The above 13 character repeat patterns account for 50% of English words (117893 of 235786 words, using nltk's corpus.words).
Last active
December 26, 2015 03:19
-
-
Save mobeets/7085343 to your computer and use it in GitHub Desktop.
Popular character repeat patterns
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
name | desc | value | |
---|---|---|---|
AABCDEFG | occident | 13155 | |
AABCDEFGH | milkgrass | 11979 | |
AABCDEF | crowtoe | 11021 | |
AABBCDEFGH | improperly | 10006 | |
AABBCDEFG | upsitting | 9699 | |
ABCDEF | larigo | 8459 | |
AABCDEFGHI | wantonlike | 8330 | |
ABCDEFG | dogface | 8225 | |
AABBCDEFGHI | overcleanly | 7915 | |
AABCDE | bleery | 7362 | |
AABBCDEF | milliare | 6661 | |
ABCDE | sixer | 6647 | |
ABCDEFGH | nailshop | 6336 | |
AABBCDEFGHIJ | excursionism | 4776 |
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> | |
<html> | |
<head> | |
<title>Popular character repeat patterns</title> | |
<script type="text/javascript" src="http://d3js.org/d3.v3.min.js"></script> | |
<style type="text/css"> | |
body { | |
font: 12px sans-serif; | |
} | |
.bar rect { | |
fill: steelblue; | |
opacity: 0.8; | |
} | |
.bar text.value { | |
fill: white; | |
} | |
.axis { | |
shape-rendering: crispEdges; | |
} | |
.axis path { | |
fill: none; | |
} | |
.x.axis line { | |
stroke: #fff; | |
stroke-opacity: .8; | |
} | |
.y.axis path { | |
stroke: black; | |
} | |
</style> | |
</head> | |
<body> | |
<script type="text/javascript"> | |
var margin = {top: 30, right: 10, bottom: 10, left: 100}, | |
width = 700 - margin.right - margin.left, | |
height = 500 - margin.top - margin.bottom; | |
var format = d3.format(",.0f"); | |
var x = d3.scale.linear() | |
.range([0, width]); | |
var y = d3.scale.ordinal() | |
.rangeRoundBands([0, height], .1); | |
var xAxis = d3.svg.axis() | |
.scale(x) | |
.orient("top") | |
.tickSize(-height); | |
var yAxis = d3.svg.axis() | |
.scale(y) | |
.orient("left") | |
.tickSize(0); | |
var svg = d3.select("body").append("svg") | |
.attr("width", width + margin.right + margin.left) | |
.attr("height", height + margin.top + margin.bottom) | |
.append("g") | |
.attr("transform", "translate(" + margin.left + "," + margin.top + ")"); | |
d3.csv("data.csv", function(data) { | |
// Parse numbers, and sort by value. | |
data.forEach(function(d) { d.value = +d.value; }); | |
data.sort(function(a, b) { return b.value - a.value; }); | |
// Set the scale domain. | |
x.domain([0, d3.max(data, function(d) { return d.value; })]); | |
y.domain(data.map(function(d) { return d.name; })); | |
var bar = svg.selectAll("g.bar") | |
.data(data) | |
.enter().append("g") | |
.attr("class", "bar") | |
.attr("transform", function(d) { return "translate(0," + y(d.name) + ")"; }); | |
bar.append("rect") | |
.attr("width", function(d) { return x(d.value); }) | |
.attr("height", y.rangeBand()) | |
.on("mouseover", function() { d3.select(this).style("opacity", 1.0); }) | |
.on("mouseout", function() { d3.select(this).style("opacity", 0.8); }); | |
bar.append("text") | |
.attr("class", "value") | |
.attr("x", function(d) { return x(d.value); }) | |
.attr("y", y.rangeBand() / 2) | |
.attr("dx", -3) | |
.attr("dy", ".35em") | |
.attr("text-anchor", "end") | |
.text(function(d) { return d.desc; }); | |
svg.append("g") | |
.attr("class", "x axis") | |
.call(xAxis); | |
svg.append("g") | |
.attr("class", "y axis") | |
.call(yAxis); | |
}); | |
</script> | |
</body> | |
</html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment