<?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 (mcroydon)</title>
    <link>https://pinboard.in/u:mcroydon/public/</link>
    <description>recent bookmarks from mcroydon</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="http://highlyscalable.wordpress.com/2012/02/01/mapreduce-patterns/"/>
	<rdf:li rdf:resource="http://lwn.net/Articles/452307/"/>
	<rdf:li rdf:resource="http://strangeloop-riak-mapred.heroku.com/#1"/>
	<rdf:li rdf:resource="http://infolab.stanford.edu/~ullman/mmds.html"/>
	<rdf:li rdf:resource="http://borthakur.com/ftp/RealtimeHadoopSigmod2011.pdf"/>
	<rdf:li rdf:resource="http://www.dataspora.com/2011/04/pigs-bees-and-elephants-a-comparison-of-eight-mapreduce-languages/"/>
	<rdf:li rdf:resource="http://tech.backtype.com/the-dark-side-of-hadoop"/>
	<rdf:li rdf:resource="http://blog.basho.com/2011/03/30/why-mapreduce-is-easy/"/>
	<rdf:li rdf:resource="http://code.google.com/p/appengine-pipeline/"/>
	<rdf:li rdf:resource="http://blog.cloudant.com/39351506"/>
	<rdf:li rdf:resource="http://brandynwhite.com/"/>
	<rdf:li rdf:resource="http://engineeringblog.yelp.com/2010/10/mrjob-distributed-computing-for-everybody.html"/>
	<rdf:li rdf:resource="http://s4.io/"/>
	<rdf:li rdf:resource="http://www.dist-systems.bbn.com/people/krohloff/papers/2010/SHARD_Rohloff_Kurt_HadoopWorld_2010.pdf"/>
	<rdf:li rdf:resource="http://www.dist-systems.bbn.com/people/krohloff/shard.shtml"/>
	<rdf:li rdf:resource="http://www.theregister.co.uk/2010/09/09/google_caffeine_explained/"/>
	<rdf:li rdf:resource="http://code.google.com/p/appengine-mapreduce/"/>
	<rdf:li rdf:resource="http://www.google.com/buzz/bslatkin/6SXDRWXFWkN"/>
	<rdf:li rdf:resource="http://www.cloudera.com/blog/2010/03/how-raytheon-researchers-are-using-hadoop-to-build-a-scalable-distributed-triple-store/"/>
	<rdf:li rdf:resource="http://www.lucidimagination.com/blog/2010/03/16/integrating-apache-mahout-with-apache-lucene-and-solr-part-i-of-3/"/>
	<rdf:li rdf:resource="http://www.larsgeorge.com/"/>
	<rdf:li rdf:resource="http://glinden.blogspot.com/2010/03/gfs-and-its-evolution.html"/>
	<rdf:li rdf:resource="http://www.cloudera.com/blog/2010/03/why-europes-largest-ad-targeting-platform-uses-hadoop/"/>
	<rdf:li rdf:resource="http://www.umiacs.umd.edu/~jimmylin/book.html"/>
	<rdf:li rdf:resource="http://www.larsgeorge.com/2009/11/hbase-vs-bigtable-comparison.html"/>
	<rdf:li rdf:resource="http://www.cloudera.com/hadoop-world-nyc"/>
	<rdf:li rdf:resource="http://www.larsgeorge.com/2009/10/hive-vs-pig.html"/>
	<rdf:li rdf:resource="http://www.cloudera.com/hadoop-data-intensive-application-tutorial"/>
	<rdf:li rdf:resource="http://wiki.apache.org/hama/GraphPackage"/>
	<rdf:li rdf:resource="http://www.slideshare.net/kevinweil/hadoop-pig-and-twitter-nosql-east-2009"/>
	<rdf:li rdf:resource="http://cluster-fork.info/index.php?title=Main_Page"/>
	<rdf:li rdf:resource="http://databeta.wordpress.com/2009/10/18/mapreduce-online/"/>
	<rdf:li rdf:resource="http://www.manamplified.org/archives/2008/11/hadoop-is-about-scalability.html"/>
	<rdf:li rdf:resource="http://www.cloudera.com/blog/2009/10/15/analyzing-human-genomes-with-hadoop/"/>
	<rdf:li rdf:resource="http://www.cloudera.com/desktop"/>
	<rdf:li rdf:resource="http://riak.basho.com/"/>
	<rdf:li rdf:resource="http://www.cloudera.com/blog/2009/07/31/tracking-trends-with-hadoop-and-hive-on-ec2/"/>
	<rdf:li rdf:resource="http://www.umiacs.umd.edu/~jimmylin/cloud-computing/NAACL-HLT-2009/index.html"/>
	<rdf:li rdf:resource="http://db.cs.yale.edu/hadoopdb/hadoopdb.html"/>
	<rdf:li rdf:resource="http://dbmsmusings.blogspot.com/2009/07/announcing-release-of-hadoopdb-longer.html"/>
	<rdf:li rdf:resource="http://project-voldemort.com/blog/2009/06/building-a-1-tb-data-cycle-at-linkedin-with-hadoop-and-project-voldemort/"/>
	<rdf:li rdf:resource="http://thinkvitamin.com/dev/should-you-go-beyond-relational-databases/"/>
	<rdf:li rdf:resource="http://rcrowley.org/2009/06/27/bashreduce"/>
	<rdf:li rdf:resource="http://www.facebook.com/note.php?note_id=89508453919"/>
	<rdf:li rdf:resource="http://blog.marcua.net/post/117671929/mit-database-systems-6-830-ta-course-notes"/>
	<rdf:li rdf:resource="http://www.cloudera.com/hadoop"/>
	<rdf:li rdf:resource="http://cwiki.apache.org/confluence/display/MAHOUT/Mahout+on+Elastic+MapReduce"/>
	<rdf:li rdf:resource="http://huguk.org/2009/04/huguk-2-wrap-up.html"/>
	<rdf:li rdf:resource="http://pypi.python.org/pypi/hash_ring/1.2"/>
	<rdf:li rdf:resource="http://www.greenplum.com/"/>
	<rdf:li rdf:resource="http://lucene.apache.org/mahout/taste.html"/>
	<rdf:li rdf:resource="http://www.dbms2.com/2009/04/15/cloudera-presents-the-mapreduce-bull-case/#more-751"/>
	<rdf:li rdf:resource="http://www.cloudera.com/blog/2009/04/22/using-hadoop-to-annotate-billions-of-web-documents-with-semantics/"/>
