This project demonstrates how multiclass classification works in a neural network, and how it is different from a regular MLP that only performs binary discrimination. This project is an interactive tutorial. Please open the code and read through the comments as you click on every script to see how it works! Instead of a single output neuron, the output layer of a multiclass classification neural network has one neuron per class. The expected target value therefore has to be a vector of all zeros with the index of the expected class activated to 1. For this there is a "vectorize (number)" function. In order to generate an output vector that can be diffed with the target vector the output layer's response is not activated with sigmoid (or anything else) per neuron, but the whole output vector is instead activated with the softmax function, which answers a probability distribution and sums up all neurons to 1. When using a mutliclass neural network for classifying the output vector is scanned for the index of the greatest probability. That index represents the class.data:image/png;base64,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 project demonstrates how multiclass classification works in a neural network, and how it is different from a regular MLP that only performs binary discrimination. This project is an interactive tutorial. Please open the code and read through the comments as you click on every script to see how it works! Instead of a single output neuron, the output layer of a multiclass classification neural network has one neuron per class. The expected target value therefore has to be a vector of all zeros with the index of the expected class activated to 1. For this there is a "vectorize (number)" function. In order to generate an output vector that can be diffed with the target vector the output layer's response is not activated with sigmoid (or anything else) per neuron, but the whole output vector is instead activated with the softmax function, which answers a probability distribution and sums up all neurons to 1. When using a mutliclass neural network for classifying the output vector is scanned for the index of the greatest probability. That index represents the class. reportAttributeOfdraw a list of numbers as vertical lines distributed evenly across the stage.

de:male Balken _ _ ca:dibuixa amb barres _ _ 0.8 0 1posslicewidthstagelengthpen sizesizeleftstage2Draw a picture of the specified model of a neural network where each layer is represented as a vertical line of dots and each weight as a line between 2 neuron-dots. The line width represents the weight's absolute value, negative values can be rendered in another color.

de:male neurales Modell _ _ ca:renderitza el model neuronal _ _ 1 1 rgba(214,49,0,255)flat line endsfalseabsbottomstage100flat line endsReport a copy of the given table in which the numerical data of each column is distributed between 0 and 1 using the column's min and max values (feature scaling).

de:normalisiere Tabelle _ ca:_ normalitzada Report a function (ring) that can be called with a single row (record) in the form of the given data set to normalize it using the sample's min and max values. Use this reporter to create a normalization function from a training set that can be applied to validation or live data.

de:Normalisierung für Tabelle _ ca:normalització per a la taula _ Split a table into 2 sets by randomly assigning its rows to each partition at the given ratio while making sure that every category (as indicated by the tag in the last column) is represented equally in both sets, reports a 2-item list containing the shuffled and split data. Use this block to create training and validation data sets.

de:teile Tabelle _ im Verhältnis _ ca:partició de _ per _ 0.8each groupshuffledeachcolumnsGenerate a new block in the sensing category that either reports the class of a given sample data record (for the the "classifier" option) or whether a given sample data record classifies as the given tag (name) based on an example dataset (for the "predicate" option) in the form of a binary truth table. The generated predicate block offers its estimated accuracy in its help screen / comment and can then be exported and shared. By default training happens all automatically using a neural network with one hidden layer, observing the learning progress and partitioning the dataset internally into a training set and validation set. Optionally you can specify an exact number of epochs (0 = automatic), a partitioning fraction (0 = automatic, 1 = none), and none to 8 hidden layers with arbitrary neurons (0 = no hidden layers). You can abort / shorten the training process manually by positioning the mouse pointer near the stage center and pressing the mouse button down. Running the command again updates any previously generated block, i.e. you can optimize existing blocks by re-training them with different parameters.

de:generiere _ für _ in _ _ $_predicate$_predicate=$_predicate $_classifier=$_classifier$_tag§_dynamicMenu$_auto 0.8 $_autoclassifierclasspredicate01

de:klone _ _ ca:clon _ _ $_field $_thing11

de:Objekt _ ca:objecte _ $_field $_thing11

last1logitsobjecttopologyset learning ratealphapredictsampleclassifylength1outputsamplefitnlasterrordeltailength1layerabssampletrainsetvalidatelengthsetget modelweightsset modellengthlast1logitsmodelshuffleget topology2dimensionsweights111dimensionsweightsversion1_Layer_inputsthingweightsthingsetupinoutsolvesamplelearnerrorreshuffledeltathingadjust weightslearning rate0.1activationsigmoidCreate and report a new neural network with the specified topology representing the number of inputs, arbitrary hidden layers, and output(s).

de:neues neuronales Netzwerk _ ca:nova xarxa neuronal _ 5 1

de:generiere Prädikat für _ in _ _ $_tag§_dynamicMenu$_auto 0.8 $_autovar name_AI: var getterai1var_declare(scope, name)global1initsampleblocks222213323423get model1normblocks22labelide_translate(text)is _ ?def1txt_transform(name, txt)selectclassifycommentpredict whether the data sample classifies as , estimated accuracy: 210001099.9%.oldcustom?type3labelblockspredicate01

$_auto 0.8 $_autotopology1length23auto303length.25lengthcolumnsaiepochs0donefalselastlengthlogscale110rendererTurtle spriteflat linesflat line endsflat line endstruereadout1last100010%flat line endsaccuracyvalidatereadout100010%Train a single epoch or validate a neural model on a truth-table dataset (a list of number-vectors with the expected classification in the last column). For "train" this reports the accumulated activation error over the epoch. For "validate" this reports the overall classification accuracy of the dataset. For "confusion matrix" this reports an aggregated binary error table in the form: TP, FP FN, TN

de:_ Netzwerk _ mit _ ca:_ xarxa _ amb _ $_traintrain=$_train validate=$_validate ~ confusion matrix=$_confusion matrixshuffledPredict and report the classification of a given data sample - a list of numbers representing a single record in a dataset - using the specified neural network instance. The result is a list of numbers representing the neural network's output layer. The "classify" selector reports the absolute classification, "predict" reports the unrounded output of the forward pass, letting you determine the neural network's confidence.

de:_ _ mit Netzwerk _ ca:_ _ amb la xarxa _ $_classifyclassify=$_classify predict=$_predictQuery the model or the learning rate of a given neural network. For "model" this reports a list of weight-matrices representing the neural network's hidden and output layers. Models can be exported and shared among projects. For "learning rate" this reports a single number representing the neural network's eagerness to adjust its weights when learning.

de:_ von Netzwerk _ ca:_ de la xarxa _ $_get modelget model=$_get model get learning rate=$_get learning rate get topology=$_get topologyAssign a pre-trained model to the given neural network or change its learning rate.

de:_ von Netzwerk _ auf _ ca:_ de la xarxa _ a _ $_set modelset model=$_set model set learning rate=$_set learning rate

de:blockifiziere _

de:generiere Prädikat für _ in _ _ $_tag§_dynamicMenu$_auto 0.8 $_auto1initsampleblocks222213323423get model1normblocks22label ide_translate(text)of _deftxt_transform(name, txt)selectclassifycommentpredict the data sample's , estimated accuracy: 210001099.9%.oldcustom?type2labelblocksreporterclassCreate and report a new sprite that can serve as a layer in a neural network of sprites. It responds to 3 events / methods: 1) setup Initializes the layer with a list of 2 numbers representing the number of inputs and the number of desired output neurons. 2) predict Reports the result of a forward pass of a single sample / record with the precision of the activation function, i.e. not rounded for classification. If you wish to use this answer to classify the record you must also sum and round the list of results. 3) learn Adjusts the layer's weights depending on the given delta vector and reports a new delta vector to be backpropagated to the previous layer, if any. You can either use a single sprite as a SLP (perceptron), or clone it several time to create additional hidden layers for a deep neural network by using a forward PIPE for prediction and a backward PIPE for learning.

de:neues Perzeptron Objekt var_declare(scope, name)globallearning ratelearning rate

