Skip to content

Instantly share code, notes, and snippets.

@Saurabh7
Created March 18, 2014 06:17
Show Gist options
  • Save Saurabh7/9614499 to your computer and use it in GitHub Desktop.
Save Saurabh7/9614499 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"metadata": {
"name": "multiclass_reduction"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "heading",
"level": 1,
"metadata": {},
"source": "Multiclass Reductions"
},
{
"cell_type": "heading",
"level": 4,
"metadata": {},
"source": "by Chiyuan Zhang and Sören Sonnenburg"
},
{
"cell_type": "markdown",
"metadata": {},
"source": "Since binary classification problems are one of the most thoroughly studied\nproblems in machine learning, it is very appealing to consider reducing\nmulticlass problems to binary ones. Then many advanced learning and\noptimization techniques as well as generalization bound analysis for binary\nclassification can be utilized."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "\n\nIn `SHOGUN`, the strategies of reducing a multiclass problem to binary\nclassification problems are described by an instance of\n`CMulticlassStrategy`. A multiclass strategy describes\n\n* How to train the multiclass machine as a number of binary machines?\n * How many binary machines are needed?\n * For each binary machine, what subset of the training samples are used, and how are they colored? In multiclass problems, we use *coloring* to refer partitioning the classes into two groups: $+1$ and $-1$, or black and white, or any other meaningful names.\n* How to combine the prediction results of binary machines into the final multiclass prediction?\n"
},
{
"cell_type": "markdown",
"metadata": {},
"source": "The user can derive from the virtual class [CMulticlassStrategy](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CMulticlassStrategy.html) to\nimplement a customized multiclass strategy. But usually the built-in strategies\nare enough for general problems. We will describe the built-in *One-vs-Rest*,\n*One-vs-One* and *Error-Correcting Output Codes* strategies in this tutorial.\n\nThe basic routine to use a multiclass machine with reduction to binary problems\nin shogun is to create a generic multiclass machine and then assign a particular\nmulticlass strategy and a base binary machine."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "## One-vs-Rest and One-vs-One\n\nThe *One-vs-Rest* strategy is implemented in\n`CMulticlassOneVsRestStrategy`. As indicated by the name, this\nstrategy reduce a $K$-class problem to $K$ binary sub-problems. For the $k$-th\nproblem, where $k\\in\\{1,\\ldots,K\\}$, the samples from class $k$ are colored as\n$+1$, and the samples from other classes are colored as $-1$. The multiclass\nprediction is given as\n\n$$\nf(x) = \\operatorname*{argmax}_{k\\in\\{1,\\ldots,K\\}}\\; f_k(x)\n$$\n\nwhere $f_k(x)$ is the prediction of the $k$-th binary machines.\n\nThe One-vs-Rest strategy is easy to implement yet produces excellent performance\nin many cases. One interesting paper, [Rifkin, R. M. and Klautau, A. (2004). *In defense of one-vs-all classification*. Journal of Machine\nLearning Research, 5:101\u2013141](http://jmlr.org/papers/v5/rifkin04a.html), it was shown that the\nOne-vs-Rest strategy can be\n\n> as accurate as any other approach, assuming that the underlying binary\nclassifiers are well-tuned regularized classifiers such as support vector\nmachines.\n\nImplemented in [CMulticlassOneVsOneStrategy](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CMulticlassOneVsOneStrategy.html), the \n*One-vs-One* strategy is another simple and intuitive \nstrategy: it basically produces one binary problem for each pair of classes. So there will be $\\binom{K}{2}$ binary problems. At prediction time, the \noutput of every binary classifiers are collected to do voting for the $K$ \nclasses. The class with the highest vote becomes the final prediction.\n\nCompared with the One-vs-Rest strategy, the One-vs-One strategy is usually more\ncostly to train and evaluate because more binary machines are used.\n\nIn the following, we demonstrate how to use `SHOGUN`'s One-vs-Rest and \nOne-vs-One multiclass learning strategy on the USPS dataset. For \ndemonstration, we randomly 200 samples from each class for training and 200 \nsamples from each class for testing.\n\nThe [CLibLinear](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CLibLinear.html) is used as the base binary classifier in a [CLinearMulticlassMachine](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CLinearMulticlassMachine.html), with One-vs-Rest and One-vs-One strategies. The running time and performance (on my machine) is reported below:"
},
{
"cell_type": "raw",
"metadata": {},
"source": "-------------------------------------------------\nStrategy Training Time Test Time Accuracy\n------------- ------------- --------- --------\nOne-vs-Rest 12.68 0.27 92.00%\nOne-vs-One 11.54 1.50 93.90%\n-------------------------------------------------\nTable: Comparison of One-vs-Rest and One-vs-One multiclass reduction strategy on the USPS dataset."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "First we load the data and initialize random splitting:"
},
{
"cell_type": "code",
"collapsed": false,
"input": "import numpy as np\n\nfrom numpy import random\nfrom scipy.io import loadmat\n\nmat = loadmat('../../../data/multiclass/usps.mat')\nXall = mat['data']\n\n#normalize examples to have norm one\nXall = Xall / np.sqrt(sum(Xall**2,0))\nYall = mat['label'].squeeze()\n\n# map from 1..10 to 0..9, since shogun\n# requires multiclass labels to be\n# 0, 1, ..., K-1\nYall = Yall - 1\n\nN_train_per_class = 200\nN_test_per_class = 200\nN_class = 10\n\n# to make the results reproducable\nrandom.seed(0)\n\n# index for subsampling\nindex = np.zeros((N_train_per_class+N_test_per_class, N_class), 'i')\nfor k in range(N_class):\n Ik = (Yall == k).nonzero()[0] # index for samples of class k\n I_subsample = random.permutation(len(Ik))[:N_train_per_class+N_test_per_class]\n index[:, k] = Ik[I_subsample]\n\nidx_train = index[:N_train_per_class, :].reshape(N_train_per_class*N_class)\nidx_test = index[N_train_per_class:, :].reshape(N_test_per_class*N_class)\n\nrandom.shuffle(idx_train)\nrandom.shuffle(idx_test)",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "import SHOGUN components and convert features into SHOGUN format:"
},
{
"cell_type": "code",
"collapsed": false,
"input": "from modshogun import RealFeatures, MulticlassLabels\nfrom modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine\nfrom modshogun import MulticlassOneVsOneStrategy, MulticlassOneVsRestStrategy\nfrom modshogun import MulticlassAccuracy\n\nimport time\n\nfeats_train = RealFeatures(Xall[:, idx_train])\nfeats_test = RealFeatures(Xall[:, idx_test])\n\nlab_train = MulticlassLabels(Yall[idx_train].astype('d'))\nlab_test = MulticlassLabels(Yall[idx_test].astype('d'))",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "define a helper function to train and evaluate multiclass machine given a strategy:"
},
{
"cell_type": "code",
"collapsed": false,
"input": "def evaluate(strategy, C):\n bin_machine = LibLinear()\n bin_machine.set_bias_enabled(True)\n bin_machine.set_C(C, C)\n\n mc_machine = LinearMulticlassMachine(strategy, feats_train, bin_machine, lab_train)\n\n t_begin = time.clock()\n mc_machine.train()\n t_train = time.clock() - t_begin\n\n t_begin = time.clock()\n pred_test = mc_machine.apply_multiclass(feats_test)\n t_test = time.clock() - t_begin\n\n evaluator = MulticlassAccuracy()\n acc = evaluator.evaluate(pred_test, lab_test)\n\n print \"training time: %.4f\" % t_train\n print \"testing time: %.4f\" % t_test\n print \"accuracy: %.4f\" % acc",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "Test on One-vs-Rest and One-vs-One strategies."
},
{
"cell_type": "code",
"collapsed": false,
"input": "print \"\\nOne-vs-Rest\"\nprint \"=\"*60\nevaluate(MulticlassOneVsRestStrategy(), 5.0)\n\nprint \"\\nOne-vs-One\"\nprint \"=\"*60\nevaluate(MulticlassOneVsOneStrategy(), 2.0)",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "LibLinear also has a true multiclass SVM implemenentation - so it is worthwhile to compare training time and accuracy with the above reduction schemes:"
},
{
"cell_type": "code",
"collapsed": false,
"input": "from modshogun import MulticlassLibLinear\nmcsvm = MulticlassLibLinear(5.0, feats_train, lab_train)\nmcsvm.set_use_bias(True)\n\nt_begin = time.clock()\nmcsvm.train(feats_train)\nt_train = time.clock() - t_begin\n\nt_begin = time.clock()\npred_test = mcsvm.apply_multiclass(feats_test)\nt_test = time.clock() - t_begin\n\nevaluator = MulticlassAccuracy()\nacc = evaluator.evaluate(pred_test, lab_test)\n\nprint \"training time: %.4f\" % t_train\nprint \"testing time: %.4f\" % t_test\nprint \"accuracy: %.4f\" % acc",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "As you can see performance of all the three is very much the same though the multiclass svm is a bit faster in training. Usually training time of the true multiclass SVM is much slower than one-vs-rest approach. It should be noted that classification performance of one-vs-one is known to be slightly superior to one-vs-rest since the machines do not have to be properly scaled like in the one-vs-rest approach. However, with larger number of classes one-vs-one quickly becomes prohibitive and so one-vs-rest is the only suitable approach - or other schemes presented below."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "## Error-Correcting Output Codes\n\n*Error-Correcting Output Codes* (ECOC) is a\ngeneralization of the One-vs-Rest and One-vs-One strategies. For example, we\ncan represent the One-vs-Rest strategy with the following $K\\times K$ coding \nmatrix, or a codebook:\n\n$$\n \\begin{bmatrix}\n +1 & -1 & -1 & \\ldots & -1 & -1 \\\\\\\\\n -1 & +1 & -1 & \\ldots & -1 & -1\\\\\\\\\n -1 & -1 & +1 & \\ldots & -1 & -1\\\\\\\\\n \\vdots & \\vdots & \\vdots & \\ddots & \\vdots & \\vdots \\\\\\\\\n -1 & -1 & -1 & \\ldots & +1 & -1 \\\\\\\\\n -1 & -1 & -1 & \\ldots & -1 & +1\n \\end{bmatrix}\n$$\n\nDenote the codebook by $B$, there is one column of the codebook associated with\neach of the $K$ classes. For example, the code for class $1$ is\n$[+1,-1,-1,\\ldots,-1]$. Each row of the codebook corresponds to a binary\ncoloring of all the $K$ classes. For example, in the first row, the class $1$\nis colored as $+1$, while the rest of the classes are all colored as $-1$.\nAssociated with each row, there is a binary classifier trained according to the\ncoloring. For example, the binary classifier associated with the first row is\ntrained by treating all the examples of class $1$ as positive examples, and all\nthe examples of the rest of the classes as negative examples.\n\nIn this special case, there are $K$ rows in the codebook. The number of rows in\nthe codebook is usually called the *code length*. As we can see, this\ncodebook exactly describes how the One-vs-Rest strategy trains the binary\nsub-machines."
},
{
"cell_type": "code",
"collapsed": false,
"input": "OvR=-np.ones((10,10))\nfill_diagonal(OvR, +1)\n\n_=gray()\n_=imshow(OvR, interpolation='nearest')\n_=gca().set_xticks([])\n_=gca().set_yticks([])",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "A further generalization is to allow $0$-values in the codebook. A $0$ for a\nclass $k$ in a row means we ignore (the examples of) class $k$ when training\nthe binary classifiers associated with this row. With this generalization, we\ncan also easily describes the One-vs-One strategy with a $\\binom{K}{2}\\times K$\ncodebook:\n\n$$\n\\begin{bmatrix}\n+1 & -1 & 0 & \\ldots & 0 & 0 \\\\\\\\\n+1 & 0 & -1 & \\ldots & 0 & 0 \\\\\\\\\n\\vdots & \\vdots & \\vdots & \\ddots & \\vdots & 0 \\\\\\\\\n+1 & 0 & 0 & \\ldots & -1 & 0 \\\\\\\\\n0 & +1 & -1 & \\ldots & 0 & 0 \\\\\\\\\n\\vdots & \\vdots & \\vdots & & \\vdots & \\vdots \\\\\\\\\n0 & 0 & 0 & \\ldots & +1 & -1\n\\end{bmatrix}\n$$\n\nHere each of the $\\binom{K}{2}$ rows describes a binary classifier trained with\na pair of classes. The resultant binary classifiers will be identical as those\ndescribed by a One-vs-One strategy.\n\nSince $0$ is allowed in the codebook to ignore some classes, this kind of\ncodebooks are usually called *sparse codebook*, while the codebooks with\nonly $+1$ and $-1$ are usually called *dense codebook*.\n\nIn general case, we can specify any code length and fill the codebook\narbitrarily. However, some rules should be followed:\n\n* Each row must describe a *valid* binary coloring. In other words, both $+1$ and $-1$ should appear at least once in each row. Or else a binary classifier cannot be obtained for this row.\n* It is good to avoid duplicated rows. There is generally no harm to have duplicated rows, but the resultant binary classifiers are completely identical provided the training algorithm for the binary classifiers are deterministic. So this can be a waste of computational resource.\n* Negative rows are also duplicated. Simply inversing the sign of a code row does not produce a \"new\" code row. Because the resultant binary classifier will simply be the negative classifier associated with the original row."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "Though you can certainly generate your own codebook, it is usually easier to\nuse the `SHOGUN` built-in procedures to generate codebook automatically. There\nare various codebook generators (called *encoders*) in `SHOGUN`. However,\nbefore describing those encoders in details, let us notice that a codebook \nonly describes how the sub-machines are trained. But we still need a\nway to specify how the binary classification results of the sub-machines can be\ncombined to get a multiclass classification result.\n\nReview the codebook again: corresponding to each class, there is a column. We\ncall the codebook column the (binary) *code* for that class. For a new\nsample $x$, by applying the binary classifiers associated with each row\nsuccessively, we get a prediction vector of the same length as the\n*code*. Deciding the multiclass label from the prediction vector (called\n*decoding*) can be done by minimizing the *distance* between the\ncodes and the prediction vector. Different *decoders* define different \nchoices of distance functions. For this reason, it is usually good to make the\nmutual distance between codes of different classes large. In this way, even\nthough several binary classifiers make wrong predictions, the distance of\nthe resultant prediction vector to the code of the *true* class is likely\nto be still smaller than the distance to other classes. So correct results can\nstill be obtained even when some of the binary classifiers make mistakes. This\nis the reason for the name *Error-Correcting Output Codes*.\n\nIn `SHOGUN`, encoding schemes are described by subclasses of\n[CECOCEncoder](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CECOCEncoder.html), while decoding schemes are described by subclasses\nof [CECOCDecoder](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CECOCDecoder.html). Theoretically, any combinations of\nencoder-decoder pairs can be used. Here we will introduce several common\nencoder/decoders in shogun."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "* [CECOCRandomDenseEncoder](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CECOCRandomDenseEncoder.html): This encoder generate random dense ($+1$/$-1$) codebooks and choose the one with the largest *minimum mutual distance* among the classes. The recommended code length for this encoder is $10\\log K$. \n* [CECOCRandomSparseEncoder](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CECOCRandomSparseEncoder.html): This is similar to the random dense encoder, except that sparse ($+1$/$-1$/$0$) codebooks are generated. The recommended code length for this encoder is $15\\log K$.\n* [CECOCOVREncoder](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CECOCOVREncoder.html), [CECOCOVOEncoder](http://www.shogun-toolbox.org/doc/en/latest/classshogun_1_1CECOCOVOEncoder.html): These two encoders mimic the One-vs-Rest and One-vs-One strategies respectively. They are implemented mainly for demonstrative purpose. When suitable decoders are used, the results will be equivalent to the corresponding strategies, respectively."
},
{
"cell_type": "markdown",
"metadata": {},
"source": "Using ECOC Strategy in `SHOGUN` is similar to ordinary one-vs-rest or one-vs-one. You need to choose an encoder and a decoder, and then construct a `ECOCStrategy`, as demonstrated below:"
},
{
"cell_type": "code",
"collapsed": false,
"input": "from modshogun import ECOCStrategy, ECOCRandomDenseEncoder, ECOCLLBDecoder\n\nprint \"\\nRandom Dense Encoder + Margin Loss based Decoder\"\nprint \"=\"*60\nevaluate(ECOCStrategy(ECOCRandomDenseEncoder(), ECOCLLBDecoder()), 2.0)",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": "Using a kernel multiclass machine"
},
{
"cell_type": "markdown",
"metadata": {},
"source": "Expanding on the idea of creating a generic multiclass machine and then assigning a particular multiclass strategy and a base binary machine, one can also use the [KernelMulticlassMachine](http://www.shogun-toolbox.org/doc/en/current/classshogun_1_1CKernelMulticlassMachine.html) with a kernel of choice.\n\nHere we will use a [GaussianKernel](http://www.shogun-toolbox.org/doc/en/3.0.0/classshogun_1_1CGaussianKernel.html) with LibSVM as the classifer.\nAll we have to do is define a new helper evaluate function with the features defined as in the above examples."
},
{
"cell_type": "code",
"collapsed": false,
"input": "def evaluate_multiclass_kernel(strategy):\n from modshogun import KernelMulticlassMachine, LibSVM, GaussianKernel\n width=2.1\n epsilon=1e-5\n \n kernel=GaussianKernel(feats_train, feats_train, width)\n \n classifier = LibSVM()\n classifier.set_epsilon(epsilon)\n\n mc_machine = KernelMulticlassMachine(strategy, kernel, classifier, lab_train)\n\n t_begin = time.clock()\n mc_machine.train()\n t_train = time.clock() - t_begin\n\n t_begin = time.clock()\n pred_test = mc_machine.apply_multiclass(feats_test)\n t_test = time.clock() - t_begin\n\n evaluator = MulticlassAccuracy()\n acc = evaluator.evaluate(pred_test, lab_test)\n\n print \"training time: %.4f\" % t_train\n print \"testing time: %.4f\" % t_test\n print \"accuracy: %.4f\" % acc\n\nprint \"\\nOne-vs-Rest\"\nprint \"=\"*60\nevaluate_multiclass_kernel(MulticlassOneVsRestStrategy())\n\n",
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": "So we have seen that we can classify multiclass samples using a base binary machine. If we dwell on this a bit more, we can easily spot the intuition behind this.\n\nThe `MulticlassOneVsRestStrategy` classifies one class against the rest of the classes. This is done for each and every class by training a separate classifier for it.So we will have total $k$ classifiers where $k$ is the number of classes.\n\nJust to see this in action lets create some data using the gaussian mixture model class ([GMM](http://www.shogun-toolbox.org/doc/en/3.0.0/classshogun_1_1CGMM.html)) from which we sample the data points.Four different classes are created and plotted."
},
{
"cell_type": "code",
"collapsed": false,
"input": "from modshogun import *\nfrom numpy import *\n\nnum=1000;\ndist=1.0;\n\ngmm=GMM(4)\ngmm.set_nth_mean(array([-dist*4,-dist]),0)\ngmm.set_nth_mean(array([-dist*4,dist*4]),1)\ngmm.set_nth_mean(array([dist*4,dist*4]),2)\ngmm.set_nth_mean(array([dist*4,-dist]),3)\ngmm.set_nth_cov(array([[1.0,0.0],[0.0,1.0]]),0)\ngmm.set_nth_cov(array([[1.0,0.0],[0.0,1.0]]),1)\ngmm.set_nth_cov(array([[1.0,0.0],[0.0,1.0]]),2)\ngmm.set_nth_cov(array([[1.0,0.0],[0.0,1.0]]),3)\n\ngmm.set_coef(array([1.0,0.0,0.0,0.0]))\nx0=array([gmm.sample() for i in xrange(num)]).T\nx0t=array([gmm.sample() for i in xrange(num)]).T\n\ngmm.set_coef(array([0.0,1.0,0.0,0.0]))\nx1=array([gmm.sample() for i in xrange(num)]).T\nx1t=array([gmm.sample() for i in xrange(num)]).T\n\ngmm.set_coef(array([0.0,0.0,1.0,0.0]))\nx2=array([gmm.sample() for i in xrange(num)]).T\nx2t=array([gmm.sample() for i in xrange(num)]).T\n\ngmm.set_coef(array([0.0,0.0,0.0,1.0]))\nx3=array([gmm.sample() for i in xrange(num)]).T\nx3t=array([gmm.sample() for i in xrange(num)]).T\n\n\ntraindata=concatenate((x0,x1,x2,x3), axis=1)\ntestdata=concatenate((x0t,x1t,x2t,x3t), axis=1)\n\nl0 = array([0.0 for i in xrange(num)])\nl1 = array([1.0 for i in xrange(num)])\nl2 = array([2.0 for i in xrange(num)])\nl3 = array([3.0 for i in xrange(num)])\n\ntrainlab=concatenate((l0,l1,l2,l3))\ntestlab=concatenate((l0,l1,l2,l3))",
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": "_=scatter(traindata[0,:], traindata[1,:], c=trainlab, s=100)",
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAD9CAYAAAClQCyNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nZcAVCoWinqIMuEKhUNRT/h8lBQ56Q81PqQAAAABJRU5ErkJggg==\n"
}
],
"prompt_number": 2
},
{
"cell_type": "markdown",
"metadata": {},
"source": "Now that we have the data ready , lets convert it to shogun format features."
},
{
"cell_type": "code",
"collapsed": false,
"input": "feats_tr=RealFeatures(traindata)\nlabels=MulticlassLabels(trainlab)",
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "markdown",
"metadata": {},
"source": "The [KernelMulticlassMachine](http://www.shogun-toolbox.org/doc/en/current/classshogun_1_1CKernelMulticlassMachine.html) is used with LibSVM as the classifer just as in the above example.\n\nNow we have four different classes, so as explained above we will have four classifiers which in shogun terms are submachines.\n\nWe can see the outputs of two of the four individual submachines (specified by the index) and of the main machine. The plots clearly show how the submachine classify each class as if it is a binary classification problem and this provides the base for the whole multiclass classification."
},
{
"cell_type": "code",
"collapsed": false,
"input": "from modshogun import KernelMulticlassMachine, LibSVM, GaussianKernel\n\nwidth=2.1\nepsilon=1e-5\n \nkernel=GaussianKernel(feats_tr, feats_tr, width)\n \nclassifier=LibSVM()\nclassifier.set_epsilon(epsilon)\n\nmc_machine=KernelMulticlassMachine(MulticlassOneVsRestStrategy(), kernel, classifier, labels)\n\nmc_machine.train()\n\nsize=100\nx1=linspace(-10, 10, size)\nx2=linspace(-10, 10, size)\nx, y=meshgrid(x1, x2)\ngrid=RealFeatures(array((ravel(x), ravel(y)))) #test features\n\nout=mc_machine.apply_multiclass(grid) #main output\nz=out.get_labels().reshape((size, size))\n\nsub_out0=mc_machine.get_submachine_outputs(0) #first submachine\nsub_out1=mc_machine.get_submachine_outputs(1) #second submachine\n\nz0=sub_out0.get_labels().reshape((size, size))\nz1=sub_out1.get_labels().reshape((size, size))\n\nfigure(figsize=(20,5))\nsubplot(131, title=\"Submachine 1\")\nc0=pcolor(x, y, z0)\n_=contour(x, y, z0, linewidths=1, colors='black', hold=True)\n_=colorbar(c0)\n\nsubplot(132, title=\"Submachine 2\")\nc1=pcolor(x, y, z1)\n_=contour(x, y, z1, linewidths=1, colors='black', hold=True)\n_=colorbar(c1)\n\nsubplot(133, title=\"Multiclass output\")\nc2=pcolor(x, y, z)\n_=contour(x, y, z, linewidths=1, colors='black', hold=True)\n_=colorbar(c2)\n",
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAABHEAAAFACAYAAAA79uDuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngu6zagAAAABJRU5ErkJggg==\n"
}
],
"prompt_number": 4
},
{
"cell_type": "markdown",
"metadata": {},
"source": "The `MulticlassOneVsOneStrategy` is a bit different with more number of machines.\nSince it trains a classifer for each pair, we will have a total of $\\frac{k*(k-1)}{2}$ submachines. Let's visualize this in a plot."
