{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![](\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAACs4AAAG4CAYAAADvvIAoAAAACXBIWXMAAAsTAAALEwEAmpwYAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAHF4SURBVHgB7P1/rNWFne//vsfhfGUc2Eb7lVNww50hyjnsbW5HnFvAtNj7HREGpn98oW7MNJmRCjmd6Q3+IGknufSq5zBJ9cZfJKaeCGKbtBEU/+nVgHiTyjQCvUecM4HNXPU43whCj97a44bpVxNv5rvfa7nGXbr3Zu/1WT8+a63HI/lkA5uy1/qsz1o0+Nyv9TvzFi77lwAAAAAAAAAAAACALndJAAAAAAAAAAAAAEAPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPEM4CAAAAAAAAAAAA0BOEswAAAAAAAAAAAAD0BOEsAAAAAAAAAAAAAD1BOAsAAAAAAAAAAABATxDOAgAAAAAAAAAAANAThLMAAAAAAAAAAAAA9AThLAAAAAAAAAAAAAA9QTgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPQE4SwAAAAAAAAAAAAAPUE4CwAAAAAAAAAAAEBPmBEAAABATxj8d0viD/qviT+Yv6hyXPZ7s2LO5+YGUC7v/fJsvD96/POvz8fwG6/F/3b6rTjx/z0WAAAAAABAcb8zb+GyfwkAAACgK2Us+5Xla+KLX1gRl102O4DO9Otfn4uf/9dD8dPDL4poAQAAAACgAOEsAAAAdJnfv2x2rPmTofiz/2WDWBa6UK7R7v1/7YyfvvpiAAAAAAAA0yOcBQAAgC6y9k82xNCf3SGYhR4goAUAAAAAgOkTzgIAAEAXmPO5ufHXt2+LwUVLAugtGdDe99C34r3RjwAAAAAAwOSEswAAANDhrMwC//zr85X12Rf/33sCAAAAAACY2O/OvqL/vgAAAAA60q1f3RRf/1//Ov7Nv7k0gN71P/2b/ymuH1wW8TsRw2+8HgAAAAAAwPiEswAAANCh/vr2bfFnf7IhAGoGFy2JOf/z3Pj//P2hAAAAAAAAfptwFgAAADpQRrP/1+VrA+BCfzB/kXgWAAAAAAAmIJwFAACADnPrVzdZmgUmlfFs/E7E8BuvBwAAAAAA8BnhLAAAAHSQtX+yIb7+v/51AFzM4KIl8c//+/l4859OBAAAAAAAUHVJAAAAAB1hzufmxtCf3REAUzX0Z5sqrx0AAAAAAECVcBYAAAA6xH1bH4/LLpsdAFP1+5fNir++fVsAAAAAAABVwlkAAADoAF9ZviaushoJ1GFw0ZJY8ycbAgAAAAAAEM4CAABARxj66qYAqNfQn22K37dYDQAAAAAAwlkAAAAoO2uzQFG/f9msWPsnQwEAAAAAAL1OOAsAAAAlZ20WaIQ1/8ttAQAAAAAAvU44CwAAACU2+O+WWJsFGiJXZwcXLQkAAAAAAOhlwlkAAAAosa8sXxMAjfKVG72mAAAAAADQ24SzAAAAUGJf/MKKAGiU/8sXbgoAAAAAAOhlwlkAAAAoqcF/tyQuu2x2ADTK7182KwYXLQkAAAAAAOhVwlkAAAAoqT/ovzYAGu0P5nttAQAAAACgdwlnAQAAoKRycRag0YSzAAAAAAD0MuEsAAAAlNRlvzcrABrt/2TNGgAAAACAHiacBQAAgJK66sq5AdBosy6bHQAAAAAA0KuEswAAAFBSc/5n4SzQeFd9zmsLAAAAAAC9SzgLAAAAAAAAAAAAQE8QzgIAAAAAAAAAAADQE4SzAAAAAAAAAAAAAPSEGQEAAAAAACXW1zc75l89N/oun/Ubvz7y4fk49e7ZGBk5F52s2+8fAAAAAJSJcBYAAAAA6EiDA9fGqptXRDsdPvr66HFsWv+bvr5Zsen2DeN+7sTJt+LAwVei1SY7lzuf3tvycHP50iVx47LrKx8HF19bCUsnc2L4zTj97tnYP3ru8jE5dfpslNl071/en+GTb47et9dG7+Pftfz+Neu5dvrdX1TC4Hz8WnGNbdq4Ifpmz4pGOXfuXLxz+r/HyOjHVt0HAAAAAIr7nXkLl/1LAAAAAKXz7H8+HADNcOt/WB7dYGjdmnjk//ndaKeHHtsZD+/YNa3/zfz+uXHklefH/dzIyPm45at/0fIwcrJzueymdS25PRmPbt44VImKLxaSXkzGzHv3vTB6vBhlUbt/q1auiMHFi6KIVt+/VjzXMjw9cfKN2Pv8i3H4yPRi9Kk6Ovq86x99/jVL7T5k3NyOAB4AAACAqbkkAAAAAAAohVyjfeTBbdFLMijdeucdcfSVfXHPlk2Fo9mUS66PPPjdSqA8tH5NtNOF969oNJvKdP8aJVdth9avjed+9HjH3q/afXjqie/FyddfqjyX5zcx1AUAAACgPsJZAAAAAIASyShy88YN0Qvyvh78yQ8aFsxeKKPFDExfGv0a7QgYu/3+NUvtfmVA26n3Kx/vjGjzPghoAQAAAMpFOAsAAAAAUDIZWnZ7aLd19D4+9+PHo78F93NwYFG89JMfxqqVN0WrZPzc6vvXLeuzNfkcqN6vtdHJagFtLg8DAAAA0H7CWQAAAACAkunrmxW7vv9AdKtc4LynjohwZORcnDp9tnJMV57Tp574Xkvixfu/e1fct+2umK6i9y9XWrstzqzer21dscKcQXyGwNZnAQAAANprRgAAAAAAdJmHd+yqKz6crhMn34hmGRy4Nu7fdmfcu/2x6CYZQU51QfTVI8fipZcPxatHj40+nr+ohKVj9fXNjsHF18Z1o+fqlptXxI3Lllz0z8x4MT302K5ohm6/fxeq97l2ed+suPrqubF86fWj92/RRX9/hsjHT74Zh0fPWaMdHj3/e/e9GNPVf/XnK8/T/tH7MZX7kPL3P/ujx+PWr3+rJa9RAAAAAPw24SwAAAAA0HUyRGxGYNdqmzbeFvtf/ruuuC8pl1gvFpVmPPrk7r2x8+k9vxWSjvd7M3rM48ndeypLnvdsueOiXyPj0gxV9+57IRpp6+ifW5b7NzJyvvK/abZGPNfyfi1fumT0/N0R/ZOssT7ywLa45at/edHzNl0ZsBa9FjJyXr1yRdy6bs1FA+e8v+JZAAAAgPa5JAAAAAAAKK2MBTPK63QZlW66fcOkvydDz6U3rY+Hd+ysK47MCPHub2+PZTeti9MXCRLv33ZXJWBslM0bN8Q9d94x6e85cPCVlt2/XGgdXDy1FdR2q4WrX/v6tyYNWPPx2rRxKMooH8+87RnD5uNzsRC3Fs92w3MbAAAAoNMIZwEAAAAASiwDu61bvhGdrLKUOklUmtFhBqH3bX+0IWuiGWIuvWldPPTYrgl/T1/frHjkwW3RCLUl2Mnc+58ejW98829adv/Srie+11FhZi0Mnux+bb79ttLfp9r9yGOywDmvm6dGHyMAAAAAWks4CwAAAABQcps23hbLL/L272X23I8en/BzGZJebGm0XrnsOlmEuXzpkhhavyaKuligmgHlzqf3RKNd7P51anSd9+vwkWPjfi6D56F1xR+zVqit6J44+caEvyevwVwrBgAAAKB1hLMAAAAAAB3gqe8/0JFv655han//3Ak/f9e3/zZODL8ZzZIR5pO7J45W79myKYrI+ze4eNGEn8+l2WZEwTUXi2c7Nbq++zvbJ/zc6ltWRKfI9dmv/fnk8Wxeg5343AYAAADoVMJZAAAAAICSyMBzsqXNRx/cFp1m6yRh6kM7dsaBg69Es2Vcevr02XE/l6usRcLSi92/ZizNXmiyhda0dcsd0WkyOJ3oPuVKayeFpiMj5yvx7ETXYD63O3EZGAAAAKBTCWcBAAAAAEpiZORcZWkzP45n1coVHfW27pOtzWYY+fAkS6mNlOHiXd+eeMG03rC0LPcvTXbdZGjaiauz+18+NOHnBgeujU5ysWswl4GtzgIAAAC0hnAWAAAAAKBEMricLLDLt3WfP0GsWTaTrbHe+vVvRSsdPnqs4Qumk92/DFlbKa+bJ3fvnfDzq25eEZ3mwMGJw9n5V38+Ok1eg7kqPZFNG4cCAAAAgOYTzgIAAAAAlEwGgxMFdvm27o88uC3KLmPUidZY9+57oRJ6tlp+3YmsXvnlmI7BgUWT3r+JIt1m2vn0MxOuzm5Yv7bjFk0nu0b6r+6MePxCD+/YOeFjtPn22wIAAACA5hPOAgAAAHSoGTMi5syLmL+welw5p/prQHfIwO70BOFgRqmbN26IMhtav2bCzz28Y1e0w/6XJ14wHVi8KKbj1nUT37+9z78Y7TAycn7C1dkMrqcbB9N4F3uMli9bEgAAAAA0l/+UAgAAANBhLp1ZDWbnLhg/lH3vTMSptyM+/iiADpaB3V3f3h7P/fjxcT9/37a74tUjr8eJk29EGd24dPwA8NWjx9qyNpvynN67/dHomz3rtz53+t1fxHQsX3r9uL+e960da7M1uTq7eePQuOuyq1feFHv3tSfq5TPPPv9CbL3zjnE/t+rmFW29fgAAAAB6gXAWAAAAoEP0XRExZ241mp1Mfj4PAS10vsNHj8WTu/dMuC6764nvxS1f/csJ3/q9XQYHFkV//9xxP/dsm8PNnaPns6j5o/ftuoFFTfvzi8g4+MTwm+Muly5fas20DGpx9XiP0eqVK+K+7Y8GAAAAAM1zSQAAAABQahnMXndD9bhYNDtW/t4bvhTx779Q/TOAzvTwjp0TrspmwLl1yzeibCZaY00ZA3e6gcXXTvi5Iz9/Pdpt/8uHxv31vr5ZlWumU0x2WzMQ7mSvHh3/Osn7PN5aMAAAAACNI5wFAAAAKKmxwWyR8PXKq+oLb4FyyEDw7m9vn/DzmzbeNu5yZTsNThCW5tJmHp1uouXWfKyOD78R7Xbg4KEJPzdZ1Fw2kwXKp9/t7OtosoD8xg56jAAAAAA6kXAWAAAAoGQybv2jpcWD2Qvln3XNQHWFVkALneXE8Jtx7/bHJvz8Iw9sK9VK5fyrx18KHT75ZnSD6yYIOo+fbH80mzJOHhk5N+7nBhYvik6xeuWKCT93osOvpROTXCv9V3fOKjAAAABAJxLOAgAAAJTAjBkR8xdGfPEr1bj1sib2b5fO/M2ANr82UH47dz8Th4+Mv1KZb+++dcs3oiwGByYIS0uwxtoIs/tmjfvrGTiXxTsTLPtePsFtL5u8pm+cYNm3G5aLc5349AT3YaLnDwAAAACNIZwFAAAAaKNaMLvkS9WPrYxYawHtF5ZVv3b+HCi3u7+zfcIl0U0bb4tVK2+KMpho/fb0u50dO9ZcNzD+auvpEsWcE637Di7ujChzaN3a6O8ff3n18NFj0Q2OT/AYXV6i9WgAAACAbmRPBAAAAKANMlLNtde5C9q/+Jq3JcPZPN47E3Hq7YiPPwroaK2IAydaf22mXNl8aMdTcf+2O8f9/KMPbotbvvpGW9c45/dP/Dbzp979RXS6vkkWW0fOnYuy+HDk/Li/3tcBUebQ+rVxz513TPj5h3fsim4wUQTff/XnAwAAAIDmEc4CAAAAtFDfFRFz5laj2TLK25WHgJZOd/+2u6KZMkxddtO6aIedu5+JG5f+0bjrshl1PvLgtvjan38r2qUTwswiJlsDLVMYPFGUWfY1080bN8R9kzx/9+57oa1heCN1ctwMAAAA0MkuCQAAAACaLoPZ626oHmWNZsfK23jDlyL+/Reqtx0ol7u+vT1OTxAPLl+6pBIftkvf7IkXWc9NEArSeBNdH5Mt5rZLhqKrVq6Il37yw0mj2dQta7NporgZAAAAgOayOAsAAADQRBmdLljYufHplVdVj5FfRbx3trpEC7TfyMj5Sjz73I8fH/fz92zZFPsPHirdMueHQsGuM7j42piu+VfPrXwcGP3fXjdwbeXPmMrK6kM7dnbN2iwAAAAA7SOcBQAAAGiCXGydNz/isi55t+UMf/OYvzDi1NsCWiiDw0ePxZO794y7Lpuroo88uC2+9uffCmim+y+yENsoea0//Fj3rM0CAAAA0D6XBAAAAAANMWNGNSz94lcirhnonmh2rEtnVu/bDV+qxsEzfFs2tNXDO3bG6QkWOJcvXRL33HlHtNrIufMTfu7yvi58YSypvsu751xnNHvf9kcDAAAAABrBf9oAAAAAKCjj0bkLqkevhKS1gPbjhdX12Tw+/iigNPa/dChGzp2LZvlwpHl/9nSMjJyPu769PZ778ePjfn7rlk1x+OjrcfjIsWiVkUnOzey+WdHN5l/9+Tgc5dA3e/xzfWqC0LqM8lp66LFdsfPpPdGN5vfPHffXT73bOY8RAAAAQCcSzgIAAADUKePRXF1tZzA78quId96OmPl7o7dlbkTfFdFSeQ5yZXf+pwHtqbcFtJTDzh/saWks2k6Hjx6rLHJu3rhh3M8/8sC2uOWrfzlp0NpIk0XFZQpL69Up4WnfBOu+IyWJvi9m774X4t7tj3XM7a3H/KvnBgAAAACtd0kAAAAAMC0Zp+ba6g1fqgaj7YhmM5g9/lr1yB9ntFr7ef64HTIiznOS5yaDWqB18m3sT5x8Y9zP5arl1i3fiFbJFdyJ9M2eHd3g9ATx7MDiRVEW1y2+dtxf//Dc+SizAwdficXX3xJ3f3t7V0ezaaIF5tMdtAoMAAAA0IkszgIAAABMUQazCxa2ftV1rIxi3ztbjWXHk7+eRy6/ZtSbMWur5dfM44P3I868M/FtBRrrjm/+Tbz0kx+MuzS6aeNtsf/lv2vZCm+Gf/3jvA394MC10Q3+x8i56I/fvn+XTxBCtsNEUeaJ4TejkY4PvzFpLH2hkXPn4vLZs2P5siXjfr5M8XGzXTcw/n3tlFVjAAAAgE4lnAUAAAC4iHYHs598EnH2neqRP56Kjz+KeGu4vQHtlVdVj8oi7tn2LeFCr8jY7qEdT8X92+4c9/OPPLAtbvnqX7ZkxfP4yTfHD2cXd0c4Ozx6/8aLHpcvXRJl0Nc3a8Ios9Frpvf97WPTDrLz9h195flxI+9cSN60cSgefmxXdLPBgYkD4by+AAAAAGieSwIAAACAcWVset0N1aMd0WxGshm+HvtZ9eNUo9mxagHta5/+GR99FC2X5+6agYgbvtSegBd6yc7dz0wYMWaQ+OiD26IVJlrMzFhwvFiy05yYIGzMc1yG+zc4yWrriX9sf5SZC7VP7t474ec3335bV1wnkxlcfM2Enzv97i8CAAAAgOYRzgIAAACMMWNGdaH1i1+pxp6dGsxeKAPa2p+ZIW07AtpLZwpooRXu/s72CVdlV61cEZs3bohmO3Dw0ISfGxzo/NXZE8MTx6erV3452i0f54lMdttbaefTz0x4neYiba7OdrNVK28a99czKj4+/EYAAAAA0DzCWQAAAID4LJhd8qXqx/x5q438qhq1/vynjQtmx/PemfIEtHmu8+dA4+Ta673bH5vw8/ds2VRZRm2mEycnDv9W3bwiOt3ho8cmjD6H1q+NdvvTCcLZE8NvTHi7Wy0D0Yd2PDXh53N1ttnXabvk/Vo9wWOU1xYAAAAAzSWcBQAAAHpaWYLZ469Vj4xaW2VsQJu3odUymM1zngFthrQCWmicvfteiAMHXxn3c7nm+ciD26KZMoo8fGT8AHDD+rWjt2F2tMvJ11+Kd//b4d86nnrigWn9ORMttw4uXtTW+7d86ZLonyA4ffXo61EmO3c/E6dPnx33c3md3rPljuhGy5deP+Hn9k+y1gwAAABAYwhnAQAAgJ7Ud0U11vziV8oRzLYjXK3JgLYd4e5Yc+YJaKHR7vr29gmjxIwrN2/cEM20/+XxA8AMIjdtHIp2yPs9UdT66pHpLX1mnDyedt6/NLR+zYSfe+75F6Ns8jqdSK73Ll+2JLrN1i2bJvycxVkAAACA5hPOAgAAAD0lg9nrbqgeGWu2w9hQtZ3B7IXytuT67Gs/K0dAm48VUL9cfZ0sSrxny6bKW8Y3S4alIyPnxv3c5ttva8sq62RR6ZGfT2+NNcPgst2/fDwzNh3PieE34vjoUTYZih6eJFre2mWrs3kNTrQInM+ZUxPE7gAAAAA0jnAWAAAA6Aljg9l2B5mXXxkx8/fKuayay7sZr145J9oqb0O7A2foBhklPrl7z7ify2XUXd9/IJolw91Xj74+4ddu9SprRqU3Lh1/vTRjxelGpXn/9uwbf8E179/WLd+IVtv1xPcm/NzOp/dGWT20Y9eEn8uV4G5Znc1rcLK12b0lXAQGAAAA6EbCWQAAAKCrjQ0wy7JgmsFsLqrWllXLENDmufnDRRFLRm/T/IXVgLYM8nbVzpWAFurz8I6dcXqCFcvBgWvj/m13RrPsnCDaTbnK2szF2wvds+WOCZc+9x88FPXY9fTE92/TxttaGnxu3rghBhcvGvdzGQbnmmlZXWx19v7/+13RDfK5NtE1+OpFzgEAAAAAjSOcBQAAALpORp8Zf37xK9XosizB7HgyBs0otF3LqmOXeOcuKE8we6GxsbGAFqYnl1G/8VffmfDzGXjm0QyTBZG5yvrsjx4f/Tg7mi1XS4fWr53w85MFsJPJIPXJSeLgRx7Y1pI4OL9GhsETeXiSRdeymGx1NgPvofVropPl0uyqlTdN+Pl7vr09AAAAAGgN4SwAAADQNWrBbNlWU6fiwmXVZq7Qjg2Ly7TEOxVjA9q8D2VY64VOcGL4zXjoscnDxGa5+zvbY2Tk3Lify+DzuR89Hs2UX+PRB7dN+PlcYj01wSLvVOSi72T3b9f3H2hqHFw7hxN9jbKvzdZkZD3Z7bx/290tiaybIaPZe+6cOGwueg0CAAAAMD3CWQAAAKDjdXIwe6GxYWh+vKyBjVAGsn+4qHvOU96H2nkS0MLFZeDZjreCzyDwoR1PTfj5jHZf+skPmxJF1qLS/glWX/O2FV1jzUXfi92/vA3NWJ692P1Ld3fQkmk+FhNFyLlQvGnjUHSSvKafeuJ7k0azjbgGAQAAAJge4SwAAADQsWorrbmc2ukh6HhyefaPllZXYfPH9bryquqfkcfcBd15ngS0MDWTrb82087dz0wa7Vbj2R80NC5dtXJF5c+cLCrduXtPQ5Y+p3L/nm1wPLt544aL3r+HMpY+2vpYul75WDy5e++En998+20dszo7tH5NHH1l3+h1eNOkv+/Wr3/L2iwAAABAiwlnAQAAgI6TwWwtBC0SlHaKWiB8w6dLsVOJQ2srvBkV//svVP+Mbjc2oO2F+wv1uNj6azNltHt6kkAwo9Ijrzwfjzy4rVBgmv/bXPl86okHJo0s9+57IXY+vSca5Rt/9Z2W3L/lS5fEcz9+PO7bdtek9+/E8Jvx8GOdt2S68+lnJl2d3brlG1FW+Xhs3jhUeXweefC7F418cw1YNAsAAADQel22LwIAAAB0s4whFyxsXxT5ySfVY2abVk0zmM0YNo/3zoweZyNGfvWbvyfPzbz5EVfOibbLc9WOddsMaPPIc5PnKM8V8JlcR11985dj+bIl0UoZCGZc+tyPHp80KBxav7ZyZNi69/kXJ11yrck/b3DxtbH1zjsqYelUbsu92x+LRhoZOR9f+/q3KvdvshXYeu9f3q+MMqd6/+4YPdedKM9jrs7mYzmeTRtvi51P7y1FcJoB9MDiRbGg/99WlmXzGpzqIm5Gs3kNAAAAANB6wlkAAACg9Coh5Nz2BrNn36ke+eO8PRmnXtbGd4uuxaG/Ph9xZvR2/e7ov/J87qpyLK3WgtUP3qverrydV81rfXCc5yKPDI1PvS2g7TVPff97lQCvFZbetC46Ta6/vvSTH7T8be9zBbUWl17sa9cC01wfPXHyzTg++r/NH587V10jnT17diVcHFy8KAYHro2pyuDy1tHbMNGqaRH5Z08lnk3Nvn+dvGSaq7MZCU90jeRq79f+/FvRKKtXrogbX3l+Wv+b/jpXg/Mx/sY3/yYOH714MA0AAABAcwhnAQAAgFLKpdK5C6rHjDb9C8aFwWxNZe31TDXKzKA3w9B2uWxWxDUDUQofvF+NeMeu4OZ5y2g1z2Gu4PYvbH1Am0u9eY4EtL0lg7tWR6GdJKPKu769PZ564oFotYxnb/nqX04pLk21tdWpLK1O5WvnEmszo9LpxLOpkffv1SPHRu/f3zQlCm6ljN4f2vFU3L/tznE/Xzlfy5ZMaa13Klr1epGPzz3f2d7RUTMAAABAN7gkAAAAAEokI9kMHJd8qfqxHdFsrri+NRzx859WQ8ux0exYGYjm73vtZxH/9EbERx9Fz6mFsXmu/vG//mY0e+Hvy2D12M+q56wd56oW0N7w6bV1aYsDXiibAwcPxZO790Q71OLSVr5Vfd7XW776Fy2JFtt1/5q1pNsOO3c/E6cneay2brkjOkU+Jvf+p0c7fgkYAAAAoFtYnAUAAABKoQwLsxl9vvP2xPHnRD7+6LNl2lyfzRXaXKPtZnmOzpyK+OC9mLbaYm+7zlUGsxnO5pG3I8Pfj3sweob08I6d8acrV9T9tvNFZEB497e3x+Gjr1ciyGbdhlyZvXf7o6NfpzHrpFPVqvuXK6YP79jV8vvXCrmK/NyPHx/3c41enW2GDGaf3L03dj69p2uCZgAAAIBuIJwFAAAA2iqjyYwnM6Jsl3qD2fHUotDLZkXMW9De+9VouRr7/uh9++X7jT1XeQ3Mmx9x5ZxouUq8O09AS+8aGTk/aZzYCrnKmtHnrevWxob1axoWmGZQ+uzzL7Z09XU8+fXzGFq/tqEBbVnuXzPldZFhbAay43nkgW2x7KZ1USYZyO4/eGj0cXkxTpx8UzALAAAAUELCWQAAAKAtMpZcsLC9y6yVcPNsYyLQC/36fMRbw9UY8/IrI/pH7+vMmdGRMpitLermjxstz38etSXYdsTGYwPaZl0TUFYZJz65e09s3rgh2iXXWXP9No8MTFet/HLcuHRJ9PXNnvafk9HigdGjbAustYB21coVsfrTY7r3LyPMPfteLOX9a5aHduyK5yYIZ+f3z61ct3n9tlpea+nEyTdGf/yLePfds/Hq6GOSC8cAAAAAlNvvzFu47F8CAAAAKJ1n//Ph6EbtDmZrEWgGkq1eF63EmXPbGwtPRyOXeKejnQFtTd7nDGjzOulGt/6H5QGdYHDg2hhcvCj6r/58JZLsv/qztdaRc+cqi7kZMJ5+9xeVkLQWM3aKvH95nwYXX9uV9w8AAAAAykg4CwAAACXVbeFsxpDXDrY/mG3Waup0lCEMnUiem/fPRPzy/favruZ5ynN01bz2rfVmXH38v7Q+sm424SwAAAAAAL1qRgAAAAA0WQaQX1g2+g8RbfiXiDIFszUZYb41HHHq7YjLr4zoX9i+MLSmrOcpz1HepivntOc81a7d469F/PpcAAAAAAAAHU44CwAAADTd4B+3Ppr99fmIM+9EvHcmSivD0Lx9eVx5VcS8Ba1f5M1V2Xfebv+67GQy5K2dp1ygbXVAm9fu4i9E/Ncj5YmKAQAAAACA+ghnAQAAgKbK0LGVkWMnhKDj+eD96pELp/MXVhdWmxUbZ/z5/pmI/36281ZUxwa0c+a2LjTOx2XuguoCLgAAAAAA0LmEswAAAEBTZdzYCp0azF4oV2jfGh79R5s3qvFsI9dVc4X3v5+pRrOdvpxaC2gznJ03v3qumq3Va8AAAAAAAEDjCWcBAACApmp2bFgJKM92fjB7oQxbGxWHdktUPJ68T3nUlnpzibZZfn92AAAAAAAAHU44CwAAAHS0y6+MGPkfEb8+1/krqhO5MA7tu/LiK7R5Ls6+Uz269bzUzJhRjYpnNTlsneFf0gAAAAAAoOP5534AAACgo2VMes1AxMcLIz78IOLU26M//ii6Ut6vt4arP85l1VyhveyCWDQD21++H/H+me4PZvOxz/Mwd4GoFQAAAAAAmBr/SQEAAADoCrWIMo+MR8+civjgveha752pHnm/L/296q99/L93bzQ8Vt8VEQsWVj8CAAAAAABMh3AWAAAA6DoZVOaREWku0OYSbTev0PZCLJuLsrkse9W8iJkzAwAAAAAAoC7CWQAAAKBr5RrrNQMRn3xSXZ/NiLYXItNukgH0566qBrMz/EsWAAAAAABQkP/cAAAAAHS9DC7nzKseI7+KeO/s6HEmKLEMZhcsrH4EAAAAAABoFOEsAAAA0FMyxMxj/sLqAu2HH1ihLYsMnOcuqB7WZQEAAAAAgGbwnyAAAACAnnTpzIhrBqo/zvXZjGgFtO2RIfPnroq4ap5gFgAAAAAAaC7/KQIAAADoeXPmVY+RX0W8d7Ya0tJ8GcwuWFj9CAAAAAAA0ArCWQAAAIBPZcCZx/yFEWfeifjgPSu0jZaLsnMXVA/rsgAAAAAAQKv5zxMAAABAKX30UcTMmdEWl45+3T9cVD1yffbMqYhfnwsKyCB5ztyIK+e0P5j95JPqR+EuAAAAAAD0Hv95AAAAACidXHk99rOIOfMi+he2L6BNeRvy+PX56gpthrRMTYapGcpmMJvhbLuN/Cril+9HvD/6GP6flwlnAQAAAACgF/nPAwAAAEBpZaSaR22tNAPWdrlsVsQ1AxHzF0Z88F41os3Al9+WQercBdWjDHHqB+9XH68MZwEAAAAAgN4mnAUAAABKL4PHPE69HTFvQcQVc9q3QnvpzM+i0ErYe1aQWZOB87z51ZXZdvvkk4iz71SP/DEAAAAAAEASzgIAAAAdIxde/+mN6pHrs7lCm7Fmu1Ruw7zq7cqoN0PaXpOLsleNnoPPXdXex6ImI+aMmXMVWDALAAAAAABcSDgLAAAAdKTK2uvocdms6gptBqztkiu01wxEzF8Y8eEH1Yg2Y9pulsFsbXl3Rpv/hSkD2Qxlrf8CAAAAAAAXI5wFAAAAOtqvz0e8NVyNVa+cUw05Z86MtsiAtrZCWwl7uzDkzFXZBQvLsS6bwezZd6qHdVkAAAAAAGAqhLMAAABAV8iF11pEWYlX57Y37qwFtHm7MurNRdROjTtzUfaq0fvyuavKEcxmjPzO29ZlAQAAAACA6RPOAgAAAF2nsvZ6proAO39hNWBtl7wN1wxEfDx6Oz78oBrRZkzbCWoLurniO6PN/4qU0fH7o4/pL98XzAIAAAAAAPUTzgIAAABdKwPVt4arserlV0b0L4yYOTPaohah5vHB+xFn3ilvAJqrsgsWlmNdNoPZ2pJwpy72AgAAAAAA5SGcBQAAALpeBrS1FdpKvDq3vVHolVdVj7xdGfXmEm27V2hzUTaXZa+a1764eKyMit9527osAAAAAADQWMJZAAAAoKfUAtpcgJ2/MOLKOdVotB3yNlwzUF1S/eC9akTb6oD2slkR/3ZeNZid0eZ/Kcrz8P7oY/PL9wWzAAAAAABAcwhnAQAAgJ6UgepbwxGXvh1x+ZUR/Qvbt7SawWplCXdeNRh972w17m2mXNxdsLC9y7s1tUXgs+9U41kAAAAAAIBmEc4CAAAAPa0WbeZx5VURc+ZWV2jbJUPWPHINNxdoP/ygcSu0GejOXVA92r0umzISfudt67IAAAAAAEDrCGcBAAAAPvXB+9Xj0pnVcLXvyvat0OZtuGag+uOMejOirTegzRD3c1dFXDWv/cFsLsrmsmzep0YFwdBphtavia1bNkURd31nexw+ciwAAAAAAJge4SwAAADABTLofGu4Gpnm+mz/wvYFtGnOvOqRy6zvna1Gp1ORweyChdWP7fbr8xH/ffR2v3+mGs9CL8totr9/bhSxfOn1wlkAAAAAgDoIZwEAAAAmkIFnRqp5ZHw6Z241YG2XvA155BpuLtB++MFvr7Zm7Dt3QfVo97psytj3nberH4EMXpcUjmbT5ttvi4cf2xUAAAAAAEyPcBYAAABgCjL8zCOD1QxX+65s3wrtpaNf95qB6o8z6j1zqhrJZtibC7ntDmYzOD77TvWwLgu/aWj9mmiEvr5ZsXzZEquzAAAAAADTJJwFAAAAmIZceH1ruPrjXJ/tX9i+gLZ2G9q5gjtWhsW/fD/i/TOCWZjIjUuXRKNsvn2DcBYAAAAAYJqEswAAAAB1yrXXPPquqK69liVgbbUMZt95u/oRmNiqlSuiv39uNMrypUuir292jIycCwAAAAAApuaSAAAAAKCQDEZzhfa1n0WcfSfio4+i6+Wi7Km3I37+04jjr4lmYSqG1q+NRurrmxVD69YEAAAAAABTJ5wFAAAAaJCPP4r4pzcijv2sGtL+ugtHIGuRcN7HDGczoAUubn7/3Fi9ckU02upbGv9nAgAAAAB0sxkBAAAAQMO9d6Z69F0RMWfu6DEvOlbGsR+8N3p/zlqWhXotX3p9NMPypUuir292jIx0YakPAAAAANAEwlkAAACAJsrQNI9cZ71yTsTcBREzZ0ZHyGD27DvVw7IsFDO0bm00y6aNQ/HwY7sCoBf09c2Kp554IOoxMnI+vvHN7wQAAADQ24SzAAAAAC3w8UefRai5PpsrtLlGW0YZ+p45VV2ZBYqb3z83li9bEs2SUa5wFugVl/fNrqxt1+PU6bMBAAAAIJwFAAAAaLH3zlSPS2dGzF9YDWnbLRdl3x+9Tb98vxrOAo1zx+0boplqYe7hI8cCAAAAAIDJCWcBAAAA2iRXaN8ajjj1dsTlV0b0L4yYOTNaKoPZ2hJu/hhovD9duSKabdXNK4SzAAAAAABTcEkAAAAA0FYZ0OYC7bGfVUPaViy+5tc4/lrEz39aDXdFs9Ac+Xbi/f1zo9k2rF8bfX2zAwAAAACAyVmcBQAAACiRDGjzuHRmxPyFEXPmRcNkHPv+6J/9y/dbE+cCEUPr10Qr9PXNisGBa63OAgAAAABchHAWAAAAoIRyhTbXZ3MN9vIrI/oXRsycGXWpLdqefceyLLTa6pUrolW2brkjviacBQAAAACY1CUBAAAAQGnVotdjP4v46KOYtvzfv/azaoArmoXWyrXZvr7Z0SrLly5p6dcDAAAAAOhEwlkAAAAAgCYYWrc2Wm1o3ZoAAAAAAGBiwlkAAAAAgAab3z83li9bEq22+pYVAQAAAADAxISzAAAAAAANtnzp9dEOy5cuiesGFgUAAAAAAOMTzgIAAAAANNjWLZuiXseH34jTp89GvW5Z+eUAAAAAAGB8wlkAAAAAgAYaHFgU/f1zo16b/upv4smn90S9Nt9+WwAAAAAAMD7hLAAAAABAA226fSjq9erRY3Hq9NnYu++FGBk5F/Xo65sVy5ctCQAAAAAAfptwFgAAAACggW5cWn+0+uy+FysfR0bOx4nhN6Neq25eEQAAAAAA/DbhLAAAAABAg6xauSL6++dGvfYfPPSvP35ox66o14b1a6Ovb3YAAAAAAPCbhLMAAAAAAA2yemX9S68HDh6KkZFz//rzEyff+I2fT0df36zR2/LlAAAAAADgNwlnAQAAAAAaIGPVofVro157973wGz8fGTkfe/a9GPUqclsAAAAAALqVcBYAAAAAoAGKrM2eOn029h889Fu/fmCcX5uq5UuXRF/f7AAAAAAA4DPCWQAAAACABhhaV//C6+Gjxyb89ZGRc1GvTRuHAgAAAACAzwhnAQAAAAAKmt8/N5YvWxL12vv8ixN+bs++F6NeNy6t/zYBAAAAAHQj4SwAAABQOpfOjLjuhog58wIaqu+K6rU1c2ZAQ91aYG321OmzcfjIsQk/f+DgoajX8qVLCgW9AAAAAADdZkYAAAAAlFAGjnnMXxhx6u2I984E1C0j7Dlzq9cUNMOG9WuiXoePHrvo508MvxGDA4uiHqtuXjFpmNtr+vpmx+V9s6K/f27Mv3pu5dcu7/v9mD17duXH586diw9H/nn0OB8joz8+ffpsJW6mmDzveb7zvOf5T/1Xf/5fP3/heT8x/GaMjJwL6pMr2H2j1/RE5/v0u7+ofDz17tkY+fB89aPz3ZEu9lhf+NzyeAMAAIBwFgAAACi5XJ+9ZuCzgPbDDyI+/ijgomaM/svX3AXVY4Z/BaOJctU1g6V67Xp670V/z/6Df1d3OLth/dq4b/uj0Ysy1hxcfG2sWrkiFow+Rvnjeh+rDDlPv3t29LF4JQ4ffb2hMe38Om9TJYQrYfyW9yefFwOj5/vG0Y/z+z9feSymK+/bqdO/iBMn34jh0ePVI39f+XGZlOGxy3O7evQaL3q+85rOa/zVI8fi8M9fb3pwX++567+6/tfbIl93Mq2I62uvZ9cNXDP6/Lqh0OtZyuvvxMk34/joa1s+v04Mv1W65xcAAAA0y+/MW7jsXwIAAAAonWf/8+HoBjfeHA2V0WzGsxnR9lpAu+RLETNnTut/UjlHr/0sekozg9lXX46ucOt/WB40ziMPbouh9WujHhlbLbtp3UV/X1/frDj5+sGo19e+/q2eWZ3NuGzD+j+NVStvqoRl9QSEU5Eh7c6nn2lIRPvuf6vv7/yHHtsZD+/YFWWQoWwGyn86evQ3IUysydgvz3kGzBmUtzMczgDzyCvPRz2KPnZ5XW/eOFQ573k0Q+1c79n3YhwYPd+NVu91XzZTfR2vR15jQ+vXNPVxHivvS66c733+RUvlAAAAdDVbGwAAAEBHyQXaOfOqx3tnejOgZXx5bcxbEHHVPAuztNaNBWKmnbv3TOn3jYycr0RMy5fV97W2brkjvtblEVRGZVvvvKMlcVkaHLg2Hnnwu5W4cOfTe2LvvhdbsjpZJnkOcul00+0bmhYoXyi/Tga6eTwy+vMDBw9VIto8/70gr+8MKeuN9adj7LmuBZUZ+/badd5qY+P/Vr2e1WSoO79/beX6ysc5n1/5+uYxBwAAoNv4TwgAAABAxxob0L43+t/zR34V9KC+KyIWLKx+hFbLgK3IuuaBlw9N+ffuH/299Yazg4sXVWKsdq5zNkurg9kL5Xm9Z8umuHXd2nh4x86eCDjbfc7HqoWd+Rjk+W/EAnAZ5XV2/7Y7WxLMjmdsULl33wsC2iaorQi3MkSfTD7mmzZuqBwecwAAALrNJQEAAADQ4TKeve6G6pE/pjdkKFt73EWztEsuAtbr1aPHphUhZbhUr76+WTG0bk10k4w2n/vx45WjDAFnRma5QJu3Z36BmLrMcmG2TOd8rNr5f/ZHj1eC9m6yeeOGOPrKvrZFsxfK29GN57ldMpLNED0f4wzAyxDNXqj2mOftBAAAgG4gnAUAAAC6RsaT1wxE3PAlAW23mjGj+tj+0VLBLO2XoV6+TX29np3mMunIyPk4fORY1Gv1LfXf1jKpLG9+965Sxpspb1O3RYW1c/7ST35YynM+Vi2gPfLK8x3/GOR5f+TBbXHftrtKF1PWzvNTTzzQtaF4K9Si6LIGs2Pl45y3M59bHnMAAAA6nXAWAAAA6DqXzvwsoJ27oPpzOlsGs/MXRiz5UvWxvazcbQk9YvnS66OIw0enH8EWWZ3N4LHTY6e8DxmZ5VuZl1ktKuyGdcY85wd/8oPSn/ML1R6DDE/LHiSOJ29/nveyrMxOZNXKFZVQfHDxomDq8vHN+L+MUfTF5G3Px7zI4joAAAC0m3AWAAAA6FoZzP7hoogvLKvGlgLazjM2mM2P+XMoizsKhIQHDh6KU6fPxnTtf/lQjIyci3rd2sELnLWV2U6KzHKdsZPj2do57+/g4DrD05d+8oOOisYrUeWPOue81yJQIeXUZIye12TZ15snk4/5U098ryu+OQAAAIDeJJwFAAAAul7GlnPmVRdoBbSdoe+K6mP1xa8IZimnjIauG6h/YXH/wUNRj5GR83X/b9Pm22+LTpOhbEZ5nbZ4WtOJ8Wxe3y/95Icde84vlPcn315+88by359Oi2Zr+vpmVULKsi/ktlteg532DQCT6fRvDgAAAKB3CWcBAACAnlILaK+7oRpnUi75mORjk0c+VlBW92ypPxTK+HXvvheiXnv3vRj1yrht+bLOWTmsvV19Jy8zpozLOiHaTLVwc3Dg2ug29227q9SRX6dGs2PdP3qOBxfX/00F3Wzr6OtAXoPdRjwLAABAJxLOAgAAAD2pFmhmRCvQbL+xwaygmU5wY4GQc//BV6KIw0ePxcjIuajXqptXRCfohohwrIzLyh4UZiybbyHfLed8PPk43L/tziijXd9/oOPPfcb5u574XuX5y2cymr2ni+PSTvrmAAAAAEjCWQAAAKCnXToz4pqB6jFjRtBiec7/cJFgls6S66dF4ra9z9e/GFuzp8Dq7Ib1a0v/NuHdFs2mWlBY1nOf0Wye8255C/nJbNp4Wzzy4LYokwwru2XlN5+/ZTu/7dTt0WxNrul20qI5AAAAvc1/DgIAAACI6urs5VdGHP8vER9/FLRARsuDfxwxc2ZARxlavybqder02Th85FgUdeDgobrX/TLgvHHp9bF/9M8oo26MZmvyvuXa6d3f3h5l0kvRbM3Q+rWV5eZ7tz8W7Zbnv9vCyvwGg7xPDz+2K3pZqx7bvJbfGf375fS7Z0d/fP63Pp+v+32zZ8d1o7enmc/zp77/QNzy1b+o/F0HAAAAZSacBQAAAErnk08iTr0dMXdBa6PKDDmv+2PxbCu0K5rNa+vsOxFXzRPsUp+Mj1avXBH1Ony0eDRb+3NOnz5bd1y6aeOG0oazrXi7+krAPHoOh0++GR+OnK/8PIOzC/VfPbfymC8YvT3Lll5f+fl1A4uiiAw28+s+uXtPlEHGvBm7NTOmy6jv1dHzfWL4zdHz/ItJz3fKuG9gcfUoer4nk8uzI+fOx0Ntjjvz/BdxfPiN0ev59Xh39JxOFE+ODSevHj3Py0ev52ae25RLq8/ue3HCiHLvvheiHtXX4ZuiHnle9h98JRrpw9Hrezy151Yz5DnN1/Da69h0QtV8rufjn3+X3VhwQf23/+xZlbXhr/35twIAAADKTDgLAAAAlM7//9O4MY9cgu1f2LrIMYPOawYjTrwWNNEfLGptuJoh9HtnqtdUxrMZzkI9MjQqEhjuff7FaJQ9+16MrXUuGeYaZN6PkQmCr3a5/7t3Ne3t6l89cixeevlQ5bxN9X6PjdFqoWvGcHn+bl23Jm6s823J79myqRK9tXuVsZnrvnm+M+Y88PIrlWB2KmrnY2xgntdpPu9Wrfxy3bHkZPKxeHX0djZiCboeuWBdz/nP8/vs6OtJXkfTeR6PPbeNuJYvZrKIst7l5bzd9V4LGbm2avH5ni13NPS5lY9zvn4d+DSYLfLn5J9x4NNvnqisA4/e1kZdA/nn5SJ6Wb45AAAAAMYjnAUAAABKLWPHPDKgnTc/4rIWvIv05VdU124zsqTx8rH83JxoiZFfRbzzdvUjNMLQurVRr8rKaQPjvAMvH6o7nE1D69bEzqfLEzZlQLjp9g3RSBmIPbl7b+V+NioSzsfx1OkXKmuZGfBlcJYrstNRllXG+7fd2fBoNoPOh3fsati6cj5uea5r5/uO0WvkT1euaOjtfuSBbXHr17/VlpA5V1mnqtHXcyOu5YvJiHL5siVtC5PbZdXoNdrIc5mryI18HRsrn6u3fv1Y5Tb/x213NeS5lUH6dL5JAQAAAFrtkgAAAADoABnP/v3RiOOvVX/cbPMXRszwLcdNkQvCzZahbF4reYhmaZTKOmOBRb79n677NcqJfHv2AjHa6ltWRFnkuZ1OQDgVGQPe8tW/jId37GxavJXhYa5XLrtp3bTfdj6DwqeeeKAS0LZDnu9VDVxwzWA2Q+AMUBsVzV4oz/d92x+Nr41+jeme78nk9dfqxyEXOY++8vyUI8Vc71x60/qmXc+1a/kb3/xOnG5wQLx1S/2Bf6fKALUR8nmVry/NfB2ryQXapaNfKyPdovKbAzLMBwAAgLISzgIAAAAdJSPIt4YjXvtZcwPajGZzdZbGyrXZmTOjafKaEMzSLMuXXh9F7GrCuuv+l+uPcWtLkGXQyOXTjMsy4MwIsFULorXoMI/pRIeNXqWcqsq66J2NiRnzfH/jm3/T1GD2QmOD5UZFnvl8aGRIfDF9fbOndM3nfc3rOYPhVqx3ZjyZYfKBg69Eo5TptaYVVjVoETlj6XYsIWeke+/2x6KofG2b3+BFawAAAGgU4SwAAADQkT7+6DcD2o8+iobruyJosDlN6Cc++STi1NsRP/9p9ZoQzNIsRRZRcx22GfFT0dXNojFwIwytX9OwYPHE8JuVldlWBZwXyscjo8PTLQ7dpuu5Hz0ejZBrmHm+GxlZTkc+p1Z+9S8atj776IPbKkFrWdTOb6uv5zyvGUM3Ynm0ZvPtG6JXNOK+PrRjZyWWbpedu5+pxOlF3dODa8MAAAB0BuEsAAAA0NFqAe2J/1L92MiA9vIrqsuzNEaey0bGyLVg9tjPqh/z59AsgwOLCi0I7nx6bzTDyMj5OHyk/qhu8+23RTtlpFgkSB6rFq2eanO0Wos5izwuzZTnu5PXMC+Uz4EM/Br19vKbNg5FGeT1nOe3FSuzE8nl0UbFs7k6W6YouVlyYbXoum5Gsw83MFquV16DRZdnc3W2Fx53AAAAOo9wFgAAAOgKGdDm8mxGlI0MaPuuDBrksgZ1E/lY/9Mbgllaa9PtxWK6Zi5G7n/5UNQrQ8F2voV6LjM2IuLMwCvjyXZGhmNlzNnot7tvhIz67rmz+AJku9cwx9OoyDNj8naHfrXruQzyvDZi0Tdfa1av/HJ0u6Ir3nmuyxDN1uTybEbyRZQlRgcAAICxhLMAAABA1xkb0I78Kgq5dGbQIDN/LwrJx/L4axGvjT62Z98RzNJaNy6tPy599eixpq5yZmhVJBgdWrcm2qFREeeJ4TdLExle6K7R23Xi5BtRFo142/SyrGGOpxHxbLtXZ/O1oujKZ6Pdu/3RON2A17DVK2+Kbreq4H18eEf5nlv5vCry+Ld72RwAAADGI5wFAAAAulYGtBla5vHL96IuM2YEDVJvhPzP5z97HIuG0FCPVStXFFpFfXbfi9FMuW6a8Wi9MmZrx8JmIyLOjAzv+KvvRFnlY3PHN/+mIdFhURkq59umF1HmaLamEQup7Vqdzev51q9/qzTLyTV5Hd/VgDh9+dL2rVu3yo0FFmfzuj1VgteKCxV9/DNGv25gUQAAAECZCGcBAACArpex5a/+f0GHynVZwSzttHrliihi/8FD0WwPFVgpzKip1auzGXEWPa8pI8MyhmZj5e27qwSLuEVD5QMHXyl9NFtTdCG1XauzuTZa1uv58NFjhYPkPK/Ll3VvPJv3r0hwvevpvVFW0338M/7O359r4IuvvyWOD5dneRsAAACScBYAAAAAYAJFVzozHGrFeuSJk28U+jqrbykesU7H8qXXF170zPXTskezNRmdPbl7T7RL0eu4Gv/+bXSKRiyktvrt5fe/dKhwmNpsD+8oHk4P/vtro1sNLq5/VTWv2bLHpRd7/F89cizu2/5o3PLVv6jEshnNturvQAAAAJgu4SwAAAAAwASWF3jb7XSgBWuzKaOrPftejHrlW6i38q3pt27ZFEVkyNkp66c1D+/YWWgFtYiia7O57Ntp8VvRWLnV66j3/e2jUXb5vDt85FgUMTjQveFsXjP1On6y/Ius+fiPXVDPn+dz7Bvf/E4llM3Xifz5ieE3AwAAAMpOOAsAAAAAMIGhdcVWOve3KJxNRSPdVr01/aqVK6K/f24UkYFWp8m4+f+xvfVxZNG12QzhOmXZ90IZKxcJfrcWDI6nKlc5O+UcP1RwdTYj/W51+ez6w9nTHfL453MqV2WX3bSucuSP8+8eq7IAAAB0GuEsAAAAAMA4MjgssjiZi5etlF+vSLy0+uYV0QqrVxb7Op0UGV4oA7Oii53TVWQ1Oc/zrqfrX21tt4yVn9y9N+o1uHhRS5aY9z5f/1p0qxV9nZlfMJovs/4uvm81uSbbyTE9AAAA1AhnAQAAAADGccftG6KIdsRwhSLBgUVNf2v6fCvzIuun6eGCi5ft9lCLb//WLZuiXnmuOz2Q2/n0M3WHnnm9rl755WimPL+tjqmL2rOv2GtbN8ez9bq8BYE2AAAA8BnhLAAAAADAOP60wDJqu2K4oiu3q5q8OtvLa7M1RRc7pyNj6HpXMPM85/nudLk6++rR16Ney5c2NybfubvzFn2Hh9+IIrp1mfV0gdemgcXXBgAAANA6wlkAAAAAgAtkLFck7ioasBb5ukWC3Q3r1zb1remLRoid9Jb2kymyDDwdt65bE/Xq9GXfsYrEqatX3hTNdOTn9Ue97XK44G2ef/Xng9+UK7x9VmcBAACgZYSzAAAAAAAXGFpff3CYdj3dmjByPEXWNfOt6QcHmrd8eGOBcLYT39J+IjuffiZaYfnS66Ne7Yq/m6HIym8+J+Y3aSE113CPF1xvbYd8LhZZTe6b3Z2B6Kl3fxFFDK0r9vcOAAAAMHXCWQAAAACAC6xeuSLqlVFZO2O4olHm1i13RDMMDiwqtOK7/+Ch6BYZTDY7As7Y87rRc16PvfteqFzH3aTI9VMkQJ5MJ8fJ7xS4PjJG7kan3y32nFl9S/1/7wAAAADTI5wFAAAAABgj12aLvGV2kbeFb4SiUebg4kVNecvwovHhc8+/GN1k/8vNDYGLnO8DXRQp1xR5TiwvsJQ8mU5cm60ZPvlm1KsZry9lUHSJN6+zzRs3BAAAANB8wlkAAAAAgDGG1q2NIg683P7osEiUmWuQzXjL8CLxYbtXfJuh2XHqqpU3Rb26ad235vDPX496DS6+NpqhSHzabh+OnI96Xd6li7PpxHCxx/SeLZsqa9EAAABAcwlnAQAAgNL53RkRc+YFNEXfFREzZgTEeDJYWr6s/sDz1aPHSvEW93v3vRBFNOMtw/uv/nzUq5Pf0n4ieZ2cbuK1cl2dseerXXiuU5E10Pn9zfk/JR+eqz8+bbciy6rdrOiSdH7jwrM/elw8CwAAAE0mnAUAAABKJ6PGawYibviSgJbGyWvpj5ZGXHeDcJaJFXl7+/TsvhejDEZGzhd+a/rrBhZFo2QMVuTPO9CFC6ipWZFqnu/+OsO7Ay9157lO79QZKuf5bEbIeLoEkT2N1YjXqrzWXvrJD2Pzxg0BAAAANIdwFgAAACitS2f+ZkArdmS68pqZvzDii1+pXkuXzQ6Y1B23FwuVyrSMWnR19paVX45GGVxcLMI90cFvaT+ZZt2vIuf7xD9257lOwwXO92CdC76T+XCkcxdnGV8uGxf5poWajLXv23ZXPPXEA9ZnAQAAoAmEswAAAEDp1QLaLyyrRpD5c5hMLZhd8qXqR9E1UzE4sKjwKuqpEi1I5luGF3k79c233xaNMv/qz0e9cj23TOe1kQ4ffT2aochy8onh7g1ni4SqGTI2WpHnJ+W19/nGLY+vWrkijrzyfDzy4DYBLQAAADSQcBYAAADoGBnMZgSZC7QZ0gpouVDtGhHMUo9Ntw9FEfsPlust7jM4LXKbMhRcvmxJNEJ/geDr+Mk3oludOn0mmmGwzgA8r5lujjmL3Lf+q0WLTE2ufZ9ucOw/tH5tJaB97sePj/54zejrswl9AAAAKEI4CwAAADTVJ59EU8yZJ6DlM31XVK+FGwSzFHDj0voj0QwOM5Yqm737ii0frrp5RTTCYIEl325eQM3r5nQT1nQvn13fOmqzQt6yKHKurX0yHQ/t2BXNsHz076lHHvxuHH1lXzz1xAOViNa1CQAAANPnPyEAAAAATfXP5yIuvyKaJgPaPD54P+LMOxEjvwp6SAazCxZWPzaba6u7ZYxUZBV1/8FXoowOHz1WWdmsd51ww/q18fCOXYVXSOsNOVMzwtIy+R+j57Y/Ghu+DQ5cG/X48Nz5YHyXW/hkGvIbKYbWrWnYaveF8jV91coVlSPla/3x4TfjwMuHKt9s0M3L0QAAANAIwlkAAACgqTI2vLwFUeOVV1WP/HrvnR09uns0r+e1Mpitea+7272el6t9Rex9vtiyazPt2fdibN64IerR1zcrVq/8cuHl2iKLiCf+sXsXZ9PwyTfjugKLvOOpN5TO1eV3/9vh4LfN7qs//qY33f2d7fHST35Q9/NxOvKbP/KovdbXQtrDR1//12+gAAAAAD5zSQAAAAA00dl3Ij76KFomQ8prBiJu+FJ1iZbuko/pHy2NuO6G1kazH38kxu5mGYcOrV8b9Tp1+mwcPnIsyurAwUNRRJFzU9MnOpzQhyONXXn1tu3NMf9q55Xpyb8b7t3+WLRDLaJ96onvxcnXX4qXfvLDuG/bXbFq5U0tCXkBAACg7CzOAgAAAE31yScR//j3Edf98eg/RLTwXyIunVkNaOcvjDj1dsTv+leQjjXjd6uP49wFrb2GavIaPv5fgi62+tO3uq5XrvmVWd6+06fPRn+dQWUGWBlaFVksLBJq5W3vZo1eguwXeEJp7N33QuU5ufXOO6KdBgeurRy1RdoTw2/GiZNvxP6DfxfDox9PdfnrLAAAAFzIfzICAAAAmu7X5yP+65HR/2j/xxEzZ0ZL1QJaOtcf/Ltom5FfRbx5oro4S/caWldsUXXv8y9G2e3Z92KhcGvTxqF4+LFdUY+ia7PdHnR1exgMve7hHTsrH9sdz45VC2lri+JjQ9r8ZotGB/0AAABQNpcEAAAAQAtkeHjsZxFvDVdjRCizvEaPv1Y9RLPdLd/WfvmyJVGvjDoPHyn34mx69vkXoogbl9Z/ji73tuAtNf/qzwdQLhnPPlTnNx+0Qi2ifeqJ78XJ11+K5378+OjP11T+jgQAAIBuZHEWAAAAaKn3zlSPvisi5oz+t/g58wJKI4PZd94Wd/eSVStXRBEHDr7SMWHR8eE34rqBRVGP5UuXVALjToiEoRkEhBSV8Wyuuv7HbXdFf8mvp8pr/qffMLF33wuVJdr8+w4AAAC6hXAWAAAAaIsME/M49XbE/IUCWtqrEnSfFcz2os23b4giNm28rXL0glU3r2h5OJuLvt3uw3Pno5H6LrfwC2V14OChGD75Zty37a5YXfAbN1oll2jzyNfjjH/37nsxAAAAoNNdEgAAAABt9PFHEW8NR7z2s2q8CK3yySfVcPvnP61eg6LZ3pNremVf/SuTDevXBo03MtLgcHb2rADKKwPUO775nbj729vjdAd9c0CuLj/y4HfjyCvPx9D6NQEAAACdTDgLAAAAlMLYgDZjxo8+CmiKWjB77NNrLX9ObxL+TE9f36xYvmxJtNL8Hgib51/9+QB6z959L8TSm9bFQ4/tEtACAABAiwlnAQAAgFLJgLYWNWZI2+6A9tKZETNmBAXlObyszSOIglkudOPS1kag3WDz7RsCgMZ5eMfOSkDbqQu0jzy4rSe+yQEAAIDuIpwFAAAASuu9M+0PaOfMi/jCsoj5C6sRLdOTwWyeuyVfivjcnGiLkV9Vr6Gf/1Qwy2dyJa9f6DNty5cuib6+2QFAY9UWaL/259+q/LhTDK1fG8/+6HHxLAAAAB1FOAsAAACU3tiANiPIVstgNuPPG74Ucc2AgHYqaucsg9n82I7V3rxWjr9WPfIagrFWrbwpmL6+vlkxtG56b8394ci5KKLbY6y+yxsbInfSYiXw2w4fPVZZn118/S2VjxnRjhR8HW22fJ1+6Sc/rES0AAAA0Am80SAAAADQMTJ+zKPviog5c6trsK2WXzOPvB25Xvpxm5Zwy6qdj01NBrPvvN2eyJrOkIHP6pUrgvqsvmVF7Hx6z5R//8jI+WBifbNnBcCFMpbNaDaPu6O6+L186fWVj9cNXFu69e/8xopHHtxW+XEnLeYCAADQm4SzAAAAQMfJIDKPDFdzzbSdAe0H70eceUekmcHsgoXVj+1SCavPeiy4uAyPqF9GWxlsTWcBMX9vvZHX4OJr41QXr6iWaVG3Euh9e3sA5ZNLtHlE7Kr8vBbQLhv9O+26xYuivySvJeJZAAAAOoFwFgAAAOhYufb61nB7A9orr6oeGWtmtJnxZi9pdzD7yScRZ9+pHvljmIo7bt8QFLNp41A8/NiuKf/+XJ2tN5zNFcNuNv/qxsZup979RdSrLOEdcHG1kPbJ3dUF8MGBa2Nw8aLKN4cMLL42rhtYFO2S8eyJ4TfjxMk3AgAAAMpIOAsAAAB0vLEBbcazV40eM2dGS2U4mkcGvHk7uj2grSzuzhXM0nly3bOdMVG3GFq3dlrhbC7G1htlDizOx+vF6FazGxwGn363/nXey2d3d6QM3awSqo4etaXX/GaFjGhzmTaXu29ctiRaadcT34tbvvqX01onBwAAgFYRzgIAAABdIwPajFZrAW3/wtYHtJeOfr1rBrozoJ0x+i9JcxdUjxlt+lclwSxF3bPljqC4DJCXL1sSh48cm9LvP/Xu2Vge9VnQ5SuojQ65PywQqdW7CgyUTwarBw4eqhw1GdHWYtrrBq5t6nM+/564f9udcfe3twcAAACUjXAWAAAA6EoZrOZRhoC2dlsy7O1EZQhmR341eg7Pdv+SL81349LWLu51s1U3r5h6OHu6/hXUfMvxbjXYhPXjkZHzlWCuniBufpdHytDrDh89VjkiqovhGdAOrV9T+buxvwnP/6H1a2Pv8y9O+e8KAAAAaJVLAgAAAKCLZWh57GcRbw1X48tWy4A249kbvlQNaS9tccBbREayeduXfKn6sR3RbD5mx1+rHqJZilrepDCoV21Yv3bKcebpAuFsxpzduoTaf/Xnoxkynq2XeBZ6R0a0uQi79KZ1lY9FXqsnstXSOwAAACVkcRYAAADoCbXV174rIubMrS7Rtlp+zTzydpx6u7wLtO08RzUZzL7zdntiZ7pXruoVkSueHxYIEsvo8r5ZdUepfaP/28GBa6e0JHjiH9+KIm5cen3sH/N2491ieZMWkI+ffLPuSHxw8bWFFoKBzrR33wuVI1diM3Zt1Dea5Ovc8mVLrM4CAABQKsJZAAAAoKdkiJlHhqu5otrugPa9s+WJQzOYXbCw+rFdynZO6B4Zea5euSKKuPXr/7c4PvxGdJN7tmyKrXfWvwaYcdXXphBDnTpdbDJ62dIlXRrOXh/NUCR87b/a4iz0slpAe9+2u2Lzxg3RCKtuXiGcBQAAoFQuCQAAAIAelGuvbw1HvPazaqzZDhnPXndD9WjnumuGsrXb0Y5o9pNPqiFzPhb5mIhmaYaMZutdVk0nht/oumg27Xz6mSgilwSncl5HRs4XOn83Nikwbaf5/XPjuoFF0QzDBc51rggD3Lf90bh3+2PRCBvWry30dzAAAAA0mnAWAAAA6GljA9qMNz/6KFouY9VrBiJu+FJrA9qx4W47g9ljn577j9tw7ukdQ+vWRhF7970Y3SiD1qIrgEPr1kzp9x0++nrUa3BgUSU07SbLmxgDH/55/ec6Y2iAtHP3Mw2JZ3P1XZQPAABAmQhnAQAAAKIabWa8+Q9HqiFtOwLaS2c2P6CdMSNi/sKIL36l+rXKEMzmz6GZMrhcvqxYDHjg5UPRrfYXvG+rb1kxpd83XHCx99b1Uwt0O8WqlTdFs5w6fTZGRs5FPfL5YhkSqMl49snde6KoVTdP7e8KAAAAaAXhLAAAAMAYGXG+d6YadZYhoM3INX9eVC2YXfLpn5k/b7Vfn6+e05//VDBLaxVd9nz16LFKiNit9u57IYrIhdKphMmFA90uiq4yTl29srn358Twm1Gv1Su/HAA1D+/YWXeMX7Ogy1bDAQAA6GzCWQAAAIAJjA1oR34VLZfBbEauGdBmSFtv7NruYDbP3fHXIv7+SPWcQqtt3bIpinh234vRzUZGzsfhI8eiiKnEyfl1jhdYnR0cWFR4ObgsisbcU1EkVB5avzYAavL1+8nde6OIgcXXBgAAAJSFcBYAAADgIjL2zPAzjw/ei7aYM6++6LUW37YzmM2jHeExpIwt+wuu3B0+Wiwq7QRFV2c3337blH7fgYN/F0Vs3XJHdIOiMfdUFFmcHVy8KPr6ZgdAzc6nnym0Ojvf4iwAAAAlIpwFAAAAmKKMP//xHyJe+5nl1MmMDY0Fs7TbptuHoogDBw/FqdNno9vlOmmRIKqvb9aU1mCLRsjLly7p+NXZofVrCsfcU5Hnut7HNB/PoXVrAqAmV2eLBPlJPAsAAEBZCGcBAAAApunjjyLeGhbQjvXJJxGn3q6ekzw3glnK4salxSLL/Qfrf7v7TpJBVNH7OpXQMmPO0wVD5E5fnW3F2mzNnn0vRr1W37IiAMY6frJYOAsAAABlIZwFAAAAqNPYgDaj0Y8+ip5TC2aPfXoOPu7Bc0B5rVq5otCyZ8ake/e9EL1ib4HIMq1eeVP09c2+6O/bU/DrdPLqbKvWZmsOFIihu2HdF2isIsvkAAAAUCbCWQAAAICCMhbNaPQfjlRD2l4IaC8MZvPnUDarVxZbzNx/8JXoJbkGWySK6uubNaXV2Z1PPxNFPfLAtilFumWSb1HeyrXZVPQx7fR137EyBH7qiQcq8bK3i+9d7Xrs8/Uqr8H7tt0Vz/348Tj5+sHoRCPnzgcAAAB0A+EsAAAAQINkPPremWpM2q0B7a/PV+/bz38qmKXcMo4aWr82itj7fLFl1E5UdA129S0Xj5VzyXd/gSXUVI1QvxGd5J4td7R0bbbmyd17o14Z+mVo2g02bdxQWaF+5MHvxpFXno+XfvLDSsRoVZdm+O1Q9qXKx82j12H+en6jQSdee32zZwUAAAB0gxkBAAAAQMNlQJvHnHmjx9yIviuio438KuKdt6sfoRMsX3p9FHHq9Nk4fORY9JoDBw9Vwq56VYOw2RddOd25e0/hReBNG2+L0+/+Ip4c/bPKLpdmi4bc9Trw8qHYemf9y7H3b7s79h/8u45+i/YMrS+83gYHrq0ceb3nfTt89PXKynR+zOc/3Suvh0Y/xvm6N7j42kqcfd3odZWvhRez6uYVHff3zODAoijCcwsAAICysDgLAAAA0EQZzx5/rXp88F50nAxla7dfNEsnGVpXLFLMt7jvRXm/TxcMmzZtHLro78mv04hgrBMWQzOgu6dAuFrUieE3Cp3rXMbstHXfC+Xa72Qyehy7RpvHIw9uq1xb+Tm6y+UNfEzzuhlvUXYqNqxf23HXV//Vn4965do4AAAAlIVwFgAAAKAFMjr9x3+IeO1n1Zi27MYGv4JZOk2uCRaNKXc9Xf/b23e6PftejCJW3zy1JdmHduyKRnjq+w/E4OJiK4jNkoumTz3xvWi3ouc6133btZhbVIaN073t+RqS/5vnflQNIsseZzM9A4uviUbJGHSqoeyFMkqfyjcalEU+L64rsDh7/OQbAQAAAGUhnAUAAABooY8/inhruJwB7SefRJx6u3rb8jYKZulUtxZcm823kj4+3LuBz7PPvxBF5Ft5TyU0zNXZvfuKfa2U8VkuPZYtbsyYLsPLMixKNmLh9/5td5U2UJ5Invv/OHq7i8gw8sTwm0F5fDhyLoqoN3Qdz4mCMejm22/rmNXZiy03X4znEQAAAGUinAUAAABog7EBbcaqH30UbVMLZo99els+buNtgUbYsH5NFLH3+eIxZyfLcLhoZLlqiquz925/NEYKRnCpEs/+qPo26WWQtyNj3jIFcUVXZ/Mc73rie5XVyU6x9c47or/g7d1/8JWGXKM0TsbMRaxeeVM0St6WIq+X+bzauuUbUXa1FeYiDrx8KAAAAKAshLMAAAAAbZSRasaq/3CkGtK2MqC9MJjNn0OnyyXBoqHcs/tejF63v2DgtGGKgVVGZw/teCoa5b5td8UjD25rW9yZoWx+/fsKrpw2QyNWZ/O8Pvujxzsint26ZVNsur14SL33ea8HZXT69NmoV8aqjVyoLvp6uWnjbaVbzL5QfmNCEUUDYwAAAGg04SwAAABACWS0+t6ZasTa7ID21+erX+PnPxXM0n2GCq7Nvnr0WGVxtdft3VdsdXc6YdrO3c80NKjKVcSMO4teC9P/umvi6Cv7prXKmNdaK9dM7/3bR6OoTohnc/H3njuLva18erUBsTHNcfzkm1HE1i3Fr4+aoq+X6ZEHtpX2OZUReiOWmwEAAKBMhLMAAAAAJTM2oB35VTRM/lnHX4v4+yPVrwHd6MalxVb7rM1WNWIdcDph2t3f2d7QgDQDtEce/G4ceeX5pga0uTC7eeNQHB39Ovn18udT9ero+V1207rYf7B1b19+YvjNeOixXVFUnt+XfvLDlsfJU5GRX6MWf3fu3huUUy4oF5Hr5FvvbEw824jXy3xO7fr+A9N6DWmFfD41IkK33AwAAEDZCGcBAAAASirj1gxd8ygS0NaC2aJ/DpRdRnxFV/GKxljdpOjbjw8uXjTlCCyXV+/69vZotLEB7SMPbotVK28qHKbl/z6ju4wzc2H2vm13T/u6y0j4nu80/v5Oxc6nnyn0Nvc1uSqc5/b+bXeWIvbL23D/d+9qSOSXcm32gJXM0soIvKh7tmya1kL0ZB7aUTxIHxy4Nl76yQ9KsTybz6d8zWzE8ylf3y03AwAAUDYzAgAAAIBSq4Wvl86MmL8wYs68qf3vPng/4sw7Yll6R0aRRWQod6oBQWG3yLcfz9XYeqPIDCuH1q2JnU/vmdLvP3DwUGUNtVErkGNliDa/f+2/RnIZSB8ffjPeffdMHD/5VuXXxotJ+2bPrkSxC/r/bVx99by4buDaGFx8beFQNO9nu661XMfMSPm5Hz8ejbBp422V597DO3aOXjPtWZXMkPnRB7cVDufHuufb7QmbmZp8DmeAXvS5mHHo/P7PF15iztuTcejyZcVWz/O16tkfPV5Z4W5XbJoB71Pff6Bhz6eHGxAVAwAAQKMJZwEAAAA6xMcfRbw1HHHq7YkD2k8+iXj/TDWYzd8PvSJjo9UrV0QRz+7zVtJjZWD56tHXC53X1besmHI4mzK+zIitUSuQE8nQMo92yCB5OuekGTLyu3f7Y5W12EaoLfvmgmcrA9p8DDO0bvRj+dDofRDRl9+e0ets88YNUVRet7euW1u5dvcf/LtKkFuPXJ19blnxazGfT8/96PHKa0VGp626FjNCzufTptuLn9Oa/AaFvB8AAABQNsJZAAAAgA5TC2j/tzci+q6I+P3Zn/36B+9V41noNcuXXh9F7T94KPhNO3fvKRTOZtCYEdh0wq+7P136bHY82w55Hsqyvrhz9zMxuPiahp7nsQHtrqefqUSIjY7+Mu7L1d9mBLOp8hg9ZiGzE+RKdSPC2VS7dh+J31yk/nDkn+PUu9VreP7V1QXW/qs/X/n9N45ef/m5r/35tyq/3qjV2Zp8buY1nn9uMwPa/BqrRl/nN6xfU3jB90Kb/uo7AQAAAGUknAUAAADoUBnIfvB+9YBed0fBhbxcxKt3ZbCbnTj5RuG3Q791/Zpph4jdGs/e+vVvlWrJ9N7tj1beln1w8aJopIwK79t2d+U4MfxmvJpB4dHXY3j0epru/c9rL4PFG5f9UaxaeVMlmm103FeT13o+RnSGRoeqNdNZpL7wWrz7O9vjpZ/8oGHXaD6X5vevrbwW5v3Nv6tODL9VeW2uVy0+v3HZ9U1d37bcDAAAQJkJZwEAAACAjpZh0XUDxcK/A9ZmxzUycr7w26Fvvv22uhY8uy2eLWNElo/vHd/8m8rbwvf3z41mqIS5o0ftGso49cTJNytf+8PRH194TjLqu7xv1uhRjfuadbvGc9e3/1bo12Ee2rErnlvWnPBzKvpGr9X8++f4cDVkzevnoR1Pxf3b7oxGGxu51p5H4y3jjnXhSm5G8vl8bLYDB1+x3AwAAECpCWcBAAAAgI52z5Y7oogMnfYLZydU9O3QMyzLRchchpyujGdPnf5FbL2z2GPcbhnNljUiy+v/a1//VlPj2bEyjG3WwmUR+Rhl7EdnyRXWJ3fvKfQaVdSyL17/r+Fs2rn7mRhcfE1To//a86iMz6V8Tbl3+2MBAAAAZXZJAAAAAAB0sBsLhkMZXjGxPD+5bljEqptXRL0e3rGzEtAWvQ3tkm+tXvblxVo8e7pH11bLHDZzcfka0c5rd7wF13u3PxonTr4RvSZfS24dfS2x3AwAAEDZCWcBAAAAgI6Va3tFVzL3Pv9iMLknd++NIjasX1tZSKxXxqe3fPUvOy7sfOjT6LcT9Go8K5rtfCMj5+Mbf/WdaJfxVl/zNt3xzb/pqeeTaBYAAIBOIpwFAAAAADrW0Po1UUQGPoePWJy9mKKrvH19s+LGpddHEflYLb1pXeUtwMseo+U67r3/6dGOCzLzHK/86l/EgYOvRLfLxyijZtFsdzgx/GbltaEd5vfPHfcbA3opRhfNAgAA0GmEswAAAABAR8oYc2j92ihi/8FDwcVlOFs0MN60cUM0ws7dz1RitFyhLaMM+HIdd+fTe6ITVdY7v/k38VAXB6W1oLGs1xD1ydeGdl23E31jQC/E6K+O/t2Qr3miWQAAgP+jvfsPjfu+7zj+brvMkFkXSuiImjNsBZlZCgx7DEn+w8mgTtI4YWDXcmggdSabdWQkrgPJoCqzwX8shjo/wDQjVn50JNRSnI3ZMnaUlNgFO15BJhDJIO2PUsuoJMsfPsnK/mvv802UpqmdWvdDurvv4wHHWb/s7+Xu+1X+eOolmolwFgAAAABoSndv3BDVGmzSuHE5nDl3PqqRfp351VYZK5ECrbQW2nP75oaJHxdWZu+878GWCMgOPHsovv2d1lvLfP7Fw1nklwJnWk963S5HPNtTvr5dSyvH6Omal5Zm0/UPAAAAmolwFgAAAABoSn2bq1ubHZ+YtJC3CIde+mlUa8dDfVFLnw1o0/1yRJ4pGEtBXPftW5p2ZfZa0tJwWstMsWmzy1Zmv/Nw7Nn3tMivxaV4NgXsS3k9uK2z449+znIcV718vDL7YMtd8wAAAMgP4SwAAAAA0HRWFdujt2ddVOPQS0PB9UuriWffGYtqrO+u7jm7lhRFpuXZ7ts3Z3Fk+nO947T3JqY+DWZTENeqMWZ63lNsmuLkM1U+/8thIWxOK7MpBCYf0qLwtx94uOpr1vXqWrP6uha103Gl61Szrs+m8yn9kEJambXaDAAAQDP7kwAAAAAAaDJ3bdwQ1RLRLd6JN09XFSz3dq/Lvr6eMVt6Xhee2yywLv+bnWs6oqt8S6uQ1xO3XU2Kc9PfO3FhKk6Mns7dWnF6vCmWS/89dz/SH+t76hNB10oK/J5/cShbxLQwm0/ZynD5Ndu3ZVM8Vn7NFsvXg3opFFZGV/n6cr3XthTbD78+kp1L6fganfMJAACAViOcBQAAAACazs7t26IaZ86N5S58rIW05Lp3YFdUo7d77ZKtQKbn+OL0yO+9L4WzKaJNVn0S0hVvveXTj8/OzsXl0tynXz99acZr5TNSPLz1gbEsoO3bck/DRX8CPz4vXbfSLb1W+7f3xW2dq6Meuv6qY1HXtnRdSeutB54dLB/XtvjWxg11jXsrkVamh18/nv2wgPMJAACAViKcBQAAAACaSgr2qo2Lho8cDxavVJrLwrBqVmd3br8/DizjrylP8dfCIu3Zc0GFFpZ9U/SXzsmtm+9ZthXa9JweLp/TJ0dPW5LmmhYC2rQMu2P7tlhfg+8lC1IEW5qdi0qkr92z7+nsltbU7/7kVuk6drXS8QyVz6fPrncDAABAq/nS17/R85sAAAAAGs7wv58NgHrY+o+9ATSGp/YPVLza+qNnDmXhaqNIoV9aFE7RX+eajrote6ZQ9r2JqTh77ry4j6qkiDYFtD3l123x1vbres2m19+vpmdi4sJUdktrrPVYpU5Begpp00J2PaP0dOzpHKrnYwEAAIBGY3EWAAAAAACoWgoK0+pruiUppE3R36piexRvvSWLFAttbdnbNxVWfuGi5kK8N35hMls6TlHf5bR4fG5M2EfNjE9MZbfnXzz86fs+fr3+4RLt9KWPX3dL9fr7fBSezp90XL87p9rL59DK8rn08Tl1Lem8TOfO5fJ9egwXp38dl8r3v8qC2fPZxwEAACBvhLMAAAAAAEDNpSDv4/gvoGmkMLYR4+yFyHchTAcAAAAq9+UAAAAAAAAAAAAAgBwQzgIAAAAAwDIpFNoCAAAAAFg6wlkAAAAAAFgmN7WtDAAAAABg6QhnAQAAAABgmawqtkelpi/NBAAAAACwOMJZAAAAAABYBoXCyihWEc6WSnMBAAAAACyOcBYAAAAa1Pv/Z0UOqL0PPnRtgUbRtWZ1VOPyrHAWAAAAABZLOAsAAAANav7/ZwOg1t4XzkLD6O1eG9UYn5gKAAAAAGBxhLMAAADQoH55UQwD1N6VeQuVNJdCoS1a1frudVGpUmmufPNDNgAAAACwWMJZAAAAaFDCWaAeJibHAppFb/e6GD36cuwdeDRazapie/T2VB7OvndhMgAAAACAxRPOAgAAQIMSzgL14NpCs9j7w13x2qsHo1hsjx0P3R99WzZFK9n9SH9UY3zCuQwAAAAAlRDOAgAAQIManxyL+Xm/ghmonSvzc9m1BRpZWmJ94+hPYsf2bb/3/r0Du6JrzepoBekxru+ufG02Ofnm6QAAAAAAFk84CwAAAA3sf94VxQC184t3TwU0sp0PbYs3jr4cXZ0df/CxQmFlDD73b1l02uz6Nm/KlnSrYXEWAAAAACojnAUAAIAG9vaZ4wFQK64pNKoUw7726sHYM7ArCoW2L/y84VcOfuHnNLr0GHY/2h/VOHNuLEolq/QAAAAAUAnhLAAAADSw9CvV5+eFMUD13v9wJrumQKO5a+OGbGW2t3vddX1+Ftk2aTybjjkde7WGj4jgAQAAAKBSwlkAAABocCM/GwqAag0fGwxoJCki3fvDXfHCc08uOoLt6uyIvQOPRrN5ev8Polhsj2qUSnNxYvR0AAAAAACVEc4CAABAgxt566dWZ4GqpLXZt8+MBDSKtC47evTl2LF9W1Sqb8umiqLb5ZCO8an9A3HXxtujWidGT0Wp5P8LAAAAAKBSwlkAAABocFfm52Lo2AsBUClrszSap/cPVL28mty1cUO8cfTlWFWDv6te0rG99srBLPSthQPPOp8BAAAAoBrCWQAAAGgCaXV2fHIsABbL2iyNaNfj+6JWUpj6xtGfxM6HKl+vrZeFsLersyNqYejISFycngkAAAAAoHJfaftqcU8AAAAADW988nz8Xe89ccMNKwLgelyZn40fPLkz5j+aC2gk05dmolBoi79Ze1vUwooVfxp3bOiJuzduiLd/fi5KpeV9zaeY94Xnnox//t6D5WOrzfftFMzufmLfsj82AAAAAGh2FmcBAACgSXzw4UwMHXshAK7X8LHB7NoBjWjPvqdj/MJk1FJX5+p459Tr8dT+gSxeXWq93euyfzsdQ/pzLR14dtDaLAAAAADUwJe+/o2e3wQAAADQNPru3RFb7+sPgC8yfPRQDB0bDGhkKW597ZWDUaxT5Dp0ZCROjP48To6einpJy7nbtnwr7tp4e81j2QXpcXz/8X0BAAAAAFRPOAsAAABN6OHvDsQd6zcFwNW8fWYkDr4ssqM5dHV2ZPFsClDrpVSajbPnzseJ0VMxPvG/VS3dpuPsWtMR63vWZqFsvWLZBWlldusDD1ubBQAAAIAaEc4CAABAkxLPAlcjmqUZLUU8+3njE1NRmp3NgtTPRqmz5fddLl2J4q23ZG+nY7qpsDK61qzO7uu1jns1Kfi9877vimYBAAAAoIaEswAAANDE+u7dEVvv6w+AZPjooRg6NhjQjPq2bIqn9g8Ev/MP3/uXODl6KgAAAACA2vlK21eLewIAAABoSuOTYzH/0ZVY/ZddccMNKwLIpyvzs/Hqf/44/uvkfwQ0q/ELU3HyzdPx9/d+M1as8D3t+4/vi/8+NhoAAAAAQG1ZnAUAAIAW8LWb22PPYwfjz29eul8fDTSGFNAffGlffPChX+VOa+jq7IgXfvxkFIv5/J5WKs3Gv+57JoaOjAQAAAAAUHvCWQAAAGghd/Ruiq339QtoIQfSyuzwscEYeetwQKtZVWyP1145mLt49uL0TPT/0xMxPjEVAAAAAEB9CGcBAACgBQlooXWlYPb4W0Mx8rPD2Z+hle0Z2BU7H9oWeXDmnbHY/cS+LJ4FAAAAAOpHOAsAAAAtrGv1urhj/T3xt3+9If7sxrYAmlMKZH/x7ul4+8zxGJ8cC8iTvi2b4rFH+lt2fbZUmo0fPTMYh16yHg0AAAAAS0E4CwAAADmRItq/WNVRvl8bN97YFl+7ud0iLTSg9z+cifmPZuOXF6c+vYllybtCYWXs2H5/PPZof7QSK7MAAAAAsPSEswAAAAAANIVVxfbY/Uh/tkLbzFIwe+DZwTh7ThQPAAAAAEtNOAsAAAAAQFNZCGjXd6+LYrF51tMFswAAAACw/ISzAAAAAAA0pUKhLe7euCG2br4n1vesi0aUYtk33jwdh48cj1JpNgAAAACA5SWcBQAAAACg6aUV2hTR3vnNDcsa0aY49r2JqSyWPTF6Oi5OzwQAAAAA0DiEswAAAAAAtJS0RNvbvbZ8Wxddazrits6O7H31kMLY8QuT8c6581kwO35hyrIsAAAAADQw4SwAAAAAAC0vhbMpok3LtMVbb8neXlUs37e1ffLxlXHTVeLahcXY6Uszcbk0F5c+uU+x7MXpX4tkAQAAAKDJCGcBAAAAAAAAAAAAyIUvBwAAAAAAAAAAAADkgHAWAAAAAAAAAAAAgFwQzgIAAAAAAAAAAACQC8JZAAAAAAAAAAAAAHJBOAsAAAAAAAAAAABALghnAQAAAAAAAAAAAMgF4SwAAAAAAAAAAAAAuSCcBQAAAAAAAAAAACAXhLMAAAAAAAAAAAAA5IJwFgAAAAAAAAAAAIBcEM4CAAAAAAAAAAAAkAvCWQAAAAAAAAAAAAByQTgLAAAAAAAAAAAAQC4IZwEAAAAAAAAAAADIBeEsAAAAAAAAAAAAALkgnAUAAAAAAAAAAAAgF4SzAAAAAAAAAAAAAOSCcBYAAAAAAAAAAACAXBDOAgAAAAAAAAAAAJALwlkAAAAAAAAAAAAAckE4CwAAAAAAAAAAAEAuCGcBAAAAAAAAAAAAyAXhLAAAAAAAAAAAAAC5IJwFAAAAAAAAAAAAIBeEswAAAAAAAAAAAADkgnAWAAAAAAAAAAAAgFwQzgIAAAAAAAAAAACQC8JZAAAAAAAAAAAAAHJBOAsAAAAAAAAAAABALghnAQAAAAAAAAAAAMgF4SwAAAAAAAAAAAAAuSCcBQAAAAAAAAAAACAXhLMAAAAAAAAAAAAA5IJwFgAAAAAAAAAAAIBcEM4CAAAAAAAAAAAAkAvCWQAAAAAAAAAAAAByQTgLAAAAAAAAAAAAQC4IZwEAAAAAAAAAAADIBeEsAAAAAAAAAAAAALkgnAUAAAAAAAAAAAAgF4SzAAAAAAAAAAAAAOSCcBYAAAAAAAAAAACAXBDOAgAAAAAAAAAAAJALwlkAAAAAAAAAAAAAckE4CwAAAAAAAAAAAEAuCGcBAAAAAAAAAAAAyAXhLAAAAAAAAAAAAAC5IJwFAAAAAAAAAAAAIBeEswAAAAAAAAAAAADkgnAWAAAAAAAAAAAAgFwQzgIAAAAAAAAAAACQC8JZAAAAAAAAAAAAAHJBOAsAAAAAAAAAAABALghnAQAAAAAAAAAAAMgF4SwAAAAAAAAAAAAAuSCcBQAAAAAAAAAAACAXhLMAAAAAAAAAAAAA5IJwFgAAAAAAAAAAAIBcEM4CAAAAAAAAAAAAkAvCWQAAAAAAAAAAAAByQTgLAAAAAAAAAAAAQC4IZwEAAAAAAAAAAADIBeEsAAAAAAAAAAAAALkgnAUAAAAAAAAAAAAgF4SzAAAAAAAAAAAAAOSCcBYAAAAAAAAAAACAXBDOAgAAAAAAAAAAAJALvwUd+2uwxT2hDAAAAABJRU5ErkJggg==\")