data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAeAAAAFoCAYAAACPNyggAAAQAElEQVR4AexdB5wURdZ/PTMbWWDJIBkRYYm7gKgY0FMQSQu458kZ8M4zoYgBs7CY0ylmvWAWvzuEXRAEMe2hGGF3yaBIliBpSZtmZ/r7v97ppqene6ZndmbZUPurmkqvXlW/7q1X71XVKweJP0EBQQFBAUEBQQFBgWqngGDA1U5y0aCggKCAoICggKAAUf1mwOILEBQQFBAUEBQQFDhJFBAM+CQRXjQrKCAoICggKFC/KSAYcP19/+LJBQUEBQQFBAVOIgUEAz6JxBdNCwoICggKCArUXwoIBlx/3339fnLx9IICggKCAieZAoIBn+QXIJoXFBAUEBQQFKifFBAMuH6+d/HU9ZsC4ukFBQQFagAFBAOuAS9BdEFQQFBAUEBQoP5RQDDg+vfOxRMLCtRvCoinFxSoIRQQDLiGvAjRDUEBQQFBAUGB+kUBwYDr1/sWTysoIChQvykgnr4GUUAw4Br0MkRXBAUEBQQFBAXqDwUEA64/71o8qaCAoICgQP2mQA17esGAa9gLEd0RFBAUEBQQFKgfFBAMuH68Z/GUggKCAoICggI1jALVzIBr2NOL7ggKCAoICggKCAqcJAoIBnySCC+aFRQQFBAUEBSo3xQQDLga379oSlBAUEBQQFBAUEClgGDAKiVEKCggKCAoICggKFCNFBAMuBqJXb+bEk8vKCAoICggKKCngGDAemqIuKCAoICggKCAoEA1UUAw4GoitGimflNAPL2ggKCAoICRAoIBGyki0oICggKCAoICggLVQAHBgKuByKIJQYH6TQHx9IICggJmFBAM2IwqIk9QQFBAUEBQQFAgxhQQDDjGBBboBQUEBeo3BcTTCwpYUUAwYCvKiHxBAUEBQQFBAUGBGFJAMOAYElegFhQQFBAUqN8UEE8fjAKCAQejjigTFBAUEBQQFBAUiBEFBAOOEWEFWkEBQQFBAUGB+k2BUE8vGHAoColyQQFBAUEBQQFBgRhQQDDgGBBVoBQUiCUFhg8f3mjs2LFZmZmZt7LnOOfFsk2BW1BAUCD6FKjbDDj69BIYBQVOCgWysrKcYLRT4bcmJCQclmX5v+jIi+w5znlcBj+VYZEvnKCAoEANp4BgwDX8BYnuCQqAqf7J7XYfAqN9Gr6jFUW4DP5phuU6VnAiX1BAUKBmUEAw4JrxHmLRC4GzDlAAjPQdMNUP8SgN4e26hlyH69qtIOAEBQQFqp8CggFXP81Fi4ICtiiA9d13wUivtgVsAsR1GYdJkcgSFBAUqAEUEAy4BrwE0YUYUKCWowTjvBKPcBV8Vd1VPlxVxSPqCwoICkSZAoIBR5mgAp2gQFUpcNVVVzUAjtfho+Ve9+GMFj6BR1BAUCAKFBAMOApEFCgEBaJJgWPHjt0KfMyEEUTkjJUa+HAa80VaUEBQ4CRSQDDgk0h80bSggBkFsHY7xSy/KnmxwFmV/oi6ggKCAkSCAYuvQFCgBlFg9OjRp6A7reCj7Vr5cEcbb83DJ3okKFBLKCAYcC15UaKb9YMCDodjeKyeNJa4Y9VngVdQoC5TQDDguvx2xbPVRgo0i2GnY4k7ht0WqMOggACtRRQQDLgWvSzRVUEBQQFBAUGBukMBwYDrzrsUT1I3KHAgho8RS9wx7LZALShgkwK1DEww4Fr2wkR36zYFvF7volg8oYNkuuTQmnWxwC1wCgoICkRGAcGAI6Nbja41bty4NpmZmVMyMzMf8vkpnFejOy06p1Bg/vz5uxDZCx9V17l0P513ZNO369Lp87X96M9r0iglqg0IZIICggJhU0BjwBioM8eOHfsNwt/gP0f8/LCxkahxsiiQlZUVj3c2De/uGKQoHsSfR18e9vnnOY/LGIZhkS9cDaWAJEkzo921Ace2qSj/IEn0vjOBdq7vR2+uzaBz1QIRCgoIClQvBRQGPGbMmOvQbI4sy4MR8jnEPyD8EvkXIRSuhlMAjPUmt9tdjPc3A10NZkGpAcMwLNcBrHA1kAIpKSkvoVvH4aPljncv2T8RyL6AV5xM1FiW6FpJpqWQin+Gfwje8qpDpZL4ERQQFIgqBRQG7HA4HjFixUDtkCTpSWO+SFtT4GSUgJEuRruvwjvh7TqGfdVX124dAVdNFHjvvfeY+d4YxeZuTF9R+k5aAfGEupOXaBpw/wKvutMQYW3JVjBhoaIGMYQTFKgOCjjYOg6YbWuLxtIt8kV2DaCAj4EOq0JXhvlwVAGFqBoLCuTm5r4PvO/BV9W958Ol4AET3targB5B2A0S8HmQgN9CwWF41QkVtUoJEQoKxJgCLOWyNGTVjCIhWxWK/JNHATDOW9B6VZgvqiuOmTDjUhKR/4ia0aYAGOfV0EK9Gynes45ucT+xPfe/VvV75tPXPQrpL94yaifLxNcfChW1FbFEvqBADCggGGwMiBprlFdccUVzDMwvRKsdxsU4o4VP4IkeBXJycq7B+7kCGI/C23ao8/ilh1aOA2N9d2M69Q1Wsdc6OtazkD6AVCxU1MEIJcoEBaJMAcGAo0zQ6kBXUlIySZblqL07xsU4q6PvdbWNWD4XmPD/xcXFNQFTvRt+m1VbvrIFXI53em7vfFpAMj3oIVr08wDqwvmhPJiwUFGHIpIoFxSIEgWiNohHqT8CjT0K3G8PLCyoWOAMqwMC2JoCs2fP9oARPwPfqaysrDGY7R8BPZk9xzmPyxD/K/KK4M8dM2bMpWmF9Cqk4DcqPLRkzUCy2usB8EAnVNSBNBE5ggLRpIBgwNGkZjXgGjt2bA80Ew8fbcfniBl3tPEKfFGmwKJFi46A2c7GGvFL7DnOedwM4r8jVM4ROxyOJxAnqJdnQBJe7PDQJxsGU0POC8eHVlHTacD3MLzYRQ0iCCcoYJcCggHbpVTNgRsTw67EEncMuy1Q6ykAdTUz4L1QQ/fJzMzkzVXUI5Mmgwlv9xbTe3I2Rfx/L1TUekqLuKBA1SgQ8T9i1ZoVtSOlAAbVhEjrhqoXS9yh2hbl0aMA1NV8rEg9w//o8OHDE6Rs8jqS6SqSqMP6XHoxGq0JFXUlFcWvoECkFBAMOFLKiXqCAjWYAlgTfg3d4w1bHRMSEm5CnLovo6NeJ10KJnzJ2n40nfOi4YWKOhpUFDjqIwUEA65lb12SpLJYdTmWuGPVZ4HXnAJYE+bv5EFf6b1ZWVmNOd7rJ9rjctJQSaIb1vWjmzkvml6oqKNJzdqAS/SxKhQQDLgq1Ds5defFolmn7KWHdiyctC6d3l7Tj65Z2Yc6x6IdgbP6KJCbm/u+JEmr0GIrt9s9BaHiui2nzU6i4STRo6szaKSSGYMfoaKOAVEFyjpFAcGAa9nrzMnJWY8ul8NH1SXKFeWJnvIvJInOdUj0dpyTNoMZsxcMOaqUrl5kXq/3Pl+LU8aOHdvSF6fTC2ilR6KrnTKFNNSh1ok0FCrqSCkn6tV0ClS1f46qIhD1TwoFHo92q8cd8Y9DfTixRz6d6vYQG224Bm0sFQwZVKjFbt68eZ+g+1/Dp8qyfA9CzUViqEOrHGEE35gw9BEh7US1ukcBwYBr4TtNSkp6RZIkbzS77nQ6/6Pi67uKtmCgfBfeFkOGpHy1UFmr1Kt5ocPhUKRgfDM3jxw5soO+h1Ux1KHHE0lcqKgjoZqoU5coULsZcF16E2E8y4cffrgf0sxtYVQJBZrn8XgWqGdGjcDBGDJgz4N/R6+yFgwZFKlBbu7cucvQnQX4ZhJdLhcbzEDyhKuqoY4TmCKLCRV1ZHQTtWo/BQQDrqXvMDc392V0/VP4KjtIRgVgwBcjvBrrhEtGjRoVdAOWniFDSu6iV1mjM4Ihgwg1zeHdshQso1/8jnsh9HPRMtThhzSCBL4nWypqRwLtXN+P3lybQedG0IyoIihQIyggGHCNeA0RdYLAhC9BzSozYUhGt0MyujUnJ2co4u9CHf0ZGPEDWVlZ8cAf0gmGHJJEJx0A73YNOsFXG0p4x4qJSqQ1FwtDHRryCCPBVNRA2ViW6FpJpqXQuPy8Jp0eQtgR+cIJCtQaCggGXGtelXlHfUz4ZpR64G05l+ylyw7k0+Ajv2rwGJRvB9N9Dvj46MogpE9xu90F48aNG6wB2YwIhmyTUNUMVlFRMQ2ScCmaHWn2XmNlqAPtVcnZUVFjIGPVurBFXSVKi8rVTQF8t9XdpGgv2hQA03wtLi4uGYPrdOA+Dm/pOpYdpOwdH1PGse004tBqUyYMaekAcE5yOBzXe73ef2Bt+BUw52aWSEMUxIQhh2hTFAdSYMGCBdsxsXqVS/BeA6Rgzo+1oQ5uoypeqKirQj1Rt6ZRQDDgmvZGIuzP7Nmzy8E4HwbjTAHjPAVoboef5vO3+/L+uye+ER1yNUB2pbNiwlw6d+7cZWDs6WDsuzBw/wBGrBj257KqeMGQq0K9qtXFu3wKGLTrChEPcNVlqCOg4TAzhIo6TIIJ8BpHAcGAa9wrqXqHwDh3gxHPhH/E52dyHjA/USa56D/NB5BMEpKVLhgT9jH2x8LZpFWJ1f6vYMj2aeWDjDjAJO13VObbkgiTMlMpGOXVaqiD26uKFyrqqlBP1D2ZFAibAY8fP/40qCPPGTFiRJOT2XHRdvgUADMuRK1FO+NTaVmjUxE94YIxYYb6+OOPt2DwjmiTFtcPxwuGHA61woeNi4tjBux3XaEZlpNhqMOsH+HkCRV1ONQSsCebArYZMJhuS6ggP4Mk9DPUkV/Hx8fvQh6rOE/2M4j2w6AApB7lmrpPm/SEKjrZr2YoJszAYOJV3qTFeMLxgiGHQ63QsNBqBFxXaFXrZBrqsOoT2SwQKmqbhBJgJ40CthkwmO576OVF8IpDOhF+Bpjw35QM8VMrKABV9FKsAy7zQAW9oGmfgD7bYcKQhKO6SSugEyEyBEMOQSAbxWbXFVpVO9mGOqz6ZTdfqKjtUkrAVTcFbDFgSL6d0LGh8AEOTPi6gEyRUaMpAAasrP2tT2pNvyRp9vm1PtthwgwMZh6TTVqMOxwvGHI41KqEtbqusLI08LemGOoI7Fl4OXVARR3eAwvoGk0BWwwYA3abIE8RrCxINVF0sigAxrkQ75SvqaOFTXqTVzqxIUvtk10mDHUm776O6SYttU92Q8GQ7VHKt5zA34HfdYVmtaVs8jqS6SooTjqsz6UXzWBqW55QUde2N1b3+muLAde9xxZPBM2Fshb8e1xD+r4hX34USBNmwmce3cyGG5RC1FGMdSgJw091btIyNB0yWdcYclZWVgcs/dwLzdR09hznvJCEMAHwWlxXaAJKNdVQh1lfw8mraSrqcePGtcM7vQt+ms/fxXnhPFOdha1jDyYYcB17oXYfp6ioaDZgt8LTV41Pp2JHPEcD/OiDqxIzju/YrhYEY8IM45OqqmRJi/HE0tdGhjxkyJBEZrbwZW63exveAy8jZINO2RznPC6Dn86wyLflgl1XaIagphvqMOtzOHknS0U9fPjwBH53YLglmBTtwDt9Bn6Gzz/DeVzGMAwbH5E6MQAAEABJREFUzjMJ2JpLAcGAa+67iWnP8vLyKtDAc/B0HMyXmTDHzfxlB1a07FR2cIlahkHBUhJmmJO9SYv7EI6v6QwZg+5tqampxXgmZrjmMyUUwnFZNsNyHaRtOUeQ6wrNENQWQx1mfQ8nr7pU1HhXtyQmJirvF/9biVZ99JVlMyzXsYIT+bWHAmEy4NrzYKKnoSlQXFz8JqD2wtP3jbrQvrgUjgZ6mRL/tmdplxRP+b/UQgwGQZkww2GtuUZs0uK+hONrEkPGQPs5+s7ndiWEdh3DzvTVDVmH3xOALK8rRFmAO72AVnokutop07sb06lvAEAdyjCqqPFofPzyF4SqOw0DaUS2qPGOeGL7Ev6fgEJFFzz0wb7kqxscWJTWaArYfuk1+ilE5yKiwJIlS47jn1nZUMPHknhDlhUijOhd79/5SYUkSc+rMKgbkgnXxE1aav/thieLIWOAZeb7B7v9NIH7gw+HSZF/Ft7rfciR4U2vK0R+gKuNhjoCHiLMDFZRwz8C302W6DxJprfwv8HnqlVMf5Aket/OdYl4N5+h0sXwkbqLfTgirS/qnWQKCAYcxguoi6ANGjR4Dc/FtoHp56RWpseSUK66Gx/dlpMvhcmEuXJN3qTF/QvHVwdDxsB6J/pUFeaL6opjJsy4lITVD5YN1qDM8rpClJm62myow/SBwshUVdSeMmony3Qlqn4Br7qg1yXi/U4B4EXwVXUX+XBVFY+ofxIoIBjwSSB6TWpy1qxZh8BQ31D7xFKw2bEktRwz/hce35LzIuqEJQmr9WvDJi21r3ZDuwx5fQb9ui6d3oa/emUf6myFf/To0XyZxjNW5RHkP+PDGbRqqOsKrSrXdkMdVs9lNz9cFfWygclsvEjZf2G3jRBwz+H9tgoBI4prIAUEA66BL6W6u+RyuXiNsYTbNRxLYpUkZxORFjSF6u0/kw/l3B0pE4a0dVItaWlPEqOIGUP2yjQRUtLXaPI8+HfinLTZiiE7HA4eoKHZBGR0nOTDGRSbnesKrRDUFUMdVs9nNx+q6W3wQVXU2xOa/gP4ov1+bwRO4WoZBQQDrmUvLBbdxTrtHuB9C15xvCPadyyJBwm3kun/c0bLIzQDjPSOSJkwo+PNP3FxcVG/7pBx1yTPDLlXIb2DgXkifBe3h7oEY8gg+kMx6L8tnHifIa8rNOublE11zlCH2XOGk2elol6e0jEcNHZhH7QLKOBqDgUEA6457+Jk94RVYl7uhOFYkhkDJqii71/fj4ZUlQmD+dc4S1pMA6OPZjoYQz4Ql3KRTOSMZns+XM6xY8eG3K2M92nrukIfTr+grhrq8HvICBJ6FfX8Zv1GbklsHgGWkFVceL+9QkIJgBpFAcGAa9TrOHmdyc3N/RWtfwSvOD6WtN+VAl5AfGXSFiXT8ANV9Pure1ErDNpVkoQZbV3apMXPE47XM+S/n3KRth4fDg47sLIsj7YDB60EL0nsBXyfzMzMK+3UUWHquqEO9TkjDX9o2Lmfl6RIq4eqNyYUgCivWRQQDLhmvY+T3Ru2rqT0QTmW1LS3R0kQNcaYsdEX1wdtnS5SzgZHgwkzYkwEqv26Q263BvlYSL/q440BQ30jlHe73U+jwgF4AhN+JjMzM2QdPc6722Xe88/W564vdca9+PcLer2vL6vvcdBzLNM1Fh64XbHAK3DGjgKCAceOtrUOM5hfITq9CF5xG5NauTYntmBb0E1Jpg3IPAjv7yQauT6d7uDMaDFh4KnTm7SYVrXAf4MBfQ/WhFujr+fAh+W2JDTb9FWj0//vgiMb/9S57EDXsCoLYEGBekIBwYDryYu2+5gOh+NJPezHTXqXQfpls5UjwIT5zLC+WIlDFf3Y6gzqwwkwzyqroxkP+/qySYuflf2aNErpUHYolreLzcMk6wa7Hsx3KvcLvhnU0nfbrafC3fnVmisTPe7Jf9vzdY+nd+Y+pebXtjCa/QVNc0DPmDjg5v/TmOAWSGNDAcGAY0PXWosVTG8p/pGXqQ+wN75R41VJ7bYh7ZIcNADh6/D+TqZEh0xzNgymhlwQTSZclzdpMcNd35+GQoPwOPwyRwIdyDqw4nqmYSw83uv8cPCC8fBygK3rCq3w1mdDHUaaZGVlJeEdxBnzo5ieF0VcAlU1UEAw4Gogcm1rAoOEthbMfV/YtLckEe2XZRoGafcrmWgT5+s9yrt6i4nXDpXsaDJhRlgXNmmZMVzZS5+CnvfBn43njG/mPlbulL1IIhVd58E7WRkuSm8Y1xVa4a7vhjrGjBkzCGvfr1RUVOwEPadb0amK+RV4v2zNrIpojNVFOpYUEAw4ltStpbghBS+UJIklH+UJjjoTuixP6bicE2C0D0sOuhxqaV4b5iy9v3FtBmm7ZjEgRE0drTbik8oGYX3yFLfbXTBu3LjBallNC+0wXPS5HDT9Fhz3CdB1mLeMmnkkxwzkR9s9EgnCcK8rtGqjRyZNxhLGdkzS3pOzqc6PO/gu24Dp3j127Ng1+F/6HnS5Gd9sU4Sxco/GCrHAGzsK1Pl/hNiRrm5jxmDhtxac27RvKpjuRgyip8OfL8n0gBkFkP/C+n7UiXx/sWDCwFkjN2lFynB7FNDgngV0f48VtITPjEJK+ifIJ8NHy8k+nBHhc4R5XaFZI1I21XlDHaxiBuO9DIz3E9B7B+jwFP6PeiLUXLLXTWce3ULQcmh5UYjw+w1cGooC4vqOItbPLxhwrClcS/EXFRXNRte3wisOUtmZ3zTuNpcTYLL3lxC9B0a8gNMGr5iq/GoIaUciwDCjLglzm5DUT+p1h9FiuPwseh8XF8eWGkzPXuvh7MYvKVo3/5Gt8/U39titqsAxnREJ67pCwAe4umqow6Bi5v+b4Xh47TiZA/8o3Ur20oR9P9E9OxfT6IMraQw8YKLl7pg/f/7eaCETeKqPAoIBVx+ta1VLeXl5vKOSrWNp/V6U2rOfJClrls0TJXrAU0HXofA3eKNTTFXqM2PFhGfPnl1tlrRixXD1dILKcrLH42GVJe+G5mNh+uKw4w285V+dd/jnrnFO+gHLAxEfB5IkKezrCs06W1cMdUDSDalibuU+SpccWgum+ylN/P076lX8G8XJlUfrBxzbRj2Ld5uRKNy8z7EsMzPcSgK+ZlCgZjPgmkGjetuL4uLiN/Hw2swa6rThixqnvYu8CkzqJyXEU1NIw9qaL/I1h3zFVKWWgUismDBQUyw2aVUHw+W+sx8xYkQTqC4/AI1fQHq30+k8EwNrOv5Bv0Q6UvfFB/M/udDtoUGSRHl4J8vX96NrKII/vDve4MPvXkIf/TbphYuu23LaDPFwOJY0Hl2dQSPDrX+y4LOyspLAeIOqmCVJOtizeNfmG/f+r+y2XV/QeUd+oYYes+0SRH/e9wOY8q6qPM5n+EYurgoCUffkUgD/3ye3A6L1mkuBJUuWHMdg+6K+h0sbdxuDgfMV5Lkwl3++RyHlyRI9jnSAQ75iqlJfgIE8JupotQ0MSHx0JqJNWtXJcNX+cjh+/Pg+UDvzJrcJSM9yu90D5syZs2pbb2ryyLbcH5DHd8cisOewviiPP1DgfmZ37kSu0XcVHe+RT7eAAd+Gd/LC+gx6eWUfasBl4fiKioppYDClqDMSjKhKm99OL6CVHomudsr07sZ06gucNdaFUjGj4/hXoEUNvO6rpu9YMPvP+37s0qH0UALyQ7oJ+35UVNJSSMgTAHgHXqRuxbc+FKFwtZgCggHX3JdXI3rWoEEDNr5RpOvMZR817/8hBgzlWNLadBr+eyOajvIf4Y1OM1WpL4g1EwZ+W5u0ThbD1dNCr3LGwHobBtU/L1y48BDDHHPR1JQKegbxY5gI3YIwG74c3spxWfaBw0eSoeL8oqKceDOXBovJ0jtgwANkmYZEopKuynWFWid0kd75tIBkehDca9HPA6iLruikRzHBaJOZmRl0FzPe11p09B6Hw9H+4Z25t9y/Y+Fd8R73Dciz7fjik59SOoEMSpX9wMkTHCVh/PGVZZeWlibjO3nZWC7StY8CjtrXZdHj6qTArFmzDuEfX39BgCM/uf3VGMgVqVeS6PmGR0mCdHU5+nUQ3t/pTFXqC8AkYyoJc1u8eQiSpXbd4YRRI/5qNHxhPIeLegHHgoy7lAFTZWemcgZNNG3DugyaRBK9eVf3LJZ2xsybN+8VDLoz4BPwTB2lyjVZZsjZHOc8LoOfgfX7Ulc8/U0mOgPSrp9hj575tMntiVwljbaewsPzhOxcSIaXIl4lV5MMdWTZVDHjgV/FhOhMvK9eoPfTD2+ZO8TpoeWYlIYlyfOVn/9qfS7tjm8MlESg7V3AmcQMHfGp8NN9firncRnam7Fo0aIyEn91ggKCAdeJ1xjbh3C5XLzJo0TXyrUvtx/6EUmkHEtKlukWSFdbwZRv08FoUeRrpiq1TEQwoFgzYZRX1bGE+/Dm2UMe35rT4I5dnx87xV30r3+3GPzpQVeyZvgCbVQLw0U7mrNSOasA6/pRJnnpN2aWUPtOxWDPUjCpf7Nnz94O2j2Zm5vLDHkGxzlPLefwtB9opyTRfZB2n/hlELXjPNVXRSWNtiK+rlBt3xj2LKQZEAEXOzz0iWpNzQgTyzQmEoMg7aqGMgJ2MaNtCOm0CEwwC/8L7UD3SZgQ/bBlCCViojQTg+gsMN8mgLPt3JKT3m85iPbGKcbjSJKk+aDtO4wAE8ediD8L/7DPP8t5XCZ83aIAvp269UDiaaJPAQzue4D1LXjVJe12NJiEwf12zoD0e39+OrUAw3gf6cDziAZTlYDRHAaYqDFhZrhWEm5z97G+f9m7jNKP7XD/o9W5pYub9NpeIiWMYsMXsZBwtQc0RIKpnBlU2ansoLaQDHMhkXVAXjsM9l8jDNth3fcfYAw/GlXRKiJMmiJSSUPangkcEV1XiHqmrkcmTQYTrjZDHeGqmHNzcy8FE/wI/wvKRHQVVObFh+l79Nl00mn6kLrMnGb9aGtCMzVnv8fjuUlNiLD+UEAw4Przrqv6pHwkyasigVR2w2M9Jnwv6Y4lcZkjme6G6nMTx/UejMDPVKW+LFImHIzhog+KaUe0U462v4VXLE31Pbi96ZG45HZLG3Vd8EiH4U9N6z6uL2Bi7kaY7HLGc2sqZ+4Ab7rCgP6XtHx6hdOQfh+GxDWN45F6K1W0ig+TprBV0mBCfKb4SR+OR4cPH57gi0ccSNkUc0MdmNDY2sWMh3gV37emYgbj9TsvtCadrohE5Qy8ilvUpBcVNmivxPlHkqS75s+fv4vjwtcvCggGXL/ed8RPCwngV1T+CF51qaWlpTc5iVgKVo4l/ZxBPRRjCxKNJ4nMNpP4mapUEXEIZhRSEo6E4aoSLqRczdIU2jqA55kEleL1Xq/3H6x+hGSqiSPcn2j6UCpntS3dpiuCWvRc5O8Es9uOMGIXTBWtIo1EJV1WVsab87YBR8eEhISoSG/Kt+OkS/HtXLK2H/HGPqCvugMtI5mO+KkAABAASURBVFIxG1uuispZxbW00Wn0daMTx7HBfDXVswojwvpDAcGA68+7jsaT+p3/BPOafEvzodsxYLLEphxL4kZ659MqqKVtmapkeNWDMQYw4WtGXfLW2nTSbguSveR3eQHq+km4ZgwXMKYOkk3MLWmBsWuGNTDY+u1y1ncKa4nKpquOq0nZAQ3YqZB+/dZ+9fDhxEOpolVcPQrJtkratxHoQV/deyFdNvbFqxQohjqcNFSS6Aashd8cKbKqqpiN7VZV5cz48lM60OImPTmqeqF6VilRT0PBgOvpi4/ksSE1FqLeInjVtUpOTv5LqUyPSb7bksAsh3MhJM7nSCZbpioZnj1LuI9vz1mcfnzHdk6zP+xMnPhJk94Bm6bQnqJSDofhMj6jh4QZE0tadlTOal/AaDLJt+mK8yCR/xXhPPTtMMKouFCqaLWRcFTS+B74zPUq1G3ldrvDOquMOpYuUkMdmARERcVs7FhVVc6Mb0tic8pt2o+jmsfgO1WonjVy1MsIvoF6+dx1+qF9s/8pGMgf8vkpnBeNh4baVl37U9HdcUfjIYdkibRjScv7UxwXhjJVyQyXN02BaftJuFn7V3QYfIQ13oyFaFmjU2l28/7b1duCwNwHw2sq5Uqoqv1G05KWXZUz91jZdEWVm644DSbCkuQYMLd/czpa3o4qWm0rHJU0tCBsopKrToG035Ij0fCnF5BtQx3RUjEb+x0NlTPj3BfXkD5ocQZV4APmNPs42fvp3Nzctzlu8CJZjyggGHAdedkYuOMxAE7LzMw8hkGRN3Q8j0d72Oef5zwuYxiGRX5EDmrbpZIkLdNV7pSamppVLNHLUEVvhNR7erJMbDSCeq+hvVBFW5qqlBLoEKuUIc0GSLgjD61+orGn9G21nYIG7Tvc32HsJb3W0TE1LxYhGB9LdRFZ0uL+gL62VM4Mq226KiRW4XMWVVRUTJVlOSqqZwWh7seuKlqtYkclPW/evE8Az7u0U9HvexCPmsNShqWhDp5Q4nu2bSgD79VvF3OoTlZB5SzrcRe5kujNVmcTn/lV8xO8FaVtKw5GrF5X8Yiw9lNAMODa/w4JA9FNbre7GAPgDDxOMBODDRiGYbkOYCNyYMB+a8FAct+AFeQ2HktiCZecFE9E6+ADHBivC5mWa7jvfLz4WrTFEwmAEaHvt4PB8W5sJR2rn5ycnLA3aYWjclb7feyEpSslCxOjKh07UpCE+LGrilbR2FFJQyuiSMF4VzePHDmSn0GtXuUwrZBexXf1RoWHliw6s3UnMN7L8O1+ggnlDiAPuO4PfWBjMKgjn4n3qBjKwKTRbxcz6gV1kaqc8T3vA2IE+IVjpvtWy8F02JmE1AnXprzoyZkLv9l8IkfENArUs4hgwLX8hWMwWoxHeBXeCW/XMeyrvrp262hwGNAWSpK0Sssg6g3GOFIuo68hBRdABGiOISffkUAHWMIFXBq8uZNoCdTJliplDKIBG7PQVsyZMHcWz2lrk1Y4KmfGy35dv0pLV+qmK86rqKio8rEjxhPMh6OKVvGEUkkznQBb5esKgcPU3d9xzOKVDdolxsklW+I85bYNZZgiC5IZqcoZ3ztvnPsfwhYqerfP0Ma+uBQ1Swnblx3a8fy+b5TlGiVD/NRrCggGXItfv4+BDqvCIwzz4QgbBaRRv7Xg1mWHP2CGCxV0OiPDYMTWl1j6LYdI8C0+NDZhyNIJF5/wMo1cn053nMgIjJ1MJjw7xHWHmAzYVjmrTwbmm4m4YukKoeKwjhmVY0cKshA/4aqiVXTBVNKYkLEUjNdOV4MmvdQ6kYaQdNvg29RUzP9t3r/tYVcy/XH/CszxuBkitLmWiO6BBN4+XBUz6vm5SFXO6MlKfNtsmOR8PcLcZv1knaENpSjZ6/b+oWjDvRK0RUqG+Kn3FMC3o6eBiNcWCmBwugV9rQrzRXXFMRNmXEoi2A+rlNVNU49snze5SUWxBr47vlGjLYnNVYa7UymQqEDdpdy9gO6VJbpNyTf8IN/UVKUe7GQyYe6HySatGXgHszAR0a4PRB/9DGtwPaM3brpSy8FMonbsSMUZLAxXFa3islJJ49mrfF0hVPCWu5hlkghMmBrjmwMT/g10j1jFrD6LGkaqckaXXvDKNBXfL08+VHS0JDXtaEGD9ph3allK5LwjPxdkfrd3lpIQP4ICoEDUGXBWVlZTDExXYQZ7K/xAtCFclClwxRVXNMeAzQN/VDAzLsZpRKZnuJBSl7GEyypljCz3OWX5zHOO+Bu8+k/zASuY4ZYQZQBmP8mULiUQS3YKagze7yPyOry/kynRIdOcUHaAMcifNHW02mFIWrxJ63owgHuRdwVo9z+sqSvXById1PGmK/zDXZum23TFFTIzM6N+7IjxBvORqKJVfFYqaajQp4EepYAL67pCSP+2DGW4nfFZbimpc9/jO0sf3zbvErRTJVcVlbOXaEKFRK87JfoQ33mi2pHCBu3X5TXu1lBNq+FpJfuOn3PkF9Oz8SqMCOsfBTAeRO+h+R8Jg9EGYHzX6/W+CP8jBpeXkK4VrrZ0sqSkZBIYQNTeHeNinMEYrkx0NuijSriKaccepXtGIW8vvOKOOBP7P9gts2tGAe2TTY4lMVAkpiq5nupPNhOGenUy6MXnmz0In4RvERcX9yjyQ1rSOuaiqcluelZ9Fg4xYY3JsSPGHcpHqopW8RpV0k/tWhAPevB+BML/vnGjnlpNCTE591MxI/Nm1G2KUHNg5gEq5uHf79nqioKhjqqonD1OGiC76BuXlz5FZ7X3ftDV4LPZLQZo68AoU5yD5KJRh1Z+3itfgVfyxI+gAFMgaoP4qFGjkvEPMxdIjR/gLWDCPMNHkXBRosD9UcKjoWlXfmiaXsI1Y7iSg4axhKtumjr7x2LeePOihqQyoqjjzI4lcbFiblCi8SSFZ6qS66r+ZDBhs13O8+bNuw/MV7vuEN/5lWofjSHWfSfhmd/Ub7piGEiNU8F4YnLsiPGH8pGqolW80Gr42ZKevOurPSgrgg+4rhCTDUsVM+AVhzGE9wkE3cUcqaEOpQH8VEXlnNyYzmwSR0WOCloCVPod30tfPOVCnpQZxz8aemjdluYVx/z2TKCucIICFDUG7HQ6zwE9T4EPcBhgLgvIFBkRUQCSVg9UZEkUQfTc7rjGDrfkZLzlEpEi4RoZbo8VtMR4DrdBgwZsE5gHXLUzfEzkVLNjSSpA73xaJclkqo5D/gvr+1EnCvFXnUw42C7nUJu0+DHAfAM2XXE+GBIP4BHfdsQ4quqroopW29arpFu7Dz+ApQlWQ5PD4VCkYNaMYXIS9nV/Kn6zMBxDHWr9qqqc0/JpCuHvaCnl4H+kO6KKw2R1w8w2F+WWS84AtXhDb/nX5x/9pRB1v1eAxY+ggI4CUWPAmLmyKk2H+kQ0WNkJKBGzSYExNuHCAvNIDprXrN/regnXjOEakc6aNesQ3u8bunz+ppRdzT0LaJFkuC1JhYMU/RyFaapSrauG1cGEMeGxtcvZZJPWA2Cw8VabrvgZIP3G/NgRtxPKV1UVreLv4bMlPeTIzwdSPGWEiXcfMN4dkiQx87GlYsaEpkTFFyrERM7SUIexblVVzr0K6EPGWXKY+Fs/j+M+v/2r1NMm7ktoqGh+fHlqsP+6PV9vqSA6aRoOtSMirJkU4MGyZvZM9MqUAhjUqnz1myliZOY3aL/HKOEiO6RzuVwzAaQfOK8F82mNPHIabkviPNWHMlWpwgULo8WEjW2YqZzRllHdbqxGubm5vElLs6S1okGnO42brrgSpELenLYTDGc7p0+2r6oqmvuPd570UKdx/Z495eJdTSqKIRhyLvFxNCXCP2DGIVXMDGfXg7ZQV5NiqGPNQFK+OWPdqqqc+ywnxWjGhn7ER+mu1uE/UIFlmc8b97wP/5cBqucOZQdntnQfLcJEYb2ujogKCmgUEAxYI4WIYHCMj4QKYCJ7UO8teNUlQbpT1HXd8mk91j7Z1KLLQ6RZtWLA3msoqKnK9f1oCNn4A2OM6u7oYCpnG90h9EexpDXuQOHSuc36nQcp8BVI0s30dUHraj12pG/bLF4VVTQmE367mEsdcRfvSGgCLW1lS+3LDsmJXvdnUElnYbLWLjc3dxLWz3+oLK36b89CmkEyLXZ46BP9TvpoqJw755GiTscywlSvRHdrvZWo1OmgzOkdxg5CXoBWCu93/k17lrbERy+kXxBIOHMKCAZsTpcam4t/7LJYdQ6z+HvAKI7Cr4ZfAP8yBte7xo0bdxmY0gBIOAGzfF1f2DqVV00D1w0TJkxowulSmQJuS+J89lBb5qk7pjmt98h/f3UvaqXPs4rn5OREhQnjmW2pnK36oeZjwJ7U//jWv5tt0gJD/ivgonrbEfBVwVVWDUcVjW8i5C5mYFXOgx9yJUt37frslEe2zi3EZE2vKQFIdFyPTJoMJrzdW0zvydnkiJbKmXu3IYOuJIme5rjqZaK/TW07ejO+82fVPF24f+yB/BcAU3LaKlJooCsTUUEBjQKCAWukqDWRebHqKZh7b0goXRwOB9tgftvr9W5FvBMGmYmIv+V2uzeDeZgyaKfT2QT9YrOYCBSXWlpaehPHgh1L4vLfG9F0hD/CG11bp4v+Zcy0SleFCUeqcjbrC5hvJvIVS1dgOAHXHaJsDKTAqN52BJxRccFU0ZiAhbWLGc/YHt/UqmPOBMpr1K2ZJNNyaDWuiUpHDUikbPI6kukqMMoO63NpntNDyyWivgaw4EmJXuBdzqrKmYGxhn8uZpX/5Ljq8RxTe+bT+/jf4CNXzdV8NZQk6a6Bx7ZdCdH572qeCAUFzCggGLAZVWpwHpjMenSvHD7ajhnFejCMfXPmzFk+d+7cj6AmfBbt3QI/Er53bm5uQ0h0lgwaHdJvTuFNOFNUCfrJjiO/d0vObSSTdlsS4BV3QR5VYFC7HAleH0SgcxKFNFWpgyb0M2xJGNJ9HzzXcuCZAD8LEw1bhjUAG+AwYHdFZtu0Qsol3Z9uk9ZxZPeFpK1s0kI8bAdG2AH178VkaDp7jnNe2IhMKpipovEO/VTMqDYcHsv7+K10WF2gRWBIASpmTNyUzUnfNOqauCeu8WPQarywPoNeXtmHgl0aUok1zN+EOHLj+2JblSPBfHlCaAuDTHQITHZCWj5NUVXOXHFVf+qO7zIHODVDGw6Znu5RSM+C5jyRMFU9P7YtZ6Ms02aeeDIe4QUFrCggGLAVZWp2/uMx6N6vUCuOCIU3FING/SXwioPk3ALSwDUIJx6luH982GKgIi2US67Hrxk5zE/F/eCp45v/ntBohlLR8INBO6SpSn2VcJgwBtKoqJy5fStLV1zGnpkk6HEYPgM0OQWMvgA0H8xlofyQIUMSMzMzmeGWod421OcjPtmol81xzkN5Gfx0hkV+xI5V0aD5T/u9yfyO1qC/Ee9ixiTuE3Tka/jUF0+5oDXwDpBlGhLnpB98kxUUVd1pKmdpsnmgAAAQAElEQVSi68LBBua7kg1rqLuc1bqrB1J7o6ENlL3bvZDuGT169Cmguanq2ePx3ASGPRnSeNQs1aFd4eooBRx19Lnq9GMlJSW9gkERk/boPCakBUbUA9IKD7g/gimEZMRcwcxDCnrMkJ9y6NChTDDF3k9++n2KTNJn8d6KxMsOFjRBe34q7pmtL3zsx5ROsqE+YUBTTFU+e2F6x4Ayiwy0F1QSjqbKWe1CcRzdZbR0pZZxWOG77Qh9UzZpgVbXgwb/ANMM2KTF8KpH+W2pqanFSDPDDbZRjsuyGZbrAD4shwmCpmJ+uu2wi+K8FX0HHN3SU48E3x1rKV4FA7JtixnPqUjBqHvzPaeMLHd7aJAkUR6ky6iopNek0xXRUjkT/nacRU0dJoY2khrTDSgmPM+rCJXJJELNSVA9P75zfm9Jom/Z4IxWUKMjonMnkwKCAZ9M6kfY9ocffrgfA+BtEVYPqDb2QAFd/fsP5Y09pWzkfiCYQsSMGKrrpZIkLdM10gkMIUtNx0ky97vi1JLfz3hmx7yFYEZ+Ku79cU06gwP7G5lGZUwSujZ3H9oCxmK6Bg01csAmMeA2ZcKAjZrKGV1THNZ9J2FG9JbR0pVSiB+ocQOOHYFWIa87xPN+juoz4UEC/NpzDDvTVzdkDfRtEGD9DGUcdiY5P22SRsMOraPGnhJLFXNI5ADg50TAVtMSXS7Xw3rDHZCII1ZJbxlCiesyaCYGsVkSUZVVzugjMU4zQxsNE2ksq6ehMbkGcKaqZ3xv7zhlus5TSv8AjHCCAiEpgG83JIwAqIEUwHrsy+gW26JFELnrWbybBhzbRt1Ldsffs3Nx8vmHf3kODPQnMPiIGTHqs3pU3ylFAuKMYMeSuPyuLwu2eSUyNVV5xrGt0pQ9Xz4ACcT2JjFMJnYBL6/vIoAwLcu3Q02Yj0Qb9PM20PHPCxcu5PtckRWZA/PNRM3feuZTwMQB+YpDW6bHjqDS57X3x9CniwHDV/ktGTVqVGeuBKbIzPcPHI/Q/8GHI6A6tBxtUKZd9weAAEMZyxt2Xut2uFbe/dunn4NOl4KRfoT+lgA2bIdn428Ac6sT1xViLfUdMOCIVNKaylkmntDZ7g86YKpyVhGYGdrwumho++/oYCjVMyYDl+N5Puq1jmKxR0PtogijSIGTjUow4JP9BqrQPgZFNn0XMRPuVbyL/rzP7zhmk2FFa299fFvOv8HkRmLQjIgRY6BeiLqrdI/WG5LDSDVdGuRYEsP0zrc2Vdmy7Mj0R3+dsx9tfIT1RVubxNAXvjBiG+P2eSfy2LhCN0h/do9Z+ar6B751zIBNV3ooMLqQx450m7TedTqdn6EOaxGqwnzVLjATvpMTehUzJiY7kPcUJlpBVczNHcUjJZkGrs+g6wEfscvJyVmDyu/CS2hTm6DxpMXtobBU0hGrnIn+ZdzljP5ozsrQRu+fiGkVVPU877f5+0Cny9Ly6T8aQhERFAhBAcGAQxCophf7mPDN6KcH3rY7/8gvNGGf2ckfipNlev2xrXMHYNA8I1JGjEH2SUNn7lXTvDsUkoKykUyS6Pnl/SlOLVPDSE1VQkIL2MWNZ7gfeP3og/71BBMahTJbx6ygtg5QcYfadIU2KSsri020jsF7snXsCHDvo29jUfds+Gi5ZzIzM1/FGvROPPNsILW9i9lsVzTqR+TQvul1hXZV0qwehpQ5E4NW2CpnkmkBSdS/zB34rfHDQIsxFZqXAEMbfVbQBi7HBDKo6nmDTDd4JPoXwwovKGCXAviW7YLGAE6gjAoFMGi/FhcXx7dRTQfC4/BWjssUgwJrk9tQiSOA72n1wISz16XTa/dvm7skEkZcVFTEA/1WFSGYymCoPbVjSla3JanwHEbDVCUGTr9dzpIkada4EOfLEFgFbOuYldtwDvrltoOXPNP2YsJzWRoqAdOZimcPyxoS+jWOnz+KXgKum9CPkNf9YQIToGLmXdFA8GNFOfmdhwXOsNyCBQu2ow+8gcn0usJgKumqqpx7ZNIYkkkz1KHvuJmhDQyMfzt9BX3DcKFUz2x9C/8vZ4vrBplawodDAXxn4YAL2JpKAQyczEgeBjNOgVTHt1Ldjr5O8/nbOY/L4O9B3kv7XSmU0ywd0aDuxmQvLVzVm5pA5csbpmxLxHl5eRXA/By85jD43qsmgt2WpMJUxVSl1S5nTCZMN2apbYKOARI06gQw6AuLNh7eFt9k7iFXSmM8l6WhEpSNhkq5lZkErbZpEj5kkheVLDD3sHcxc8PBDHRwuV2P9tmeMt+eFXBdIeMwU0lHrHKWSDOsIWX7GerQbHpjCSHA0AYY9d3d8+l97g97/O/wpMF01/P8+fN3UQlNhnSt4eQ6wgsK2KGAYMB2qBQbmJhhBbPcDUY7E/4Rn5/JeWqDkJb5OMvuNcmn0JeNu6vZVuHFLhct43ORDAA8thlxcXHxm6jD668IiMCMhmdmZvZTEvgJdlsSihXXo5DCNlUJZhd0lzMYalAmrDRs8cMM+pFf57T7w6F1s/87f8ETwOW3ixu01QyV4HnPA8NZitCSQRvXoCGxs/UmvZELi56Enw1G8qjL5WqHb2IS1s/9Fv9DYYuWKhr0+h1t8a5uXlPV1oKRpzlNJS3R3VAL/wuDVNgqZy9RgGENPhrkddKlYJaXrO1H060MbaQVkqaxwPsIqnre2J+ay0SnYu33e+0BRERQwCYF8G3bhBRgdYYCYCIsBSnrXZ+ndqf1UEerDycRYexSU1rYw+kBE86gHmqOHUa8ZMmS42A+RsmAd8OqaAichiX1Ckgdk37W4dcAEAnHVCUGTD+VM5iN6S5nMIKImDAkJlNLV+im4kBbRYL2eDx7wXznox1LBo31WL9z0FBXbwa9eIe2givaP2ivHP0LUDHbbSdaqmhMUpgB78Wz9sGE7Eqz9lnl7JXpZnyPLrNyqzwww6C7nHv9RHtcThoqSXSDy0usYtZfkqEY2lBxh1I9M5zHS3dB1aMxbM4TXlDALgUEA7ZLqToGB8b0viRJX/JjzWmWQQdclZYBMYBhPKFjnO/nZWrvlGkZ1oUv0ueHYsRWF/aTD0moY0kMZsdUpZXKmetbeTDHsJiwnU1XalugrdWxI4VBg24Bu7jRn4aozypaBDFxmO9UDW80VNGYBBxGL56EZ/fo8OHDEzii+mionFVcZmFSHBXhO+c+6Jnv0iSfoQ21DjQGQVXPK/tQO0wQknrnE5uHVauJUFDANgUEA7ZNqroHiAHmRjCK0mJHHL3T6iwql1xuPGU8fCm82T21TZD/yfoMUiwCIa45MBRT1XRJSQkfk1qpARLxN3eHLk2lIY4lMWyPQtoqS2R65hP5j3WSj7PkGLYt55wc+7cohbJ0xf1kD6ku5LEjhrPw5Rb5NSI7WqrosrKy1/BAfDSsY0JCgnJpR1V2OUNtE6ByBv4Ax20EM7ShVoAmJajqmeHinTRVXDfIlBA+UgrwYBhpXVGvllNgzpw5v+ARlF3RvClrbvN0ZsDIIt5wsgWRz+CNTjmmBCY83VjAaTNGjPzz4fXu2qysrNZqhp1jSQzbM594Y8zrHPfzMiX+af/yTqkVpfdBsjdVOfvBGxJ2mPC6fhTU0pWKEs/VGPFQx44AYun8jktZQkVWEBXc0VBFL1q0qAyP8CA8u3tzzm7br/gwfU8ymU6yGMjMQ5INqnI21jExtHFAImpc4qZU8v3ZUT2vxnIJ2hbXDfpoJoLIKCAYcGR0qzO1sO7IKk9mtrQquW3yDw07M1Pm5zsfA9NyRAIZHjJlmZRjSmZneFFMRkbMeTqfhHan6NJULNHLJNFGMrktSQ/nSKa7MfAFWJxq5j5Gd/+2uKMeNpx4MCYM5psJXEEtXaFccXiusI8dKRV9P9BIzPdFox5EE3c0VNGYLPEyyCo8aKsdCY1+xPfGG9CQtOfwHVQ4JHpVf31gsJob+hF/61frYA5UOOgcfMtvVHhoyZqBpEwKoRkKqnrm+liYngo1kbhukIkhfMQUEAw4YtLVjYoff/xxMZ7kRnjFzWvat8VhZ5KyQxYD3H1Q7X0hScS7psnkTzumZFKmZOkYcZYkSUCnZPOO6FvHjRs3ujJFZOdYEsPyTta8Jt2nVUimy5k3rs0g0009XDeUN2PCV4669F+oF9TSFcoVB+mXzxW3mzdvHt/+o+SF++Nyudbr6RRufSv4Rp5Semx7jinRrOoEy6+SKtqHeMsQShxxaJWyfvptwy5xx5wJvpLgAb5L5fpAh0zXgXk+DW3My1iPrdzEYFEVkyhLQxs9C2kGJn6LHR76ZOKooWzUZowRDd4Jb6h7h/PXZdCZmCz8ypobTgsvKBApBQQDjpRydageJJEleBzVhF7qK23O5w0qipSJgeaf5KEPJYmYSbsBZ3R+x5SMhWoajPgjWZY/UtMIk71e7zystWm3L9k5lgT4yZ816v7vJak9eLMY0Pg7SaYX1vejThThn5EJH3PG//WBzmNPtYMO0u/DYKB89toOuB8Mnqsb1o6vdLvdfwRd/u1XGIVEl9L935KX/r0unQrWpNMdv6RTi6qi7ZFP/8D3EZGBDt7lXAyV89mHf728U9kBKnXE0dJGp4XsEpivpnLuUUjvyBKFtCUdytAGN9ojkyZ7SNo1+uCqFyVwY87T+f0evmZQzZBpMiWRcXe/WipCQQHbFBAM2Dap6jYgmAfbC2YDCXTMmTj0v80GvIDBrggDbKrsoIXeBGLLVpeCCmYXFwQcUwKcmQs49wmm7HfpA0Q002NJxl3O3zU5vT/GyQUmjTTFoPyfr4YQtIQmpTayjEwYfbwdDNLPqIgRzZgxYwJuOzLCGNP8TKgH1GP5cokWcXFx/8VkiE1RZgMW5MdvdJycn3RKVloBpZOD/gq1bXvMpArXp9M8SIaZa9KIN95F1FIkqug1husD+cYlbvz7hl2oyJXEUXOvM6yhAvTMp03uILakoREJaWiDcUnZ5H283SWeRhUlzlEHV3OW5iVJuksxuIGcNRk0TJKqdN0gsAgnKFBJAUdlIH7rOwUWLFjwmyRJD6t0KExpd8dRZ+JkX7orldJbGMA/90g0mCRSjNP7yioD2fyYUmVh5S+YSyFii+D17r9oV7v04Z6OY9/5JbHVCgC4PESK2UgrwxrRMFWJdkzdY1tyfk3xlGuSaCgmjGcwPXZkRJ6VlRUP1ftgcN1rIS0PwcQnDwz/LWgIls2ePVvZAe0b7Kca61YhPdWHk9JWUH5aPt3uLaPOUN++JUl0rSOBtkCt+vy6/pQRbhvhqKJZ5Yx2Amw5d4QE3L1kD1VIDvo8tUdAF2QiReWMfk/pnIcv0QDRdxUdhzR+C7Qft2HypV1vaMfQhooK7+OaEkfC6Ldbnk2nleylCw9vUIokSZqH96OonjnDKZO4bpAJIXxUKCAYcFTIWDeQ9O3b9wU8SQE8u85PtR/eVSJSmDLC0ZCYZvCZR4+TBmNQXM9ABt8EadNjSshXnMPhO3vG7gAAEABJREFUUM9/Kmn8nHHo0KGzka/dvvTfFv0HFTviCQxi2HMX9noT6r/vARdwfWBVTFUCn6VjqRCFv73/8SfXYQBWJgFIoz/y7RioAyRhqI5DHjtCPU3FDGa+D4P6W1grzrG6CjEnLnemS/ZGvJbM/WXf+/hv8mPbc+dxXO/5yry0QsrtUUBj4oj6eWVMqiJUUYP5hVRFqypnksl0l7MqBec36EB74xppXcV3pqmctUyLSI9C8lNJu7z0KUD1Z339DG2gTHH6Xc/HsA79VquzadDRrTT46ObD+PZuVoDwg8mDuG4QdKiSE5X9KCAYsB856nciOzvbC0Z4g44Kdz/YZfz7MtF8zkM4DerDy/h6Nkifg5EXyTGlpWBqfNUeqiuuU2pqahYkQO0ccbEz4aevGp+uFPY/tvVaJ8lHnU7nmWBaAetuGHTDNlWpILb4gcrSz9IV2gxqrAMSreWxIysVM3D+bNG8ks07y3/YTg1mz5vPx7e+UDIj+Ek/voOu2P+TBMlwCaTbNlYoTiugfb0K6DloOCJWUQdTReObucLpoeWYxFnucm7lPkIZxyuPnn/aJK2yqyYq58oC619WSXtcNBwQneE7wKsuwNCGWoBv/lXEm8Mr7qCrAb3d8iy65NAa12M75ytaAVbTg47iukGFQuInWhQQDDhalKwjeMAIf8KjvATPEl+i1+t9nRLpWqS1TVnr+1K3PqvpULGDRiA/7GNKYMDGteD7gEdxaH8hBsTrvm/U5fd9cSnUwn2MzjyyuSX68a9x48Zxewqc/iccU5X6esa4laUrMExLJgwVst+xIzDkePRzMCReSxWzsV19mtW0pYmUeOYPdAQMS35ya+7000v3sioc8x89ZNC4PO5A4eas/StUoM6SlxaDsfNkQc0zDSNVUZuporcMoURIjQEqZ9OGkXlR0XpyyV7akNSavm7cbYaVyhmglo7bdFbQ+wBIhlddMZjylZ1N1Nd4T6YGN/YkpEJr4P0TVM7vbkynvs5Eut4j0b9UhCIUFIiAAgFVBAMOIInIiIuLywYVdsMzE77wgVaZl2IAHwEOoG3KWnsWNeWjQ5CabpIkYngy+btRvU1JXzZ37tyFkiTx+U81uzcGwpGcQKjYcvaQ1HBFSqe3OO+Cwxsp2VPmt1mL81V/QR5VSDJdjjTbuEagcxKNXJ9Ofpa3dKV+0WCWrsyY8JgxY/4BBMqxI/S7G1TRyi5mOypm1Atwe/pQg6SD5DxnGR3lQjb0j0F/3FOLv7uuqKiIGQrTWVkn5nITz2XZDNv/+NZhKN8Lrzi8uz54F7Psbk6LREWtV0WHUjkrnTL8pFaUEDQeihnURalpFxqKbSVNDG2wWL0FTHmRT7uh4Rk9evQpeFfPahknIrzr+WYstywgmR70EC3Ccoi4bvAEfUQsShSodgY8dOjQBhioHseA9SvCXfCzIDG0i9LzCDRRoMDs2bMPAo1yWQNCdk9P65a1H4P43zgBr2zKQqg4DLwzpDCPKWHge1Kp7PtB+kF8Cx8g5HXo3axyvuPLNX8B3k+TveX0x30rfpAkSdushe9HO77EKKCKDmqqcnUG9WE4K7+uH4W0dGVkwujP39DfVPTFbxcz4IKqmM368M1galjSlDytV9FxtbzCS/e5HKRoC/Ly8kpzc3NnwCdggtQRbd8HOGbI2RznPC6Dn5EHWFbFkoN417rC0ADL7tJWh0nRbnDCrg9HRe1TRZ/j8tBqSPB97bahwEn0QlFSw56IF8GfiwkO9x9Re26DuaGNYVa7pKFp8VM9q62Antqu57RCYpjvUHaGaqgDceEEBaJCgWpnwA0aNOCzoPdh4OqCJ+B1qSugXvwGg5h+swSKou8ERvsUwEDOVoq+9NVo43a7s7FO+BEG1Yc5D6GyKYvj7MGE30DIA+YhhEYXcEypqKiIjzVt1QEOQnwC/Cy0NWDOnDmKhKweSzqtdG//p7blXINBU9ushe9mAb4bjRGD6bDqMVAlLlOiQ6Y5G8DkgD/AgfnatnTlcrnuBYKP4VU3BpHekOq1XcxI23aY1EjfD6JGiaVUqleRQnU7CerPuaevoP1GZJggbQeTfxLviBnyDI5znhGO1ckkEVt+8urKblyXTso71OXZjjJOqIbNd1Fn0JluN90FZCnwLLEjCO1AA22X81MLlrHEOpNr4V0rkw+Oh/J4h1O9Ep2YNEpU6nRQZp8VtKEvJjX4Pm+BluQ2dZf0VSOH3Qic/O4QnHBgvn67nlkLIUl0GJKwYqjD6hs6gUHEBAXsU6BaGTBUPheA8V5i0j02IahKVybFIutkUMDhcNwoSVKpr222XDWwRwFNx4DptynLV05QR9s+pgQpjQ1pPKfW5RBt5YOp+Nly7pZP60miV1AOoYqeB6PTNmsBPkAitjJViQlDV28xKXavgUtzPrVkSEtXYPSaihntMpPZpCLBN226O1ottwrlbHJs7UeNB3Wg46zOV+Ew6HeXJErqXkj6zWpqcVghmGWOTDSF/P8eWptOt/pnhZcyqqhRm+1XfAdGZbrLGeWmDn0L2OUMaZ4Z8F7QtU9mZuaVphV1mXYMbTA4tCTKLmmvTBf89fdvX21WoSkbuJi9onrmiOrV6wZ7ZNJkPNt2fEPvyXhvarkIBQWqQoFqZcAY0IOppIKVVeUZRV2FAuH/QAplu9Aa04LE+UZ2drbDbFOWih3rZuvtHFMaMWJEE9QZDK85DLgZGHD7aRm+SKlMj4GB7sc63DAwjuGcbcWI72s59ou5zdP/BaatThwYXPU3guFqA7rVpisVmPsINSh4b4ChjHMB86QkSSGPKAHO1MlZ5NyaS406ZdIRaTZhmbESjE0qYtC/s/sKipqd4Z4F9BLo5yf14h9/JqTssZWtVu23jOgivBuWtMNDJNELyY3pTKMtZ0jzh4HoSXh2jxqvK+RM1eN92jK0ocJDS7LpkfYjNm1ObCFN2p2n7bzmcrxPTfXMabwL7bpBKZu8mNxdhe+qw/pcepHLhRcUqCoF8H9YVRT26+MDD9YetI32cQnI6qFARUUFG7Df4mstfeXKlbf1/I4OSl4K2JTlgyE7x5RGHf/5F8Bfjm9iA0K9u0+f4Djb3IXq8HGOSxI9v7w/xXGcvRkjXtGg45OLG/eSudzoJZk0U5Vmm65C7WJGOe8kHgNJ/d85OfavMtT3g/vPx4w6FdJhHtj1ZfFOujPeRQ9LBHlLX1DFOGsugEJTz4M4DrTw7rr+lIH8iNyWMHc5q42gbU3lrFe7q+Ucml1XyPl6v6o/dcf7zMFzJKr5WGp4Oq2QnlHTxhCzqWtKHXGj5zftQwua9qaRB1fT6IOrKNHr1mw9q3XwLvyuG2Q75F4nXUoSXbK2H01X4UQoKBApBYIxxEhxinp1iALGyxogpU4bOXJk2x4r6WcMpOqygd+mLH78UMeUzjv8S7O/7l224lQ6zmddi7iOz18GKfhUX1wLiiV6GQPfRpLp9GSZbtEKfBEjI17auGvShuTWvlIiXUQxVbkeKlgsjL7VcTUpa9YYmDUVM57R0lAGJiRTUa4N8OEyYWZa+mNGun7RmnS6DKLwuq4/UaClMT1ghPG9jYnVzp/oqqeQlz6BFMlnn3XZoaOR7HJWsWIS9W4C0edq2iw0Xlfom/hooKsHUnuXl2wZ2lArYQnMb9czG/14pc0Q6lK6T35ox8KuejqszqAe+L4Drhvs9RPtcTlpKJ7hhnX9SDPSobYhQkGBcCggGHA41KqnsJD2luDR/wPPLtXlcinq0V4FZLkpiwF5XRPrwpbHlE4t3df/L1uXvJ/qKVVxczX+JgOODTEuqDnZTjRB6rk/P51MLxPQM+L5Tfv9dMRpalv4DAyu/e9uM+KAmYoZTPVn7ojRgwmwYQfl2JG+DPCW54T1cMZjRvqyTQOpPVRAaUxTfX404xfkUUWxg3ijm7LBzYe7FegZ1FCHD04LMFG4IpRhDQ1YH4HKGZOos5Alu4kKMQkKaosa3x1vBOS+tnK73do69o6zqKmjgvib5PcBdIqzNLShlOIHS2CvItAMbiBOB1wN6N8tz77ZIdFXoMPy9f3oGs53EVleN9htOW3GuxqOZ3kUjFo5Psd1hBcUCJcCPNiFW0fA10MKQPK7E4+tSqqXQ0odijT1KKDpYGbzOY5QsZTFcb1/sPP4nIVNe//ukUw/t4tv3P2/UU7iMVmrdS2YXYD4irXMRZA8PkU7zRMlekCDNokwI37748VnbEtszmYiTSDommHHN9+B5wqwxWwGzHmAtbztKBQTNjtmxDjZ43mk8gqaVu4hZWLDedH1J7BhInOYHHQJ6Lj5RC7ZMtTB0jvWjW0b1tDhL0b8WFwcPZuWT9/Dm++i7k8B6nCv16suSUyBlqIl9+FoKeVARd8dOBUH+m1omEhjrdTZDIS6zFhNdz2/t+DT1/12SafTbGhHtvHSB9c186cX0EqPRFc7ZVIMdZjBiDxBgVAUMB0RQ1US5fWPAsbLGkCB10eNGlV51CSRAixloVxxGPgUwxrLGp7a8IvU03l3q6LyVQp9P408JacMOLo1zpfkIAnMTpN4OEP1kDxYCq4gmSb9nEE91Hyr8PJvdryprh8bYS46vP7aJ7ctjDfmm6UhKfPGq52zZ8/mYzJmIGTFhL8fRAHHjPQINvSnO50O+jsfl9HnxyqetoJ2g8GEZagjUpUzmOPKCif1BsP8pqKc/qk+k3EXtVeG2t1LAdclzps3j1XmX6NeKlT/95gZ2vC6aGj774jPrgMs0BlVzzoIv13PPQpJ2SWNPl+C7+uPepW0ro4W7Z1PmqGOnwdQF61ARAQFbFJAMGCbhBJgRMbLGqCKvofpYrYp68ULu54KKfkDDJqaYY0pX66