<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (jd)</title>
    <link>https://pinboard.in/u:jd/public/</link>
    <description>recent bookmarks from jd</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://observablehq.com/@mbostock/methods-of-comparison-compared"/>
	<rdf:li rdf:resource="https://mockaroo.com/"/>
	<rdf:li rdf:resource="http://www.convertcsv.com/generate-test-data.htm"/>
	<rdf:li rdf:resource="https://medium.com/airbnb-engineering/how-airbnb-democratizes-data-science-with-data-university-3eccc71e073a"/>
	<rdf:li rdf:resource="https://snap.stanford.edu/"/>
	<rdf:li rdf:resource="http://www.gdeltproject.org/"/>
	<rdf:li rdf:resource="http://www.joke2k.net/faker/"/>
	<rdf:li rdf:resource="http://shop.oreilly.com/product/0636920023784.do"/>
	<rdf:li rdf:resource="http://shop.oreilly.com/product/0636920030195.do?cmp=af-strata-books-video-product_cj_0636920030195_7133220"/>
	<rdf:li rdf:resource="http://source.mozillaopennews.org/en-US/articles/introducing-tabula/"/>
	<rdf:li rdf:resource="http://blogs.ischool.berkeley.edu/i290-abdt-s12/2012/12/13/uc-berkeley-course-lectures-analyzing-big-data-with-twitter/"/>
	<rdf:li rdf:resource="http://www.sciencebasedmedicine.org/index.php/moneyball-the-2012-election-and-science-and-evidence-based-medicine/"/>
	<rdf:li rdf:resource="http://www.visualisingdata.com/index.php/2012/04/the-data-journalism-handbook-is-now-live/"/>
	<rdf:li rdf:resource="http://rdf.ookaboo.com/"/>
	<rdf:li rdf:resource="http://www.datasciencetoolkit.org/developerdocs"/>
	<rdf:li rdf:resource="http://mbostock.github.com/protovis/"/>
	<rdf:li rdf:resource="http://scraperwiki.com/"/>
	<rdf:li rdf:resource="http://googlecode.blogspot.com/2011/02/visualize-your-own-data-in-google.html"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://observablehq.com/@mbostock/methods-of-comparison-compared">
    <title>Methods of Comparison, Compared</title>
    <dc:date>2020-08-31T04:14:54+00:00</dc:date>
    <link>https://observablehq.com/@mbostock/methods-of-comparison-compared</link>
    <dc:creator>jd</dc:creator><description><![CDATA[Mike Bostok]]></description>
<dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:b7216c84b64b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://mockaroo.com/">
    <title>Mockaroo - Random Data Generator and API Mocking Tool | JSON / CSV / SQL / Excel | https://mockaroo.com/</title>
    <dc:date>2018-07-28T21:47:07+00:00</dc:date>
    <link>https://mockaroo.com/</link>
    <dc:creator>jd</dc:creator><dc:subject>data generator</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:6e1b0022cc61/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:generator"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.convertcsv.com/generate-test-data.htm">
    <title>Generate Test CSV Data</title>
    <dc:date>2017-11-16T17:25:41+00:00</dc:date>
    <link>http://www.convertcsv.com/generate-test-data.htm</link>
    <dc:creator>jd</dc:creator><description><![CDATA[generates random test data of various types.  there are many similar sites, but this was the only one i found that would let me generate 5000+ rows.  UI is not quite as friendly, for example compare to http://generatedata.com which has nicer UI but isn't free for >100 rows.]]></description>
<dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:6817c373b0e4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://medium.com/airbnb-engineering/how-airbnb-democratizes-data-science-with-data-university-3eccc71e073a">
    <title>How Airbnb Democratizes Data Science With Data University</title>
    <dc:date>2017-08-30T17:32:24+00:00</dc:date>
    <link>https://medium.com/airbnb-engineering/how-airbnb-democratizes-data-science-with-data-university-3eccc71e073a</link>
    <dc:creator>jd</dc:creator><description><![CDATA[Jeff Feng's blog on educating employees on using data]]></description>
<dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:a86135a508b5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://snap.stanford.edu/">
    <title>SNAP: Stanford Network Analysis Project</title>
    <dc:date>2014-07-25T01:28:24+00:00</dc:date>
    <link>https://snap.stanford.edu/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[library plus large network dataset collection]]></description>
<dc:subject>data datasets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:bf161c77e2ac/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:datasets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.gdeltproject.org/">
    <title>The GDELT Project: The Global Database of Events, Language, and Tone</title>
    <dc:date>2014-05-31T16:18:58+00:00</dc:date>
    <link>http://www.gdeltproject.org/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[database of world events (from 1979)

http://gigaom.com/2014/05/29/more-than-250-million-global-events-are-now-in-the-cloud-for-anyone-to-analyze/]]></description>
<dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:974ec8e821b4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.joke2k.net/faker/">
    <title>Faker by joke2k</title>
    <dc:date>2014-01-23T00:53:44+00:00</dc:date>
    <link>http://www.joke2k.net/faker/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[python library to generate fake data, including names, addresses, phone numbers, user agents, ip addresses, company names, timestamps, and more]]></description>
<dc:subject>fake data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:d28627860847/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:fake"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://shop.oreilly.com/product/0636920023784.do">
    <title>Python for Data Analysis - O'Reilly Media</title>
    <dc:date>2013-11-27T05:58:52+00:00</dc:date>
    <link>http://shop.oreilly.com/product/0636920023784.do</link>
    <dc:creator>jd</dc:creator><description><![CDATA[Wes McKinney's book on Pandas
example code: https://github.com/pydata/pydata-book]]></description>
<dc:subject>python data books</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:55d24af827ca/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:books"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://shop.oreilly.com/product/0636920030195.do?cmp=af-strata-books-video-product_cj_0636920030195_7133220">
    <title>Mining the Social Web, 2nd Edition - O'Reilly Media</title>
    <dc:date>2013-11-23T06:09:45+00:00</dc:date>
    <link>http://shop.oreilly.com/product/0636920030195.do?cmp=af-strata-books-video-product_cj_0636920030195_7133220</link>
    <dc:creator>jd</dc:creator><description><![CDATA[How can you tap into the wealth of social web data to discover who’s making connections with whom, what they’re talking about, and where they’re located? ...learn how to acquire, analyze, and summarize data from all corners of the social web, including Facebook, Twitter, LinkedIn, Google+, GitHub, email, websites, and blogs.

 - Employ the Natural Language Toolkit, NetworkX, and other scientific computing tools to mine popular social web sites

 - Apply advanced text-mining techniques, such as clustering and TF-IDF, to extract meaning from human language data

 - Bootstrap interest graphs from GitHub by discovering affinities among people, programming languages, and coding projects

 - Build interactive visualizations with D3.js, an extraordinarily flexible HTML5 and JavaScript toolkit

 - Take advantage of more than two-dozen Twitter recipes, presented in O’Reilly’s popular "problem/solution/discussion" cookbook format

The example code for this unique data science book is maintained in a public GitHub repository. It’s designed to be easily accessible through a turnkey virtual machine that facilitates interactive learning with an easy-to-use collection of IPython Notebooks.