},
{
"cell_type": "code",
"collapsed": false,
"input": "C=2.0\n \nbin_machine = LibLinear()\nbin_machine.set_bias_enabled(True)\nbin_machine.set_C(C, C)\n\nmc_machine1 = LinearMulticlassMachine(MulticlassOneVsOneStrategy(), feats_tr, bin_machine, labels)\nmc_machine1.train()\n\nout1=mc_machine1.apply_multiclass(grid) #main output\nz1=out1.get_labels().reshape((size, size))\n\nsub_out10=mc_machine1.get_submachine_outputs(0) #first submachine\nsub_out11=mc_machine1.get_submachine_outputs(1) #second submachine\n\nz10=sub_out10.get_labels().reshape((size, size))\nz11=sub_out11.get_labels().reshape((size, size))\n\nfigure(figsize=(20,5))\nsubplot(131, title=\"Submachine 1\")\nc10=pcolor(x, y, z10)\n_=contour(x, y, z10, linewidths=1, colors='black', hold=True)\n_=colorbar(c10)\n\nsubplot(132, title=\"Submachine 2\")\nc11=pcolor(x, y, z11)\n_=contour(x, y, z11, linewidths=1, colors='black', hold=True)\n_=colorbar(c11)\n\nsubplot(133, title=\"Multiclass output\")\nc12=pcolor(x, y, z1)\n_=contour(x, y, z1, linewidths=1, colors='black', hold=True)\n_=colorbar(c12) \n",
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAABHEAAAFACAYAAAA79uDuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xl8VPW9//HXQIKsIggECFFEUHZIi1IXKuiNuCJuFSsW\nkeJyayu1vVd/ttpo1WKX60VtLdYNpKLee61YK6lrtGpLWsUNqYAaCWtFdhGBkN8fk0QiYZJMZnLO\nnLyej8fInJkz53wmyPc9+c73fL+xioqKCiRJkiRJkhRqLYIuQJIkSZIkSXWzE0eSJEmSJCkD2Ikj\nSZIkSZKUAezEkSRJkiRJygB24kiSJEmSJGUAO3EkSZIkSZIygJ042qfRo0dz7733BlrDAw88wKhR\no/b5/CmnnMKDDz7YhBVJkqqYE5IkgBYtWvDBBx/s8/nBgwfz0ksvNfo4kuzEibyXX36Zo48+mgMO\nOIADDzyQY489ln/84x/1em0sFiMWi6W5wsZ56qmnuPDCC1N+3HfeeYexY8fStWtXWrTwn4mk6DIn\nkjNr1ixGjBhBx44dycvL4+qrr6a8vDzl55GkdOrduzf77bcfn3zySY3H8/PzadGiBcuXL2/wMS+6\n6CKuu+66Go+98847fP3rX29UrWFS23sM0/EUbf52GmGbN2/mtNNO48orr2TDhg2sXLmSn/zkJ+y3\n335BlxZ6rVq1YsKECYF/wyxJ6WROJO+zzz5jxowZfPLJJyxYsIDnnnuOX/7yl0GXJUkNEovF6NOn\nD3Pnzq1+7O233+azzz4LfSe91FzZiRNhS5YsIRaLcd555xGLxWjdujUFBQUMGTIEgMLCwhrfTpaW\nltKiRQt2795d/diyZcsYOXIkHTt2ZPz48WzYsKHGvg888AAHHXQQBx54IL/97W/5+9//ztChQ+nU\nqRPf/e53q4/z/vvvc/zxx9OlSxe6du3KxIkT2bRpU/XzZWVlnHXWWXTr1o0uXbrUeC3Af/zHf9C5\nc2f69OlDUVFR9eN7DuV/4IEHOPbYY/e576ZNm5gyZQo9e/akV69eXHfddTXe654OO+wwJk+ezMCB\nAxv8c5ekTGFOJJ8Tl112GccccwxZWVn07NmTCy64gFdeeaXBfweSFLSJEycye/bs6u1Zs2bxrW99\ni4qKiurHvnz57L4uZb377rt56KGH+PnPf06HDh0444wzgPiIn+eeew6A8vJybrnlFvr27cv+++/P\niBEjWLly5V7H+tOf/kR+fj4dO3bkoIMO4oYbbqh+bvv27UycOJEuXbrQqVMnjjzySP71r39V13bo\noYey//7706dPHx566KFa3/fnn3/OtGnTyM3NJTc3l+9///vs2LFjn++vRYsWvP/++wnf4/Tp0xk0\naBCdO3fm4osv5vPPP0/6eNK+2IkTYYcffjgtW7bkoosuoqioqPqDdZW6etcrKiqYPXs2999/P6tX\nryYrK4vvfe97NfYpKSlh2bJlPPzww1x55ZXccsstPP/88yxatIhHH320xrWvP/rRj1i9ejWLFy+m\nrKyMwsJCIN6Qn3baaRxyyCF89NFHrFy5kvPPP7/6dQsWLKB///588skn/Od//idTpkyp8R72fB8l\nJSX73Peiiy6iVatWvP/++yxcuJCnn36ae+65p/4/UEmKGHMidTnx4osvMnjw4HrtK0lh8rWvfY3N\nmzfzz3/+k/Lych555BEmTpxYY5/6Xj57ySWXcMEFF3D11VezZcsW5s2bt9fr/+u//ouHH36Y+fPn\ns3nzZu677z7atGmz17Hat2/PnDlz2LRpE3/605+46667qo83a9YsNm/ezIoVK1i/fj0zZ86kTZs2\nfPrpp1x55ZUUFRWxefNm/vrXvzJ8+PBaa7355pspKSnhzTff5M0336SkpISbbrop4fuLxWL7fI8A\nDz30EE8//TTvv/8+S5YsafTxpNrYiRNhHTp04OWXXyYWizF16lS6devGGWecUd1LvWfvem1isRjf\n+ta3GDhwIG3btuWnP/0pjz76aI3XXXfddbRq1YqCggI6dOjAN7/5Tbp06ULPnj0ZNWoUCxcuBODQ\nQw/lhBNOIDs7my5duvD973+fF198EYh/oF69ejW/+MUvaNOmDfvttx9HH3109TkOPvhgpkyZUl3P\n6tWrq9/Dl+1r37Vr1zJ//nxuu+022rRpQ9euXZk2bRoPP/xwo37GkpTJzInU5MR9993H66+/zg9/\n+MM695WkMLrwwguZPXs2zzzzDAMHDiQ3N7dRx0uUH/fccw8333wz/fr1A2Do0KF07tx5r/2OO+44\nBg0aBMCQIUOYMGFCdS60atWKTz75hKVLlxKLxcjPz6dDhw5AfIRL1SVhOTk5+xxZ/9BDD3H99dfT\npUsXunTpwk9+8pMGTYT/5fcYi8W44ooryM3NpVOnTvzoRz+qcZlaQ48n7YudOBHXv39/7r//fsrK\nynjnnXdYtWoV06ZNq/fr8/Lyqu8fdNBB7Ny5k3Xr1lU/lpOTU32/TZs2e21v3boVgLVr1zJhwgR6\n9epFx44dufDCC6snUCsrK+Pggw/e5wTC3bt3r77ftm1bgOrj1nffjz76iJ07d9KjRw86depEp06d\nuOyyy/j444/r94OQpIgyJxqXE48//jjXXnst8+fPr/WXEEkKu1gsxoUXXsjvf//7Wi+lSrUVK1Zw\n6KGH1rnfggULGDNmDN26deOAAw5g5syZ1blw4YUXMnbsWCZMmEBubi5XX301u3btol27djzyyCP8\n9re/pWfPnpx22mm89957tR5/1apVHHzwwdXbBx10EKtWrWrUe/tyJjb2eFJt7MRpRg4//HAmTZrE\nO++8A0C7du3Ytm1b9fNr1qzZ6zV7zki/fPny6m9I66tq2OS1115Ly5Yteeedd9i0aRMPPvhg9TwD\neXl5LF++PK2reuTl5VXPvL9hwwY2bNjApk2bePvtt9N2TknKNOZEw3KiqKiISy65hCeffLL622JJ\nykQHHXQQffr0Yf78+Zx11ll7Pd+uXTs+/fTT6u3a8qBKXZdd5eXlsWzZsjpr+uY3v8n48eNZsWIF\nGzdu5LLLLqvOhaysLK6//noWLVrEq6++ypNPPlk9r8+JJ57I008/zZo1a+jfvz9Tp06t9fg9e/ak\ntLS0env58uX07Nmz+v0myr99vccvZ2JjjyfVxk6cCHvvvff4r//6r+qJwsrKypg7dy5HHXUUAMOH\nD+ell16irKyMTZs28bOf/azG6ysqKpgzZw6LFy9m27ZtXH/99Zx77rn1bmT27MHfunUr7dq1Y//9\n92flypX84he/qH7uyCOPpEePHlxzzTVs27aN7du38+qrrzb27dfQo0cPTjzxRK666iq2bNnC7t27\nef/992vMxfBl27dvr57c7PPPP6+emEySosKc+EJDc+L555/nggsu4LHHHmPEiBEprUWSgnDvvffy\n/PPP1zo/zfDhw3nsscf47LPPWLZsWcIVXHNycvjggw/2+fy3v/1trrvuOpYtW0ZFRQVvvfUW69ev\n32u/rVu30qlTJ1q1akVJSQkPPfRQdb4UFxfz9ttvU15eTocOHcjOzqZly5b861//Yt68eXz66adk\nZ2fTrl07WrZsWWsd559/PjfddBPr1q1j3bp13HjjjdWT+Q8bNoxFixbx5ptvsn379uo52hK9x4qK\nCn7zm9+wcuVK1q9fz80338yECROSPp60L3biRFiHDh1YsGABI0eOpH379hx11FEMHTqUX/3qVwAU\nFBRw3nnnMXToUI444ghOP/30Gh+8q+YLuOiii+jRowc7duzg9ttvr/F8Ins+/5Of/ITXX3+djh07\ncvrpp3P22WdXP9+yZUv++Mc/smzZMg466CDy8vJ49NFHq4/x5fPs67x17Tt79mx27NjBwIED6dy5\nM+eee+4+v0UoLS2lbdu2DB48mFgsRps2bRgwYEDC9ytJmcacSD4nbrrpJrZs2cLJJ59Mhw4d6NCh\nA6eeemrC9ytJYdanTx++8pWvVG/v2T5+//vfp1WrVuTk5DB58mQmTpy4Vx5UmTJlCu+++y6dOnWq\ndVTPVVddxTe+8Q1OPPFEOnbsyNSpU9m+fftex/nNb37D9ddfz/77789Pf/pTzjvvvOrn1qxZw7nn\nnkvHjh0ZOHAgo0eP5sILL2T37t3cdttt5ObmcuCBB/KXv/yFu+66q9b3++Mf/5gRI0YwdOhQhg4d\nyogRI/jxj38MxFeqvf766/m3f/s3Dj/8cEaNGlXne4zFYnzzm9/kxBNP5NBDD6Vfv36NOp60L7EK\