A D3 rendering of Anscombe Quartet, a classic data visualization example where four data sets have the same summary statistics, showing a reason why visualization is important - to see different distrubitions of data, which summary statistics can't always uncover.
Last active
September 12, 2016 01:58
-
-
Save pstuffa/b294fbd9a3a180499165 to your computer and use it in GitHub Desktop.
Anscombe Quartet
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
group | x | y | |
---|---|---|---|
I | 10 | 8.04 | |
I | 8 | 6.95 | |
I | 13 | 7.58 | |
I | 9 | 8.81 | |
I | 11 | 8.33 | |
I | 14 | 9.96 | |
I | 6 | 7.24 | |
I | 4 | 4.26 | |
I | 12 | 10.84 | |
I | 7 | 4.82 | |
I | 5 | 5.68 | |
II | 10 | 9.14 | |
II | 8 | 8.14 | |
II | 13 | 8.74 | |
II | 9 | 8.77 | |
II | 11 | 9.26 | |
II | 14 | 8.1 | |
II | 6 | 6.13 | |
II | 4 | 3.1 | |
II | 12 | 9.13 | |
II | 7 | 7.26 | |
II | 5 | 4.74 | |
III | 10 | 7.46 | |
III | 8 | 6.77 | |
III | 13 | 12.74 | |
III | 9 | 7.11 | |
III | 11 | 7.81 | |
III | 14 | 8.84 | |
III | 6 | 6.08 | |
III | 4 | 5.39 | |
III | 12 | 8.15 | |
III | 7 | 6.42 | |
III | 5 | 5.73 | |
IV | 8 | 6.58 | |
IV | 8 | 5.76 | |
IV | 8 | 7.71 | |
IV | 8 | 8.84 | |
IV | 8 | 8.47 | |
IV | 8 | 7.04 | |
IV | 8 | 5.25 | |
IV | 19 | 12.5 | |
IV | 8 | 5.56 | |
IV | 8 | 7.91 | |
IV | 8 | 6.89 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<!DOCTYPE html> | |
<meta charset="utf-8"> | |
<html> | |
<style type="text/css"> | |
.axis path, | |
.axis line { | |
fill: none; | |
stroke: #000; | |
stroke-opacity: .1; | |
shape-rendering: crispEdges; | |
} | |
.dots { | |
fill: #66ddff; | |
fill-opacity: .75; | |
stroke: steelblue; | |
stroke-width: 2px; | |
} | |
body { | |
font: 12px sans-serif; | |
} | |
.dots:hover{ | |
fill: red; | |
stroke: #99212c; | |
} | |
.line { | |
stroke: blue; | |
fill:none; | |
stroke-width: 3; | |
} | |
</style> | |
<body> | |
<h2></h2> | |
<button id="one">I</button> | |
<button id="two">II</button> | |
<button id="three">III</button> | |
<button id="four">IV</button> | |
<div class="g-chart"></div> | |
<script src="linearRegression.js" charset="utf-8"></script> | |
<script src="https://cdnjs.cloudflare.com/ajax/libs/d3/3.5.5/d3.min.js" charset="utf-8"></script> | |
<script> | |
var margin = { top: 20, right: 20, bottom: 30, left: 40}, | |
width = 350, | |
height = 350; | |
var x = d3.scale.linear() | |
.domain([0,20]) | |
.range([0, width]); | |
var y = d3.scale.linear() | |
.domain([0,20]) | |
.range([height, 0]); | |
var xAxis = d3.svg.axis() | |
.scale(x) | |
.orient("bottom") | |
.innerTickSize(-height) | |
.outerTickSize(0) | |
.tickPadding(10); | |
var yAxis = d3.svg.axis() | |
.scale(y) | |
.orient("left") | |
.innerTickSize(-width) | |
.outerTickSize(0) | |
.tickPadding(10); | |
var svg = d3.select("body") | |
.append("svg") | |
.attr("height", height + margin.top + margin.bottom) | |
.attr("width", width + margin.left + margin.right) | |
.append("g") | |
.attr("transform","translate(" + margin.left + "," + margin.top + ")"); | |
svg.append("rect") | |
.attr("width",width) | |
.attr("height", height) | |
.style("fill-opacity", .05); | |
svg.append("g") | |
.attr("class","x axis") | |
.attr("transform","translate(0," + height + ")") | |
.call(xAxis) | |
svg.append("g") | |
.attr("class","y axis") | |
.call(yAxis) | |
d3.tsv("data.tsv", function(error, data) { | |
if (error) throw error; | |
dataOne = data.filter(function(d) { return d.group == 'I'; }) | |
dataTwo = data.filter(function(d) { return d.group == 'II'; }) | |
dataThree = data.filter(function(d) { return d.group == 'III'; }) | |
dataFour = data.filter(function(d) { return d.group == 'IV'; }) | |
data.forEach(function(d) { | |
d.x = +d.x; | |
d.y = +d.y; | |
}); | |
lr = linearRegression(data.map(function(d) { return d.y; }), data.map(function(d) { return d.x; })) | |
d3.select(".summary") | |
.html(function(d) { return "slope: " + lr.slope + "<br />" + | |
" intercept: " + lr.intercept + "<br />" + | |
" r2: " + lr.r2;}) | |
var max = d3.max(data, function (d) { return d.x; }); | |
var myLine = svg.append("line") | |
.attr("x1", x(0)) | |
.attr("y1", y(lr.intercept)) | |
.attr("x2", x(max)) | |
.attr("y2", y( (max * lr.slope) + lr.intercept )) | |
.style("stroke", "black"); | |
d3.select("body") | |
.select("h2") | |
.text("Group I"); | |
dots = svg.selectAll(".dots") | |
.data(dataOne, function(d,i) { return i; }); | |
dots.enter() | |
.append("circle") | |
.attr("class","dots") | |
.attr("cx", function(d) { return x(d.x); }) | |
.attr("cy", function(d) { return y(d.y); }) | |
.attr("r", 8); | |
d3.selectAll("#one") | |
.on("click", function() { | |
lr = linearRegression(dataOne.map(function(d) { return d.y; }), dataOne.map(function(d) { return d.x; })) | |
d3.select(".summary") | |
.html(function(d) { return "slope: " + lr.slope + "<br />" + | |
" intercept: " + lr.intercept + "<br />" + | |
" r2: " + lr.r2;}) | |
d3.select("body") | |
.select("h2") | |
.text("Group I") | |
dots.data(dataOne) | |
.transition() | |
.duration(2000) | |
.ease("elastic") | |
.delay(function(d,i) { return i * 100; }) | |
.attr("cx", function(d) { return x(d.x); }) | |
.attr("cy", function(d) { return y(d.y); }); | |
}); | |
d3.selectAll("#two") | |
.on("click", function() { | |
lr = linearRegression(dataTwo.map(function(d) { return d.y; }), dataTwo.map(function(d) { return d.x; })) | |
d3.select(".summary") | |
.html(function(d) { return "slope: " + lr.slope + "<br />" + | |
" intercept: " + lr.intercept + "<br />" + | |
" r2: " + lr.r2;}) | |
var max = d3.max(dataTwo, function (d) { return d.x; }); | |
var myLine = svg.append("line") | |
.attr("x1", x(0)) | |
.attr("y1", y(lr.intercept)) | |
.attr("x2", x(max)) | |
.attr("y2", y( (max * lr.slope) + lr.intercept )) | |
.style("stroke", "black"); | |
d3.select("body") | |
.select("h2") | |
.text("Group II") | |
dots.data(dataTwo) | |
.transition() | |
.duration(2000) | |
.ease("elastic") | |
.delay(function(d,i) { return i * 100; }) | |
.attr("cx", function(d) { return x(d.x); }) | |
.attr("cy", function(d) { return y(d.y); }); | |
}); | |
d3.selectAll("#three") | |
.on("click", function() { | |
lr = linearRegression(dataThree.map(function(d) { return d.y; }), dataThree.map(function(d) { return d.x; })) | |
d3.select(".summary") | |
.html(function(d) { return "slope: " + lr.slope + "<br />" + | |
" intercept: " + lr.intercept + "<br />" + | |
" r2: " + lr.r2;}) | |
var max = d3.max(dataThree, function (d) { return d.x; }); | |
var myLine = svg.append("line") | |
.attr("x1", x(0)) | |
.attr("y1", y(lr.intercept)) | |
.attr("x2", x(max)) | |
.attr("y2", y( (max * lr.slope) + lr.intercept )) | |
.style("stroke", "black"); | |
d3.select("body") | |
.select("h2") | |
.text("Group III") | |
dots.data(dataThree) | |
.transition() | |
.duration(2000) | |
.ease("elastic") | |
.delay(function(d,i) { return i * 100; }) | |
.attr("class","dots") | |
.attr("cx", function(d) { return x(d.x); }) | |
.attr("cy", function(d) { return y(d.y); }); | |
}); | |
d3.selectAll("#four") | |
.on("click", function() { | |
lr = linearRegression(dataFour.map(function(d) { return d.y; }), dataFour.map(function(d) { return d.x; })) | |
d3.select(".summary") | |
.html(function(d) { return "slope: " + lr.slope + "<br />" + | |
" intercept: " + lr.intercept + "<br />" + | |
" r2: " + lr.r2;}) | |
var max = d3.max(dataFour, function (d) { return d.x; }); | |
var myLine = svg.append("line") | |
.attr("x1", x(0)) | |
.attr("y1", y(lr.intercept)) | |
.attr("x2", x(max)) | |
.attr("y2", y( (max * lr.slope) + lr.intercept )) | |
.style("stroke", "black"); | |
d3.select("body") | |
.select("h2") | |
.text("Group IV") | |
dots.data(dataFour) | |
.transition() | |
.duration(2000) | |
.ease("elastic") | |
.delay(function(d,i) { return i * 100; }) | |
.attr("cx", function(d) { return x(d.x); }) | |
.attr("cy", function(d) { return y(d.y); }); | |
}); | |
}); | |
</script> | |
<div class="summary"></div> | |
</body> | |
</html> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// http://trentrichardson.com/2010/04/06/compute-linear-regressions-in-javascript/ | |
function linearRegression(y,x){ | |
var lr = {}; | |
var n = y.length; | |
var sum_x = 0; | |
var sum_y = 0; | |
var sum_xy = 0; | |
var sum_xx = 0; | |
var sum_yy = 0; | |
for (var i = 0; i < y.length; i++) { | |
sum_x += x[i]; | |
sum_y += y[i]; | |
sum_xy += (x[i]*y[i]); | |
sum_xx += (x[i]*x[i]); | |
sum_yy += (y[i]*y[i]); | |
} | |
lr['slope'] = (n * sum_xy - sum_x * sum_y) / (n*sum_xx - sum_x * sum_x); | |
lr['intercept'] = (sum_y - lr.slope * sum_x)/n; | |
lr['r2'] = Math.pow((n*sum_xy - sum_x*sum_y)/Math.sqrt((n*sum_xx-sum_x*sum_x)*(n*sum_yy-sum_y*sum_y)),2); | |
return lr; | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment