Last active
February 2, 2016 13:05
-
-
Save AYLIEN/465b66785970335357a2 to your computer and use it in GitHub Desktop.
Sort Concepts by Relevance
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
var _ = require('underscore'), | |
AYLIENTextAPI = require("aylien_textapi"); | |
var textapi = new AYLIENTextAPI({ | |
application_id: "YourApplicationId", | |
application_key: "YourApplicationKey" | |
}); | |
function escapeRegExp(r) { | |
return r.replace(/[-\/\\^$*+?.()|[\]{}]/g, '\\$&'); | |
} | |
var titleWeight = 3, | |
articleWeight = 1; | |
textapi.combined({ | |
url: 'http://techcrunch.com/2016/02/01/nasas-super-guppy-gives-mars-bound-spacecraft-a-lift/', | |
endpoint: ['extract', 'concepts'] | |
}, function(err, result) { | |
if (err === null) { | |
var title; | |
var article; | |
var concepts; | |
_(result.results).each(function(r) { | |
if (r.endpoint == 'extract') { | |
title = r.result.title; | |
article = r.result.article; | |
} else if (r.endpoint = 'concepts') { | |
concepts = r.result.concepts; | |
} | |
}); | |
var cw = _.chain(concepts).map(function(o, c) { | |
var w = _.chain(o.surfaceForms).map(function(sf) { | |
var e = new RegExp('\\b' + escapeRegExp(sf.string) + '\\b', 'g'); | |
var inArticle = (article.match(e) || []).length; | |
var inTitle = (title.match(e) || []).length; | |
return (inTitle * titleWeight) + (inArticle * articleWeight); | |
}).reduce(function(memo, num) { return memo + num; }, 0).value(); | |
return {'concept': c, 'weight': w}; | |
}).sortBy(function(i) { return -i.weight; }).value(); | |
console.log(cw); | |
} | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment