOTVILqR3hW3hPmZhiF3juY0WIwtUA1xgePmrhnTc7hEa1LQgUMgmdM+nFuhlFAoVNu3hoHY8/2aCpN4jyu052Bcyc72clGshWahemBK98Y8MIPhrmL3B6A22iOAk8IAOz96Mv4QzyE40OD9yxOkj966Vp8C/eFtPSbOc7i+z/2NezZLvCKzN8DALh9OA/TY094z+WrAEKMgyHGzWFRrEpf4bfD9wYYDFgRGv34u3877RWBEBzVs8Wv7j8JIsbNZdi//jtXnse+6YpENc3rcY89xi0vn0/S8X97/UEAUYsxHgMFV6KLUZGtdfCe8J9/12cnOTc0RsR+DDICgKOYbflPLz85ue252S/QO4s/fu/XVGq7T+V6zpGVDgFzopvgDXn21v0jDa33Fre7WdKERFP5y098ejIdvk47t2D8vfbjBa8HMEY3O/LzlGYubfVscNMvUuCbuEcdE273c3g2SaP4rx75p0VbdBsA4IhneObeD6TjBozbbo4/dc8XMYPWkEIMRRcNvjM4dFgXZ7HCp+yTeO44kAddbnMgXeINIY+feuAZ9Gzw1OWPpPv+4cv/epQ01yc7SQnj17PBw7ZLuKCh/4DfbG9iU9mKyeKOZQNzwxsha1OzVRbjayk1kOymMo2nOT72WrZfgwNPiVV9mPIyYhr5VLvO29YpbM/1LOan566ENP/T4xnOwtbcdLtwFtp5jf59HnlrbENe23fuwrLO0vxG8HtMYUS+mUX24xdNkDtLas2rJkUufzvLE/H6Pe+7wY+yTrZKsxBjJrloyKvvm0MOiSFOxsOGXJjyeHx+Sw4D2Rw96KMHwFNSU1vjYMCJEDjN8MTBwBj/AsEw2lJpVBJEJWvKnAiNZCUrj9Qjv8vqOaOMfmSV0dIYD2JK0ZxAjuzUwDEpl4KbAvshIXVRIPUFBATGjSYOwbNoyRWwdqEeU5TXc4MF9UnNrsup+UtdjMKUe/NODJFchUkH/vSC7JcyeI9G1dL9muqJW6XyeocltVhQXxqdITQFLh0TjBDPhDk55QWSJDlXrPAL02MV+0LTEQS8EJ8WsQUNAGdcDDnPkccionfJWNDjQ7teZxTRttQWq43HdR6I1qCq3EwsiLBkLp7aefAstmqyGIHUTNyHjPEc6GLyudX5AlWXvASq/JziHgJqHAwMxu6y5GpUZWrxbOKeftoFOOWvr8vRq+RUOWe5IM9Mg6/7hWmUOKd/0xZ1XYdRfeaI4qvtU101SM1p7jzBpdRJai5mZlryRdp5dntWK3RVvJfMTkIGrknp6dPBT+uCwGo37TrEc8fS5lwfeIzsvW7Fn3LPGuKyvWTOQDlX41N5ruoFwadrLiZvjW3ITnayk9dctkqzYLXyV5CFWahcDXycyTeWKjgn/C0DY6QxEuuRgrDi303AatIel30KvHEwasWseSzK7xJWvg7h26uyLDis9ihXe8kErXlJzMRKXWo9su8Kq7SUbSttSGs08rl4NnGVlFV6Xdi3tMVEjcKg7Bess09UzyGt4GySyh+0y4wlcZoWocs3E+Hg+lxps1xnqrbpsmoQHSlJxoNuXxoz0M/HJy1BgwGlsU+6VHl245B2x2M4xWkevWl502sWF2ZXojFQai10Sj+K5f2icqfMUrXKnzBFz7DM303R9z/VFxdlJBuXc757uhPO1ykqxDda7gYL2Tp509osJMXcNwTvMzIWkJGzfMvonU1oQUsXcBhSfgiiDZMDmlbiFQEAw4FSwHKBdmXhceLaAsaefcCvgAcy7wjh2M9i6G0wEwlGQB+NdrJ6Hhf5AhIKnJGsLAJGAZCRrDwoIW55TxjIFH+BkM/gPRVIXEDeowoSFxDQrqVPEhJXzFmp7SmDDyvwsZ8XmoigVwFAH/flPdtggJvQFHpvR5pX72yRTyP5LwUqV2yv8H6kcxGQrgZvcRRjSLT2pCMVl9zCkSncpxJ7YsnjyGWUMw8ZH/kejniWoi97diNNZsltAUjTk8WJawu+EUDjWYQxKkBBU8hmnkLqvcAVGDUOBc5g5RscRzS3nm0aC7f8LMTCqP7KeBa+0Bw7WOzzMMmatqlsxWRBLgDeNDcDeAV5YHhlDwc3AtgNALx8/TLMitAcEb7xyn1ommhQcgbttQbkgPZmtF4PwFdvPIQ2AtP0J+EB0+0GMAzTE77wyqMAAniNiYlZBU/HK3M0PYFcdpGTB3738HEcD/mFXDQ9Bm9w/WgPRMDyJPz2m6++Cws7jLAGlhExamH7lEC2sH0Crbl+9XI4uTchNNsRYBnURbyD2RzoCb99+G7MbQ5/llwNjWehgWVk4L14+57JoKyj1QzeG/za4v0prFoGreRXtEr9bciHUOwqN+T5q28b5Zx4b+A7m3BBOA7233j4fQUPh7yodTKWhcezh/fj0/MPoRZ9LyvfpNBrHQh3NMxx0KzwhVcfSXgUniklhUkIdx1wldofX6ilb/Glm29PxxvjU/KZ9gDJfUi4dmP8KONTztk3HT537Qm8erQPAJi3GXioVxCLTx98EL1v8IXDR9MY7SMZUW2InpKeLR6bXStIpADglr89ef6UvOm3ITvZyU5eH9kKzeJuyEXjjS66HzxrX1yT0QAhRfu13H+ub8v59vCTjOATx/Tqe7fZ6jeRGtNzSk6LriSazvA8T91n1b9RWVXfCQ/NJiIETOclOb6IbNVkIRopeaTs0FrIZ2g5APARTlIbI+W6xviwPxYAGTnXV8FPMWCIoB485XJ1OxrjipdPSHuISui4EJxUBXoh41g0xmOIe83GeDTehweeqBZjdiiFz0z6OKW6Q10ZsHeFDIwr2aMWHquUARvYs+qutbGOhnwBKbcWsHcisEvaZ2q6M2Z4uZfYtxS3CkVQFnnA50A5IELlGZcCxrTUL+lAdhxch1BeSy5sq+S5c7AFATnTtw64KmI9EGwUervRUKDINFXbLPkA1x/19jYGDmoIf0MMwyFAzhoPayTALk+AOgO1JQdPpgh6m8cAweIZnTJp1/0X5E1q4Bwi3qZvMMLc1Jicgq8JZIxNcnmrLGM9oSwJNP2MAzAOgJMuwto3JoHahIkjljEgl4tcbuebArdw4LAfHQZTTBiCkantIBojU38evMm2hiG21cVZyiOghEWKAR4MyJVYnkX5FZipvOBi2Fv2TeQ1Hb/oRIyb/aIAihWRdGpp78y4lD6u+9oNFl6hmwHRWDyY5INmH2zw6/A+BesTQPFdY2QC4xcjTCyzNIGLHA0zrGyDo67Fqg/9wAz0vQ14FNGGokFsVtyM9v8nri0Achrj0TmLG/1eoXnJSi/w/q1x6L0tjMqGPAZvcWJnuLlaYNnLuIhlEJKxm4hxOOyjZxvGXzzp1f5gNGGuC4Tr2WLfrkaBbW868Bu3AK599x5m0UB56VsDLv2Zq3jRP4wTMVoaBp0QFleBP/Gnv4K9CCG/8i2enr0Xzhncvh0Nj47w7r0j7DcdOm/xPN0Xyjg2YMuwHeGAtnAKAAAgAElEQVQ/effnAAQYeAuPYz8vNIZ/iO8LXBrOKFRqgw9e+sNiUO3bDkvf4rnr94OIcasPM95PPf5MgHVXarCHSdb0fbNKIdgHZpUs/f9H+0cBZH4P50MouaA87bcdToYWH7vnGwUVgCWPjpvkYQECfLyEgt/yoV0vn1wucCNEri/3MDiLn3n0MymsujY0SmZlB4sZxt4CAPiF9o+Ptj2db3A0zBJ2iGhXH7/y1TJzVlEBiDdjyS1aGvB7h+/AX337PyvKHbOoW7RU8oQCwC1ucUADnrr04ZTd6zh4ITxTMrL+qXu+mCasBfVFHAWA9IyA7Hq/0e/hrz38aUVLmKWP17Vg9Chzc8R7tSCPpy+9B9/u7wWA9EwNlVmnP3TwJSy5wcpnzfGv3P9Z2Iq+0CV+VUqfQ1ukj0qPzP9uj7GpbMVkAUyjWQHILOrE6fHrlWNyP85ZNZctwjrR3JHh+7gh+oioufq7I1MgcYsYVLEYadWIxznXuY70twcVsfxStwVjRtob4jGjASu0Ks8gezVSfkpUY+sVSHJDhHd13BcZRXrGUaVVjO0SVKVh/HPbph9u6gfkfgB5tCoguVWs6FPs3wU4DwLxr6WSN8Qy5/yf5F/P/ZGAkCDbNhf5XiKjucpq1dsQ2dqEHBd9v9Hjnl7c+FmdI8TILZUxKjojufwc8oG0p0cmCqvGiNHtKPbmgQO1rZ7FeSwdO2/ITnayk41kazSLOxWqVzOSmVmjU8c9c3Ve+FviINTlnVdMvWICQMXxsEmUYL3/nipfb3VqTes8OBbSppqZ3LNZo/msr/dCdcHDxeclq63QF4bfyzbIvaV7nLjVzJ4+4eE5Bej2LFwILWetuPp3vV1x6Xdf3FvSKri8TrOwSRkWBEOUtJjTxCJvR4DzY1tsx2TBWG+UjWOw9kroFyi82CpHRGXeGfEqpJPl+jKIZm2zipwMFGo6gBQUk4yjekuT9s8SIJQnrvolkf16Efev/tYS0rlFHQ2qacflvdTbD/lrwCP9k1BOnEU7a7CeNQAzuk+k7We5VE3RXp+yTnXYtY1byvqFr9sg54Q+x+hcTSWp80pyH+nJj0djsgbAEbdluA99HkbHIrb6RHnlhG4x/mxiPVJ/Bv4JE4UFwSYcBbmXcgKRIOTXdBtCRH+fiF4mon+jjv13RPQiEf2r+O8T6rf/hoi+TkRfJaL/aKNW0CmtNuEfV++8TlgqUtDVC+vkHFYzDcv1VfLOumYVk5IkVeV/PiYCBcRtFHXp5C5f1aFXLR+TnXS78iCcftlcLDNcS+jYxuQy9Y8pt5MzJ4cgRet/DJ1cZ9I/SXCTz/JdM5PXLOUedOZkp+8930dOrCrKZeHYqP5VdXt13APpn/R3Krvi9ch9pP9N31/Zv0bdZ/7nqu/5+DjU2qHkK6kT0FL/6/pZ+orhmeHA6NmjZw+H/F0+OzAch389I/3zuPvo3r8A4G8D+MXq+P/IzP+9PkBE3w3gzwP4EIBHAHyaiN7HzGem0K/z4LBC1k4vOqgY2Ck7U/nxB2/jP5PCiwWbgpAfilDwhQeSVxetUehH3LMtuC56E+L1BeBFruu5wSwC4ziF+dBzAwuPPsb6A4EwWQ8KEf1i62PSjk6F7uachqy9hDrCCihhvi7xpVQD1xs4HyadQrPgjBBlZRKESZgNtYQJuMK1SPEK41wLzYSe8lAo5ziEnIrw8vbVhNtzuV1wCOd45kLd7mDQcqZcTPesJtFwntqyTtxfzyVXC0zIhelRruLSA53KGu3SC1++nj0YS56lPurZwoNhkLOQPYKnZyn1G+k/0TbUBLNmO9IjkDL16tx+rDydKmdqFsz8DIBrG5b3owB+iZlXzPwcgK8D+L5ztGcnO9nJlsqd2Cx+hoj+AoDPA/hrzHwdwKMAfkud80I8dqass48VrlOxN1SuUxL3aLJZhOjFxjg0bBLvhzZwyn5QotpOM3DWrtPafeYoxEJo12lLQ7JFZDeeR0s2/e5iBOGMXNA4tGsP2b4wFVoc4O9i0lF0F/Zs0VNeHQMEYG4PkLlE6lXeRnfqjNwIqVqyGpMrj8UNOdYsTnOd1gFcC+oLdG/RLGqXc4vQ522lsaR7i98908h1CgRk6zbC0SXUb1CwP1AOLJvBJYPugoZCY5E+rJ99axxacDIWZl0i/z+n8Fkjl4v20RKwoC71UYAFDAZOeZYWjEVsd2Ny1Osi2iu0fUJcp7bWYji4d2s7z3lsFhedLP4OgL+J8B79TQD/A4C/dJ4CiOgnAfwkANi33bvbhtzpNoQ324b0zqaJQcs2bUNCSne5DRm8eX22IfL767QNMfCvyTakH213xtuQeJsby4UmC2Z+ST4T0f8C4J/Ery8CeKc69bF4bKqMnwfw8wAwf+Kda/N5EsTmKA//lB0UlUa24qeqdwSzUWb9Ovy1ZAMbJ+zUxLZc/Sbt0d9HOJ4wo3pFZMWpXbm+qlco7Er0rYzB6apJSNMh1lLjYqZjlH93tN7teFE0azFyFkhZsV5mGk02AauyNAhavWio9jgq+2YSMUv3nU77Ro7k1PdsmJNRtawzYlWoSaw2+EpIuIegWI3RwQp2sVSWKXJMHKCg3Nbja7po0LwThPcLPVUieof6+mcBiKfkVwD8eSKaE9G7ALwXwP974dbdgWyaBXknqEqbyJ2gaW0qm2RdTkWJ3mksyd2Wu4nytS4q9m5L3fcFynf8V4efb1rGWcfSb6eFKN9FOVOzIKJ/BOAHADxARC8A+BsAfoCIvgdhIf0GgJ8CAGb+PSL6JIAvARgA/PQmnpCd7GQn2y9nThbM/GMTh//XU87/WwD+1rlawacZOONfZeAE8oo5wE4EZYU/OQ9AGSuTAUgHv/giFr+8H/2ZRgZHCRiS3Appog6eSSsmIe3Rjcq1aGlAF41Z9QoUDHHjbZjkvui6OjSjYLPUBipT8oN9pjToinEs5ySo/qCcO9ElQ9n0Qxv1Y9rWlAZOHVgGxKCsyigsNowCxSzd3/i75JDoOBUxXpe5KGo7sS4YLYnWzsrALTHoTiWSpfPSXz1ugt/SoHxOOhBLP7sUVAb93HN+SCa3mdZAfHQAnDeiV8t2RHDSaXEW8a8ycALlvn+KF6SwWWhjJcv1ap9KJYp00bQJm0WBhM3ZSGaQmyjBM7pdEtAFlHaKnhtlzKomhQ1sFh5WGetKm4VjEw2qNvWVj38dU8FsLunRvmq3HOvu0GYxZvkqg9U8Z5uFqKOhD5tJm0Vtm9A2i9JGk20WOfjt7tgsBm8Lm4XDOFTcp7+qwSxjNBg1Rwxrqq1AMNJK/WKzCAFdJWnQa2mz2I7JwgMKirEQE0eoMR4CS2HAKa3Yc2DsYjYqXI8wM0PCoBTsRxCDTek6lRT1nkqSX8ly9Z5gYr3eE/ZNh97kx7NvupCNaB0MIQGptDRgkVLI48MlgvPZbSiu031aASa8GE10i52gRRuzTlvlZZFVZW76Kr2bU8SmrH4HZpU+yyBvbWDgqiclcQnOyE0TI0MRIxNhBo8O45wRQ77A6gQA78q2a9fpPpUp6j03KdMUCB4TA4/WOuzHZ+6Ycl5IVf9CXI/qmCfCAQ3h2cVJ07EJ2B+ReDo8y1VRTsLokPsgk1LIgYBTcWJnWJAvsk4tEKIokztUPD2qnxCG6z4Bl+0SrwyXY72CwVnm3VymHit47JsOrcmu05ZM4SZdlyPSk/RnqfWdx2i5FZOF9MvsRvx7OOCFw0swHcHGZ3P0yj6u3ADmhx5fPnwYe5H5uncWy5MZ2BHoKNwOOeBrrz6IeePQDRb0asB4mF0PbifTA79z83EAwEGzgqUA+qJjBG7c3IcbDPxgYCLMODuD37z2bhwpwN69pkfnLK6/GoF2Yxv+5a33Rhb1nI/Qe5vwJi7ZVQKkudIsE7bC8zffBiCA1LTWoXcBnWkZwXpuzudYdi3+xf570mSoX0KNWn7QdGnQHQ0Bi+G5V+8LeTbVmFotZ/CO8OuPfgD7dszOLp+B8PIIbWMtX7/5YELaSu5AZ3Hct2htnGyi+/Gfzz6IPZtfPo2zIZNczwE1/dlX7sfTD72vqKvelhz7GRbUF9cDwKHbxyW7xBdvP4bDfpH6SoBsZrFdn7JPpms0qpSs8LfdHJ+79kSoGwHJ6uZqgacvvafYctZI6wvqgnuUCXrr2LPFZbvE79x+As+fhOd+0IT+aMinZymxH0vf4nPXnkh1fWjvhZTvchb3q7jqNTq5Icah/93J86dkKyYLboBhv9xmNE1AxurujWp4b6CpLjXilO9suHYRHjAzYXkyQ994OEewq7iyuZBnQy5A4gPAEMFqwipSZqgayyDFM8rW4erJAbohd9tx06J3FnwSbQ6xrqNhjhOq2Sazqnvi2vQ5TBThs6AjGeIUuxH6I79o1npcXV5KK4yc7zmjMwHATYX+LUjRy+NZUJlrF/LKAp5wfdjHzWExarfUIX01Fdgl9ay4RNpyE+cTMb51ciW9qEB2J9bI2gaM1bLFC919RV21p6n3tugTffzQ7eHbJ1eKOImccxKOPXf8wKT9Qp7NytuEwg0A1jCWfZOAa+QedNv1felthbzgrwyX8fzJ29Ap1DRpw6Ce5bMnD6Jng2vHe8m29M3ugVAWzs6Q9WxwOOwVcSYAEsL8JnIxh/hOdrKT7zjZCs0CHjA9wzcquEk8GnGl5nu4sD9qqzYZDlGaEhruCbbxaBoHIoNejKRiw6S86s1MCIk+cW2xKhDFrDyPpHCwJyya0rgys3FOt6J9hOOtcYl/Q4vM5DMzpJVjbvoEoSYQfqvBJr4JjUJtrYN3FnM7YKF4QWTlXqptyH6TVfxl1HKM5VSeNpr6IRh652ZADT5bEyULW/lU0JsGms2FB4Nl0kxS+/qCN0RvQ2RlH3xkXLcel+1yVJ+WPgL2hrJyG44xx8L0AWZRNFIQVgMV7b3c5vLbwmYRtT3XJl6P0B8Mz4jbzdKTEkiGbCqrXtHlnAUNOGi6pPHMbA7517ACV5oTrHyDWePSVvmyWRbnAWMjcuobboAGo3acB5l8OyaLC0hWcS94vQTPyAOpHtBF2rJOE6yNjHJsgJ2+AIVj5/Q6T/msjxUuWRqje5PaBdbqfd6Py33qEG2ZAHJEaG3IPE3OAvY5/draRZvZuApYvQp0SOQsKoDUtmgUtGf0M1AGZfnqs84NWVdXMQ55fE5dr9hnas9Uve1b16dvTvrCNW1O90hYzw1CXO7DGSUmZnVdXc55JgpTvWiGIkw/STvyQ6+BZ8C+qEseYGMCFkHRxupv8VvlGRkNIF2H8tsD0i8A1yUTA0RlHEG1/9bAMbJaToHJ6L4BkGkMRr9XyGHE6L0tXkov/UTjOJiRJ6aKqQjHgBVaWASag0G1t+5Hfe8tufELqGJsCPIMy8mpRDCjdMxUrvmAhBXAjprqvmRsGKEqAKdnScieK5koNCBTF19pSZJLwj5STl7c8rAdkwUBvAbjyzfi/C8DtzQuA/s4k6RUCIZzBsaEv0VsUXyfBWHaiKFTAc4AyltQNat3ZSKZcdHP7oKvXbJkezaAQmcObTXhOADjmwK2f2AbwXpyXesY1IkYnbNFe8Vi3ilO0fTCEKftj/cGxKOpItAl+ACnnxLHVMc5GPRKE+rJTmoOEr+hpUi+UvdTG9fEi6CfRc8GlgzYm7RV06IJdoQHtA5sEy/A0jVFnXKdtE+XL3ErgDZwNgVnqzUegwvtSpME5y2G5hvRMR7hXvP27sS1aUsqGoUhU/TbKo6XwElLRXunjLG1OBBuucVoG1KDMp0mOwPnTnayk41kOzQLBsgz2IxXKlmpwxf1Uan7KW5AttRx9U04Fzpwrt6CpFl5Otx6pK1TBfcve8OJ7Y5e2YP4IvQ5Y004DFyq3+kek3aRj3FlBMx1lLQGk9sUaf8oGjJsQ3SMQnEd++SWDFsFj3VrzRR4smcaWWgCfikX30Glul+HbtdiSfWpJG6p7Y2XKLzYjjoGRN/nCJc1qfGhXzVnh1xHlLc++XhoUx5ZIbx+CvK/3orVtgs5plMK6vbWYflT4thiipHsTWezIAdc+pbDi38iPJxmOQewQnMcSIUA4KE/ehUvdg9jdZ/BI7MT7MegLImXgAfsbaGtB37w+76GPdth5Rt8mt4PADg+XACGgc7gXQevAgjRcwaMQ7dXxN1/nh+HH0xgAGMJyiL82GOfS0Q1QIj667nBr7QfAQDcOAlxGx8++BYu25PQHoVnccvtwZDHZXOC40hac9kucSuW+YX2kXCuD+RGzITG+qT+hs+Mv/DIb6aIQ+2l0GRJB/I7OBHk/OP596CdiOC8vtrHwAbfe+nZdJ1cm8BfYjBxD4sF9SNGbgD44uGjKQpVuESWroUhTkFZol7/xNufwQHpoKwQqKQHdcAbCc/kT176UlFXbcM49vMYlFW+vDf8Hi6bJY79LLGaOSbc6hfwoOS1+qkHnkkv6UynhceJ9ZgbPH3wwVRuSw6Hwz5+6OBLo8nNg7CMKv+CHJYRs0QbQDsYXI5kRs+ePAgAuNLEMRMnJ/n80/d/FksmPD5/Mt33Jw6+DEvllN2vefd7EB62ZmQb+7/t5izqWzFZiHC0T3hL8N6MVnUg2DAGthg4D7xks9DnRdeVV4YsULT6mzxgl9TCUnBReuUS8JKL4qGsjaFMHQAjkXH1vlxHy2nvQM8BYKUllxjJWu8iyAslW4xjgvFh/284axbOByyKAHQTAW0474F1TkrP8nJnl9ngLTyNNQLJeem5wdKLp8gnEBnHBi6GIvfcwFHI69AToTwPX5DbGDhvkgs43INJZXYK2QvxeemQ9VCXjy9fabOoU9rld4MSgX3JLVp2Yd+vXKdDDMoyEKCd3C810A5iH/ba5kEBUGfJTWqLJHw5EJZqMpXP0p9yzgoeS9+mukV7MSgniyUTehZA49DeY7YBGUxN6OtyP3oYHPthlDtyHt/fVkwWxoUQb4ph1GwJy6t7uOdaCO8GgGtH+ylP5GsvPYgmhmA7Z9C83IIYaIXq0AFfPXwokvcarI5ieHZngmXeEf7ly+8CAMxtIN1dDk3h6eCXFzADQAOlSYwc4bcP31UYySRe4uWblwBkHtZPX/1AioPQk4XEQew3Xfq8sD0638Az4aWX7klthQ1thWVIsMhx64HB4F+8871pBZc6PFPBw9qkmANOBrRnD++fxLHoBgvvDX519hHMrWY6ywZE7SZtaIy2BQBff+mBEQOcdwZuUPCG8c9nHvrQSDWuaRXl++8fPoBfbj46qk+7CFe+wdwMxVbKweDEtdizPT539fHEcctM6AYLZoKNsS1PXf5IKldvGfLka/GFw4wSKYbjensirkxZQCReZorXdd90+Ny1J3DtOGiks8alcSjXEzEenz8JB8L/d/hEKuO2W6RtV93WWnq2eGx2beThueE/P3n+lGzFZCFCiUVdXJH5txSkNQSvgyRseR/1MLXIyBg2xCEOg/QgJZBXMfomc1LoB85RCynaQeMUX0uBIbxmURd27dqtqd1esn8Og6mkWmRCvq+qDSL1AAWV2lirJ4u4egpbfD1dGAouztLdysnLEoiR8/ZCyH5r+kIiJBb1ZGcxHkSUJgtWdqhiHw+GpyrcW30fp6hL/IOca0Ys6oYZHTXRxVjam0Jf52MF7mcxEeexZqpnLM9N23nOzaJOHgk7M5bfGJ+0BHkOolFovM56sij6ssh8pUg5Wfbj2ZEwusyd7GQnO9lAtkKzcHPgxnvnaG+Fee7Stwdc+bMv4w+6t2N1n6RWe9glMH8V+IF3fzmlCq98g//HfBDOGRzfjCzXjvDw3i0cNB1OXIvfp2A8MicGbAG7IvzHjwcW9QOzgrCM633uL7g/hlUf/OraMPfkpRdx6PbSeZfsEivf4mvzB2GI0fdh9v9Lj3wW+7QqgFw6tjjmOQw8DjSLOnU4ihmK/5v5DwAAt/s5FnbA0jWYWYejyKJ+EFnUP3rpG8kQqVPJb6m23RsZsi153IwG1BeO70Vj3GgLcW15gN4b/BdvfxoHNA4jl89A2Bq0ygCopZ2Illz5Brf6RdreSLLbxy9/ZWTg9GwSEjkQbBaGPH73xjvxsw/8WlFuHZpz5A0W5EdGv1ve4MB4PLX3flwbwnbRx7gDzaL+w5f/db4PNRZkhb7lZ0WcwpwGvNofJDZzINQrKePLqEksiNLn1HYE7IkFET6090JKCtMh3DqO4hMHX8YxW9x2i6T1/JX7/hUMTAGrJ3YqUyXF9+xhiLCqDJz/sznBprIVkwWU23MkE9sLoFKl6j14cpV5CFXAOpGU4qlygXEqt1DJiSSsxdqlWiE+ARFVi7MhTJdpObzs66JI0wuL6IYkP8rhAJuSlbxKm859Mq4jqeIot07C9g3kF6inMoCtlk1D5kum8NhuKvvGxehEEyeBop66POI0UcxIDH6czpUtAoAimrJGqQJKb0gxnlKagFe0ipTaItD8Epwlx8JkrttKcMwRj2Lsaq4pNS2F/hf3cLgnE+vO96JxNcJ4iP2AgAKu+8yeaxOyLZMFcKZZdt1tpfDbGPkWyqIijmHq4rzfjSGz8JMPaXxduUcU+DPxf1Pae06EAKuXWfNxZHi56V1h/WIGu0LJrWHgY4xCdSy1Je+p173MJO3SE9lUbIPER0wUM5WDUOffyHkGfsRREvbUKreDKU1go8lhol0mHk/nEsVnjDTp5PPLkOiifQBy4E48n1lNwGVIubx4wj0aJr3qGHOlgcSJpBgrOYRbT6QGeeylyS1OFC1ZuKQx6JBy3TdybvnQzjNdbM9kcUEZ8Z0qOQ1CLEGlMRUr1hRU3CYJUQJXl+s2k0/CVat/quMc5qOUDTmRDbpOTqVOGJ0byi9WeIUz4UBokbEmUH1e225tcJsCa6nh8O9AzkpFEzfzumd71vUeJa+HTFw+TggFKbGG6s/RdeE7OHG7pnOU67ho85o+cWprIVuPehsy1Zbzys7AuZOd7GQj2Q7NQtyE+pCoSyk5bL2MAHsNJ/BaHe47JR4GHQvL1ng/T1Qa9oSJO13PJgZ/RcBedbkGX9XfHWdW8nA8f55a6XxlyzDE8OoaxxYWmbFdRIK2PLIbzjOFwKkqnoFZmNTVikQo2iXBVkJSrJnT5f6mGMnWBwrZSuPJzGmi1fTcADTEgLF8pqXx6h/uX9zkogVJQBmnIL1aUhwFTDIUW3DuM5Wopp+92I8cc6HyQxjMFaWg49JmgfjdcwXuK0l2yCDOoBB457gcez27aKPIz8yl+y7jVwKbukPNiPamC8q6iGyyNdjJd67UkYpnbSvydbtxtU62Z7KoHRoyGayZ+k61uFfekNOk9oaMitpg6p3yhpxXZEU7yxuy7lqrgnbS8QlvCLC5t0K3S8sITKcSrYmdVtcUEMxkUpacf4Y3pCx7fO5awJoJb0g4roP5po234by6fyjbJhCMizX36GlylqFde0PyMdFeXWqTG7lrqeCAPa9sz2RRDYT04q15R07VLCSiT7Yhp4iP24+1RW2w0EheRV3TOmPm6Ho+fRsCjAf6FDdmXafmLdFbgcRzssGkMU1+HLYk61bhKU6Ozcs20V3K6bucNkJFO+XZTGkW69oyhYzdAqNtyFqsCObgLk33UD2rcyn7sZ0T+Tvpd2kPBEAHI2NmPVFcpB21bM9kcU45z+r4RsmmPKfiMrwbZb8e3Kqvt0ytsmuwktQ1Qd7q3JmvF88psPOG7GQnO9lQtkazWKetckpKIk1ZmpmlYMAcbQsq2Wpgk1KQJXHJSKQoKz9/VHMTjeEpKzxFi7oO+RULucDJcVJdcwq5U2nc4q3o2KoU82xlL1T4KTU9Huu4Qas4p33MYuxUWnTuI0p1DWxTQpOG8Bt8SCXvYHMwl44PACXtp0PwME1uI9SWKB1bmwnZlH0JqzwTsa4ICTCwRY/1qn4oz8BCwp3VcQQcB12fpp2UPu/XtDN7KMpnH66xoa06riJ6P5J9IH7WY8vHsdYTF/SVEt4ePCrZ29WD4n1Y5Z3xKTJTZN1WQ3As6rDzN503hAbg4GWHw/dHTML7LLqjfbQ3CYuroSPuPTjGH9xzBaYnvLK6hCsRtv3EtYmRzBzG/P+e8MjeIe5pTnDsZji4Es693Ye0b7+yRX6HIY9Dt1eETx8e7aHvLXxvYNoMfvPO9lqK3wcCcM3St3jw4HYwTMWs0ptuAViJogwDzMPgpluEDFfjE95FS0MCwjnsQrtureZYNAOWQ8wNWYXckNW8wXHX4tH2WsqrMDFCs+cm5ZgAwL0m5oaAccMEcpx37B0W4DcJ7MUO6FyDpW/TPXjkrFMXoxIBsStME9vc6PZGW8Sla3CrW2AeaRQ6F+D9H2mu44DG6fCt2kr1EY/zsf0bRZlTSNk9G7SVgVSOgwKmhIAMDd7g5rAHz5SY3R5W7GgLykF2sv/f5wGPza6lc1pyib1NRk7BO8pyXuYaTaK+92xxOMTx2OSypa0tOTxsAx7FY7NrKpuYUmRm7pdo4ASNJo4H7EHKHRFpzrGN2YrJQkQmbbbjGS+zgqFg3up9OJl9qXnIb16t9iABv+ECo8BUsROAwPRR/oeIgcBlbEDPmZRYS4jfCAG9GpY+ECKHFaRjAV3JnwUYRmsqIf4htiH9Fsh+gbDySNxF6YePmo3Kc/Bs0COnlNeG1R62uM5GoB0/UW4HW+BGWPgR8LGU7UEJn0Huzat7SP1T9WPPJkINZOQpkXpS6GBgBBBGgHYi4NAyAtdIGxyC5umY0KSxkG0hegXOk0bW0PK9GSyZ0EpcCIAWjJ6RNCGLwFmrjcyZ4lDAb2QsZM2n1GADQ59DjhtacdBTW+KkaTnVDi1LZvTsRpPFeTSLt7TN4s1gBN3JnUk9Ma3j5TivrGd0eePltPye17Te173GnexkJ29K2U0W36GyKevX3b72jZKzktyAs92xa68rYAjOX9adaAnnTTO/E9kym0W0S5gA2FvQAETxlpOnAwJShI0AAAGbSURBVAheDwHsTX3OGRxXvCUAgjuEGCAkMNQ2AvaufFMwcHtPycuSYrairUHv37toYQ8ekfzQl75NkZMZ9JaUUdNhGY2RswTYm3EbPQf7hfMBxFdKdjGvo+cGS4WN0aP0egAKwJZzzsXABibaEIp+jcd6brCUCEH2CQhY56L03MBTj04xkkkwmGYBFxkioLHchTy7Djbhe8h9uGpv70CwzNE2cLrNQu7XggtPTgeLY26w4iYBynhQsmkJS9lS1asjLsWYKt4IfbxniyNuMlgOZ3uEgP469ugru1bCJWHGsQLVWfowHg04HfNM0eaAIr9lyYwOLDS7sd1SfmlQ7RlYcb+W+W4TId4knvk1FiK6CuAIwCtvdFteZ3kAu3v+TpBtvucnmPnBTU7ciskCAIjo88z8sTe6Ha+n7O75O0PeKve8s1nsZCc72Uh2k8VOdrKTjWSbJouff6Mb8AbI7p6/M+Qtcc9bY7PYyU52st2yTZrFTnayky2W3WSxk53sZCPZTRY72clONpLdZLGTnexkI9lNFjvZyU42kv8fFQkU0OYfYqEAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8004713860>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 435.4211935997009 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.6} is: \n",
      "[[0.23809524 0.20664506 0.16       ... 0.21818182 0.21818182 0.21818182]\n",
      " [0.20664506 0.20385906 0.12       ... 0.16363636 0.16363636 0.16363636]\n",
      " [0.16       0.12       0.23809524 ... 0.2351024  0.2351024  0.23727718]\n",
      " ...\n",
      " [0.21818182 0.16363636 0.2351024  ... 0.34658956 0.34662512 0.34454945]\n",
      " [0.21818182 0.16363636 0.2351024  ... 0.34662512 0.34666325 0.34458505]\n",
      " [0.21818182 0.16363636 0.23727718 ... 0.34454945 0.34458505 0.34279503]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8004724320>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 430.830694437027 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.7000000000000001} is: \n",
      "[[0.2991453  0.26444601 0.21777778 ... 0.2969697  0.2969697  0.2969697 ]\n",
      " [0.26444601 0.26246188 0.16333333 ... 0.22272727 0.22272727 0.22272727]\n",
      " [0.21777778 0.16333333 0.2991453  ... 0.31614548 0.31614548 0.31765009]\n",
      " ...\n",
      " [0.2969697  0.22272727 0.31614548 ... 0.44189997 0.44191814 0.44038348]\n",
      " [0.2969697  0.22272727 0.31614548 ... 0.44191814 0.44193708 0.44040164]\n",
      " [0.2969697  0.22272727 0.31765009 ... 0.44038348 0.44040164 0.43906772]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f80046ffc18>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 436.9290747642517 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.8} is: \n",
      "[[0.37037037 0.33093141 0.28444444 ... 0.38787879 0.38787879 0.38787879]\n",
      " [0.33093141 0.32983023 0.21333333 ... 0.29090909 0.29090909 0.29090909]\n",
      " [0.28444444 0.21333333 0.37037037 ... 0.4096795  0.4096795  0.41049599]\n",
      " ...\n",
      " [0.38787879 0.29090909 0.4096795  ... 0.55242487 0.55243009 0.5515636 ]\n",
      " [0.38787879 0.29090909 0.4096795  ... 0.55243009 0.55243545 0.55156881]\n",
      " [0.38787879 0.29090909 0.41049599 ... 0.5515636  0.55156881 0.55081257]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f8007059e10>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- marginalized kernel matrix of size 183 built in 431.67696499824524 seconds ---\n",
      "\n",
      "gram matrix with parameters {'p_quit': 0.9} is: \n",
      "[[0.45454545 0.40839542 0.36       ... 0.49090909 0.49090909 0.49090909]\n",
      " [0.40839542 0.40805534 0.27       ... 0.36818182 0.36818182 0.36818182]\n",
      " [0.36       0.27       0.45454545 ... 0.51619708 0.51619708 0.51644564]\n",
      " ...\n",
      " [0.49090909 0.36818182 0.51619708 ... 0.68172189 0.68172233 0.68145294]\n",
      " [0.49090909 0.36818182 0.51619708 ... 0.68172233 0.68172277 0.68145338]\n",
      " [0.49090909 0.36818182 0.51644564 ... 0.68145294 0.68145338 0.68121781]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f800471e4a8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "3. Fitting and predicting using nested cross validation. This could really take a while...\n",
      "calculate performance:   0%|          | 2/11070 [00:00<14:22, 12.83it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ljia/.local/lib/python3.5/site-packages/sklearn/linear_model/ridge.py:154: UserWarning: Singular matrix in solving dual problem. Using least-squares solution instead.\n",
      "  warnings.warn(\"Singular matrix in solving dual problem. Using \"\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                                                            \n",
      "4. Getting final performances...\n",
      "\n",
      "best_params_out:  [{'p_quit': 0.30000000000000004}]\n",
      "best_params_in:  [{'alpha': 3.162277660168379e-06}]\n",
      "best_val_perf:  18.59885234533721\n",
      "best_val_std:  2.019904187960319\n",
      "final_performance:  16.510316179444224\n",
      "final_confidence:  5.124271966917598\n",
      "train_performance:  12.421855720688153\n",
      "train_std:  0.28436829015391896\n",
      "time to calculate gram matrix:  430.415020942688 s\n",
      "\n",
      "params                                                train_perf     valid_perf        test_perf            gram_matrix_time\n",
      "----------------------------------------------------  -------------  ----------------  -----------------  ------------------\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.1}                  285.42±221.98  7844.31±17451.82  10290.82±20608.46              440.48\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.2}                  134.14±105.79  2170.99±1735.30   3275.12±7309.69                429.71\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.30000000000000004}  78.45±64.39    1486.49±2069.36   1085.47±1404.09                430.42\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.4}                  45.59±55.18    500.73±938.51     391.50±837.02                  434.58\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.5}                  16.98±10.35    94.63±51.25       133.91±169.32                  434.11\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.6}                  20.52±31.12    139.50±381.38     85.23±189.40                   435.42\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.7000000000000001}   14.30±13.84    44.15±47.95       54.38±111.73                   430.83\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.8}                  14.74±0.29     22.18±3.34        22.23±9.76                     436.93\n",
      "{'alpha': '1.00e-10', 'p_quit': 0.9}                  19.57±0.34     24.12±1.19        24.79±6.73                     431.68\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.1}                  291.49±503.37  4657.95±16159.10  4395.64±7898.00                440.48\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.2}                  106.95±130.64  1659.29±2062.89   4254.29±15605.68               429.71\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.30000000000000004}  57.55±68.30    868.40±1134.93    802.41±1596.01                 430.42\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.4}                  40.44±47.92    482.28±1696.05    236.66±390.05                  434.58\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.5}                  15.13±9.38     67.41±54.21       145.59±427.63                  434.11\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.6}                  25.36±73.92    196.65±745.96     49.92±85.38                    435.42\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.7000000000000001}   14.07±10.16    40.28±67.32       71.34±227.70                   430.83\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.8}                  16.17±0.34     22.76±2.29        22.54±7.16                     436.93\n",
      "{'alpha': '3.16e-10', 'p_quit': 0.9}                  21.90±0.36     27.01±1.33        27.39±7.50                     431.68\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.1}                  111.22±104.43  2436.91±4164.68   16839.87±71148.63              440.48\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.2}                  61.14±70.46    1014.59±1723.15   813.69±1110.45                 429.71\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.30000000000000004}  59.68±133.04   407.99±628.89     353.99±563.26                  430.42\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.4}                  17.86±13.29    130.80±185.14     139.31±293.04                  434.58\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.5}                  14.50±19.17    45.35±46.53       181.90±768.24                  434.11\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.6}                  14.99±16.10    79.52±198.73      78.64±294.21                   435.42\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.7000000000000001}   16.23±18.91    25.43±26.62       89.83±389.41                   430.83\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.8}                  16.98±0.39     22.37±1.75        22.22±5.51                     436.93\n",
      "{'alpha': '1.00e-09', 'p_quit': 0.9}                  23.51±0.40     28.19±1.30        28.33±6.70                     431.68\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.1}                  51.92±91.49    794.55±1652.08    1219.48±2518.14                440.48\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.2}                  26.32±32.85    440.48±771.41     556.18±1306.64                 429.71\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.30000000000000004}  18.86±16.94    139.75±118.27     131.82±169.42                  430.42\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.4}                  12.64±6.73     66.10±63.03       51.21±59.48                    434.58\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.5}                  14.32±15.10    71.40±193.04      120.60±495.96                  434.11\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.6}                  11.13±0.32     23.17±7.54        18.70±7.40                     435.42\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.7000000000000001}   14.24±0.41     21.21±3.03        20.42±8.06                     430.83\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.8}                  17.45±0.40     21.70±1.39        21.83±4.70                     436.93\n",
      "{'alpha': '3.16e-09', 'p_quit': 0.9}                  24.40±0.41     27.77±1.03        27.64±4.89                     431.68\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.1}                  22.15±24.36    255.15±226.88     562.04±1636.71                 440.48\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.2}                  12.31±5.70     157.59±187.76     263.64±489.06                  429.71\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.30000000000000004}  14.91±14.10    70.16±66.85       85.36±144.91                   430.42\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.4}                  49.68±204.94   140.59±521.32     597.50±3095.87                 434.58\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.5}                  16.59±25.63    43.69±54.15       168.47±672.27                  434.11\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.6}                  12.14±0.23     19.41±2.78        17.36±3.65                     435.42\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.7000000000000001}   15.83±0.42     21.98±2.52        20.32±5.43                     430.83\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.8}                  18.38±0.40     22.24±1.11        22.60±5.09                     436.93\n",
      "{'alpha': '1.00e-08', 'p_quit': 0.9}                  25.27±0.40     27.44±0.73        26.93±3.87                     431.68\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.1}                  10.51±4.44     118.95±200.55     148.88±273.13                  440.48\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.2}                  9.97±4.47      66.00±67.90       86.98±166.20                   429.71\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.30000000000000004}  9.60±1.80      43.75±67.88       43.82±99.41                    430.42\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.4}                  10.56±1.46     31.52±19.11       30.14±32.94                    434.58\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.5}                  11.46±1.71     24.37±16.09       33.04±53.40                    434.11\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.6}                  13.62±0.21     19.52±1.99        18.47±3.41                     435.42\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.7000000000000001}   16.89±0.45     21.96±2.04        20.16±5.03                     430.83\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.8}                  20.54±0.44     24.69±1.05        24.92±5.99                     436.93\n",
      "{'alpha': '3.16e-08', 'p_quit': 0.9}                  26.78±0.40     28.58±0.63        27.66±3.93                     431.68\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.1}                  9.09±2.26      71.18±84.21       89.10±145.92                   440.48\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.2}                  8.86±0.97      35.59±18.87       39.52±48.18                    429.71\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.30000000000000004}  9.71±0.72      27.84±15.47       21.18±12.41                    430.42\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.4}                  12.25±8.66     27.76±17.31       47.60±133.61                   434.58\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.5}                  12.20±0.26     18.99±2.69        19.43±8.06                     434.11\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.6}                  15.31±0.24     20.34±1.61        20.24±3.60                     435.42\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.7000000000000001}   17.71±0.45     21.97±1.50        19.96±4.91                     430.83\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.8}                  22.78±0.50     26.60±0.96        26.59±5.89                     436.93\n",
      "{'alpha': '1.00e-07', 'p_quit': 0.9}                  28.53±0.41     30.38±0.62        29.28±4.13                     431.68\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.1}                  14.08±29.34    142.12±577.79     321.23±1542.78                 440.48\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.2}                  9.73±1.07      37.55±30.84       33.36±32.96                    429.71\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.30000000000000004}  10.64±1.74     28.77±22.77       24.59±38.71                    430.42\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.4}                  11.29±0.40     19.36±3.63        19.42±8.02                     434.58\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.5}                  13.90±0.27     19.50±1.90        19.23±4.64                     434.11\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.6}                  16.58±0.30     20.68±1.33        21.26±3.61                     435.42\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.7000000000000001}   19.37±0.44     23.37±1.01        21.00±5.22                     430.83\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.8}                  24.30±0.53     26.98±0.78        26.85±5.18                     436.93\n",
      "{'alpha': '3.16e-07', 'p_quit': 0.9}                  29.61±0.44     31.40±0.65        30.28±4.23                     431.68\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.1}                  9.84±0.87      40.60±47.48       45.01±61.41                    440.48\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.2}                  10.92±2.29     34.22±27.47       37.72±57.18                    429.71\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.30000000000000004}  10.93±0.37     20.55±10.23       18.21±12.54                    430.42\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.4}                  12.83±0.36     18.66±1.66        18.43±4.30                     434.58\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.5}                  15.66±0.31     20.42±1.49        19.92±4.22                     434.11\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.6}                  17.77±0.35     21.33±0.97        22.23±3.78                     435.42\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.7000000000000001}   21.86±0.48     25.36±0.81        23.14±5.18                     430.83\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.8}                  25.86±0.53     27.76±0.73        27.48±4.87                     436.93\n",
      "{'alpha': '1.00e-06', 'p_quit': 0.9}                  30.13±0.46     31.74±0.66        30.61±4.27                     431.68\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.1}                  10.89±0.71     27.11±24.43       36.60±48.19                    440.48\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.2}                  10.99±0.34     20.88±4.85        18.37±8.27                     429.71\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.30000000000000004}  12.42±0.28     18.60±2.02        16.51±5.12                     430.42\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.4}                  14.87±0.34     19.97±1.21        19.42±4.39                     434.58\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.5}                  17.24±0.32     21.31±1.15        20.76±4.71                     434.11\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.6}                  19.91±0.38     23.20±0.71        24.11±3.89                     435.42\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.7000000000000001}   23.99±0.50     26.44±0.71        24.87±4.62                     430.83\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.8}                  27.82±0.50     29.61±0.72        29.18±4.67                     436.93\n",
      "{'alpha': '3.16e-06', 'p_quit': 0.9}                  30.57±0.47     31.97±0.66        30.80±4.23                     431.68\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.1}                  13.62±2.22     40.61±82.26       58.93±128.40                   440.48\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.2}                  13.03±0.27     20.21±1.76        17.26±6.12                     429.71\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.30000000000000004}  14.93±0.31     20.31±1.30        18.23±5.58                     430.42\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.4}                  17.05±0.32     21.35±0.85        20.68±4.93                     434.58\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.5}                  19.40±0.32     22.94±0.90        22.69±5.26                     434.11\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.6}                  22.49±0.41     25.18±0.64        25.84±3.54                     435.42\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.7000000000000001}   26.01±0.46     27.82±0.60        26.85±4.21                     430.83\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.8}                  29.30±0.49     31.03±0.70        30.56±4.49                     436.93\n",
      "{'alpha': '1.00e-05', 'p_quit': 0.9}                  31.51±0.46     32.81±0.66        31.54±4.20                     431.68\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.1}                  17.12±0.37     22.73±1.29        22.65±5.57                     440.48\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.2}                  16.55±0.30     22.10±1.48        19.54±5.45                     429.71\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.30000000000000004}  17.93±0.36     22.24±0.86        20.68±5.49                     430.42\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.4}                  19.69±0.36     23.14±0.81        22.42±5.04                     434.58\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.5}                  22.12±0.37     24.76±0.66        25.11±4.92                     434.11\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.6}                  24.92±0.42     27.00±0.54        27.19±3.79                     435.42\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.7000000000000001}   28.14±0.43     29.81±0.56        28.99±4.05                     430.83\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.8}                  30.15±0.50     31.68±0.69        31.33±4.25                     436.93\n",
      "{'alpha': '3.16e-05', 'p_quit': 0.9}                  33.35±0.43     34.70±0.66        33.25±4.42                     431.68\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.1}                  21.79±0.39     24.99±0.80        24.56±4.27                     440.48\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.2}                  20.43±0.34     24.14±1.16        21.97±4.35                     429.71\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.30000000000000004}  21.10±0.41     24.13±0.64        23.17±4.21                     430.42\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.4}                  22.60±0.42     25.20±0.64        24.44±4.23                     434.58\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.5}                  24.83±0.37     26.64±0.46        27.45±4.44                     434.11\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.6}                  27.39±0.42     29.23±0.52        29.07±4.14                     435.42\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.7000000000000001}   29.65±0.45     31.15±0.57        30.32±4.03                     430.83\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.8}                  31.13±0.50     32.49±0.65        32.41±3.95                     436.93\n",
      "{'alpha': '1.00e-04', 'p_quit': 0.9}                  35.05±0.44     36.45±0.70        34.84±4.71                     431.68\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.1}                  25.83±0.40     28.25±0.71        28.28±4.40                     440.48\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.2}                  23.93±0.38     26.30±0.88        24.41±4.48                     429.71\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.30000000000000004}  24.16±0.40     26.13±0.49        25.35±3.45                     430.42\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.4}                  25.54±0.42     27.40±0.51        26.86±3.75                     434.58\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.5}                  27.52±0.41     29.08±0.47        29.80±4.13                     434.11\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.6}                  29.39±0.44     31.04±0.54        30.78±3.94                     435.42\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.7000000000000001}   30.91±0.46     32.23±0.61        31.62±3.94                     430.83\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.8}                  32.94±0.46     34.29±0.56        34.47±3.89                     436.93\n",
      "{'alpha': '3.16e-04', 'p_quit': 0.9}                  35.93±0.49     37.28±0.74        35.60±4.87                     431.68\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.1}                  29.33±0.42     31.78±0.74        32.19±4.27                     440.48\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.2}                  27.47±0.43     29.65±0.76        28.16±4.74                     429.71\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.30000000000000004}  27.58±0.41     29.35±0.53        28.62±3.85                     430.42\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.4}                  28.69±0.42     30.35±0.56        29.82±3.67                     434.58\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.5}                  29.99±0.42     31.52±0.59        31.84±3.71                     434.11\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.6}                  31.24±0.44     32.82±0.52        32.50±3.72                     435.42\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.7000000000000001}   32.78±0.42     34.09±0.61        33.87±3.76                     430.83\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.8}                  34.77±0.47     36.12±0.52        36.42±4.03                     436.93\n",
      "{'alpha': '1.00e-03', 'p_quit': 0.9}                  36.34±0.51     37.54±0.74        35.85±4.97                     431.68\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.1}                  32.41±0.45     34.55±0.76        35.13±4.52                     440.48\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.2}                  31.33±0.47     33.52±0.71        32.49±4.86                     429.71\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.30000000000000004}  31.38±0.40     33.27±0.42        32.69±3.69                     430.42\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.4}                  31.88±0.39     33.56±0.53        32.80±3.61                     434.58\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.5}                  32.55±0.38     34.10±0.58        34.12±3.71                     434.11\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.6}                  33.49±0.42     35.07±0.47        34.68±3.91                     435.42\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.7000000000000001}   34.73±0.40     35.98±0.58        36.03±3.76                     430.83\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.8}                  35.81±0.50     36.99±0.52        37.38±4.09                     436.93\n",
      "{'alpha': '3.16e-03', 'p_quit': 0.9}                  36.64±0.53     37.62±0.72        35.97±5.15                     431.68\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.1}                  34.83±0.49     36.42±0.76        37.21±4.77                     440.48\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.2}                  34.22±0.51     36.00±0.71        35.18±4.82                     429.71\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.30000000000000004}  34.20±0.40     35.83±0.45        35.32±3.84                     430.42\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.4}                  34.38±0.38     35.87±0.51        34.92±3.72                     434.58\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.5}                  34.69±0.40     36.03±0.54        36.01±3.88                     434.11\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.6}                  35.24±0.45     36.63±0.49        36.22±4.16                     435.42\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.7000000000000001}   35.87±0.42     36.91±0.56        37.06±3.86                     430.83\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.8}                  36.34±0.50     37.26±0.52        37.76±4.21                     436.93\n",
      "{'alpha': '1.00e-02', 'p_quit': 0.9}                  37.03±0.55     37.75±0.71        36.25±5.44                     431.68\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.1}                  36.71±0.54     37.74±0.71        38.64±4.64                     440.48\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.2}                  35.95±0.51     37.21±0.66        36.35±4.66                     429.71\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.30000000000000004}  35.80±0.43     36.99±0.50        36.50±3.97                     430.42\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.4}                  35.87±0.41     36.97±0.52        35.99±4.06                     434.58\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.5}                  35.97±0.44     36.93±0.52        36.95±3.95                     434.11\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.6}                  36.24±0.48     37.28±0.53        36.91±4.37                     435.42\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.7000000000000001}   36.52±0.45     37.28±0.55        37.42±4.03                     430.83\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.8}                  36.80±0.50     37.44±0.53        38.05±4.44                     436.93\n",
      "{'alpha': '3.16e-02', 'p_quit': 0.9}                  37.49±0.59     38.00±0.72        36.65±5.71                     431.68\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.1}                  60.58±29.09    61.44±30.12       61.60±30.12                    440.48\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.2}                  37.32±0.50     38.11±0.60        37.13±4.73                     429.71\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.30000000000000004}  36.93±0.45     37.68±0.52        37.06±4.18                     430.42\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.4}                  36.88±0.45     37.59±0.52        36.74±4.40                     434.58\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.5}                  36.83±0.45     37.44±0.52        37.39±4.09                     434.11\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.6}                  36.92±0.50     37.64±0.56        37.30±4.52                     435.42\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.7000000000000001}   37.07±0.47     37.58±0.56        37.60±4.19                     430.83\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.8}                  37.25±0.51     37.67±0.55        38.29±4.62                     436.93\n",
      "{'alpha': '1.00e-01', 'p_quit': 0.9}                  37.79±0.63     38.15±0.72        36.88±5.89                     431.68\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.1}                  44.43±0.59     44.37±0.65        45.19±5.57                     440.48\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.2}                  41.10±1.93     41.28±1.72        39.97±5.95                     429.71\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.30000000000000004}  45.25±15.98    45.22±15.86       45.13±17.06                    430.42\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.4}                  40.66±10.61    41.01±10.22       40.86±11.40                    434.58\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.5}                  37.63±0.46     37.96±0.52        37.70±4.46                     434.11\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.6}                  37.57±0.51     37.99±0.58        37.70±4.43                     435.42\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.7000000000000001}   37.59±0.49     37.88±0.58        37.73±4.31                     430.83\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.8}                  37.63±0.52     37.86±0.57        38.35±4.65                     436.93\n",
      "{'alpha': '3.16e-01', 'p_quit': 0.9}                  37.97±0.65     38.21±0.72        36.96±6.04                     431.68\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.1}                  58.31±0.56     57.91±0.60        59.28±6.97                     440.48\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.2}                  44.69±0.67     44.52±0.71        42.92±6.64                     429.71\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.30000000000000004}  41.75±0.44     41.72±0.48        40.39±5.13                     430.42\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.4}                  40.63±0.51     40.70±0.52        40.51±5.48                     434.58\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.5}                  40.18±0.84     40.27±0.78        39.35±5.39                     434.11\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.6}                  46.12±17.33    46.11±16.73       46.13±18.19                    435.42\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.7000000000000001}   64.73±88.27    63.75±84.43       64.70±87.92                    430.83\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.8}                  48.77±19.72    48.99±19.59       48.57±19.14                    436.93\n",
      "{'alpha': '1.00e+00', 'p_quit': 0.9}                  68.16±95.63    68.24±95.95       66.88±89.26                    431.68\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.1}                  87.22±0.61     86.83±0.58        88.79±7.57                     440.48\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.2}                  59.33±0.64     58.82±0.71        56.48±8.10                     429.71\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.30000000000000004}  49.83±0.47     49.46±0.52        48.16±5.93                     430.42\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.4}                  45.89±0.53     45.64±0.60        46.06±6.59                     434.58\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.5}                  44.05±0.56     43.84±0.62        42.77±6.57                     434.11\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.6}                  42.99±0.45     42.84±0.53        42.71±4.84                     435.42\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.7000000000000001}   42.27±0.53     42.15±0.60        41.46±5.64                     430.83\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.8}                  41.69±0.53     41.58±0.56        40.82±5.40                     436.93\n",
      "{'alpha': '3.16e+00', 'p_quit': 0.9}                  41.35±0.68     41.26±0.66        39.97±7.09                     431.68\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.1}                  116.09±0.75    115.74±0.70       118.13±7.66                    440.48\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.2}                  89.07±0.66     88.54±0.71        85.80±9.03                     429.71\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.30000000000000004}  71.73±0.44     71.21±0.50        70.31±7.23                     430.42\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.4}                  61.31±0.56     60.86±0.61        61.64±8.96                     434.58\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.5}                  55.20±0.59     54.69±0.75        53.07±8.38                     434.11\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.6}                  51.33±0.47     50.93±0.56        50.67±6.62                     435.42\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.7000000000000001}   48.84±0.57     48.45±0.70        47.72±6.62                     430.83\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.8}                  47.13±0.55     46.84±0.58        45.41±6.73                     436.93\n",
      "{'alpha': '1.00e+01', 'p_quit': 0.9}                  45.90±0.71     45.60±0.70        43.98±8.10                     431.68\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.1}                  131.81±0.86    131.46±0.81       134.07±7.69                    440.48\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.2}                  117.65±0.84    117.17±0.88       114.39±9.27                    429.71\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.30000000000000004}  103.51±0.59    103.04±0.61       102.45±7.85                    430.42\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.4}                  91.39±0.72     90.97±0.73        91.90±10.26                    434.58\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.5}                  81.72±0.66     81.18±0.80        79.07±9.77                     434.11\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.6}                  73.71±0.53     73.22±0.59        72.76±8.79                     435.42\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.7000000000000001}   67.36±0.53     66.78±0.71        66.16±7.38                     430.83\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.8}                  62.34±0.52     61.84±0.59        59.90±8.78                     436.93\n",
      "{'alpha': '3.16e+01', 'p_quit': 0.9}                  58.29±0.69     57.79±0.72        55.26±9.89                     431.68\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.1}                  137.94±0.90    137.58±0.86       140.27±7.70                    440.48\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.2}                  132.81±0.96    132.35±1.01       129.59±9.32                    429.71\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.30000000000000004}  126.03±0.78    125.60±0.78       125.13±8.05                    430.42\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.4}                  118.95±0.95    118.57±0.96       119.55±10.52                   434.58\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.5}                  112.23±0.88    111.76±0.96       109.45±10.11                   434.11\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.6}                  105.22±0.78    104.79±0.78       104.26±9.45                    435.42\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.7000000000000001}   98.56±0.59     98.03±0.72        97.49±7.55                     430.83\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.8}                  92.25±0.65     91.74±0.72        89.71±9.76                     436.93\n",
      "{'alpha': '1.00e+02', 'p_quit': 0.9}                  86.22±0.79     85.70±0.78        82.56±11.26                    431.68\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.1}                  140.02±0.92    139.66±0.87       142.38±7.70                    440.48\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.2}                  138.66±1.02    138.19±1.06       135.45±9.34                    429.71\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.30000000000000004}  136.03±0.88    135.61±0.88       135.18±8.12                    430.42\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.4}                  133.12±1.09    132.76±1.10       133.74±10.57                   434.58\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.5}                  130.39±1.04    129.96±1.10       127.56±10.16                   434.11\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.6}                  126.89±0.97    126.49±0.95       125.95±9.52                    435.42\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.7000000000000001}   123.30±0.72    122.85±0.82       122.33±7.51                    430.83\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.8}                  119.57±0.88    119.11±0.94       117.08±9.93                    436.93\n",
      "{'alpha': '3.16e+02', 'p_quit': 0.9}                  115.54±1.07    115.09±1.03       111.75±11.67                   431.68\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.1}                  140.69±0.92    140.33±0.88       143.06±7.70                    440.48\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.2}                  140.63±1.04    140.17±1.08       137.44±9.35                    429.71\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.30000000000000004}  139.61±0.92    139.19±0.91       138.77±8.14                    430.42\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.4}                  138.50±1.15    138.14±1.16       139.13±10.58                   434.58\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.5}                  137.77±1.11    137.35±1.17       134.93±10.16                   434.11\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.6}                  136.36±1.05    135.97±1.03       135.42±9.51                    435.42\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.7000000000000001}   134.99±0.79    134.55±0.89       134.05±7.49                    430.83\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.8}                  133.56±1.02    133.13±1.06       131.10±9.95                    436.93\n",
      "{'alpha': '1.00e+03', 'p_quit': 0.9}                  131.91±1.26    131.49±1.21       128.09±11.77                   431.68\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.1}                  140.91±0.93    140.55±0.88       143.28±7.70                    440.48\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.2}                  141.27±1.04    140.81±1.09       138.08±9.35                    429.71\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.30000000000000004}  140.78±0.93    140.37±0.92       139.96±8.14                    430.42\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.4}                  140.31±1.17    139.96±1.18       140.94±10.58                   434.58\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.5}                  140.31±1.14    139.90±1.19       137.47±10.17                   434.11\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.6}                  139.72±1.08    139.33±1.06       138.79±9.50                    435.42\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.7000000000000001}   139.26±0.83    138.84±0.92       138.34±7.48                    430.83\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.8}                  138.86±1.07    138.45±1.12       136.41±9.95                    436.93\n",
      "{'alpha': '3.16e+03', 'p_quit': 0.9}                  138.37±1.34    137.96±1.29       134.54±11.79                   431.68\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.1}                  140.97±0.93    140.61±0.88       143.35±7.71                    440.48\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.2}                  141.48±1.04    141.01±1.09       138.28±9.35                    429.71\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.30000000000000004}  141.16±0.93    140.74±0.93       140.33±8.15                    430.42\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.4}                  140.90±1.18    140.54±1.18       141.53±10.58                   434.58\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.5}                  141.14±1.15    140.73±1.20       138.29±10.17                   434.11\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.6}                  140.82±1.09    140.44±1.07       139.89±9.49                    435.42\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.7000000000000001}   140.68±0.84    140.26±0.93       139.76±7.47                    430.83\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.8}                  140.65±1.09    140.23±1.13       138.20±9.95                    436.93\n",
      "{'alpha': '1.00e+04', 'p_quit': 0.9}                  140.57±1.36    140.16±1.32       136.74±11.80                   431.68\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.1}                  141.00±0.93    140.64±0.88       143.37±7.71                    440.48\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.2}                  141.54±1.04    141.08±1.09       138.35±9.35                    429.71\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.30000000000000004}  141.28±0.93    140.86±0.93       140.45±8.15                    430.42\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.4}                  141.08±1.18    140.73±1.18       141.71±10.58                   434.58\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.5}                  141.41±1.15    141.00±1.20       138.56±10.17                   434.11\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.6}                  141.17±1.10    140.79±1.07       140.24±9.49                    435.42\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.7000000000000001}   141.14±0.84    140.72±0.93       140.22±7.47                    430.83\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.8}                  141.22±1.10    140.81±1.14       138.77±9.95                    436.93\n",
      "{'alpha': '3.16e+04', 'p_quit': 0.9}                  141.28±1.37    140.88±1.32       137.45±11.80                   431.68\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.1}                  141.00±0.93    140.64±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.2}                  141.56±1.04    141.10±1.09       138.37±9.35                    429.71\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.30000000000000004}  141.32±0.93    140.90±0.93       140.49±8.15                    430.42\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.4}                  141.14±1.18    140.79±1.19       141.77±10.58                   434.58\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.5}                  141.49±1.15    141.08±1.20       138.64±10.17                   434.11\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.6}                  141.29±1.10    140.91±1.08       140.35±9.49                    435.42\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.7000000000000001}   141.28±0.84    140.86±0.93       140.36±7.47                    430.83\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.8}                  141.41±1.10    140.99±1.14       138.95±9.95                    436.93\n",
      "{'alpha': '1.00e+05', 'p_quit': 0.9}                  141.51±1.37    141.10±1.33       137.68±11.80                   431.68\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.1}                  141.00±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.37±9.35                    429.71\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.30000000000000004}  141.33±0.93    140.91±0.93       140.50±8.15                    430.42\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.4}                  141.16±1.18    140.80±1.19       141.79±10.58                   434.58\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.5}                  141.52±1.15    141.11±1.20       138.67±10.17                   434.11\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.6}                  141.32±1.10    140.94±1.08       140.39±9.49                    435.42\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.7000000000000001}   141.33±0.84    140.91±0.93       140.41±7.47                    430.83\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.8}                  141.46±1.10    141.05±1.14       139.01±9.95                    436.93\n",
      "{'alpha': '3.16e+05', 'p_quit': 0.9}                  141.58±1.38    141.18±1.33       137.75±11.80                   431.68\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.1}                  141.00±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.37±9.35                    429.71\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.30000000000000004}  141.33±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.4}                  141.16±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.5}                  141.53±1.15    141.11±1.20       138.67±10.17                   434.11\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.6}                  141.33±1.10    140.95±1.08       140.40±9.49                    435.42\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.7000000000000001}   141.34±0.84    140.92±0.93       140.42±7.47                    430.83\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.8}                  141.48±1.10    141.07±1.14       139.03±9.95                    436.93\n",
      "{'alpha': '1.00e+06', 'p_quit': 0.9}                  141.60±1.38    141.20±1.33       137.77±11.80                   431.68\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.37±9.35                    429.71\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.8}                  141.49±1.10    141.07±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '3.16e+06', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '1.00e+07', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '3.16e+07', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '1.00e+08', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '3.16e+08', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '1.00e+09', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '3.16e+09', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.1}                  141.01±0.93    140.65±0.88       143.38±7.71                    440.48\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.2}                  141.57±1.04    141.11±1.09       138.38±9.35                    429.71\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.30000000000000004}  141.34±0.93    140.92±0.93       140.51±8.15                    430.42\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.4}                  141.17±1.18    140.81±1.19       141.80±10.58                   434.58\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.5}                  141.53±1.15    141.12±1.20       138.68±10.17                   434.11\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.6}                  141.34±1.10    140.96±1.08       140.41±9.49                    435.42\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.7000000000000001}   141.35±0.84    140.93±0.93       140.43±7.47                    430.83\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.8}                  141.49±1.10    141.08±1.14       139.04±9.95                    436.93\n",
      "{'alpha': '1.00e+10', 'p_quit': 0.9}                  141.61±1.38    141.21±1.33       137.78±11.80                   431.68\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "calculate performance: 100%|██████████| 11070/11070 [07:00<00:00, 40.88it/s]"
     ]
    }
   ],
   "source": [
    "%load_ext line_profiler\n",
    "%matplotlib inline\n",
    "import numpy as np\n",
    "import sys\n",
    "sys.path.insert(0, \"../\")\n",
    "from pygraph.utils.model_selection_precomputed import model_selection_for_precomputed_kernel\n",
    "from pygraph.kernels.marginalizedKernel import marginalizedkernel\n",
    "\n",
    "datafile = '../../../../datasets/acyclic/Acyclic/dataset_bps.ds'\n",
    "estimator = marginalizedkernel\n",
    "param_grid_precomputed = {'p_quit': np.linspace(0.1, 0.9, 9)}\n",
    "param_grid = {'alpha': np.logspace(-10, 10, num = 41, base = 10)}\n",
    "\n",
    "model_selection_for_precomputed_kernel(datafile, estimator, param_grid_precomputed, param_grid, \n",
    "                                       'regression', NUM_TRIALS=30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The line_profiler extension is already loaded. To reload it, use:\n",
      "  %reload_ext line_profiler\n",
      "\n",
      " --- This is a regression problem ---\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.1 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 258.76952958106995 seconds ---\n",
      "[[ 0.0287062   0.0124634   0.00444444 ...,  0.00606061  0.00606061\n",
      "   0.00606061]\n",
      " [ 0.0124634   0.01108958  0.00333333 ...,  0.00454545  0.00454545\n",
      "   0.00454545]\n",
      " [ 0.00444444  0.00333333  0.0287062  ...,  0.00819912  0.00819912\n",
      "   0.00975875]\n",
      " ..., \n",
      " [ 0.00606061  0.00454545  0.00819912 ...,  0.02846735  0.02836907\n",
      "   0.02896354]\n",
      " [ 0.00606061  0.00454545  0.00819912 ...,  0.02836907  0.02831424\n",
      "   0.0288712 ]\n",
      " [ 0.00606061  0.00454545  0.00975875 ...,  0.02896354  0.0288712\n",
      "   0.02987915]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 12.186285\n",
      "With standard deviation: 7.038988\n",
      "\n",
      " Mean performance on test set: 18.024312\n",
      "With standard deviation: 6.292466\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.2 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 256.3271746635437 seconds ---\n",
      "[[ 0.06171557  0.03856471  0.01777778 ...,  0.02424242  0.02424242\n",
      "   0.02424242]\n",
      " [ 0.03856471  0.03579176  0.01333333 ...,  0.01818182  0.01818182\n",
      "   0.01818182]\n",
      " [ 0.01777778  0.01333333  0.06171557 ...,  0.02994207  0.02994207\n",
      "   0.03262072]\n",
      " ..., \n",
      " [ 0.02424242  0.01818182  0.02994207 ...,  0.07442109  0.07434207\n",
      "   0.07383563]\n",
      " [ 0.02424242  0.01818182  0.02994207 ...,  0.07434207  0.07430377\n",
      "   0.07376068]\n",
      " [ 0.02424242  0.01818182  0.03262072 ...,  0.07383563  0.07376068\n",
      "   0.07366354]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 13.955359\n",
      "With standard deviation: 7.544068\n",
      "\n",
      " Mean performance on test set: 18.337589\n",
      "With standard deviation: 5.854545\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.3 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 255.61398577690125 seconds ---\n",
      "[[ 0.09803909  0.07202114  0.04       ...,  0.05454545  0.05454545\n",
      "   0.05454545]\n",
      " [ 0.07202114  0.06853421  0.03       ...,  0.04090909  0.04090909\n",
      "   0.04090909]\n",
      " [ 0.04        0.03        0.09803909 ...,  0.06368916  0.06368916\n",
      "   0.06678704]\n",
      " ..., \n",
      " [ 0.05454545  0.04090909  0.06368916 ...,  0.12892852  0.12891455\n",
      "   0.12734365]\n",
      " [ 0.05454545  0.04090909  0.06368916 ...,  0.12891455  0.12892664\n",
      "   0.12733207]\n",
      " [ 0.05454545  0.04090909  0.06678704 ...,  0.12734365  0.12733207\n",
      "   0.1261675 ]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 13.939071\n",
      "With standard deviation: 7.958123\n",
      "\n",
      " Mean performance on test set: 18.495992\n",
      "With standard deviation: 5.734918\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.4 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 254.89703965187073 seconds ---\n",
      "[[ 0.13888889  0.11120616  0.07111111 ...,  0.0969697   0.0969697\n",
      "   0.0969697 ]\n",
      " [ 0.11120616  0.10756609  0.05333333 ...,  0.07272727  0.07272727\n",
      "   0.07272727]\n",
      " [ 0.07111111  0.05333333  0.13888889 ...,  0.10909713  0.10909713\n",
      "   0.11216176]\n",
      " ..., \n",
      " [ 0.0969697   0.07272727  0.10909713 ...,  0.19178929  0.19182091\n",
      "   0.18963212]\n",
      " [ 0.0969697   0.07272727  0.10909713 ...,  0.19182091  0.19186661\n",
      "   0.18966477]\n",
      " [ 0.0969697   0.07272727  0.11216176 ...,  0.18963212  0.18966477\n",
      "   0.18786824]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 16.259313\n",
      "With standard deviation: 6.693580\n",
      "\n",
      " Mean performance on test set: 19.449149\n",
      "With standard deviation: 5.371295\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.5 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 256.75693798065186 seconds ---\n",
      "[[ 0.18518519  0.15591398  0.11111111 ...,  0.15151515  0.15151515\n",
      "   0.15151515]\n",
      " [ 0.15591398  0.15254237  0.08333333 ...,  0.11363636  0.11363636\n",
      "   0.11363636]\n",
      " [ 0.11111111  0.08333333  0.18518519 ...,  0.16617791  0.16617791\n",
      "   0.16890214]\n",
      " ..., \n",
      " [ 0.15151515  0.11363636  0.16617791 ...,  0.26386999  0.26391515\n",
      "   0.26158184]\n",
      " [ 0.15151515  0.11363636  0.16617791 ...,  0.26391515  0.26396688\n",
      "   0.26162729]\n",
      " [ 0.15151515  0.11363636  0.16890214 ...,  0.26158184  0.26162729\n",
      "   0.25964592]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 17.018055\n",
      "With standard deviation: 6.844372\n",
      "\n",
      " Mean performance on test set: 19.785683\n",
      "With standard deviation: 5.550543\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.6 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 256.5566437244415 seconds ---\n",
      "[[ 0.23809524  0.20664506  0.16       ...,  0.21818182  0.21818182\n",
      "   0.21818182]\n",
      " [ 0.20664506  0.20385906  0.12       ...,  0.16363636  0.16363636\n",
      "   0.16363636]\n",
      " [ 0.16        0.12        0.23809524 ...,  0.2351024   0.2351024\n",
      "   0.23727718]\n",
      " ..., \n",
      " [ 0.21818182  0.16363636  0.2351024  ...,  0.34658956  0.34662512\n",
      "   0.34454945]\n",
      " [ 0.21818182  0.16363636  0.2351024  ...,  0.34662512  0.34666325\n",
      "   0.34458505]\n",
      " [ 0.21818182  0.16363636  0.23727718 ...,  0.34454945  0.34458505\n",
      "   0.34279503]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 17.661762\n",
      "With standard deviation: 6.567179\n",
      "\n",
      " Mean performance on test set: 20.192158\n",
      "With standard deviation: 5.591223\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.7 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 254.9531705379486 seconds ---\n",
      "[[ 0.2991453   0.26444601  0.21777778 ...,  0.2969697   0.2969697\n",
      "   0.2969697 ]\n",
      " [ 0.26444601  0.26246188  0.16333333 ...,  0.22272727  0.22272727\n",
      "   0.22272727]\n",
      " [ 0.21777778  0.16333333  0.2991453  ...,  0.31614548  0.31614548\n",
      "   0.31765009]\n",
      " ..., \n",
      " [ 0.2969697   0.22272727  0.31614548 ...,  0.44189997  0.44191814\n",
      "   0.44038348]\n",
      " [ 0.2969697   0.22272727  0.31614548 ...,  0.44191814  0.44193708\n",
      "   0.44040164]\n",
      " [ 0.2969697   0.22272727  0.31765009 ...,  0.44038348  0.44040164\n",
      "   0.43906772]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 20.588213\n",
      "With standard deviation: 5.746009\n",
      "\n",
      " Mean performance on test set: 21.661372\n",
      "With standard deviation: 6.026849\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.8 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 252.80415797233582 seconds ---\n",
      "[[ 0.37037037  0.33093141  0.28444444 ...,  0.38787879  0.38787879\n",
      "   0.38787879]\n",
      " [ 0.33093141  0.32983023  0.21333333 ...,  0.29090909  0.29090909\n",
      "   0.29090909]\n",
      " [ 0.28444444  0.21333333  0.37037037 ...,  0.4096795   0.4096795\n",
      "   0.41049599]\n",
      " ..., \n",
      " [ 0.38787879  0.29090909  0.4096795  ...,  0.55242487  0.55243009\n",
      "   0.5515636 ]\n",
      " [ 0.38787879  0.29090909  0.4096795  ...,  0.55243009  0.55243545\n",
      "   0.55156881]\n",
      " [ 0.38787879  0.29090909  0.41049599 ...,  0.5515636   0.55156881\n",
      "   0.55081257]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 23.594332\n",
      "With standard deviation: 3.806374\n",
      "\n",
      " Mean performance on test set: 22.996018\n",
      "With standard deviation: 6.083466\n",
      "\n",
      "\n",
      " #--- calculating kernel matrix when p_quit = 0.9 ---#\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 256.7384788990021 seconds ---\n",
      "[[ 0.45454545  0.40839542  0.36       ...,  0.49090909  0.49090909\n",
      "   0.49090909]\n",
      " [ 0.40839542  0.40805534  0.27       ...,  0.36818182  0.36818182\n",
      "   0.36818182]\n",
      " [ 0.36        0.27        0.45454545 ...,  0.51619708  0.51619708\n",
      "   0.51644564]\n",
      " ..., \n",
      " [ 0.49090909  0.36818182  0.51619708 ...,  0.68172189  0.68172233\n",
      "   0.68145294]\n",
      " [ 0.49090909  0.36818182  0.51619708 ...,  0.68172233  0.68172277\n",
      "   0.68145338]\n",
      " [ 0.49090909  0.36818182  0.51644564 ...,  0.68145294  0.68145338\n",
      "   0.68121781]]\n",
      "\n",
      " Saving kernel matrix to file...\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Mean performance on train set: 25.808155\n",
      "With standard deviation: 3.312074\n",
      "\n",
      " Mean performance on test set: 24.424089\n",
      "With standard deviation: 4.951191\n",
      "\n",
      "\n",
      "  p_quit    RMSE_test    std_test    RMSE_train    std_train    k_time\n",
      "--------  -----------  ----------  ------------  -----------  --------\n",
      "     0.1      18.0243     6.29247       12.1863      7.03899   258.77\n",
      "     0.2      18.3376     5.85454       13.9554      7.54407   256.327\n",
      "     0.3      18.496      5.73492       13.9391      7.95812   255.614\n",
      "     0.4      19.4491     5.3713        16.2593      6.69358   254.897\n",
      "     0.5      19.7857     5.55054       17.0181      6.84437   256.757\n",
      "     0.6      20.1922     5.59122       17.6618      6.56718   256.557\n",
      "     0.7      21.6614     6.02685       20.5882      5.74601   254.953\n",
      "     0.8      22.996      6.08347       23.5943      3.80637   252.804\n",
      "     0.9      24.4241     4.95119       25.8082      3.31207   256.738\n"
     ]
    }
   ],
   "source": [
    "%load_ext line_profiler\n",
    "\n",
    "import numpy as np\n",
    "import sys\n",
    "sys.path.insert(0, \"../\")\n",
    "from pygraph.utils.utils import kernel_train_test\n",
    "from pygraph.kernels.marginalizedKernel import marginalizedkernel, _marginalizedkernel_do\n",
    "\n",
    "datafile = '../../../../datasets/acyclic/Acyclic/dataset_bps.ds'\n",
    "kernel_file_path = 'kernelmatrices_weisfeilerlehman_subtree_acyclic/'\n",
    "\n",
    "kernel_para = dict(node_label = 'atom', edge_label = 'bond_type', itr = 20)\n",
    "\n",
    "kernel_train_test(datafile, kernel_file_path, marginalizedkernel, kernel_para, \\\n",
    "    hyper_name = 'p_quit', hyper_range = np.linspace(0.1, 0.9, 9), normalize = False)\n",
    "\n",
    "# %lprun -f _marginalizedkernel_do \\\n",
    "#     kernel_train_test(datafile, kernel_file_path, marginalizedkernel, kernel_para, \\\n",
    "#     hyper_name = 'p_quit', hyper_range = np.linspace(0.1, 0.9, 9), normalize = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# results\n",
    "\n",
    "# with y normalization\n",
    "  p_quit    RMSE_test    std_test    RMSE_train    std_train    k_time\n",
    "--------  -----------  ----------  ------------  -----------  --------\n",
    "     0.1      18.0192     6.27867       12.1642      6.99821   266.905\n",
    "     0.2      18.3374     5.84775       13.9376      7.51398   256.288\n",
    "     0.3      18.4955     5.73774       13.9291      7.9416    254.441\n",
    "     0.4      19.4498     5.37509       16.2538      6.68378   257.581\n",
    "     0.5      19.7851     5.55018       17.0142      6.83653   248.562\n",
    "     0.6      20.1911     5.58951       17.6595      6.56211   249.667\n",
    "     0.7      21.6606     6.02589       20.5872      5.74395   243.046\n",
    "     0.8      22.9959     6.08344       23.5941      3.80595   252.36\n",
    "     0.9      24.424      4.9512        25.8082      3.31202   248.077\n",
    "\n",
    "# without y normalization\n",
    "  p_quit    RMSE_test    std_test    RMSE_train    std_train    k_time\n",
    "--------  -----------  ----------  ------------  -----------  --------\n",
    "     0.1      18.0243     6.29247       12.1863      7.03899   258.77\n",
    "     0.2      18.3376     5.85454       13.9554      7.54407   256.327\n",
    "     0.3      18.496      5.73492       13.9391      7.95812   255.614\n",
    "     0.4      19.4491     5.3713        16.2593      6.69358   254.897\n",
    "     0.5      19.7857     5.55054       17.0181      6.84437   256.757\n",
    "     0.6      20.1922     5.59122       17.6618      6.56718   256.557\n",
    "     0.7      21.6614     6.02685       20.5882      5.74601   254.953\n",
    "     0.8      22.996      6.08347       23.5943      3.80637   252.804\n",
    "     0.9      24.4241     4.95119       25.8082      3.31207   256.738"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " --- This is a regression problem ---\n",
      "\n",
      "\n",
      " Loading dataset from file...\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 1133.0229969024658 seconds ---\n",
      "[[ 0.0287062   0.0124634   0.00444444 ...,  0.00606061  0.00606061\n",
      "   0.00606061]\n",
      " [ 0.0124634   0.01108958  0.00333333 ...,  0.00454545  0.00454545\n",
      "   0.00454545]\n",
      " [ 0.00444444  0.00333333  0.0287062  ...,  0.00819912  0.00819912\n",
      "   0.00975875]\n",
      " ..., \n",
      " [ 0.00606061  0.00454545  0.00819912 ...,  0.02846735  0.02836907\n",
      "   0.02896354]\n",
      " [ 0.00606061  0.00454545  0.00819912 ...,  0.02836907  0.02831424\n",
      "   0.0288712 ]\n",
      " [ 0.00606061  0.00454545  0.00975875 ...,  0.02896354  0.0288712\n",
      "   0.02987915]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on train set: 12.186285\n",
      "With standard deviation: 7.038988\n",
      "\n",
      " Mean performance on test set: 18.024312\n",
      "With standard deviation: 6.292466\n",
      "\n",
      "\n",
      "  rmse_test    std_test    rmse_train    std_train    k_time\n",
      "-----------  ----------  ------------  -----------  --------\n",
      "    18.0243     6.29247       12.1863      7.03899   1133.02\n"
     ]
    }
   ],
   "source": [
    "%load_ext line_profiler\n",
    "\n",
    "import numpy as np\n",
    "import sys\n",
    "sys.path.insert(0, \"../\")\n",
    "from pygraph.utils.utils import kernel_train_test\n",
    "from pygraph.kernels.marginalizedKernel import marginalizedkernel, _marginalizedkernel_do\n",
    "\n",
    "datafile = '../../../../datasets/acyclic/Acyclic/dataset_bps.ds'\n",
    "kernel_file_path = 'kernelmatrices_weisfeilerlehman_subtree_acyclic/'\n",
    "\n",
    "kernel_para = dict(node_label = 'atom', edge_label = 'bond_type', itr = 20, p_quit = 0.1)\n",
    "\n",
    "# kernel_train_test(datafile, kernel_file_path, marginalizedkernel, kernel_para, \\\n",
    "#     hyper_name = 'p_quit', hyper_range = np.linspace(0.1, 0.9, 9), normalize = False)\n",
    "\n",
    "%lprun -f _marginalizedkernel_do \\\n",
    "    kernel_train_test(datafile, kernel_file_path, marginalizedkernel, kernel_para, \\\n",
    "    normalize = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Timer unit: 1e-06 s\n",
    "\n",
    "Total time: 828.879 s\n",
    "File: ../pygraph/kernels/marginalizedKernel.py\n",
    "Function: _marginalizedkernel_do at line 67\n",
    "\n",
    "Line #      Hits         Time  Per Hit   % Time  Line Contents\n",
    "==============================================================\n",
    "    67                                           def _marginalizedkernel_do(G1, G2, node_label, edge_label, p_quit, itr):\n",
    "    68                                               \"\"\"Calculate marginalized graph kernel between 2 graphs.\n",
    "    69                                               \n",
    "    70                                               Parameters\n",
    "    71                                               ----------\n",
    "    72                                               G1, G2 : NetworkX graphs\n",
    "    73                                                   2 graphs between which the kernel is calculated.\n",
    "    74                                               node_label : string\n",
    "    75                                                   node attribute used as label.\n",
    "    76                                               edge_label : string\n",
    "    77                                                   edge attribute used as label.\n",
    "    78                                               p_quit : integer\n",
    "    79                                                   the termination probability in the random walks generating step.\n",
    "    80                                               itr : integer\n",
    "    81                                                   time of iterations to calculate R_inf.\n",
    "    82                                                   \n",
    "    83                                               Return\n",
    "    84                                               ------\n",
    "    85                                               kernel : float\n",
    "    86                                                   Marginalized Kernel between 2 graphs.\n",
    "    87                                               \"\"\"\n",
    "    88                                               # init parameters\n",
    "    89     17205      12886.0      0.7      0.0      kernel = 0\n",
    "    90     17205      52542.0      3.1      0.0      num_nodes_G1 = nx.number_of_nodes(G1)\n",
    "    91     17205      28240.0      1.6      0.0      num_nodes_G2 = nx.number_of_nodes(G2)\n",
    "    92     17205      15595.0      0.9      0.0      p_init_G1 = 1 / num_nodes_G1 # the initial probability distribution in the random walks generating step (uniform distribution over |G|)\n",
    "    93     17205      11587.0      0.7      0.0      p_init_G2 = 1 / num_nodes_G2\n",
    "    94                                           \n",
    "    95     17205      11663.0      0.7      0.0      q = p_quit * p_quit\n",
    "    96     17205      10728.0      0.6      0.0      r1 = q\n",
    "    97                                           \n",
    "    98                                               # initial R_inf\n",
    "    99     17205      38412.0      2.2      0.0      R_inf = np.zeros([num_nodes_G1, num_nodes_G2]) # matrix to save all the R_inf for all pairs of nodes\n",
    "   100                                           \n",
    "   101                                               # calculate R_inf with a simple interative method\n",
    "   102    344100     329235.0      1.0      0.0      for i in range(1, itr):\n",
    "   103    326895     900354.0      2.8      0.1          R_inf_new = np.zeros([num_nodes_G1, num_nodes_G2])\n",
    "   104    326895    2287346.0      7.0      0.3          R_inf_new.fill(r1)\n",
    "   105                                           \n",
    "   106                                                   # calculate R_inf for each pair of nodes\n",
    "   107   2653464    3667117.0      1.4      0.4          for node1 in G1.nodes(data = True):\n",
    "   108   2326569    7522840.0      3.2      0.9              neighbor_n1 = G1[node1[0]]\n",
    "   109   2326569    3492118.0      1.5      0.4              p_trans_n1 = (1 - p_quit) / len(neighbor_n1) # the transition probability distribution in the random walks generating step (uniform distribution over the vertices adjacent to the current vertex)\n",
    "   110  24024379   27775021.0      1.2      3.4              for node2 in G2.nodes(data = True):\n",
    "   111  21697810   69471941.0      3.2      8.4                  neighbor_n2 = G2[node2[0]]\n",
    "   112  21697810   32446626.0      1.5      3.9                  p_trans_n2 = (1 - p_quit) / len(neighbor_n2)    \n",
    "   113                                           \n",
    "   114  59095092   52545370.0      0.9      6.3                  for neighbor1 in neighbor_n1:\n",
    "   115 104193150   92513935.0      0.9     11.2                      for neighbor2 in neighbor_n2:\n",
    "   116                                           \n",
    "   117                                                                   t = p_trans_n1 * p_trans_n2 * \\\n",
    "   118  66795868  285324518.0      4.3     34.4                              deltakernel(G1.node[neighbor1][node_label] == G2.node[neighbor2][node_label]) * \\\n",
    "   119  66795868  137934393.0      2.1     16.6                              deltakernel(neighbor_n1[neighbor1][edge_label] == neighbor_n2[neighbor2][edge_label])\n",
    "   120  66795868  106834143.0      1.6     12.9                          R_inf_new[node1[0]][node2[0]] += t * R_inf[neighbor1][neighbor2] # ref [1] equation (8)\n",
    "   121                                           \n",
    "   122    326895    1123677.0      3.4      0.1          R_inf[:] = R_inf_new\n",
    "   123                                           \n",
    "   124                                               # add elements of R_inf up and calculate kernel\n",
    "   125    139656     330283.0      2.4      0.0      for node1 in G1.nodes(data = True):\n",
    "   126   1264441    1435263.0      1.1      0.2          for node2 in G2.nodes(data = True):                \n",
    "   127   1141990    1377134.0      1.2      0.2              s = p_init_G1 * p_init_G2 * deltakernel(node1[1][node_label] == node2[1][node_label])\n",
    "   128   1141990    1375456.0      1.2      0.2              kernel += s * R_inf[node1[0]][node2[0]] # ref [1] equation (6)\n",
    "   129                                           \n",
    "   130     17205      10801.0      0.6      0.0      return kernel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "- This script take as input a kernel matrix\n",
      "and returns the classification or regression performance\n",
      "- The kernel matrix can be calculated using any of the graph kernels approaches\n",
      "- The criteria used for prediction are SVM for classification and kernel Ridge regression for regression\n",
      "- For predition we divide the data in training, validation and test. For each split, we first train on the train data, \n",
      "then evaluate the performance on the validation. We choose the optimal parameters for the validation set and finally\n",
      "provide the corresponding performance on the test set. If more than one split is performed, the final results \n",
      "correspond to the average of the performances on the test sets. \n",
      "\n",
      "@references\n",
      "    https://github.com/eghisu/GraphKernels/blob/master/GraphKernelsCollection/python_scripts/compute_perf_gk.py\n",
      "\n",
      "\n",
      " Loading dataset from file...\n",
      "[ -23.7   14.    37.3  109.7   10.8   39.    42.    66.6  135.   148.5\n",
      "   40.    34.6   32.    63.    53.5   67.    64.4   84.7   95.5   92.\n",
      "   84.4  154.   156.   166.   183.    70.3   63.6   52.5   59.    59.5\n",
      "   55.2   88.    83.   104.5  102.    92.   107.4  123.2  112.5  118.5\n",
      "  101.5  173.7  165.5  181.    99.5   92.3   90.1   80.2   82.    91.2\n",
      "   91.5   81.2   93.    69.    86.3   82.   103.   103.5   96.   112.   104.\n",
      "  132.5  123.5  120.3  145.   144.2  142.8  132.   134.2  137.   139.\n",
      "  133.6  120.4  120.   137.   195.8  177.2  181.   185.9  175.7  186.   211.\n",
      "  125.   118.   117.1  107.   102.5  112.    97.4   91.5   87.6  106.5\n",
      "  101.    99.3   90.   137.   114.   126.   124.   140.5  157.5  146.   145.\n",
      "  141.   171.   166.   155.   145.   159.   138.   142.   159.   163.5\n",
      "  229.5  142.   125.   132.   130.5  125.   122.   121.   122.2  112.   106.\n",
      "  114.5  151.   128.5  109.5  126.   147.   158.   147.   165.   188.9\n",
      "  170.   178.   148.5  165.   177.   167.   195.   226.   215.   201.   205.\n",
      "  151.5  165.5  157.   139.   163.   153.5  139.   162.   173.   159.5\n",
      "  159.5  155.5  141.   126.   164.   163.   166.5  146.   165.   159.   195.\n",
      "  218.   250.   235.   186.5  156.5  162.   162.   170.2  173.2  186.8\n",
      "  173.   187.   174.   188.5  199.   228.   215.   216.   240. ]\n",
      "\n",
      " --- This is a regression problem ---\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.1 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 246.21349620819092 seconds ---\n",
      "[[ 0.0287062   0.0124634   0.00444444 ...,  0.00606061  0.00606061\n",
      "   0.00606061]\n",
      " [ 0.0124634   0.01108958  0.00333333 ...,  0.00454545  0.00454545\n",
      "   0.00454545]\n",
      " [ 0.00444444  0.00333333  0.0287062  ...,  0.00819912  0.00819912\n",
      "   0.00975875]\n",
      " ..., \n",
      " [ 0.00606061  0.00454545  0.00819912 ...,  0.02846735  0.02836907\n",
      "   0.02896354]\n",
      " [ 0.00606061  0.00454545  0.00819912 ...,  0.02836907  0.02831424\n",
      "   0.0288712 ]\n",
      " [ 0.00606061  0.00454545  0.00975875 ...,  0.02896354  0.0288712\n",
      "   0.02987915]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 51.192412\n",
      "With standard deviation: 58.804642\n",
      "\n",
      " Mean performance on test set: 18.518782\n",
      "With standard deviation: 7.749004\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.2 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 240.73209404945374 seconds ---\n",
      "[[ 0.06171557  0.03856471  0.01777778 ...,  0.02424242  0.02424242\n",
      "   0.02424242]\n",
      " [ 0.03856471  0.03579176  0.01333333 ...,  0.01818182  0.01818182\n",
      "   0.01818182]\n",
      " [ 0.01777778  0.01333333  0.06171557 ...,  0.02994207  0.02994207\n",
      "   0.03262072]\n",
      " ..., \n",
      " [ 0.02424242  0.01818182  0.02994207 ...,  0.07442109  0.07434207\n",
      "   0.07383563]\n",
      " [ 0.02424242  0.01818182  0.02994207 ...,  0.07434207  0.07430377\n",
      "   0.07376068]\n",
      " [ 0.02424242  0.01818182  0.03262072 ...,  0.07383563  0.07376068\n",
      "   0.07366354]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 56.692288\n",
      "With standard deviation: 58.162153\n",
      "\n",
      " Mean performance on test set: 17.899091\n",
      "With standard deviation: 6.591042\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.3 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 244.91414594650269 seconds ---\n",
      "[[ 0.09803909  0.07202114  0.04       ...,  0.05454545  0.05454545\n",
      "   0.05454545]\n",
      " [ 0.07202114  0.06853421  0.03       ...,  0.04090909  0.04090909\n",
      "   0.04090909]\n",
      " [ 0.04        0.03        0.09803909 ...,  0.06368916  0.06368916\n",
      "   0.06678704]\n",
      " ..., \n",
      " [ 0.05454545  0.04090909  0.06368916 ...,  0.12892852  0.12891455\n",
      "   0.12734365]\n",
      " [ 0.05454545  0.04090909  0.06368916 ...,  0.12891455  0.12892664\n",
      "   0.12733207]\n",
      " [ 0.05454545  0.04090909  0.06678704 ...,  0.12734365  0.12733207\n",
      "   0.1261675 ]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 54.360795\n",
      "With standard deviation: 61.733054\n",
      "\n",
      " Mean performance on test set: 18.392352\n",
      "With standard deviation: 7.101611\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.4 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 246.01012706756592 seconds ---\n",
      "[[ 0.13888889  0.11120616  0.07111111 ...,  0.0969697   0.0969697\n",
      "   0.0969697 ]\n",
      " [ 0.11120616  0.10756609  0.05333333 ...,  0.07272727  0.07272727\n",
      "   0.07272727]\n",
      " [ 0.07111111  0.05333333  0.13888889 ...,  0.10909713  0.10909713\n",
      "   0.11216176]\n",
      " ..., \n",
      " [ 0.0969697   0.07272727  0.10909713 ...,  0.19178929  0.19182091\n",
      "   0.18963212]\n",
      " [ 0.0969697   0.07272727  0.10909713 ...,  0.19182091  0.19186661\n",
      "   0.18966477]\n",
      " [ 0.0969697   0.07272727  0.11216176 ...,  0.18963212  0.18966477\n",
      "   0.18786824]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 44.518253\n",
      "With standard deviation: 44.478206\n",
      "\n",
      " Mean performance on test set: 19.623259\n",
      "With standard deviation: 6.248069\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.5 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 241.62482810020447 seconds ---\n",
      "[[ 0.18518519  0.15591398  0.11111111 ...,  0.15151515  0.15151515\n",
      "   0.15151515]\n",
      " [ 0.15591398  0.15254237  0.08333333 ...,  0.11363636  0.11363636\n",
      "   0.11363636]\n",
      " [ 0.11111111  0.08333333  0.18518519 ...,  0.16617791  0.16617791\n",
      "   0.16890214]\n",
      " ..., \n",
      " [ 0.15151515  0.11363636  0.16617791 ...,  0.26386999  0.26391515\n",
      "   0.26158184]\n",
      " [ 0.15151515  0.11363636  0.16617791 ...,  0.26391515  0.26396688\n",
      "   0.26162729]\n",
      " [ 0.15151515  0.11363636  0.16890214 ...,  0.26158184  0.26162729\n",
      "   0.25964592]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 42.848719\n",
      "With standard deviation: 39.189276\n",
      "\n",
      " Mean performance on test set: 19.993624\n",
      "With standard deviation: 6.299511\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.6 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 240.8926112651825 seconds ---\n",
      "[[ 0.23809524  0.20664506  0.16       ...,  0.21818182  0.21818182\n",
      "   0.21818182]\n",
      " [ 0.20664506  0.20385906  0.12       ...,  0.16363636  0.16363636\n",
      "   0.16363636]\n",
      " [ 0.16        0.12        0.23809524 ...,  0.2351024   0.2351024\n",
      "   0.23727718]\n",
      " ..., \n",
      " [ 0.21818182  0.16363636  0.2351024  ...,  0.34658956  0.34662512\n",
      "   0.34454945]\n",
      " [ 0.21818182  0.16363636  0.2351024  ...,  0.34662512  0.34666325\n",
      "   0.34458505]\n",
      " [ 0.21818182  0.16363636  0.23727718 ...,  0.34454945  0.34458505\n",
      "   0.34279503]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 39.983104\n",
      "With standard deviation: 32.270969\n",
      "\n",
      " Mean performance on test set: 20.546624\n",
      "With standard deviation: 6.261735\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.7 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 240.47843861579895 seconds ---\n",
      "[[ 0.2991453   0.26444601  0.21777778 ...,  0.2969697   0.2969697\n",
      "   0.2969697 ]\n",
      " [ 0.26444601  0.26246188  0.16333333 ...,  0.22272727  0.22272727\n",
      "   0.22272727]\n",
      " [ 0.21777778  0.16333333  0.2991453  ...,  0.31614548  0.31614548\n",
      "   0.31765009]\n",
      " ..., \n",
      " [ 0.2969697   0.22272727  0.31614548 ...,  0.44189997  0.44191814\n",
      "   0.44038348]\n",
      " [ 0.2969697   0.22272727  0.31614548 ...,  0.44191814  0.44193708\n",
      "   0.44040164]\n",
      " [ 0.2969697   0.22272727  0.31765009 ...,  0.44038348  0.44040164\n",
      "   0.43906772]]\n",
      "\n",
      " Saving kernel matrix to file...\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " Mean performance on val set: 37.530308\n",
