2c:null 2d:["$","title",null,{"children":"tSNEJS (non TFJS) for keywords on data.csv upload | Christopher Pietsch | Observable"}] 32:T2d0c,tSNE = { // create main global object var tsnejs = tsnejs || { REVISION: 'ALPHA' }; (function(global) { "use strict"; // utility function var assert = function(condition, message) { if (!condition) { throw message || "Assertion failed"; } } // syntax sugar var getopt = function(opt, field, defaultval) { if(opt.hasOwnProperty(field)) { return opt[field]; } else { return defaultval; } } // return 0 mean unit standard deviation random number var return_v = false; var v_val = 0.0; var gaussRandom = function() { if(return_v) { return_v = false; return v_val; } var u = 2*Math.random()-1; var v = 2*Math.random()-1; var r = u*u + v*v; if(r == 0 || r > 1) return gaussRandom(); var c = Math.sqrt(-2*Math.log(r)/r); v_val = v*c; // cache this for next function call for efficiency return_v = true; return u*c; } // return random normal number var randn = function(mu, std){ return mu+gaussRandom()*std; } // utilitity that creates contiguous vector of zeros of size n var zeros = function(n) { if(typeof(n)==='undefined' || isNaN(n)) { return []; } if(typeof ArrayBuffer === 'undefined') { // lacking browser support var arr = new Array(n); for(var i=0;i 1e-7) Hhere -= pj * Math.log(pj); } // adjust beta based on result if(Hhere > Htarget) { // entropy was too high (distribution too diffuse) // so we need to increase the precision for more peaky distribution betamin = beta; // move up the bounds if(betamax === Infinity) { beta = beta * 2; } else { beta = (beta + betamax) / 2; } } else { // converse case. make distrubtion less peaky betamax = beta; if(betamin === -Infinity) { beta = beta / 2; } else { beta = (beta + betamin) / 2; } } // stopping conditions: too many tries or got a good precision num++; if(Math.abs(Hhere - Htarget) < tol) { done = true; } if(num >= maxtries) { done = true; } } // console.log('data point ' + i + ' gets precision ' + beta + ' after ' + num + ' binary search steps.'); // copy over the final prow to P at row i for(var j=0;j 0 ? 1 : x < 0 ? -1 : 0; } var tSNE = function(opt) { var opt = opt || {}; this.perplexity = getopt(opt, "perplexity", 30); // effective number of nearest neighbors this.dim = getopt(opt, "dim", 2); // by default 2-D tSNE this.epsilon = getopt(opt, "epsilon", 10); // learning rate this.iter = 0; } tSNE.prototype = { // this function takes a set of high-dimensional points // and creates matrix P from them using gaussian kernel initDataRaw: function(X) { var N = X.length; var D = X[0].length; assert(N > 0, " X is empty? You must have some data!"); assert(D > 0, " X[0] is empty? Where is the data?"); var dists = xtod(X); // convert X to distances using gaussian kernel this.P = d2p(dists, this.perplexity, 1e-4); // attach to object this.N = N; // back up the size of the dataset this.initSolution(); // refresh this }, // this function takes a given distance matrix and creates // matrix P from them. // D is assumed to be provided as a list of lists, and should be symmetric initDataDist: function(D) { var N = D.length; assert(N > 0, " X is empty? You must have some data!"); // convert D to a (fast) typed array version var dists = zeros(N * N); // allocate contiguous array for(var i=0;i`\n","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":558,"value":"data = {\n const text = await Files.text(upload)\n const csv = d3.csvParse(text, d => {\n return {\n id: d.id,\n keywords: d.keywords.split(\",\")\n }\n })\n return csv\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":305,"value":"labels = {\n const labels = {}\n data.forEach(d => {\n d.keywords.forEach(k => {\n labels[k] = 0\n })\n })\n \n return Object.keys(labels)\n}\n","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":332,"value":"nodes = data.map(d => {\n const vectors = labels.map(l => {\n return d.keywords.indexOf(l) > -1 ? 0 : 1\n })\n return {\n id: d.id,\n keywords: d.keywords,\n vectors\n }\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":194,"value":"vectors = nodes.map(d => d.vectors)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":510,"value":"iterations = 200","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":512,"value":"perplexity = 30","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":532,"value":"epsilon = 10","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":275,"value":"positions = {\n const tsne = new tSNE.tSNE({\n dim: 2,\n epsilon: epsilon,\n perplexity: perplexity \n })\n \n tsne.initDataRaw(vectors)\n \n for (let i = iterations; i--;) {\n tsne.step()\n yield tsne.getSolution()\n }\n \n return tsne.getSolution()\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":410,"value":"viewof filter = select({options: labels})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":7,"value":"chart = {\n const data = nodes.map((node, index) => ({ ...node, position: positions[index] }))\n \n const minX = positions.map((d) => d[0]).reduce((a, b) => Math.min(a, b), Infinity)\n const maxX = positions.map((d) => d[0]).reduce((a, b) => Math.max(a, b), -Infinity)\n const minY = positions.map((d) => d[1]).reduce((a, b) => Math.min(a, b), Infinity)\n const maxY = positions.map((d) => d[1]).reduce((a, b) => Math.max(a, b), -Infinity)\n \n const x = d3.scaleLinear().domain([minX, maxX]).range([0, 1000])\n const y = d3.scaleLinear().domain([minY, maxY]).range([0, 1000])\n \n const svg = d3.select(DOM.svg(1000, 1000))\n .style('width', '100%')\n .style('height', 'auto')\n \n const node = svg.append('g')\n \t.selectAll('circle').data(data)\n \t .enter().append('circle')\n \t .attr('r', d => d.keywords.indexOf(filter) > -1 ? 4: 2)\n .attr('cx', (d) => x(d.position[0]))\n .attr('cy', (d) => y(d.position[1]))\n\n \n \n return svg.node()\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":3,"value":"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":26,"value":"color = {\n const scale = d3.scaleOrdinal(d3.schemeCategory10);\n return d => scale(d.group);\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":76,"value":"drag = simulation => {\n \n function dragstarted(d) {\n if (!d3.event.active) simulation.alphaTarget(0.3).restart();\n d.fx = d.x;\n d.fy = d.y;\n }\n \n function dragged(d) {\n d.fx = d3.event.x;\n d.fy = d3.event.y;\n }\n \n function dragended(d) {\n if (!d3.event.active) simulation.alphaTarget(0);\n d.fx = null;\n d.fy = null;\n }\n \n return d3.drag()\n .on(\"start\", dragstarted)\n .on(\"drag\", dragged)\n .on(\"end\", dragended);\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":11,"value":"d3 = require(\"https://d3js.org/d3.v5.min.js\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":428,"value":"import {select, slider, textarea} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"},{"id":506,"value":"$32","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined"}],"files":"$W33","stdlib":"1","titling":"auto"}} 31:"$30:body"