# SVM Learner rejecting 1 column due to incompatible type

**URL:** <https://forum.knime.com/t/svm-learner-rejecting-1-column-due-to-incompatible-type/6813>\
**Category:** KNIME Extensions\
**Tags:** text-processing\
**Created:** [January 5, 2016, 3:56am UTC](https://forum.knime.com/t/svm-learner-rejecting-1-column-due-to-incompatible-type/6813 "2016-01-05T03:56:15Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jasleen\_Bhullar](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/j/ea666f/32.png) [@Jasleen\_Bhullar](https://forum.knime.com/u/Jasleen_Bhullar)\
**Post date:** [January 5, 2016, 3:56am UTC](https://forum.knime.com/t/svm-learner-rejecting-1-column-due-to-incompatible-type/6813/1 "2016-01-05T03:56:15Z")

</div>

Training And testing the SVM Classifier for sentiment analysis of Text. The input file contains CSV file containing 2 columns : Text and Sentiment (POS OR NEG). The process works fine with Decision Tree and Naive Bayes but gives "SVM Learner rejecting 1 column due to incompatible type" error in SVM Learner. I am attaching the screenshot of my process here.

![](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAnsAAAHxCAIAAACale3jAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsMAAA7DAcdvqGQAAIQJSURBVHhe7b0LmB1HeeavkUe+gAbE1QmJlLt21rkKCFGCgYQQ2IQJSLmDMSz77GZJjICNY+OdzYYocUjYTcKSZE2MIixlgLEHxtYRYzSMRiMP0lgytgSCsQYkx7ZYJhLWSqtMHv0jHpT4/9Wlq7+uvpyv+3TP6XPO+3vKctVX9VZVV/fp9/SZc7pXXLhw4WkAAAAAVEw5jttKJ9DKgVYOtHKglQOtHGjjwHGLAK0caOVAKwdaOdDKqVoLxy0CtHKglQOtHGjlQCunai0ctwjQyoFWDrRyoJUDrZyqtXDcIkArB1o50MqBVg60cqrWwnGLAK0caOVAKwdaOdDKqVoLxy0CtHKglQOtHGjlQCunai0ctwjQyoFWDrRyoJUDrZyqtXDcIkArB1o50MqBVg60cqrWwnGLAK0caOVAKwdaOdDKqVqb4LgUAQAAAEC54Bq3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWgvHLQK0cqCVA60caOVAK6dqLRy3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWgvHLQK0cqCVA60caOVAK6dqLRy3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWgvHLQK0cqCVA60caOVAK6dqLRy3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWgvHLQK0cqCVA60caOVAK6dqLRy3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWpvguBQBAAAAQLngGrcI0MqBVg60cqCVA62cqrVw3CJAKwdaOdDKgVYOtHKq1sJxiwCtHGjlQCsHWjnQyqlaC8ctArRy8mi3Dq6IMDDUsDX5aef26u0Y3Gojcto556LUTcuPobRdYLXTmwfy76RW51xoUEJpcVzJqLMWjlsEaOXk0UbOKLowsHnalHKDdZbTLVpys/CQiRSiaG1B+2ptzsMFPdOMC8eVUWctHLcI0MrJo42eUcJTpjHfASragK7SBKdU02Rw0MQpqscVCIkwaKNKm9SSNfSmaaGg0rrt0HV8VlGJmVl4Cl2udfbpEm308OHwfUR74cKFRhgweyVsEd/dkd10oTEUa8kPM42tUfGwu6ennTJj0BA2aapW28s20NsiLYgE3TokBuV0ybEhpmotHLcI0MrJo42eMvWpQp9NdNxVhHEmME101Jxi1g/TuFEha57Yh8uas6pf7WvCwXhwqOE7rq42Oa8f3c6OrcCxISeuZbsiiqqwcbNnhpXW7aT4TszYTVvXx+uj+1HHdZ6NYIhe4yYNFcLEOquOZxdTgsgWeb3ooM6aoP7rTBjMA44rORItHLcI0MrJow3PHkGBnUCCeOT05Gr46SQ8y6QLXSHSxMIMl/WhJX7bWFBtb1RiOkqK+YN3+/71KVebtCcZulqj3xWx5nyPuHDiboq0DAvRkXU86MFFFdxxU7oKiHZJqO31grqo0VLdiTdiEFwfCeahO44NOVVr4bhFgFZOHm14CjHo69QgHpxJ7DmEoc43kSa6sH44SehOa7bK9BY9SxnHjWBlWhQQGS1AXz+5YdmQSTGTDwfHsSEnro3uX4bZx3qd9V5IdNwI1EvibooO4XoIu9LY5ioaBhWpjuv3YKfE1Wp7XStTrbM6FvSjCwGBOjEopjuODTlVa+G4RYBWTh6tf94JtJF49FQVwE88pkVZ17hJmDOepzLB2Kd/tqOkmD94t+9fn5K1SbuSiC+496kyb+BI3E2RlmHBH9jUDLhPfgPKusblzWMNFbpBGDVr5QWF1Gj/iqmzFo5bBGjl5NH6Z49AG42z802Y1U1M1gS96xgFO+WwPlibIMr/jusNYYKhKBZs6rh+j3ZsRbfvX5+ytWy5bUEtrssECx47NpguzIY5tptYX0zEujIYhZtKQOTvuMldOWLTo3eQQYxJzUjhNG0vTm2C5ld2LpgHHFdyJFo4bhGglZNH658SAm3sVKEDBhs2Z5bE7ypzoTlXKdgJLgzaxkobH4JgwVAfDTqtUrFTKZ9KMODgIAsSedbKB1oN35duZcOgWXHz14pgv+lWbCe6/ZG4m1K/qxzuRkJH2CFmoDlHBg3nFWtK8E0Z3Kq2NxzH3yI7ONuKsMfEoJia7V8RddbCcYsArZxl0sZOcR2xvWrWbNIdMWePXtDy3STT6sMx4sGKXlgrDrRx4LhFgFbOMmk7yHH5tUv0qqO+c06na7Upu6mpNtDF/LaL1yoFaOPAcYsArRxo5UArB1o50MqpWgvHLQK0cqCVA60caOVAK6dqLRy3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWpvguBQBAAAAQLngGrcI0MqBVg60cqCVA62cqrVw3CJAKwdaOdDKgVYOtHKq1sJxiwCtnDpoV115VaXJDqPp5XXOS6dr//lbXzvyjdcd/ocXl56oW+rcDqPp5XXOS521lTmuvgeQQ91/xd34LHoHtNQJRO75oojcnkcjn3z8rmutbDi0cuqgJVO8a8eOihIc1+by0+naiuzWJOrcDqPp5XXOS5211Tpuwo3OiDyO61w2WrLIJw/H7WUtHDcbaOVwreeRpSc7jKaX1zkvddYuo+O6CK8KL2RjV7CexzZThTHfp4noQ1oS5Lp39URLHkylzns0jV7WwnGzgVYO13oGWXqyw2h6eZ3zUmdtWx3XeKp+dmO8ua2NWqIqsfjw+kClgrZt2FXYUseiQZozG5Q1EFD1XkkDWjlcC8fNBlo5XOsZZOnJDqPp5XXOS521y/J3XGOFzt+CjPE+/XRoVuvQ1RxTG9oojRtariYcVDXgLV33LqjmHA4aHz6LqvdKGtDK4Vo4bjbQyuFazyBLT3YYTS+vc17qrG3nNW7MUgN7NISGqQVBZ8kqG3Xdu5jtUudVbbI8YbpZ1HmPptHLWjhuNtDK4VrPIEtPdhhNL69zXuqsbbvjBte4cbhhaonpjofduLG2qml2MDpnVy+ilUWDVk5ZWjhuNtDK4VrPIEtPdhhNL69zXuqsrcvfcbk7WiIhXTAlFm8M2ayp1sPp3v2WJqjrgyDNmfUUn24WVe+VNKCVw7WtOO7IJ+544Iu/8OBXrt81dbNXZRIc1+by0+lazyBdUiebKH83Nei1kSQ7jKaX1zkvdda21XGDoMH3O+aHCtPSNEpQGc/VEfa95CAa/a5ygpzPqTl13qNp9LK2FcedevCGQyc2UppbuN6rMgmOa3P56XStZ5Au0bnE5Vet6qN/V17R93d7/62J6BPPipUr1b8mkpbsMJpeXue81FlbmeOKgVYOtHK4trDj3nPv+43dUvrc/Gu8WpPguDaXn07XegbpkrHSZw5c8bwXrurrs7b67Of0O9M1CY6bQbdq4bhFgFbOsmnXrVu3bds2W4hqiznujh0ffeCLv+Ac9749t3oNTKLO+dBdv84eXa/NOK48g3SJWyld3bo8xbnpNnVcHFfFqLMWjlsEaOUsm5bOX8Tq1au3bNlCRa4t5ri7Jn/X2e3+o0M7dt7Fa//yb9/zgY+89oM7X3PL+1/8ite+yA3d9evs0fXajOPKM0iXVq6017hXXb2yf1UfmS79S4n6MY5LmTfe8Hz3rxN6iaoIHFd5qbMWjlsEaOUsm9acngz9/f1DQ0NPPvmkqSrguCMf+/Dc8Vc6xx0d/wCvJbvdfm9Y++G7NxrTNUNv2rTJDZ0L7F85y6Y1u9XgHVeeQbp0RX94XctTX5913NnHf+zaa681fX7xqc28DU+mgQHHlZw6a+G4RYBWzrJp7ZmJ0dfXt2HDhgMHDqQ57o4dHx3bdfvHRv/Si1Pac+A/OEOdnHurV0tXt67WpN/94w12VI0b2k5OBvavnGXT2j3KcDvXM0iXqA39S5e2ZLF0vWu+JLX3Kz/qHJcSGe3VV1/94P/Z8PCZV5lIPClZFBxXEuqsheMWAVo5JWovX748NjZ2RxKNRsOek6LQGYquDNIcd+rQm8ksH/zqyz+1+308/olP/tmhEz9prHTuK68Y+fj/5rWUPrjzNabWpfd96KV2yAAzNE3MTjEKbQhtjt2wgB7fv7koV1vsuPIM0iVq4EUoGSGn6U+GbLsoTY+rS5cu2a0KwP6VU7UWjlsEaOWUqJ2amjp58qQtxLAnJMbGjRvNp3Bpjnvoq9ZWH/zqT43dd3sQv2vmkTc6K23sfY9r71LTa1w3dBoHDx48duyYLQT0+P7NRYnaxx9/fM+ePbYQw+5Rhtu5nkG6RG34Ba67zHUN4j8ZSkxKE6XpcXX27Nnx8XHvzVyP799cVK1NcFyKAFA35ubmZmdnbSEJe07SrF27dnJy0lZcuJDmuPse/iVnmQ9+5fq771V/rL33/mEXnP3Sv9uxczuXmJTxd1xv6DSeeOKJ0dFRWwBtZffu3fPz87YQw+xWg7dzPYPMTiSnf5v+ZIgnM6hBeFwRx48f37Vrly2AmoFr3CJAK6cUbfZViMGcmNasWWN+UMHHTXPckU/c8bkvhVercwuvvPvePznw6M+6yFjjjzyJS/HvKpuh5dvbaDQWFxdtQdP2dS5Ap2uXlpZGRkZsIYmM48ozSJ5IkhHxfjLk8l5SA+c/rgh6A0FvT22h8/dRXuqsheMWAVo5rWsTPyiL09/ff9ttt9lCdNw0x6U0MvrXB+ZDi3V/vqW096Ff9xonJuqcDy3f3vjbiPauczE6XZv48T4n47jyDJIn56MuszL9J0OmQTwVO64Mn9eYfB3WOS/dqq2Z41742tM7Xvf0HS8uP1G31Dmj6pVNA1o5pL148SLZLV2I2JAYPm6G41L6+D0fOnD8Z5zRmvTgV1/+sbsTvsMcT9S5HUYj3156D0FXV7SBttzWdba5/HS0Nr4LmsLH9QySJ+ej7he3GT8Z8iIu2WE0BbZ3ZmZmYWGBMm1f5wJ0q7ZmjluR3ZpEnTNanXN4I2eD9KbMpa2VBJpkMC+uZTeWFs27ybhulKS7U7eyvefOnZuYmPA+ehXCx812XEqfGPuLuYXw77KUJvb/ltcmLRV2XOLw4cNHjhyxhdbWClo5Tnvy5MmpqSmTF8LH9QySJ/Pi8qB44k+GuJAnO4ymwPbS+4k9e/acOnWq7etcgG7V1sxxPY8sPTFanbN23OBBC8Z+RaZb2lo1J2KAgTY+7/BpEWlkjtvkIRCtbO/evXvn5+dtISd83KaOS+nuT31gbuF6Y7cH5n92599t8xqkpVYcl66uduzYYQutrRW0cpx2fHz8zJkzJi+Ej+sZZGJy17jm33iqznGJS5cuNRqNJ554wpbz0/Z9VIA6a+G4RVBaz6y47xj/VTAzC4NBVEtMPlSb4OCgbTyweWugo5Z2zvH+zWQClY7641ltqj+agQe0yOsgfIYx6zRpFN45k6dPMotjx47t27fPFvLD96/EcSndc9/7D8y/eu74q8Z2pX5hKp5acVyCrkIef/xxk8+r5UArx2jPnj07NjZmInL4uJ5BJiY61F0m/pMhk1xjL9lhNIW3d2lpqdjfZQzt3UfFqLMWjlsEpTX+4WwjLIa2w5qEwQvD623WeJxXrXMmaj0rDA8OR8cNVaapipqcDrJ6wmwvU3uYgYPW/ijrg1GslnWdmA1z7hnGKZNM5tSpUxMTE2UdV0LHLZZadFyzpSZf1vbmpTe1s7OzBT5B4eN6Bll6ssNoWtleOsbIdON3xpDQ3n1UjDpr4bhFUFrfu6zHRMKuwFwpHFcHTVPPqqyeqUxPdK0Z6d81YFEmYtlg3EgoQqQmeRSDLmpSB+TyC85ykyeZwPnz580JotV9FFBnxyVGRkbMJUhZ25uXHtTS0bVjx46mX4CPw8f1DLL0ZIfRtLi9i4uL9Mauxe3NC7Rx4LhFUNqIKYUeFQ1bZ9FB6zDhuLrSdyAW5L5kug0cN4JqzEZlIpYNxo1OjxNpnDGKacSmmTAgH+XCheF4NDJYFDoVkt2S6VK+1X0UUHPHPXbs2MGDBylT1vbmpQe1bs3zwsf1DLL0ZIfRtL5WBb4mRrQ+bjG6VQvHLYLSet6li57ZhAXmMOG4ia7FglxlevKvcR0sykQs68aNxDiRCm8Uo+XB5FGCLG+Z9xqX3omfOnXK5FvdRwE1d9yLFy/SZS5df5S1vXnpQe3Y2NjZs2dtOQ98XM8gS092GE0pa1XgfUYp4xagW7Wd4bh0ek7Da9kkMVqdc9SUQgvRcZb1LSbJgXStqdZZ2y3zJdNWfYOJdRpmE0fi2XB7WVNbYAMHjRNH8RtnDMiaen/HjWkieLcjKOu4qrnjEuank2Vtb156TXvixIlGo2ELOeHjegZZerLDaMpaq6Z3/PBo1z7qVm3HOK5twKCgwWuclRitztmYSgjzj7DK+IuGtw/aGuOi8qBzIB2yMuZLxq3sd4YDGWF7SjEz1z8V2fZGpm6bRnQaNsr6YaMNhWzGbBTeR9g2WISUSTq8W9MRZR1X9Xdc873ZsrY3L72m3b17t/t+eF74uJ5Blp7sMJoS14p/Pb4p7dpH3artBsclvPapiVH1yqYBbSKJ3+woa9z6Oy5BjovfTcoprL148eLOnTsLfIfIwMc98o3XeR5ZYqLO7TCaEteKtp0u8YU/RG7LPiK6Vdtbjrtu3TpzO3Ki6pVNA9o45ieD8ZvtlTUumWKlyQ6jKTxnusTfu3evLeSn6n2URsdpjxw54n2Ukgs+7j9/62sVmS51S53bYTTlrhX/fmI2bdlHRLdqO9hxHXLH1e68YvXq1Vu2bKl6ZdOA1oPecdOLP/FrLD21VrQOd911V7EfTRI9tVZEYe2OHTtOnz5tC/npmrVKe5vr0TXbK6RqbS86rqG/v3/Tpk3Zj3dOo+q9kkZXajP+qtRra7Vv375c32rh9NpaFdOa5zVhrQySp3JhreRItF3luC6TlpTTRunr69uwYcOBAwdsXzKq3itpdJ/Wu5W/R6+t1alTp0ZHR20hJ722VsW05rdnWCsHrQa9BckwXayVHIm22xzX5ROTaeBBpksXu41G444kRkZG3M9DHVXvlTS6TNv0J/k9uFbxx9QL6cG1sjkx58+fN29osFachYWFmZkZW4iBtZIj0XbJN6c8PLlLtpqxcePG7A+Wl5aW6H0xwW8FXvVeSaObtPhEKw5pzceetpyHHlwrmxPjfoqKtfLgj6/3wFrJkWgTHJci7cIzSJfIGu3kGMYyE/HkLtlqzdq1aycnJ+3AzTh+/PjHP/7xubm5c+fO2RBogdOnT4+NjdHFnC2DADrAdu7cSetjy6AksLDZ0Mnw6NGjtgAqoxc/VV6zZs22bdvyzpmuxg4fPkw+gb8D5SKupZUU/hywN9cq44Ijg95cKzn8s1OsVRx6Ve7Rj6+35QCslRyJtre+OdXf33/bbbcZVbE5nz9/fmJiYvfu3U2/VZ9GaWuVk/pop6amTp48aQuZ9OZaudssm6CQ3lwrOfxGymWNe/z48enKoM7tMJplWCs65OK/01uGcRPpVm1XOW7zxGhlzvPz86Ojoxlfss2grLXybsJQerLDaErbv/r+A4cPH7aFZpQ4bi7ars34xVQaPbtWEshFyHFtobxxrTe2zN7pvZ/d+9mpvVO2HGCH0SzPWtG7PTJdfGelGBItHLcIpL106RI5B/lu3m+WlrVWZIre7QZLTBU57in29HUJZY2bl7Zr8y4U0bNrJcF7+HxZ41pjnJ6emZk5dOjQwqOP/v3Jk184euTAgc/ZCg2N/vDDnz+hoQwVbcX09NT01O27ht+z6+03feaGLRNvveXed3xiz05b1w7HJdzTqU2xwLjsjuyxm6dzEu+uHpA6rrthe6AMhgtvYr9sa+Uh0cJxi+C0dHQ2Gg16vck/ZC5rrTrOcb1XsoSy1iovddDSmzlaMVsQ0MtrlQ0dct7D58sa1/jivn37yGX/aWnJpW+cOX3w4AFTS/5KNsxrqehM93333XzT3hve+cCNLr37vrd9avIeU2uH0SznOp85c4ZOa2bFcmrZ40r4c8MSacFxBwYGgo5VWRXhuEIiWs8gg6TewWTitU9NjBJXdmFhgc6PwrsFlTVuZzkunfXGxsb4p1USylqrvNRBS4dTrkeZ9vJaZRNfybLGNb744Nzc0oV/5J5KaSH4Ey9d1HpVlChIVfdPTbzr06HXmrRl/42/v+tmo7XDaJZ5nd2v1PJpoyYa0bprU2eNvHGs9sKFYVWtvZS7aeDpmwetlHoZ3Gxiuk3YUzQ0MDhoKlxfCS3tuwQV0AMHmxKbnp19dHqSteoMxy0tMUqbs4YchV7VZCpNv4Jb1rgd5Lj0ZnliYqLAjR3KWqu81EEbvzLLppfXKpv4pwVljWt88ZFHHvEMldK5s2f3799PtSdOnPCqKFGQqkYnR26afovnuJRubbxDd2xP7YblX2fzTiWX1rphMHGmDd01bBPGEmqt4zrPc9gWWzcP6E6oqAu2T1Vrn2rqdarrTc4FtSRjcn6QteQNAiRrBcctQprW3NVhdnY247PTssbtIMelBeF/RZNT1lrlpSZa85h6W2hGj69VGol/ES9rXOOL3eq4BDnuQw89ZAsCmCEp3LjMs1ghaJ1Yax034miaoAGpVaX+X6QHGnd4vXJDhQ6yam+G1jcVqp7341pGOg/1fk+EZJ3huEXI1pK7jIyMpHlMWeN2iuM+/PDD5Li2IEcf5pzgkJdS3f7NxmrV/KMvRwHeuN43bLNp8/YWYhm0id/6Lmtc44td+amy4/777xf+lo+ImBMbNxoPvCr4f2JtU8el//N/bQ86t2LFepLpjsKgzjGftC1V3rVkDU1e1dqGDN0i7MkhWWc4bhGaaukal2wm/uM2oqxxO8JxFxcXd+3aJf9oNEQd5oPD4bh0fNtXgpBK928G5Wr5r0iz6Y7tlSPRpv2yuaxxjS923zenOOfOncvxJ6GoDblxuZOFhaBxYm1Tx1Xywa36nzBmMomfKpsBXJDFcgQZYfcOyTrDcYsg1J45c4bOmAcPHuQfMpc1biuOO/KJOx744i88+JXrd03d7FWZVIrjLi0t0eY/9dRTtpwLdZhzx9Vlc/jbr0CYg10f9wp37FPEfJOCCF4nzVWEC9pXbHIzF0sJ2jkH89VDq6952Oq4Rk3MzjO+ztl3meeUdVzlpc7atLt3lTWu8UWim34d5EFaOn3RxYPsm/PquHcvO/MtJHXM67B7QdgW+hWQVtvccSkTvHZ4jETrh2l7zetLD+Sqk8dMbGmC0Tkl9xQiWWc4bhFyaY8dOzY6Our+IFfWuK047tSDNxw6sZHS3ML1XpVJrTuue5UW3F51aDPHVcXwJeGOczrqw1eCjepXwsDmBmlVNnzNxFUsF+1gYIiCrjJaZ3OpwfXDQU4HVSY+HMtSLsjG14quz+gqTfLbs7KOq7zUVpuxdGWNa42xZepzB4w4RkvvnhuNhuy3BvqID7AvDCIMs9eAaxCrbe64iTnW0eBg0AGrZmMmtQy/q8xjVmaIhIKCQbLONXPcHa/zPbLERJ0zSpuzAHrZ07tgOmSLO5CGaws77j33vt/YLaXPzb/GqzWpdced0A8ipUzB7Q1fDhZ7bKu4O8zpoLevT503cfVKoJwel1q7VyRXxXqINDDatM5d0BEJ2u11HfKew7zrkKColSeu1cHgiTfZFFxnTVdqM57CVNa4XXaXx0Sc9uzZs3QGy/hOaJy2z7kATksv0YTXeiaScWvmuBe+VpXpUrfUOaO0OYtZXFyki93ZzG8ye6xbt27btm22EB23mOPu2PHRB774C85x79tzq9fAJOqcD513e/lz5guuszYn9qlyADcw/aJgmNeH9T8zrnW2ZNszBa0K/m/Q2sTOjTwaIVjQfiLtRnEZLxiqw0LiWtG7NDpsbCGdguus6Uqte88XB2slh2tpPelNTDf/Yk29Qh3sBS5DMm7NHDcnnaidm5ujE6jwrrlmz69evXrLli1U5OMWc9xdk7/r7Hb/0aEdO+/itX/5t+/5wEde+8Gdr7nl/S9+xWtf5IbOtb3ec+YLrpU2J4HjuryDO25gZqkq2zjawGgTO2cE0ggqqD6RDjvkPYd53jlFbUdpa5VhHo6C66zpPm322xSslRxPK/9iAdHja5UIHLcILWovXrxIbxXpNNr0ywjGcQ39/f1DQ0Pu+fkFHHfkYx+eO/5K57ij4x/gtWS32+8Naz9890ZjumboTZs2ZT+638DvD2couFbanJo5LnO9SE59rKzGdcHmKtZCZe2vC/xmYSgjKHFcJqJckE1bq4wPSB0tHpM2l596arM/isdayYlr076PFgdrFQeOW4RStHTVMjY2dvjw4YxPaYzhcfr6+jZs2HDgwIE0x92x46Nju27/2OhfenFKew78B2eok3Nv9Wrp6tbVmvS7f7zBjqpxQ9vJxVhaWhofH/e+q1JwrbQ5NXVc41eaiOn5N3RLVSV3Ffuusus8DHEtD9o5uxH50JFpBCL1xeomjkvQfs3+/lTbj+cCVKSlFxQtV8bfbrBWchK1s7J72mCt4sBxi1CWlk4NR44cufPOO+9Igi4WzTnZg5yPrjjTHHfq0JvJLB/86ss/tft9PP6JT/7ZoRM/aax07iuvGPn4/+a1lD648zWm1qX3feildsgAMzRNzE4xyvbt26v7/bEYcjJlYHXYvyKYDWdom15YdMz2MirSkhmQJdhCElgrOWla/KUjjkQLxy3Csmmt0TE2btxoPt1Nc9xDX7W2+uBXf2rsvtuD+F0zj7zRWWlj73tce5eaXuO6oXOx7OvcEY6rbDYgvIDO0NIFbvZj6uu9vclUpG162xCslZw0LR2KiXf44WCt4iQ4LkVATbDnZM3atWsnJydtxYULaY677+Ffcpb54Feuv/te9cfae+8fdsHZL/27HTu3c4lJGX/H9YYGbWH37t109WYLIIUnnnhidHTUFkCVPPXUU7TUi4uLtgwE4Bq3CMumNYa3Zs0a80Mdrk1z3JFP3PG5L4VXq3MLr7z73j858OjPushY4488iUvx7yqbobt+nT3qqaVTW6PRsIUYWCuD5PEPWCs52VpzX7m0P5ljreLUy3F76hflEvr7+2+77TZbiGrTHJfSyOhfH5gPLdb9+ZbS3od+3WucmKhzPnRHrJVHV2ozPi/FWhEJn73zz+8t7ptxjMiX2rJIGLcVbSKuQ9ZzaWslnq2h6bjxnyc4SptzTuqsrZfjWm9smfrfNa0YXJvhuJQ+fs+HDhz/GWe0Jj341Zd/7O6E7zDHE3Vuh9F0+lrlpbba+MPVHVgrImF9kgwmQduKa7aiTUQ4ZzERbdmOS6T9eq2sOf/D0sUbPzn3+p0PvH7n/lLTA9QtdW6H0ZS2zinU1HG7+87gNpcfrs12XEqfGPuLuYXw77KUJvb/ltcmLXWC46ozh7pgcd87ijA9lOu8EqX8OctOc+layzXXXPOnf/pnf1jD6wmaZP7lzhq3WYeJ2tHYw+cTV5609vt1tl7fQ1ehH7XKH3qhqi2mFz2u+zkY9eHy0VFcmMXtvYJ5UA3nPeiCdRhOno7nsJ2aedCKHf+xmWR2bpo0JWsfMRK/Hy7UJsK12m49sywtUeet3F+PI9HW0XG7++lXZWmbOi6luz/1gbmF643dHpj/2Z1/t81rkJY6wHHDk1Ei3ea4wYl1evitb3rFK3413lVV69wMrdXn8fzLnT5u8w7j2lNJD59PXPlgzhQ3/7JmerUDAdW6hbcNLlxohD2a+oQhgm6j4w+vt92FQT2cHcON5qpZO3WDfSZheZNLUJuWFFTbm1AtIn0f+fB7uxrk2jhcW8HVLU8PqHcghe6v5yHR1tFxu/sJz2VpJY5L6Z773n9g/tVzx181tiv1C1PxVD/HpROGwZwsXNGerAKC+MDg+vC84mkN0R74aUjl1T2ndC73hcWFBr8aMdFoG1eKzEeRvFbBedOUzv7x9cPDw1apqzTsb5NhMFDpEU1eZ8NpuHuFUPXWQBduHevfxsxk2B1GjANZPCWfpclHO7TbGwZNB37ZU2m2rlelAR23wT1JD5/nnVnMc6WCGitWBT1Fl/Gh9VJxtX+9BgkSauym6qA5h/P3nZ7nEyajr3GtlqK8H5PnI/qdq3VO6FNErtfv1NQUf3x9Lq0H18Y8suRkjguD/P56cSTbW0fHfeSRRzxDpXTu7Nn9+/dT7YkTJ7wqShSkqtHJkZum3+I5LqVbG+/QHdvj0VDWnPNSllbouMVS3Rw3PJ24XNKJI9IsOMknaLnYBHlvKu8cN2oVYT6i5jF9Ro6NGEooZLWsG0vyWumhbYe6eNstt/zgv6eLOerKTok1CYNhVmf8ap0zUfuEsjCc3qkO6qjJmXtshfUOXW1CqlblYh362jDLOwzzvAPluEEL4uLFizt27LAFjtKEzQx2nVWV6Y01i7XXwxtU3LyjMiJL0hA6aHCtzZwdOs618TmEtRLH5UQ6V9ub0KeIXK/fy5cv0/sed2eMXFoPrvUMsvRk14zR9P56iUi2F45bhDpoe8lx6WzizhHBKSbhxMGbuU+VZVoeUXl2jWuPGp4P+gkzJq96iFwDuW7D/rnEJ3mtlJZrtm7euPGtWz4YCbsCdc+NyKCDpmlYz4IXhpUXGJXrKdK/k7GoiaU5rm6pG6rK5A7Vk8OTpLzDiCosaPdisvhHmhYl8bs360xjqD/gmkrXLNJeTcMWgrjsGpdBfdjp05zNccXg2vgcwlqJ48bmEMjV9ib0KSLv6/fSpUuNRsN8oz6vlsO1nkGWnuhQipN9f72xsbH417Ml24tPlYtQB20POW7kHBGcbuInjmiETEQV0rTulGXgzVRe7rgcFWzmuCYftuckr5VuHzad3vzcVav++M+3Tf76i1jYOpDp222wRU+TzVjXs2C640ZwUd5VquPqptTS/o9vd8DAUMMEfSnrkA3I4xHHpXNf6nP7ld7vXq0zxe32uMm58YL2fl61jPwd1zTgzQw0TT7lIO/+jhsGE4eLZ5o7blIukNvt9fsUUeD16x5fX0Dr4FrPIEtPdCh5NL2/Hh1v8efzS7a3jo6Lb06lwbW4xo2dOHizZbvGjfZDc27quA7XTUDyWikta6iLv/nnBz/57p8Pw64N9Rk3MB10M7b1LNj8GtfBoqardMfVbQe3Up1pH+9QbW+yNIxGVGEh4rhZz1bSEo/1w7FvP9l2vn2Gav23a6rQ+0hPT0fDLWMqwrXgcfZdZb5FQYMwH3TIIk0dNzarsEM151jnukVzko/JZtA1LpnuU089Zcv54eN6Bll6MqtmWLt2reTD5PHx8TNnzthCgGSt6ui4BH4dlAjX9pLjsvOKy4VnkJBIs+BUl6DlYpuN1kkdNyHXxHFDQTSvSV4rPSEuoi27fWlpZNufu/M8a2Lqg+mbaFita91MAk2i4/JOE4NmpAzHNY2D5gkd6m97JU04FjR51kHEcenkvri4aPIS2n48F6DjtKdOndq9e3finTEk8HE9g2ya3vCx2S0PHP/DL//Dn37lqT/80uI79x9/w8is14YnOpSIXPfXS3yQg0RbU8dtEdwBo8VUN8e1p2BFcJZVZ98gH2JOz3Razvld5VBJ5c3B39soFrhFJE9ang90OpLsuLZ7lXeC6HwUyWvlZmaxKvXV3F3/OahK/q6yGyEY1PzyVEd1yEw62XGJ+FxZta40jhv2b8ezRDpTRDu025s5YVUOG7i+Qsely6mxsTETFVKD4zk3nag9duzY1NSULeSEj+sZZHb6xZHZ3zvyNfJanv7bkVMU91q6VOD+eok3E5Vo6+W4uMtjNlzbY46bm67Xeh+l9uxaZT98PpGeXasCtKg9cuTI4cOHbTkPfFzPIOPpV7ft+U9/9Sn6l/Lv3L/g2a1Jvz3zKJfwZIfRCLc38Zt6Em29HDcvvawlU6w02WE0vbzOeVlOLX9MfW+u1eVmD59PpDfXqhita2dlj6/nN34i+LieQfL0lr/59Gfe8TuLb3jjP7zhjYtv3DT5m+/54IEve15r0h98adHTumSH0Qi3N/GdhEQLxy0CtHKglZNXy1/2vblWTR8+n0hvrlUxStEm35wkivmzgbnxExX5uJ5BuvSmj3zm0V9/C3ktT4+95W0f+vxJz25N8uQu2WE0wu1dWFiYmZmxhQCJFo5bBGjlQCsnr5Y/Kqc316rpw+cT6c21KkYpWjpEG41G/Mu9HOO4hv7+/qGhIff7HM8gXfrEe/67Z7cmfe4P/4fntZRunz/tyV0yoxiE25t4S1GJFo5bBGjlQCungNbdV68H14rO4OPj47ach5LnrL7Y5X1lLMLW4DdkTcbN7KfkOYspS3vp0iV6exT/DavDmi3D3fjJM0iXvvqrv+F5rUlP/vpv/PXCg39zfO9fLHzFOe7vHDzpyV2yM9AItzfx2JNo4bhFgFYOtHIKaN1j6ntwrby7+Mopec5w3BQ8Ldnt9u3b7U2botAxbG02irnxk2eQLnlGa9LJ//rvDs294uCxl5u068u/+2dfefz2R0//8t0HPblLdn4a4fbStoyMjNhCgEQLxy0CtHKglVNMaz5Z7bW1On36tP/weTElz5k7pcpbnHkqxw2eB8gc1f1Simu72XGzsYvBcDd+8gzSpeO/9mbfbt/7885rXbr/izf+xidTL5QpmQkYhHOmA+/OO++0hQCJNsFxKQIA6BQeeuihffv22ULPUKOtVr/AXj+scuo2jkMNL6h/7WzC0aAfY7U9iLVZzdq1aycnJ23FhQueQbo08jt/EHHcN77x8OfCq1uefm/if3hanuwwOSHHPXfunC2IwTVuEaCVA62cYlp6u719+3Z68dtyfjpxrXbu3JnxR8FsSp5z8rWp+yw58qlykKf/h3fzsDFc4wY3fqIi13oG6dKv/e3ksTe/zTnuE//59Z7RurTjwH/wtDzZYTTyOcdvrSzRNnNc9iFJQMIxkWdl/cNKv7NzB1z8YxdWxTCtzLjugM5F8pwzD3pHnu31gVYOtEIOHjxI13y2kJ+O297HH3989+7dtpCfkuccPWnos5bBBrcOWnMlbXCyYq0UukHmyact60wsm5bf+IngWs8geXrTRz5z303v/T+bNpPjnvydIc9oXRo79OuekCc7jEY+5/itlSVaieNGDgIV4Ldt0+RZWb/HqOMODAy6zulAHWBVXKSOVyqbcct0XBnQyoFWTmHt2bNnR0dHbSE/kXG/eeLp4y96+ksryk/ULXXOKLy9e/bskdxUIY2S91F4drLnpWgwPEFdCJ87lHTS8s9yEUqes5g6aD2DjKc33jV944d3v+3jY57RuvSRB37Lk/C07rOPpSU7gyTit1aWbG9ux41G1BGmYc99VA0sTBm0DB7B4Yg67iBVW8ud3qwKrIqJdGRgc0NPXh28CV9M0Khmqpegxk1Y3w9WdxIYvC5sTdw6EwknoeccKKmVybrmsVlw6nAE5wVaOe3Sjo2NZf/eMYPIuBXZrUnUOaPY9pqHz9doH7kTQ3iGMHl7ilAnBh0Oz3XstBHmuDxGjbZXTFlazyAz0j0PvsnzWpO23PcRryVPnsvyZGeQRPzWypLtbeka1x0qiQcS10YOr6gjeY67deugqSXDDf0v4VhUXZq7t6su0w5ZFQlDbhoqvH5Y/5/NlrKsh0jjYBYmoqbMfFgHqbkVsj4SqMMRnBdo5bRLW9Zd432PLD0xim2vuaVtjfYRe8GrrIFdWqhTg70kCM42CnXeigQzTxw12l4xZWk9g8xIb7vnnr1HXuPZ7V/PvMdr5iXPZXmyM0gifmtlyfbm/ztueMw4S6KRhhM+JAlNKHSj+GHlOy79q0r6f66tLyIoFDquq+N5RUQYTpjy5vkwqhcdspmwfaSx7TVoPbx+YPNmE3Md8PZZ1OEIzgu0ctqlPXfu3EjaU9mbERnXM8jSE6PA9l4OHj7fifsIWjlc6xlkdrrh7ns/Mvtb+7/wMweOXb/roc3//f4/Hdo547XxkueyPNkZJBG/tbJke/Nc45KnRExFlRlhFasIjMp1EtqXxXdc+p/6U66+1HXCaA8a5XCB40aGjrSLCJMmTA3U/+3/WPukxrZ77da2JRtQRXjjZOpwBOcFWjlt1MbfdAuJjOsZZOmJUWB7T548aS7l27jONpcfaOVwrWeQpSfPZXmyM0gifmtlyfbm+1RZe4orhmbDOlFGZaMR93KqaI+k9R2XWqsrSOuD0aoQ6pL/HdfWxdpFAnwabs7UQv/51rhk2D7S2KGimzcPuE+k7ZVuFD23NM+V7JU0oJXTg9rE++BIiIzrGWTpiVFge90XRNu4zjaXH2jlcK1nkKUnz2V5sjNIIn5rZcn25v07riq7gHMW/XNuz7FM3jpP6EGUY6ZNxB1Xt9HNXYR3q1AtqGwmbwuE38yPRKYxMKRzuom7LGXto41NzgymLq4pa4Sx1k9vvpLCUZy8nKPQjMx7bU6Ocd0iBJky5mzIN/Pyxs1H52olD2mJExnXM8jSEyPv9vKHz7d3nYsBrRyu9Qyy9OS5LE92BknEb60s2d68jmvPmcEZU/tP9BRqz6kqxr+WHISbfVc5PRPB9GAmT5NI+mKCxvVgCSdsPpFWqDaBMNI+YetMY6tV9WHnrrUN+kNbSjgKU3rOJse4sf5LmLMh58xLGzcnnav1HlMvJDKuZ5ClJ0be7eUPn2/vOhcDWjlc6xlk6clzWZ7sDJKIf6Qk2d5mjiujDnslL5VrPXehov2dkv4llaq12EaqgfqUOhIkQifXv2jy3we4YqAIB6JIpFMlCJqHbyL8mbAOVZWK6e1NHChpwiGexBXZO5hMuvbYSKEUbfxWOE2JjOsZZJDiHB3z24gSI9f2mltruRspt32dCwCtHK71DLL05LksT3YGScRvrSzZXjhuEUTawK4s2tiorLXkPYHruGa6gY2G9ZSznah69ffjSM+RhiYXDKQJC/qzhKAi7CFtJpEMzTltID/IMDG1vRGJGVdE5fsohY7W0lUgXQuavJDIuJ5BBolw+StXqX+vWLniC4HpGlauVP+aSGpi5Npeb7vavs4FgFYO175+5wOeR5aaHrDDaHLNmRzXvQUkJFo4bhFEWs9dmHvZiIXsKGJvijAfsTKrjdQGEtcyMi4VrFzf78Z1Fek2IDaTIBP99VfSQJFBDbY3PefEuTWn8n2UQkdr+WPqhUTG9QwySMZKn7V6xbc9f0Vfnw0+b01ouiZV57jew+fbvs4FgFYO1974ybmYTZaWqHM7jCbXnL3PkyRaOG4RRFrPXUL3slpyoQDdLM3AVN4Q/P3Y1fJmqhB3tSCoxk113NSZBJnwb+2KpIF43uC0anuTJAJqvX9TqIO26YNj161bZ+4Xb4iM6xlkkAiXp6tblye46fJmiYkPLd/eYt9SSQNaOXXQ/sPSRW26pV/pPkDdUud2GE2uOXu3VpZo4bhFEGk9d4k4kPI4W+ea8faJzqRcUn+/OqylkGsWmGhESwXrrCmOmzmTIINrXDl10Mb9yUMZ44oVq1ev3rJlCxUj48Y80qSV2mXpGveaq1as6lemS/9SIozjEv/pl8N/ndBLBjO0fHvj7yHqsM55gVZOR2i9WytLtHDcIoi0nruE7qXv5+yqVD7dwJwz2rznuKze5Xg/qmDrkx3XHzQaDDI05yYD8XyAaai2N3luzal8H6XQBVrvM1gP63ua/v7+oaEh8+hvRcwjTeq/wo+Y1NdnHff/e3jFtddea/p8+qvreRueODT0pk2bwqFTSPycvMf3by6glZNL691aWaKtwnHVaZWwJ+hm5JgAnbgduvdAyyvMCT12aqdAZELT+ntE7MdKecxANGevw6BotKpkcDPg7VmebZv5rrLXs6tP0OqC3ey0T5VVc0N0LVSHQVd6zpkD8XxI9tyak+PYiNHj2vn5+dnZWVuIYXcLo6+vb8OGDQcOHPAM0iWC/qVLW7JYut41X5L6f3Oh46r01fVXX3315S+uePrRNTYSS3HCoVOI306P6PH9mwto5eTSend5k2grcNxqzqqqV9atOpfbe06prKtQzbSVUIY7rFfU7djzjggVkU67lUWDVg60cjwtXRFu3779jiQajYb1uijkfHTF6RmkS4QXMSniuIKUiBmaJmanGIU2JH6/6B7fv7mAVk4urfdeUKIt33GDyxpz60T3w1AidsWjfXBoaL2JKkcMmkTcUUEVXkx75nD0E1pF0FL17RSRApsJezxfpJ/4VCMs2x71gFYOtBnYo5uxceNG++luzCNNIvgFLk8tOm44dB6wf+VAKyeX1ru1skSb4LgUaQn1vVayQpMxOYW6EeQQXZTyHGthfi0a5p1OE0riaGVCLcWDKMta3BDxDBuNxQDoHozVGdauXTs5OWkr6GwQ88hyE8cbGoDO4vjx47t27bIFGQmOW4BIJ+5i0b9q5HlzxakuPcnadJBfhroGAVzNCMd1F6VM6HrkXVvU3Ny9n7zZ8tGTB25l0aCVA62cXFrzUlmzZo35oU5EG/NILxFehKfsWkoGM3TXr7MHtHI6Quv9KECiXS7H5XlVCK1Q5Li8kpEweTVQ0NSqksSqWYbjchIGbmXRoJUDrZxc2v7+/ttuu80WPG3MI3kizL88Q3hB+jct8aG7fp09oJXDtXQpOV0Z1LkdRpNrzt6tlSXaDrnGTYio3tcP61+euI41LEBt9Bdu46ap1ZFJuky8xxitLBq0cqCVU5o25pE8GTfdv91miP83Z/M8SP+mJkZPr3NOellrvbFl9k7v/ezez07tnbLlADuMJtecvVsrS7TL5rjMM8MctRA6ru4s2hs1aahxVZY5ZERLqsFB9sB6h+ouzXFZFwkTUWQtGusnhAVbWfBQmzhKJhfUr4NyagLKmbOHYBMqGVdAT2s9g4wm56Ymw/+NF5MTo6fXOSe9rLXGOD09MzNz6NChhUcf/fuTJ79w9MiBA5+zFZrZ2dmHH/78CQ1lqGgrpqenpqdu3zX8nl1vv+kzN2yZeOst977jE3t22roWHJfgt1aWaJfPcY01alyQWkgdV+E6IHR9MG6swqHmkNSViqc6LuswSZu9spF+EmhlwUNts1HiwHHl9LTWM8hoIlzmq59W/xooz4OmTXJi9PQ656SXtcYX9+3bRy77T0tLLn3jzOmDBw+YWvJXsmFeS0Vnuu+77+ab9t7wzgdudOnd973tU5P3mFo7jCbvnPmtlSXaChw3J52tDb3emIcrm0+zgx9HOXdRwaGkJ9wFQiUJbN7v3I3LRkkoerie1wc3uGDBiMQF9QSYI+ovbZu82oAmj/+Ldq7mHBGZjqITcKVgREP7929+Ol7rGWQsEV6Ep+xalRg9vc456WWt8cUH5+aWLvwj91RKC8GfeOmi1quiREGqun9q4l2fDr3WpC37b/z9XTcbrR1Gk3fO/NbKEi0ctwiBlozCOkRoTy6nMrFqHbTmRGrmrWHQZhM6D+fsQp426NDhYuo3T8F8kiSxHlkg6rhBLzrL8hG1i6k565b+iKGEQlbLulG0e/8WoeO1nkGWnhg9vc456WWt8cVHHnnEM1RK586e3b9/P9WeOHHCq6JEQaoanRy5afotnuNSurXxDt2xPi8F5J0zv7WyRAvHLUKgDf0qxJkGd49IUH+azYPMcnTU9JnQeTjnZG1cEtayT5WTJGGHASziX+PaIXjeDc3noAYapjnzzl0+DHJJhE4+NopQC61nkKUnRk+vc056WWt8sZ6Oy2+tLNHCcYsQapVtGALPSHAULxhzXMqEjsMKqkGk8+i4sVGiHSlYLWmVAVIhURKTRrT5HJej/07PugrzftC255No//7NT8drPYMsPTF6ep1z0sta44v1/FSZ31pZooXjFiFB6xwn1VFcUHiNywg6D8dN1rpJOMLaZbzGjfSj5sw7d3kedLhuNDXav2I6XusZZOmJ0dPrnJNe1hpfrOc3p/itlSVaOG4RrJbbg8snOkokGHdc1hPlTDap83DOaVonCXCxHH/HtdmwThmuraQ6NwbPJ3Wpc+oXXKzvMO8yoSCab/v+LUTHaz2DLD0xenqdc9LLWuOLRA1/HcRvrSzRwnGL4LRkEAGBo2gnUcVUm0lw3LCnwc3OxuKdszkHo6i8a+h645iW5OM5v6scKlcMDA0FV64Uc5bI86TleaujiJqz6igYKMyb7lXeCbxNaPv+LUDHaz2DLD0xenqdc9LLWmuMLVP6HTCIU6dOTUxMmLxEC8ctQoVabk4xsFZyoJUT0R5/ke+RJSbqnNHT65yTXtbW9i6PBL+1skQLxy1C2VpztWdwV4oJYK3kQCsnov3miapMl7qlzhk9vc45gVbOcmr5rZUlWjhuEaCVA60caOVAKwdaOXm1/NbKEi0ctwjQyoFWDrRyoJUDrZwCWndrZYkWjlsEaOVAKwdaOdDKgVZOAa27tbJEC8ctArRyoJUDrRxo5UArp4DW3VpZooXjFgFaOdDKgVYOtHKglVNA626tLNEmOC5FAAAAANCUycnJo0eP2kIzcI1bBGjlQCsHWjnQyoFWTgGtu7WyRAvHLQK0cqCVUwdtne82wIFWToVadru4+K0EItrMe/vEMVrqPocmoMj2BtNj95CX4m6tnDou23Y4bhGglQOtnDporTe2TBV31ONAK6cirb5xT2hOynyjphvRdorj5te6WyunauG4BLRyoJXT6VprjLW8azwHWjnVaMkNvatabqru4jcIRBw3qXZgcDC40TphxlWOO2jbmorQg5UkOr7r1d27XpE41ubNkWjYZth7TlrQTg0VtGLDqtB11133zne+lyRqzpmdUwGOWwRo5UArpw5a44v1fDIaB1o5lWjJRzzDY5hKpXXNyIoCzwulkVpniQozLtX78q2DTmszFmprO+AfDCeMr8dynXjV0SeTBnPSWZY3Oas+c+bMR//kNoqpOWd2TsBxiwCtHGjl1EFrfLGeT//mQCunEm1ocHFsndYGthO6DlfGay1mXK+pzlun9Q3XdRWZcxgMO+BjuXyQyfkscJXRt1b+K+p8mMbN7JyA4xYBWjnQyqmD1vjiI4884hkqpXNnz+7fv59qT5w44VVRoiBVjU6O3DT9Fs9xKd3aeIfu2J60DL28znmpnZZ7kEdgMFobtEuyn4TaADMut1VmmBSMGS6hOjG4OhJxYmO5fJDJ6biKVatWfehDH6LOhxpw3HSglQOtnE7XGl+E46YBbYAzHoczFmuOWhs0C13H1mritRYzLmsatqDc4GCC4TouDK8PpsbHCuBjuXyQyem4th9za2U158zOCThuEaCVA62cOmiNL+JT5TSgdSgfce6i/cdZsDElpXX2xFzHxRJrDWZc1acJ8wYqH4zkCDvljttsLJcPMnkcN8yN/NWfPm/dmxs058zOCThuEaCVA62cOmiNL+KbU2lAG4E8x+EsSeEqYvajyK5VmHGpXfBdZd47tY40NrC5JH5XOeiBjxXmVY7m439X2Q7K89QhzytuueW2fz9xRs05s3PKwXGLAK0caOXUQWt8kcCvgxKBVk5VWvKvwNQSWf45m1srS7Rw3CJAKwdaOXXQWmNsGdwBIw60ctK0+mqRX+8msPxzprenCwsLEi0ctwjQyoFWTh20uMtjNtDK6R2tubWyRAvHLQK0cqCVA60caOVAK6eY1txaWaKF4xYBWjnQyoFWDrRyoJVTTGturSzRwnGLAK0caOVAKwdaOdDKKaY9derUxMSERAvHLQK0cqCVA60caOV0iZb/8CYJ9VMiXd1k3Mx+is35zJkz4+PjEi0ctwjQyoFWDrRyoJXTJdoaO66+tfKIRAvHLQK0cqCVA60caOV0iZY7pcpbnHkqx40+2k9jb1KRcbcNTrE5X758+c4775RoExyXIgAAAECNUHeDWj+scuoujkMNL6iiNhwN+jFWWyLkuOfOnbOFdHCNWwRo5UArB1o50MrpEm3ytan7LDnyqXKQp//zOzLqWAXXuMTIyMji4qItpAPHLQK0cqCVk0NLZw+HPqUUH1edgPh9aFNxZ7QQp808i6WRMGdxPx2wj2JAKydBGz022CvABt0D/EgbHKv8dULoBpnHWOE5j4+PP/bYY7aQDhy3CNDKgVaOUKvOGN6pZ2Czem5JMVR3RR3XzVnslJyE7RX3U/N9lAi0chK04bGhDnl7lLADxh2fFy40gmjSMZt5jBWe88TEhHdLtUTguEWAVg60cmRaOol495VVp5D1w/q5JQODg/opJfqEok5MGnZ+UW0twSmJlRIlAers5X0zRY+8Na5SM3FzdAW/md5eF6Q2XoPEbu0GDpPW1bsGMrr32EimS7TqYNM72mVs3h5q6nDQYf2XWtuAgmG1yXF5jMJznpmZOXr0qC2kA8ctArRyoJUj0oankAhKq04l4bkk6QzDxC6qMvYaN/ukRLV+tdP6AiqzgXQ23jm7FgmqWT/hXCNKW33hwrC7fGEiEV17bKTQJVq2m/WBoNHvwEyUDpOkR/tR2BAEMw+XwnM+fPjw3NycLaQDxy0CtHKglSPSqvNKwulCaSOnktCwUjRBUKmM4zaR8JDNO23sLEYB55I6k9A5vxaxhP14o2ktG0U7ruswH117bKQArZzC2iNHjszOztpCOnDcIkArB1o5Iq2zsihKywxJuxQn1LAK3VipnONy/GHcN1N0XoudNjK0xs7T/i+xc+W43iCun0iHQScsGGxv2JucWu/fFKCV0xbtwsLC5OSkLaQDxy0CtHKglSPTknUl2JT9O27oUtYToyjbs1HXWKt1LFESwqoDsdNGhjZQaGDzVvf+IKHz1q5x2VoF9UK699hIBlo5hbWnTp3atWuXLaQDxy0CtHKglSPUKt9hRkV2Q36jvqsctb3QhlyON1B5Z2PGcZMkDDWQUbt+nJb3HKBi7PIz3nnk77imB9ZPwmRYrb61QbxrETiu5EAr5MyZM2NjY7aQDhy3CNDKgVZODi15jMO6l++4rFFoR8YFdcx95WSarjQDL02QOKjO/2aK6s64temYj25ivB+/c729XpD346qCblWlzZPWVfvjNmOZ9lEMaOV0nHZpaWnnzp22kA4ctwjQyoFWDrRyoJUDrZzCWnNrZVtIB45bBGjlQCsHWjnQyoFWTitaclzyXVtIAY5bBGjlQCsHWjnQyoFWTivanTt3Li0t2UIKcNwiQCsHWjnQyoFWDrRyWtGOjY2dOXPGFlKA4xYBWjnQyoFWDrRyoJXTinbXrl2nTp2yhRTguEWAVg60cqCVA60caOW0op2cnFxYWLCFFOC4RYBWDrRyWtOq37YSCT/raYYel/3yJg9VbW+z6bRvnaGV0mva2dnZI0eO2EIKcNwiQCsHWjktaeP3bxKjx4XjioBWTq9p5+bmDh8+bAspwHGLAK0caOW0ol2v7wQRXOIm3Tsi8iA/R9CSPYMlQa5wQT1E4IhqzqE7qmE2bw66pHau+/DKO+xcPXGPiIhMR9EJuBKbT6/tX2jltEt79OjRmZkZW0ghwXEpAgDoMNQ17nryMELdAHGoEcmp2qCaEWkZNEiQx3tnAVbJhtFZlo+oIzHd0h8xrKaQ1bJuAKgdx48f37Vrly2ksIL+s07bAq10Aq0caOX0nFbZkbkEpEtCdy1I+cglaRTbUo/rWsjkQURpw1rKuatZng/6CTMqT1aqVLxzlw+DXBLSkfsIWjGdqH3sscfGx8dtIQU4bhGglQOtnJa0znG5gTnbiwQDgqAZ1zptmtxzPa4NJbwdz3PH5QSduxFd3g+y9pqO3EfQiulE7eLi4sjIiC2kAMctArRyoJXTkrZjrnHDfuz28s5dngcdrpsW1wpaMdDKOXfuXNNbK8NxiwCtHGjltKQNHZcZk8slGlhQr8alXPDFpAQ519usrSOtCthKylpBNJ/UpcoNqRzrO8y7TCiI5DtyH0ErpibaM2fO0JWr4+TJk5+PMjEx0QgYHx/fvn27VaYAxy0CtHKgldOSljmutiZDzMl8VIUi73eVQyWVNwdXrhRz9sjznm1a3VBDby+fW5g33au8E/D54NiQ07Pas2fPWqvUZPslMTo6ekcUMlFbp5mamrLKgFOnTtneFxdPnDiB+yqnAq0caOVAKwdaOT2o9fzy8ccfty4XsGfPHuuEmrGxMeuTARSxdZpsvyTOnz9f9fbCcYsArRxo5UArB1o5bdGSe9E1n7WyxUXyNutyAXn9ktpbZQB5sO1dQw5thq7zWsFxiwCtHGjlQCsHWjkFtOSXxsaMa8b9kq4XrRNqxsfHrU8GjI6O8o9kJyYmrDIgzS8N3brOcNwiQCsHWjnQyoE2g6WlJetjGnJN63IBMzMz1gk1iX7pqujfuF+ePHnS9q5JfEod9lEcOG4RoJUDrRxo5XSx1vNLghzuwIEDxuoIzy8J65MBIyMjtkJDrmmVAQsLC7ZrTcZTXbGP5Ei0cNwiQCsHWjnQyqmt9uLFi9bHAo4cOWJ8zrjm7OysdcKAO++801qlxvNLwmkNnl8SduwUsI/kVK2F4xYBWjnQyoFWTkXaS5cuWRMLOHbsmDU6zd69e60NBnh+uWPHDlsRcPjwYaM1rjk/P2+7Drh8+bIdPh3sIzl11sJxiwCtHGjlQCsnUdvULw8ePEgWyL/Rs337dmuVGiraigCSWLHm4Ycftl0HSPzSgH0kp1u1cNwiQCsHWjk9riXrsiYWQJeD1ug0dLFobTBwzbx+SQZM3fJfrZBJ2+Fl9Pg+ygW0ceC4RYBWDrRyOlqbyy8Nd911l7VKzZ133mkrAmZnZ61Yc+TIEdt14Jp5/dLQs/uoANDKkWjhuEWAVg60ctqrNU7mWFhYsEYXYG0wYGRkxFqlJpdfGk6fPm0mUIDe3EfFgFZO1Vo4bhGglQOtnFa0jz32mPUxTV6/JGxFwMzMjFUG2K4DzC1ksY/kQCunW7Vw3CJAKwdaCeYRJe7viwVuue7dEk/olwbsIznQyoE2Dhy3CNDK6QUtv+U6uWbTW66nPaLEfYdWcst1O3YA9pEcaOVAK0eiTXBcigDQOzzxxBNkk475+fkDUXbv3k1e6Ij7pbmFrIPaW2UA9Wl715B92rEBAL0ErnGLAK2cqrXulusGd8t18jmTaXrL9fgjSpzWkH3LdQ/sIznQyoFWTp21cNwiQCsnW+vdQtZ7RAk5n+QRJbZO42657lxTcst1D+wjOdDKgVZOt2rhuEWA1pB4y3XOzMwMeaQ1Q431yQDvFrLeI0rINQv4pQH7SA60cqCVA20cOG4RukObcct1g3tEiXNN65MBibdc5ywsLJxg9/ch7NgysI/kQCsHWjnQypFo4bhFqIO2qV96jygh15Tfct3gHlHiXNOOnYde3kd5gVYOtHKglVO1Fo5bhNa1wluuc7xbyDb1S+8RJeSa8luue/TmPioGtHKglQOtnDpr4bhFOHfunPWxgLx+KbzlOodMutfWGVo50MqBVg60ciTaXnRcc8t1/vfFprdcpwtKa5Wa+C1kJX5pRu+stTJAKwdaOdDKgVZOnbUd6bjWxALX9G4hK/RL/h3aprdcv3jxoh1bs8zb64BWDrRyoJUDrRxo47TBca2JBRw9etQaXYC1wYCMW64b1/RuIdvULw113itpQCsHWjnQyoFWDrRxKnfcsbEx65MBxiwdk5OT1ioDrE8G8Fuue9R5ZdOAVg60cqCVA60caOVItJU7LlmszaVQ59VJA1o50MqBVg60cqCVU7UWjlsEaOVAKwdaOdDKgVZO1Vo4bhGglQOtHGjlQCsHWjlVa+G4RYBWDrRyoJUDrRxo5VStheMWAVo50MqBVg60cqCVU7UWjlsEaOVAKwdaOdDKgVZO1Vo4bhGglQOtHGjlQCsHWjlVa6t13EuXLm3fvt0WUqjz6qQBrRxo5UArB1o50MqpWpvguBQpi8XFxZ07d9oCAAAA0MNUe427tLQ0MjJiCym0MgFo5UArB1o50MqBVk63auG4RYBWDrRyoJUDrRxo5VStheMWAVo50MqBVg60cqCVU7UWjlsEaOVAKwdaOdDKgVZO1Vo4bhGglQOtHGjlQCsHWjlVa+G4RYBWDrRyoJUDrRxo5VStrdZxz5w5Mz4+bgsp1Hl10oBWDrRyoJUDrRxo5VStrdZxFxcXG42GLaRQ59VJA1o50MqBVg60cqCVU7UWjlsEaOVAKwdaOdDKgVZO1Vo4bhGglQOtHGjlQCsHWjlVa+G4RYBWDrRyoJUDrRxo5VStheMWAVo50MqBVg60cqCVU7UWjlsEaOVAKwdaOdDKgVZO1Vo4bhGglQOtHGjlQCsHWjlVa6t13IWFhZmZGVtIoc6rkwa0cqCVA60caOVAK6dqLRy3CNDKgVYOtHKglQOtnKq1cNwiQCsHWjnQyoFWDrRyqtbCcYsArRxo5UArB1o50MqpWgvHLQK0cqCVA60caOVAK6dqbYLjUqQsjh49Ojk5aQsAAABAD4Nr3CJAKwdaOdDKgVYOtHKq1lbruPPz87Ozs7aQQp1XJw1o5UArB1o50MqBVk7V2mod9/MaW0ihzquTBrRyoJUDrRxo5UArp2otHLcI0MqBVg60cqCVA62cqrVw3CJAKwdaOdDKgVYOtHKq1sJxiwCtHGjlQCsHWjnQyqlaC8ctArRyoJUDrRxo5UArp2otHLcI0MqBVg60cqCVA62cqrVw3CJAKwdaOdDKgVYOtHKq1lbruAcPHjx27JgtpFDn1UkDWjnQyoFWDrRyoJVTtbZax52ZmVlYWLCFFOq8OmlAKwdaOdDKgVYOtHKq1sJxiwCtHGjlQCsHWjnQyqlaC8ctArRyoJUDrRxo5UArp2otHLcI0MqBVg60cqCVA62cqrVw3CJAKwdaOdDKgVYOtHKq1sJxiwCtHGjlQCsHWjnQyqlaC8ctArRyoJUDrRxo5UArp2pttY47MTFx6tQpW0ihzquTBrRyoJUDrRxo5UArp2pttY7baDQWFxdtIYU6r04abdGu6FXs9ucEx5UcaOVAKwfaOAmOS5GyGB8fP3HihC2A1iDvsbleoje3GgDQleAatwht0RrvsYX8dKgW17hCoJUDrRxo5Ui0cNwitEULx81FD66VzeUHWjnQyoE2Dhy3CG3RwnFz0YNrZXP5gVYOtHKgjQPHLUJbtKHjbh2kvGFwK5WnNw8EWYtuMbB52tToSqMNpFRnWhp0mHcQpY1rRfOyhZy0cc42lx9o5UArB1o5VWvhuEVoi5a8R2m1iWrDDI3Wt1zXxmQGBqjQUOOqsirCcTOBVg60cqCV063aah13dHT0/PnztpBCnVcnjbZoY47LiAbDks1tHlwxOKzGJWcd3JzQQYrjarkmbB/GwqiWaydXsa16gMFB025gqKHbJPYWFUampKDtpQpbyEnH7V8CWjnQyoFWTtXaah13ZGRkaWnJFlKo8+qk0RYteY/WapfyDSo0WUK1MHkbJg8k49NuHRhi1N6SHJd1Obw+qFZBq2UaM6VAr4W6lcmtD4RWmSqMQdtL1baQk47bvwS0cqCVA62cqrVw3CK0RUveY7XGyBShV+lYaGPWFQOfo9D64QuqZnAr8z4HM8EA3uxCaLkaY5SKmIcSTKkrlONGBg2bJ4zLoe2lelvIScftXwJaOdDKgVZO1Vo4bhHaoiXv4VrtYURgY7qszEu5WCRIBfo/XeSqf+23qYIGlgTn080iKI2NBuPYfqJyNoCucI4bQTdIGJdD20v1tpCTjtu/BLRyoJUDrZyqtXDcIrRFS97jayOGpU3NXMI6P3XmRy3XD9M/1JgZoiPB+XgzNy4PMk1Uzhrpitg1bkjCuBwal+ptISdt2UcEtHKglQOtnDpr4bhFaIuWvIe02rqsSXk2por6C0vRkC5SZmD9oLrETTS/JOdj7RpDYTdBQy2x9c0dlwf9ejhuALRyoJUDrZyqtXDcIrRFS95jtMbrDMa4LMYPeSw0t+nANLnhOXiXClvNwoEt2jFUZNDZZdQ4fUfVjhsUDEHbqDAGbS/V20JOOm7/EtDKgVYOtHKq1sJxi9AWLXlPD64VHFcItHKglQOtHIm2Wse94447bC6dOq9OGm3RwnFz0YNrZXP5gVYOtHKgjQPHLUJbtHDcXPTgWtlcfqCVA60caOPAcYvQFi0cNxc9uFY2lx9o5UArB9o4cNwitEULx81FD66VzeUHWjnQyoE2Dhy3CG3RwnFz0YNrZXP5gVYOtHKgjQPHLUJbtHDcXPTgWtlcfqCVA60caOMknMQpUhbkuDYHWsY4bq/Rm1sNAOhKKrzGvXz58p133mkL6bQygZ7S4ho3Fz24VjaXH2jlQCsH2jgVOu7S0tLIyIgtpFPn1UmjLVo4bi56cK1sLj/QyoFWDrRx4LhFaIu2RMf952997cg3Xnf4H15ceqJuqXM7jKbFOcNxhUArB1o50MqRaOG4RWiLtkTHrchuTaLO7TCaFucMxxUCrRxo5UArR6KF4xahLdoSHdfzyNKTHUbT4pzhuEKglQOtHGjlSLRw3CK0RQvHzUVZa5UXaOVAKwdaOXXWwnGL0BYtHDcXZa1VXqCVA60caOXUWQvHLUJbtHDcXJS1VnmBVg60cqCVU2dthY579uzZsbExW0inzquTRlu0cNxclLVWeYFWDrRyoJVTZ22Fjru4uNhoNGwhnTqvThpt0cJxc1HWWuUFWjnQyoFWTp21cNwitEW7DI675rn9b/nta03+uh97xite+2yTf/DrL/6hlzzzw+PrTZHS55946eHFl7iil+wwmhbnDMcVAq0caOVAK0eiheMWoS3aZXDcG2+6tq9vxa1/uo7y7/vL76YR3/wOa8Drf/CaK69auedLP0L5x27/udO/uGnxN95gquLJDqNpcc5wXCHQyoFWDrRyJFo4bhHaol0Gx6X0c298DpnuX4x8H+Xf/p5vo0GNAX/uiR8beNYVL/z2VXS9+8S7f54c9x/euMmpvGSH0bQ4ZziuEGjlQCsHWjkSLRy3CG3R5nXcdevWbdu2zRai43oG6aUffukzr+jv+7upQcq/5g3KgD80+v2Uv+dz11H8Za981sMLP76w7ae/cPAnncRLz/+t+9KSnYEMmjMcVwi0cqCVA60ciRaOW4S2aPM6LrUnVq9evWXLFipyrWeQXqKr2O/87quuunpl45EfouJ1G57Zv6qP7Jbyf/BX6qPm37zl213jxOS5LE92BjJozjScLeSkLfuIgFYOtHKglVNnLRy3CG3Rkvfk0iq/Dejv7x8aGnryySdNlWeQ8fTA3//Ymuf2P2tN//6TP0YGfO2LrrzmmSsn59UfcX/l7S+gq96/GvsB3t5LnsvyZCYghLaXJm8LOem4/UtAKwdaOdDKqVpboeOePHlyamrKFtKp8+qk0RYteU8urbbaCH19fRs2bDhw4IBnkC4dOvXSBx976eGvqy8hf+bYD199zcpv+84ryXH3ffVHVz/riue9cNWBUxuoavBHnrHqyr6JL/ywE3rJc1me7ORk0PbStG0hJx23fwlo5UArB1o5VWsrdNyFhYWZmRlbSKfOq5NGW7TkPZ728uXLY2NjdyTRaDS0yfqQ6W7alPqNp4Nf+glKcws/boqjD1zXv6rvuh97BuXvPfxDq1b1fd+/vYby5Ls/cN01H/2M+kNvYvJclieamJ1iFNqQS5cu2Q0LoO2lOdtCTtqyjwho5UArB1o5ddbCcYvQFi15j6c9duzYwYMHbSGGdtgIGzduNB8sewbp0sEvK8d98KR1XEp/eff3r1y54qd/fg3l79y1nvLX/5z9kW5G8lyWJzO3OIuLixMTE/QewpY1tL00bVvIScftXwJaOdDKgVZO1doEx6VIKRw9enRyctIWQMuQ99ic5vTp0zt37jx37pwtx9Ama1m7di3fF55BRtKiH/lvf/Fd1MObfvOFlDffnDL5jOS5LE92Bkk89NBD+/bts4UAGs7mAACgw8E1bhHaojXeYwtPP01rSytsC0lQe2LNmjXmN0Jc6xlk0/Qfb/526urm29e6/C3vV/m05LksT3YGKczOzs7Pz9uCnjONZQs5acs+IqCVA60caOXUWQvHLUJbtOQ9TnvmzJnx8XGTT6O/v/+2226zhei4nkFK0ut/7Xl9fSs+8NHvpfxrN6kf6f6vj6sf6SYmz2V5sjNI4fLly41Gg7bOFGnOcFwh0MqBVg60ciRaOG4R2qLljjs2Nnb27FmTF8LH9QzSpUNff/HB+ZfNHX+ZjSy++OCXX3bwyz9x+OuquOEnV6+8os98YeqHXvLMq65eaZvFkh1Gk3d7L168SG8mlpaWKE9aOK4QaOVAKwdaORItHLcIbdE6x52fn5+dnTVBOXxczyBdevDvX2q+rkzWS8VDX7PfXj705EtNg3Xfe9WqK/saj/zQg19/8d9++t+YYDzZYTQFtpeucelKl653SQvHFQKtHGjlQCtHoq3QcT+vsYV06rw6abRFaxz30qVLo6OjdCFoo2L4uJ5BhunrL5mb/4mD7Bp37isve3DhZe7rVAdObXjO8/tXP+uKfV/9UdsmKdlhNMW21/yYm7RwXCHQyoFWDrRyJFo4bhHaojWOe/DgwWPHjtlQHvi4nkHmSpPzP/LMgSvMt6jSkh1GU3h7aUsfeughOK4QaOVAKwdaORItHLcIbdGS9zzxxBNjY2O2nBM+rmeQpSc7jKaVtdq1axccVwi0cqCVA60ciRaOW4S2aMl7xsfHFxcXbTknfFzPIEtPdhhNK2v11FNP0Vabb1HlpeP2LwGtHGjlQCunai0ctwht0ZL33H///baQHz6uZ5ClJzuMpsW1oq2my3rvXlQS2rKPCGjlQCsHWjl11sJxi7D8WrIc8p7Tp0/bcn74uJ5Blp7sMJoW14q2+vHHH9+zZ48NiVn+fWSAVg60cqCVU2ctHLcIy689fPgweU9Z43oGWXqyw2hanDNtNWWExxKnrLXKC7RyoJUDrZw6a+G4RVhm7dLS0ujoaC87LkGXuXSxa/ISylqrvEArB1o50Mqps7ZCx216419DnVcnjWXWGrMp0XGPfON1nkeWmKhzO4ymxTk7x72sH014/vx5U2xKWWuVF2jlQCsHWjl11sJxi7CcWvdXzBId95+/9bWKTJe6pc7tMJoW5+wcl6Br/cTH6CZS1lrlBVo50MqBVk6dtXDcIiybll/Ylei4eWmjljsusbi42Gg0bCGTHlwrm8sPtHKglQNtHDhuEZZNy585D8c1ZD+H39GDa2Vz+YFWDrRyoI0Dxy3C8mgvXrw4MjLifooKx3VIDq0eXCubyw+0cqCVA20cOG4Rlkc7NTV18uRJW4DjMuhdCH+MbiI9uFY2lx9o5UArB9o4cNwiLIM2/sx5OC7n4sWLY2NjGc9Q6sG1srn8QCsHWjnQxkk4iVOkFO6///5jx47ZAsjJ6OjoE088YQsa47jLz7cWvpeSLSw7GVv92GOP0ZuSc+fO2TIAANSbCq9xG42G5Lb7rUygW7WJXw5qyzXu5cde/a0vP4sSZWwoJy3OOe0a15DxcP7lXysDtHKglQOtnDpr4bhFqFSb9nlpiY57/PjxaRnGbk3613+csNFMqHM7jKbFOWc7LpH2wOCy1iov0MqBVg60cuqsheMWoVJtmoWU6LjWG5tx+eTLueNS0VYE7J3e+9m9n53aO2XLAXYYTYtzbuq4ly9fnpiYiB9pZa1VXqCVA60caOXUWQvHLUJ12rNnz9IFri1EqcJxZ2ZmDh06tPDoo39/8uQXjh45cOBztkLD7dYkWzE9PTU9dfuu4ffsevtNn7lhy8Rbb7n3HZ/Ys9PWLa/jEpcuXaJF8x6jW9Za5QVaOe3Ubh2kQ8swuNXGJfTiWhUF2jhw3CJUpx0fH0/70QudGsoa1/jivn37yGX/aWnJpW+cOX3w4AFT6y5wzVnJ5N1l7vvuu/mmvTe884EbXXr3fW/71OQ9ptYOo2lxzjS