nZ1CSJEmSJClphxxyCPfeey/HH3980KUo4ho9Eufiiy8mJyeHIUOGVD+2fv16CgoKOOywwzjxxBPZ\nuHFjY08jSU2qtrbty773ve/Rr18/hg0bVr3CjmoyIyRFlTmRGuaEpKjavn07I0eOZPjw4QwcOJD/\n9//+X637NTQrGt2JM3nyZIqKimo8Nn36dAoKCliyZAknnHAC06dPb+xpJKlJ1da27empp55i2bJl\nLF26lLvvvpvLL7+8CavLHGaEpKgyJ1LDnJAUVa1bt+aFF17gjTfe4K233uKFF17g5ZdfrrFPMlnR\n6E6cUaNG0alTpxqPPfHEE0yaNAmASZMm8fjjjzf2NJLUpGpr2/a0Zzs3cuRINm7cyNq1a5uqvIxh\nRkiKKnMiNcwJRcWHH37opVTaS9u2bQHYsWMH5eXldO7cucbzyWRFWiY2Xrt2LTk5OUB8pm0DS1LU\nrFy5kry8vOrtXr16sWLFigAryhxmhKTmwJxInjkhKSp2797N8OHDycnJYcyYMQwcOLDG88lkRVZa\nKt1DbStBVD0uSbVpzHzrbWMxPkvide3bt2fLli0Nes2X67Rda7h9ZUTVc5JUG3Oi+TAnJCUjLDnR\nokUL3njjDTZt2sTYsWMpLi5m9OjRCWutq21LSydOTk4Oa9asoXv37qxevZpu3brtY8/CdJw+wxQD\nowOuIQyK8edQjD8DaGy78BlwUxKv+/HWrQ3aPzc3l7KysurtFStWkJubm8SZm5/6Z4QpAXu3DPOB\nBZX3WwLl/BBo37RFBaIY28hi/BmAORF9DckJFrnQLr8uhO8UBl1F8Pb8OdxzKyx4HnodQsV/zwyy\nqiZV+Cso/EHQVQQv1rNxr09HTnTs2JFTTz2Vf/zjHzU6cZLJirRcTjVu3DhmzZoFwKxZsxg/fnw6\nTiNJtcpO4tZQ48aNY/bs2QD87W9/44ADDqge+q3EzIjGORkYVHm/HIDZgdUiZSpzItzMCUlBS0VO\nrFu3rnp1vc8++4xnnnmG/Pz8GvskkxWNHolz/vnn8+KLL7Ju3Try8vK48cYbueaaa/jGN77Bvffe\nS+/evXn00UcbexpJalJfbttuuOEGdu7cCcCll17KKaecwlNPPUXfvn1p164d999/f8AVh5MZkR5H\nA+8C8e+ftwVai9RcmROpYU5IiqrVq1czadIkdu/eze7du7nwwgs54YQTmDkzPjos2ayIVTTmYrFG\niF/nVRjEqUOmFOgdcA1hUIo/h1L8GQAUNuoa1lgsxq+SeN0PaNy1s0q9WCxmSlB7y7ASuIeqTpz2\nwA+bsqSAlGIbWYo/AzAnVCUWi3k5FUBJMRw5Ougqgrfnz6GZXk5V/CqMPjroKoIX69m49jrsOZH2\niY1Vl95BFxASvYMuIAR6B11AZCQz7F0Kq961PNaGqg4cgK3ER+O0bZqCAtM76AJCoHfQBUSGOaFI\nsQMnzp+DHTgpFOacsBNHUuTYsCnqOgPHAS8CMWAaP6cjUOjYJalezAlJUiJhzokw1yZJSQlzz7mU\nKmOIr55QAtwBTAu2HCmjmBOSpETCnBN24kiKHBs2NRenEJ8fZyXwWsC1SJnEnJAibNN6eGIWfP45\nHHtS0NUoQ4U5J8JcmyQlJcw951KqdSLeibM76EKkDGJOSBH16RaYOpa8zxYzdjTcfeVVQVekDBXm\nnLATR1Lk2LCpOSoHYBf+C5Dq5r8SKYLKy+E742DDxxw9An57K8RiQRelTBXmnAhzbZKUlDD3nEup\ndhjwDvAyADcDVwAHBliRFH7mhBRB/1oJy96B7duYfTu0bBl0QcpkYc4JO3EkRU6YG10p1YYCnxBf\nqQoqaMEd7Ob7QMcgy5JCzZyQIip7P9i5g1atgi5EmS7MOWEnjqTIsWFTczMG2Ab8naq5cX4NXA34\nNaRUG3NCkpRImHMizLVJUlLC3HMupcupwOtUzY2zg/gC5O0DrEgKL3NCkpRImHOiRdAFSJKk1HD+\nRkmSpGhzJI6kyLFhk0YCbYIuQgotc0KSlEiYcyLMtUlSUsI8/FFKpxOAPwMxFnAFCzgQKKQw2KKk\nEDInJEmJhDkn7MSRFDk2bGqujiI+wfFfgN8AVwZbjhRa5oQkKZEw50SYa5OkpIS551xKtxOAzcCb\nwO8DrkUKK3NCkpRImHPCThxJkWPDpuYun3gnzudBFyKFlDkhSUokzDkR5tokKSlh7jmXmtJGAO4D\nLg62EClkzAlJUiJhzgk7cSRFjg2bmrv2NbaWA2uA7oHUIoWROSFJSiTMORHm2iQpKWHuOZeaQheg\nAHim+pHf8j3gdleqkgBzQpKUWJhzokXQBUhSqmUncatNUVER/fv3p1+/ftx66617Pb9u3TpOOukk\nhg8fzuDBg3nggQdS/l6kZB0DHLvH9q8B2BpILVLYmBOSpERSkRNlZWWMGTOGQYMGMXjwYG6//fa9\n9vnlL39Jfn4++fn5DBkyhKysLDZu3JiwtlhFRUVFI95b0mKxGPiNoKS9FNKYZikWi7Emidd1hxrn\nLS8v5/DDD+fZZ58lNzeXI444grlz5zJgwIAvKi0s5PPPP+dnP/sZ69at4/DDD2ft2rVkZTnIMRVi\nsZgpkQJ3A6uqt04GRgZWi5Qa5oTiYrEYLArkVxmF0erl8M2jYdsWKpZsDroaBSjWk1DkxJo1a1iz\nZg3Dhw9n69atfPWrX+Xxxx+vkRN7evLJJ/nv//5vnn322YTncSSOpMjJzmr47ctKSkro27cvvXv3\nJjs7mwkTJjBv3rwa+/To0YPNm+MfEjZv3syBBx7oB3OFTrvKP78CwNDgCpFCxJyQJCWSipzo3r07\nw4cPB6B9+/YMGDCAVatW7b1jpYceeojzzz+/ztrsxJGkWqxcuZK8vLzq7V69erFy5coa+0ydOpVF\nixbRs2dPhg0bxowZM5q6TKneOgHQJuAqpOgwJyRJ9VVaWsrChQsZObL2EdHbtm3jz3/+M2effXad\nx/KrAEmRU58vOf+yG17eve/n45d8JnbLLbcwfPhwiouLef/99ykoKODNN9+kQ4cODahWSq9hwFLg\nOeAyCukOFHqhmpo5c0KSlEgqcqLK1q1bOeecc5gxYwbt27evdZ8//vGPHHvssRxwwAF111b3KSUp\ns2S3rHuf41vC8XtsT99V8/nc3FzKysqqt8vKyujVq1eNfV599VV+9KMfAXDooYdyyCGH8N577zFi\nxIhkS5dSbjCwEXgWmAl8N9hypFAwJyRJiaQiJwB27tzJ2WefzcSJExk/fvw+j/Xwww/X61Iq8HIq\nSRGUldXw25eNGDGCpUuXUlpayo4dO3jkkUcYN25cjX369+9fPfHY2rVree+99+jTp09TvEWpQY4l\nvlpVBXAXAPX42kiKMHNCkpRIKnKioqKCKVOmMHDgQKZNm7bPc23atImXXnqJM844o361JfumJCms\naptYrKGysrK48847GTt2LOXl5UyZMoUBAwYwc+ZMAC699FKuvfZaJk+ezLBhw9i9ezc///nP6dy5\nc+NPLqVBAfAqsBOAm4BrgFYBViQFx5yQJCWSipx45ZVXmDNnDkOHDiU/Px+IX2a7fPlyIJ4TAI8/\n/jhjx46lTZv6zV3oEuOSQqbxS8dWdEvidf9q3FKESj2XGE+9G4iPxom7FjtxlJnMCcW5xLhqcIlx\nVUrFEuNhzglH4kiKHls2qVYtgPLqrVVA76BKkYJlTkiSEglxTjgnjqToyUriJjUDJ9fYeoDLHeuk\n5sqckCQlEuKcMJIkRY8tm1SrEcB24itVAfwWgE+BdgFVJAXEnJAkJRLinAhxaZKUpHosCSg1V8cC\nG4DXgA7AZtoGW5AUBHNCkpRIiHPCThxJ0WPLJiV0OPFOnNbAZmIBVyMFwJyQJCUS4pwIcWmSlCRb\nNklSIuaEJCmREOeEExtLktTMHFD5578AKAuuEEmSJDVIiPuXJClJIb6GVQqDbsBpwJMA3MtllY/d\n6GpVai7MCUlSIiHOCTtxJEWPLZtUpxHAZ8BzxFepiv+z2UJ8umMp4swJSVIiIc6JEJcmSUmyZZPq\nZRTwLrAa2AXAB8CwACuSmog5IUlKJMQ5EeLSJClJIR7+KIVNq6ALkIJgTkiSEglxTtiJIyl6bNmk\nJH0adAFS0zAnpOjZthUqdgddhaIixDkR4tIkKUm2bFK9fQ34qHrraabyNL9zgmNFnTkhRcumDQz6\nz0Fszobzzgm6GEVCiHMixKVJUpJs2aR6GwCcCvypcntlgLVITcackKJj21a49CS2bIGCr8PPfxx0\nQYqEEOdEiEuTpCSF+BpWKYyOIL5S1fPA0wBUALEAK5LSzJyQouPGy+HTLYzMh7t/ATHjS6kQ4pyw\nE0dS9NiySQ32deKdOLuCLkRqCuaEFB0rPoAOHbnoPGgZ4l+8lWFCnBMhLk2SkmTLJklKxJyQJCUS\n4pwIcWmSlCS/hZGS0gKIr+vxAXBooLVIaWVOSJISCXFOtAi6AEmSFA7jq+89SAcKmeoqVZIkSaFi\nJ46k6MlK4laLoqIi+vfvT79+/bj11ltr3ae4uJj8/HwGDx7M6NGjU/s+pCY2FDil8v4W4HcA/Cuo\ncqT0MSckSYmkICfKysoYM2YMgwYNYvDgwdx+++37PN3f//53srKyeOyxx+pVmiRFSwpatvLycq64\n4gqeffZZcnNzOeKIIxg3bhwDBgyo3mfjxo185zvf4c9//jO9evVi3bp1jT+xFLAjgXVASfUjTwEX\nBVSNlCbmhCQpkRTkRHZ2NrfddhvDhw9n69atfPWrX6WgoKBGTkA8T66++mpOOukkKioq6jyuI3Ek\nRU/LJG5fUlJSQt++fenduzfZ2dlMmDCBefPm1djnoYce4uyzz6ZXr14AdOnSJV3vSGpSB9XYKg+o\nCimNzAlJUiIpyInu3bszfPhwANq3b8+AAQNYtWrVXvvdcccdnHPOOXTt2rVepdmJIyl6UjD8ceXK\nleTl5VVv9+rVi5UrV9bYZ+nSpaxfv54xY8YwYsQIHnzwwXS8Gylgu4MuQEo9c0KSlEiKLrutUlpa\nysKFCxk5cmSNx1euXMm8efO4/PLLAYjFYvUqTZKipR4tW/Gq+G1f6tOA7ty5k9dff53nnnuObdu2\ncdRRR/G1r32Nfv36NaBYKXxqfg+0BagA6v43IWUMc0KSlEgKcqLK1q1bOeecc5gxYwbt27ev8dy0\nadOYPn06sViMioqKel1OZSeOpOipR8s2+qD4rcoN/6j5fG5uLmVlZdXbZWVl1cPhq+Tl5dGlSxfa\ntGlDmzZt+PrXv86bb77ph3NlvBzgTOAPAGxmKjeQCxS6WpWiwpyQJCWSgpyAeGf+2WefzcSJExk/\nfvxez7/22mtMmDABgHXr1jF//nyys7MZN27cPs/r5VSSoicF17COGDGCpUuXUlpayo4dO3jkkUf2\nakzPOOMMXn75ZcrLy9m2bRsLFixg4MCBaXxjUtMZBpxcef8eYHOAtUgpZ05IkhJJQU5UVFQwZcoU\nBg4cyLRp02o9zQcffMCHH37Ihx9+yDnnnMNdd92VsAMHHIkjKYpS0LJlZWVx5513MnbsWMrLy5ky\nZQoDBgxg5syZAFx66aX079+fk046iaFDh9KiRQumTp3qh3NFykjgNeKLjNdjtLCUOcwJSVIiKciJ\nV155hTlz5jB06FDy8/MBuOWWW1i+fDkQz4lkxCrqc9FVGsSvIy4M4tSSQq2wXteC7kssFqPi6iRe\ndyuNOq9SLxaLmRIhMBNYDUwAHvZvRKFgTiguFovBIv9Omr2Jx8Du3fzph3/jlBOCLkZhEOvZuPY6\n7DnhSBxJ0VPLcEZJyamaujV+mfcyoG9gtUgpY05IkhIJcU44J46k6EnxkoBScza68s9lAMzhIkfj\nKArMCUlSIiHOCTtxJEnSPh1GfKWqKg8AzpAjSZIUDL9XkBQ9tmxSSg0DtgF/rn7kfuBHQZUjNZ45\nIUlKJMQ5EeLSJClJtmxSyh3Bnp04O4MrREoFc0KSlEiIcyKtpfXu3Zv999+fli1bkp2dTUlJSTpP\nJ0lxIZ6ITDWZE5mqfdAFSI1jTmQMc0JSIEKcE2ntxInFYhQXF9O5c+d0nkaSagpxz7lqMicyR4vK\n224ATgu0FqnRzImMYU5ICkSIcyLtpTXFOumSVEOIG13tzZzIDC2AbwAPA/AwFwG9gUJXq1ImMicy\nijkhqcmFOCfSujpVLBbj3/7t3xgxYgS/+93v0nkqSfpCyyRuCoQ5kVn6A+Mr7z+Aa1Qpg5kTGcOc\nkBSIEOdEWvuXXnnlFXr06MHHH39MQUEB/fv3Z9SoUXvsUbzH/d6VN0nNS2nlLYVC3HOumurKieI9\n9u2NKREGw4l33pQAzwdci5qLUsyJ5qvO3yd+XfjF/SNGw5Gjm7hCSUErfhWK/5rig4Y4J9JaWo8e\nPQDo2rUrZ555JiUlJV/qxBmdztNLygi9qfmreXHjDxniRlc11ZUTowOqS4l1q/zzEyD+y3XvgCpR\n89Abc6L5qvP3ie8UBlOYpNAYfXT8VuWGX6XgoCHOibRdTrVt2za2bNkCwKeffsrTTz/NkCFD0nU6\nSfpCiIc/6gvmRObbAMALAVchJcGcyAjmhKTAhDgn0ta/tHbtWs4880wAdu3axQUXXMCJJ56YrtNJ\n0hdC3HOuL5gTmesgIAbEpxr9CHgPODzAiqQGMicygjkhKTAhzom0lXbIIYfwxhtvpOvwkrRvIW50\n9QVzInN1A86jaqUqgLlMBu53pSplCnMiI5gTkgIT4pwIcWmSlCRbNintqlaqerxy+34ANgP7B1SR\n1ADmhCQiPO5zAAAgAElEQVQpkRDnRFqXGJckSdE1HOhceb8tAJ8FVoskSVJzEOL+JUlKkhNQSk0m\nVvnn2cCD5ARZilR/5oQkKZEQ54SdOJKix5ZNajJVQ3r/FWgVUgOZE1I0fL4d1q2FFi3J8t+1UinE\n/z+FuDRJSpItm9RkTgZmA38GzqeQw4FCJzhW2JkTUubbuRN+cB4HV7zPgD4w+qigC1KkhDgnnBNH\nUvS0TOJWi6KiIvr370+/fv249dZb93m6v//972RlZfHYY4+l8E1ImaEP8I3K+3OJLzguhZ45IWW2\n3bvhRxfBP9/goFz4v3ugVaugi1KkpCAnysrKGDNmDIMGDWLw4MHcfvvte+3zz3/+k6OOOorWrVvz\nq1/9ql6lhbh/SZKSlIKWrby8nCuuuIJnn32W3NxcjjjiCMaNG8eAAQP22u/qq6/mpJNOoqKiovEn\nljLQQOA04Enio3Li43LGBliRVAdzQspsf3oI3v47tGnHk7OhbZugC1LkpCAnsrOzue222xg+fDhb\nt27lq1/9KgUFBTVy4sADD+SOO+7g8ccfT3CkmhyJIyl6spK4fUlJSQl9+/ald+/eZGdnM2HCBObN\nm7fXfnfccQfnnHMOXbt2TdObkTLDIOKTHJcDsCDQWqQ6mRNSZtuyEXoeDIO+yv4dgi5GkZSCnOje\nvTvDhw8HoH379gwYMIBVq1bV2Kdr166MGDGC7OzsepdmJ46k6EnB8MeVK1eSl5dXvd2rVy9Wrly5\n1z7z5s3j8ssvByAWiyFJygDmhCQpkRRddlultLSUhQsXMnLkyEaX5uVUkqKnHi1b8evx277U54P2\ntGnTmD59OrFYjIqKCofJq1nLJj4SJ/6vYDfwNjAkwIqkBMwJSVIiKciJKlu3buWcc85hxowZtG/f\nvilKk6QMU4+WbfSR8VuVG+6p+Xxubi5lZWXV22VlZfTq1avGPq+99hoTJkwAYN26dcyfP5/s7GzG\njRuXdOlSpsoCJlI1Jw7A/zGR/2OOK1UpjMwJSVIiKcgJgJ07d3L22WczceJExo8f31SlSVKGSUHL\nNmLECJYuXUppaSk9e/bkkUceYe7cuTX2+eCDD6rvT548mdNPP90P5mrW+gDnAv9TuR2foq+C+Bgd\nKUTMCUlSIinIiYqKCqZMmcLAgQOZNm1anfvWl504kqKnjmtS6yMrK4s777yTsWPHUl5ezpQpUxgw\nYAAzZ84E4NJLL238SaQIGkR8mfESIA9YbAeOwsickCQlkoKceOWVV5gzZw5Dhw4lPz8fgFtuuYXl\ny5cD8ZxYs2YNRxxxBJs3b6ZFixbMmDGDd999N+FlV7GKgC7OjV9HXBjEqSWFWmGj5gyIxWJUvJ3E\n64Y0rAdc6ReLxUyJDPUy8CzQH/inf4tKOXNCcbFYDBb5d9IsPXQnPDcPunanYuacoKtRyMR6Nq69\nDntOOBJHUvTYskmhsCvoAqR9MSckSYmEOCdCXJokJcmWTQrUYcBzwDLgbAqr16gqdFSOwsKckCQl\nEuKcCHFpkpSkFFzDKil53YivVPUg8H9AGfG5cqTQMCckSYmEOCfsxJEUPbZsUuAO5YuVqkoqb7AF\n6BBcUVIVc0KSlEiIcyLEpUlSkmzZpFAYBPwZ2Fz9yEbsxFEomBOSpERCnBMhLk2SkmTLJoWGC4wr\nlMwJSVIiIc6JEJcmScmpCPE1rFJzU/OfYymQF0gd0p7MCUlSImHOiRZBFyBJqVae1fCbpPQ4kz1H\n4zzHFa5QpRAwJyRJiYQ5J4wkSZHjh20pPPKAC4A5ldsbAqxFqmJOSJISCXNOhLg0SUrOrpbJDDLc\nnfI6JMX1Bc4A5gH/G3AtEpgTkqTEwpwTduJIipzyrGSath0pr0PSF/oQv6yqPOhCJMwJSVJiYc4J\n58SRJEmSJEnKAI7EkRQ55S1DPJ281Ey1IT4SZxcAC4CBQIcAK1JzZk5IkhIJc07YiSMpcsoJb6Mr\nNVetgIuA+4EK5gPz+QbwqKtVKQDmhCQpkTDnhJ04kiJnV4gbXak5O4iaK1U9CsDyymekpmNOSJIS\nCXNO2IkjKXLKbdqk0OoLfBV4rfqR17ETR03NnJAkJRLmnAhvZZKUpDAPf5QErYMuQM2eOSFJSiTM\nOWEnjqTICXOjK+nLtgVdgJohc0KSlEiYc8JOHEmRE+ZGVxIMB14FKoCjWMLYysmNC53kWE3EnJAk\nJRLmnGgRdAGSlGq7aNngW22Kioro378//fr149Zbb93r+d///vcMGzaMoUOHcswxx/DWW2+l+61J\nkdCV+EpVMeCvwLuBVqPmyJyQJCWSipy4+OKLycnJYciQIbWeY926dZx00kkMHz6cwYMH88ADD9Sr\nNjtxJEVOOVkNvu11jPJyrrjiCoqKinj33XeZO3cuixcvrrFPnz59eOmll3jrrbe47rrruOSSS5rq\nLUoZ72Dgm5X3HwW2BFiLmh9zQpKUSCpyYvLkyRQVFe3zHHfeeSf5+fm88cYbFBcX84Mf/IBdu3bV\nWZudOJIip5yWDb59WUlJCX379qV3795kZ2czYcIE5s2bV2Ofo446io4dOwIwcuRIVqxY0STvT4qK\nfkDbyvufBlmImh1zQpKUSCpyYtSoUXTq1Gmf5+jRowebN28GYPPmzRx44IFkZdU9441z4kiKnPpc\nw/qP4k95rXjfE6quXLmSvLy86u1evXqxYMGCfe5/7733csoppzSsUElSIMwJSVIiqciJukydOpXj\njz+enj17smXLFh599NF6vc5OHEnN0ojR7Rgxul319swb1tV4PhaL1ftYL7zwAvfddx+vvPJKyuqT\nmovsyj/vAeBvwNcCq0XakzkhSUqkrpyoyy233MLw4cMpLi7m/fffp6CggDfffJMOHTokfJ2XU0mK\nnFRMRJabm0tZWVn1dllZGb169dprv7feeoupU6fyxBNPJBwuKal2E4hPcBy/AryIM1yhSk3AnJAk\nJZKqCfATefXVVzn33HMBOPTQQznkkEN477336nydI3EkRU5tE4s11IgRI1i6dCmlpaX07NmTRx55\nhLlz59bYZ/ny5Zx11lnMmTOHvn37NvqcUnPUg/hKVfdXbsdnFFkMDAimIDUL5oQk1fTRCvhse9BV\nNN5+rVJznFTkRF369+/Ps88+yzHHHMPatWt577336NOnT52vsxOnUSqAh4GqSepOo/YPnfcBn9Ty\nuPu7v/unQ32uYa1LVlYWd955J2PHjqW8vJwpU6YwYMAAZs6cCcCll17KjTfeyIYNG7j88ssByM7O\npqSkpNHnlpqbg4EzgT9UP/JH7MRROpkTCo1du+B3P4OPVwVdSWb45hVw6EB47g/wr9UweETQFUXC\nbx6Aa6dDty5BV9J4h9XdB1IvqciJ888/nxdffJF169aRl5fHDTfcwM6dO4F4Rlx77bVMnjyZYcOG\nsXv3bn7+85/TuXPnOo8bq6ioqGh0dUmIX0dcGMSpU6QCmA18WP1IO2C/WvbcULn3l7m/+7v/3tYD\njWmWYrEYL1Yc2eDXHRcradR5lXqxWCyjU0INsw74NVXtRWvgmiDLUagVmhMCKn+fWJTBfye7d8P1\n34Y//BGIwG/PabcVaAkcS6eOv+fIfHjiAWiVopEXzdWc/4Np18PGDUFXkhrdgNVE+/cJR+Ik7X/Y\nswMH4sujNmSJVPd3f/dPj1T0nEsKRhawixOCLkMRZ04ocBUV8POr4K/PEJ8Z7MCgK8oAFcD7wHyy\nsuCxe2t24CxeCm8vDqq2zLRiNdw0Iz4grB21f/GaaVqn6DhhzomAO3EKa3lsAHBeLY/P4sudJsHu\nH28hWgHjCPwHKUXGwyk4RjITi0kKVnviqy3EJzjeGWgtij5zIkIuODroCpLz+Xb4ZC20bgOcT/xX\naCW2A5gBbOCz7bD2YzjkoPgzJQvhlIkwbCA0YOG4Zm/75/EOnJYtYCyw99TsmacF8IsUHCfMORG6\nvocYi6ltAP3uEO6fBVwB7L+P10oKRlNMRCYptVoD3wbuBip4mjN4mnyg0IvqlAbmRIS8sTboCpJU\nTnxM8nnYgVNfrYCpwG/Y+ukO+nytDfDvvP38rzjlQvh0Ayx6JT6uSfWzm/iXJyfhTHRfFuacCLSy\nff0Dq20YV6J/jEHsnwVcjh04UhiFefijpH3bc6WqecABgVajKDMnomR40AU0Qm/8baKhDiDekXM3\nsB2YScGE+OiLLGBLkKVloBhwIjAo6EJCKMw5EWgnzveCPHkjtSPeFywpfMLc6EpK7GBgGPAmVRcu\nS6lnTkTJ0KALUJPrChwPPA1sp2tniLWA1evhOwFXpugIc04E2onTKciTS4qsMF/DKqlu2ZV/vg7A\nX4GjAqtF0WROSJmuJfHxN9CiZXxOlxbBFqSICXNOhPdCL0lKUpivYZVUt6pLnOOTHH+EnThKNXNC\nynRfTHixcydUtHQuHKVWmHPCDktJkhQqX2PPDyj/5GQnN5Yk1bCD+OTQu1iyBJYthmOCLklqIuHt\nXpKkJIX5GlZJdTuQ+EpVvyP+Xet8AN4gsycwVZiYE1Km21R9rwXxGXKGBFaLoijMOWEnjqTICXOj\nK6l+egKTgAeqH3kcOAxoG0xBihRzQsp0W6vv5QEjgitEERXmnLATR1LkhHkiMkn11xvYD/gcgBNw\nXUilijkhZbrd1fc6BliFoivMOWEnjqTICfNEZJKSNQg/tihVzAlJUiJhzonwViZJSQrz8EdJDdOK\nqpE4C4mPxpEaz5yQJCUS5pywE0dS5IS50ZXUMN8C7gJ28xdO5i+MBApdrUqNZE5IkhIJc07YiSMp\ncsLc6EpqmK58sVLVfKpmxfkMaBNcUcp45oQkKZEw50SLoAuQpFTbRcsG3ySFV0/grMr7TwDxLh0p\neeaElOm6Vd97C9gSXCGKqDDnhCNxJEVOmCcik5ScA4EYUAHAjkBrUeYzJ6RMdwJQBnzELuBXtOZq\ntjtGUykT5pwIb2WSlKQwD3+UlAq7695FSsCckDJdDJgE3A2sAbbza2Aa/oKr1AhzTvj/uKTICXOj\nKyk5nYGWwC4AtgHFwOjA6lFmMyekKGgBTAV+CsCnwHr2vNBKSl6YcyJtc+IUFRXRv39/+vXrx623\n3pqu00hS2tSnHfve975Hv379GDZsGAsXLmziCjObOaGGaA1cwp4fXIo5xVWqFDBzIr3MCdWtJfFR\nOVL4XHzxxeTk5DBkyJBany8uLqZjx47k5+eTn5/PTTfdVK/jpqUTp7y8nCuuuIKioiLeffdd5s6d\ny+LFi9NxKknaSyomIqtPO/bUU0+xbNkyli5dyt13383ll1/eVG8x45kTSkY34itVVX1c/zTAWpTZ\nzInwMyckBSkVOTF58mSKiooSnue4445j4cKFLFy4kB//+Mf1qi0tnTglJSX07duX3r17k52dzYQJ\nE5g3b146TiVJeyknq8G3L6tPO/bEE08wadIkAEaOHMnGjRtZu3Ztk7zHTGdOKFk9gYGV9yuCLEQZ\nzZwIP3NCUpBSkROjRo2iU6dOCc9TUdHwTzNpmRNn5cqV5OXlVW/36tWLBQsW7LVf8R73e1feJDUv\npZW3VKrPNaylxR/xUfHyfT5fn3astn1WrFhBTk5OElU3L+aEGiNt14IrpEpJdVKYE+FX35wwKSSV\nEs7fJ+oSi8V49dVXGTZsGLm5ufzyl79k4MCBdb4uLZ04sVj9rkscnY6TS8oovan5cas4BcesT6Ob\nN7oPeaP7VG+/dMNfajxf33bsy73n9X1dc2dOqDGqOnE+DrQKNZ3epDopzInwq//PaXQ6y1BGiAEV\nVBDPBSc2bn56E87fJ+ryla98hbKyMtq2bcv8+fMZP348S5YsqfN1afkyKzc3l7KysurtsrIyevXq\nlY5TSdJeymnZ4NuX1acd+/I+K1asIDc3N31vLELMCTXGaOJTWS4GxlBIoRMcq4HMifAzJ1R/x1Xf\n+x9iFHJJgLUoKlKRE3Xp0KEDbdu2BeDkk09m586drF+/vs7XpaUTZ8SIESxdupTS0lJ27NjBI488\nwrhx49JxKknaSyomIqtPOzZu3Dhmz54NwN/+9jcOOOAAh8jXkzmhxugEXEr8Q8wLQHwth78HWJEy\njTkRfuaE6u84YGTl/QrgHkdqqtFSkRN1Wbt2bfVozZKSEioqKujcuXOdr0vL5VRZWVnceeedjB07\nlvLycqZMmcKAAQPScSpJ2kttE4s11L7asZkzZwJw6aWXcsopp/DUU0/Rt29f2rVrx/3339/o8zYX\n5oQaqxtwMXAPsAuAPwFDiC9GLiVmToSfOaGGORnYArwL7Ob3wLRgC1KGS0VOnH/++bz44ousW7eO\nvLw8brjhBnbu3AnEM+J///d/ueuuu8jKyqJt27Y8/PDD9TpurCKZ6ZBTIBaLOfhZ0l4KSW6W9iqx\nWIzvVvy8wa+7I/afjTqvUs+cUH3cRFUnDsAPgfaB1aKmUmhOCKiaN6cw6DIUGkuAhwBoC/xnoLUo\nSIVE+/eJtIzEkaQgJXNNqiSp+TAnJEmJhDkn7MSRFDnJXJMqKTO1BrZWb/2F+JB6KTFzQpKUSJhz\nIi0TG0tSkMrJavBNUmaaAtUfs1qzgOu9tEL1YE5IkhIJc07YiSNJkjJW1UpVMWA7sDDYciRJktLK\nrxUkRU6Yr2GVlHrdgLOA/yN+QZVUF3NCkpRImHPCThxJkRPmRldSeuwfdAHKKOaEJCmRMOeEnTiS\nIifMja6k9NoddAHKCOaEFG3lQAXxS22lZIQ5J+zEkRQ5YZ5NXlJ65ADZwGagJ4UMAEYBhU50rFqY\nE1IU9SQ+1X05nwM3kA+cYQ4oKWHOCTtxJEWOq4hIzU9r4HLgTmBV5U3aF3NCiqL2wGXAryu3FwJt\ngitHGS3MOeHqVJIip5yWDb5Jynyd+WKlKoDnACgNqBqFmTkhRVVXYOoe26+yKKhSlNHCnBPh7V6S\npCT5YVtqvnKAfsCS6kdWA70DqkZhZU5IUZYLHAx8BMBKYFCQ5SgjhTkn7MSRFDlhvoZVkhQ8c0KS\nlEiYc8JOHEmRE+ZrWCWlX80WoHVAVSjMzAlJUiJhzonwViZJSQrz8EdJ6Xcy8cupdgHHMI8C5rk6\niWowJyRJiYQ5J+zEkRQ5YW50JaVfB+Dfia9U9QquTaK9mROSpETCnBOuTiVJkiKnaqUqgGcB2BlY\nLZIkSaniSBxJkRPmicgkNZ0c4t9W7Ybq/0pgTkiSEgtzTtiJIylywjwRmaSgrAD6ALGgC1EImBNS\n81ERdAHKSGHOifBWJklJCvM1rJKaVltgKwAPAl8BxgVZjkLCnJCiLgf4CIDXgGOBdkGWo4wT5pxw\nThxJkVNOywbfGmL9+vUUFBRw2GGHceKJJ7Jx48a99ikrK2PMmDEMGjSIwYMHc/vtt6fq7UlqgEvY\n8xur1znWVaqEOSFF30lADwB2AL+gLZ8HWo8yTSpy4uKLLyYnJ4chQ4bUeo7f//73DBs2jKFDh3LM\nMcfw1ltv1as2O3EkRU66P5xPnz6dgoIClixZwgknnMD06dP32ic7O5vbbruNRYsW8be//Y1f//rX\nLF68OFVvUVI97U98paqqDzwvA7AgqHIUEuaEFHUtgG8DB1Zub+MunB1N9ZeKnJg8eTJFRUX7PEef\nPn146aWXeOutt7juuuu45JJL6lWbnTiSImcXLRt8a4gnnniCSZMmATBp0iQef/zxvfbp3r07w4cP\nB6B9+/YMGDCAVatWNf7NSWqwzsCZNR55LZhCFBrmhNQctAQuq97aVHmT6iMVOTFq1Cg6deq0z3Mc\nddRRdOzYEYCRI0eyYsWKetXmnDiSIqc+E5F9WvwPthUn94vc2rVrycnJASAnJ4e1a9cm3L+0tJSF\nCxcycuTIpM4nqfFa19hyZoTmzpyQmovsoAtQhkp3TnzZvffeyymnnFKvfe3EkRQ59Rn23nr0SFqP\n/uLD8robZtZ4vqCggDVr1uz1uptvvrnGdiwWIxbb92o3W7du5ZxzzmHGjBm0b9++zrokpdf+wGYm\nBV2GAmZOSJISSUVO1NcLL7zAfffdxyuvvFKv/e3EkRQ5qZhN/plnntnnczk5OaxZs4bu3buzevVq\nunXrVut+O3fu5Oyzz2bixImMHz++0TVJSl4e0ArYDHyVQk6vfLzQiY6bJXNCkpRIU61O9dZbbzF1\n6lSKiooSXnq1J+fEkRQ56Z7rYNy4ccyaNQuAWbNm1frBu6KigilTpjBw4ECmTZuWkvclKXmtgSuI\nf3v1GvBssOUoYOaEJCmRdOcEwPLlyznrrLOYM2cOffv2rffr7MSRFDnlZDX41hDXXHMNzzzzDIcd\ndhjPP/8811xzDQCrVq3i1FNPBeCVV15hzpw5vPDCC+Tn55Ofn59wdnpJ6bc/cDnxDz8vA6WBVqMg\nmROSpERSkRPnn38+Rx99NO+99x55eXncd999zJw5k5kz45dd3XjjjWzYsIHLL7+c/Px8jjzyyHrV\nFquoqKhI6butp1gs5gBmSXspJP7tZLJisRg9Kj5o8OtWx/o06rxKPXNC6fIA8Q6cQcAi/gMnOs40\nheaEACrnGioMugyFXiEAMeB7QP0uWFEmKyTav084EkeSJDVLiwBYGnAVkiRJ9efExpIip6kmIpOU\nmfarsbUIGB5MIQqMOSE1JzGgggpgCTCyjr0lCHdOOBJHUuSU727Z4Juk5mMc8ZWq4pYywssxmh1z\nQmpOzqy+Nx8o5LzgSlHGCHNOOBJHUuTs2uWHbUn71o74SlUzgHLgHwA8DxwfXFFqUuaE1JwMBT4H\n/lS5/QgfAH2CK0gZIMw5YSeOpMgp32XTJimx/YF/B+6ofuR1YAzxYfeKOnNCam6OAD4GSgB4ApgW\nZDkKvTDnRHgrk6QklYe451xSeBxYY+sq7MBpPswJqTk6iKpOnN3BFqIMEOacsBNHUuSEudGVFFYu\nHd2cmBOSpETCnBN24kiKnF07w9voSgqXDsAWAP4AnBNoLWo65oQkKZEw54SdOJIiZ3e5TZuk+rkM\n+G9gJ+8wgnc4DSh0tarIMyckSYmEOSfCW5kkJSvEwx8lhUvVSlW3E1+laiMAbxFfzUSRZU5IkhIJ\ncU7YiSMpekLc6EoKn47A6cDjwDIgPvGlnTiRZk5IkhIJcU7YiSMpena5woykhmkVdAFqWuaEJCmR\nEOdEi6ALkCRJCpetuFqVJEXNF7+Uf47LjCtz2YkjKXp2JXGT1KwdCrSu3trIEG5wguMoMyekZuhQ\nYD8g3olzIwdRyE8CrUghFuKcsBNHUvSEuNGVFE77EZ/gOLty+22q5sdRJJkTUjPUGvguX8woshyY\n67hL1S7EOWEnjqToCXGjKym82hPvyKn6cOQ8ORFmTkjNVFVLX2UJbwZVisItxDnhxMaSomdn0AVI\nylQdge7AKuDTgGtRGpkTUjN2ANCTeEsPmwKtRaEV4pywE0dS9JQHXYAkKdTMCUlSIiHOCTtxJEWP\nw94lNULbyj//DsRXqQrvMqNKkjkhSUokxDnhnDiSoifN17CuX7+egoICDjvsME488UQ2bty4z33L\ny8vJz8/n9NNPT+KNSArCOcSnv/wAGMQNTHaVqugxJyRJiaQoJ4qKiujfvz/9+vXj1ltv3ev5DRs2\ncOaZZzJs2DBGjhzJokWL6izNThxJ0ZPmD+fTp0+noKCAJUuWcMIJJzB9+vR97jtjxgwGDhxILOY3\n+VKmaM0XK1UtAu4HYH6AFSnlzAlJUiIpyIny8nKuuOIKioqKePfdd5k7dy6LFy+usc8tt9zCV77y\nFd58801mz57NlVdeWWdpduJIip40fzh/4oknmDRpEgCTJk3i8ccfr3W/FStW8NRTT/Htb3+bigoX\nsJQySXvg32s8UhJMIUoPc0KSlEgKcqKkpIS+ffvSu3dvsrOzmTBhAvPmzauxz+LFixkzZgwAhx9+\nOKWlpXz88ccJS3NOHEnRU58P228XwzvFSR1+7dq15OTkAJCTk8PatWtr3e/73/8+v/jFL9i8eXNS\n55EUrP1rbPkLdqSYE5KkRFKQEytXriQvL696u1evXixYsKDGPsOGDeOxxx7j2GOPpaSkhI8++ogV\nK1bQtWvXfR7XThxJ0VOfRnfA6PitysM31Hi6oKCANWvW7PWym2++ucZ2LBardQj8k08+Sbdu3cjP\nz6e4uLgeBUkKPyc5jgxzQlKlEC9CpCClICfqc5nsNddcw5VXXkl+fj5DhgwhPz+fli1bJnyNnTiS\nVItnnnlmn8/l5OSwZs0aunfvzurVq+nWrdte+7z66qs88cQTPPXUU2zfvp3NmzfzrW99i9mzZ6ez\nbEkp1IL4aJwvxkj8L3BuUOUoZMwJKZP1A1YB8DIwDDgwyHIUSbm5uZSVlVVvl5WV0atXrxr7dOjQ\ngfvuu696+5BDDqFPnz4Jj+ucOJKiZ2cStwYYN24cs2bNAmDWrFmMHz9+r31uueUWysrK+PDDD3n4\n4Yc5/vjj/WAuZZgYcDmwX+V2HxZR6EpV0WBOSM3cGGAQALuBO8hiU6D1KHRSkBMjRoxg6dKllJaW\nsmPHDh555BHGjRtXY59NmzaxY8cOAH73u99x3HHH0b59+4Sl2YkjKXrKk7g1wDXXXMMzzzzDYYcd\nxvPPP88111wDwKpVqzj11FNrfY2rjkiZqQ3wXeIrVX1A/BtbRYA5IYlzgEMr7+/iLry0SntIQU5k\nZWVx5513MnbsWAYOHMh5553HgAEDmDlzJjNnzgTg3XffZciQIfTv358///nPzJgxo87SYhUBTYUf\ni8X8LkvSXgqhUSt0xGIxmJXE6yfFXBkkZMwJhUkJ8BRwCPCh/2cGrNCcEFDV8VUYdBnKaDuAW4D4\n6MsfEF+dUJmtkGj/PuGcOJKip4FLwUpSXRJPMaiMY05IApysXvsU4pywE0dS9IS40ZWUmaquP98I\nxMdMt8AP/xnMnJAkJRLinLATR1L0hLjRlZSZBgHPAhsA+CmHAecDN3gpR2YyJyRJiYQ4J+zEkRQ9\nIeRpRE8AABmZSURBVG50JWWmVsAVwH8DnwNLgHmBVqRGMSckSYmEOCfSsjpVYWEhvXr1Ij8/n/z8\nfIqKitJxGkmq3a4kbmpS5oQyUdVKVVXz47wBwMqgylFjmBOhZkZIClyIcyItI3FisRhXXXUVV111\nVToOL0mJ7Qy6ANXFnFCmag90AtZVP7I9sFrUCOZEqJkRkgIX4pxI2+VULsEoKTDlQReg+jAnJAXG\nnAg9M0JSoEKcE2m5nArgjjvuYNiwYUyZMoWNGzem6zSStLcQD3/UF8wJZaqOlX9mA9AjuEKUPHMi\n9MwINY2WVF0kWwG8GmgtCpUQ50SsIslu7oKCAtasWbPX4zfffDNf+9rX6Nq1KwDXXXcdq1ev5t57\n76154liM0Xts9668SWpeSitvVYpp3LdvsVgMbkji9T+J+a1fipkTiqodwAzgU+BwYAKuUpVepXw5\nKcyJzNfYjIDKv0uTQo1WBuz5/1cBhTwTVDFKQinN6/eJpC+neuaZ+v2P/e1vf5vTTz+91udGJ3ty\nSZHRm5oft4pTcVC/MQ0Fc0JR1Qr4DvGOnPeAJ4ItpxnoTcqTwpwIXCoyIm50SupRc5YHXAg8WLn9\nDG8Aw4MrSA3Um+b1+0RaLqdavXp19f0//OEPDBkyJB2nkaTahXj4o+LMCWW6tsAllfffDLIQJcec\nCDUzQk3vUGBU9dZfgitEYRHinEjLxMZXX301b7zxBrFYjEMOOYSZM2em4zSSVLsQzyavOHNCUdAW\niAVdhJJjToSaGaFgdKx7FzUfIc6JtHTizJ49Ox2HlaT6CfFs8oozJxQVFZU3+B0whTSuGaFUMidC\nzYyQFLgQ50TalhiXpMA47F1SE2gNdAI2wP9v7/6Do67vfY8/V5Iq9RdaJGCSmlOTkARDwAZtOxeP\nvRABGSNtbcF6bA61thWZ2ql/HKZzqqktGObOnXGUcQa97W3stJD+gtC5mhrLcAbtUE4Lg+2EU6Il\nZ0IgaYXGWuMYCXv/WBISQ5bN5sf3m+8+HzNr8t397u57Sfy8Nu/9fj8foIPreIx/xUmOpwRzQpKU\nTIhzwiaOpOgJ8aArKTpiwAPAE0AP8N9AA5A4NscTrULNnJAkJRPinLCJIyl6QnwOq6Ro+QCwnkQj\npxf4LwBeAf5HcEXpwswJSVIyIc4JmziSoifE57BKip4PkljT5NcD1xwLrBalyJyQJCUT4pywiSMp\nekJ8+KOkaOo/eepK4E1uDLIUpcKckCQlE+KccAkFSdFzOo3LKJw6dYqqqiqKi4u57bbb6O7uPu9+\n3d3d3HXXXZSWllJWVsa+ffvSfEGSwi777NdEM6cwuEKUGnNC0jDnjm/4O4lTZJXBxiknmpqaKCkp\noaioiM2bN593nz179rBw4UJuuOEGbr311guWZhNHUvS8l8ZlFOrq6qiqquLIkSMsWbKEurq68+73\n0EMPcfvtt3P48GFeffVVSktL03xBksLuo8AVQDdwHY/xKLXUukpVeJkTkoa5gcSag4n/5Tcxg1r+\nPdCKFKBxyIm+vj7Wr19PU1MTLS0tbNu2jcOHDw/Zp7u7mwcffJBf/vKX/PGPf+RnP/vZBUuziSNJ\no7Rr1y5qamoAqKmpYefOncP2efPNN9m7dy9f/OIXAcjKyuLKK6+c1DolTZ4s4EES8+P0r1IVD7Qi\nBcmckKaiLGAdcNnZ7W7gGc4EV5CmuP3791NYWEhBQQHZ2dmsWbOGxsbGIfv8+Mc/5jOf+Qx5eXkA\nzJw584KPaxNHUvT0pXEZha6uLnJycgDIycmhq6tr2D5Hjx7lmmuuYe3atdx4443cf//99PT0pPuK\nJE0BF5NYqWoaiVWqOoMtR8mYE5LOK5tzIznAXzgUYDUK0DjkREdHB/n5+QPbeXl5dHR0DNmntbWV\nU6dO8clPfpLKykp++MMfXrA0JzaWFD2pzF3wxh44uWfEm6uqqujsHP4n2MaNG4dsx2IxYrHYsP1O\nnz7NgQMH2LJlC4sWLeLrX/86dXV1PPbYYykUJ2mq+iCJz3DfBBJvw94ALvypmiaZOSFpRJeQOK3q\nDSDUK01rIo1DTpxv7H+/9957jwMHDvDrX/+anp4ePv7xj/Oxj32MoqKiEe9jE0dS9KQy6M64NXHp\nd+TbQ25ubm4e8a45OTl0dnYye/ZsTpw4waxZs4btk5eXR15eHosWLQLgrrvuGnFOBEnR1DPovwoZ\nc0KSlMw45ERubi7t7e0D2+3t7QOnTfXLz89n5syZTJ8+nenTp3PLLbdw6NChpE0cT6eSFD0TPGFl\ndXU19fX1ANTX17Nq1aph+8yePZv8/HyOHDkCwEsvvcS8efPSejmSppYPDdl6HmfHCSFzQpKUzDjk\nRGVlJa2trbS1tdHb20tDQwPV1dVD9rnzzjt5+eWX6evro6enh9/+9reUlZUlLc0mjqTomeC5DjZs\n2EBzczPFxcXs3r2bDRs2AHD8+HFWrlw5sN9TTz3FPffcQ0VFBa+++irf/OY3x/rKJE0BdwOXD2x1\n8k98Gxs5IWNOSJKSGYecyMrKYsuWLSxbtoyysjJWr15NaWkpW7duZevWrQCUlJSwfPly5s+fz803\n38z9999/wSZOLB6PB/KuIhaLufCmpGFqgbEMS7FYDBancf+9sTE9r8afOaGp7F3gCeCdgWvmA58O\nqpyIqTUnBPTPN1EbdBmKpC30z4lzO3BToLVotGqJ9t8TzokjKXpSOYdVkibQxcAXgaeBGHCGgkDr\n0fuYE5KkZEKcEzZxJEWPywhICoGLz369CDjDjUGWovczJyRJyYQ4J2ziSIqeUc5dIEkTqW/gv9OC\nLUTnmBOSUvR20AUoGCHOCZs4kqInxIc/SsoclwNXAyeBOXyHL5M4tarWOTyCZ05ISupm4P8B8B/E\n+A/+lVr+b7AlaXKFOCdcnUpS9JxO4yJJ4ywGfJVEM+cE8ByuURUa5oSkpBYB/3z2+zjwA04EWI0C\nEOKcsIkjSZI0QbKB9cAlwFHguwC8HGBFkqTUfBKoPPt9nO8R6jNslEE8nUpS9IR4IjJJmediEn8G\nvEz/HwBvBFmOwJyQlKL/CfwOSIzfzm6WQUKcEzZxJEWPH5NIkpIxJyRJyYQ4J2ziSIoe5y6QFDLT\nh2z9GTiDZ7UHyJyQJCUT4pzw3YOk6AnxRGSSMtPHgKsGtv7OtTzGo65SFRxzQpKUTIhzwiNxJEVP\niM9hlZSZpgHrgCeBt4Au4N1AK8pw5oQkKZkQ54RH4kiKnr40LpI0wfpXqppGYtj5e7DlZDZzQpKU\nTIhzwiNxJEWPh71LCqmLSSw3/jb2BQJlTkiSkglxTtjEkRQ9IR50JUkhYE5IGqX42YsyRIhzwiaO\npOgJ8TmskpRDYn2qnwOuUhUQc0JSSi4mcTJsYtDYAawGYgFWpEkS4pzwXYOk6AnxOaySdA+Jlare\nAKbzGKXU4ue7k8yckJSSacAD9Ldt/gv4NjcGWZAmS4hzwiaOpOiJp3GRpEnSv1LVZcA7wGEAfhZg\nRRnInJCUsquBrw7aPsDeoErR5AlxTtjEkSRJmmTZwL8w+JD81wOrRZJ0ITnAPw9stQRXiGQTR5Ik\nKQhOTChJU4mjtsLBJo4kjdKpU6eoqqqiuLiY2267je7u7vPu9/jjjzNv3jzKy8v5/Oc/z7vvvjvJ\nlUoKs6ETY/YS6qUwNCrmhCQJoKmpiZKSEoqKiti8efOw2xsbG6moqGDhwoV89KMfZffu3Rd8TJs4\nkjRKdXV1VFVVceTIEZYsWUJdXd2wfdra2nj22Wc5cOAAf/jDH+jr62P79u0BVCsprK4GZg1snWEl\n36WW2sDq0fgxJyRJfX19rF+/nqamJlpaWti2bRuHDx8ess/SpUs5dOgQBw8e5Ac/+AFf/vKXL/i4\nNnEkRdB7aVxSt2vXLmpqagCoqalh586dw/a54ooryM7Opqenh9OnT9PT00Nubm7ar0hS9MSA+4EZ\nZ7cP4fy5k8eckCQlM/ac2L9/P4WFhRQUFJCdnc2aNWtobGwcss+ll1468P0//vEPZs6cecHKbOJI\niqDTaVxS19XVRU5ODgA5OTl0dXUN2+fqq6/m4Ycf5sMf/jDXXnstM2bMYOnSpWm/IknRlAU8CHwQ\nOAa8Emw5GcSckCQlM/ac6OjoID8/f2A7Ly+Pjo6OYfvt3LmT0tJSVqxYwZNPPnnBypydSVIEpfKJ\n6V7g5RFvraqqorOzc9j1GzduHLIdi8WIxWLD9nv99dd54oknaGtr48orr+Szn/0sP/rRj7jnnntS\nqE1SJskG5gH/CbwZcC2Zw5yQJCUz9pw439h/PqtWrWLVqlXs3buXe++9lz/96U9J97eJIymCUvnE\n9ONnL/2GzlfQ3Nw84j1zcnLo7Oxk9uzZnDhxglmzZg3b53e/+x2f+MQn+NCHPgTApz/9aX7zm9/4\n5lySQsGckCQlM/acyM3Npb29fWC7vb2dvLy8ER9t8eLFnD59mpMnTw5kw/l4OpWkCJrYuQ6qq6up\nr68HoL6+nlWrVg3bp6SkhH379vHOO+8Qj8d56aWXKCsrS/sVSYq2y85+TUx3+DLQF1gtmcGckDRa\nlw189xfgreAK0aQYe05UVlbS2tpKW1sbvb29NDQ0UF1dPWSf119/nXg8MSPegQMHAJI2cMAmjqRI\nmtg35xs2bKC5uZni4mJ2797Nhg0bADh+/DgrV64EoKKigi984QtUVlYyf/58gJRmm5eUmRaTWKnq\nHwC8xCy+A5wJsqSIMyckjdYC4Dog0Wb/31xMLf8WaEWaSGPPiaysLLZs2cKyZcsoKytj9erVlJaW\nsnXrVrZu3QrAz3/+c8rLy1m4cCEPPfRQSqsUxuL9bZ9JFovFXERT0jC1wFiGpcS5p0fTuOc/jel5\nNf7MCWWa08AWoHvgmjzgPhLrWOmcWnNCQP/PsjboMpRRzgDPAP3zYV3KN3mbDwRYkYarJdp/T3gk\njqQImthPWCVpImQB6xj85uwYg1s6Gk/mhKR0XATcT2JKeoC3ORJgNZpI4c0JmziSJEkh8QHO/WmQ\n4JEfkhQu04APDmw5SmuyuTqVpAhKZTZ5SVLmMickScmENyds4kiKIA97lzR15QOvAXAlcEWgtUSX\nOSFJSia8OeHpVJIi6HQaF0kKh88D1wDwJrP4Lo84cesEMCckScmENyc8EkdSBIW3cy5JF3IR8BXg\nKeAvwE+CLSeizAlJUjLhzQmbOJIiyE9MJU1tWcDngP8DtAdcSzSZE5KkZMKbEzZxJEVQeDvnkpSq\n/nPeEyufvANMD6yW6DEnJEnJhDcnnBNHUgSF9xxWSUrVRSQaOD0A/C/C/IZy6jEnJI3FuT+jTwRY\nhSZSeHPCJo6kCHovjYskhcssIHdg6wxXsZFvOcnxODEnJI3FioHvfgPU8qngStEECW9O2MSRFEHh\n7ZxLUqpiwH30r1QFfwOeAeBMQBVFiTkhaSyKYUjjZgd/CqoUTZDw5oRNHEkRFN7OuSSNRv9KVZee\n3e4C4D+DKidCzAlJY1UBVA1sNdA/h5miIbw54cTGkiLIN9uSoiMLuB54deCa3sBqiQ5zQtJ4mAc0\nAx4jGT3hzQmbOJIiyMPeJUXTYmAvi4MuIwLMCUlSMuHNCU+nkiRJCrmrzn49CIT500FJkjSxPBJH\nUgT5B46kaLkVeA3oAK5iI+uB77hS1RiYE5KkZMKbEzZxJEVQeA9/lKR09K9U9TTwBvAskJhCMxZc\nUVOaOSFJSia8OWETR1IEhbdzLknpugj4KrAJ6ATgEDAfz45PhzkhSUomvDlhE0dSBIW3cy5JY5FF\nomWTWAVlJ4l1qy4PsKKpypyQJCUT3pxI+6Obn/70p8ybN49p06Zx4MCBIbc9/vjjFBUVUVJSwosv\nvjjmIqOsLegCQqIt6AJCoC3oAiLlvTQuqUs2/g3W1NRESUkJRUVFbN68OZ0XMqWZE+OjLegCQqIt\n6AJCoO2814b3k8JwMyfCwJwYL21BFxASbUEXQF/Az98W8PNHy/jkRCrj/Ne+9jWKioqoqKjg4MGD\nF6ws7SZOeXk5O3bs4JZbbhlyfUtLCw0NDbS0tNDU1MS6des4c+ZMuk8TeW1BFxASbUEXEAJtQRcQ\nKafTuKRupPFvsL6+PtavX09TUxMtLS1s27aNw4cPp/NipixzYny0BV1ASLQFXUAItJ39+pFB113O\nk/y7ExynwZwIA3NivLQFXUBItAXwnJcDlw5sfZfZ1PJIAHUktAX2zFE09pxIZZx//vnnee2112ht\nbeWZZ57hgQceuGBlaTdxSkpKKC4uHnZ9Y2Mjd999N9nZ2RQUFFBYWMj+/fvTfRpJSsPEfsI60vg3\n2P79+yksLKSgoIDs7GzWrFlDY2PjaF/IlGZOSBPjbuDas9+/RWKy4+A//51qzIkwMCc09U0D1gMX\nn93uBJ4jHlxBGjdjz4lUxvldu3ZRU1MDwM0330x3dzddXV1JKxv3mfCOHz9OXl7ewHZeXh4dHR3j\n/TSSlMTEfsKaio6ODvLz8we2HQvPMSekselfqWrm2e1TAPw+qHKmKHMizMwJTS3TSTRy+qeb/W9e\nC7AajZex50Qq4/z59jl27FjSypJObFxVVUVnZ+ew6zdt2sQdd9yR9IEHi8XOv/xlbcqPEG17gi4g\nJPYEXUAI7Am6gMioHfU9LrvssiHbYx3/Rhr3osacmBx7gi4gJPYEXUAI7BnxlufPXpSa2lHfw5xI\nz0TnhEnRb0/QBYTEnqALAOL8KMBn3xPgc0dL7ajv8f6cSHWcj8eHHrt1ofslbeI0Nzen9KSD5ebm\n0t7ePrB97NgxcnNzh+33/kIlaTyM19iSzvg32PvHwvb29iGfKkaFOSFpqjEnJpc5IWmqGa+xJZVx\nPtXxbrBxOZ1q8Iusrq5m+/bt9Pb2cvToUVpbW7npppvG42kkKXRGGuQrKytpbW2lra2N3t5eGhoa\nqK6unuTqwsOckJSpzInUmBOSoiaVcb66uprnnnsOgH379jFjxgxycnKSPm7aTZwdO3aQn5/Pvn37\nWLlyJStWrACgrKyMz33uc5SVlbFixQqefvrpjDlcVFJmGGn8O378OCtXrgQgKyuLLVu2sGzZMsrK\nyli9ejWlpaVBlj3pzAlJmcqcSI05ISnKRhrnt27dytatWwG4/fbb+chHPkJhYSFf+cpXePrppy/8\nwPFJ9pOf/CReVlYWv+iii+K///3vh9y2adOmeGFhYXzu3LnxX/3qV5NdWmAeffTReG5ubnzBggXx\nBQsWxF944YWgS5o0L7zwQnzu3LnxwsLCeF1dXdDlBOa6666Ll5eXxxcsWBBftGhR0OVMmrVr18Zn\nzZoVv+GGGwauO3nyZHzp0qXxoqKieFVVVfxvf/tbgBUqCObEcOaEOZGJOWFGaCTmxFCZnBHxuDnR\nz5xIyIScGPfVqS6kvLycHTt2cMsttwy5vqWlhYaGBlpaWmhqamLdunWcOXNmsssLRCwW4xvf+AYH\nDx7k4MGDLF++POiSJkVfXx/r16+nqamJlpYWtm3bxuHDh4MuKxCxWIw9e/Zw8ODBjFpCc+3atTQ1\nNQ25rq6ujqqqKo4cOcKSJUuoq6sLqDoFxZwYzpwwJzIxJ8wIjcScGCpTMwLMicHMiYRMyIlJb+KU\nlJRQXFw87PrGxkbuvvtusrOzKSgooLCwMGN++SAzJ2bbv38/hYWFFBQUkJ2dzZo1a2hsbAy6rMBk\n4u/A4sWLueqqq4Zct2vXLmpqagCoqalh586dQZSmAJkT55eJY4Q5MVSm/Q6YERqJOTFcpo0P/cyJ\noTLt9yBTc2LSmzgjOX78+JCZms+3hnqUPfXUU1RUVHDffffR3d0ddDmToqOjg/z8/IHtTPuZDxaL\nxVi6dCmVlZU8++yzQZcTqK6uroHJvHJycujq6gq4IoWFOWFOZNrPfDBzIsGMUDKZnBOZmBFgTgxm\nTiRkQk4kXWI8XVVVVXR2dg67ftOmTdxxxx0pP06UJjAb6d9k48aNPPDAAzzyyCMAfOtb3+Lhhx/m\ne9/73mSXOOmi9PMdq1deeYU5c+bw17/+laqqKkpKSli8eHHQZQUuFov5exJR5sRw5sRwUfr5jpU5\nMZwZEW3mxFBmxPlF5ec7HsyJ4aKaExPSxGlubh71fdJZH30qSfXf5Etf+tKogmkqe//PvL29fcin\nJ5lkzpw5AFxzzTV86lOfYv/+/Rk76Obk5NDZ2cns2bM5ceIEs2bNCrokTQBzYjhzYjhz4hxzIsGM\nyBzmxFBmxPmZE+eYEwmZkBOBnk41+Jy96upqtm/fTm9vL0ePHqW1tZWbbropwOomz4kTJwa+37Fj\nB+Xl5QFWM3kqKytpbW2lra2N3t5eGhoaqK6uDrqsSdfT08Nbb70FwNtvv82LL76YMb8D51NdXU19\nfT0A9fX1rFq1KuCKFCRzIsGcMCfMiQQzQu9nTmRuRoA50c+cOCcjcmKyl8P6xS9+Ec/Ly4tfcskl\n8ZycnPjy5csHbtu4cWP8+uuvj8+dOzfe1NQ02aUF5t57742Xl5fH58+fH7/zzjvjnZ2dQZc0aZ5/\n/vl4cXFx/Prrr49v2rQp6HIC8ec//zleUVERr6ioiM+bNy+j/h3WrFkTnzNnTjw7Ozuel5cX//73\nvx8/efJkfMmSJZFeFlDJmRPDmRPmRCbmhBmhkZgTQ2VyRsTj5kQ8bk5kWk7E4vEMm8JakiRJkiRp\nCgrN6lSSJEmSJEkamU0cSZIkSZKkKcAmjiRJkiRJ0hRgE0eSJEmSJGkKsIkjSZIkSZI0BdjEkSRJ\nkiRJmgL+P+EDqRpS84mvAAAAAElFTkSuQmCC\n"
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": "",
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment