{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 1. Representing Time in Connectionist Networks\n",
"\n",
"This notebook explores how time has been represented in artificial neural networks. There are complex, mathematical models. However, we examine three straightforward methods.\n",
"\n",
"For this exploration, we will use the encoding method from this week's lab.\n",
"\n",
"First, we define some text:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"text = (\"This is a test. Ok. What comes next? Depends? Yes. \" +\n",
" \"This is also a way of testing prediction. Ok. \" +\n",
" \"This is fine. Need lots of data. Ok?\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And an encoding methodology:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"letters = list(set([letter for letter in text]))\n",
"\n",
"def encode(letter):\n",
" index = letters.index(letter)\n",
" binary = [0] * len(letters)\n",
" binary[index] = 1\n",
" return binary\n",
"\n",
"patterns = {letter: encode(letter) for letter in letters}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1.1 NETTalk (1987)\n",
"\n",
"Consider the problem of reading. That is, given input text, produce a representation of pronouncing that text.\n",
"\n",
"Consider the word \"cache\". The first \"c\" is pronounced /k/, but the second \"c\" is pronounced /sh/. Now consider the made-up word: Tacoche. How would you pronounce it? How do you even go about making a guess?\n",
"\n",
"In 1987, the program NETTalk was created to attempt to solve this problem."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![](\"images/nettalk.png\")
"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"29.0"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"203 / 7"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Additional input units are called **context** or **state** units.\n",
"\n",
"How is time represented in NETTalk?"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false,
"format": "tab"
},
"outputs": [
{
"data": {
"image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEABALDA4MChAODQ4SERATGCgaGBYWGDEjJR0oOjM9PDkz\nODdASFxOQERXRTc4UG1RV19iZ2hnPk1xeXBkeFxlZ2MBERISGBUYLxoaL2NCOEJjY2NjY2NjY2Nj\nY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY//AABEIAWgB4AMBIgACEQED\nEQH/xAAYAAEBAQEBAAAAAAAAAAAAAAAAAQIDB//EACAQAQACAgMBAQEBAQAAAAAAAAABAhExITJB\nElEiYUL/xAAUAQEAAAAAAAAAAAAAAAAAAAAA/8QAFBEBAAAAAAAAAAAAAAAAAAAAAP/aAAwDAQAC\nEQMRAD8A8/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAXEpDX0CYn8MS3HMM/X+AyLM5QAAAXEoBjJpY\nJnIIAAGAADAAABgw3XQMBOwAAAMSAAuJBAWNgg1aGQAAAAAMAAAAAYGqpbYIAAAAAAAAAAAAAAAD\npXrDm6V6w5gRt0nTnG27aBJtEwRMRDLUV/QPpbaMwW6glNlimy+wWuk+saWumJ2DpHMMRGZw1Xqz\nHYGusEWyWx6n8glowtY4yWnKx1BJs1Dm3XQMTsJ2AtdtWnDNdrfwFi2WbbWuy+wWsYjKfTXjOKgs\nxmErPi5jDNdg1M4Kyl0rsCY5bjSTHJM8gzjlq3EGP6S0gVhZtgrpidg3E5hmYxK1LbBrxPqF8cwa\np6YzYo1nkGbTjiGVtHKAAAAAAAAAAAAAAA6V6w5gBG27aYAHTcOZkGvnG1t1lgBqmy+2QG66YnYA\n3XqznEoA3P8ARFcbYMyC2x4tZzGGQGvlqMY4c8gE7ABa7W/jIDVdl2QG6zmMJ88smZBq2MJXaANz\nGWNSuZQHSNMTPKAOjnOwBqsrNcsGQbiIhmZzKAOnjmANU0kzygDe4YAAAAAAAAAAAAAAAAAAAADG\nAAAAwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAC4lAAAAAAAAAAAAAAAAAAWuwQatC10DA1eFroGY4\nkmcley38ArCW21Wcpa3gLTTM9papomcSDGBvcMSAC17AhiW5xBE5BgatGCscAmJ/Ea+sLMZjIMDV\nUtsEG4jhmY5BBvVWAAbtzAMDVdraOAYGqwk8yCLiWojEJ9f4DI1aErsEG5xDMzkEG9Qn1nwFt1Yb\nt1SsAziRubYnRmJgGAAAAAAAAAAAAAAAAbnmpPFSs8JYFnmC3EFZ4S2wSvZb+JXst/AKaS21oWj0\nFppm22qaZtsGqaZnbVdMzsEWvZFr2Bb+JXa38SuwW/ix1S3i1ngExH6uYj1PnknEQCRPLUxnDDpG\ngSZ5Jj+oZttuNAzafGVttAG68ww1XYLHEETmC2koCxxDMbatPDAN20w3uE+QX/lK7W0xjCV2BdI2\nt2QbtphvcJ84BbdWazhq3VK49BcxJNYSa/ixxAMCzzKAAAAAAAAAAAAAAAAAAAAALmf1ADIAAAAA\nAAAALmf1AAMgAZAAAAADIAAAC5n9QAAAAAyZAAAFzP6mQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\nAB//2Q==\n",
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from IPython.display import YouTubeVideo\n",
"YouTubeVideo(\"gakJlr3GecE\", width=600)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from conx import Network\n",
"\n",
"class NETTalk(Network):\n",
" def initialize_inputs(self):\n",
" pass\n",
"\n",
" def inputs_size(self):\n",
" # Return the number of inputs:\n",
" return len(text)\n",
"\n",
" def get_letter(self, i):\n",
" if 0 <= i < len(text):\n",
" return text[i]\n",
" else:\n",
" return text[0]\n",
" \n",
" def get_inputs(self, i):\n",
" inputs = []\n",
" for index in range(i - 3, i + 3 + 1):\n",
" letter = text[i]\n",
" inputs += patterns[letter]\n",
" return [inputs, inputs]"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"pattern_length = len(patterns[\" \"])\n",
"input_length = pattern_length * 7\n",
"\n",
"nettalk = NETTalk(input_length, 80, input_length)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'00000000100000000000000000000000000001000000000000000000000000000010000000000000000000000000000100000000000000000000000000001000000000000000000000000000010000000000000000000000000000100000000000000000000'"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\".join([str(v) for v in nettalk.get_inputs(0)[0]])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"Training for max trails: 500 ...\n",
"Epoch: 0 TSS error: 13070.2553377 %correct: 0.0\n",
"Epoch: 10 TSS error: 716.730931536 %correct: 0.0\n",
"Epoch: 20 TSS error: 468.573515397 %correct: 0.0\n",
"Epoch: 30 TSS error: 431.95824528 %correct: 0.0\n",
"Epoch: 40 TSS error: 416.634038769 %correct: 0.0\n",
"Epoch: 50 TSS error: 265.945084501 %correct: 0.37593984962406013\n",
"Epoch: 60 TSS error: 261.9540547 %correct: 0.42105263157894735\n",
"Epoch: 70 TSS error: 251.242554953 %correct: 0.47368421052631576\n",
"Epoch: 80 TSS error: 249.358370138 %correct: 0.42857142857142855\n",
"Epoch: 90 TSS error: 240.833746482 %correct: 0.47368421052631576\n",
"Epoch: 100 TSS error: 238.423773943 %correct: 0.47368421052631576\n",
"Epoch: 110 TSS error: 236.585542687 %correct: 0.47368421052631576\n",
"Epoch: 120 TSS error: 235.335515939 %correct: 0.47368421052631576\n",
"Epoch: 130 TSS error: 234.6405665 %correct: 0.46616541353383456\n",
"Epoch: 140 TSS error: 232.128789819 %correct: 0.47368421052631576\n",
"Epoch: 150 TSS error: 223.954463761 %correct: 0.47368421052631576\n",
"Epoch: 160 TSS error: 222.844211745 %correct: 0.47368421052631576\n",
"Epoch: 170 TSS error: 218.780971297 %correct: 0.47368421052631576\n",
"Epoch: 180 TSS error: 212.348584825 %correct: 0.38345864661654133\n",
"Epoch: 190 TSS error: 208.880241851 %correct: 0.47368421052631576\n",
"Epoch: 200 TSS error: 200.669794731 %correct: 0.47368421052631576\n",
"Epoch: 210 TSS error: 199.049227988 %correct: 0.45112781954887216\n",
"Epoch: 220 TSS error: 185.857938381 %correct: 0.43609022556390975\n",
"Epoch: 230 TSS error: 184.198280768 %correct: 0.47368421052631576\n",
"Epoch: 240 TSS error: 183.701842181 %correct: 0.47368421052631576\n",
"Epoch: 250 TSS error: 182.849165753 %correct: 0.47368421052631576\n",
"Epoch: 260 TSS error: 180.944417168 %correct: 0.47368421052631576\n",
"Epoch: 270 TSS error: 174.454805672 %correct: 0.47368421052631576\n",
"Epoch: 280 TSS error: 170.033090104 %correct: 0.47368421052631576\n",
"Epoch: 290 TSS error: 169.799503757 %correct: 0.47368421052631576\n",
"Epoch: 300 TSS error: 169.685143824 %correct: 0.47368421052631576\n",
"Epoch: 310 TSS error: 169.584419763 %correct: 0.47368421052631576\n",
"Epoch: 320 TSS error: 169.335318947 %correct: 0.47368421052631576\n",
"Epoch: 330 TSS error: 168.368304961 %correct: 0.47368421052631576\n",
"Epoch: 340 TSS error: 156.421263067 %correct: 0.5488721804511278\n",
"Epoch: 350 TSS error: 152.673945599 %correct: 0.5488721804511278\n",
"Epoch: 360 TSS error: 148.779486623 %correct: 0.5639097744360902\n",
"Epoch: 370 TSS error: 148.566616051 %correct: 0.5639097744360902\n",
"Epoch: 380 TSS error: 148.3543419 %correct: 0.5639097744360902\n",
"Epoch: 390 TSS error: 141.709235563 %correct: 0.556390977443609\n",
"Epoch: 400 TSS error: 139.634931458 %correct: 0.5639097744360902\n",
"Epoch: 410 TSS error: 135.253393552 %correct: 0.5639097744360902\n",
"Epoch: 420 TSS error: 132.899621933 %correct: 0.5939849624060151\n",
"Epoch: 430 TSS error: 129.947022062 %correct: 0.5939849624060151\n",
"Epoch: 440 TSS error: 129.634026189 %correct: 0.5939849624060151\n",
"Epoch: 450 TSS error: 129.34233424 %correct: 0.5939849624060151\n",
"Epoch: 460 TSS error: 127.807039826 %correct: 0.5939849624060151\n",
"Epoch: 470 TSS error: 127.60060166 %correct: 0.5939849624060151\n",
"Epoch: 480 TSS error: 127.514805405 %correct: 0.5939849624060151\n",
"Epoch: 490 TSS error: 127.376012662 %correct: 0.5939849624060151\n",
"Epoch: 500 TSS error: 126.600145442 %correct: 0.6015037593984962\n",
"--------------------------------------------------\n",
"Epoch: 500 TSS error: 126.600145442 %correct: 0.6015037593984962\n"
]
}
],
"source": [
"nettalk.train(report_rate=10, max_training_epochs=500)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[[0, 13070.255337690462, 0.0],\n",
" [10, 716.73093153640559, 0.0],\n",
" [20, 468.57351539725056, 0.0],\n",
" [30, 431.95824528003442, 0.0],\n",
" [40, 416.63403876878135, 0.0],\n",
" [50, 265.9450845005108, 0.37593984962406013],\n",
" [60, 261.95405469996177, 0.42105263157894735],\n",
" [70, 251.24255495313702, 0.47368421052631576],\n",
" [80, 249.35837013797794, 0.42857142857142855],\n",
" [90, 240.83374648196263, 0.47368421052631576],\n",
" [100, 238.42377394323839, 0.47368421052631576],\n",
" [110, 236.5855426873446, 0.47368421052631576],\n",
" [120, 235.33551593933615, 0.47368421052631576],\n",
" [130, 234.64056650023889, 0.46616541353383456],\n",
" [140, 232.12878981907664, 0.47368421052631576],\n",
" [150, 223.95446376119079, 0.47368421052631576],\n",
" [160, 222.84421174504089, 0.47368421052631576],\n",
" [170, 218.78097129678011, 0.47368421052631576],\n",
" [180, 212.34858482531087, 0.38345864661654133],\n",
" [190, 208.88024185073471, 0.47368421052631576],\n",
" [200, 200.66979473088767, 0.47368421052631576],\n",
" [210, 199.0492279875393, 0.45112781954887216],\n",
" [220, 185.85793838145366, 0.43609022556390975],\n",
" [230, 184.19828076777677, 0.47368421052631576],\n",
" [240, 183.70184218147062, 0.47368421052631576],\n",
" [250, 182.8491657534002, 0.47368421052631576],\n",
" [260, 180.94441716786105, 0.47368421052631576],\n",
" [270, 174.45480567201344, 0.47368421052631576],\n",
" [280, 170.03309010410015, 0.47368421052631576],\n",
" [290, 169.79950375737079, 0.47368421052631576],\n",
" [300, 169.68514382370628, 0.47368421052631576],\n",
" [310, 169.58441976319799, 0.47368421052631576],\n",
" [320, 169.3353189471139, 0.47368421052631576],\n",
" [330, 168.36830496114825, 0.47368421052631576],\n",
" [340, 156.42126306674979, 0.5488721804511278],\n",
" [350, 152.67394559851809, 0.5488721804511278],\n",
" [360, 148.77948662250174, 0.5639097744360902],\n",
" [370, 148.56661605062305, 0.5639097744360902],\n",
" [380, 148.35434190048989, 0.5639097744360902],\n",
" [390, 141.70923556269494, 0.556390977443609],\n",
" [400, 139.63493145836725, 0.5639097744360902],\n",
" [410, 135.25339355186716, 0.5639097744360902],\n",
" [420, 132.89962193267056, 0.5939849624060151],\n",
" [430, 129.94702206152613, 0.5939849624060151],\n",
" [440, 129.63402618887667, 0.5939849624060151],\n",
" [450, 129.34233423992214, 0.5939849624060151],\n",
" [460, 127.80703982616402, 0.5939849624060151],\n",
" [470, 127.60060165960947, 0.5939849624060151],\n",
" [480, 127.51480540540372, 0.5939849624060151],\n",
" [490, 127.37601266242373, 0.5939849624060151],\n",
" [500, 126.60014544226198, 0.6015037593984962]]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nettalk.get_history()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"application/javascript": [
"/* Put everything inside the global mpl namespace */\n",
"window.mpl = {};\n",
"\n",
"mpl.get_websocket_type = function() {\n",
" if (typeof(WebSocket) !== 'undefined') {\n",
" return WebSocket;\n",
" } else if (typeof(MozWebSocket) !== 'undefined') {\n",
" return MozWebSocket;\n",
" } else {\n",
" alert('Your browser does not have WebSocket support.' +\n",
" 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n",
" 'Firefox 4 and 5 are also supported but you ' +\n",
" 'have to enable WebSockets in about:config.');\n",
" };\n",
"}\n",
"\n",
"mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n",
" this.id = figure_id;\n",
"\n",
" this.ws = websocket;\n",
"\n",
" this.supports_binary = (this.ws.binaryType != undefined);\n",
"\n",
" if (!this.supports_binary) {\n",
" var warnings = document.getElementById(\"mpl-warnings\");\n",
" if (warnings) {\n",
" warnings.style.display = 'block';\n",
" warnings.textContent = (\n",
" \"This browser does not support binary websocket messages. \" +\n",
" \"Performance may be slow.\");\n",
" }\n",
" }\n",
"\n",
" this.imageObj = new Image();\n",
"\n",
" this.context = undefined;\n",
" this.message = undefined;\n",
" this.canvas = undefined;\n",
" this.rubberband_canvas = undefined;\n",
" this.rubberband_context = undefined;\n",
" this.format_dropdown = undefined;\n",
"\n",
" this.image_mode = 'full';\n",
"\n",
" this.root = $('');\n",
" this._root_extra_style(this.root)\n",
" this.root.attr('style', 'display: inline-block');\n",
"\n",
" $(parent_element).append(this.root);\n",
"\n",
" this._init_header(this);\n",
" this._init_canvas(this);\n",
" this._init_toolbar(this);\n",
"\n",
" var fig = this;\n",
"\n",
" this.waiting = false;\n",
"\n",
" this.ws.onopen = function () {\n",
" fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n",
" fig.send_message(\"send_image_mode\", {});\n",
" fig.send_message(\"refresh\", {});\n",
" }\n",
"\n",
" this.imageObj.onload = function() {\n",
" if (fig.image_mode == 'full') {\n",
" // Full images could contain transparency (where diff images\n",
" // almost always do), so we need to clear the canvas so that\n",
" // there is no ghosting.\n",
" fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n",
" }\n",
" fig.context.drawImage(fig.imageObj, 0, 0);\n",
" };\n",
"\n",
" this.imageObj.onunload = function() {\n",
" this.ws.close();\n",
" }\n",
"\n",
" this.ws.onmessage = this._make_on_message_function(this);\n",
"\n",
" this.ondownload = ondownload;\n",
"}\n",
"\n",
"mpl.figure.prototype._init_header = function() {\n",
" var titlebar = $(\n",
" '');\n",
" var titletext = $(\n",
" '');\n",
" titlebar.append(titletext)\n",
" this.root.append(titlebar);\n",
" this.header = titletext[0];\n",
"}\n",
"\n",
"\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(canvas_div) {\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._init_canvas = function() {\n",
" var fig = this;\n",
"\n",
" var canvas_div = $('');\n",
"\n",
" canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n",
"\n",
" function canvas_keyboard_event(event) {\n",
" return fig.key_event(event, event['data']);\n",
" }\n",
"\n",
" canvas_div.keydown('key_press', canvas_keyboard_event);\n",
" canvas_div.keyup('key_release', canvas_keyboard_event);\n",
" this.canvas_div = canvas_div\n",
" this._canvas_extra_style(canvas_div)\n",
" this.root.append(canvas_div);\n",
"\n",
" var canvas = $('');\n",
" canvas.addClass('mpl-canvas');\n",
" canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n",
"\n",
" this.canvas = canvas[0];\n",
" this.context = canvas[0].getContext(\"2d\");\n",
"\n",
" var rubberband = $('');\n",
" rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n",
"\n",
" var pass_mouse_events = true;\n",
"\n",
" canvas_div.resizable({\n",
" start: function(event, ui) {\n",
" pass_mouse_events = false;\n",
" },\n",
" resize: function(event, ui) {\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" stop: function(event, ui) {\n",
" pass_mouse_events = true;\n",
" fig.request_resize(ui.size.width, ui.size.height);\n",
" },\n",
" });\n",
"\n",
" function mouse_event_fn(event) {\n",
" if (pass_mouse_events)\n",
" return fig.mouse_event(event, event['data']);\n",
" }\n",
"\n",
" rubberband.mousedown('button_press', mouse_event_fn);\n",
" rubberband.mouseup('button_release', mouse_event_fn);\n",
" // Throttle sequential mouse events to 1 every 20ms.\n",
" rubberband.mousemove('motion_notify', mouse_event_fn);\n",
"\n",
" rubberband.mouseenter('figure_enter', mouse_event_fn);\n",
" rubberband.mouseleave('figure_leave', mouse_event_fn);\n",
"\n",
" canvas_div.on(\"wheel\", function (event) {\n",
" event = event.originalEvent;\n",
" event['data'] = 'scroll'\n",
" if (event.deltaY < 0) {\n",
" event.step = 1;\n",
" } else {\n",
" event.step = -1;\n",
" }\n",
" mouse_event_fn(event);\n",
" });\n",
"\n",
" canvas_div.append(canvas);\n",
" canvas_div.append(rubberband);\n",
"\n",
" this.rubberband = rubberband;\n",
" this.rubberband_canvas = rubberband[0];\n",
" this.rubberband_context = rubberband[0].getContext(\"2d\");\n",
" this.rubberband_context.strokeStyle = \"#000000\";\n",
"\n",
" this._resize_canvas = function(width, height) {\n",
" // Keep the size of the canvas, canvas container, and rubber band\n",
" // canvas in synch.\n",
" canvas_div.css('width', width)\n",
" canvas_div.css('height', height)\n",
"\n",
" canvas.attr('width', width);\n",
" canvas.attr('height', height);\n",
"\n",
" rubberband.attr('width', width);\n",
" rubberband.attr('height', height);\n",
" }\n",
"\n",
" // Set the figure to an initial 600x600px, this will subsequently be updated\n",
" // upon first draw.\n",
" this._resize_canvas(600, 600);\n",
"\n",
" // Disable right mouse context menu.\n",
" $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n",
" return false;\n",
" });\n",
"\n",
" function set_focus () {\n",
" canvas.focus();\n",
" canvas_div.focus();\n",
" }\n",
"\n",
" window.setTimeout(set_focus, 100);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items) {\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) {\n",
" // put a spacer in here.\n",
" continue;\n",
" }\n",
" var button = $('');\n",
" button.addClass('ui-button ui-widget ui-state-default ui-corner-all ' +\n",
" 'ui-button-icon-only');\n",
" button.attr('role', 'button');\n",
" button.attr('aria-disabled', 'false');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
"\n",
" var icon_img = $('');\n",
" icon_img.addClass('ui-button-icon-primary ui-icon');\n",
" icon_img.addClass(image);\n",
" icon_img.addClass('ui-corner-all');\n",
"\n",
" var tooltip_span = $('');\n",
" tooltip_span.addClass('ui-button-text');\n",
" tooltip_span.html(tooltip);\n",
"\n",
" button.append(icon_img);\n",
" button.append(tooltip_span);\n",
"\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" var fmt_picker_span = $('');\n",
"\n",
" var fmt_picker = $('');\n",
" fmt_picker.addClass('mpl-toolbar-option ui-widget ui-widget-content');\n",
" fmt_picker_span.append(fmt_picker);\n",
" nav_element.append(fmt_picker_span);\n",
" this.format_dropdown = fmt_picker[0];\n",
"\n",
" for (var ind in mpl.extensions) {\n",
" var fmt = mpl.extensions[ind];\n",
" var option = $(\n",
" '', {selected: fmt === mpl.default_extension}).html(fmt);\n",
" fmt_picker.append(option)\n",
" }\n",
"\n",
" // Add hover states to the ui-buttons\n",
" $( \".ui-button\" ).hover(\n",
" function() { $(this).addClass(\"ui-state-hover\");},\n",
" function() { $(this).removeClass(\"ui-state-hover\");}\n",
" );\n",
"\n",
" var status_bar = $('');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"}\n",
"\n",
"mpl.figure.prototype.request_resize = function(x_pixels, y_pixels) {\n",
" // Request matplotlib to resize the figure. Matplotlib will then trigger a resize in the client,\n",
" // which will in turn request a refresh of the image.\n",
" this.send_message('resize', {'width': x_pixels, 'height': y_pixels});\n",
"}\n",
"\n",
"mpl.figure.prototype.send_message = function(type, properties) {\n",
" properties['type'] = type;\n",
" properties['figure_id'] = this.id;\n",
" this.ws.send(JSON.stringify(properties));\n",
"}\n",
"\n",
"mpl.figure.prototype.send_draw_message = function() {\n",
" if (!this.waiting) {\n",
" this.waiting = true;\n",
" this.ws.send(JSON.stringify({type: \"draw\", figure_id: this.id}));\n",
" }\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" var format_dropdown = fig.format_dropdown;\n",
" var format = format_dropdown.options[format_dropdown.selectedIndex].value;\n",
" fig.ondownload(fig, format);\n",
"}\n",
"\n",
"\n",
"mpl.figure.prototype.handle_resize = function(fig, msg) {\n",
" var size = msg['size'];\n",
" if (size[0] != fig.canvas.width || size[1] != fig.canvas.height) {\n",
" fig._resize_canvas(size[0], size[1]);\n",
" fig.send_message(\"refresh\", {});\n",
" };\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_rubberband = function(fig, msg) {\n",
" var x0 = msg['x0'];\n",
" var y0 = fig.canvas.height - msg['y0'];\n",
" var x1 = msg['x1'];\n",
" var y1 = fig.canvas.height - msg['y1'];\n",
" x0 = Math.floor(x0) + 0.5;\n",
" y0 = Math.floor(y0) + 0.5;\n",
" x1 = Math.floor(x1) + 0.5;\n",
" y1 = Math.floor(y1) + 0.5;\n",
" var min_x = Math.min(x0, x1);\n",
" var min_y = Math.min(y0, y1);\n",
" var width = Math.abs(x1 - x0);\n",
" var height = Math.abs(y1 - y0);\n",
"\n",
" fig.rubberband_context.clearRect(\n",
" 0, 0, fig.canvas.width, fig.canvas.height);\n",
"\n",
" fig.rubberband_context.strokeRect(min_x, min_y, width, height);\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_figure_label = function(fig, msg) {\n",
" // Updates the figure title.\n",
" fig.header.textContent = msg['label'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_cursor = function(fig, msg) {\n",
" var cursor = msg['cursor'];\n",
" switch(cursor)\n",
" {\n",
" case 0:\n",
" cursor = 'pointer';\n",
" break;\n",
" case 1:\n",
" cursor = 'default';\n",
" break;\n",
" case 2:\n",
" cursor = 'crosshair';\n",
" break;\n",
" case 3:\n",
" cursor = 'move';\n",
" break;\n",
" }\n",
" fig.rubberband_canvas.style.cursor = cursor;\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_message = function(fig, msg) {\n",
" fig.message.textContent = msg['message'];\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_draw = function(fig, msg) {\n",
" // Request the server to send over a new figure.\n",
" fig.send_draw_message();\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_image_mode = function(fig, msg) {\n",
" fig.image_mode = msg['mode'];\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Called whenever the canvas gets updated.\n",
" this.send_message(\"ack\", {});\n",
"}\n",
"\n",
"// A function to construct a web socket function for onmessage handling.\n",
"// Called in the figure constructor.\n",
"mpl.figure.prototype._make_on_message_function = function(fig) {\n",
" return function socket_on_message(evt) {\n",
" if (evt.data instanceof Blob) {\n",
" /* FIXME: We get \"Resource interpreted as Image but\n",
" * transferred with MIME type text/plain:\" errors on\n",
" * Chrome. But how to set the MIME type? It doesn't seem\n",
" * to be part of the websocket stream */\n",
" evt.data.type = \"image/png\";\n",
"\n",
" /* Free the memory for the previous frames */\n",
" if (fig.imageObj.src) {\n",
" (window.URL || window.webkitURL).revokeObjectURL(\n",
" fig.imageObj.src);\n",
" }\n",
"\n",
" fig.imageObj.src = (window.URL || window.webkitURL).createObjectURL(\n",
" evt.data);\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
" else if (typeof evt.data === 'string' && evt.data.slice(0, 21) == \"data:image/png;base64\") {\n",
" fig.imageObj.src = evt.data;\n",
" fig.updated_canvas_event();\n",
" fig.waiting = false;\n",
" return;\n",
" }\n",
"\n",
" var msg = JSON.parse(evt.data);\n",
" var msg_type = msg['type'];\n",
"\n",
" // Call the \"handle_{type}\" callback, which takes\n",
" // the figure and JSON message as its only arguments.\n",
" try {\n",
" var callback = fig[\"handle_\" + msg_type];\n",
" } catch (e) {\n",
" console.log(\"No handler for the '\" + msg_type + \"' message type: \", msg);\n",
" return;\n",
" }\n",
"\n",
" if (callback) {\n",
" try {\n",
" // console.log(\"Handling '\" + msg_type + \"' message: \", msg);\n",
" callback(fig, msg);\n",
" } catch (e) {\n",
" console.log(\"Exception inside the 'handler_\" + msg_type + \"' callback:\", e, e.stack, msg);\n",
" }\n",
" }\n",
" };\n",
"}\n",
"\n",
"// from http://stackoverflow.com/questions/1114465/getting-mouse-location-in-canvas\n",
"mpl.findpos = function(e) {\n",
" //this section is from http://www.quirksmode.org/js/events_properties.html\n",
" var targ;\n",
" if (!e)\n",
" e = window.event;\n",
" if (e.target)\n",
" targ = e.target;\n",
" else if (e.srcElement)\n",
" targ = e.srcElement;\n",
" if (targ.nodeType == 3) // defeat Safari bug\n",
" targ = targ.parentNode;\n",
"\n",
" // jQuery normalizes the pageX and pageY\n",
" // pageX,Y are the mouse positions relative to the document\n",
" // offset() returns the position of the element relative to the document\n",
" var x = e.pageX - $(targ).offset().left;\n",
" var y = e.pageY - $(targ).offset().top;\n",
"\n",
" return {\"x\": x, \"y\": y};\n",
"};\n",
"\n",
"/*\n",
" * return a copy of an object with only non-object keys\n",
" * we need this to avoid circular references\n",
" * http://stackoverflow.com/a/24161582/3208463\n",
" */\n",
"function simpleKeys (original) {\n",
" return Object.keys(original).reduce(function (obj, key) {\n",
" if (typeof original[key] !== 'object')\n",
" obj[key] = original[key]\n",
" return obj;\n",
" }, {});\n",
"}\n",
"\n",
"mpl.figure.prototype.mouse_event = function(event, name) {\n",
" var canvas_pos = mpl.findpos(event)\n",
"\n",
" if (name === 'button_press')\n",
" {\n",
" this.canvas.focus();\n",
" this.canvas_div.focus();\n",
" }\n",
"\n",
" var x = canvas_pos.x;\n",
" var y = canvas_pos.y;\n",
"\n",
" this.send_message(name, {x: x, y: y, button: event.button,\n",
" step: event.step,\n",
" guiEvent: simpleKeys(event)});\n",
"\n",
" /* This prevents the web browser from automatically changing to\n",
" * the text insertion cursor when the button is pressed. We want\n",
" * to control all of the cursor setting manually through the\n",
" * 'cursor' event from matplotlib */\n",
" event.preventDefault();\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" // Handle any extra behaviour associated with a key event\n",
"}\n",
"\n",
"mpl.figure.prototype.key_event = function(event, name) {\n",
"\n",
" // Prevent repeat events\n",
" if (name == 'key_press')\n",
" {\n",
" if (event.which === this._key)\n",
" return;\n",
" else\n",
" this._key = event.which;\n",
" }\n",
" if (name == 'key_release')\n",
" this._key = null;\n",
"\n",
" var value = '';\n",
" if (event.ctrlKey && event.which != 17)\n",
" value += \"ctrl+\";\n",
" if (event.altKey && event.which != 18)\n",
" value += \"alt+\";\n",
" if (event.shiftKey && event.which != 16)\n",
" value += \"shift+\";\n",
"\n",
" value += 'k';\n",
" value += event.which.toString();\n",
"\n",
" this._key_event_extra(event, name);\n",
"\n",
" this.send_message(name, {key: value,\n",
" guiEvent: simpleKeys(event)});\n",
" return false;\n",
"}\n",
"\n",
"mpl.figure.prototype.toolbar_button_onclick = function(name) {\n",
" if (name == 'download') {\n",
" this.handle_save(this, null);\n",
" } else {\n",
" this.send_message(\"toolbar_button\", {name: name});\n",
" }\n",
"};\n",
"\n",
"mpl.figure.prototype.toolbar_button_onmouseover = function(tooltip) {\n",
" this.message.textContent = tooltip;\n",
"};\n",
"mpl.toolbar_items = [[\"Home\", \"Reset original view\", \"fa fa-home icon-home\", \"home\"], [\"Back\", \"Back to previous view\", \"fa fa-arrow-left icon-arrow-left\", \"back\"], [\"Forward\", \"Forward to next view\", \"fa fa-arrow-right icon-arrow-right\", \"forward\"], [\"\", \"\", \"\", \"\"], [\"Pan\", \"Pan axes with left mouse, zoom with right\", \"fa fa-arrows icon-move\", \"pan\"], [\"Zoom\", \"Zoom to rectangle\", \"fa fa-square-o icon-check-empty\", \"zoom\"], [\"\", \"\", \"\", \"\"], [\"Download\", \"Download plot\", \"fa fa-floppy-o icon-save\", \"download\"]];\n",
"\n",
"mpl.extensions = [\"eps\", \"jpeg\", \"pdf\", \"png\", \"ps\", \"raw\", \"svg\", \"tif\"];\n",
"\n",
"mpl.default_extension = \"png\";var comm_websocket_adapter = function(comm) {\n",
" // Create a \"websocket\"-like object which calls the given IPython comm\n",
" // object with the appropriate methods. Currently this is a non binary\n",
" // socket, so there is still some room for performance tuning.\n",
" var ws = {};\n",
"\n",
" ws.close = function() {\n",
" comm.close()\n",
" };\n",
" ws.send = function(m) {\n",
" //console.log('sending', m);\n",
" comm.send(m);\n",
" };\n",
" // Register the callback with on_msg.\n",
" comm.on_msg(function(msg) {\n",
" //console.log('receiving', msg['content']['data'], msg);\n",
" // Pass the mpl event to the overriden (by mpl) onmessage function.\n",
" ws.onmessage(msg['content']['data'])\n",
" });\n",
" return ws;\n",
"}\n",
"\n",
"mpl.mpl_figure_comm = function(comm, msg) {\n",
" // This is the function which gets called when the mpl process\n",
" // starts-up an IPython Comm through the \"matplotlib\" channel.\n",
"\n",
" var id = msg.content.data.id;\n",
" // Get hold of the div created by the display call when the Comm\n",
" // socket was opened in Python.\n",
" var element = $(\"#\" + id);\n",
" var ws_proxy = comm_websocket_adapter(comm)\n",
"\n",
" function ondownload(figure, format) {\n",
" window.open(figure.imageObj.src);\n",
" }\n",
"\n",
" var fig = new mpl.figure(id, ws_proxy,\n",
" ondownload,\n",
" element.get(0));\n",
"\n",
" // Call onopen now - mpl needs it, as it is assuming we've passed it a real\n",
" // web socket which is closed, not our websocket->open comm proxy.\n",
" ws_proxy.onopen();\n",
"\n",
" fig.parent_element = element.get(0);\n",
" fig.cell_info = mpl.find_output_cell(\"\");\n",
" if (!fig.cell_info) {\n",
" console.error(\"Failed to find cell for figure\", id, fig);\n",
" return;\n",
" }\n",
"\n",
" var output_index = fig.cell_info[2]\n",
" var cell = fig.cell_info[0];\n",
"\n",
"};\n",
"\n",
"mpl.figure.prototype.handle_close = function(fig, msg) {\n",
" fig.root.unbind('remove')\n",
"\n",
" // Update the output cell to use the data from the current canvas.\n",
" fig.push_to_output();\n",
" var dataURL = fig.canvas.toDataURL();\n",
" // Re-enable the keyboard manager in IPython - without this line, in FF,\n",
" // the notebook keyboard shortcuts fail.\n",
" IPython.keyboard_manager.enable()\n",
" $(fig.parent_element).html('![](\"')
');\n",
" fig.close_ws(fig, msg);\n",
"}\n",
"\n",
"mpl.figure.prototype.close_ws = function(fig, msg){\n",
" fig.send_message('closing', msg);\n",
" // fig.ws.close()\n",
"}\n",
"\n",
"mpl.figure.prototype.push_to_output = function(remove_interactive) {\n",
" // Turn the data on the canvas into data in the output cell.\n",
" var dataURL = this.canvas.toDataURL();\n",
" this.cell_info[1]['text/html'] = '';\n",
"}\n",
"\n",
"mpl.figure.prototype.updated_canvas_event = function() {\n",
" // Tell IPython that the notebook contents must change.\n",
" IPython.notebook.set_dirty(true);\n",
" this.send_message(\"ack\", {});\n",
" var fig = this;\n",
" // Wait a second, then push the new image to the DOM so\n",
" // that it is saved nicely (might be nice to debounce this).\n",
" setTimeout(function () { fig.push_to_output() }, 1000);\n",
"}\n",
"\n",
"mpl.figure.prototype._init_toolbar = function() {\n",
" var fig = this;\n",
"\n",
" var nav_element = $('')\n",
" nav_element.attr('style', 'width: 100%');\n",
" this.root.append(nav_element);\n",
"\n",
" // Define a callback function for later on.\n",
" function toolbar_event(event) {\n",
" return fig.toolbar_button_onclick(event['data']);\n",
" }\n",
" function toolbar_mouse_event(event) {\n",
" return fig.toolbar_button_onmouseover(event['data']);\n",
" }\n",
"\n",
" for(var toolbar_ind in mpl.toolbar_items){\n",
" var name = mpl.toolbar_items[toolbar_ind][0];\n",
" var tooltip = mpl.toolbar_items[toolbar_ind][1];\n",
" var image = mpl.toolbar_items[toolbar_ind][2];\n",
" var method_name = mpl.toolbar_items[toolbar_ind][3];\n",
"\n",
" if (!name) { continue; };\n",
"\n",
" var button = $('');\n",
" button.click(method_name, toolbar_event);\n",
" button.mouseover(tooltip, toolbar_mouse_event);\n",
" nav_element.append(button);\n",
" }\n",
"\n",
" // Add the status bar.\n",
" var status_bar = $('');\n",
" nav_element.append(status_bar);\n",
" this.message = status_bar[0];\n",
"\n",
" // Add the close button to the window.\n",
" var buttongrp = $('');\n",
" var button = $('');\n",
" button.click(function (evt) { fig.handle_close(fig, {}); } );\n",
" button.mouseover('Stop Interaction', toolbar_mouse_event);\n",
" buttongrp.append(button);\n",
" var titlebar = this.root.find($('.ui-dialog-titlebar'));\n",
" titlebar.prepend(buttongrp);\n",
"}\n",
"\n",
"mpl.figure.prototype._root_extra_style = function(el){\n",
" var fig = this\n",
" el.on(\"remove\", function(){\n",
"\tfig.close_ws(fig, {});\n",
" });\n",
"}\n",
"\n",
"mpl.figure.prototype._canvas_extra_style = function(el){\n",
" // this is important to make the div 'focusable\n",
" el.attr('tabindex', 0)\n",
" // reach out to IPython and tell the keyboard manager to turn it's self\n",
" // off when our div gets focus\n",
"\n",
" // location in version 3\n",
" if (IPython.notebook.keyboard_manager) {\n",
" IPython.notebook.keyboard_manager.register_events(el);\n",
" }\n",
" else {\n",
" // location in version 2\n",
" IPython.keyboard_manager.register_events(el);\n",
" }\n",
"\n",
"}\n",
"\n",
"mpl.figure.prototype._key_event_extra = function(event, name) {\n",
" var manager = IPython.notebook.keyboard_manager;\n",
" if (!manager)\n",
" manager = IPython.keyboard_manager;\n",
"\n",
" // Check for shift+enter\n",
" if (event.shiftKey && event.which == 13) {\n",
" this.canvas_div.blur();\n",
" event.shiftKey = false;\n",
" // Send a \"J\" for go to next cell\n",
" event.which = 74;\n",
" event.keyCode = 74;\n",
" manager.command_mode();\n",
" manager.handle_keydown(event);\n",
" }\n",
"}\n",
"\n",
"mpl.figure.prototype.handle_save = function(fig, msg) {\n",
" fig.ondownload(fig, null);\n",
"}\n",
"\n",
"\n",
"mpl.find_output_cell = function(html_output) {\n",
" // Return the cell and output element which can be found *uniquely* in the notebook.\n",
" // Note - this is a bit hacky, but it is done because the \"notebook_saving.Notebook\"\n",
" // IPython event is triggered only after the cells have been serialised, which for\n",
" // our purposes (turning an active figure into a static one), is too late.\n",
" var cells = IPython.notebook.get_cells();\n",
" var ncells = cells.length;\n",
" for (var i=0; i= 3 moved mimebundle to data attribute of output\n",
" data = data.data;\n",
" }\n",
" if (data['text/html'] == html_output) {\n",
" return [cell, data, j];\n",
" }\n",
" }\n",
" }\n",
" }\n",
"}\n",
"\n",
"// Register the function which deals with the matplotlib target/channel.\n",
"// The kernel may be null if the page has been refreshed.\n",
"if (IPython.notebook.kernel != null) {\n",
" IPython.notebook.kernel.comm_manager.register_target('matplotlib', mpl.mpl_figure_comm);\n",
"}\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"![](\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAYAAAA10dzkAAAgAElEQVR4Xu3dB5gdZdn/8W8ICRACoUhRKQIvJfQqTZpCQpUuRYpKJ1EhNM2f3kGKCJEOogTpIAJhAaUXX0hEKYISOkSEYBJ4gQSS/K8nMwuHZZOc3XvLnJnvXNchSzL3nHk+c5+TX6b2wEkBBRRQQAEFFFCgUgI9KjVaB6uAAgoooIACCiiAAdAmUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZgAKzYBne4CiiggAIKKKCAAdAeUEABBRRQQAEFKiZQtgB4GrAVsDjwAfAAcCTwRivbdQ3gMeBxYMMWf34CsC8wNzASGAQ8W7HecLgKKKCAAgooUFKBsgXAU4AbgaeBPsCFwPLAai2232zAE8C/gdlbBMAjgMHAFsBo4DhgL2AZ4MOS9oHDUkABBRRQQIEKCZQtALbcdKsAo4D5gPE1f3gWMEv+e99pEQBfAs4BLsjn7wm8BQwBhleoNxyqAgoooIACCpRUoOwBMB3+PRBYsmb7pcO9F+d7BY8CagNgOuQ7DlgX+EtNTVO+V/HwkvaBw1JAAQUUUECBCgmUOQBuCtwC7ADck2/TOYGngB8Aj+SHd2sD4CLAa0B/4IWaPrgWmADs36I3kt/XgPcr1DMOVQEFFFBAgTIIzJUf4ZtahsG0dQxlDYBbA78D9gZuq0G5CPgYOCT/vXR+X2QP4Nenc4FJW7eD8yuggAIKKKBA1wukHT9vdv3bdv87ljEAfj8/f29n4N4WxC8D/YDJ+e+nC0V65Yd91wHS+X+tnQM4Bji0lXMA0yHj8a+//jpzz51+rM40dOhQTj311OoMOB+p467WJnd7u72rIFDFPp8wYQKLLrpo2rwpE6QjfJWbyhYA09W7JwLb5Id4W27QBYFZa37zMGB9YHvgbWAKkM7zS8tJt5NJYfBYYA9g2VauAp4WAMePH1+5ADhkyBDOOSddK1OtyXG7vasgYJ9XYSt/PsYqbu8UAPv1S9nPAFiWbk8B7hNgYj6gFHDTsf10S5d0zl/LqeUh4OY/Px44AEjnBzw5g/sAGgDL0jl1jqOKX5SJxnHX2SAlmc3tXZINWecwqri9DYBQtj2AdbZ7h802LQC+99545p23WoeAm5qaGDhwYIdBNsqCHHejbKmOWU+3d8c4NspS3N6NsqXi62kANABGu2haAFxyyfEMHTo3e+4JvXtHF2m9AgoooIACCnSmgAHQABjtr2kB8MILx3PeeXPzwQdw2GGw334wZ7rhjJMCCiiggAIKFE7AAGgAjDblZ+cA9u07N7feCunC2FdegZ/+FAYPhnnnjb6F9QoooIACCijQkQIGQANgtJ++dBHI1Klw771w2mnwxBNw0EFw6KHw1a9G38p6BRRQQAEFFOgIAQOgATDaRzO8Cvjxx7MgePfd8IMfwBFHwJK1D6WLvrv1CiiggAIKKNBmAQOgAbDNTdOioK7bwDz9NJxxBtxwA2y/Pey+OwwYALPPHn176xVQQAEFFFCgrQIGQANgW3um5fx1BcDmopdegosugptugv/8B7bcEnbcMfu1b9/oqlivgAIKKKCAAvUIGAANgPX0yYzmaVMAbF5QOk/w73/PgmB6jR4N6ZZ6KQxus40XjkQ3ivUKKKCAAgrMSMAAaACMfkLaFQBbvunzz8PNN2evFAw32QR22AG22w4WWii6itYroIACCiigQK2AAdAAGP1EdEgArF2JdAuZ5jCYLiJZbz3YcENYeeXs9T//A7PWPs04OgLrFVBAAQUUqJiAAdAAGG35Dg+AtSs0Zgz84Q/Z7WTSnsFnnsn+dIUVPg+EKRSutBIssEB0KNYroIACCihQDQEDoAEw2umdGgBbrtzkyfDii1kYTK90dXH69eWXYeGFPw+Fm26anVPopIACCiiggAJfFjAAGgCjn4suDYDTW9kJE7K9gykM/u1v2e1mNt4YLrggC4ZOCiiggAIKKPC5gAHQABj9PBQiALYcRLrFTHoUXVMTnHMO7L039OgRHar1CiiggAIKlEPAAGgAjHZyIQNg86Buuy17FF06Z/CSS+Ab34gO13oFFFBAAQUaX8AAaACMdnGhA2Aa3PjxcOSRcM01cMopMGgQ9OwZHbb1CiiggAIKNK6AAdAAGO3ewgfA5gHedx/stx8suCBcdhksv3x06NYroIACCijQmAIGQANgtHMbJgCmgX74IRx3HAwbBkOHwlFHQa9eUQLrFVBAAQUUaCwBA6ABMNqxDRUAmweb7iu4zz7ZhSGXXw5rrhllsF4BBRRQQIHGETAAGgCj3dqQATANetIkOOMMOO00GDw4+9VzA6PtYL0CCiigQCMIGAANgNE+bdgA2Dzw556DLbaAk0+GPfeMclivgAIKKKBA8QUMgAbAaJc2fABMAOkWMeedlz1ZZJZZoiTWK6CAAgooUGwBA6ABMNqhpQiAEyfCEkvAhRfCtttGSaxXQAEFFFCg2AIGQANgtENLEQATwtlnw/XXw+OP+9SQaFNYr4ACCihQbAEDoAEw2qGlCYAffACLLQY33gjf/naUxXoFFFBAAQWKK2AANABGu7M0ATBBHH88PPII3HNPlMV6BRRQQAEFiitgADQARruzVAFw7FhYfHFITw1Za60ojfUKKKCAAgoUU8AAaACMdmapAmDCOOwwePlluPnmKI31CiiggAIKFFPAAGgAjHZm6QLgm2/CUkvBqFE+LzjaHNYroIACChRTwABoAIx2ZukCYALZb7/sSSFXXRXlsV4BBRRQQIHiCRgADYDRrixlAPzXv2ClleD55+Eb34gSWa+AAgoooECxBAyABsBoR5YyACaUXXeFr3wFLrggSmS9AgoooIACxRIwABoAox1Z2gD41FOw3nrZBSELLRRlsl4BBRRQQIHiCBgADYDRbixtAEwwW20Fq6wCp54aZbJeAQUUUECB4ggYAA2A0W4sdQB8+OEsBL72GvTrF6WyXgEFFFBAgWIIGAANgNFOLHUATDgbbABbbgk//3mUynoFFFBAAQWKIWAANABGO7H0AXDECNh7b3jlFejTJ8plvQIKKKCAAt0vYAA0AEa7sPQBcOpUWH112GcfGDw4ymW9AgoooIAC3S9gADQARruw9AEwAV13HRx5JLz4IvTqFSWzXgEFFFBAge4VMAAaAKMdWIkAOHkyLLccHH10djjYSQEFFFBAgUYWMAAaAKP9W4kAmJAuuwzOOQeeeQZmmSXKZr0CCiiggALdJ2AANABGu68yAXDiRFhyyezJINtvH2WzXgEFFFBAge4TMAAaAKPdV5kAmKDOPReuuQb+93+hR48onfUKKKCAAgp0j4AB0AAY7bxKBcAPPoDFF88uCtl00yid9QoooIACCnSPgAHQABjtvEoFwIR14onwwAPwpz9F6axXQAEFFFCgewQMgAbAaOdVLgC+9162F/DOO7OnhDgpoIACCijQaAIGQANgtGcrFwAT2KmnwjHHwMorZ4+J22ILWGcdmHXWKKf1CiiggAIKdL6AAdAAGO2ySgbAhPbuu3D33ZAeFXfXXfDppzBgQBYGN98cFl44Smu9AgoooIACnSNgADQARjursgGwFi7dKHrkyOywcAqETz4Jq66ahcG0h3DttaFnzyi19QoooIACCnSMgAHQABjtJANgK4LvvANNTVkYTL9OmZLdO/D886FPnyi59QoooIACCsQEDIAGwFgHgQFwJoJp7+ATT8ARR0DfvnDrrTDbbFF26xVQQAEFFGi/gAHQANj+7skqDYB1Ck6YAN/5Diy6KFx/vReM1MnmbAoooIACnSBgADQARtvKANgGwXQLmY03zq4e/u1vfaZwG+icVQEFFFCgAwUMgAbAaDsZANso+PbbsOGGWRC86CIfKddGPmdXQAEFFOgAAQNg+QLgacBWwOLAB8ADwJHAG3m/fBM4GlgLmAN4NT3iFvhNi346Adg3P8Q7EhgEPNtKzxkA2/FBfOON7CbS220H55xjCGwHoSUKKKCAAgEBA2D5AuApwI3A00C63vRCYHlgtbxPtgAWAO5Mt7IDNgb+AOwJ3JbPcwQwGEjzjgaOA/YClgE+bNFvBsB2fgBHj872BO6zT/Z4OScFFFBAAQW6SsAAWL4A2LJ3VgFGAfMB46fTWLcArwCH5n/+EnAOcEH+/+kOdm8BQ4DhBsCO+3j+4x9ZCDz8cDjqqI5brktSQAEFFFBgRgIGwPIHwHT490Bgyek0QtqD9zyQ4sfv8kO+44B1gb/U1DTlexUPNwB27JfKU0/BJpvASSfB4LTf1UkBBRRQQIFOFjAAljsAbgqkvXs7APe00ku98sO+6dcBwBRgEeA1oD/wQk3NtcAEYH8DYMd/Kh9/PHuM3HnnwQ9/2PHLd4kKKKCAAgrUChgAyxsAt8736O1dc25f7bZPF4CkcDgr8N2ac/vSHsE27wEcNGgQvXv3nrb8gQMHTns5tU3g/vth663h8sthl13aVuvcCiiggAIKzEygqamJ9ErTpEmTGDZsWPqxX76DZ2blpfvzHqUbEXw/P39vZ+DeVsY3D3BHfhHITsAnLeZp7RzAMfk5gp4D2IkNkx4dt9NOcO21sM02nfhGLloBBRRQoNIC7gEs3x7AdBZZuqY0xYdHWunuhfLDwemWLnsAk1uZJ53nl5aTbieTwuCx+bzLehVw539f3Hwz7LVX9si4TdNBfCcFFFBAAQU6WMAAWL4AmM7jS3v0Jua9kvZwTs1v6ZICYQpz6bYuzbdzSX+WpofywNfcYscDBwBzAU96H8AO/uTNZHFXXw0HHQTpsPAaa3Tte/tuCiiggALlFzAAli8AdnXXeh/AThI//nj44x/hf/8XeqYb8TgpoIACCijQQQIGQANgtJUMgFHB6dR//DGsuCIMGQIHH9xJb+JiFVBAAQUqKWAANABGG98AGBWcQX26KGT33eGFF2DBBTvxjVy0AgoooEClBAyABsBowxsAo4Izqd9+e5h3Xrjiik5+IxevgAIKKFAZAQOgATDa7AbAqOBM6l99FZZfHu65B9Zbr5PfzMUroIACClRCwABoAIw2ugEwKlhH/amnwg03wBNPwKzp1t1OCiiggAIKBAQMgAbAQPtMKzUARgXrqJ84EVZaCX784+zlpIACCiigQETAAGgAjPSPATCq14b69PSe9Ii4dEHIQul23k4KKKCAAgq0U8AAaABsZ+t8VuYewKhgG+rTY+LmnBOuuqoNRc6qgAIKKKBACwEDoAEw+qEwAEYF21D/+uvQvz+k28NssEEbCp1VAQUUUECBGgEDoAEw+oEwAEYF21h/xhkwfDiMGuUFIW2kc3YFFFBAgVzAAGgAjH4YDIBRwTbWT5oEK68MBx4IhxzSxmJnV0ABBRRQADAAGgCjHwQDYFSwHfX33gs77JBdEPLVr7ZjAZYooIACClRawABoAIx+AAyAUcF21qcrgnv1gquvbucCLFNAAQUUqKyAAdAAGG1+A2BUsJ31b74Jyy0Ht98OG23UzoVYpoACCihQSQEDoAEw2vgGwKhgoP6ss+A3v4G//jXbG+ikgAIKKKBAPQIGQANgPX0yo3kMgFHBQP0nn8Cqq8KPfgSHHRZYkKUKKKCAApUSMAAaAKMNbwCMCgbr77sPvvtdeP55+PrXgwuzXAEFFFCgEgIGQANgtNENgFHBDqjffXeYOhV+//sOWJiLUEABBRQovYAB0AAYbXIDYFSwA+rfeiu7IOTWW+Hb3+6ABboIBRRQQIFSCxgADYDRBjcARgU7qP688+AXv4CmJlhhhQ5aqItRQAEFFCilgAHQABhtbANgVLCD6tMh4BNOgBQEb7vNZwV3EKuLUUABBUopYAA0AEYb2wAYFezg+ksugSFD4Le/zZ4W4qSAAgoooEBLAQOgATD6qTAARgU7oT7tAUwXhpxxBgwa1Alv4CIVUEABBRpawABoAIw2sAEwKthJ9Y8+CttsAwceCCefDD16dNIbuVgFFFBAgYYTMAAaAKNNawCMCnZifbo34MCB2ZXB6dCwTwvpRGwXrYACCjSQgAHQABhtVwNgVLCT69MtYrbYIrtJ9PXXQ9++nfyGLl4BBRRQoPACBkADYLRJDYBRwS6oHz8ett8e3n8f7rgDFlywC97Ut1BAAQUUKKyAAdAAGG1OA2BUsIvqJ06EvfeGkSPhrrtgqaW66I19GwUUUECBwgkYAA2A0aY0AEYFu7B+yhQ4/HAYPhzuvBPWWKML39y3UkABBRQojIAB0AAYbUYDYFSwG+rPPju7afSNN8KAAd2wAr6lAgoooEC3ChgADYDRBjQARgW7qf6aa2C//eDxx2GllbppJXxbBRRQQIFuETAAGgCjjWcAjAp2Y/3BB0O6QCQdEnZSQAEFFKiOgAHQABjtdgNgVLAb619+Gfr3h+eegyWX7MYV8a0VUEABBbpUwABoAIw2nAEwKtjN9XvsAXPNBRde2M0r4tsroIACCnSZgAHQABhtNgNgVLCb659+Gr75TUh7AxdeuJtXxrdXQAEFFOgSAQOgATDaaAbAqGAB6tMzg1dYAU4/vQAr4yoooIACCnS6gAHQABhtMgNgVLAA9Y8+CptvDq+9BvPMU4AVchUUUEABBTpVwABoAIw2mAEwKliQ+o02goEDYejQgqyQq6GAAgoo0GkCBkADYLS5DIBRwYLUp8fD7bUXvPIK9OlTkJVyNRRQQAEFOkXAAGgAjDaWATAqWJD6qVNh9dVhn31g8OCCrJSroYACCijQKQIGQANgtLEMgFHBAtVfdx0ceSS8+CL06lWgFXNVFFBAAQU6VMAAaACMNpQBMCpYoPrJk2G55eDYY2HPPQu0Yq6KAgoooECHChgADYDRhjIARgULVn/ppfDLX0K6P+AssxRs5VwdBRRQQIEOETAAGgCjjWQAjAoWrH7ixOyxcL/+NWy7bcFWztVRQAEFFOgQAQOgATDaSAbAqGAB688+G264AR57DHr0KOAKukoKKKCAAiEBA6ABMNRAgAEwKljA+vffh8UXh5tugk02KeAKukoKKKCAAiEBA6ABMNRABsAoX3Hr04Ugjz8Od99d3HV0zRRQQAEF2idgADQAtq9zPq9yD2BUsKD1776b7QV88EFYY42CrqSrpYACCijQLgEDoAGwXY1TU2QAjAoWuP6QQ+DNN7PzAZ0UUEABBcojYAA0AEa72QAYFSxw/euvw9JLw9/+BssuW+AVddUUUEABBdokYAA0ALapYVqZ2QAYFSx4/Q9/mN0P8PLLC76irp4CCiigQN0CBkADYN3NMp0ZDYBRwYLXP/88rLpq9ni4RRYp+Mq6egoooIACdQkYAA2AdTXKDGYyAEYFG6B+xx1hscXg3HMbYGVdRQUUUECBmQoYAA2AM22SmcxgAIwKNkD9k0/CxhvDq6/C/PM3wAq7igoooIACMxQwAJYvAJ4GbAUsDnwAPAAcCbxR0wkrA+cD6eYe44BLgRNadEr6/33z+/yNBAYBz7bSTQbAinzJbLYZrL8+HH98RQbsMBVQQIESCxgAyxcATwFuBJ4G+gAXAssDq+V93Bf4J3AFcCKwDDACOAs4L5/nCGAwsAUwGjgO2Cuf98MWnwcDYIm/IGqH9uc/w047wWuvQd/URU4KKKCAAg0rYAAsXwBs2YyrAKOA+YDxwN7AGcDXgCn5zD8Bfgwsnf//S8A5wAX5//cE3gKGAMMNgA37eQ+t+NSpsPba2e1gTjwRllgitDiLFVBAAQW6UcAAWP4AmA7/HggsmfdZCnb98717za23LvAw0A+YJT8snH7vLzW92ZTvVTzcANiNn9hufut//AOOOQZuuw0GDIBBg2DgwOw2MU4KKKCAAo0jYAAsdwDcFLgF2AG4J2/Ly4A5gd1q2nS5/Py+RfMA+FoeEl+omedaYAKwvwGwcT7gnbWmb7wBl1ySvdLh4IMOgnS/wPnSfmYnBRRQQIHCCxgAyxsAtwZ+lx/yva2mEztlD+CgQYPo3bv3tLcZOHDgtJdT+QUmTYKbb4Zhw2DkSNhtt2yv4Oqrl3/sjlABBRRoNIGmpibSK02TJk1iWPryzo7+pR08lZt6lHDE38/P39sZuLfF+NLFHGe2OAfwp/lFHzM6B3AMcKjnAJawWzpoSOlxcb/+NVx9NayyShYE00Ujs83WQW/gYhRQQAEFOkzAPYDl2wOYrt5NV/duAzzSSqek6zfTod10FXC6YjiFvjuAs2uuAk7n+aXlpNvJpAtCjgX2ANLTYL0KuMM+fuVc0LhxcNVVWRhMPw8ZAkcdVc6xOioFFFCgUQUMgOULgOnK3k+AiXlTpj2cU/OLPpoD4YrAr/P7AKYrg9OtYk5q0cTpbm8HAHMBT3ofwEb9iHffek+ZAvfeC1ttBaNHZ08ScVJAAQUUKIaAAbB8AbCrO8v7AHa1eIO930YbZecGHpiuRXdSQAEFFCiEgAHQABhtRANgVLDk9WeeCQ89BH/8Y8kH6vAUUECBBhIwABoAo+1qAIwKlrz+2WdhrbVg7FiYY46SD9bhKaCAAg0iYAA0AEZb1QAYFSx5fXqCSHpqSLooZMstSz5Yh6eAAgo0iIAB0AAYbVUDYFSwAvWDB0MKgtktp5wUUEABBbpbwABoAIz2oAEwKliB+hEjsqeFvPwy9CjjnTcrsA0dogIKlEvAAGgAjHa0ATAqWIH6jz6C+eeHJ56AFVaowIAdogIKKFBwAQOgATDaogbAqGBF6rfZBr71LW8KXZHN7TAVUKDgAgZAA2C0RQ2AUcGK1F90EVxzDTz4YEUG7DAVUECBAgsYAA2A0fY0AEYFK1L/+uvZ1cDvvAPzzluRQTtMBRRQoKACBkADYLQ1DYBRwQrVr7IK/PznsOuuFRq0Q1VAAQUKKGAANABG29IAGBWsUP3QoZD2BP7udxUatENVQAEFCihgADQARtvSABgVrFD9I4/AttvC229Dz54VGrhDVUABBQomYAA0AEZb0gAYFaxQ/eTJsOCC2XOB11uvQgN3qAoooEDBBAyABsBoSxoAo4IVq99jD1h8cTjllIoN3OEqoIACBRIwABoAo+1oAIwKVqz+97+HM86Ap56q2MAdrgIKKFAgAQOgATDajgbAqGDF6t97LzsM/MorsMgiFRu8w1VAAQUKImAANABGW9EAGBWsYP0GG8Cee8L++1dw8A5ZAQUUKICAAdAAGG1DA2BUsIL1p58Ojz4Kt91WwcE7ZAUUUKAAAgZAA2C0DQ2AUcEK1j/zDKy9NowdC7PPXkEAh6yAAgp0s4AB0AAYbUEDYFSwgvVTp8I3vgEXXwybb15BAIesgAIKdLOAAdAAGG1BA2BUsKL1Bx+c3Qz6/PMrCuCwFVBAgW4UMAAaAKPtZwCMCla0/o474Mc/htGjoUePiiI4bAUUUKCbBAyABsBo6xkAo4IVrf/wQ5h/fhg5EpZfvqIIDlsBBRToJgEDoAEw2noGwKhgheu33ho22giOOKLCCA5dAQUU6AYBA6ABMNp2BsCoYIXrL7wQrrsO7r+/wggOXQEFFOgGAQOgATDadgbAqGCF6197DZZaCt55B+aZp8IQDl0BBRToYgEDoAEw2nIGwKhgxetXWgmOOQa+972KQzh8BRRQoAsFDIAGwGi7GQCjghWv/9nPYMwYuOqqikM4fAUUUKALBQyABsBouxkAo4IVr3/4Ydh+e/j3v7P7AjopoIACCnS+gAHQABjtMgNgVLDi9Z9+CgsuCHfeCeusU3EMh6+AAgp0kYAB0AAYbTUDYFTQenbfPbsY5KSTxFBAAQUU6AoBA6ABMNpnBsCooPUMHw5nnw2jRomhgAIKKNAVAgZAA2C0zwyAUUHrGTsWFloIXn0Vvv51QRRQQAEFOlvAAGgAjPaYATAqaP00gfXXhx/8APbbTxAFFFBAgc4WMAAaAKM9ZgCMClo/TeC00+Avf4FbbxVEAQUUUKCzBQyABsBojxkAo4LWTxP4+99hvfWYdjh4ttlEUUABBRToTAEDoAEw2l8GwKig9dMEpk6FxRaDyy+HAQNEUUABBRToTAEDoAEw2l8GwKig9Z8JHHhgtvfvvPNEUUABBRToTAEDoAEw2l8GwKig9Z8J/PGPcMgh8OKL0KOHMAoooIACnSVgADQARnvLABgVtP4zgQ8/hPnnzy4GWXllYRRQQAEFOkvAAGgAjPaWATAqaP0XBH7yE7j0UthlF0g/r766QAoooIACHS1gADQARnvKABgVtP5LAs89BxdcAFddBautBj/+MeywA/TqJZYCCiigQBUpCCAAACAASURBVEcIGAANgNE+MgBGBa2frsC4cXDFFVkYnDgRDjoI9t8fFlxQNAUUUECBiIAB0AAY6Z9UawCMClo/U4HJk+HOO+FXv4KHHoJdd832Cq6xxkxLnUEBBRRQoBUBA6ABMPrBMABGBa1vk0Dt4eFVV83OE/TwcJsInVkBBRTAAGgAjH4MDIBRQevbJdB8eHjYMBgzBpZYInt94xuf/9z8e/PM0663sEgBBRQorYAB0AAYbW4DYFTQ+pBAOjz8wgvw8sufv1555fOfU1Ds1++LoXDJJbPDx+kCEx87F+K3WAEFGlTAAGgAjLauATAqaH2nCqQAmMJhbShMN5p+4gl4//3sNjPrrAPrrpv9uuii3oS6UzeIC1dAgUIIGAANgNFGNABGBa3vFoH07OHRo+Hxx+Gxx7Jf//a37Arj2kCY9hT26dMtq+ibKqCAAp0mYAA0AEabywAYFbS+MALpSSQjR34eCFMwfOcdWGUV2Hbb7IITzycszOZyRRRQICBgADQABtpnWqkBMCpofWEF0l7C116DRx+FSy6BUaPgpz/Nnlc833yFXW1XTAEFFJipgAHQADjTJpnJDAbAqKD1DSOQ7kF40knZHsLBg2HIEFhggYZZfVdUAQUU+EzAAGgAjH4cDIBRQesbTiAFwBQEH3wwezrJ4YfDQgs13DBcYQUUqLCAAdAAGG1/A2BU0PqGFUhXEqcgeO+9cMABcMQR8LWvNexwXHEFFKiQgAGwfAFwF2AQsArQF+gFTKnp6e8DRwGLAxOAG4EjgU9q5jkB2Dc/v29kvrxnp/O5MABW6AvDobYu8Ne/ZkFwxAjYd1846ihYZBG1FFBAgeIKGADLFwA3A9Lp6enGFZe1CIArA38FUkhMwW9RoAm4GTg6b9MjgMHAFsBo4DhgL2AZ4MNWWtkAWNzPt2vWxQJPPw0nnwy33ZbtETz3XO8p2MWbwLdTQIE6BQyA5QuAzZt+I+DPLQLgdsDlwPw1/fELYHlgq/z3XgLOAS7I/78n8BYwBBhuAKzzk+VslRZIzyseMABOPx322KPSFA5eAQUKKmAArFYAnAO4D/gVcC2wBHAHcCZwRX7IdxywLvCXmp5NewmfBg43ABb0k+xqFU7guuuy28Wkx9TNnfaTOymggAIFEjAAVisAptbbDzgjPz8w7d37LfAjYCqQzlp6DegPvFDTpykspvMF9zcAFujT66oUWiDdQ3DTTbObSJ+T9qk7KaCAAgUSMABWKwDuDfwS2Bp4BEg3rkjnCX4A7BbZAzho0CB69+49rbUHDhw47eWkQNUF0qHg9Ci5dLXwiitWXcPxK6BAdws0NTWRXmmaNGkSw4YNSz/2y3fydPfqdfn79+jyd+yaN2ztHMB06Ddd+LF9zSpskx8OnjP/vdbOARwDHOo5gF2z4XyXcgkcdlj2eLn77vOCkHJtWUejQGMLuAewfHsAZ8kv/EgBcAQwFzA5hX1gJ+BCIIW+x4D0DIO0B3AeIM2fpnSeX7oKOF0UksLgsUA6jX1ZrwJu7A+7a989AhMmwLLLZlcE77pr96yD76qAAgq0FDAAli8ApsO8V+bn9KXtnfZwpvP7NgEeBH4MHAx8Ffgo/70U+l6vaY7jgQPy8Pik9wH0i0OBmMDw4XDkkfD88zBX+ieZkwIKKNDNAgbA8gXArm4p7wPY1eK+X8MJpAtCNt4Y1l4bzkzX3DspoIAC3SxgADQARlvQABgVtL4SAukm0SkApvMB+6fr7J0UUECBbhQwABoAo+1nAIwKWl8ZgXRfwGeegXvu8YKQymx0B6pAQQUMgAbAaGsaAKOC1ldGYNy47IKQdOeFndIlWU4KKKBANwkYAA2A0dYzAEYFra+UwFVXwTHHwD/+AXM233ypUgIOVgEFiiBgADQARvvQABgVtL5SAlOmwAYbwEYbwamnVmroDlYBBQokYAA0AEbb0QAYFbS+cgJPPQXrrQfp12WWqdzwHbACChRAwABoAIy2oQEwKmh9JQUGD4YXX4QRI7wgpJIN4KAV6GYBA6ABMNqCBsCooPWVFPjvf7MLQi65BLbbrpIEDloBBbpRwABoAIy2nwEwKmh9ZQWuuAJOPBGeew769KksgwNXQIFuEDAAGgCjbWcAjApaX1mBdEFIOhdwwIAsCDopoIACXSVgADQARnvNABgVtL7SAk8+CRtuCOlJIUstVWkKB6+AAl0oYAA0AEbbzQAYFbS+8gIHHghvvAG33155CgEUUKCLBAyABsBoqxkAo4LWV15g7NjsdjAXXAC77VZ5DgEUUKALBAyABsBomxkAo4LWKwDccQfssgs0NcH660uigAIKdK6AAdAAGO0wA2BU0HoFcoGLL4ahQ+HRR7NbxDgpoIACnSVgADQARnvLABgVtF6BGoEUAK+9Fh57DBZaSBoFFFCgcwQMgAbAaGcZAKOC1itQI5BuDbPnnvCvf8F998Gcc8qjgAIKdLyAAdAAGO0qA2BU0HoFWghMnAgDB8Lcc8Mtt0DPnhIpoIACHStgADQARjvKABgVtF6BVgTSo+K+9S3YeOPs6uAePWRSQAEFOk7AAGgAjHaTATAqaL0C0xF49VVYZx0YMgSOOEImBRRQoOMEDIAGwGg3GQCjgtYrMAOBUaOyvYCXXprdJsZJAQUU6AgBA6ABMNpHBsCooPUKzERgxAjYaSe46y7YYAO5FFBAgbiAAdAAGO0iA2BU0HoF6hBIewCPOgoeeQT696+jwFkUUECBGQgYAA2A0Q+IATAqaL0CdQocfTQMH57dI3DhhesscjYFFFCgFQEDoAEw+sEwAEYFrVegToGpU2GvveAf/4AHHvAegXWyOZsCChgAW+0Bb64Q+2gYAGN+VivQJoFJk2DzzaFPH7j1Vph11jaVO7MCCigwTcA9gO4BjH4UDIBRQesVaKPAuHHZPQIXWCA7H7BfP5hnni/+2vL3UmD0XoJthHZ2BUosYAA0AEbb2wAYFbRegXYIvPUW/O53kMJgeo0f//mvtT9/8EG28PQ0kRQK55gDZp8dZput9V9b/lmar/nVu3f2c/OvtT83/16qT2F03nmzX9P/OymgQPEEDIAGwGhXGgCjgtYr0IkCn36aDvV8HhA//hjSo+Zqf23t99I8H30E6ZBz+jm9pvdz7Z+lmhRAP/wwG1TLQNgcDGt/XXllWG89z2nsxDZw0Qp8ScAAaACMfiwMgFFB6xUooUAKhSkIpkfaNe+lbP659texY+HJJyHt0Vxrreym1+mVAmHfviWEcUgKFETAAGgAjLaiATAqaL0CCvDKK3D//dkrXeH8xhsGQttCgc4UMAAaAKP9ZQCMClqvgAJfEkiBMAXB5lCYAuGaa2Z7B3ffHVZaSTQFFIgIGAANgJH+SbUGwKig9QooMFOB5kB4222Qno/80kte1TxTNGdQYAYCBkADYPQDYgCMClqvgAJ1C6QLVtLtb9LewdVXr7vMGRVQoIWAAdAAGP1QGACjgtYroECbBNIh4CWWgFNOaVOZMyugQI2AAdAAGP1AGACjgtYroECbBG66Cf7f/8seiefNrdtE58wKfCZgADQARj8OBsCooPUKKNAmgf/7v+ww8BNPwAortKnUmRVQIBcwABoAox8GA2BU0HoFFGizwI47QrqB9HHHtbnUAgUU8FnA03qgh50QEjAAhvgsVkCB9ghccw2cfjr8/e/tqbZGAQXcA2gAjH4KDIBRQesVUKDNAunxdukw8DPPwNJLt7ncAgUqL2AANABGPwQGwKig9Qoo0C6BrbeGb30LfvazdpVbpEClBQyABsDoB8AAGBW0XgEF2iVw5ZXw619nF4M4KaBA2wQMgAbAtnXMl+c2AEYFrVdAgXYJjB0LCy8ML74Iiy/erkVYpEBlBQyABsBo8xsAo4LWK6BAuwU22wy23BIOPbTdi7BQgUoKGAANgNHGNwBGBa1XQIF2C1x0EVx9NTz8cLsXYaEClRQwABoAo41vAIwKWq+AAu0W+Pe/YZFF4PXX4atfbfdiLFSgcgIGQANgtOkNgFFB6xVQICSw4Yaw665w8MGhxVisQKUEDIAGwGjDGwCjgtYroEBI4Lzz4Lbb4E9/Ci3GYgUqJWAANABGG94AGBW0XgEFQgLp8O+SS8KYMfCVr4QWZbEClREwABoAo81uAIwKWq+AAmGBtdeG/feHffYJL8oFKFAJAQOgATDa6AbAqKD1CigQFjjzTLj/frjzzvCiXIAClRAwABoAo41uAIwKWq+AAmGB0aOhf3/4z39gnnnCi3MBCpRewABoAIw2uQEwKmi9Agp0iMCqq8Lhh8Mee3TI4lyIAqUWMAAaAKMNbgCMClqvgAIdInDSSTBqFNxyS4cszoUoUGoBA2D5AuAuwCBgFaAv0AuYUtPFvYHjgd2BdL3cO8AxwNU185wA7AukcDcyX96z0/kkGABL/RXh4BRoHIHnnoM11oB33oG+6dvPSQEFpitgACxfANwMmA/oA1zWSgC8DZgNOBB4OQ+B8wL/yrvkCGAwsAUwGjgO2AtYBviwlU4yAPoFo4AChRFI5wGeeCLsvHNhVskVUaCQAgbA8gXA5kbbCPhziwD4HSAFwMWBd6fTkS8B5wAX5H/eE3gLGAIMNwAW8nPsSimgQC5w9NHw4otw7bWSKKDAjAQMgNUKgKcB2wB35YeAPwHSvfPTXr+x+SHfccC6wF9qGqcJeBo43ADoF4oCChRZ4K9/hQ02yA4DzzFHkdfUdVOgewUMgNUKgJcC6Tap5wNHAXPle/U+BbYEFgFeA/oDL9S0Zvq39ARgfwNg935gfXcFFJixwNSpsNRScO65sO22aimgwPQEDIDVCoBnAz/NLw75OG+KdYCH899LF4i0aw/goEGD6N07lcPAgQOnvZwUUECB7hA44gh4+2347W+74919TwWKK9DU1ER6pWnSpEkMGzYs/dgv38lT3BXvpDXr0UnL7e7FtnYO4PeB3+R7/poDYDrc+2B++PcjoLVzAMcAh3oOYHdvUt9fAQXqEXj8cdh88+ym0Pm/S+spcx4FKiXgHsDy7QGcJb/wIwXAEXnYm5zCPpDOiPkHcBPw83yvX7qwI4XB7fLOT+f5pauAt8rD4LFAuq3qsl4FXKnvBgerQMMKTJkCiy0Gl12WBUEnBRT4soABsHwBcG/gSmBqvrnTHs708yb5nr50O5d0hW/a8zceuCM/HzAd+m2e0n0CD8jD45PeB9CvDgUUaDSBn/wEPvoILk1nPjspoMCXBAyA5QuAXd3m3gewq8V9PwUUmKnAAw/ATjvBmDEw66wznd0ZFKicgAHQABhtegNgVNB6BRTocIHJk+FrX8vuB7hJOv7hpIACXxAwABoAox8JA2BU0HoFFOgUgQMOgF694ILm29p3yru4UAUaU8AAaACMdq4BMCpovQIKdIrAPffA3nvDG2/ALOnyOCcFFPhMwABoAIx+HAyAUUHrFVCgUwQ++QQWWghuvx3WW69T3sKFKtCwAgZAA2C0eQ2AUUHrFVCg0wR++EOYbz44O90G30kBBdwDWNMDZb0RdFe1uQGwq6R9HwUUaLNA2vs3eDC8/DL08Nu+zX4WlFfAPYDuAYx2twEwKmi9Agp0msDEibDIInDkkZAeEeekgAKZgAHQABj9LBgAo4LWK6BApwqMGgWbbQaHHgpHH92pb+XCFWgYAQOgATDarAbAqKD1CijQ6QJPPw2bbgr77QcnneTh4E4H9w0KL2AANABGm9QAGBW0XgEFukTg+efhO9+BXXeFs84yBHYJum9SWAEDoAEw2pwGwKig9Qoo0GUCo0fDt78NW28N55/v/QG7DN43KpyAAdAAGG1KA2BU0HoFFOhSgVdfzULgxhvDJZdAz55d+va+mQKFEDAAGgCjjWgAjApar4ACXS7w5pvZ4eA114Tf/AZmnbXLV8E3VKBbBQyABsBoAxoAo4LWK6BAtwi8/XZ2Ychyy8Hw4dC7d7eshm+qQLcIGAANgNHGMwBGBa1XQIFuE3j3XRgwILtX4PXXw+yzd9uq+MYKdKmAAdAAGG04A2BU0HoFFOhWgf/+F7bYAvr1g1tugT59unV1fHMFukTAAGgAjDaaATAqaL0CCnS7wIQJsNVW2bmAf/wj9O3b7avkCijQqQIGQANgtMEMgFFB6xVQoBAC//d/8N3vwscfw513ZnsEnRQoq4AB0AAY7W0DYFTQegUUKIzARx/BjjvC2LFw992GwMJsGFekwwUMgAbAaFMZAKOC1iugQKEE0h7AHXaA996DpiZDYKE2jivTYQIGQANgtJkMgFFB6xVQoHACKQRuvz2MG5eFwLnTN52TAiUSMAAaAKPtbACMClqvgAKFFGgOgePHw113GQILuZFcqXYLGAANgO1unrzQABgVtF4BBQorkELgttvCBx9kIXCuuQq7qq6YAm0SMAAaANvUMK3MbACMClqvgAKFFkgXhqQQmK4SNgQWelO5cm0QMAAaANvQLq3OagCMClqvgAKFF2gOgR9+CCNGuCew8BvMFZypgAHQADjTJpnJDAbAqKD1CijQEAIpBDbfJzCFQG8W3RCbzZWcjoAB0AAY/XAYAKOC1iugQMMIpD2AKQROmpTdLNoQ2DCbzhVtIWAANABGPxQGwKig9Qoo0FACKQRusw18+inccYchsKE2niv7mYAB0AAY/TgYAKOC1iugQMMJpBC49dYwZUoWAuecs+GG4ApXXMAAaACMfgQMgFFB6xVQoCEF0lXBKQSm6fbbDYENuRErvNIGQANgtP0NgFFB6xVQoGEFmkNguln0N7+ZPTYuPTVkZq8+faBHj4YdtiteAgEDoAEw2sYGwKig9Qoo0NACKQRecgm8+y5MmPD5K4XC2v9PP6cridM0yywzD4ktQ+Rqq8H//E9DU7nyBRIwABoAo+1oAIwKWq+AApUR+OQTeP99SOEw/doyIE7v/997D159Ff75T5h33spwOdBOFDAAGgCj7WUAjApar4ACCsxEYOpUGDgQll8efvlLuRSICxgADYDRLjIARgWtV0ABBeoQeO45WGMNGDkyC4JOCkQEDIAGwEj/pFoDYFTQegUUUKBOgUMPhWeegbvv9iKSOsmcbToCBkADYPTDYQCMClqvgAIK1Ckwbhwss0x20cl229VZ5GwKtCJgADQARj8YBsCooPUKKKBAGwQuvRROOw3SIeHZZ29DobMqUCNgADQARj8QBsCooPUKKKBAGwQmT4a11oKddoKhQ9tQ6KwKGAC/0APeijP2kTAAxvysVkABBdos8Mgj2VXBzz8PiyzS5nILFMA9gO4BjH4MDIBRQesVUECBdgh8//tZ0fDh7Si2pPICBkADYPRDYACMClqvgAIKtEPgjTdgueWgqQnWX78dC7Ck0gIGQANg9ANgAIwKWq+AAgq0U+DUU+HGG+GJJ6Bnz3YuxLJKChgADYDRxjcARgWtV0ABBdop8PHHsMIK8LOfwX77tXMhllVSwABoAIw2vgEwKmi9AgooEBC49dYs/P3rXzDPPIEFWVopAQOgATDa8AbAqKD1CiigQECg+TnBaU/guecGFmRppQQMgAbAaMMbAKOC1iuggAJBAZ8THASsYLkB0AAYbXsDYFTQegUUUKADBA45JHs6SLoquId3uO0A0XIvwgBoAIx2uAEwKmi9Agoo0AEC6TnBSy8Nl10G227bAQt0EaUWMAAaAKMNbgCMClqvgAIKdJBAek7w6afDs8/6nOAOIi3tYgyABsBocxsAo4LWK6CAAh0k4HOCOwiyAosxABoAo21uAIwKWq+AAgp0oMDDD8Pmm8MLL8DXv96BC3ZRpRIwABoAow1tAIwKWq+AAgp0sEB6TnC6EOTqqzt4wS6uNAIGQANgtJkNgFFB6xVQQIEOFnjzTejfH3bcEU44ARZbrIPfwMU1vIABsHwBcBdgELAK0BfoBUxppVPXAB4DHgc2bPHnJwD7AincjcyX9+x0ut0A2PBfAw5AAQXKKPDSS3DMMXDLLXDQQTB0KMw/fxlH6pjaI2AALF8A3AyYD+gDXDadADgb8ATwb2D2FgHwCGAwsAUwGjgO2AtYBviwlSYzALbnk2eNAgoo0EUCTz0FP/85PPooHHkkpPsFzjlnF725b1NYAQNg+QJgc7NtBPx5OgHwLGAWYDzwnRYB8CXgHOCCfEE9gbeAIcBwA2BhP8uumAIKKDBDgfvvh6OOgtdeg2OPhX33hV7pGJFTJQUMgNULgOlw78XAasBRLQJg2ps3DlgX+EvNJ6IJeBo43ABYye8JB62AAiURSM8NToeE0+HgdMuYk0+GnXeGWdIuAadKCRgAqxUA007/p4AfAI/kh3dr9wAuArwG9AdeqPkkXAtMAPY3AFbq+8HBKqBASQU+/RR+8xs4/nhYeOHs5tGbblrSwTqsVgUMgNUKgBcBHwOH5N2Qzu+rDYDt3gM4aNAgevfuPW2xAwcOnPZyUkABBRQotsBHH8H558Npp8Gaa8J558Hyyxd7nV279gs0NTWRXmmaNGkSw4YNSz/2y3fytH/BDVpZ1kdmt3YO4Mv5hp6cb6t0oUg6AyQd9l0HSOf/tXYO4BjgUM8BbNAOd7UVUECBmQj8979w3HFw3XXw2GOw5JKSlV3APYDl2wOYzuRIoS4FwBHAXEAKfJOABYBZa5r6MGB9YHvg7fx2Mek8v3QV8FZ5GDwW2ANY1quAy/514PgUUKDKAun8wHSF8F13ZVcMe8uYcneDAbB8AXBv4Epgat66aQ9n+nkT4MEW7dzyEHDzHx8PHJCHxye9D2C5vwQcnQIKKNAskC4M+d73YMwY+NOfYI45tCmrgAGwfAGwq3vV+wB2tbjvp4ACCnSiQDovcLPNYMEF4YYboGe6GZhT6QQMgAbAaFMbAKOC1iuggAIFExg7FtZfPwuCv/pV9lxhp3IJGAANgNGONgBGBa1XQAEFCijwyiuw7rowZAgckZ4R5VQqAQOgATDa0AbAqKD1CiigQEEFRo2CjTeGiy+G3XYr6Eq6Wu0SMAAaANvVODVFBsCooPUKKKBAgQXSVcE77gi33w6bpMsJnUohYAA0AEYb2QAYFbReAQUUKLjAlVfCoYfCQw/BSisVfGVdvboEDIAGwLoaZQYzGQCjgtYroIACDSBw4olwySXw+OOwSHpwqFNDCxgADYDRBjYARgWtV0ABBRpAIN0oev/9swD48MPQLz1AzKlhBQyABsBo8xoAo4LWK6CAAg0i8OmnsO22kO4VOGIEzDZbg6y4q/klAQOgATD6sTAARgWtV0ABBRpI4IMPsiuDl1kGrr4aZkkPIHVqOAEDoAEw2rQGwKig9QoooECDCbz9dnaPwO23hzPP9GkhDbb5pq2uAdAAGO1bA2BU0HoFFFCgAQX++U/YfHP4ylfgwgthjTUacBAVXmUDoAEw2v4GwKig9QoooECDCqRzAU87Dc46C370Izj5ZJhnngYdTMVW2wBoAIy2vAEwKmi9Agoo0OAC//oXDB4MTz0Fv/gF7Lmnzw8u+iY1ABoAoz1qAIwKWq+AAgqUQCDdJuamm+CQQ2CppWDYMFhxxRIMrKRDMAAaAKOtbQCMClqvgAIKlEjg/fch3TQ6BcBBg+C446Bv3xINsCRDMQAaAKOtbACMClqvgAIKlFDgmWfg4IPhpZfgl7/Mnifco0cJB9qgQzIAGgCjrWsAjApar4ACCpRUIB0WTvcKPPxwWHVVuOACWHrpkg62wYZlADQARlvWABgVtF4BBRQoucC4cXD00XDFFdmVwoce6t7A7t7kBkADYLQHDYBRQesVUECBigik5wh/73uw5ppZGPSWMd234Q2ABsBo9xkAo4LWK6CAAhUSGDs2u03MCy/AjTfCaqtVaPAFGqoB0AAYbUcDYFTQegUUUKBiAlOmwOmnwymnwLnnwn77eUi4q1vAAGgAjPacATAqaL0CCihQUYH77oPddoMBA7LHyc05Z0UhumHYBkADYLTtDIBRQesVUECBCguMGQO77grp0PANN0D//hXG6MKhGwANgNF2MwBGBa1XQAEFKi7w6adwzDHZzaMvvjjbK+jUuQIGQANgtMMMgFFB6xVQQAEFpgncfjvstVe2RzCdGzjbbMJ0loAB0AAY7S0DYFTQegUUUECBzwReeSW7VUy6UCQdEl5iCXE6Q8AAaACM9pUBMCpovQIKKKDAFwQmTsyeHpKeInLSSbDUUvCVr8ACC2QvLxaJN4wB0AAY7SIDYFTQegUUUECBVgWuvz67Ovg//4F3381eac/gHHN8MRDWhsP0c3rNP/8XX717i1wrYAA0AEY/EQbAqKD1CiiggAJ1CaTw99//wjvvZGEw/dry5/T/6Yri5tf772eLnmuuLBC2DIfp/9dYAzbfHHr2rGs1SjGTAdAAGG1kA2BU0HoFFFBAgU4TSIeT33vv80CYgmNtQEyB8U9/ym5E/aMfwT77wGKLddrqFGbBBkADYLQZDYBRQesVUEABBbpVIN2G5q674NJLYcQI2HRT2H9/2Gor6NWrW1et097cAGgAjDaXATAqaL0CCiigQGEE3nwTrrwSLrsM0t7DH/4Q9t0XllyyMKvYIStiADQARhvJABgVtF4BBRRQoHACkyfDvffCJZdk9yfccMPsmcXbbQdluKDEAGgAjH7oDIBRQesVUEABBQot8O9/w1VXZYeIJ0yAnXeGr30tu7Bk7rm//Gvz7/XtW9wLSwyABsDoh84AGBW0XgEFFFCgIQTSVcj33w9/+AOMG5eFwfRKVxrX/vzBB58PJ92zMAXC2WfP9hymVzqvsPnn6f1/egpKut3N9F59+nzxz1LYTIep6907aQA0AEY/dAbAqKD1CiiggAKlEkiHj1MIrA2GH38Mn3wCkyZlr5n9nM4//OijL74+/PDLv9c8TwqgKaCuvHJ2W5v0WnNNWGGF1kOhAdAAGP3QGQCjgtYroIACCigQFEjhb/RoGDny89eoUVlgTKEwhcHmYJhCB4u+8gAACxxJREFU4ccfT6Bfv37pXdN/JgTfviHLezTkWhdnpQ2AxdkWrokCCiiggAKfCbQMhU8+CSkUpr2RK644gVGjDIC2S/sFDIDtt7NSAQUUUECBLhVoDoUPPTSBffYxAHYpfsnezABYsg3qcBRQQAEFyi/gOYCeAxjtcgNgVNB6BRRQQAEFuljAAGgAjLacATAqaL0CCiiggAJdLGAANABGW84AGBW0XgEFFFBAgS4WMAAaAKMtZwCMClqvgAIKKKBAFwsYAA2A0ZYzAEYFrVdAAQUUUKCLBQyABsBoyxkAo4LWK6CAAgoo0MUCBkADYLTlDIBRQesVUEABBRToYgEDoAEw2nIGwKig9QoooIACCnSxgAHQABhtOQNgVNB6BRRQQAEFuljAAGgAjLacATAqaL0CCiiggAJdLGAANABGW84AGBW0XgEFFFBAgS4WMAAaAKMtZwCMClqvgAIKKKBAFwsYAA2A0ZYzAEYFrVdAAQUUUKCLBQyABsBoyxkAo4LWK6CAAgoo0MUCBsDyBcBdgEHAKkBfoBcwJe+rbwJHA2sBcwCvAucCv2nRdycA+wIp3I3Ml/fsdHrTANjFH1rfTgEFFFBAgaiAAbB8AXAzYD6gD3BZiwC4BbAAcCfwLrAx8AdgT+C2vJmOAAYDad7RwHHAXsAywIetNFxlA2BTUxMDBw6MfgYbrt5xN9wmC62w2zvE13DFbu+G22TtXmEDYPkCYHMzbAT8uUUAbK1RbgFeAQ7N//Al4Bzggvz/ewJvAUOA4QbAzwWGDBnCOeckqmpNjtvtXQUB+7wKW7na3+cGwGoHwLT37nngKOB3+SHfccC6wF9qPv5NwNPA4QbAan9hpNH7F6N/MVZBwD6vwlau9ve5AbC6ATCdG5gO+6ZfB+TnCS4CvAb0B16o+fhfC0wA9p9eAHz99deZe+6UJ6szDR06lFNPPbU6A85H6rirtcnd3m7vKghUsc9TAFx00UXT5u2X/x1fhU39hTH2KOmIZ3QIOF0Akg79zgp8t+bcvpTg2roH8OvAGyU1dFgKKKCAAgqUXSDt/Hmz7INsbXxVC4DzAHfkF4HsBHzSAqW1cwDH5OcItnYOYPL7GvB+FZvHMSuggAIKKNDAAnPl5/lPbeAxtHvVyxYAZ8kP66Y9gCOAtHEnA5OABYF7gHRLlz3y328Jl87zS1cBbwWkMHhsPu+y07kKuN3wFiqggAIKKKCAAt0lULYAuDdwJdCc5tP40s+b5Ld9Sbd1ab6dS/M8D+WBr3kbHA8ckIfHJ2dyH8Du2m6+rwIKKKCAAgoo0G6BsgXAdkNYqIACCiiggAIKVEXAABjb0m15akjsnYpRnfagHpPvRW3eu/pH4PvFWL0OW4sZPVEmvcnKwPnAGvmFQ5cCqRcafZrZuNNTdT4GPiW7g0Dai55umzS9J+U0gsdp+RGAxYEPgAeAI1tc3FXG7V3PuMu4vdNpPenm/l/JTw1KT3v6GfC3mmYt4/auZ9xl3N4tv4PSBaDbApvm9wou8/f5TL9/DYAzJZruDG19akj736k4lSkAfgfYsDir1ClrMqMnyqRHDP4TuAI4MX9KTDrf9CzgvE5Zm65b6IzGndYi/QWRtv99XbdKnf5OpwA35vf6TE8QuhBYHlgtf+eybu+Zjbus23tp4D/A+PxOED/JA/9X83/QlHV7z2zcZd3etV8gKfjvDqTvufRKD4so6/au64vTAFgXU6sztfWpIe1/p+JUViUANou3djuhdJ7pGfnV383PmU5/ifwYSF+yZZimdxulNN7afzmXYawtx5CeIz4qf6RkCglV2N7JoOW4mwNBmbf3bMBBwNn5RYJjK7K9Wxt32bd3utXLw8C38vv9Nvd1VT7frX5XGwDb91dYe+4Z2L53KlZVCoDpSul0IU16PQr8v/xxesVa045Zm9aCUHr+XbpZeHpedPOUDoOmL5d0Q9F0GLHRpxkFwH/nV9q/ClyUP3O70cdbu/7p8O+BwJL5b1Zhe6ehthx3cyAo4/beMn+0Z/q8pn/UnAukIzppKvP2ntG4y7y909jSE72uBy7Pt3lzACzz9p7p97IBcKZErc7QnqeGtO+dilWVDo2lex6+DqRDJr8A1snPiWu+urpYaxxbm9aC0GXAnMBuNYteLj8PLt1WPj07utGn6QXAdDV9Cv3p1krpEEq6N+bPgYsbfcD5+qe/FNI5Qjvkt4xKv12F7d3auNPYy769031h0x6gdDP/m/IeqML2bm3cZd7eB+fn/Q3Mt3HtkYwqbO/pfj0bANv3N1dV9wC21Oqdn0uzDXBv+ygLXeUewGwPyfSmdGJ5epRiOqzS6NPW+TPBUyBIj4lsnsq+h2B6425te5ZpezePL/0d+F9gg/w80LJv7+mNu6zbO+3JT0dn1s53XKRx1gbAqmzvVr+fDYDt/2urrU8Naf87FbeyOQCmR+qlm2yXbWotAKYTic9scQ7gT/MbiJf9HMCW2zcFgvSv6vUbfMOnq9gvAHZu5R8yZd7eMxr39AJBGbZ37djSI0HTuZ57AjfnVwiX/fOdxt9y3GXd3ukfdOkIxYT8zgVpnPPn2/y6/IhGOpKVjmg1/2O3bN/n0/16NgC2/2+uKj41JP0Fma6cSidLL5QfAk57f1YC/q/9lIWrnNETZdLh3xfyq4DTlZQp9KXHC6YTyRv9KuAZjXvV/Av06ZqrgX+fPy1nWOG2YP0rlJ78k67mTnuxH2mlLF0lWMbtPbNxp6ug098PZdve6YKta/MrgRcA0mc4PRY0ndf7dn5VaBm398zGXdbtPXt+QVftRzsd8k+3vEo7LdItrcq4vev6BjQA1sU03Zmq9tSQP+Tn/KUQlA6bPJjfFzDtDS3TNKMnyqQxrwj8Or8PYNp7kG4dclIJAGY07nTaQ9ozks5/TV+a6SKQZJDugdjIU/pXf3om+MR8EM33N0wX+TQHwjJu75mNOx0aLuP2TvctXTMPemmv0BP5PwDSld/NUxm398zGXdbt3dp3U/M5zGlnRprKuL3r+k42ANbF5EwKKKCAAgoooEB5BAyA5dmWjkQBBRRQQAEFFKhLwABYF5MzKaCAAgoooIAC5REwAJZnWzoSBRRQQAEFFFCgLgEDYF1MzqSAAgoooIACCpRHwABYnm3pSBRQQAEFFFBAgboEDIB1MTmTAgoooIACCihQHgEDYHm2pSNRQAEFFFBAAQXqEjAA1sXkTAoooIACCiigQHkEDIDl2ZaORAEFFFBAAQUUqEvAAFgXkzMpoIACCiiggALlETAAlmdbOhIFFFBAAQUUUKAuAQNgXUzOpIACCiiggAIKlEfAAFiebelIFFBAAQUUUECBugQMgHUxOZMCCiiggAIKKFAeAQNgebalI1FAAQUUUEABBeoSMADWxeRMCiiggAIKKKBAeQQMgOXZlo5EAQUUUEABBRSoS8AAWBeTMymggAIKKKCAAuURMACWZ1s6EgUUUEABBRRQoC4BA2BdTM6kgAIKKKCAAgqUR8AAWJ5t6UgUUEABBRRQQIG6BAyAdTE5kwIKKKCAAgooUB4BA2B5tqUjUUABBRRQQAEF6hIwANbF5EwKKKCAAgoooEB5BAyA5dmWjkQBBRRQQAEFFKhLwABYF5MzKaCAAgoooIAC5REwAJZnWzoSBRRQQAEFFFCgLgEDYF1MzqSAAgoooIACCpRHwABYnm3pSBRQQAEFFFBAgboEDIB1MTmTAgoooIACCihQHgEDYHm2pSNRQAEFFFBAAQXqEjAA1sXkTAoooIACCiigQHkEDIDl2ZaORAEFFFBAAQUUqEvg/wNqZkNJrovpigAAAABJRU5ErkJggg==\")
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%matplotlib notebook\n",
"\n",
"import matplotlib.pyplot as plt\n",
"plt.plot([item[1] for item in nettalk.get_history()[10:]])"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def winning_output(outputs):\n",
" \"\"\"\n",
" Given outputs, what letter is this associated with?\n",
" \"\"\"\n",
" value = max(outputs)\n",
" index = list(outputs).index(value)\n",
" for key,value in patterns.items():\n",
" if value[index] == 1:\n",
" return key\n",
" return \"?\""
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'N'"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"winning_output([0 for i in range(input_length)])"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import random\n",
"\n",
"def select(outputs):\n",
" index = 0\n",
" partsum = 0.0\n",
" sumFitness = sum(outputs)\n",
" if sumFitness == 0:\n",
" raise Exception(\"outputs has a sum of zero\")\n",
" spin = random.random() * sumFitness\n",
" while index < len(outputs) - 1:\n",
" score = outputs[index]\n",
" if score < 0:\n",
" raise Exception(\"Negative score: \" + str(score))\n",
" partsum += score\n",
" if partsum >= spin:\n",
" break\n",
" index += 1\n",
" return index"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"29"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pattern_length"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"test = [random.random() for i in range(pattern_length)]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"26"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"select(test)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def winning_output(outputs):\n",
" \"\"\"\n",
" Given outputs, what letter is this associated with?\n",
" \"\"\"\n",
" index = select(outputs)\n",
" for key,value in patterns.items():\n",
" if value[index] == 1:\n",
" return key\n",
" return \"?\""
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'l'"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"winning_output(test)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"test2 = [0] * pattern_length\n",
"test2[10] = .5\n",
"test2[11] = .5"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'d'"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"winning_output(test2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1.2 Jordan Net (1986)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![](\"images/jordan.png\")
"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from conx import Network\n",
"\n",
"class Jordan(Network):\n",
" def initialize_inputs(self):\n",
" self.last_output = [0] * pattern_length \n",
" self.last_inputs = [0] * (pattern_length * 2)\n",
"\n",
" def inputs_size(self):\n",
" # Return the number of inputs:\n",
" return len(text)\n",
"\n",
" def get_letter(self, i):\n",
" if 0 <= i < len(text):\n",
" return text[i]\n",
" else:\n",
" return text[0]\n",
" \n",
" def get_inputs(self, i):\n",
" #import pdb; pdb.set_trace()\n",
" inputs = patterns[self.get_letter(i)] + list(self.last_output)\n",
" targets = patterns[self.get_letter(i)]\n",
" self.last_output = self.propagate(self.last_inputs)\n",
" self.last_inputs = inputs\n",
" return [inputs, targets]"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"jordan = Jordan(pattern_length * 2, 10, pattern_length)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------\n",
"Training for max trails: 10 ...\n",
"Epoch: 0 TSS error: 1746.01059228 %correct: 0.0\n",
"Epoch: 1 TSS error: 357.091669532 %correct: 0.0\n",
"Epoch: 2 TSS error: 125.155245219 %correct: 0.0\n",
"Epoch: 3 TSS error: 122.93406114 %correct: 0.0\n",
"Epoch: 4 TSS error: 121.433076871 %correct: 0.0\n",
"Epoch: 5 TSS error: 119.980575008 %correct: 0.0\n",
"Epoch: 6 TSS error: 118.31517078 %correct: 0.0\n",
"Epoch: 7 TSS error: 116.234642512 %correct: 0.0\n",
"Epoch: 8 TSS error: 113.57362279 %correct: 0.0\n",
"Epoch: 9 TSS error: 110.311626446 %correct: 0.0\n",
"Epoch: 10 TSS error: 106.69250351 %correct: 0.0\n",
"--------------------------------------------------\n",
"Epoch: 10 TSS error: 106.69250351 %correct: 0.0\n"
]
}
],
"source": [
"jordan.train(report_rate=1, max_training_epochs=10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1.3 Simple Recurrent Network (1990)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![](\"images/srn.png\")
"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from conx import SRN\n",
"\n",
"class Elman(SRN):\n",
" def initialize_inputs(self):\n",
" pass\n",
" \n",
" def inputs_size(self):\n",
" # Return the number of inputs:\n",
" return len(text)\n",
"\n",
" def get_letter(self, i):\n",
" if 0 <= i < len(text):\n",
" return text[i]\n",
" else:\n",
" return text[0]\n",
" \n",
" def get_inputs(self, i):\n",
" inputs = patterns[self.get_letter(i)]\n",
" targets = patterns[self.get_letter(i + 1)]\n",
" return [inputs, targets]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"elman = Elman(pattern_length, 10, pattern_length)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"elman.train(report_rate=1, max_training_epochs=10)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 1
}