0LWRC71Ro6dxvl4my1iov0Mppm7YxNLBixcBmOlCnN1Muj+dineVAGweOW4SKtCdPnpyamrKFGHRiKGtc44sPzs0tXfhH7riUFoI/8RqL9RyXElXdPzXxrk+HXmvSlv03/v6um43WDqNpcc40tC00w3uMbllrlRdo5bRNGzpuFOO/mrA2DKqYHldfIA8M6DgzbldUxNr04DpDGwOOW4QqtHR9NjIykvEDU3rhljWu8cVHHnnEs1tK586e3b9//+UTP+4sVp0xmONS1ejkyE3Tb/Ecl9KtjXeYnu0wmhbnTEPbgoDDhw8fOXLE5Mtaq7xAK6d92mHzmXJoqwrtkeZyN8yGOe2qA0MNGlcH3ZWxqdBd+V24NhrsIzndqq3QccfGxs6ePWsL6dR5ddKoQsvdIhF6+ZY1rvHFDMd1/kpJnTeY41KqreMS7jG6Za1VXqCV005teFUamCJzSwcz09ByvaaRNmFNQne9uM5F6VZthY5LV2zel1kSqfPqpFG69vz58/QGhf8ZMg69fssa1/hi2qfK/AKXEo1L8Ag1qOGnyoZLly6Nj4/Tepa1VnmBVk7btYHtKr80+SzHNSa6fjjJcSNoARwX2gTguEUoXeuuzDKg129Z4xpfTPvmFDfXtPSvFz5Vq29OccxjdJ966ilbzk9Z65wXaOWUpnXOmGCRUcc1hexr3BA4LrQJwHGLUK7W+8pPGvT6LWtc44tE/NdBl0+8xDNXGpfwgpdPvLg+vw6Kc+rUqV27dtlCfspa57xAK6cVrf7ilHVD5pfMI11UZ0wwMFwaN+qmrIvk3gKwj+R0qxaOW4QStZcvXx4dHZUsFL1+yxrXGmOMfzn/Mc9ZKdG4hBekRO3rcAeMNObm5g4fPmwLOSlrnfMCrZwWtdoPLeH1qfFXQ9RQNaqhHjfmpqy7IAzHhTYBOG4RStQeOXJEaAz0+i1r3LS7PNKVq2erGYkaW1mUZb7LYxqk9R53KKesdc4LtHKglQOtnKq1cNwilKW9GH3mfDYlOm4a35p/nmerWWn+eVaWSYtzbsVxaWHHx8clX5j3qHqd04BWDrRyoJVTtRaOW4SytLkuwpbBcYlvPXqt76yJ6dFr/+XsB60mkxbn3Irj0r90BJLpZvzKOZFlWOdEoJUDrRxo5VStrdBx77zzTsnVW51XJ41StIuLi41Gw+QlLI/jJtJGbYuOS9A6T0xMCD9IMHToWtlcfqCVA60caONU6Lh33HGHzWVS59VJoxSt8A4hDjhuLvi4GY/RTaRD18rm8gOtHGjlQBsHjluE1rWJz5zPhrynN7HbnxNvH5Hjku/aQjM697gqBrRyoJUDbRw4bhFa1KY9c74pPbhWNpcfT3s55TG6ifT4WuUCWjnQyulWbYLjUqQUyHFtDkTZu3fvww8/bAtguTh9+jS90SHTtWUAAFhecI1bhFa0TzzxBJ33bSEnvbZWpWvjj9FNBGslB1o50MrpVi0ctwitaMlu05453xTpuPouOZHb3ajI+sj9b1JRTaO3ykkZl92gJ2wfBm1MacM78ngdN6GKfZT9EGJDFeNKgFYOtHKglVO1Fo5bhMLahYWFyclJW8iPdFxre8zeyndcctHg7nhKEd5L1mhdTD/92/aX0HUmFe2jgwcPHjt2zBaSqGjcpkArpyztN5fOH//U//rSyO2lJ+qWOrfDaHp5nfPSrdqqHHdpaWlkZMQWMqnz6qRRTHtZP3P+9OnTtpwf6bjG2cj+nL2piHNcd8nJ3S8IDgwOhrboWsbcmnfuSjRKeI9airn70AbktNzq9tHExMSpU6dsIUZ142YDrZyytBXZrUnU+bp167Zt22bG6uV1zku3auG4RSimNZdWyzFuYGyhLTLHtU4YyUWDgRW7ILtMTSRo2Mxxcxpuhfvo0qVLY2NjafdEW459lAS0csrSeh5ZejLvWFevXr1ly5ZeXue8dKsWjluEAlr3zPnlGDd0tq2DxgJDxyUjdKbnLJUHndjV0rjDkUvaCKp94LMkse1UlDuuLvPHtEiodK1oj4yPj5P12jJjOfZREtDKKUvrGWTpSRuupb+/f9OmTU8++aQdOw+9vI/yUmctHLcIBbTuY8zlGNeZps4ql1MR7bisylVGg85+lX0yEs1StYlUqK5M662m8+icQxeXUPVapT2ZeDn2URLQyilL6xlk6Um/GiL09fVt2LDhwIEDdgYyenkf5aXOWjhuEfJq+Zl9OcaN2yrZX5FrXBtMHlebq5PFsHJPy0dqyjKsVeLTEpdh3ESglVOW1jPI0pO12ShkunSxa2cgo5f3UV7qrIXjFiGX9nL0mfPLMW7Eca01um8/OZtluWgw9nfcC8PrXUtLst2G3bgpRLVsSAHLs4/ozRC9JbIFzfKMGwdaOWVpPYMsPalXXpSNGzcW+GC5l/dRXuqsheMWIZfWu4pajnE9x7X+aB3XmqqCt7G2nPJdZd8mg9YhVhJT0JxZ4xx2SyzPPqK3RN5jdJdn3DjQyilL6xlk6cke+Jq1a9fm/TDZ0cv7KC911lbluOfPn6cLO1vIpM6rk4ZcG3/mfHdvb5yO0NIbxLGxMfctKqyVnE7XegbpEhnkT/7kxnh66Utf4rXMTsZr16xZs23btl5e57x0q7Yqx5U//LXOq5OGXItPLDtFyx+ji7WS0+lazyBdIpu0LaI869lrnv/853uNM1J/f/9tt91mtL28znnpVi0ctwhCbeIidPH2JtJBWvcIRayVnE7XegbpUqLj/uu//uuqK6/KZbpWqenldc5Lt2rhuEWQaON/HTR06/am0VnamZmZhYUFrJWcjtDyGz8RXOsZpEsZjmtMd2Dg2T/yA9/lqeLJKjVdv84e0MaB4xZBok175ny3bm8anaWl90l03D722GO2nB+ss5xl06o/pQY3fqIi13oG6VLccV//C6//Hx/4n9/85je/9a1vPfnkk88euPJZq1d5qniyYk3Xr7MHtHHguEVoqr148eLo6CjuZ0R0nNbsO/rXlnOCdZazbFrjuIb+/v6hoSH3+xzPIF2ilqaB44Y330DBFzzvmi3v3PId3/6c7/3Ovquv6vNU8WTFGuwjOd2qheMWoal2dnZ2fn7eFqJ05fZm0Ilausalo5d/w1wO1lnOsmm11UZwN37yDNIlamPFAQ8//HBf34r3v7vvu79j5Ste3HdiYiW1Ofg3v+cJvWTFGuwjOd2qheMWIVt79uzZjGfOd9/2ZtOh2oWFhZmZGVvOQw+ulc3lp0St+X3XHUnQiUibrI+58ZNnkC5RA9s144XPf8ZH/6jvX46tvHREpWuf13fFyhUveuEzfvy67/HkLlmlpsf3US66VVuV4546dWpiYsIWMqnz6qSRraVXfvwLU47u295sOlfb9DG6ifTmWhWjLO3jjz+e/aIzFstxN37yDNIlamO0Bhru1T/98itX9e38476nv7zSpT0f7nvmNSuePXClJ3fJ6jWdvs55gTZOguNSpHWOHj06OTlpC71Ez254VzI+Pn7ixAlbAPXj3Llz+/bt271791NPPWVDSRiXNaxdu5a/Qj2DdIla2hPi00/vuGvHmmddRc5K/srtltz3ylUrNv7I9z34kf/uyV2ywwCgqeoaV/6hXCsTqJv2sn7mfPaXbrppeyV0tDb7MbqJ9OxaFaBFLe2XRqMh+RzCeK258RMV+bieQbrEHfd9v/++V17/U9/xbauvWNl37fP6zEfK/3Js5Uf/qO8Fz73aE3rJdqHp0HW2ufxAGweOW4Q0reRzyG7aXgmdrnUPNrblZvTyWuWlFe38/DztlzNnzthyJvzGTwQf1zNIl7jjOuhgoPiJCfXNqe/6jr73v7uvr2/F3X94k6flySo1vbaPoI0Dxy1Covbs2bPj4+NNT81ds71CukCb9hjdRHp8rXJRWEtvbXfv3p346zsJfFzPIF1KdFzi6qtWfu939n3ntz/nylVXvuA5V1GzoZdn3WmZ33yjp/YRAW2cihx36+aNG9/61rfS4WjIeGRMwgSmNw+YJ9HoB9HYh9IkBaWT5/0EtLLhiVr3zPlsSh9XCLRy4trPa2whEffQJHukmQcm8YNOt6BXgnuUUlAZSAeGGnxc1qMm+7lLadsbHvthzsdq3UssD8u8jy5evEjva48dO1bWuJ5BukRrZVtEefbAlS98/sDX/8/XqcEX/+6Pbn7TL7xqw3WelidqRpibbyzzWjmglVO1tkrH3fJBW7BnGlPyiWuTTgzJZ4uqVyeNuFZ+GVSfOcuBlog/lCJEm6g+xKeHAqP1Lde1MZmBgeA1ocqqmOi4gT77RUSkbW/yKyeK1koaJrCc+4je0Y6OjppPkssa1zNIl2gxbIsoG1+2keyWMmuevcaTJCbqx9Hf379p06YCD8cllnOdOdDKkWiXw3HZ+ciehgwmcuHCsD6ZqFNOBKq2JwEmCoOq4wsNfX5TBCcjM5Z6xiuLOklibTgrM4nmZx1veyVfmHJUvUfTgFZOovbSpUt0dXX+/Hlb5pjjyh7PgZYFIyWb2zxojzQ6Ogc361iG4zK9jtvXS9ihxo3mYoODrhfeXyhRmgsXGpFypIHrMzauZtn20eHDhycmJkp/oqJnkC7RRj7jGc8kW01Lq668ypMkJrVaUdzNN+wMZCzbOntAK0eircpxf+PVr/6V3/xzW3InC5Wxr1X38reOG55a2IkhzCYH1wc5N4I9UwSD+WpW665FmFi3M8FMvO1t/pEjo+o9mga0ctK03mN0GebIUUcR04YHFqFamLwNb908oMtU1AWK5XBcVxHEadxQkNg4rGY96+z6YRqXBVk+7MkEgxaOZdhH5pPkI0eO2LKmrHE9gyw9qTWLYW6+YWcgYxnWORFo5Ui0VTnu217/+te/7X/agnqlmhetxrxyFSpoHTd8IbNXfphNCLJzATsx+GeIqJrVDgd2zfthw2TBt5dOB94z57Opeo+mAa2cDG3qrV30YaRZ744fHTOHkzqy7EEWHHAUUnX6fyYm+1Q5EndHr5pzUOOCRNja5SIdKPT2hlEuZ4WYTFP1PlpcXHSfJHPKGtczyNITrZmHu/lGLqpe5zSglSPRVum4r3+9PcTc61S/etmr3pwpynDcpGiCmtUmOq7Oa0kmfHuz/ryXRNV7NA1o5WRr054KRejjhwgOS3c8qSMwEqQC/Z//S7Hsb04Fx2V4XBNaGMH15h/Sgc5Igg4UenvDbrmcxSPjOirdR5///OcbjUbid5LLGtczyNITrZlj7dq1eT9MdlS6zhlAK0eiXY5rXAd/JbuXb0df48pvZumoeo+mAa2cptqpqamTJ0/aQpQL7sBS6IPLXMIGh2p4wNHRNrhV/2NjWZ8qh0TirjM+ZxckwtYuF+tYa8Mol7NCTKapaJ0vXrxIXpvxx5qyxvUMsvREa0aYm29UtFZNgVZO1drld1z26rdnioKOy7sLTwvsbJGgZrXhiTEM6nYmmInZ3sspz5zPpuo9mga0cppqadeTH7iPOtmR+LT+Mp85xBSqSn9VLxrSRcqoKpulWAHHdb3RnF3H4RD8kA51rIdg4HjQ5MOevHEDqljnxcXFsbEx+teWkyhrXM8gS0/85htVrJUEaOVUrV1Wxw1eygr3HcqY49qThAqx13hiMPW7yt4ZwuVYLb8UCabFvtiZidnejE8XM6h6j6YBrRyJdmlpid5vuS+oB8enIjgWNfbYYrHwIPRzRRyXYGO7cMIhzXVBtWJwq9neoBvdJGzgZp48n9LX2XyS3PSb/2WN6xlk6ckOoyl9rYRAK6dqbUWOm+Pru7VaHXVSiZwvkyEtnRHSnjmfTa22Vwi0idA1LnmD96U5rJUcT0uvpuxPkjlljXv8U//L88gSE3Vuh9HUZJ1zAa0ciRaOG32/L/FbrZ2ZmVlYWLDlPLR/e/MDbRrz8/Ozs7O2oMFayeFaevtCb2GzP0nmlDXuN5fOV2S61C11bofR1GGd8wKtHIm2Ksel0xCdjGwhkzqvThpPPPHEWPoz57PpxO2FNgPv8RVYKzlOe+TIEf4RvYSeXasCQCunam1Vjiu/BKzz6qRBb8bzfmHK0YnbC20Gly9fnpiYcBdnWCs5pL106RKt3uHDh21ITA+ulc3lB1o5VWvhuLmha/e9e/faQn46bnsJaLOhizO6RDOP0cVayXnsscfozavk+R9xsM5yoJVTtRaOmw96S07niNOnT9tyfjprew3QNsU9qxFrJeTYsWNjY2O5PknmYJ3lQCunai0cNx/mj3adNWcDtHKKaU+ePDk1NYW1agq9bd2zZw+9lLBWcqCVU2dtguNSpHUmJyePHj1qC92C+cLUuXPnbBmAKLOzs3Nzc7YAkjCfJM/Pz9syAL0ErnFz0Gg0zBdkOmjODmjltKLdtWtXsT9MEl2/VseOHaMXkfmDN9H12+sBrZxu1cJxpfBnznfKnDnQymlF+9RTT42nPUa3GV28Vu6TZH7DkDrM+fjx49OVQZ3bYTR12N68QCtHoq3Kcd3lYFMi2m+eePr4i57+0oryE3VLnTNybTidJvgz51tZNGjldKiW7JZMlzzGhsTwcb9+8f/+ytz7f2bmttITdUud22E0Va/V2bNnx8bG4o/YqnrcNLjWemPL7J3e+9m9n53aO2XLAXYYTR22Ny/