/HVLDYJIw2HJFnT/3yCZkY+jz5aHeDRMmTOCd0r6cysB4LKky1/xX3cWc3WHU5grJUWAC1XZfg8bfjBtnbuJSDy9Jkq3bjsyY8NNtMmdA8nTr8anxDf1oMFTrJaevoA1qXnWEvBuYHHQp2joGrzpTQx1VUTkn+3Y5+wx0nLE+g65XG1PDUIY+Gnnd0xkWWpLbilxJV3Pc5w9UOGgYb/rzpU0Dh8MRoHpmQLxTv13PnIcv8FSoox+G91NJc5mZTyukV/H+3qjw0BJhqMOMQiIvGAUEAw5GHVHmR4Hs7OyAyxrGjx9/GgMZN2W1Kzu2Efm83uhnWANSg+kxpaYVx6lX8S5U0VxqaWnpTVpKFyk1OZakFkN1HQ+GOhiS97WYICjX/c3O/fjfcV4vG/4IkJJalx/uenbRz34GPVRcaoiJBKux582ePfuwmhcszMnJuQP/WCztK2CQNll9+pyS0P1s7E/NPRKNg0r2FV12tUUhCedj1sMMDV3UmtUMdbC6NxKVs0wUsMvZzFa01qIuwn0CPfxU1PfuWPh+l9J9hz0kOT9XryuUSDO0oaseEMV3YKl6xnt6x1gBKuXrKkrpBT+VdAa9vLIPNTDCqumehTQDEjY0i4wAABAASURBVLMw1KESRIS2KYBxwjasABQUIKyt/gQyKOYMIaUmevmyBmSw4w1EG5La8OYY6l68x3n17z8syc3N9TOswXAssZjdpjTksP/eJ+CezKZLuY7e89qcqlaWpMpjSRhoLXcxr+tHmWAK61HH1EjE0KL11Kr8sKmtaTD0xmh7DJ7j3whtOT5mdPfu3OmSJAU9J6w3NWkLcQyAwOxMDXWAZo8WH6bvwVhMaWbVFdA5wLCGCgumFvLaQhVWr6ImiR4fdXA1vwfKP3Fd4V3QGnyjwpuFdlXPal1MNi7HN/IRt815mkpapiFxTvohmEq6RyZNBq1qoKEOfhLhayoFHDW1Y6JfNZcCcYbLGjIzM69kdS/CD95tOWjohuTWHu5995LdQ6G+vIzjRm92TKlN+WHqVqLdH8BVWiUnJ/+FI0ZfrDuWtDmx7Xtgdi3Qr/+CUb4PyUbj5L5BU7F0BbXr+8CjnYVFXHEu2UNX7/2uLEl2r8akwo8RYy16KvK0Y0dKhSA/W4ZQonrMCP2w3B2NwX4SpK25YCL7g6CrlqKeBfSSRORnqANM7wHk9Q2rA5K5YQ09jmCqaD2cGoeW4BzEn23lPnFd4cfN+hSB2d0fahd1OKrnNWkUL8kUcN0gvplNbg8NkiTKQ/lydZc0Gf6kbPIKQx0GoohkSAoIBhySRALASAGoYlmVe8LuLtHTYH7LAaeonHcmpJyO+CZ4jOP0z/V9qRvHjZ7XRY3HlIYcYfscJyBd5L3v4/4NtaMjkEgVFfNjHcZe+V1Klw8Zsnfxb394cMvcn9Evvg2IsxRvZunKkUx3y0RK3xQg30+qpyThoe0Ll2HQ9rM1jeKbnE5nI4QhndkxIzMmfPWo4W9iQI+KqcmQnbIJoOxml4lvd7JZ4wQY6Bmgcj5R6h+zq4rmWmxow+OlXDBbxdDGRdBUYB3YszmheeqT7UdcibXXt0DHax0JtAUTmuf1RkXGjh0bnuo50fq6wb6r6Dik91vAgG+DhPwC1rFNVdLdl9FRr5MuxUcvDHVQzfir6b0QDLimv6Ea2j+WNCVJ+tLXvTaIt4e/Dfl/nvzlpl8lL1layvLV0QIMbtptSp1K91PHMubvlcUV5Gizr0HzpTMv7H0eJGy/6/7+unQz17M8llQcR3clu8nvujllkJRoPAZJU1OVj2yd2wRM8wwfIz4I6bcpVOFB14i5p8GOGQGfnyR8xJlw7X3tM9tyvZrieZczaDIo3P6A+VqqnK1w4X2HVEWbGdpIrSh510MSb+qjI464GWmFlIuJw5g4on76XdQrBsTf36Ci1O+9+/rit+vZl0d8wQKYecjrBnuou6RlslRJC0MdKlVFaIcCDjtAAkZQwEiBEZW2nLUdtGBUcZIk8bVtCqhxUxaVknK3r1Jo8oNB+Q1kXwp/6HzDWvCPDTv3uODwurn37v5sFRi8n4rZ6lgS1jAneYk0S1fAq7ne+bQK0swDWoYugnzFVKXH4zmC7Nd8jDjg0geUKQ4MyPQ2I6VQ92Nkwigy3ZiF/Gp3WCaI2LBGsm+Xc7idDqaKDmZoA98Ym0YtQnvadYXGXdTrklrfcsvur5pf9fsPlFa8m5wyvgRUQN275s+fvwtRf1dCkzH5sGXf2Y5KWhjq8CevSFlTILYM2LpdUVKLKTB+/Pg+rHIG0x2Nx1gPrzhIim9k82UNSoqIN2VJvrVFhH7XF/pA/AKooz8/Et9gyKll+w60djP/qyzeE9eIfk1o0axR+fG8del0UWVu5a/ZsSQw30yU/saDJUJTB8npOZJpgUmhYqrSJZFy7Gju3LmWty9dNnbsyK39Am8zMsGpZD2yNedbSPdsPlFJg363Q1UasDtaKayGny1DKBGq27ANa2DSYVvlbPUYVqpo7lMwQxuYyPwOnDPhCZOjgOsKH+gwtvecZhltnmk7lFakdKD+x7bT1N+W0PgD+bsf256zmuvpPdaYm+N5Tk3Lp+/1+cHidlTSwlBHMAqKMpUCggGrlBChLQqAYSiGNQDcBhLFbZAUByC+BZ5dOl/WwBHVg9FNxwA3n9MITS1lcRnwdmMV85NtLu7zVeO0cQOPbtEYO5f/r3E3Dprg5xOswd2AUHOlMulvS7oVBcqmK4RBnaeCrgPAb/BGd8akXV8dwpryYbXAjBFXyPLHd3Qeu2S8Z5zZFZtqVSVUTU2+sGjpJaDb80omfk4WE2aVc3GUdznjccJy0HoEqKLtGNrA5I8Z8F7Qrg9/M2qj+l3PbHVtXXIbeq/lIHq5zQX700r2vExeCjD0gTXmuyqIbG+yU9viMJRKGpqWBZjkPeghWiQMdTDFhDdSQDBgI0Wil65TmFjljMHOz7BGTk7Oix9//DGbGbxRfVgMisplDWpaCS0sZTHOMWPGgPeOvRZMSdvFPOXL1UtbHt9/nou8u5X6+NmW0JS2JjZHjOKwXvc6mPB0TrA3HEt6tNhJtjYT9V5De6Fy1q4nZFyqhwR+9fp+NIQMf8yIH9ieMzjFU34Z+mypmtZXw8TDz9Qk6Oa3Jgya3Q4iVJskHLHKGQ/lkOmHPstJb8YSuZE7vSp6Qz9i9TKfS1YRmhra8E2MnvQBadcVQiI2Nbhx3JV4V//l5Y9Dw5JODvqrQ6L2bqq0RQ3NTA+plH714Qo7YC1LsF3SWKcWhjrCpmr9qSAYcP151xE/6XifyhkIlF3Obrd7wJw5c1YhrTisy/LZX/VCBe2yBqUQP2aWsm4YeeGNqqEMMKS3wNiWYWDVdjGPWnF0fwU5/FSMeY0UKRgYiWSZsqGOfo3P3HJGceWxpCOQOBolm9yWxDBmHlJMnizR42ZlyH9/dS9qpS/bArUtHzN6/+NP5qDf6matoIzYzNQk6lY7E+a+R6Jy1j8/aHI96O5/ZEkPEGZcp4p+3ivRiZ31EpWirbF9VtAGM5TG6woxgbG161lv6AMrw+C/RI6EwF3UZm1a5YVSSQtDHVaUE/mCAYtvICgFMLD5qZzBbAMMazCCiooK/8saMjOHcr7q7+8ylpY1PPX/fOmuk3/7cvi8efNyFi5cGGAb2gdDxcXFbyKuHQz+Oakl7Y5vjCzN3ZjspYWrelOTZA9dD6b8IJdAqrW8LYnLjf73RjQdeT/CG11bp4v+pWbu6UMNkg6S85xldFTNw8TBco143LhxIzb0I0tTkzk5OdXGhKuiciao+NXn9YUPrU0nVvX7klULJCLWoiTrsWBg+hukS7YBrc/W4sbrCqFFsL3rmZHIiXQq2l3Xo4ACdlFDQ3DHL+nUguHC8ZjMVdqSlilgl3SPTJoMOgpDHeEQtB7AOurBM4pHjIACrB42UzlboTK7rIHX5PQq5s9aZdyGQU+RnhCG3JS1ZMmS4xhY/Xan5lWuBeu7cbHLRYWQZsp7FtBLkkSWx5L0lfTxC/KoAkz78nLJWabPV+ISjVyfTncEO2bEcFaM+Jl2F897sNO4rQxj5quDCYOhVGmXM9SoD+J9Ke9NfQYMHDMhTY9V05GGG/vTOXh3//SrL9Pd3fPpfb88k0Rubq52XSGKlfUJhJqTJMl81zMgXHTiukHjLmq9ipo39LGRDlSx5TBpMDXcIWWT15FMV5FEHdbnkt83bQuxAKqTFMD/UZ18rnr9UJC82oB5ToF/yOencJ5dooRSOVvhMV7W4HA4XoFknAcmo6mYIXFMl4lCbspS22jQoMFriPOxEwREa5JPoYOuALO8HRwOemh1BvWwOpakVA7yc2/HMe2/Sj3dTAomqEIfa1pKp3XOI7Ozw35YfYxYUU03qzh+4ICrQTOv1xv0HDHoE5YknJWV1QGaiXvxbqez5zjn+XUEiS1Ql4NJRrTLGdWvSMunKeoz83tDnmZFDO/QQTK9qzd+gfKwnNHQhlJZotK4BPpQidv4wQRtrhkYmO880PUdszLQ5EyJ6NeMAtpnLNerqKFRsTT0YaynT1uppLsvI1uGOvC/2g7v9C74aT5/F+fp2xDxukGBGsmAR40a1RwDy4vw233+Rc6rGySPzVNgAI7nf1bQ6xgGfD7ryDttWWph/zzncRnDMKxVL1A+2ePx8JEMZZczpAxTlbOxPup1KywsnIABcZZahkHwksTEyp1Tap4SWmzKUsoMP7NmzToEPHxGWCmRIUJ83airEvf7kam9U6ZlFTK1BcgrKHN5iJgGiIZ2aGPqt816jgKkxmQQr3QyJcpe+g8bbKjMCP376Na5nabu/GwMJiF+lrVApx8xmI4wYgCzCMqEhwwZkoj3xwy3DGvw20BnXh/PBp5sjnMeysvgpzNsVVTOHicNSCsgdbkATVS6vY3pVsT4ekAEikshL33iM/epZNj9MTO0gbrvQhORp7+2EHmWjjUsKLwF3uhMDW5oQDJNpiQKKoWyPWhI/qaGPqBRsKWi7lFIASppK0Mdw4cPT+B3h++jBP+rO/BOn4Gf4fPPcB6XMQzDas8iIrWaAjWOAfPH5XQ6vwJV+Z+9PUL2t3IelyEtnIEC+Ke8CQNwMf+zoihAPESe6howDMNyHTWTw3BVzmodvYo5Li7uv1jX5bW4l7gcbfld1sB57M02Za09i5pymZl3uVx87KRELVvesJP7iDOJJxlqlho2QeQTkmk/JJz9skzDsFY5HHlBHWih3XYENaGpqUrg6+otpqeDIvIVQq3aXZJIMTWpl4glSQq6WcuKCaN/t6WmphYDfTZ8PLyV47Lspo0bFe+Ma7Ycfe5rBWiaL9ELyY3pTKtdzqyqL3YQb8TTNuABTyswzSWQhNsgXulC/AYztKHfFR0CDWFMeBUwYame12TQMEmib1kaRV1b7rQC2tergJ7DpCSdHOS3izqUitpMJW001IH3ewsmqsr75f8Zq075yrIZlutYwYn82kOBGseAExISskC+XvBG18tXZsyv12n8Iy4GAXgggvYVMXuOYV/11aVwVM4sPUOCG4zZuHbdHxiHpmLm5uNMLmvgfL0Px1LW7Nmz96Du2/CK85AUt6hpz/0y0ZdKhv9PHJKPoExRL2KwfV7dKY38AIfn4V1dY3Jzc//NhTwwSw66HFK0mbr5Rkh7pseWuC77lX2ogcdLd3ZfQX/ntOrtMmLQMkASBg6egICfImbDeSWH9M9W5zRZ1uhUG9CE+QodAqCfyhlpUzdgBR0GE7oEdNUfReoseWkx6My0NK2nZrJaPJihDd2u6Cd+GUTt1HrGEN/fNWBIY4z5kiStAg1NVc8M65TpOk8p2TqmxvBGH4mK2kwlXeqhTZJEVy9tdDovx7yEZ7E9FvtgX8L/7xJj/0S6dlHA9kuvrseSJKmvVVvByqzq1OV8/AMy8x1WhWccBhz5dlTOGPC6AdbPFjOkXdNdzGCYbMz5xJESoqfB6AIkXEgVH4GrsIqcEIbalMUMzas+66rktp3e6jT0CqQDVcbIhOsBL5NMpyfLZKamRDER1qinYkB7RknghxnEwUT6RZLpASQDHPIVU5UBBb6MeCfdGe+ih/E8mAP4MnWBHUbV9NVXAAAQAElEQVQMBuLHhHXVbUdlUHRhk970jZm6XodFJlJsOUO6C1A568D8omBCu/Ei+LvTdqgDT59kL836agi5/IANCTuGNswMdOjRsOoZ74w1LfpsJY783vhWzSbwhLXfyz1Ec1i9rABX4YdxWKioC6xU1D0K/VXSj7QdfvtnqT3wqUTckYvxP/lZxLVFxZNOgRrHgEGRYH0KVoaq9cfhH4+ZCg+CVX3odCDYDXXemRj4/dbFWC1tVDFDUvSzxYy6po7hMGFSJdQ2UHtnmwHy5h4M3iwFgFeSpaUs4GNjCR+pOGSSGm2WUq4D47hJksgUNxG4EBGBaZoeS8KkoAMRtcNEQjnuoj9mhH49hw5Zmqo0YzQYeC/DAL+u60+0A3iDulCMGIzEzEJXUJxmhYua9KKtCc3MigjUCapypiB/rFolB10KEM0eOOKXtjpMLyE0dRtsGtrgysFU0fhWWeMToHpGvXXwEmjH6+OInnC8kxnfwWWY9NmeaJyoHTwWjoqa6eb20KCljbttKnYmXBgcs63SizAWTLEFKYBqHAUEQ6txryR0h6644ormkiQpt8KEhg4NIUlSp/j4+F0MCaYUH0rFzHB2vMPhuBG4VVXurcA70LSezU1Z7csO8MCrofB6vZOHDh3aABIT34p0Iwrc8AFOJmqeKAVKtJB+H3a5XNO4gtkxo2CmKlseoRlcT/WqqUkM8NokQS0LFloxYtQxlfCQH5bDs9PcZunklU4IWsizrXIO1hgk4XyCGhUwEIjxW+luNDPUsa4fTfVKdEIrIlGpLJGloQ0rVTSkWyvV8zy8z+GSJPH3NhLf2uDK7lT+OhPpeo9E/6pMxe6XaZKWT7d7y6izLJPpLuqHOo1OWZyaNjqKvXgOWoFWUcQXOSpRMywKOMKCFsA1ggIlJSWTMMuP2rtjXMD5GGbSV2IQy0J6X05OzluQDE1VzHaJMGfOnF8Aq21cAsP0u6wBZYqzuynr5r1fD3V5PapUzXVbJScn/4UjYMK8U5olMmYunOXnIf3cuqYfDVYzIdmfi/jO/86eveP7QdQosZRK1SM3yFdcMFOVwHf/+n40hPAHhuZnahJZYTs9I0bl9fBRc/vjUmh1clsVX6HVLmcVIJwwLZ9y8PxGCczPUMeGDLoSjFr7Dhg/Pt6ghjYYBu/Uz1Y0mMwp+DbNJibKrucFCxZsR7kyScO3pknBvHsdzPDsXvmkXYTB+GPpg6moM0p28dGpEzOiqndE4slu1dEIDNVNAfwfVHeTor0oUOD+KOAwovhLXFzcf8F4P4D/2VgYaRoM/SnU3QLPLt14WQNnsu+xkn7GQP43jsN3JcP1hZCgJkHMesvrivOTPAF7x5AhQ5R1x7QC+hxSzmAM9gEqYODGGEWfQDq7CHUIktLUpPLyv28NcZtRj0IKaarSzNQktxGJZ0aMet3go+qWp3QkkuiFpMZ0ltUuZ4rwTzGAQqSs5asoMLAohjo29o/c0Abj0quirVTPeJeawQ3E+XsrQl3tukIqocl49heRd1KcUUW9Manl2THoiGIFLgZ4BUr7FAgbEv8nYdcRFU4iBaCC64Hm+bgJgqg6F5ilvW2zYTRr67IGHz5W30IsUAZyhNqmLDDfTIAo1wuCQS3FILsMadV1aty48R/VRO98Wg8JbzDSgVKkTI2Q/8k753WaE0eeBY/9tlDulElHpNmEpVuUWLigpirjaD6kq5LTV9AGi+phZeP98iZEZ1iVbABvTmxBD3Qc+5ZRyrdR1RYI1synA1DbEMcTHpLpXY+X5iFMRJniHDI9nVZI2qY3JTPIj6qKdpPjuUYVxWOMoPgW/AxuYPL4O2B41zhhxvUEJgDN0ZewrhtE/Zi5BzqMLS9xxOLfl1z4dkw3n8XsYQTiKlNAMOAqk7DaEQQMQlHsQUxw5+bmLkEfLS9rQJnmeCDHgDmfMxBOW59OdyLud70gBl1NvYgyQvpeDlXf+yfaUVFBzITNdojGDTy6dVz2to87dyqkw1I2QbBWa5qHF+SRYqoSpby7G4GfOwPq6AS/nCokoEKN5tqg1hMZMeCenJmZOSQzRj67w4g5B+JS1qIp1aUg0pTtd29ObM5WzL6/t1PmonDbv7f9mN1bE5rHjT1QCHR+rhiq5v8a8eF7KIQ/huft81GT9E9nN8n43ghzstLo/W3wsXIx+f+NVWcFXqI6xYDrwwvFoBK1wd5Ir/5Ht43Bet3zsfBTfvtcTvJqe6Qu/9f5p75l1Q5JpDE6cMcnHQ7qqod9fOvci5q7j5Xq+t/7H0NOe18PEx9H0yB5/QyYw/ABTiK6d30/mq+vEywuOYgHTlWV7ocPzO1xTBReClbfbln68R28ju2HP4oJXi//Cvhi4suluM9eaT2k5554VjSgFZ9L8FbQf5oPoFktzjgTWWG3DWY6f07z9Ph2ZYdo4LGtQKG5ZJR9gJQfTvyP5MIz86efUjpm5Dfs8IYR5mSl0a/r0HZMHHArSzExQS6QxoQCggHHhKwCqZECrT3H9pxe8nuOmr+s4akTiykuSU3rQ+hfixwSzQRjqwCjdHllmgIdcaoeplfJro/16YLk9mxGUp9FYNxu4HkLKuL/+hWoCYlGAvck2UshDUhwFeDi40pfcNzgE9DXW4BLGfQNZfUqWepw0VtY4tTb625acZyu/f1bSgQjjpQYh51J9GmTNBp2aB019mhG0SJFJ+oJCtQICggGXCNeg/1OYMZfZg5d9dwVDTvO655Pt8fK0+ARl6GXBfB0yJVMj3QcudeqLa+XNuHjvJdhFS9TUz1srrflBORr4tDu+EaN7u80LkcPo8Z7FtLl0PVMkUmCQI1a/i7OK9GZbic9p8IHCx3JNFYm2uSPQktVBKtrp6ygQXu9rWUNcZQifL3jBcAVMz9h34/fX75/OZWBEaMdzbUuP0KT9uStjZfdFyPTVvuQ6P4M2GJ4xf2U0ol2JjSh8fsLylHGqnpLPBlHt98w8Ni2fK6I/5lj8JmIW8JXVxn6EbOjUMBdgecQrhZRAGNcLeqt6CpTYB7/xMjHEjdlZ2d7HQ7HDbq+3z1+/PjTdGklqm66wnrw3yEBP8yZCLVNWZzOy8vjweY5jqseg/IJhu3LlIkkPmb0aNsRq+Y17zuXiAKOKQF3D6eHlvFtSigP6sqOEjPxH6Em16vA1TohTVWqgFYhBlFl/duqvCr5wP0i1uPzYuWf3Jo7vFfxrjO7lO6nNuWK5p+XEo6pfW7mPtYze/vC8Xbbx7fyR9RNhtdcTrN+1Klsv/vJHfPaBMOTdSj/zMsOFQzDM6/Cd5EC3y8YfHWV4UFegI+Vi+n/b6w6XZ/xCgZcy95+Tk7OenS5HD4WblJmZuYZsUCs4pw7d+5PiCvWkjAoBlzWsDaD+KojbdMVmPB0MFGFKSH0s5Slv7AfOAn4hqP//TjOXs4mx1bfMaNiR9ztBamnXWd1TInkytuU1GNKXN/Ms6nJBBfdK8n0gFk58oOaqjSro8/D+12JNDTu+I2u8/hwRxerD9v6fnQXNAl3+5LEExRZokyEVxMpkxYEijM11KGU6H7Gjh1ranDjiCt5Xhx578CygqWt6HUZpFw3ePoK2u/1eu/zoZ0CnC198ZMWuFyu9Wg8Fu+3Au93DXALV4soIBhwLXpZuq4+rotHK3ocDGwSkP2AgWo1GNndWVlZrZGOuouzuKxhW29qgg/y2rRCesWv0US6FmlF7Qtp9Z/r+5JyTnbJkiXcZ+P5TmXAlbPIuTWXGnXKpCNj3ZkTUX/e7NmzD/MxJadEQ0mio8gzuibI+GR9BumldGRVujXppJmaxMTgOTDtsExVVmKx9fuILajwgGKBU+nBhgy6EszW72gR3qNiaMOOoQ4Fie4nlMENo4EOXdXKqO66wXnz5rFKn9fuU/F931MJUP2/+F9qMW7cuAy3291PkiTjNxuNDj0aDSQCR/VSAP8n1dtgNFvjO4Lxzzo6MzNzKP4aRBN3TcaVlJT0Cv6JWRUalW4yLuDsBGSDEH8FA9UpiD+FwWInaLsQA8dlEydOTEReVBwYIasmT0hLRMplDcVxdFeym541NhLMUlaDBg1eAzwbXkCguMv+MvqS03/YTg06FdLhP67NaojcMVAxKrcdIU6QjPjM7nSOm/g4SFevgwn7lZuZmgzHVKVJOwFZy/tT8qp0OutP+5b/iEIZ3qazBXbpmDFj2tuCDANoY386Bx/iP/2qyHQ31rvfV/PYUAfifhMADDyKoQ7kBzg7Bjf0Bjr0CMyuG4QqW5mU4du+eeTIkWz/W18lZnEw3STQvDf+h84oLS1NwXOtxHe4wuPxPIVGo/l+ZUj6rwOncLWMAvg/qGU99nUXUtokfNBb8c/F6x6fJicn/4KPfZCvuE4HH3744X4wST4WE5XnBK7/Y5wYHH6EGusWSKjtQNcsIGfTfcPwzz27qKjoN9D8ZR5MkF9lh7bex4D4pQ9Rmy5Hdn6GgfytjqspYI2WYawsZc2aNesQ8PAxEwZj7zgixd955g90RCKSKyoq/G47YgD2xRK9DCl4I8fNPJhwNtTRr4EpxmGklMoraFq5h/hGJg3crqlKrYJFBG0ojDfeS33LHbTyT8t2LgLoVPhoujNAp5/w/oZHC+mq/tTd46VckkmbnDlkc0MbaQU0jYg0JgGaOlDv3XX9KQP5msM3Zqp6Rt/9DG6oBjrwnvxU0WbXDWLZYxkaWIDvPBEq4IcRj5kD03VCMOgMOp+Bb+/U+Pj4TfjWf/z444+3YOKpqJ7xv3UhOlAEHy13x/z58/dGC5nAU30UqJUMGBLZmfhnehlk0ku9bfBP+jH+AQKuvQNcnXP4p+bnZwZZpWfrWHbgiJPk9hj4vgRd2zAyDBQlGLQ+QhsjmBkj7x7QdhdoHlUVNQYi7bKGjUmtMh7qNI5VwGjO3PUqoI/AVJUBFKG2KQuD6kzU0M6mVEiOK/EdtIZnaUe77QgwmhuwgtwYvG/XMswjNyZ7aSHWFKc5HfT3vqvouBGsRyGFNFVprKOmjYy3TwF9h34pu34f3JH7WseygwHtqXUjDFuh3id414+BNk7EI3arB1J7l1exrdxMh+Td7oVkqebd25huBSyrhBEoLoW89Ilv3Z+gzQpq61mpoftRVdEV5aRI4Bsz6HKHRB+xHWYdmBLF98tSMPg+XY3nj7rFKNCzBZhuf2iN+iUmJh7D/w5PZtfw/5LSAfywFgkw/K3OQpK/9W0Iq+o+R1uMs6p4RP2TQIFayYAhkfHGDjNytcA/QCwNGZi1edLy8I93CRqPmAl3K/mdbtjzdaNHt81bB+b6P6/XuxyD0/nAqTkMIHvQztOQjHsjM6oqar6sIclTphjPB25C+29kZ2cH/Sax9jodo6jfpizuo0v2vs84fD4J0scUeO22I1++XwDV6CJJUpgIIdyMQje80V0syXQtJFNLZhjUVKWLAo6dBGO83DiXN/DSnBv2LG1QRSacB3wBkhHe9f34P1kKjVFEu/vLMwAAEABJREFUKum1Z1FTRwUtAW6e4CBQ3NKkxmS6dq6U4ueCPKoodtAERFfBq64VXvinkITbQKPF30LANYOSJGm2ntVKaqiqoqF6nuSV6bLT80m1uKaCKCG+X96g9C4SEp7fz5Ia8iJyYLpJoKGmYsZktRD/KyvwPe4zIsTktktRUdH3yGfNFWt5JgC+B9Ib4SN1n6G9iyOtLOqdfArg2z/5nQi3B/iHDPgnVXGg7KTvdFT7Uh0h/gGZCd+MthT1FkI7zjPw6Nacib9/q8CCod3w+LZcF2g3AYPTLMzSpysFhh+0xbP6qKmoedPVXb99zkxPtTBleVmDX1cMm7LWDqD0RnI5q4ehxa6ExHNMgt+LwXB7ZY75L8RAloIrIA13AB3uBBQPjgj8XMdgx5SYsYBJX44avLaNQOckGrk+ne7gHGasvMarqpr7FJyQeLmcPcMw80VfLoGUv/iq35fy9zwFZcjCrz3HsFPwvi5wOBwDUKXyRSOic2fjff+Edx2WSnrLEEqUSikHfeuu4kJjGxom0lg7dqYh4R8mB10iScQTHgUFaN/lOCUsT/C4A0wpSpI0D8zzHQXQ5EdVRWMge9broBwTEC0LE7JpwMfHxwKuK9SAQkTAdDUVc3l5eVczFbMRBWh8BSaXy5HfF34lvxMw49mofwGYMN/HfSv6pX27gAnqfLC34v0OJQoKKgprOAXw3dbwHoruhaQA/hFfwz8ym+VjxmkpqQHRcfzzTmfYYUWFl2MQXYw81T34xNacvjw4AOZ8SMKaSloFUEMwtaioqHnTVbPyct6QcqOKG0xz2siRI9uqabPQuClL8tB/79y3mKWOj3TwKYgXwwd13fJpPUnEu65dUF+O8Eg0GOkdAZVkao/1xWVYF74ooAwZPQppqywRSzdI+TvkPwY19uXBGC/XMDLf4w4aD4ZVjPf7AgbsZMBkwwc7gsZl2QzLdQBLWErYifd9Ht6p2c75sFXSJYfpDeA9D151270uGtr+OwqcfKgQhjBtBe0GtxmG7L3wimvgLTvl8v0/gTeDnSs5yo9yzaASC/IjJdGHJJPk8NJVQcBogcV1hcHqqGVgvAEq5nnz5q3m/wUVxhiaqJxfSE1NPRPvZDPCc1JSUr7h+nhXL5eWlirvV5IwvTEi8qV9ZdkMy3V82SKoxRQQDLgWvzx91/GPXA5J4WH8Y6aAifIuZpbseOML+9s5j8sYhmExsLvjHfQnMBtWzSmoMCjOfGzL3LMBcyEYoalKWgHU/QDXHuANW0W9rh8p1wvypivUZ3WmqjpMxZouS7O6VgKj3bvRr5hATPaVdKVSegtxo2rxJju740tlegy49kMSG+aQqZPvNiWz9Tlet7M8ptQzn95HH7SNRohXOpkSgfvR+GRaA7qbTgqsmG8lAqK8vLxS0GkGfAIYakcMxrymyQw5m+Ocx2XwM/IAq9bjEO+IzwA/ADiWdjWmx2Xs8a5tqaQ39COeLOmXfw5UOGhY758ocMLCiIN40GoTuO2lADkGr7jTS/bSqIMntNPor6XqWamg/pTQZHy7V8pEZ6zPoOvVbLMQOPkZilB24rpCJMwcmG6SXRWzsb6ZyhnvZsrbb79dCpysfVj9wQcfHFHrLVq0qAzlM3JycpLwv9oe/ZwKP93np3IelzEMw6r16ntY259fMODa/gZN+o8Z9m78o86Ef8TnZ3KeEfTUFXQYDGeYRLTFVwZNKr29IZ0GoN4MSZKCqqR9dbQAdWypqMF8M1FJuV4QoeKgHmT1b5GSILocaruhvnhAAGYVx8eMsB78Pvqubcp6YlvuWPR5ka5Cq+TkZL6AQJcVGM0ooH2QUhUJUZLoeZeXUpFmhv5ZIDSZHlNS4RzJdDcYwSY1rYboZ1dvMT2tpvUhnidZr3ZWJV89jD4Ohrodg/GToDczZB60n+Q8PYxZHHUWYyCPSCW9vp+poY2xfVbQBrO27ORBEs7/oVHn12TMAlX4QUe30EVF6zkZVPXMAOw39qfmMtGpygY9ie7DRMdvVzTD6D1o4Hddob6M41lZWU51FzNUxLZUzFxP7/HtXmFUOeNdfcgw48ePH+DxeHaiHwc4bebxv8rlzwLmYZ9/lvPMYEVe7aaAYMC1+/1VuffdC2gXBq1hGMR4YGJ8KR6ihWCSp+Gf/388YEuSFFQlzZX0HswgqIr68faXvn5/p8xuGOxaq/WgHvwN7SjM1Jf3OgbCZF9cC7YMocTSREpUjxn1KKDp6Lu2KWvg0c3GXfB3DBkyJOQtMdqxJJlOl730fFo+PVzsoBFoOFCiRSZoph1TQlJxzEjLi6mXJNGD4CmlSqb/T4CpSq4TDvP1Rxd+igdySMthqaTXZtCVmJCYGtoIvwcnavCu53lN+l67oCnv7zuRf+HhjTT1tyW8Znoi0yLm8dJdFURK34y7oi2qEJ6fdw3vheTfB8zySobDt9gCcb9dzKFUzFxP7ydOnJgIHIxb3eWsqZwZDpJvb0w0y/CtB92XwLDC1w8KVI0B1w8a1fmnTCukX5xEzGwUdSCktZZgIp9CEj4FA/ZuMGJFJY0B6yesDZ8fDkHAjDUV9amlBy45veT3lcec8XHAEWDoo2/fvmwntwBl7DpDFe13pGVPH2qQdJCc5ywjfytWuk1ZIw6u6ZfqKdU2+ABRp8aNG7NNYUStHVTD2rEkPH/fgnRqznlpBXQTaMGqXrPKyjGlwr7UVr+5Csz7P1AlhDRVWd3MV30AvBPbKmlImOeAHsoxH7U+yf6GNrT8MCPqrufvGnahLxuf7le7aUXxDKybj/XLNCR+6UPt0Lcktm6mFqm7ooOpovH8hwH/JDy7x8eNGzcY66opYMyFkFRNdzEzYDAPHF2KDLucgWvK22+/rUzERo4c2QHfcwIz9WB4RFn9ooBgwPXrfVs+LSTh5VhHmwgACJSEMZY6eyX69Nf+pFzVh8FkBsr+DCZsuUsa5UHddb9/fd7VO769EAOdqaGPlStXsok+/WCvXdbwzWBqWNKUPK1XUcAmM3VTlltylsXJnoRRB1e21XdEkqR79WmrOB6cz5X/grB5okQaA4VkBXU88UYxt0ndi7GW/mO8kw72KTixqxmS+XMkk6Wpyl8GUaPqlHxN+k2YWIVUSa9JaDMPz5Go1nfI5oY21HK7ISZyfgY3Pk/tQT807KxVxztwoN0AQx0aACIVTprq8pAi/SKpOHVXNDQUpqpoSLqKitnhcPyECjvg20NdPFBvKAN5YbnMzExLlTMjwrM2w2Sj3Zw5c2xJ9VxH+PpBAcGAI3/Pda4m1tHm4IPgIy+VzyZTr1Iv/QeSGkusPGBHpJJmZFBpK5uueq6jg5BAgqmo+Swo7+YlMPtEDI6v821GiaVU2jmPFGmC8Rn9vZ3GtPqsSdrXnN+jeHdCq/IjGMM5pfjekFBYwlcSZj+bBlJ7aAHSXBLxUZgKkmnSzxnUQ4UFE34Dcd40dAih0Z3i9dJnxtuUgpmqrCintejgJZDgFoda8zU2Fs00NBxBd0m/13JQ0yWpaeSFTh3tBjW0gXJbjlXPeLcBJkc/btJ7v8fh1K+7p6BhzVCHHjnTGvQrOW0V7dTncxzv6h+g64+gsTaZy8rKagFGqamY8dxsHet+hoe/F+XKRBNx2y6UypkR/fnPf26EZ+0NydfsKBiDCF+PKYDxth4/vXj0AApAEmYp9FG1AAPZMEhqyu1FnIeBK2yVNJhvJur6bbpCWnFgxpqKGhmKoQ+EiiocITPhC59tk3nbU12ygq7jQsqd+kPT7pehv8o68pAjPyPKGCo9BkHeNVyZMPxiINdMTXbLp/XgNcqxJKyFP68HxZrwt1gLZWtOu/X5SlwGA5fJ75hS7zW0F6poZY1RgdH9oM12kkRfnUzmq3YH7yCoSjqvcTd6vc155f9sP+QRtU5VQkiDPMkKOMsvO5x3lZEnC7hPbIUm0gx1IF9z+BimOh0UwMRVAFUV/eWgRg+B8Sq2mKF5KYQmR1MxI/6+JEncViu3231i4qkiCRJiQhdU5cxVwdSTjh07dk5RUdE3nBZeUMBIAcGAjRQRacK650PgXizxKdQAs7hhXTr5Db65ubmKShoAH2CAm47Q1K3NoK4oaIt15lyEQR0GRG0XtVOWNZwVRA9jgNwJVd7LaOsMIxLk/RV5ym1HUP1OR3/n9y7+jZpUFCO70oEBD8agqT+/WlmA3w396U4M5pqpyVKZtGNJa9NpODQAyeoab4lEOR4Xsc3x9ahqdE2Q4XdMqUch5YFpKzusUebnZJm6JZQRXxbhl3+yEjk5OYs7e4vOaVd+SNFA6PuxM75J/BZH6jegNR9l0heFFcc79FM96yoru56x7n6YHHSJJJG2jg86dZG8tBjvQZFSsTasXTeoq69EwfQUFfPUNpmn7IlvNLN1+ZEpz+zO3WWlYoaGRZ2Y2b6uEDS4AvVYndwXjSqGNfDtKruckVbckCFDXOXl5RfEx8d/lZeXh09YyRY/ggJ+FHD4pURCUMBHAUhmt4IJL/YlOXhwQzpN5ojqMWD/T5KkgfCmu6TZ0hU+sGvBfFmiVKuFDO/ZPLti6p55M4H3Sx1wCphogC1qDLg8KI/BAPhvDTaRrnXI8qZzjmzSsjiCQfNeDvV+Qz8ajAG+xHdDklLkdyyJ6NUkmfqXO2ilusbL514rKmgwgPXqUiQVFwd8frcphWuqUsFykn7+tiPvoRt3L40fcvhnsx60QmbEtqStVM/Ayff23oxQcWkrKMBQh0zUJ9lLs74aQi4sD0ymJHpRAfb94DvwUzHje/jxwh+OPIJv2E8V7QPXAqiG2TY1L12EvK5wYohdzhpSRFJTUzVDG0gKJyhgSgGMj6b5IrOeUwCSiDveQX+COtbPUMf6dBqvJ00wlXRxHN3lLaW/6+FDxbcMOXHMyOFw3ChJkrruG4+6NyPtd10iJOMfkLcKA3ASyhWnbsrqf2xbUYqnTMnz/QzPzMzs54vTxv7U3CPRuLR88psgQNJKxoDPEs5WwHbCID4A9DghThNRn9V0CCrpESgPeUyp4VHivmtGF1DnhJNOmKo8kXlyYpiMsJGKq3n309CidXTV7z+wdau9xt5gImTLcIexnpXqGe/vrvnz5+/Sw5sZ6kD5pa2P0KeSRN92X0ZH+Z3z0R68U1MVM+DJFU9/w7sMaqAD35kiBUuSZHldIbQnIVXO3B579CnA0AbnCy8oYKRAnWbAWVlZTvxzXgm112sIHx8/fnxPIwFE2poCwQx1GGtB4vBTSWPdV9t0ZYS1ShuPGc2ZM+cXwOqNV/ytb9++k7GWp+yixoDJG2lOB0N4AIzYT0XN1xe6ZM/fzj6qaTKBSnHKYMuxCi/d53LQExxnz4xXp2pegYH7Zs7HOu79+enUguN6D6bshro+1DGlTxrIlIN6F+knM0hrDirqx1ZnUB8t4yRE1vfDZEmiu7WmJSrtXro7E8xpAPLMNhAxk/kJ/1e2VNL4HwyqekYbAQ6ScD5odngtWN0AABAASURBVDUmQF61ENqFC4sdCaei3TOg4g1pKCPUrmjGi0kkf0eW1xWirZAqZ8bDHmPMgFCGNhhOeEEBpkCdZcAToS6qqKj4Eg/5HgZoPkJyH/4xVmIguBZ5wtmkQPcCsjTUYUShqqQbeErHPt7+0r891GlcwJEhYx01bXXMCO+QpbItPrj0lStX3jZ79mxlFzXyOJ/XY02vS5zRNeubfsd/ezjR6wao5i7DgHoq1hEnOWWaC9Xzfj3j1auaexaQclsSGHFz/bEkDZMv0iOfgh1TughMYyhAPy+WiPsaKDHLlOiQac6GwXRS1oOxTm9paAPMKXCXNB7G51ohDKmSHj169Cn4HzTbMOWnegauAAftRA647xR9QZKnbMpj23IHQX28eja+BX2ZWRzvJ2BXtBEOkzmemOFVn7iukMcQfCszAWtqWAP5fg6Sb298r8LQhh9VRCIYBeosAy4qKpqMf3rjphsn8mZCMjZaSwpGo3pfhjVcS0MdRuI8snVugwd2LP7nMWd8Dmj9EyY85xth9GmMeNL3g6iR1TGjjz/+mFW/PIFSqgGnclkDBrtzkbETkveP8Ja2qJ9ue9GAlhXH+KIGgCvO0cRz/GlJoqRjTipQJV4941WgfD9OIrapXUGGY0m+Yi3AIM+b1qyOKRFJdHqCTB0jMVVJMfyDGj6koQ0wuaC7pPFOgqqkw1E96x8V/6dJeM+9H+iY+UOJM4EZoVaMgWsmJlFBDXVowIiEUkVj8rgGYO/CS3ieJ8JROaMOjRSGNpgMwodJAXzHYdaoJeCSJPFtK2a9bYRZ6tlmBSLPmgKQhIMa6uCa+k1XYIp+KmkuN3o5mxxb+1HjQR3oOKtzjeVqGriWIP4feHbKZQ14v1NdLpefEQbAabuooTrNAvCn8MP2xDVq4QAHRVxxx5xJmWsS260NdTsRA3cLciyJy/Ue6ujPsaY8GMx2hz5fifuOKXmLaZBXwjq6RKVKvv9PgKlK/+Loplb1p+4eL+WCNLYMbYBJhTTcAYnRTyWNCVhYqmcwXWUXM/D4qZiTvWW/ShJ9Sb4/mciBfgc11OEDVQI7qmiMC9Okyj0HI71ebyEqmu1yRra/wzMKQxv+JBEpmxSoswwYs1htU44JLbQy/POcBZ+Hf/gj8Bsx42aJx6SKyAplqMO46QoDtrJLGu/ifNDY73pDOYucW3OpUadMOiLNJk8o6mJwvBMwRfDsLsdAuRyS2WFOGD3yFRV1bm7uCF4vLpec98iSQ1sMdpPDMavFgGsf6Zq1BYyfJWwjCr90qeFYkl+hIVEm0TYwho2GbDWpHFNyEZ0lyfSAmqkPkf8C1mM76fNiEV89kNq7vMQTlGY6/CENbYSjkg5H9QzG2wL/f5qhDLy7H1UVM6vmocY/e08j4kk171pWu5xCXjI11KEC6ENoKYKqops3b/47vtWVvjq8HPBCamqqcn2gLy8gEIY2AkgiMsKgQJ1lwHZoADXTQMB9iX86VpPyP1w3DOzPYSB4BPnCmVAAkvCLyH4UXnESkWKow2rTFQbs3RhI/WxJY801jm8z6lRIh6VsDKEKpuA/CxYs8LusAe9s4qhRo5KD1yICM97z4I7cl0cfLLxXkvzaynK73TvxrhfiO7gMDECblBlx+h1Lkuh57r8RhtPIV241Qvwi+M/gP4c3ujgwk9dJooZg1JamKr/i4zbGmlFKrz2LmjoqiLUKHXQolyY1pht0acsoaGpLJQ0tBN8o1dyISJIkZdcz0xwT3t54B5a7mJW6JTQZ9HrxgjyqKHbQBIlolZJf+WNqqKOyKPDXShWNb0Dd5TxIrYVvbMnbb1faclbz9CH3v94Z2tATQMSrTIF6zYChZsrGP5mmftNRcyoGhVRdWkR1FICq9SEMgm+oWTIpA/eZytERNdMQQqKZgSzFlvSzbUfOUG8zQp5t17fysoZffRUCLmvw5WsBM0R1jfes41tWdS3+XVsLRp+pacVxVgMPw3cwm5kxpPSX8d4DDH0wwmKJXgYT2AimeXqyTLdwnt5zWw28NAd4LwFtFoNRZMLzmvDrejg1LsvEFzy4iWg3vNGd0fIIMb2M+VVObxlCiVIp5aCP3VVk6PMGKY7GBTP1qcLqw5ycnKAqacAOhTe6BdBmLGU629nFjDXq5ujfqWn59D0jgsbisOygSySJNI0GaNmFvCcMdTCclTdTRaMvV+AbWI46feFZAn4NIWECoe2Q57TeC0MbemqIeKQUqNcMWJIkq2NJCWDMp0dK1PpQ77iD/A11SHSl0VCHkQ6v/ZqzvFfZ7+eVSM4zwez8VNJGWLP02rVr2+GdaQMvYO4eP378aQj9HDNDlfHy5qreBfS910N3HXUk+J1hLpdcDf78+4+3o7LpLmpIOK1RpjgM/G4M9AxLUBP7HUvi9vTMF7QZD/hi+ODHlCTiTUTgL0oTfj/cBlTRQ/wyo5AoOUw8cdJvTtzuddHQHj/SgUjQQ8MRbJe0EeVhvL8XExMTj2FCpqmYjUD6NNaotesG1fy0FRRgqANlJwx1IBHMqaro0nLpTTBf3tw1C/C8PPBCKlTOWLbgHdF+1xWi3M8BThja8KNIvUhE/SHrNQMGk7V8fsx+Lcui/hZqIUJmLuUe4nOymqULL9FMo6EO9dHUY0aPLvr2V6NKWoUJFUJyetjlcl0HOMU2Nd6fclkD0opjRqhnvH0KKm8nUk1Nvr7oq2VgAIsUYPwccybQwbjkh5/YkpsLaa43shRb1MB7CuJPsVSMAVpTUZsdS+I2zZgv6muuR/BjStyWBquPyBK9v7oX8VEffXbEcdXQhg7BgQoHDWPLXrq8sKOqShoVWeIPMNyBfNVlg86fAV7TRKgFZqHZdYMqnKJtcRC3p9kNR9mlrQ6T8m0gHtQtbNL7iTJH3MUDj229DYB8wcYETAqmsMoZ/eO9BU8in92jw4cPT+CI6qE25zPQqz/44ANz4yoqoAgFBUJQwBGiXBQLClhSIN5F18le6g915hYfEAQ3ehuS8ABfmiDemR4zwmDHKtY/A+4DMLnpCIM6DHrnAmAnBsftkFBYfbsbaQKzvPDPo4f/zYzxcjmYjp+pSTBgdWDlYvq+YZdUj1NayOui6JOyixrSTVtMwLIAwJuU/FTUHzftw9JSBR5s0voM6h+K+QKH4sCE30CEGQYP9ojacm2dLvqXLcgQQJCm7/JK/oY2wODH9llBG0JUtV0M+vHkxo++hsr34l377ZI2lPslza4b1ANAEg4w1IHyG9elk3IhB+KmDn244ptGp+Z+2iSNhh1aR+cc+TUTffez5VxWVsZq6G1A0DEhIeEmhIqDxkUY2lAoIX6iQYFaxYCj8cACR3QooG26WklroZodBkb7uw9ziodoIcpPk7ODHzOCNGS5S9qHSwvAOLVjR2DCbCJRs9oEVfLTc1sP2qFKvGolXj/0SORnahIq06XAxZaPFLBDrmRandy2K5USbxhS8lgKAtxHGJSVXdTI1FTU36Z0eQdMG8I+ufDcy2SiSzABsXWlINbOrY8poRFTJ1XdVGUwQxumbUaQmZWV1QLLCheDtjw5ssLA0nxIwx1ceXUG9QBtTa8b5HLVY204wFAHyh5am058axWiJ9zEiRMTwXw1lfNPKZ1eSPC6PxtxaDWrnE8AIrZo0SLW7DyIKLt78XyNMQkUhjaYGsJHjQKCAUeNlPUHEZhrJp5Wu17QylDHzx9Tt06ZFPSYERhdwC5p4PZzGDT/igzltiOExGrfh7fl/prkdfPGGXJLztTChDYaQ2YY9hVef1OTnMceTOIJDlX/v8bdCEx0NNTnM9Q8NQSz3wNG7Gfo44vGpx8rdrB5Z0pA3bInOwz/8KkuWeAXai3rsHc+rfc4aTAg1sPbcpBUIzZViUlISEMbtjphAgSmlMRMCe9H2cUMbQQbv+HLMUygT2QBLqjhDoZ0EQW9bpBhVI+lAVY7P6KmOcT79DPUodvl7KdyToyX/4IXZ2orGu9du66wvLz8MZfLlYDlk9WMX3hBgWhQQDDgaFCxWnDUjEYgTXVFTwKuF+xeQAGGOjwyzd78MfHxLlQJ7jDYMfMLUEljkOcBfQzK/82MV69qLo9LnABmyjuZGfmtGGT5WBnHaV0GaaYmlQzdD5j+QiS1gXRPXCPakNSaMBBPW5NOl6HM1KEPPz6wPefuqb999pNHqvzXSSvelXBMin+H14shAb7MzMi0si6T11yD3Kakg/RFZfIzVQmadEBb96Kt6ew5znk+aC0I19CGVjFIBO2YGsoAc+KNXSNNqvJxp7BsSePdWV43aIJfyYJ2YRoi+h3nmqEO0MhvlzOWFwbgXSoqZ7Nd0cCjOa/Xq0jHqHMN4tu1AhERFIgCBSpHkSggEijqPgXY0hW41F8g8b5i9rS9CmgOJI+pWplMvUq99B8wzjgtL0jETCVdUVExtYn72Ct6xtvHt7nKeFkDBsg3srOzHZD6uksSJXUvJE3VbGwWUpjfWiUkWQUE/f/n+r7UTUkYfvAcyjnfeLliWIq3lNeHf27hPkaXHFqzXJKkXcA5CVV+AENcjUH/bjCr1kibulC3KRkryZLU9b0GZ/B6eRmY/Ta0xVI8q3uzOc55aLMMfvqQIUMSIzW0YWxXTeNZWgC3qaGMEAY3rsWa/Xmgj9mdyK2AP1AlLdNkSiI+b45i+25vY2K18ye6Gillsmtps4rjvG6v7XLGBEy/k56wPm9poCMlJeUb9H0DaMzXYd6jwy2iggJVpoBgwFUmYf1BwJauqIzMjOorRNjThxo08RBLIQGGOhQAGz8YHP1U0q3Kj5x3+67Pj/BxIpXx6tGAQftd1vBL/vJ7PF66s/sK+rsezhg/fPjwf5G3FV5x2xKa0pbE5m4w4FTZQcqmLKXA96MyX0jJyppviUTjEJ/Cxecc+bXTQ1tzLkQ86C5qlPs53kkOyS3YbUoKfH5KB8puP4rWJp8yChmK7huhmeOy7NTU1OItrhYseXbQAdk2tKHWAdNN0quYwUgLITmugFrebxdzKFvPgPdgcsWWvy4F7r3wfg7MTVNJr8mgYZJEynWDfkA2EmaGOhLkigbX7v2WOpYeug19n8Lr+2aozAx08POzoQ3AK7bIpSDXFQJGOEGBsCkgGLANkmGG3wqz/4fgZ0G6eQz/mPqBzQaG2g+Cdd+g1wuqx4xar6LjYCoBhjrWpZPfGl0wijCzwxrvEjDfzXvjG3WZ1jFzKJiVqclI42UNbqKH8xp3/TcYKfijdSt5eXkVKH0OXnOfpqYV+RJdSbcpi/tjttsZa49+tyVhgA+5ixrf0Bm+NrQAEpjlbUqzWpxBHzXLoAqfylurFDwivdXq7O7LGp2qQIEQGySbhjbwbZuqmEHnLcxIFYS6H/w/2Lb1DPosgiqXd8hbqqQLGnS821NK/9A1EVYU38nh11ud/++DrgZavaYVx+mGvf/7K94jL2do+fqIURU9ZMgQF9Z9L4iPj/8Kk4f/AdbyukKUCScUyMrsAAAQAElEQVQoEBEFBAMOQTYMmKdi0MgHGB9tuMI3W1+J/P7IqxcOzDcTD6ptukJccxjcTY8ZHXeQv6EOogc3pEO1qNUMjGCATFZVzc+fclEjMF/esTwQksf5GOgtDXdgYGdp7z+Msdzhci1J7TWF46F8cXHxm4DRJLLtCU1b/JLYci7yCAxc2ZTFfTJjvgzD3uy2pLfffrsUkrzpLmrUMVVRgwm/gTKWELVjSu+1PJPWJPMxYZSE6WQ8wcImvemz1DTZjqGNrKwsSxWzVdOYmJ6C/wczjYjlNYOgSzDDHa3mNEu/8KHTx05Hf0Baq5bN8yf6djlvS2zyAiYgVC65jusgQxrqwDvQVNHQIvgZ2sA3yGvBMvBdjW+xF0LhBAWqTAHBgEOTkNeijKMgm6n8d+iqtR/CatMVP5mcbX3MCJKIO95BfwIf4GveGJy8FoY6mMmpjFdVNR+KS5nkcrmewYC9GxKIny1pBZnhZ2jRmpnx3gqWarnkckyQzMwgcpnmlyxZchyTK36/Wh4G7gqZaD5nIJyWLNM3CBW1MyYVioUrLlN9t3xaj2fkNXGXh+h5NV8NITUG7KIG0+LvKcDQBzQH2jGlHxp2pvVJrVU0EYdfNe4mPdQ2849mCMDkkpiZgFbKLmYrFbNZXc6D6pnPylraemYYMw+a2FZJm9U3yxs3blyXoqKi71Gm7HI+4GowIV6qOA/pY/CqC2mog1XR0DYMvm/nonS9oQ18g/wdvwtEynWFCIUTFKgyBQQDDk3CP1iA9MUA1sKirE5kB9t0Zec2o1NX0GGHTMMgTZoa6jBjvGDcxWAIfseOmJiQcmcgDNgljTwCg5SGHN701zgi3gnLWexft3NZQ2JiIjORIq7g85f9X6uBvIa9SUnLlA78X5oxX6UcP6UyPYZn3C/LNGxtOlkamsAzhFRRP9Qhs+H/Urtd9nHTPsAcNfcMS6uMDd+sn4oZk5xfuV9WKmauY+bBuFn1PNqkbF5OTs47JvkBWWh3ESYjvHP924BCIrY29RO+heEmZX5ZgLnC6/XykbS+KFiJSZWyyzkSQx33thvfem9co2cbesoe/GUQtQM+zVVUVEyTJIl33Y8Ew+ejZFqZiAgKREIBwYBDUy3BCgRrRIlWZXUh/5iLppLJpiswTtu3GXUvoF0yGBOYmL+hjv6UGe+lvqrEy4yXaQYGwet0YzA4/5vTeo+BXTHcgUHQTyWtmpo8LWMAb8gq8NUJeVkDw82aNesQ8LH6l5PsHRsTWl+PCFtBQkAQcKlDUjxZvmu7tyWR7+/tt4OrqD9tlPall1v1wUchkCCt3gVG1d/j8fTFpOMY6GvLFrNZ28zMwTjDUj2b4eG8efPm7bitKG/EwGPb1Es2OFv1rRAJ3CWNTHaqyhlxy13O4Rjq4A1nYLJlF/1Q9DAmVD9WlNM/gVtzCxYs2I7nfpUzwPB5FzpHhRcUiJgCjohriop1mgJY950EHvBmz3XEVqe0Z90yhBJLEykxnNuM0grpFyfRCCBR1IEY3FpKXnounmibynhRpjgMgFMxyD2jJEx+jCrpZy7sMwUMvuT0FbQhOzvbC+nnBl0108sadOVKFFIgW0cqURL48RL99agz8Q94fpWZd6VS0ixlASTAFUv0MuA3kkymtyUFVPBlQB0boKJG0YkdREhEw4Gmt7GKGfTLR5t+u5jDxQ9mzlqDsFXPVu20OVI0aezBgitRfin8Xng/h75ru6TVAkigfipn5E/ApMJ0l3PPAgppqGPkyJEd8B1ohjZYFS0TBRjowGSNJ3lFaO9cMGzuL6KxdAJ3XaaAoy4/nHi2yCgA5puJmgGbrviYUdJBcp6zjI6i3LaDxJxcThSHAY3PrSIg8Cnq7JXo01/7U2MVUVZWFu8ubwep6Gs1zyrEYDujc9n+21Y1aPvs/R0ym6twYDA/Ic4DLtuJ9rusAfmmDgxpDwo0BlshOaVFTXqtBlNlK1K8+Q68lZRNWYAzdZhIWN6WZFrBJDM3N/dHZPtJXUhHyzkwuelVVWTRUD3r+7CxP2nXDeL5bamkIcmbqpz1eI1xrK/z8sTrunwHyfTuuv6UgWdqhklFuzlz5rAaWwEx7opWMvEDLQxrcnjCRpjsCSkYNBEucgo4Iq8qatZFCiibrhwUYOlKf8zI7nMz49VvroIk8nd8cFO0+jL5GeoAg+Dbjnig1ECCRf66++uz00t2pkMq8VNJQ9JjRr+b60J6uhADNktXnLT0HdxFr0kYkVWAwgbt2j93+oSEHgU0HTMGbVNWMEtZeD6/Y0kqrnBC9NdsXTUcFJawVcUdTdWz2kmPl/yuG8TkawfeX1DDHag7C74J/AupqalnYtK1GfGQzsxQB3npk0FHN/8B7QasQ+t3ReuRo3/MgINeV6iHF/HIKVDXa2I8rOuPKJ7PLgW29aYm4EF/wboZ7+pVqoH5mB4zUgotfoyMt09B5bWADI41Yd51zJucOElQRw9r4KWXoM47FxnKbUcIQ7p1GTTJKdPcOz5fvRpSid8uaUi0rDbX24Z+GtJ1Uyuk3N+bduU906t4lx4k9fjx45W34CTStSjYBE/or6WlLC6Hqv12hBWg46SfM6gH4uE6oAi3im34KuGGlBhV1bPVdYN4f0F3SfuedgsmFH9/++23eVOULyt4cEEeVRQ7aALe4SodZKsxB1c+AUm4jS5Pi5qpotG/oNcVapVFRFAgBAUEAw5BILvFWJPqCFXWE5C2/g9+Ogb81nbr1hQ446YrOdv6mJFZn5mR6SVePePVw0Md+BAGwTfUPJnohjEHV72HNTjLtV8VlkOoLQNMTUJ9OQNl2i5ppN+HZPwl8ti1cbvd2Rwxeu4zJgBz0IdLIAl9py9H/clDhw5t0PM7Oog16xGAKUK/TS1lqfW65VPQY0kqnFWINtGEVenJy8e3XeVdz8beh7puEO9QVUlvMdZFujNoZWuXNGA1h6WCw7KDLkGGhlOWqQt5aTG+hcbI93NWqmir6wr9KouEoEAICgRnwCEqi+JKCkA1N8Dr9RZiRn4vci6Hz8aAn498vrgAyZrvWKKEeKdturJzzEh9KgxcmgEN465mFcYYHnf4G+o489iWjo9smn2NEc6YXtmHGkBtaWpqEpKw3y5pj8czA4O0KiH5XdbAeLnfKvMF11vcuvzARYBfxGU+3yo5OfkvHO+xkn4GA/4bx+GDbsoqlcnyWBImZinjx4/viQnbCPibwdiegf8v/I/wv+MbiqW9YQ/6HrbDdxy2wY1Qjdi5bnDixImJeB93AldneDMXdJe0WQXOS1tBu+c368v/q3s57fN9kr0066sh5PKltcBMFW12XaFWQUQEBWxSQDBgm4QKBgbVHB+ZYeMcerA2DoeD1a36vBoZVzZdeUnbdAXGZOuYEeDCZrwqASCJ2DbUodbhMN5Jd8a76GEwTPBDzvH3WA/UDHfgvcwCQ2MzggoQJknKZQ2c4L7rmS8mBOPRp2IM+E9yuc7fwWYJOd2rgD5Cu0E3ZTGDfazL+Jbrktt8ynUqHM7XL8sc/V8wV4XBYp17M/rxFvo1EZ6luC1o8x18K9e6XK4uiA/ierHwaC8vErygY1RVz9wHcLmg1w1ichKwyxn1eNexnmkiiwjPFbBLWimw+MFyx9k/NOzyBTmI8Sk7832gloY6zFTRkNBZy8Lq7FaYcJ/Y2+BDJgJBgVAUEAzYmkK2SjDgtsAAYGU14UJbSKIMhMGrTWZm5pTMzEy2X81+CueZNWPcdLXFxjEjZl52VM1m7enz2FDHS20uXFwhOZQNUyiTwFXf3pBOAxAPcLwBCiLcuq4/0Y6AQkMGBscZyPozGJp+52/6ypUrb+P+mzFfwBMYOJu/1N+i1Ck1NTWLy9hP65r1zFFn4jccR1+nvT6k27/AXAMY7IfNBya4Hc7tcV5Phyv2/VSuMticnJyW8GfAZ8FPRXuvwi+cM2fOWqwtHkPeSuAGavxG2YEWC/FNvAs/xC5qPFvUVc/QtgS9bhD9uwKTFN6R3Bf91Axr4J2qKumADVOAs2W4A9qHAdCM7ASdD0ASzofW52pMqryor7ob16cTfztqWgmtVNHo530KANEU0KqlLy4CQQFbFBAM2BaZrIFCGONIsK4Z3RJMBOIxAEzD4HUMgwLvJmKziCytsX+e87iMYRiWWzduugp1zIgZVzQYL7fNHv3osCe+cQuX13s+OA4f7+DsFDDZhZDKT+OE6jcNpPZOojSWQtW8UCEGWVUlvVSFxWRpWomjwTy0Z2peEn3ia+cUu9JqHYQzQTdNgn2pzQUJpY44pb9YN76m5/HfvjMy2I/mzc9yeT03oi6lFe8e9sDmOb8zg+W0lUcbvfCOmLmAJ1hBVSmf72a+Chi+Qjub4bPhK29sQKbRxUL1rLQh02RKogDtEKuc0R/eYWy5y3nevHkhd0mDjnxhCj4XpTXtB5Jvb2ggytighpqZlk854L5+0iu+jWlr04mvNlTBlNBMFY3+8PWHfGwuFd9WLJcPlD6In7pFAcGA68D7xKB1E1RgxRgAeOYezIhDA4ZhWK6j33QVcMxIR5doM14VNQZD5dhRWiEFGuqQ6FNIwmwzmTAgSuUVNK3cQ0GvGFTx6kNIl6ySPh95S+DZpS5s2vuiVclttz7WYcQXj3UYO2Ps2LF+EiwkxasAqDBYhOxagm68SawLmHrL9z9edEZShftc9KsowVvhmrDvx5sf3jVnt5HB2j2WxEwf7+NxNJQPfxZ8tJ2MCdh4IH0PXj3Dzeuq05HehLbzQIOrhw8f3ghpzcVC9Wx13SA0NAEqZ0i8poY1QOegu6TxrgJU0kZDG9pDIoL3xOfGH0FUc5gBzYSkPlbL8EXMVNGYfClSML6bm7kdH6gIBAVCUkAw4JAkqtkAGDwXo4dsHi9gxo98K+fEAPPqs22HDkxbR4e+H0SNEkuptHMeqRuWlHqxYryMHNKI37Gj7gW0HJLIRJSBrxEzXc1Qh2pqsu8q0t9uA9BAx8wMasaeGND9NjlhcGyrQm9Iak3/12Lg78cd8a2Q77cGywwWnq8M9JOKAHc5Bv5jKg67m7LwUm5HnQo8kOmxJLy/oZgQrQbMfWAccQhj4abOnz9/Lhja1WVlZe3wLLzZTVsbR4Pno+13EhISdqI/iooaDDnqqme0Q06ZrvOUkt91g2jTVOXM8ME8nseWShrPEmBow4g3rYCmIc/UUAfyNWemisYkj5csxHWFGpVExC4FBAO2S6kaCIeBi5nvsEi6xlzukCv5osvHjP5iUAc6PmAFuVU8sWS8ahtgAlNdLtczappDqJfn4IM8wfhk6lXmpSXkpTI2NckwVgwWg6ymIoa0x5ucmIEom5wal5fMvmlXnntY0TpGoXi03xb+5blz5/qtwSqFRFRUVDQb8a3wigODGgymfp6S8P2gvyE3ZXXLNz+WBFy8Ts+qVt6s1cmHMhbBF2BUmuZg0aJFRzDBeBd5QyC5sfqZd4qrhiw0FTU6nVtICwAAEABJREFU8ia80VleM2gENEtjDf9PskQf9VpH5VxuR+XMcME8VMAhVdJ4dy/Gx8f/EAwPl1kZ6lD2STCAz5upovEtsRTM/1biukIfnUQQmgIY70IDCYiaR4HMzMxb0KuImC/qaa5cclww1p2pGJyoDsbLDaPvAbcdcT77h7pmvbknrtE7HPf5MzYltpgYjMFi8NN2EYO5qJuc/oj41Pu3zX37nl2L/9Ku/FC/8478shiSfyHjxaDcFoz6W+Bl9TRn+fm8vDy+2vA5fSbg79WnOW7HUlapTH7HktDmJOBiqfcKxmHht6KPfF71C4tyO9nMfC+yAsTkYzMYcXZOTg4z4gsA9x68oqJG2wFjA/IehCTN+wsAFp5bk0bx0AaMx5rrf7gmJiC2Vc4MH8xDMxFUJY26E6BlWIo2/W43Qr6fuyDP3FAHCPGp0VCHURUNGorrCv2oKRJ2KIBvyw6YgKlJFLjiiiuag+m8EK0+Ma5Pzm461Ox2omi1oeK59NJLWyN+DaSvPRgQ1XOws8GUNAn2pbZ/SNuc2GIF4BR3aum+jFt/+2IdJGZlDRaDHe8iVhgsmIipBMsVeUKh3+1cIsnjJYfjei5jj+duDaayIDMzczqnjb64uJilwL26/OGA7adLV0YT6VpENsETGHyApSz9bUnQOuQ4ZO/LgG0GH+DQJ9ZEPBEXF9cb0t2nYJDMQFkrwNJVALxFBsNO8dW1APHPBmwe/NWgx1TyL9JS6NszeH5FRa1l2ow4E+l6j0T/YnDguAITkOWI++1yRrpKDv0PqpLmNtH28GCNQBNky1CHmSq6QlxXGIy0osyEAoIBmxClpmeVlJRMwkAZtXfHuP7V8pyzrCxXhUMPCxWxxmChCuQjRA3RpqYixsD+Nhiycg4WzFWRYMF0WQrmywmU5lu7j1zzyKbZilEMJSPEj5H5qud8wbD1lzU40Pav8OdjAvAlJgR+5giXLFlyHP0y7tZlVaNf66EsZTFNstuNbr0vLoWaVhQnnHlE1fj6oeEEW+LKACO5H1Kdtt6M9AtQiScDgK15KepbxM0cl2UzLNcxAwiWx7ueQYtHjTDIw/K8kqupqMHINsNnw7P0rBRa/WwYTHjfdPazfSb+D/BBdzlb4bCbj0mLopIGPKv3Efg5W4Y70lbQbqjKh6LmXnjVBRjqMKqieXc1vmvej0Fg9uKiBpVyIrSkQNQGccsWREEsKHB/tJF6yWELJzMTk01OGoOFFKAamghgsBiUhmAw/wDMIR2M1lKCZVOT5KCEBAcNhUjJqj3lccEFZq5PJ97Nq6StfqyYrwoP6ZIZmXL2GANmX/g34f8H/xMYsZ9KOjEx8TXUK4JX3WVgIgFMx2pTFmCVTVblDsfdC5v0VnBccHgjNfAyr1SS/HMQdLkFdDkbdNGelwtUD5V4KcpnwCeg/x0BzxMBfo5sjnMel8HPyMvLK1XrhRNa7XoGDp74XIDwPXhFRY2wMzxrDjbhGU13UaO80pXQ5BUNOn2MicH3yLgN/hD8BPR1yttv27fljDq2XHl5+SDQZDKA2dCGnokiiwjvWdkljQmXmUpagemZT5vwDXL9Y0pG5U+AoQ6jKhrtPgXQIvhzx4wZw/URFU5QwJwCDvNskVtTKQAG0QN9i4ePtuNzxD2qwmBDqYghTd4NGN5tatn3lX1OmJpkQx0OmYZJRFt8FSSZyNJQB8OEYr4MA+nyIEK/yxrAwPgoimZLGuWKmzVr1iEMqm8oicof/p+5ozLq/2vclPXeuR34WJG2yernpFb0S1JLSgbzZSbsq/0h6NILjPcVXzpkgP5vB/yTYGDMkGdwnPNCVgwCgO+KJ0yjTUDmAf87aEtRUdvdRa3iyU+nFt817HLFnOb9+PmiqnJW29CHmBxqhjbQ5yqppCEJ52MCeDW+P8z9tFb8DHUYVdGgFR9fYymf8F6FFKyRTUTMKMCDiVm+yKu5FBgTw67lB5NgwTzDWoPV9xPSwLlIh7ztKN7pb2qyewHtksGEwXh5YAMKMjXUwQV2mC/DscfgzGYEv+Q4vHJZAwZP1XDH+eivppLGc/OAWgI41V2LiUprNaEPeVPW73ENFSm2/7Ht6b38b1giloK9kkRnHt1MGce234p+TIBaXJHG9XiqM86qZ0iFz5q0GbDr2e4uakjFrKJ++LW2F705r0mfnsAd9vWBqBOWwzsLMLShqqQlSXrcBFlIlXRaPoU01GFURWMyx99L7byu0IRIIit2FBAMOHa0jQlmDJQJMUEMpBikngITUtZgEf4RPsBUIsAicsAdcOzIiGhNOl3mIQowNRnKUAfjCYf5Mjx7SCg3ol+qula5rIGZIZ77QuRrKmlIl3sA/xa86pIwUeGNUWpaCSFFKpas/tH6vF4HXJX2UMYeKKDmFSe0mPviG7l/TmyV78CsIutg/kil4kn+sVI9gwZ3zZ8/33LXM2i1OTc313QXNR6JVdQP7XOlqM+YC+l52ttvR1/ljLaIDWBgopQAhsu7yzlL83h/QXdJ438qqErajqEOvSoa7YnrCjXqi0gwCggGHIw6MSjLzs52QHpKiQHqKqPEGi0EzSqjCUAAacjy2JEKHMrUJCRhS0MdkTBfbnfOnDm/IHwaXnF4/jf4/XACjGUGQr1Kmo8kaapIDNo3TJgwgaU64veJZ3wc8PnwZxU74uidVmdRCcIkr5uu2fsd1M68uZm+Q3lGp5I9l0CtuR88eNjadBqOvJPmMGkIqnq22zHQS1NRo04uvNFl6g19GAurksYzhDS0wfjRx4hV0qEMdRhV0Zhs8N6BbWi3I55bOeaHuHA1mwLV3jvBgKuJ5Ndff30cD9IrV6486Ha7jyK+EQPHOGPzGMzjx40bdwH8WMTbGsshlZQZ86KVjgVuPENj9G8MBr9/IzR14PqSHVOTWGMNMNRRLtN/k7w0FziYqS0+7iDlViPThkwyIcnyphl1jVm5rEEFgySsqaTBcP+J/KXwqks9fvz4TXiPyiYrZPpZstrvSqGcZunIJmpWcZyu37N0DWigbLLSH0uSJHoeE4g4BbCaf6xUz5Ik7cNk5OZwuzNx4sREMJuHUS8TnlpUHFuA8BHgU7d9a7uo8e3/CtrZ2kUNHJbuz3/+cyO8Gz6y9a0lkK4AErKySxp94gmTrkSJtsLvJ+ibqS3pUIY69KpoqOr5//RB4GN3r+//gOPCCwpoFBAMWCNFbCO///47WyPiQZoZEjfWDQPHHDBaPufJaRo/fnx3MOcNGPy+hJ+L+DYMBsZNS/MU4Bj8XLfn67T16XT+liGUGC30YHBT8Zx+Fq+MuMMxNQlJmI8FaUdlIEUOhTTJG7XCZr7cj48//rgYoXJpAkJCX6dBnalNfKBmZVvSikoa5QPhNYdBnAdYbZOVVuCLrEk+hVakdCjgZEv30V6gLUvVnKRiiV4miTaSTKcny3SLklnNP1aqZ3SDTVdaqp5RHuDwHfsZ1hhzaNXau3Z/fi0mHdMwkeFd4xegkraLGnTugvR0+E1gxMF3UQPIzIGpJR07duycoqIi5XYqMxizvNmzZ0ekkr4gL7ShDr0qGs/O+wzEdYVmL0HkKRSoUQxY6VEd/MFA0QKD9SSzRwOjvZfzWUL2eDx8swqvnXEWeycGKr4sQJOUMZitR4HfGRako+HKu5Tu/7dXpiElh2nOunRaCIYxDT5ihozn7oCOtYPU8TVCU7ehHw0GEy1RTU2aAhkyoQ58CFmKUQeEioMEvHLACmJmqqTD+cFAyRc1/MdXJxVriTxZ8iUrA8CwycYRSO2HV12SGjEJFUtWV329PQN9m8/lCKfxOjfH0Vc3npvtRJMk0/28W5jzq8tjYhcV1TP3NzMz08+wxrj9BbecdXTzh3inGq1AP01Fjf+FkLaoGW8wP2TIEFd5efkF8fHxX+XlKVbLgoGblqFPIVXSoBNbI9Pq470FNdRhVEXj/5uPi3F9cV0hU0F4PwoIBuxHjtgkwFhPBSO1onU3bhUS8mCEeuaLZKVD3YmVMe3XTH2mFUYYebxHAf2vZyHNAIMbkdRYOW/7v6owZEi/ym1HVv3Z2J+aeyQal5ZPfETFCiwgHypbCI3U3lBwz4Z04rOfhmx7SfT1TkAWwbO7HExlKEcM/gDSO+EtHZgLL/ZqlqwUQAtLWT0LaJEk0adgzM0TJXpAga2Gn2ipnidC5Qw6zUSXZ8HzevgLqampZw44vm0kmVw3CBiCalazRY10V3ie2IStokY756SkpHwDaVa/Ox3ownOYHAZVSeN/bxGYsJ9KOm1FcEMdelU08H+CHvEENBW4xHWFIIZwJyhgxRROQIhYlSmAfzxoSYOjkSSpRRCI5vqypKSkVyRJ0jYE6csijMuMU1+3cx6VVoUhjxkzJuSxowov3edyUFhnJZn5snlJEHQYVLhL4Neo/QZBbBnqUOH14YIFC34DTXn9Us1+fdSoUWx9yrjJKtAUpVqDSNlkBcnKz5JVMEtZTiKWgi1vSzqBOnqxaKiejSpn9G4CnnvKXavePl+S6Nvuy0g12IEicwf4X+FNd1Hjf8ZSRY1v62xJklZ/8MEHR8wxh5cLJh62SjqUoQ69KtrhcChSMPosrisM79XUeWhHnX/COviAH3744X4MULdF69GA672SkpKXMbD1tsIZLkPGYBP02NG6DJrklGmuXk1p1baarzJfSIzKhiuso44N11CHisss7Nu3L9vXVtZsUd4Zquh7IOGZbrJCud7JeN6glqysLGV1s7gtSY88mnFIc1VWPYMmV0C1amrLGe804LpBO/0HI7aros4BQ+uMpRjWRthBbRsGfQhLJQ1JOJ8kMjXUoVdFP/XbXN4NLa4rtP0m6g+gYMC19F1jsHgZXecNQAiq5D6FmuwaDKh/w8B2OQboR6Gi5N2qQZEGY8g7ilNW3LHr81Mf3jT7NrM1ZKieu0sSJXUvpGVqI6FCI/NVdzt3L7BvqCNUG9nZ2V7Q4AYVDhMTVgszjTupeRahBNg/QSr0syVthO1VQKbXF5bK5HdbkrFetNJ4r6egn88a8Uk2dz1bqZznzp2rqJAxqbpc1l03aGzHTtqGijoTz/A+vtOo7KI29gn/C2GppLF8YmmoQ6+KBo1ZCpbRnriuEEQQrpICggFX0qFW/oIJX4KOM4NAEJH71IeD5s+ffzQnJ+dBr9f7HzChf2GAY9y2kaoMOfu0rJnPnXLRr+2Tj/VH5YA15HX96GKPl+7svoICNjoB3tRZMV8V2I6hDhU2VAhm8hMGy698cNAQ+2KBAdsz1udmgDEE2JLWA3Acav3pGIXncxyhsikro4D2gXEp6/qSRDE7llQV1TMmF367nNH/Cfh2prztM6zB1w1KMl0GhqRuZgNI1RzwaypqSZKuBDY+X6yotkFrSxU14KrkwlVJYy2fzZg+om8USyQzMSEZq6qiH9+WczbK34XnyVpYyy6oI1wdpYCjjj5XvXksDFLMKPnMpieMh2bYm311/apBAliN/CnvE9YAABAASURBVMsxwJ0GlfRrLDX5AYRIVFRUTEXdZ1SGbNzUBZUdH8U5BZLxAviQu6xDMV+1O90LyNJQhwoTKsSkQ7Fkhf5fYAULRqBsskI5MwDtwn6kk1GPN5N9ABXtdKStXSIZri+kblCnv0wxPJaEZ4tY9YznsVQ5qw+pv25QzYtWiL43w8RwC77LsWVlZe3wDq4B7v/Bq+580P6dhISEnejru/BD1IKqhGjPtko6rYD4uODruvYcJNO77gpqKUl0nyzTExcc2fAPSZLY8tpITGh406UOXETrIwUEA64Dbx0DxWtxcXHJ+Ofmgf94kEc6zjAMy3WCwBHKX8KgxkYUHsKAdmswWLUs2LEjZsjg+i28RM9hsLK1y9ou81Xbh4o30FCHl/4PeOJUGLMQ/U7BM7IEmo/ys+Ct3HcoyABt7ocvQpytYyHQ3Lmg70B40+sNVSizTVlJ8cqVfbwhiyBJRvVYEk+i8C7DVj2HUjmT70+9brBXPlVFG+PD5h8YDW3YUFFfBQxfgWn/ineaDc9nkJEVmcOE1LZK2spQB775LyER/zj00IaH8B7EdYWRvYo6WUsw4DryWqE2K4cK+WEwhhSokE/BY/FgzrNy9rdzHpcxDMOiPKSDWnoXBqCbwFB+wUD2H0jElpu0GBmkX8tjR5sGUnvoc9PAJD9iWGbIUMcGPfaU7KUvoKa9RJLoU3XNl+sG85CEX0T5o/CK4/oNvMQqQiVt/MEzDXO73Ww/GFKKbMmoJUn6CvRTLFmpOIqLi99EXH/d3XBIaq1A4wsx0Gq2pAET4Mw2ZUGVGZNjSZGoniGhBVU5+z1QCU2G9M5098u2m7CCw8QoqKENvA9NRQ0crLWIqqEP4FQc/l9s7ZJ+qem41sUOmgBmy8Y3lLr4aYVB9lOHTNPwLZ5x254veemCJ2/iukIQp747fBv1nQR17/mxjrkbg9NM+Ed8fibnRfqkYCiLwViuAxO/HJKF6SYtMLJzgd/0tiMMPCFNTeoZMgaxLAxi4Nd0JnB+D/WdB8x4th2VNeAprYAeQv03OM4e7d+wLp381ujAYNpgUjELjHUxYDrBWzkI7kRgqGwe1M8S1pIlS46DJkbGw5ttWIPAqvY/A6mlSponI+incvQJ4Wg83ww8NE+cKqC+nPRzBvHVk0ARucP7Clv1DLqEVDmrPWIDIqDvqVj7/V7Ni0Y4JExDG/jO8+CvjqWKGvhDqqQf6zD2LNlBvCy0RaUDvt8uHon+hUnKk63Kjtze2n1kNpfh23mCQ+HrLwUEA66F7x4DZCcMrHeA6d0PRsJMKuZPAWk46CYtMDLLY0fhmJqEujgZEuscDOqKeUkw4z+AodpSWeuJAIn5VuDQq0QfVA11gHaTMKFgqfcKfR1DXLFkhed6TM1HHe2yBjUvMTGRje6zRKNmXYb3o6g9MXHRbEmjTe16QxWQQ2gBpqOf2qascpl6YqDmtWQXOP/zDBOpD1f1bFflrO9PItGdFUTP6POiEY/U0Ea4Kmr8/3QJp7/QCIVUST/QYewtx50JfMmGXjvSB5MqXpvO/+ueZWlo03ddYSZvLkNSuPpIAcGAa9lbx+D+V3R5AySyvzNzAFP4DoN71AdAtGHqMACthiRwOdo/DRMAZZOWr0/zoKo7bKwUjqlJHfO9BBKhn21nvYRshyEPWEHuRAddDmbmZ6jjsT/0W4m+v4x+NoMPcKCpsskK6+Rs4P9TqNUtL2vgyrNmzTqEOpq0jTz+n7oDoeJY8wBGrKik8a6W412drxTofxLJb1OW5KX/4vn3Q3Kq0m1J4aiemREVFRWxFMvny1lNOgHvecrbvl3O+u6q8V/6UDv0M6k3n2VWM6MQ4ruKiqEN9P9X+KCGPvBOeK04LFvU+M5DqqQfazf8zYKU9nyk7ZiOJJeCCZc28Jb1OPfoph2+/EeHDx+e4IuLoJ5RwFHPnrdWPy5LNHgAXs/0+4cFQ7kLg9YolFWbw8CmbNKCGu0RNHoT0gG3HW3sb9/UZDDmC/wBzg5DLvfSbSTTYySROthJI4rW9GlbXhSAz5ehbbLCIKsMnKEua+B6LpeLzTGWcNznr8X6ZWtfXAlAHza5OAGJAJV0wKYsid6BVPw6YEmK8FgSGL1t1TMmULZVztwn1Vc4aWq5J7rS7/jx4wd4PJ6dmLRE1dAG6J8HH1UVNfAFVUnPbtb/jaWp3d7FJMWr0owk4vuRd198aF3XRNl9EPn1+rpCPH+9doIB16LXD4mGLwMwvQAAjDCzuh8FauldkiTtxgRgNgbxgE1adk1Nhst8zZ6zc5656czVyW2v35TYsr0XIx/Xi/dW0DW/f0d8RSCnff4AnsPSkhUG2iWA+w88u4DLGsCs96DgLXjVJVVUVExRE2oIpmKpkg7YlEWUgS5vxAQi7NuSeKKGdxJy1/NEC1vOkNoVwxpqv83C1RnUA5OEkr6rKKhtbLO6VnmYRPYG3coWLFiw3QqmqvlmKmrgVNdr2QDNVUhru6hZM4C0pYNGKKhKenHjtJs/T+2+yYCgp1P2xo04uMblyxfXFfoIUd8CwYBr1xvnAcKqx1oZBuCGGMwehRS0kj3HOc+qYqT5kPLU246egirPb5PWugx7piajwXzN+n9n03FN7uuYecOHLQZe8GbLs+n1NudRuaNyvEvxlNGNe5bShYc3Ulrx7uVdPQcHgjnyuqsZKiUPjCHUZQ18JMmrAOMHDPCGCRMm8AUFSJ1wYG7K9YYo/x9o5qeS1m/KQg1WVypriOEeS8JEjdel/eyHAx877ZpBZizhqpwZgepByalOBwUwebU83HDkyJEdoElIAENbHW7dSOFzc3N/hc+G53Vg013UeEchVdSYgAVVSX/RuHu3vMan89KG1lVIxcn9j21Laek+yvmt3G53wIRNAxaROkoBIsGA69irzc7OduDvM0h0D2CQ78Oe45zHZdF8XDAl7dgRpGFtk1aCQ35vaaNu6aFMTcaK+WLSEbDJamd8E/qoWQYEykoKNAATBgM+euXvP3z9l51LX14X4vpFSGWWlzUwRgzivyJUjlghZJd6/Pjxmzhi5gGvqKTxfmZBezBdhelRQNMhWSqbspB3HvwBpJsn6m5L4okPnvFersee45wHWEI8pOoZdSJSOTN+9phcnSkR/RqOHW+uZ+XR52aYNLSbM2fOciuYWOfjfVRZRQ0clirpJak94n5o2Fn/GCAhOS4pWqOOwdp1hZgctQNN7oKf5vN3cZ6+sojXDQqoL79uPI14CiosLLwMZBgEb3SDfGXG/IjSkKpNjx09vGXe5hnbPt73aeMeqwCjbNIyayAWzBeDVS8wl2/B1F5GmwGbrNYkn0KfNO3jQZniHLK3oSRRj2IHZdq5frGvyWUNCqITP37HSiRJmjx06NAGJ4r9Y5C6/4eJ0QDA+Rvu0G3KQo0UjNReL0mTrhgz4lE8XxmkpW14Rm4rG+XZHOc8LkM8QCoF/n2Q5G6eWAWVM9o54WSaTElkPH51ojyMmNHQRhhVYwJaVRU1JHhLlfTHTfvQxqRWfv3uXrzX2alMWe7m6wr/jW+4BO9qB97jM/AzfP4ZzuMyvOPpYtOWHwlrdaI+M+Ba/eKsOo9/2AGRlFnVscrHoG567CjeSXfGu+jhnHnzXkRfTC1pRZv5Qvqzbcnq20an8nWCAYY6OlusIXtlGlJymOawhHz5vOwHhxatZ3u+KlnuHj9+/GlqAhJQIeiySE0jbJWcnPwXhJZu7ty5ASpp/aYsVEz4MaWTI7v9KFeJFPcA0vHwVo7LTFXPLpcrsSoqZ7XBNRk0TJLsXTeo1rEK8d6CGtqwqldd+XifEamorVTSmETRf5oPpD3xjfweoWvJ72p6JP5nEtWEMfSVZScmJhaDEd9iLBfp2kcBwYBr3zsL2mNIVE4rgGBlVnXM8vHPz0ehAo4drUmnyyBeruv6U+WuY6ilAyxpRZv5Qsq2Y8nKb5NVWkFoQx1WDPn8oo2NexTvUdYpeUB0eNxvbhlC2qApSdKTBprdwUYlDHkBSQz2fippdVPWuy3PpJxm/ahCivhfdR76WQ4JitW7fdHwSnwHA9Deh4iH7SK9btDYENOkvLz8gvj4+K/y8vIqjOU1LQ16ha2iRp0AlXSpw0VvtTybDroqFSOzm/enz1N7hPW4eJ/8MbyE/8MlYVUUwDWOAvwia1ynRIeqgQIRNgGppTGqjsHg4nfsyGhqEjCag6pVsaQVT/JVi5tk/IRBKOCcrwZsM4I1sTYYgOxYsvoQDKc3+uC3ySqYoQ6zLugZ8qbG7YcAZjc8uclxzlfezmtZQl6fTtMe2zJXcpL3Jy7z+U6pqalZvnjQAH30U0k/2DHzpg1JrYPWsVHIEv8swDWBfyE1NfVMSN2bEQ/bYe23ytcNqo2iH+ekpKR8M3v2bP3xLbW4xobhqqixth2Hv/MwMWNb48pzHXUm0lutzqYPWwykggbtlbwIfy7G/8BnEdYV1WoABQQDrgEvoTZ1ocJ325G+zzJRSFOT036b73l4+/zeZx/dlPZhizP2P9X+kn8OWEHFFMEf1sICNlmZoFEsWWGiMAEMR2GWehi0bWqoA0x0vB7OLA6mwec371bL5jftm/RBk7OuR/p/rLLOPLDSjbjmMPjeqyVCRLivYMRsuIP7fGEIcDvFHQFky7AG4CxdNK8bhNYiKoY2LDtbTQX4tmypqLE+/wW6tBH+cnhlZ/sBSMCrk9siWWV3UWZm5pQqYxEITgoFBAM+KWSvnY1C+lWPHX2tf4JQpib1auc25UcW/3Hftx2LHIltMRBbbtLS41fjYLy9MNhYbrJiODA7Zn5PQOpQLFlxnolXsk5dQYcdMtY0ibYoGUQSJhNvb0gny3V08v1h8H1fkqQvfck2axu1uqdHASmXS1z19bbByFfU1AgJKsM+753bcRmY+zT487foVNZcbvSjR4/myzSCmck0VgmVToUKWn99Xyj4gHIIbdd72J5xQEl4GVgzHxALQxvh9SL60PgeQqqo0eq/4Ffje9iPMJruOXwzraKJUOCqHgoIBlw9dK6RrYChnQ+G9jD8faNGjeoeqpOQfrVjRyrshn40WJap5PQVtEHN04d65isRLYbqdzykz2IMWIolLTCxh9D+rfo6xjgYv+1NVqibAdz3Q0pVLFkhHdR1L6Bd6P8wMF51J0wK1rEXrutH2uYqKwRQbd+I/vP9rgxyK9TiAzni87xL2RclmtesnwsJRUJWN3WBGZsyZOD9G2BBLvxGx0k+nBFhi9Z1g5hwxdzQRkQPGMVKNlTUF+GbMdsoV5Ve8Pu9sSoIRN2TQwHBgE8O3U96qxgMX8BMPA8deQj+caxVrQEjvAlxUwf4gGNHoUxNWjFftQGzTVpqmRqi3bA3Wal17YZphfSLk2gE4BWmDc7Hl6h/CkmYJVFkm7s5c+b8gpKn4RUHKfON7Oxs5X+qqKhoNjK3wiuugqQzHug8Tu5ZSDPSCmhEUmNiVbcpQ0YFfieOQC+FAAAQAElEQVQIoupO4AwXbQlNJomqdOzoZBjaCPcxow2PiaCmosa3wcsJ2nWJ0W4L+B6EF66WUUAZLGpZn0V3q0gBMNpMzMInG9CAB9HzYHh+u0KQvhSS8qOQoF6GBOy3czaYqclQzFffNtY8lU1aaONybgvqtIaQJqu0yUqP304ckvByL9FEIoIwrPx09kr06a/9iTedIdvcgSamlzX4dvY+p6+FQfheNa3f1KVnyBuTWvEkiN+FChqt0PndwKS9a9MpbI917YegJZgXSV21zuO7Pln18OY5C9V0fQuf2DH//x7bljvshj1Ly6L1Qg14XPjf6WXIE8kaTgHBgP+fvWuBj6o497Obd0hgJfIODwkgj4gEEHmpWAUEJFkSwXvlJyK9gi98FXtBUQOi9aq1+Grl2qq1xVuLQCjiAxXRAkWBBEQRBW9NEYQAJgQSINlH/9/JnuXs2XN2z27OJrubj9/Mzsw337z+J+z/fDOzM1H+gCLRPZBvvk69Kcija9QEpn0T7Hb7W0ivg6UsnaqVmJi4Ff/JC6jsngBHTYZCvlQXeVjD3pO0QMSfgqxoDTXQOmjATVZUZ6g+t0ysxH+Icxta3CK3ziX+gvEk6dUV6LKG2traV1DuCLzsJgDTQXJCGcqE/Fr7EV8p5WbG96W2by9Z90KEFKIPKeGUU5ZJdLvaKNMtNf596vlmTz/j8Xid9H/Tm+JI1COA75uo7yN30HwEMvSqBOFKebDs7oAOTZMiaHAg4gz4P6wd0XGYxSLS+u4Umxtyzn2CrOT7fEP+qRHIPddisSxDbURSWQj9HPINb7LyK2xAAEuYplqXyKowh69p5RJ0A5Us8gsx1Ui/x/S7rGH9+vU1eJmg+pRlFigTGvFIWL9SM7XWZCnkj+ZDwBH+77mDdhr/N2mfQVA9VogeBJiAo+dZNEdPArVJ16b55Se7nVlZ9dUL+u4Qv1Znhku+sLYjtslK3UcjaUwJPwQLjV4EJHWQ8Jw9eeJRKaHzgRcWzcsaUlNT6WKEKkWx62AF5yjSHGUEGIEWigATcAt98MGGjbdpyRJW642u3i/Wth1YAoICL53LDZd8scZsaJMVWtqJPs3BevGXiEfc1VjFXAzwfUVDC/fmCfW6uTdb77KGN954oxJWu5fMUYD+z92HUNNhjCmaGSYI0111JtTCVTQGAUzFN6Z4wLL4O3MEVODMqEOAvgyirlPcoehEILf2kKhIyhR7W3XyOUAjHPINdZMV1oQvx3Sud5OWKQgFqGToDhHyQR16lzVg7XwpmlKe+HQzrP6OkAng0BMW8Uz41+H/iS/R+SSPhO99pqICL06GPNo/a1RXrYdp1hNqGaeFhPuFpw9XANtIuTWRqpjrjQwCTMCRwTXuarU5T4v29ScF3SikHFw45Iu1XjrJiixZw5usVJu0fo86rlH2IxLxUA/qKC4uduElYY6iL9JlDStWrDgM2avwskvDlPU6u93+T5fLRdcYUt6NyOwBXw4SdiE02zlHbDvdoV+ZCOrdFlFgtYhHjeiqdRb2LJr0QOeJA9VyTjfg3tpRnY2XEafZDxf1OZpqdghtsTMJASZgk4CMw2p6ymPCF4a4suobsal1L1kkhaGSL0gzF6Qjn2TVVqpE9QHyCbjJas2aNbtLSkqux1Rtb0xfh3SSlqopQ8m+IR7UsWrVKjoH+nmqHH1MdTqdr2DM9PMmIlcSSx55gxEhWTnCPyE9C2EvjK0H4osRN9up17D163djqj0t9N/94nnE/UEb+qAFztmTJ7rvHiQmpTvFuLb1p5YF1g4r17txMKzSXKhZEGACbhbYo7tREAbdduRdi6R1302tc0Sd5dwG3VDIF9OtGaiTDqMvxchHwOu5fyDD0ElWICrDJ2mhzka5UA7qwDhz8BLhPYADDY+GJwt3IkIfB72nMY4e8DPwYvEqQrKGBazil6HohjfLuT11Bq0v3OsGW+JBG8HA3HqpaP3VYPGzvUNFQWKiOO9sgliPv6V1RxPS6QXL7Of7UrD+cH70IcAEHH3PpFl7BOurNTpAvyf8GqHofvYnUQ/iPYq1X0qTz6w7bfinRrCKDG2yAhndCQIaGco0Gqal/a47pP5FwsMS1jyo44Gxlwyy2+0z7Xa7tIaLtvcDQ78d4pDPg9zn99dI3zhu3LhWyPNxNC4I7oc3y93vqTNofeFcN4iZjayEhITslStX0pWHQduICoUIdQIvpknfXiIGEelm1ouhJ5PE9r7bxZo+28RO2ldAzeJZ0G/DdTfikU6I/j5PnSEWY/XmRoAJuLmfQPS1PwvE8BR1q5WrTgyoPSS2Zl5AScknuZ3ipqP/WIzX94C/8y0sLGyyk6xA2n4naUmdNfmDDuo4nNzmCW+1bpE7rKa8LEG4ycL1ruEiX55S3oS47LrDyl2LF413ZQHCDunp6TT1jKivw8sIkfhHvtKwUh956gpaeM9gEfJ1g9OnT2+Nvxe6+GJL0AbiWEE5xexwiEoi3QGlYsPwz0S11rDxTGhj3odaeSHKPvTUFWIxVo8GBJiAo+EpRFEfQBCfgSik246uOPGt+KRNH2/viHynH/1cdKo/0c3iuVhhcZf8TFi5S2ABvgP/KuKXwiIytMkKFY/Hl4fmdYHIC8nBAlCepGXaJi2MKQfea+E+1+nKBR+3udDbtz6nK0TR8R3HIbgZvhfG0wNemlKGVTgLePpc1oD0OQJHAbj7xowZk4jQz6GeqyFsDAkT+VIdqCawcw8RSRa3uK5/qZAPFAlcALlYWkg7derU6KqqKuWLBnJahtObYu5fJsqNIIDnOxZ6H8CH6z7w1BFqedaPEgSYgKPkQURRNz6nvoyv/Drlq/TOosZzepJMvn1OH6Ep6Q01VlH0aHZBltVq3QZSeRBl6AjLmYhvhUX0AtJBN1nhy2M99Ex1eHnYjXqvRx9642Ug5E1adrvdh3DRuf3wPhbuB7Z+fzqRkLYScskNOvVD1uPlJTloV1rDlYT4wJSs32UNAwcO3ASMlCeI9bDZbFOhrulQ59XIuAcekw74NOZI9x5PWUMl9rrFHKdF0HV5hvTH4KWhrq7uyuTk5I89514bKhfrSkammEMZI57ROOjPxd+E4Z3vHt25nrIozi5WEWACjtUnF7l+O78ZIvrWWRN6lqc0cKiSfL9N6yB+02nsy1jPqsUXwWPoRld4ww7ESJtFnlyxYoV085DhgiEq4svJ0CYtI4SLpv8E72PhJrlP/ydYLuhBHQ6HQ+uyhidQn9cBx/nehEYEY3m2qqoqHVnF8IFO06C8YtKlMtA15MK5bhAvDaMzMjI24Tkqf99sqL1YVAp1ijmUMeJZvXDmzBnp+eJv4YxeWU9eMelSGT09lgdBIIqymYCj6GFEQ1cynGfTnS7xi41t+kibsNTku7zdMHEiOU3+HePIMPo8F2W+KCoq6o0wog7T0n6btOy+Fi7tVvazcNEpP8LFF95r8F4LFy8ghg7q0Lqsob6+vgxt7IaXHF5KBmLNnK5DlNJaH7Ayz6D9RfApSUlJ3fFlTGdKEyEXU5xklAe/aOPGjWe06tCTuWrF3cIintPLV8sxszASbe5evny55vqmWj9W042dYg5l3O++++5ZenarV69Ow6xSV+B7P/wjHn8/ySiPdEg3lLpZN3oRYAKO3mfTLD27qnLP1OREQZushBb50o5o6hgIoxPCdvDBnJal25V+HxusoBn5RLgguI5UF77M6De6SsLtDnk5fFDChY6fM3pQB740aapdXlu1JSYm0garXykrRB+JUJUi3Tiszn/hy/gJ1EuEvIjiJNMtECCjNE+0s1hET6z9bg2g5s3Ci9NQPLsf0Cate3vl8RIxe4o5HFxWrVpF+D4NjBd7/NMkC6cuLhPdCDQDAUc3IC25d3TUZIrbsbrXNnEg2e0QtOGK1nxp2pksX5l8gdE0l8v1JUL6yRICTUfW5XjkWOC13OhJkyadp8yYMmXKCFhXN4Dc6ZAKZZbhOBEu/Ex4+lkQ9UEm3GmohH7bTIRLMiJE76YpkNlr8F4LF7qGXN8yccjtFuMxHS0fMZiB6YF1ewYJHwsfU9E+lzWAcE+gAeofAiGQHoVxXy4lmvAjVYhfOIR4ykiTeDZxe9AGTTHjmUkHZRjZxWwEL9ZhBIIhwAQcDKEWki8fNfnXdpdUwwpIn314U1cd8iWyuA6wNCwQI6LjbgahrUdeK3hNB0swgzKmTp3aDuS7CSS0xWKxLAe570B6ldZvZElf6UG0OfBahEs/C9KzcIkcN6O9efn5+Z2V9YUT779T7EsQgqaQJWsfbxztLRbx/t484a1bfVmDxWJ5Ae3Teri3SYx7vjfRBJF9AwUdi5h2UamQlhsCNRmPB22op5hrPQdlGN3FHAgvzmMEjCDABGwEJRN1orEqEIb3qMl0R11aK5dY2bmuKlvD8jXcfRDMWaPKWBN9CWQ0SqmP9JRWrVrRGqdSLOyB13D1CHcGXgZ8LFykDW3S8mk8QAKW8HbgOBMqMIZh0QpxgQsk/N0Q0QYyyakvawBGNIV/RMps+JiA8Q1qiEb+05Eg7q9ziqDWL16G4uagDbxcBj0oI/LIcwuMQAMCTMANOLToT/moSWKO6ce2zkN4zf7Udg7VtHNEMPJYuXatykHCZNnmgJQoVE8p34gyhgkXun5Oa5OWn1IIgn5lYiX+Q9FPhhpKuUVunUv8hb70SaC+rAEEfAf8O5Sn8IbXghVlQo7uHiz64TmfvvgL8UOgwtPj5KANnmIO9JQ5r7kQwPdFczXN7UYDAvJRk1WJ6dKab48zx22w5N5b3u7SMsWar0ld9a8mLS2NprL1/g7PR4n98PLvcBtFuKhH061evdq0k7RgCdNuYu/B+CC5azCj8Lzc8CrVZQ2Q58JXwcvuOrxw5MiJSIWJQtyfYBVPB6ofSwMxfdAGTzEHerqcFw0I6H3xRUPfuA8RRkA+anJHRjeJfGnNt86auPGxrhM31CUkXRSkedpAVBlEJ2i21WrNDqJEm6bC2qUcpF6fbFjDpp2khTXEh/ASs0xuACQ8BxaY9zaipKQkmlr/kfJh5V8Cf5jiHk//J808J9hT7blgz2AxHP377sId4tg5qW9sTIwetEGzDcHOYvYdKacYgeZDgP6zN1/r3LKZCCRire5hfJnfplcp5Xl0UkmHjprckpnjJV9a830se8KgU9bkJ6Er6ZCehv8jSIQI+pRGnmERpl/p1KwtgQqUlJT0KCkpkdZwodfVbre/iTFshH8GFloXyEx1jT1JS+5MjVXMBfH6HNSxN0/cRfkrVqz4CeEv4SUHHOhnUso185sxNpJJ+aZ/uNGPINcN2my2mDpoAy843XkXs+l/KVxhhBFgAo4wwE1VPQhzCvwitJcGr+fSPDqTLzx9RBDh2n/aKcjypfjydsMEpp1teoVlOQhjHUikUeTrqYt2CR/yxAMGINxboPAx/DSM4Qr4e+vr67eBkHtAZroD6Tdqk1awgzpQ/5+B4wZPqyrdGgAAEABJREFUxwlzpydOQZrD4Ti3lkwSk7yR6wYLCgpi4qANnmI26Y+Cq2k2BJiAmw365m34m7QOwiLcavI1s1OLQI40Ta1bJwhoJIh0uK6CJ2Py5Ml0TN8TnqQyoMNA6DhMpcy0OKal/U7SCqXyYAd1YPr9VmBwxlMnjRFGc0MKuMy54YYbfH4n3ZDTuE+6brCvRXinx9W1Re6gDXVL4aV5ijk83LhUdCLABBydz6VJerUvtb14pcMo4bF8TW0TBDIWFdKmKQTazuVyBdyBK5cCSfVHfbRZSxZ5Q+T5EDgs5enw60H+nyGkaeqOXuUwI43ZpNU3wEEd6ssa0D0szeKzwdlqampua4ia84m1X+m6QcsOUa9VIyzfqD1og6eYtZ4Yy2IdASbgWH+Cjez//tR2AtPOIdUC4hwLgnsdhXTJDdYdTYf3gk6jXUJCQpJeJSBmbx76tBjpP8MT+Q9DSNPU/8jPz++gV96oHNZw2Ju0Ah3Ugalm5WUNPt3By8Vdnp9p+cjDSQS7bjAaD9qIpynmcJ4Zl4l/BJiA4/8ZhzRCfOmTdUTnFG/XKwgdWo+l3+F6yU+tC/J7H+ucIR/tqK7HaBrWGx1g/6CGfg+8DJi2qzjcTVqwhDUP6lh6aC1heKtGv0nUIT09fRZFGusDXTeImYKoOWiDp5gb+6S5fCwhwAQcS0+rCfoK6/ZlkOc++EA/D/oIXbkZ/gh8tLih6LPe3/MIszuJl4uQN2n1KxOaB3UsPFBCm8ve1OnjffSTIJ08Q+JA1w1Gy0EbPMVs6FHGqBJ3Ww8BvS8sPX2WxzkCsG5vh38FXnd6GXnLQECvAYo6+KhwsHITA3TEJw9T0hdiunoBLL9F8FcEKBcwC9PSIW/SgiX8HCpdAi85txDSQR2YilZe1iDleT562Gy2qZ54eMFpcZew+F83OHXq1GY9aIOnmMN7nFwqfhBgAo6fZ2nKSECuh1ERHXwRcAczdGLSgXBvBVl/hc4/DouZfje9EWS8FOmwXaibtLQO6njy4Nu0I3qxVifwTOZryY3I6LpBkHyO+rpBsqrr6uquTE5O/njjxo0OI3WZocNTzGagyHXEEgKB+soEHAidlpn3VElJyQwMXTqpCWHcuMLCwmyQLpFtgmpQd9vxT5bBMmwLon4Gov3kKU4yOV8rhDV8EkS8EFP4b4Lgf48y12jpyTKtgzoeLV8DrhRlso4cos8D0fdJcjqUMFVoXzcIq7pJD9rgKeZQnhrrthQEmIBbypPmcQqQ40TAQHcCI/B1sDLzSTJ79uyk+vr6j0B69yJNZzLnUJxklAdZQGd0k5bWQR1Wt+uZwuM739NqAH0I+ZIGvesGC5rooA2eYtZ6kixjBM4hEP8EfG6sHAuCQIbzrGhfX61JUEGKxkQ2SDYjQEelvCNHjtB6q9aVgIM8ed4qPGvJs2HtzoCFTFcLevMwixB0k5bWQR1DT30/t+fZY5u9FXkiIOBRsIIv9yQNBVrXDUb6oA2eYjb0aFiJEZAQYAKWYOAPQmDUye/E3Qc/ehzThSfvO/RB3oyKrSL/py8EXVeYW3tIdKmrEnSBA+nGq8f0cZ7e2JR5mJp+COm90F0GcvwjLOR9sCynIO11mJYOukmrb5k45HaL8Zh7rvAUzLih4vMBqa76Gk/aG8CCn+9NBIloXTeI/kXsoA38zfBZzEGeCWczAmoEmIDViMRXOqTRfNq6t/hr1pDnXULcvDs9+8eqxHRhc9SKITX/EtcdLxV3/LhRPHjgHbHk+5JX9wwWu2dVbGlHBH1Z9X4RRwRtDQCalAciuxo66g1TbUDIr8Iabo88HweC3grr+3bkX4/8JbCcM5UK6oM60l11tsk/faF1pvcEu90+SFlWL54ofK8bjMRBGzzFrIc+yxkBYwhIXyjGVFkr3hE4bU0SuzK7fZ9bJt76wNbv8N/aDhSvtx8unu30M1Hc9VrxWNeJ4redxojPMi/4vdsl/liVkF5PBD24xpegiw+8LRaV/+31rweLtXFI0PRnMI0+1B5E2wYy72YpkOUYEO6XkFUi7yDCTk6ncz2I2G+T1r0dJ3zrtCT8HDowhoXIqzlgzTlzDEk/twDT3d1Q73zU/wh5ipNM1sTLkc91g8g37aANnmKWUeaQEWg8AtbGV8E1tBQEaqzJ4odkm1ibdfHmATvF06uyBlVpEfRbWYPFoRTb+2CScj2CvvvHDWLxgXWvLDz47pKIWdARejAgULq9SK926QIFkN7FUHgPxDsAIbkUxGeh7INYH74e8d6wpH8HPwckui8lJeXEQ90mv7yhTV/v6WF0U1Ui3nSosMJPw3R3OcrTaWXFkBdTnGSo5yz8I05hvUd4rhs066ANeYo5xSnGORyisu92sWZAqdgw/DNRjT6wYwQYgTAQsIZRhoswApoIyAT9ZXpnsazj5cv7l4o79Qi6tFU3UWe1Hkp2uTprWdBE0LQGDWvuhTmHP50ea1PcIMV5AElrQ9u4oqKiPJDw8yDjTzA1/RL0esGTa/2hrW+vza17SaZvVv0pcXn1PpIb9clQLH40e+K0+e3ss2AVN+qgDa0p5ot2inX9y0Q52mHHCDACjUSACbiRAHJx4wgoCfrvrXuJJV0mLHy466RZ6ilusqCJoGkNGrX36Hy2arxyDZqmuGWCLjy+0/bVIDEv//iukVG2Sawn+q7pHA5HjieDztT2RM8F687LzTqRmLaSJAdSJIOaooZ9nTXRIoRYCqt4V6gHbfAUs2GYWZERaDQCTMCNhpArMAsBNUHTGjSs6Gsf6Z4/Q7kGrSRom7M2yWIVNw07+c9b5E1iSoKmNeixVV93/DJPXHfxyX/1aMJd3ESCmtBYrVYpD1Zyb00FISwvdv7Zs5hFOLkv1W9PlwjhX2+Q8Foj+jzFbAQl1mEEzEWACdhcPLm2CCKgRdCvtB95FCR90cIe9psf6zpRvNhpjPAhaEetuKj2h074Q3912vEdc2kXt5qgL6veL4ZXf9dpb54Yel59jc8OZdFM/05Zkp4uT2lrRl+uwrownTPtN5K4nmL2Gy0LGIHoQwDfS9HXKe4RIxAOAkTQB5NtgtagaYqbLGhag36m89gyrFtmPtvlqge0CJrWoK+p3DPSJcS2eQfX36JF0Lm1h8SAmoPn09nK4fQtjDLDwiijV+Sp/Pz8zgUFBeOvs+eX3DPhsq1PXXXR24eSOtpPJonttKGqzzaxk07n0quA5YwAI2A+AkzA5mPaLDVaLJbV8I+g8dPweu406cCv1lOIZ3lFUuuzWgQtrUF3n7zyjBDt32g37HW1BU0ETWvQNxz9fEaqEBXF5WuL5DVomuImC5oIOruuKlpPErPYXHUf9z1T8V7O6aMFVQlpl27OzJn0+vnDn3yyS+H58fzMW+jYeNgxggATcIw8KAPddKxevXoxyPV3erqURzrId8CzUyEwuEwc/apVl2NqC1oi6K7Xiqe7jHsZ/2Euee+8/lvkTWLKn1nd/uNGzZPElATdhGvQPqOrSUjusy+tvfgmrYOoSkyX8zq4XK7H5QSHjAAj0LQIWJu2OW6NEYhdBCqTWp3sWya2b22d86NyilsmaFqD1jpJjCzoouOlggia1qCXfK99khhZ0Kmu+ogA5LRYhUtIe7/U9Zs51a2um9OMQNMjEEMtMgHH0MPirkY3ArQGrXeS2CJY0ETQtAb9eeYFL1vc4jXlSWIyQY+u3t/Ug0xs6ga5PUaAEWhAgAm4AQf+ZAQijgARNK1B/y3r4i39ysSvlSeJyQS9NVP358MR7x81MHXq1DZ2u30a/OyioqKBJFN75M2cMmXK2wg/hF9w4403tlLrcJoRYASCIxABAg7eKGswAoyAPwJE0KcStA7P8teNhARkOsjhcNANT2+i/mVOp3MXiPbXiHsd0s8i8arb7aYzr69C/PGTJ0/+febMmamIG3Yg+gy0twCeSHwdwpmGC7MiIxAnCDABx8mD5GEwAo1BAISYZrFY3gaxdlTWg/R9IN2bSAaSHIL0XRRX+bzKyspZShl06SKKp1D2KYor84is6+vr/w4ZbQAjEp+ION0kReSOKDtGoGUgwARs8nPm6hiBWEQAlu9okGsXrb5Dfr1HPtIT+gUg71GyEIRLxPoxys0jD/nHHhmiQnjI2u9aRejelZ+fP1RS8nygnA0kfgU8XW7hkfoHeIHIKC4u5u8zf2hYEsUI8B9sFD8c7hoj0IQI2AK0JeWBZJP0dOQ8EOVo6CyAV7sFnjwBXS9Zq5WsVusIWQbyvRvxAyDmjfA7kS4F0V4AmddBVgT/DSzqk7t27foJ8cdnz57t00+0ewXkNNV9EPFNhYWFU7wVcIQRaEYEmICbEfz4a5pH1NIRAFGO18NAzgMB+xCkUl/OA1FeA/lS+Ax42eXBUl8rW7og0quR8RZ8H3iB+tsgXFBRUeFdty4oKCCdDZDTVHdn6IxyuVyrUP8tkLFjBJoVASbgZoWfG2cE4gsBEKj3lA/1yALlqXWRng3v50CgA8rKyiQLGkSqZWmThX0HLOV2VBhtPoEyWt9ziymfPSPQnAho/WE2Z3+4bUYgZhEws+MgDrLsTKnSzLpM6ZCBSkCaPpvBlEUwTS3nad4mhbJWp9OZ4ymT5wl9Auh0xHpzZx+hgQQs6pGwngsxpS3X71dq8uTJF6DuPLwEpPllGhSg/iHwD3n8EIPFWC3GEGACjrEHxt1tMQg8g5F+BN9YR3VQXY2tJ6bKg2DlY790v+PwYpJgdFDXXnttN5BhKcpsRt0rUW4/0r9B6HWYEs8GOX+SkJDw/3hJKMW69AHI/surgAhImX5nvRRlj8CfgC8hwkaW10G2EInt8GSlk9/ukUHELp4Q0P3jjKdB8lgYgVhEoKSkhNYvG9V1M+ow1oHY14LVmgkC7QdC9JtGT0pKegMjVFvT94AY74FccpgSXwNyvlxKNHxkQfYy6r2yISkESHkt4rS5rD3C1vAFiYmJn6JdSgvUNwyyR+HV7lFPniRHnZlIk4W8EeH7KM9r2hIysfXBBBxbz4t7ywgwAiYjMGTIkCQQ2DOwWo+BQPfAgq1A+mG5maKiot6QS+vOskwOYRHfSHHo0+7twRRXe9R3O8mgMxbhZfA+DnVnw0tr3qiPDjjxyZcTch6s6DT0dTPkZB1fgXAcyv8vrO3nEfdz9EIxZswYzSNHJ0yY0Br9ugsk/hrCX4HYe/lVwIKIIcAEHDFouWJGgBGIBQSys7MfA4Hdi74mw5NrhfQikNIvKAErVvfKRuhJm72glw2v6aDThTIQDqBQx+d65Mpd3x6RN5DyYEX/HJKL4H0c+nknSPgSWQhCHY0xlOEFoMZms9F092+nT59OVrekgvz2KSkp29EvOgDlJoTzQexfoMwESUHxgbXvS6F/E+pXWvgKDSlqQVnpJ2tSKswPvGC0oxcBebd7mNXERDEm4Jh4TNxJRkATAVrbJa+ZycLgCMACTIFlKVmoGtpzNWRhi9CO7vdtoDyNBkPVIwYAAAV1SURBVMna1hALARIeThkgy1wQ6nrE5QNPaFr9ttraWppKh1jQz7YeQqQ3vNLRxrE/yL+lBhlmoK630b+tqO811P8JSPYzEGQHZSEQ9APQOwZZJfIPgqj1MIWKtps4cWJHlH0HLxgVeBHYV1ZWRr/b/g9t7fiQ6v5BxMfweBSMQPwigC/EpeTjd4SRH1laWhpZsHqXSXSPfA9CbwFkGPR31Pi7+CVqJjJFcM5BPgkkN4gkqEfvN9udDh8+LFnkDodjMZUhfYUfBoJcJqftdvtDqItmEdp6ZJ1B1C+iHWla3SOTAsiGgJwngbC7SgLFR3Jy8iokvdY36uyItv8PuronsEG/UQ4vGN3ULxPqCuklLVLWOBOwGm1OMwKMQItBwOl0yrul423Muj+Tcrvd0jovQt0LNDBtLeVBZ4YWMCDHyXQLlsdSlqbqNfS8chBdF5DvVuhsBzmTRV2O9P8gLTnEafOZpmWPtnzOHwchz4G1vR5laPPawyBI77Q6VYa20pD/IPK3kqc4yShP9ngJGIU8OkGtHC8Th6FDln0POZ9CyEZAZxum6c/s3LmTpvCfA1lnUp7sUW8C9KaiT7+C7t3I95kZkPX0QiZgPWRYzggwAoxA7CKg+2IBwtHN0xhuloaMpq+t1dXVbY8dO0aEQyeQaalJJ5RRBizp5QgvhZcd9eGXIK07SQCSDTTb0I10yEP/Rei+hBcDaUMbwkUgyM200YzyyaOtdZAvQZzau5TiJENactC9AC8B7yLh7R90aG37Q7ooBHIBQu0P2QeIy2eT0/r7XLT9Z8gkR+vpmC7fAr2/Qj4fwqXA9svCwkLNzXjqFwXoCyZgQoE9I8AIMAKMQMgIGJlBsNvtOSAp2q2tVf9MLaGWDMRGG8y01pZzYbFLt3GhrSK0daW6PMkoj+TQvRWhjyWLNLmcyspKeQr8vyHwW5oA0ebD4pUuBsF6Op3ERpY7VL3ufLS1QjlljXZvQ5kDeFEgK/oY4vNlbSZgGQkOGQFGgBFgBExHAKQl/cZZp+JAeT5FYLVKG8x8hOcS8vS1mhDPaQgh5/lMNSsVYMFKl32gz9I0vTJPjqMf8sY1uyxThiDgnqWlpdIaOl4a6CCW30Im75LPQpymq+mwlTiwgJUj5zgjwAgwAoxAXCIAUgy6+Qw6mr93JkDkPIQ0/U2iQF5XByQt5YFI/SxkuUJY2VIeyHqeLFOF82j9nC1gFSqcZAQYAUaAEWAETELgQp162tD6OROwDjoxIuZuMgKMACPACMQgArR+zgQcgw+Ou8wIMAKMACMQ+wgwAcf+M2y5I+CRMwKMACMQwwgwAcfww+OuMwKMACPACMQuAkzAsfvsuOctGwEePSPACMQ4AkzAMf4AufuMACPACDACsYkAE3BsPjfuNSPQshHg0TMCcYAAE3AcPEQeAiPACDACjEDsIcAEHHvPjHvMCDACLRsBHn2cIMAEHCcPkofBCDACjAAjEFsIMAHH1vPi3jICjAAj0LIRiKPRMwHH0cPkoTACjAAjwAjEDgJMwLHzrLinjAAjwAgwAnGEQBgEHEej56EwAowAI8AIMALNhAATcDMBz80yAowAI8AItGwEmIBDfP6szggwAowAI8AImIEAE7AZKHIdjAAjwAgwAoxAiAgwAYcIWMtW59EzAowAI8AImIUAE7BZSHI9jAAjwAgwAoxACAgwAYcAFqu2bAR49IwAI8AImIkAE7CZaHJdjAAjwAgwAoyAQQSYgA0CxWqMQMtGgEfPCDACZiPABGw2olwfI8AIMAKMACNgAAEmYAMgsQojwAi0bAR49IxAJBBgAo4EqlwnI8AIMAKMACMQBAEm4CAAcTYjwAgwAi0bAR59pBD4NwAAAP//DD9NsgAAAAZJREFUAwB28vD46ayoAwAAAABJRU5ErkJggg==0.1sepal_length,sepal_width,petal_length,petal_width,species5.1,3.5,1.4,0.2,setosa4.9,3.0,1.4,0.2,setosa4.7,3.2,1.3,0.2,setosa4.6,3.1,1.5,0.2,setosa5.0,3.6,1.4,0.2,setosa5.4,3.9,1.7,0.4,setosa4.6,3.4,1.4,0.3,setosa5.0,3.4,1.5,0.2,setosa4.4,2.9,1.4,0.2,setosa4.9,3.1,1.5,0.1,setosa5.4,3.7,1.5,0.2,setosa4.8,3.4,1.6,0.2,setosa4.8,3.0,1.4,0.1,setosa4.3,3.0,1.1,0.1,setosa5.8,4.0,1.2,0.2,setosa5.7,4.4,1.5,0.4,setosa5.4,3.9,1.3,0.4,setosa5.1,3.5,1.4,0.3,setosa5.7,3.8,1.7,0.3,setosa5.1,3.8,1.5,0.3,setosa5.4,3.4,1.7,0.2,setosa5.1,3.7,1.5,0.4,setosa4.6,3.6,1.0,0.2,setosa5.1,3.3,1.7,0.5,setosa4.8,3.4,1.9,0.2,setosa5.0,3.0,1.6,0.2,setosa5.0,3.4,1.6,0.4,setosa5.2,3.5,1.5,0.2,setosa5.2,3.4,1.4,0.2,setosa4.7,3.2,1.6,0.2,setosa4.8,3.1,1.6,0.2,setosa5.4,3.4,1.5,0.4,setosa5.2,4.1,1.5,0.1,setosa5.5,4.2,1.4,0.2,setosa4.9,3.1,1.5,0.1,setosa5.0,3.2,1.2,0.2,setosa5.5,3.5,1.3,0.2,setosa4.9,3.1,1.5,0.1,setosa4.4,3.0,1.3,0.2,setosa5.1,3.4,1.5,0.2,setosa5.0,3.5,1.3,0.3,setosa4.5,2.3,1.3,0.3,setosa4.4,3.2,1.3,0.2,setosa5.0,3.5,1.6,0.6,setosa5.1,3.8,1.9,0.4,setosa4.8,3.0,1.4,0.3,setosa5.1,3.8,1.6,0.2,setosa4.6,3.2,1.4,0.2,setosa5.3,3.7,1.5,0.2,setosa5.0,3.3,1.4,0.2,setosa7.0,3.2,4.7,1.4,versicolor6.4,3.2,4.5,1.5,versicolor6.9,3.1,4.9,1.5,versicolor5.5,2.3,4.0,1.3,versicolor6.5,2.8,4.6,1.5,versicolor5.7,2.8,4.5,1.3,versicolor6.3,3.3,4.7,1.6,versicolor4.9,2.4,3.3,1.0,versicolor6.6,2.9,4.6,1.3,versicolor5.2,2.7,3.9,1.4,versicolor5.0,2.0,3.5,1.0,versicolor5.9,3.0,4.2,1.5,versicolor6.0,2.2,4.0,1.0,versicolor6.1,2.9,4.7,1.4,versicolor5.6,2.9,3.6,1.3,versicolor6.7,3.1,4.4,1.4,versicolor5.6,3.0,4.5,1.5,versicolor5.8,2.7,4.1,1.0,versicolor6.2,2.2,4.5,1.5,versicolor5.6,2.5,3.9,1.1,versicolor5.9,3.2,4.8,1.8,versicolor6.1,2.8,4.0,1.3,versicolor6.3,2.5,4.9,1.5,versicolor6.1,2.8,4.7,1.2,versicolor6.4,2.9,4.3,1.3,versicolor6.6,3.0,4.4,1.4,versicolor6.8,2.8,4.8,1.4,versicolor6.7,3.0,5.0,1.7,versicolor6.0,2.9,4.5,1.5,versicolor5.7,2.6,3.5,1.0,versicolor5.5,2.4,3.8,1.1,versicolor5.5,2.4,3.7,1.0,versicolor5.8,2.7,3.9,1.2,versicolor6.0,2.7,5.1,1.6,versicolor5.4,3.0,4.5,1.5,versicolor6.0,3.4,4.5,1.6,versicolor6.7,3.1,4.7,1.5,versicolor6.3,2.3,4.4,1.3,versicolor5.6,3.0,4.1,1.3,versicolor5.5,2.5,4.0,1.3,versicolor5.5,2.6,4.4,1.2,versicolor6.1,3.0,4.6,1.4,versicolor5.8,2.6,4.0,1.2,versicolor5.0,2.3,3.3,1.0,versicolor5.6,2.7,4.2,1.3,versicolor5.7,3.0,4.2,1.2,versicolor5.7,2.9,4.2,1.3,versicolor6.2,2.9,4.3,1.3,versicolor5.1,2.5,3.0,1.1,versicolor5.7,2.8,4.1,1.3,versicolor6.3,3.3,6.0,2.5,virginica5.8,2.7,5.1,1.9,virginica7.1,3.0,5.9,2.1,virginica6.3,2.9,5.6,1.8,virginica6.5,3.0,5.8,2.2,virginica7.6,3.0,6.6,2.1,virginica4.9,2.5,4.5,1.7,virginica7.3,2.9,6.3,1.8,virginica6.7,2.5,5.8,1.8,virginica7.2,3.6,6.1,2.5,virginica6.5,3.2,5.1,2.0,virginica6.4,2.7,5.3,1.9,virginica6.8,3.0,5.5,2.1,virginica5.7,2.5,5.0,2.0,virginica5.8,2.8,5.1,2.4,virginica6.4,3.2,5.3,2.3,virginica6.5,3.0,5.5,1.8,virginica7.7,3.8,6.7,2.2,virginica7.7,2.6,6.9,2.3,virginica6.0,2.2,5.0,1.5,virginica6.9,3.2,5.7,2.3,virginica5.6,2.8,4.9,2.0,virginica7.7,2.8,6.7,2.0,virginica6.3,2.7,4.9,1.8,virginica6.7,3.3,5.7,2.1,virginica7.2,3.2,6.0,1.8,virginica6.2,2.8,4.8,1.8,virginica6.1,3.0,4.9,1.8,virginica6.4,2.8,5.6,2.1,virginica7.2,3.0,5.8,1.6,virginica7.4,2.8,6.1,1.9,virginica7.9,3.8,6.4,2.0,virginica6.4,2.8,5.6,2.2,virginica6.3,2.8,5.1,1.5,virginica6.1,2.6,5.6,1.4,virginica7.7,3.0,6.1,2.3,virginica6.3,3.4,5.6,2.4,virginica6.4,3.1,5.5,1.8,virginica6.0,3.0,4.8,1.8,virginica6.9,3.1,5.4,2.1,virginica6.7,3.1,5.6,2.4,virginica6.9,3.1,5.1,2.3,virginica5.8,2.7,5.1,1.9,virginica6.8,3.2,5.9,2.3,virginica6.7,3.3,5.7,2.5,virginica6.7,3.0,5.2,2.3,virginica6.3,2.5,5.0,1.9,virginica6.5,3.0,5.2,2.0,virginica6.2,3.4,5.4,2.3,virginica5.9,3.0,5.1,1.8,virginicasetosa,versicolor,virginica6.6,2.9,4.6,1.36.4,2.9,4.3,1.37.9,3.8,6.4,2.06.1,2.8,4.0,1.35.2,3.4,1.4,0.24.4,2.9,1.4,0.24.8,3.1,1.6,0.25.7,2.9,4.2,1.36.3,2.8,5.1,1.56.6,3.0,4.4,1.46.9,3.1,4.9,1.56.3,2.5,4.9,1.55.4,3.4,1.7,0.27.7,3.8,6.7,2.25.2,2.7,3.9,1.46.7,3.3,5.7,2.16.4,3.2,4.5,1.55.0,3.4,1.6,0.45.5,2.4,3.8,1.15.4,3.9,1.7,0.46.0,2.2,4.0,1.06.3,2.5,5.0,1.97.2,3.2,6.0,1.86.1,2.6,5.6,1.45.8,4.0,1.2,0.26.4,2.8,5.6,2.25.6,2.5,3.9,1.14.9,3.1,1.5,0.15.8,2.6,4.0,1.25.8,2.7,4.1,1.06.7,3.1,4.7,1.54.8,3.4,1.6,0.25.2,4.1,1.5,0.14.9,2.4,3.3,1.05.0,3.5,1.3,0.34.8,3.0,1.4,0.35.5,3.5,1.3,0.25.4,3.4,1.5,0.45.2,3.5,1.5,0.25.0,2.3,3.3,1.05.6,2.8,4.9,2.07.2,3.6,6.1,2.56.0,3.0,4.8,1.85.8,2.7,5.1,1.96.2,3.4,5.4,2.35.6,3.0,4.5,1.56.4,3.1,5.5,1.85.7,2.8,4.1,1.35.4,3.7,1.5,0.25.6,2.9,3.6,1.36.2,2.2,4.5,1.54.9,3.0,1.4,0.25.1,3.8,1.5,0.34.6,3.2,1.4,0.24.6,3.4,1.4,0.35.7,3.8,1.7,0.36.3,2.9,5.6,1.85.0,3.2,1.2,0.25.0,3.5,1.6,0.66.5,3.0,5.5,1.86.2,2.9,4.3,1.35.7,2.6,3.5,1.07.7,2.8,6.7,2.05.5,2.6,4.4,1.26.7,3.0,5.2,2.36.0,2.9,4.5,1.54.6,3.6,1.0,0.25.1,3.5,1.4,0.25.9,3.0,5.1,1.86.1,3.0,4.6,1.47.6,3.0,6.6,2.15.1,3.8,1.9,0.46.0,2.2,5.0,1.55.7,2.5,5.0,2.05.1,3.8,1.6,0.26.7,3.1,5.6,2.46.0,3.4,4.5,1.64.8,3.4,1.9,0.25.7,3.0,4.2,1.25.5,2.3,4.0,1.36.7,2.5,5.8,1.86.8,3.2,5.9,2.36.1,2.8,4.7,1.25.0,3.3,1.4,0.24.6,3.1,1.5,0.25.1,2.5,3.0,1.16.9,3.1,5.1,2.35.9,3.0,4.2,1.55.8,2.7,5.1,1.95.1,3.3,1.7,0.55.0,3.0,1.6,0.25.0,3.4,1.5,0.24.9,2.5,4.5,1.76.3,2.7,4.9,1.85.0,3.6,1.4,0.26.1,2.9,4.7,1.46.4,2.7,5.3,1.97.2,3.0,5.8,1.64.9,3.1,1.5,0.16.4,2.8,5.6,2.15.8,2.8,5.1,2.45.7,4.4,1.5,0.46.3,3.3,6.0,2.57.0,3.2,4.7,1.47.7,2.6,6.9,2.37.7,3.0,6.1,2.36.5,3.0,5.2,2.05.3,3.7,1.5,0.24.5,2.3,1.3,0.34.3,3.0,1.1,0.15.1,3.4,1.5,0.25.6,2.7,4.2,1.36.8,2.8,4.8,1.46.9,3.1,5.4,2.16.3,2.3,4.4,1.35.0,2.0,3.5,1.06.7,3.3,5.7,2.55.5,2.4,3.7,1.07.4,2.8,6.1,1.95.9,3.2,4.8,1.8versicolor,versicolor,virginica,versicolor,setosa,setosa,setosa,versicolor,virginica,versicolor,versicolor,versicolor,setosa,virginica,versicolor,virginica,versicolor,setosa,versicolor,setosa,versicolor,virginica,virginica,virginica,setosa,virginica,versicolor,setosa,versicolor,versicolor,versicolor,setosa,setosa,versicolor,setosa,setosa,setosa,setosa,setosa,versicolor,virginica,virginica,virginica,virginica,virginica,versicolor,virginica,versicolor,setosa,versicolor,versicolor,setosa,setosa,setosa,setosa,setosa,virginica,setosa,setosa,virginica,versicolor,versicolor,virginica,versicolor,virginica,versicolor,setosa,setosa,virginica,versicolor,virginica,setosa,virginica,virginica,setosa,virginica,versicolor,setosa,versicolor,versicolor,virginica,virginica,versicolor,setosa,setosa,versicolor,virginica,versicolor,virginica,setosa,setosa,setosa,virginica,virginica,setosa,versicolor,virginica,virginica,setosa,virginica,virginica,setosa,virginica,versicolor,virginica,virginica,virginica,setosa,setosa,setosa,setosa,versicolor,versicolor,virginica,versicolor,versicolor,virginica,versicolor,virginica,versicolor4.3210.13.60000000000000052.40000000000000045.92.40.6388888888888887,0.3749999999999999,0.6101694915254237,0.5,20.5833333333333334,0.3749999999999999,0.559322033898305,0.5,21,0.7499999999999998,0.9152542372881356,0.7916666666666666,30.4999999999999999,0.3333333333333332,0.5084745762711864,0.5,20.25000000000000006,0.5833333333333333,0.06779661016949151,0.04166666666666667,10.027777777777777922,0.3749999999999999,0.06779661016949151,0.04166666666666667,10.13888888888888887,0.4583333333333333,0.1016949152542373,0.04166666666666667,10.38888888888888895,0.3749999999999999,0.5423728813559322,0.5,20.5555555555555555,0.3333333333333332,0.6949152542372881,0.5833333333333334,30.6388888888888887,0.41666666666666663,0.576271186440678,0.5416666666666666,20.7222222222222222,0.4583333333333333,0.6610169491525424,0.5833333333333334,20.5555555555555555,0.20833333333333331,0.6610169491525424,0.5833333333333334,20.30555555555555564,0.5833333333333333,0.11864406779661016,0.04166666666666667,10.9444444444444444,0.7499999999999998,0.9661016949152542,0.8750000000000001,30.25000000000000006,0.2916666666666667,0.4915254237288135,0.5416666666666666,20.6666666666666666,0.5416666666666665,0.7966101694915254,0.8333333333333334,30.5833333333333334,0.5,0.5932203389830508,0.5833333333333334,20.19444444444444448,0.5833333333333333,0.1016949152542373,0.12500000000000003,10.3333333333333333,0.1666666666666666,0.47457627118644063,0.4166666666666667,20.30555555555555564,0.7916666666666665,0.11864406779661016,0.12500000000000003,10.4722222222222222,0.0833333333333334,0.5084745762711864,0.375,20.5555555555555555,0.20833333333333331,0.6779661016949152,0.75,30.8055555555555556,0.5,0.847457627118644,0.7083333333333334,30.4999999999999999,0.25,0.7796610169491525,0.5416666666666666,30.41666666666666663,0.8333333333333333,0.033898305084745756,0.04166666666666667,10.5833333333333334,0.3333333333333332,0.7796610169491525,0.8750000000000001,30.361111111111111,0.20833333333333331,0.4915254237288135,0.4166666666666667,20.1666666666666668,0.4583333333333333,0.0847457627118644,0,10.41666666666666663,0.25,0.5084745762711864,0.4583333333333333,20.41666666666666663,0.2916666666666667,0.5254237288135593,0.375,20.6666666666666666,0.4583333333333333,0.6271186440677966,0.5833333333333334,20.13888888888888887,0.5833333333333333,0.1016949152542373,0.04166666666666667,10.25000000000000006,0.8749999999999998,0.0847457627118644,0,10.1666666666666668,0.1666666666666666,0.38983050847457623,0.375,20.19444444444444448,0.6249999999999999,0.05084745762711865,0.08333333333333333,10.13888888888888887,0.41666666666666663,0.06779661016949151,0.08333333333333333,10.3333333333333333,0.6249999999999999,0.05084745762711865,0.04166666666666667,10.30555555555555564,0.5833333333333333,0.0847457627118644,0.12500000000000003,10.25000000000000006,0.6249999999999999,0.0847457627118644,0.04166666666666667,10.19444444444444448,0.1249999999999999,0.38983050847457623,0.375,20.361111111111111,0.3333333333333332,0.6610169491525424,0.7916666666666666,30.8055555555555556,0.6666666666666666,0.8644067796610169,1,30.4722222222222222,0.41666666666666663,0.6440677966101694,0.7083333333333334,30.41666666666666663,0.2916666666666667,0.6949152542372881,0.75,30.5277777777777778,0.5833333333333333,0.7457627118644068,0.9166666666666666,30.361111111111111,0.41666666666666663,0.5932203389830508,0.5833333333333334,20.5833333333333334,0.4583333333333333,0.7627118644067796,0.7083333333333334,30.38888888888888895,0.3333333333333332,0.5254237288135593,0.5,20.30555555555555564,0.7083333333333333,0.0847457627118644,0.04166666666666667,10.361111111111111,0.3749999999999999,0.4406779661016949,0.5,20.5277777777777778,0.0833333333333334,0.5932203389830508,0.5833333333333334,20.1666666666666668,0.41666666666666663,0.06779661016949151,0.04166666666666667,10.08333333333333327,0.5,0.06779661016949151,0.04166666666666667,10.08333333333333327,0.5833333333333333,0.06779661016949151,0.08333333333333333,10.38888888888888895,0.7499999999999998,0.11864406779661016,0.08333333333333333,10.5555555555555555,0.3749999999999999,0.7796610169491525,0.7083333333333334,30.19444444444444448,0.5,0.033898305084745756,0.04166666666666667,10.19444444444444448,0.6249999999999999,0.1016949152542373,0.20833333333333334,10.611111111111111,0.41666666666666663,0.7627118644067796,0.7083333333333334,30.5277777777777778,0.3749999999999999,0.559322033898305,0.5,20.38888888888888895,0.25,0.423728813559322,0.375,20.9444444444444444,0.3333333333333332,0.9661016949152542,0.7916666666666666,30.3333333333333333,0.25,0.576271186440678,0.4583333333333333,20.6666666666666666,0.41666666666666663,0.711864406779661,0.9166666666666666,30.4722222222222222,0.3749999999999999,0.5932203389830508,0.5833333333333334,20.08333333333333327,0.6666666666666666,0,0.04166666666666667,10.22222222222222213,0.6249999999999999,0.06779661016949151,0.04166666666666667,10.44444444444444453,0.41666666666666663,0.6949152542372881,0.7083333333333334,30.4999999999999999,0.41666666666666663,0.6101694915254237,0.5416666666666666,20.9166666666666665,0.41666666666666663,0.9491525423728813,0.8333333333333334,30.22222222222222213,0.7499999999999998,0.15254237288135591,0.12500000000000003,10.4722222222222222,0.0833333333333334,0.6779661016949152,0.5833333333333334,30.38888888888888895,0.20833333333333331,0.6779661016949152,0.7916666666666666,30.22222222222222213,0.7499999999999998,0.1016949152542373,0.04166666666666667,10.6666666666666666,0.4583333333333333,0.7796610169491525,0.9583333333333333,30.4722222222222222,0.5833333333333333,0.5932203389830508,0.625,20.13888888888888887,0.5833333333333333,0.15254237288135591,0.04166666666666667,10.38888888888888895,0.41666666666666663,0.5423728813559322,0.4583333333333333,20.3333333333333333,0.1249999999999999,0.5084745762711864,0.5,20.6666666666666666,0.20833333333333331,0.8135593220338982,0.7083333333333334,30.6944444444444443,0.5,0.8305084745762712,0.9166666666666666,30.4999999999999999,0.3333333333333332,0.6271186440677966,0.4583333333333333,20.19444444444444448,0.5416666666666665,0.06779661016949151,0.04166666666666667,10.08333333333333327,0.4583333333333333,0.0847457627118644,0.04166666666666667,10.22222222222222213,0.20833333333333331,0.3389830508474576,0.4166666666666667,20.7222222222222222,0.4583333333333333,0.6949152542372881,0.9166666666666666,30.44444444444444453,0.41666666666666663,0.5423728813559322,0.5833333333333334,20.41666666666666663,0.2916666666666667,0.6949152542372881,0.75,30.22222222222222213,0.5416666666666665,0.11864406779661016,0.16666666666666669,10.19444444444444448,0.41666666666666663,0.1016949152542373,0.04166666666666667,10.19444444444444448,0.5833333333333333,0.0847457627118644,0.04166666666666667,10.1666666666666668,0.20833333333333331,0.5932203389830508,0.6666666666666666,30.5555555555555555,0.2916666666666667,0.6610169491525424,0.7083333333333334,30.19444444444444448,0.6666666666666666,0.06779661016949151,0.04166666666666667,10.4999999999999999,0.3749999999999999,0.6271186440677966,0.5416666666666666,20.5833333333333334,0.2916666666666667,0.7288135593220338,0.75,30.8055555555555556,0.41666666666666663,0.8135593220338982,0.625,30.1666666666666668,0.4583333333333333,0.0847457627118644,0,10.5833333333333334,0.3333333333333332,0.7796610169491525,0.8333333333333334,30.41666666666666663,0.3333333333333332,0.6949152542372881,0.9583333333333333,30.38888888888888895,1,0.0847457627118644,0.12500000000000003,10.5555555555555555,0.5416666666666665,0.847457627118644,1,30.7499999999999999,0.5,0.6271186440677966,0.5416666666666666,20.9444444444444444,0.25,1,0.9166666666666666,30.9444444444444444,0.41666666666666663,0.8644067796610169,0.9166666666666666,30.611111111111111,0.41666666666666663,0.711864406779661,0.7916666666666666,30.27777777777777773,0.7083333333333333,0.0847457627118644,0.04166666666666667,10.055555555555555594,0.1249999999999999,0.05084745762711865,0.08333333333333333,10,0.41666666666666663,0.016949152542372895,0,10.22222222222222213,0.5833333333333333,0.0847457627118644,0.04166666666666667,10.361111111111111,0.2916666666666667,0.5423728813559322,0.5,20.6944444444444443,0.3333333333333332,0.6440677966101694,0.5416666666666666,20.7222222222222222,0.4583333333333333,0.7457627118644068,0.8333333333333334,30.5555555555555555,0.1249999999999999,0.576271186440678,0.5,20.19444444444444448,0,0.423728813559322,0.375,20.6666666666666666,0.5416666666666665,0.7966101694915254,1,30.3333333333333333,0.1666666666666666,0.4576271186440678,0.375,20.8611111111111112,0.3333333333333332,0.8644067796610169,0.75,30.44444444444444453,0.5,0.6440677966101694,0.7083333333333334,2