https://github.com/ptwobrussell/Mining-the-Social-Web-2nd-Edition]]></description>
<dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:25ec0736abd2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://source.mozillaopennews.org/en-US/articles/introducing-tabula/">
    <title>Introducing Tabula - Features - Source: An OpenNews project</title>
    <dc:date>2013-04-03T20:10:52+00:00</dc:date>
    <link>http://source.mozillaopennews.org/en-US/articles/introducing-tabula/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[open source tool for extracting CSV data from PDF.  nice article describing how it works, the difficulties, etc.  not sure how it works for non-interactive use (in the demo, interaction required to select region containing table)]]></description>
<dc:subject>csv pdf data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:ad1879a45904/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:csv"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blogs.ischool.berkeley.edu/i290-abdt-s12/2012/12/13/uc-berkeley-course-lectures-analyzing-big-data-with-twitter/">
    <title>UC Berkeley Course Lectures: Analyzing Big Data With Twitter | Analyzing Big Data with Twitter</title>
    <dc:date>2012-12-20T16:15:51+00:00</dc:date>
    <link>http://blogs.ischool.berkeley.edu/i290-abdt-s12/2012/12/13/uc-berkeley-course-lectures-analyzing-big-data-with-twitter/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[lectures and slides from semester course on analyzing twitter data.]]></description>
<dc:subject>data machinelearning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:41d2dfe9aa8a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:machinelearning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.sciencebasedmedicine.org/index.php/moneyball-the-2012-election-and-science-and-evidence-based-medicine/">
    <title>Science-Based Medicine » “Moneyball,” the 2012 election, and science- and evidence-based medicine</title>
    <dc:date>2012-11-13T03:40:15+00:00</dc:date>
    <link>http://www.sciencebasedmedicine.org/index.php/moneyball-the-2012-election-and-science-and-evidence-based-medicine/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[tl;dr - doctors and alternative medicine practitioners threatened by evidence-based medicine (via Moneyball, Nate Silver, and Karl Rove).]]></description>
<dc:subject>medicine data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:60d2947a1404/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:medicine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.visualisingdata.com/index.php/2012/04/the-data-journalism-handbook-is-now-live/">
    <title>Visualising Data » Blog Archive » The Data Journalism Handbook is now live</title>
    <dc:date>2012-04-30T16:33:09+00:00</dc:date>
    <link>http://www.visualisingdata.com/index.php/2012/04/the-data-journalism-handbook-is-now-live/</link>
    <dc:creator>jd</dc:creator><dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:02bb651aa7e7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://rdf.ookaboo.com/">
    <title>Ookaboo RDF data dump</title>
    <dc:date>2012-01-25T22:50:03+00:00</dc:date>
    <link>http://rdf.ookaboo.com/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[metadata for nearly 1,000,000 public domain and Creative Commons images of more than 500,000 precise topics such as places, people and organism classifications linked to DBpedia and Freebase.]]></description>
<dc:subject>labelled image data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:20a3bcae531a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:labelled"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:image"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.datasciencetoolkit.org/developerdocs">
    <title>Data Science Toolkit</title>
    <dc:date>2012-01-16T18:21:48+00:00</dc:date>
    <link>http://www.datasciencetoolkit.org/developerdocs</link>
    <dc:creator>jd</dc:creator><description><![CDATA[toolkit includes file to text (image, pdf, office docs), html to text, text to people, text to times (Chronic Ruby gem), geocoding, etc.  tools are hosted, but you can self-host too.  results aren't perfect, but interesting nonetheless.]]></description>
<dc:subject>data machinelearning analytics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:a66e49f63c31/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:analytics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mbostock.github.com/protovis/">
    <title>Protovis - A graphical approach to visualization</title>
    <dc:date>2011-11-01T03:21:16+00:00</dc:date>
    <link>http://mbostock.github.com/protovis/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[high level language, generates SVG for the brwoser
]]></description>
<dc:subject>data visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:381e2cefe7c4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://scraperwiki.com/">
    <title>Welcome | ScraperWiki</title>
    <dc:date>2011-03-23T03:08:57+00:00</dc:date>
    <link>http://scraperwiki.com/</link>
    <dc:creator>jd</dc:creator><description><![CDATA[collection of scrapers, plus online toolkit for building them]]></description>
<dc:subject>datamining scraping data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:a5b2cbd74015/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://googlecode.blogspot.com/2011/02/visualize-your-own-data-in-google.html">
    <title>Visualize your own data in the Google Public Data Explorer - The official Google Code blog</title>
    <dc:date>2011-02-18T02:36:39+00:00</dc:date>
    <link>http://googlecode.blogspot.com/2011/02/visualize-your-own-data-in-google.html</link>
    <dc:creator>jd</dc:creator><description><![CDATA[dataset publishing language]]></description>
<dc:subject>data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jd/b:300efad0d2f6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jd/t:data"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>