QypFoa+a4FdmtScdftG7dum3btpmhcm24dwutVhYNWjmdqxU+VOr5v3VfWqrIbk2izu0MNJWu1fz8vPvplEd795HBGuP09MzMzKFDhxYeffTvT578wtEjBw58zlZoZmdnH3748yc0lKGirZienpqeun3X8Ht2vf2mz9ywZeKtt9z7jk/s2Wnr4LhF6VZtzRzX88iyk2H16tVbtmyRbzidLEZHR+v2aVheoJVTivbIkSNNb+zguSxPnkeWnuwMNBWtFV3lT01NkTnx1w6n7fuIML64b98+ctl/Wlpy6RtnTh88eMDU0iaQDfNaKjrTfd99N9+094Z3PnCjS+++722fmrzH1NphNHXY3rxAK0ei7UXHNfT392/atOnJJ5+0Q6cTf+Z81XslDWjl1EGb8Rhdg+eyPHkGWXqyM9BUsVbmB8rZm1+HfWR88cG5uaUL/8g9ldJC8Cdeuqj1qihRkKrun5p416dDrzVpy/4bf3/XzUZrh9HUYXvzAq0cibZ3HdfQ19e3YcOGAwcO2AnESPx4sOq9kga0cuqgpWs7cp2MG4J6LsuTZ5ClJzsDTelrZT5Jbvr1sTrsI+OLjzzyiGeolM6dPbt//36qPXHihFdFiYJUNTo5ctP0WzzHpXRr4x26YzhuQbpV2+uOS5Dp0sUuTfiOJLZv3x4/cVS9V9KAVk5NtEtLS3QI2YMpCh1ynsvy5Blk6cnOT1Pi9tKbjOxPkjl12EfGF+G4aUArR6LtdcfduHGj5INlj6r3ShrQyukIreeyPHkGWXqyM9CUtb303nRsbCz7k2ROHfaR8UV8qpwGtHIk2qocd3x8/MyZM7aQSUQb88hyE2ft2rUZHyZnU/VeSQNaOR2h9VyWJ88gS092BppStndhYYHsNtcPkeuwj4wv4ptTaUArR6KtynFHRkYSfw8QJ6KNeaRJL7r2O1z6thd8u/XMdDy5S4Y1a9Zs27at6pVNA1o5Xa/1XJYnzyBdWvXsa9b+yo+v/t4X/uD7Nj3r33z783/qB0z8p/e991nXvWjDB9/sWv78Z299dZCPJzsDTYvbe/ny5RmN5JNkTh32kfFFAr8OSgRaORJtZzguYRtomhdjPZjU399/2232XFP1yqYBrZyu13ouy5NnkC6te9NG9XrQXP1tz6Z/1/7ay0zV6u+/duWV/S+/912U/+Stbz39i5tO/uovm6p4sjPQtLK9p06doktb4Q3mPOqwj6wxtgzugBEH2ji95bi2habqlU0DWjm9rPUMkie6rqWD/K/u+rfftvaaFX2UXbH+v7yO4q+a/N3+1Vdf9YIBut6d/c03keMuvmETF/Jkh9EUnvPJkydHR0dzfZLMqcM64y6P2UArR6Jtg+PyGz8REa1nkEFSJspoXoz1YBOj6pVNA1o5vaz1DJKnnxz9LTrIJ+deevBLP3Hr1u/rv1K57ve87Xqq+okd/6nvipXPfcl3/9Knf/cv/+Q//ubH38OFPBW+/5rh8uXLs7OzU1NT586ds6H8dPo+ygu0crpV2wbHpbMDYW78RMWI1jPIIBG2gaZ5MdaDTYyqVzYNaOX0stYzSJ6441KafujHN17/HIqs/r4Xvvzed133X3+R8t/z9ld4Ki9RGyXJef81A13Ujo+Pz8/PU77T1zkv0MqBNk7bHNfQ398/NDQU/j7HM8gg5cWTh4lR572SBrRyOl3rGSRPnuOa9Dcj1z33+av6Vvat/bWXfcemF6/oW/Fjf/YbnpAn80oxyO+/Rpw8eZLf1qOX91FeoJXTrdo2O64hvPGTZ5ClJ0ad90oa0MrpdK1nkC69Zuq9r/zYb9OrxnNck/7zu9euWrVy1bOvueY7n7Ny1RUv/+Q7PblL5qXHaXr/NfdJMn8sUi/vo7xAK6dbtRU6rr2zTpRGo2Ff31HMjZ98gyw9Meq8V9KAVk6naz2DdGlo1y2v+/i76CWT6LiUKP6q172AGvQ/46qXfPhtntwl/bLzyb7/2p133mk+Seb08j7KC7RyulVbleNmYF/cjPDGT55Blp4Ydd4raUArp9O1nkG6NLTr1mzHnTr00p961XNW9K147ku/x9PyZF56HNx/TQK0cqCNk+C4FKkU+/rWrF27dnJy0lbQTDyDLDvZYQCoPZ5B8vRTSX/HNcl9dfn516/3VF7Srz+L9zIEAFRE265xzY2fqBjRxjzSpLLuOWVH0bSy4dDKgVYO13oGyVPiN6fu+uQPP+8FV/b19a395R//7rddTw3Wv/u1npAn/ULB/ddyA60caOO0wXH5jZ+IiNYzyCARtoGmeTHWg02Mqlc2DWjl9LLWM0ie4r8O+plfeGFf34pVz1Y3xPjhP/wlanPtq6+j/I/+6a9xIU+df/+14UFaBcvgVhsWUXTc6c0DK9YPi7WqeWRikXFjtdl05j6C1qcNjusR0XoGGSTCNtA0L8Z6MKnFX/07oJUDbQYZd4PxDNKln51+72tG3kkHuXHc/3r79z3jOc949vdfa4x2zY+u61vZZ74w9azrXrTyqn4n9JIdRtOB67x1PbNZZV4DmyM3VMyk6Lg5HTdGB64ztDmQaHvLcQ3FfvXPgVYOtBnwA5KKXOsZpEuvnXyv+ebUh0d+8EXf/cyVK1du+C+vH7rvltdMvdc0eMZ3Pnflqit+6u7f/ul9733JX7/VCb1kh9F03jpr72MXiFsHQ8ulvCEesR59oTE0MDA4OOAifoMoQa2WBI6bKIkOza9iXY2LRK5xY71R7cDmzSzaefsI2iR60XENuX7171H1XkkDWjkdobXHosa7G4xnkC69Wl3j3mQkq7/vheSsPz9xKyXX4FVTt1y55hn9z7zqFRP/xQXjyYxi6MB1nh4iv0y4rmU+Ri6mGwT/D3PKcZlVugYREwyIyFdYx02SxIYOA1RWGdreMBZrHsmp2kiw0Xn7CNoEOsZxc+HJXYrT9Ff/iVS9V9KAVk5HaO1RyHAHpGeQPL1yz83P/K7nX/d7b/DiLl1/37v7n3HVD2z5OS/Ok52BplPXmazIYr0pyTOt2wV51VI7rh8M8hly1bt23CRJfOgwYttHtjdS64RBz7w3nR/u0H1UlG7VdobjlpUSyf7VPwAVkX03GM8gS0/2Faep+iyTRmla5UmBUTkrNHDrCqpjjsuJ6iNy1TRwXI5gaJVnjW1E10aGCHrxtXDcHNRZ2+uOi1/9S4BWTi6tPQoZ7oD0DLL0ZCZg6Lx11tZn8xoKKIOKuJfB1gR55Wcxx/UkHF6reg8cNyaJDx2LqO21U+C1vLegmmt1Ho4rp87a3nXctWvX5v0w2VH1XkkDWjkdobXHombdunWTk5O2Ao7bhMh3lUOj4k4VZF2dy0UdN6EBJ1Ib+zsuy8WGdoGgjdpe1541T+iN1Zo8HFdOnbW96Lj41X9eoJWTS8sPSCpyrWeQpSc7jKYz15n/HtcaloZcywu6iPUwz3GTJBzleLoy8bvK6UNHPTUg4qPBHPwZwnG7Vdtbjtv5v/qHVkpHaDPuBuMZZOnJDqPp+nX2gFYOtHIk2t5yXDuKpuqVTQNaOb2s9Qyy9GSH0fTyOucFWjnQxqmZ4x5/ke+RJSbqnFH1yqYBrZxe1v7K3Ps9jywxUed2GE0vr3NeoJUDbZyaOe43T1RlutQtdc6oemXTgFZOL2u/fvH/VmS61C11bofR9PI65wVaOdDGqZnj5gRaOdDKgVYOtHKgldOtWjhuEaCVA60caOVAKwdaOVVr4bhFgFYOtHKgldNEG/ntjc/yzjmcSoI2c56c5Z1zCLRyJFo4bhGglQOtHGjlNNHCcRnQyqlaC8ctArRyoJUDrZxsbXhDCbK05g/mSwwalN49Nm9g8/SF4fUub5tk96lHNxXsrh1BSzhuCt2qTXBcigAAQAej7iq1fthmTE5Bdjkw1KCMq08LBjC9zrK8berkLBcNBqKEgZKGBF3MCvrPOm0LtNIJtHKglQOtnC7UumvHyEUkXXeqS1OtpbyJ26DGBR36GtfWqjw5ps47FZckBt0MtpLh+gNFppdFF+6jTLpVWy/HPX78+HRlUOd2GE3VK5sGtHJ6WYvXQjZNtM7JIpZGPsdx7shxpmhQLhtEVN533Ej/QeNI0LmrevoCI6FlBl24jzLpVm29HNeeD1pm7/Tez+797NTeKVsOsMNoql7ZNKCV08tae8i2TI++FpyTRSzNel9UGxhiMoGJBvnWrnHX+wNFppdFF+6jTLpVW1PHnZmZOXTo0MKjj/79yZNfOHrkwIHP2QrN7Ozsww9//oSGMlS0FdPTU9NTt+8afs+ut9/0mRu2TLz1lnvf8Yk9O20dHLco0MopS2sPWbwWUmiidU4WtTRjiUrrzJH5JA8GKJcNQiofc9xkeSQYfFFK/R3XawnHTaFbtXV03H379tGZ5Z+Wllz6xpnTBw8eMLV0TqFTD6+lojvRvO++m2/ae8M7H7jRpXff97ZPTd5jau0wmqpXNg1o5fSy1hyxeC2k0UyrrEw5nW9p2gAVgTcqEoOG5o7L5HwgMwHqMvG7yoHWn14q3biPsuhWbR0d98G5uaUL/8jPI5QWgj9r0Rt5r4oSBanq/qmJd306PL+YtGX/jb+/62ajtcNoql7ZNKCV08tac8TitZAGtHKglVO1to6O+8gjj3gnEUrnzp7dv38/1Z44ccKrokRBqhqdHLlp+i3eWYbSrY136I5xlikItHLK0pojFq+FNKCVA62cqrVw3CJAKwdaOVxrjli8FtKAVg60cqrW4lPlIkArB1o5XGuOWLwW0oBWDrRyqtbim1NFgFYOtHK41hyxeC2kAa0caOVUra2j4xL4RUQi0MrpdK09ZPFaSAFaOdDKqVpbU8dtEdwBIw60cuqgtYdsy+C1EAdaOdDKkWjr5bi4s1020MrpdC1eC9lAKwdaOVVr6+W4eYFWDrRyoJUDrRxo5XSrFo5bBGjlQCsHWjnQyoFWTtVaOG4RoJUDrRxo5UArB1o5VWvhuEWAVg60cqCVA60caOVUrYXjFgFaOdDKgVYOtHKglVO1Fo5bBGjlQCsHWjnQyoFWTtXaBMelCAAAAADKBde4RYBWDrRyoJUDrRxo5VStXVbHtY9o5gxsbjTVpj+0WY0rfqSzRzBn9ZTp2GOom9DKokErp5u1+oHlkQNXRdbLjuSEgz55XD2KIWwfBm1MaRNbCqj7OicBrRxo5Ui07bjGjZ4u2rw6NJnchtvuORcCWjnLobUOx9xNRcp13K2D9JbWHNxKYfIUtFoXu3BhOKmliG7eR0lAKwfaODVw3MbQwMDgoDr96KCqtdhGrj1lBjZvphNGUKvGTa8NUKcYhRolPJXYOVMlayqklUWDVk43a81xyw8/FXGOGxy0kaOTH8muwrWMuXX02LYl/TIJXgQUU4ULw+sTWsrA/pUDrZxu1dbDccPzij0FKFyzSCao1g3VJ9LptaabMEs5Fw3mTLFwKmKq3itpQCun7trguA2PQBWxrhk5aJOPZKtyQfUyyjqUg4Y0StChC0bnHI4joZv3URLQyoE2Tk0cN/FUQa98HXftuVDnh2nc9FqdDzpRUDQ8leg5RyJyqt4raUArp+5afoiaY1BFjOPyg9b5n3ckm4KrpXGHWQMP1T440Eli26mo77i8pYhu3kdJQCsH2jh1dFx1SrDouGvPhTrf3HEpE54/IgU150ggB1XvlTSglVN3LTtc7WGoItpxWVV40EaCzn7Za0WReDSrNpEK1ZVpvdV0Hsw51lJAN++jJKCVA22cujmues3bgmsWzwT5Vq9xeWUeqt4raUArp+5afriaI5Psr8g1rg0mj6sahrIYVq60TVqmUvd1TgJaOdDKkWhr5ri8SuX1ucYF/VqJ44ZnLJVj7+Bpzvwclouq90oa0Mqpu5YfroQqEsX/jqu+/RQe3RrdZ+wID7txU4h+lyIf2L9yoJXTrdrafapszzyE+0Kma8+FOi9xXHt+IgY3R69xG7yYizrv0TSglbMc2sghqlCBwHHDgzbSRjchkr+r7B/MQesQK4kptOFGiMwsE+xfOdDK6VZtOxw3yvJpo+e4zphzFGjlQCsHWjnQyoE2Ttc7Ln+jH7kIqPGcU4FWDrRyoJUDrRxo4/TSNW4UaOVAKwdaOdDKgVZOnbVw3CJAKwdaOdDKgVYOtHKq1sJxiwCtHGjlQCsHWjnQyqlaC8ctArRyoJUDrRxo5UArp2ptDRw3+usgEcG3jouM24o2AFo50MqBVg60cqCVU7UWjlsEaOVAKwdaOdDKgVZO1dr2O+56+9MdY7pJP/x3sVgbdQcMh9/M4HWYos1JnfdoGtDKgVYOtHKgldOt2gTHpciyoq5x15P/EepGdUONWMzmwiCrDkhqlthhghYAAAConFp9qkwXoO4mFZSPBwMSPhlOapbYIT5Vzg+0cqCVA60caOXUWVs3x+UEZqk8Mh6JuWa8WWKHcNz8QCsHWjnQyoFWTp21dXNck0nBXbJmu6ZrltghHDc/0MqBVg60cqCVU2dtrRw36pUmF4ZYPu6aic14NkObH2jlQCsHWjnQyoFWTtXaGjiuemreith3iZ1/hiH2JWRlm973jZOaEfEOE7R5qfMeTQNaOdDKgVYOtHK6U/v00/8/R8JmTcxAV/EAAAAASUVORK5CYII=)

- [untitled.png](https://www.knime.com/sites/default/files/untitled_2.png)

---

<div class="post-metadata">

**Author:** ![kilian.thiel](https://forum-cdn.knime.com/user_avatar/forum.knime.com/kilian.thiel/32/5449_2.png) [@kilian.thiel](https://forum.knime.com/u/kilian.thiel)\
**Post date:** [January 9, 2016, 11:23pm UTC](https://forum.knime.com/t/svm-learner-rejecting-1-column-due-to-incompatible-type/6813/2 "2016-01-09T23:23:16Z")

</div>

Hi Jasleen,

this simly means that the SVM Learner can not handle the "Document" column and ignores it during training, which is fine. The SVM Learner should use the numerical columns as features and the sentimen as target. The Document column is not of any use anymore, since the model is build based on the vector representation.

Cheers, Kilian

---

<div class="post-metadata">

**Author:** ![ScottF](https://forum-cdn.knime.com/user_avatar/forum.knime.com/scottf/32/61316_2.png) [@ScottF](https://forum.knime.com/u/ScottF)\
**Post date:** [February 14, 2023, 9:02pm UTC](https://forum.knime.com/t/svm-learner-rejecting-1-column-due-to-incompatible-type/6813/3 "2023-02-14T21:02:46Z")

</div>

A post was split to a new topic: [SVM Learner Rejecting Columns](https://forum.knime.com/t/svm-learner-rejecting-columns/61758)

---

<div class="post-metadata">

**Author:** ![ScottF](https://forum-cdn.knime.com/user_avatar/forum.knime.com/scottf/32/61316_2.png) [@ScottF](https://forum.knime.com/u/ScottF)\
**Post date:** [February 14, 2023, 9:05pm UTC](https://forum.knime.com/t/svm-learner-rejecting-1-column-due-to-incompatible-type/6813/4 "2023-02-14T21:05:27Z")

</div>