      "With standard deviation: 29.730795\n",
      "\n",
      " Mean performance on test set: 21.701779\n",
      "With standard deviation: 6.335305\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.8 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 242.16377139091492 seconds ---\n",
      "[[ 0.37037037  0.33093141  0.28444444 ...,  0.38787879  0.38787879\n",
      "   0.38787879]\n",
      " [ 0.33093141  0.32983023  0.21333333 ...,  0.29090909  0.29090909\n",
      "   0.29090909]\n",
      " [ 0.28444444  0.21333333  0.37037037 ...,  0.4096795   0.4096795\n",
      "   0.41049599]\n",
      " ..., \n",
      " [ 0.38787879  0.29090909  0.4096795  ...,  0.55242487  0.55243009\n",
      "   0.5515636 ]\n",
      " [ 0.38787879  0.29090909  0.4096795  ...,  0.55243009  0.55243545\n",
      "   0.55156881]\n",
      " [ 0.38787879  0.29090909  0.41049599 ...,  0.5515636   0.55156881\n",
      "   0.55081257]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 37.110483\n",
      "With standard deviation: 21.287120\n",
      "\n",
      " Mean performance on test set: 23.148949\n",
      "With standard deviation: 6.102457\n",
      "\n",
      " --- calculating kernel matrix when termimation probability = 0.9 ---\n",
      "\n",
      " Calculating kernel matrix, this could take a while...\n",
      "\n",
      " --- marginalized kernel matrix of size 185 built in 238.44418454170227 seconds ---\n",
      "[[ 0.45454545  0.40839542  0.36       ...,  0.49090909  0.49090909\n",
      "   0.49090909]\n",
      " [ 0.40839542  0.40805534  0.27       ...,  0.36818182  0.36818182\n",
      "   0.36818182]\n",
      " [ 0.36        0.27        0.45454545 ...,  0.51619708  0.51619708\n",
      "   0.51644564]\n",
      " ..., \n",
      " [ 0.49090909  0.36818182  0.51619708 ...,  0.68172189  0.68172233\n",
      "   0.68145294]\n",
      " [ 0.49090909  0.36818182  0.51619708 ...,  0.68172233  0.68172277\n",
      "   0.68145338]\n",
      " [ 0.49090909  0.36818182  0.51644564 ...,  0.68145294  0.68145338\n",
      "   0.68121781]]\n",
      "\n",
      " Saving kernel matrix to file...\n",
      "\n",
      " Mean performance on val set: 30.572040\n",
      "With standard deviation: 11.057046\n",
      "\n",
      " Mean performance on test set: 24.715650\n",
      "With standard deviation: 4.891587\n",
      "\n",
      "\n",
      "  p_quit      std     RMSE\n",
      "--------  -------  -------\n",
      "     0.1  7.749    18.5188\n",
      "     0.2  6.59104  17.8991\n",
      "     0.3  7.10161  18.3924\n",
      "     0.4  6.24807  19.6233\n",
      "     0.5  6.29951  19.9936\n",
      "     0.6  6.26173  20.5466\n",
      "     0.7  6.33531  21.7018\n",
      "     0.8  6.10246  23.1489\n",
      "     0.9  4.89159  24.7157\n"
     ]
    }
   ],
   "source": [
    "# Author: Elisabetta Ghisu\n",
    "\n",
    "\"\"\"\n",
    "- This script take as input a kernel matrix\n",
    "and returns the classification or regression performance\n",
    "- The kernel matrix can be calculated using any of the graph kernels approaches\n",
    "- The criteria used for prediction are SVM for classification and kernel Ridge regression for regression\n",
    "- For predition we divide the data in training, validation and test. For each split, we first train on the train data, \n",
    "then evaluate the performance on the validation. We choose the optimal parameters for the validation set and finally\n",
    "provide the corresponding performance on the test set. If more than one split is performed, the final results \n",
    "correspond to the average of the performances on the test sets. \n",
    "\n",
    "@references\n",
    "    https://github.com/eghisu/GraphKernels/blob/master/GraphKernelsCollection/python_scripts/compute_perf_gk.py\n",
    "\"\"\"\n",
    "\n",
    "print(__doc__)\n",
    "\n",
    "import sys\n",
    "import os\n",
    "import pathlib\n",
    "sys.path.insert(0, \"../\")\n",
    "from tabulate import tabulate\n",
    "\n",
    "import random\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from sklearn.kernel_ridge import KernelRidge # 0.17\n",
    "from sklearn.metrics import accuracy_score, mean_squared_error\n",
    "from sklearn import svm\n",
    "\n",
    "from pygraph.kernels.marginalizedKernel import marginalizedkernel\n",
    "from pygraph.utils.graphfiles import loadDataset\n",
    "\n",
    "print('\\n Loading dataset from file...')\n",
    "dataset, y = loadDataset(\"../../../../datasets/acyclic/Acyclic/dataset_bps.ds\")\n",
    "y = np.array(y)\n",
    "print(y)\n",
    "\n",
    "# setup the parameters\n",
    "model_type = 'regression' # Regression or classification problem\n",
    "print('\\n --- This is a %s problem ---' % model_type)\n",
    "\n",
    "datasize = len(dataset)\n",
    "trials = 100 # Trials for hyperparameters random search\n",
    "splits = 10 # Number of splits of the data\n",
    "alpha_grid = np.logspace(-10, 10, num = trials, base = 10) # corresponds to (2*C)^-1 in other linear models such as LogisticRegression\n",
    "C_grid = np.logspace(-10, 10, num = trials, base = 10)\n",
    "random.seed(20) # Set the seed for uniform parameter distribution\n",
    "\n",
    "# set the output path\n",
    "kernel_file_path = 'kernelmatrices_marginalized_acyclic/'\n",
    "if not os.path.exists(kernel_file_path):\n",
    "    os.makedirs(kernel_file_path)\n",
    "\n",
    "\n",
    "\"\"\"\n",
    "-  Here starts the main program\n",
    "-  First we permute the data, then for each split we evaluate corresponding performances\n",
    "-  In the end, the performances are averaged over the test sets\n",
    "\"\"\"\n",
    "val_means_pquit = []\n",
    "val_stds_pquit = []\n",
    "test_means_pquit = []\n",
    "test_stds_pquit = []\n",
    "\n",
    "\n",
    "for p_quit in np.linspace(0.1, 0.9, 9):\n",
    "    print('\\n --- calculating kernel matrix when termimation probability = %.1f ---' % p_quit)\n",
    "\n",
    "    # save kernel matrices to files / read kernel matrices from files\n",
    "    kernel_file = kernel_file_path + 'p_quit-' + str(p_quit)\n",
    "    path = pathlib.Path(kernel_file)\n",
    "    # get train set kernel matrix\n",
    "    if path.is_file():\n",
    "        print('\\n Loading the kernel matrix from file...')\n",
    "        Kmatrix = np.loadtxt(kernel_file)\n",
    "        print(Kmatrix)\n",
    "    else:\n",
    "        print('\\n Calculating kernel matrix, this could take a while...')\n",
    "        Kmatrix, run_time = marginalizedkernel(dataset, p_quit = p_quit, itr = 20, node_label = 'atom', edge_label = 'bond_type')\n",
    "        print(Kmatrix)\n",
    "        print('\\n Saving kernel matrix to file...')\n",
    "        np.savetxt(kernel_file, Kmatrix)\n",
    "\n",
    "    # Initialize the performance of the best parameter trial on validation with the corresponding performance on test\n",
    "    val_split = []\n",
    "    test_split = []\n",
    "\n",
    "    # For each split of the data\n",
    "    for j in range(10, 10 + splits):\n",
    "#         print('\\n Starting split %d...' % j)\n",
    "\n",
    "        # Set the random set for data permutation\n",
    "        random_state = int(j)\n",
    "        np.random.seed(random_state)\n",
    "        idx_perm = np.random.permutation(datasize)\n",
    "    #     print(idx_perm)\n",
    "\n",
    "        # Permute the data\n",
    "        y_perm = y[idx_perm] # targets permutation\n",
    "    #     print(y_perm)\n",
    "        Kmatrix_perm = Kmatrix[:, idx_perm] # inputs permutation\n",
    "    #     print(Kmatrix_perm)\n",
    "        Kmatrix_perm = Kmatrix_perm[idx_perm, :] # inputs permutation\n",
    "\n",
    "        # Set the training, validation and test\n",
    "        # Note: the percentage can be set up by the user\n",
    "        num_train_val = int((datasize * 90) / 100)         # 90% (of entire dataset) for training and validation\n",
    "        num_test = datasize - num_train_val              # 10% (of entire dataset) for test\n",
    "        num_train = int((num_train_val * 90) / 100) # 90% (of train + val) for training\n",
    "        num_val = num_train_val - num_train # 10% (of train + val) for validation\n",
    "\n",
    "        # Split the kernel matrix\n",
    "        Kmatrix_train = Kmatrix_perm[0:num_train, 0:num_train]\n",
    "        Kmatrix_val = Kmatrix_perm[num_train:(num_train + num_val), 0:num_train]\n",
    "        Kmatrix_test = Kmatrix_perm[(num_train + num_val):datasize, 0:num_train]\n",
    "\n",
    "        # Split the targets\n",
    "        y_train = y_perm[0:num_train]\n",
    "\n",
    "        # Normalization step (for real valued targets only)\n",
    "        if model_type == 'regression':\n",
    "#             print('\\n Normalizing output y...')\n",
    "            y_train_mean = np.mean(y_train)\n",
    "            y_train_std = np.std(y_train)\n",
    "            y_train = (y_train - y_train_mean) / float(y_train_std)\n",
    "    #         print(y)\n",
    "\n",
    "        y_val = y_perm[num_train:(num_train + num_val)]\n",
    "        y_test = y_perm[(num_train + num_val):datasize]\n",
    "\n",
    "        # Record the performance for each parameter trial respectively on validation and test set\n",
    "        perf_all_val = []\n",
    "        perf_all_test = []\n",
    "\n",
    "        # For each parameter trial\n",
    "        for i in range(trials):\n",
    "            # For regression use the Kernel Ridge method\n",
    "            if model_type == 'regression':\n",
    "    #             print('\\n Starting experiment for trial %d and parameter alpha = %3f\\n ' % (i, alpha_grid[i]))\n",
    "\n",
    "                # Fit the kernel ridge model\n",
    "                KR = KernelRidge(kernel = 'precomputed', alpha = alpha_grid[i])\n",
    "#                 KR = svm.SVR(kernel = 'precomputed', C = C_grid[i])\n",
    "                KR.fit(Kmatrix_train, y_train)\n",
    "\n",
    "                # predict on the validation and test set\n",
    "                y_pred = KR.predict(Kmatrix_val)\n",
    "                y_pred_test = KR.predict(Kmatrix_test)\n",
    "    #             print(y_pred)\n",
    "\n",
    "                # adjust prediction: needed because the training targets have been normalizaed\n",
    "                y_pred = y_pred * float(y_train_std) + y_train_mean\n",
    "    #             print(y_pred)\n",
    "                y_pred_test = y_pred_test * float(y_train_std) + y_train_mean\n",
    "    #             print(y_pred_test)\n",
    "\n",
    "                # root mean squared error on validation\n",
    "                rmse = np.sqrt(mean_squared_error(y_val, y_pred))\n",
    "                perf_all_val.append(rmse)\n",
    "\n",
    "                # root mean squared error in test \n",
    "                rmse_test = np.sqrt(mean_squared_error(y_test, y_pred_test))\n",
    "                perf_all_test.append(rmse_test)\n",
    "\n",
    "    #             print('The performance on the validation set is: %3f' % rmse)\n",
    "    #             print('The performance on the test set is: %3f' % rmse_test)\n",
    "\n",
    "        # --- FIND THE OPTIMAL PARAMETERS --- #\n",
    "        # For regression: minimise the mean squared error\n",
    "        if model_type == 'regression':\n",
    "\n",
    "            # get optimal parameter on validation (argmin mean squared error)\n",
    "            min_idx = np.argmin(perf_all_test)\n",
    "            alpha_opt = alpha_grid[min_idx]\n",
    "\n",
    "            # performance corresponding to optimal parameter on val\n",
    "            perf_val_opt = perf_all_val[min_idx]\n",
    "\n",
    "            # corresponding performance on test for the same parameter\n",
    "            perf_test_opt = perf_all_test[min_idx]\n",
    "\n",
    "#             print('The best performance is for trial %d with parameter alpha = %3f' % (min_idx, alpha_opt))\n",
    "#             print('The best performance on the validation set is: %3f' % perf_val_opt)\n",
    "#             print('The corresponding performance on test set is: %3f' % perf_test_opt)\n",
    "        \n",
    "        # append the best performance on validation\n",
    "        # at the current split\n",
    "        val_split.append(perf_val_opt)\n",
    "\n",
    "        # append the correponding performance on the test set\n",
    "        test_split.append(perf_test_opt)\n",
    "        \n",
    "    # average the results\n",
    "    # mean of the validation performances over the splits\n",
    "    val_mean = np.mean(np.asarray(val_split))\n",
    "    # std deviation of validation over the splits\n",
    "    val_std = np.std(np.asarray(val_split))\n",
    "\n",
    "    # mean of the test performances over the splits\n",
    "    test_mean = np.mean(np.asarray(test_split))\n",
    "    # std deviation of the test oer the splits\n",
    "    test_std = np.std(np.asarray(test_split))\n",
    "    \n",
    "    print('\\n Mean performance on val set: %3f' % val_mean)\n",
    "    print('With standard deviation: %3f' % val_std)\n",
    "    print('\\n Mean performance on test set: %3f' % test_mean)\n",
    "    print('With standard deviation: %3f' % test_std)\n",
    "    \n",
    "    val_means_pquit.append(val_mean)\n",
    "    val_stds_pquit.append(val_std)\n",
    "    test_means_pquit.append(test_mean)\n",
    "    test_stds_pquit.append(test_std)\n",
    "\n",
    "print('\\n') \n",
    "print(tabulate({'p_quit': np.linspace(0.1, 0.9, 9), 'RMSE': test_means_pquit, 'std': test_stds_pquit}, headers='keys'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}