\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Route based on previous annotator\n",
"\n",
"This example demonstrates how to set up an agent to automatically route a task depending on which annotator it was annotated by. This allows for more complicated flows where you track the performance of an annotator and can conditionally route based on that.\n",
"\n",
"### Example Workflow\n",
"\n",
"This workflow allows for conditional routing of tasks, note the Agent stage follows the Annotate stage and has multiple pathways. To use this example effectively, ensure your workflow matches or closely resembles the one shown. Without the previous stage, we will have no such field and without pathways, we have no option for dynamic routing\n",
"\n",
"[📖 Here](https://docs.encord.com/platform-documentation/Annotate/annotate-projects/annotate-workflows-and-templates#creating-workflows) is the documentation for creating a workflow with Encord.\n",
"\n",
"The code in this notebook is for the **annotator name routing** agent."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"Ensure that you have the `encord-agents` library installed."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!python -m pip install encord-agents"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Encord Authentication\n",
"\n",
"Encord uses ssh-keys for authentication. The following is a code cell for setting the `ENCORD_SSH_KEY` environment variable. It contains the raw content of your private ssh key file.\n",
"\n",
"If you have not setup an ssh key, see our [documentation](https://agents-docs.encord.com/authentication/).\n",
"\n",
"> 💡 In colab, you can set the key once in the secrets in the left sidebar and load it in new notebooks. IF YOU ARE NOT RUNNING THE CODE IN THE COLLAB NOTEBOOK, you must set the environment variable directly.\n",
"> ```python\n",
"> os.environ[\"ENCORD_SSH_KEY\"] = \"\"\"paste-private-key-here\"\"\"\n",
"> ```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"ENCORD_SSH_KEY\"] = \"private_key_file_content\"\n",
"# or you can set a path to a file\n",
"# os.environ[\"ENCORD_SSH_KEY_FILE\"] = \"/path/to/your/private/key\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### [Alternative] Temporary Key\n",
"There's also the option of generating a temporary (fresh) ssh key pair via the code cell below.\n",
"Please follow the instructions printed when executing the code."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# ⚠️ Safe to skip if you have authenticated already\n",
"import os\n",
"\n",
"from encord_agents.utils.colab import generate_public_private_key_pair_with_instructions\n",
"\n",
"private_key_path, public_key_path = generate_public_private_key_pair_with_instructions()\n",
"os.environ[\"ENCORD_SSH_KEY_FILE\"] = private_key_path.as_posix()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Define the Agent\n",
"\n",
"In the following code cell, we define the custom code that routes based on prior annotator name.\n",
"\n",
"Ensure that you add:\n",
"- ``: You obtain it from the Project page in the Encord platform.\n",
"- ``: Can be found from the workflow graph or the agent name can be used\n",
"- ``: It will be listed when you expand the agent node of the Workflow on the Project page. (You can also use the pathway name that you gave it)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from encord.workflow.stages.agent import AgentTask\n",
"\n",
"from encord_agents.tasks import Runner\n",
"\n",
"runner = Runner(project_hash=\"\")\n",
"\n",
"\n",
"@runner.stage(\"\")\n",
"def by_file_name(task: AgentTask) -> str:\n",
" last_annotated_by = task.last_annotated_by\n",
" if \"expert\" in last_annotated_by:\n",
" return \"Expert\"\n",
" else:\n",
" return \"Novice\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- **Task Runner:** The code initializes a runner to process tasks.\n",
"- **Task Routing:** It defines a stage implementation that:\n",
" - Extracts the last annotated by\n",
" - Identifies whether expert is in the email i.e: john+expert@acme.org\n",
" - Routes the task onto further review dependant whether it's an expert"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Running the Agent\n",
"\n",
"The `runner` object is callable which means that you can just call it to route your tasks."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Run the agent\n",
"runner()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Outcome\n",
"\n",
"Your agent now routes tasks based on the previous annotator and routes them appropriately through the Workflow.\n",
"\n",
"> 💡 To run this as a command-line interface, save the code in an `agents.py` file and replace: \n",
"> ```python\n",
"> runner()\n",
"> ``` \n",
"> with: \n",
"> ```python\n",
"> if __name__ == \"__main__\":\n",
"> runner.run()\n",
"> ``` \n",
"> This lets you set parameters like the project hash from the command line: \n",
"> ```bash\n",
"> python agent.py --project-hash \"...\"\n",
"> ```\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"provenance": [],
"toc_visible": true
},
"kernelspec": {
"display_name": "encord-agents-Cw_LL1Rx-py3.11",
"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"
}
},
"nbformat": 4,
"nbformat_minor": 0
}