	<rdf:li rdf:resource="http://developer.amazonwebservices.com/connect/entry!default.jspa?categoryID=265&amp;externalID=2294&amp;fromSearchPage=true"/>
	<rdf:li rdf:resource="http://aws.amazon.com/elasticmapreduce/"/>
	<rdf:li rdf:resource="http://berkeley-mltea.pbwiki.com/Hadoop-for-Machine-Learning-Guide"/>
	<rdf:li rdf:resource="http://www.engr.uvic.ca/~seng474/"/>
	<rdf:li rdf:resource="http://jimbojw.com/wiki/index.php?title=Understanding_Hbase_and_BigTable"/>
	<rdf:li rdf:resource="http://bishop.camp.clarkson.edu/wiki/en/Annotated_Bibliography_of_Cloud_Computing_Papers"/>
	<rdf:li rdf:resource="http://bishop.camp.clarkson.edu/wiki/en/EE694_21_-_Cloud_Computing_and_Hadoop"/>
	<rdf:li rdf:resource="http://horicky.blogspot.com/2009/01/solving-tf-idf-using-map-reduce.html"/>
	<rdf:li rdf:resource="http://www.infosci.cornell.edu/hadoop/mac.html"/>
	<rdf:li rdf:resource="http://www.ece.rutgers.edu/~parashar/Classes/08-09/ece572/slides.html"/>
	<rdf:li rdf:resource="http://www.cloudera.com/blog/2009/02/02/the-small-files-problem/"/>
	<rdf:li rdf:resource="http://www.princesspolymath.com/princess_polymath/2008/10/hadoop-and-aws-and-python-oh-m.html"/>
	<rdf:li rdf:resource="http://github.com/tuulos/ringo/tree/master"/>
	<rdf:li rdf:resource="http://code.google.com/p/happy/"/>
	<rdf:li rdf:resource="http://www.cs.brandeis.edu/~cs147a/lab/hadoop-example/"/>
	<rdf:li rdf:resource="http://web.mit.edu/rabbah/www/conferences/08/stmcs/papers/catanzaro-stmcs08.pdf"/>
	<rdf:li rdf:resource="http://discoproject.org/"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="http://highlyscalable.wordpress.com/2012/02/01/mapreduce-patterns/">
    <title>MapReduce Patterns, Algorithms, and Use Cases « Highly Scalable</title>
    <dc:date>2012-02-10T22:55:00+00:00</dc:date>
    <link>http://highlyscalable.wordpress.com/2012/02/01/mapreduce-patterns/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Good stuff well explained.]]></description>
<dc:subject>algorithms hadoop mapreduce java patterns</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:7eadff2b1c66/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:patterns"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lwn.net/Articles/452307/">
    <title>Data Warehousing 101 [LWN.net]</title>
    <dc:date>2011-09-23T15:49:55+00:00</dc:date>
    <link>http://lwn.net/Articles/452307/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A look at data warehousing.]]></description>
<dc:subject>bigdata data databases mapreduce</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:3b48c1f06a8c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://strangeloop-riak-mapred.heroku.com/#1">
    <title>Wrap Your SQL Head Around Riak MapReduce</title>
    <dc:date>2011-09-22T15:49:36+00:00</dc:date>
    <link>http://strangeloop-riak-mapred.heroku.com/#1</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[The strangeloop edition of the Riak MapReduce talk.]]></description>
<dc:subject>riak basho mapreduce map reduce</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:c8ee20802c76/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:riak"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:basho"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://infolab.stanford.edu/~ullman/mmds.html">
    <title>Mining of Massive Datasets</title>
    <dc:date>2011-09-19T13:29:47+00:00</dc:date>
    <link>http://infolab.stanford.edu/~ullman/mmds.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Looks like a fantastic book on data mining.]]></description>
<dc:subject>book books data datamining mapreduce</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:eb6b8070f544/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:book"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://borthakur.com/ftp/RealtimeHadoopSigmod2011.pdf">
    <title>Apache Hadoop Goes Realtime at Facebook</title>
    <dc:date>2011-07-18T14:47:14+00:00</dc:date>
    <link>http://borthakur.com/ftp/RealtimeHadoopSigmod2011.pdf</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Elephants gone wild.]]></description>
<dc:subject>hadoop hbase mapreduce programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:42284ab7d3fe/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hbase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.dataspora.com/2011/04/pigs-bees-and-elephants-a-comparison-of-eight-mapreduce-languages/">
    <title>Pigs, Bees, and Elephants: A Comparison of Eight MapReduce Languages « Dataspora</title>
    <dc:date>2011-04-28T14:42:15+00:00</dc:date>
    <link>http://www.dataspora.com/2011/04/pigs-bees-and-elephants-a-comparison-of-eight-mapreduce-languages/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice overview of toolkits.]]></description>
<dc:subject>hadoop hive java mapreduce pig</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:714acebe26c0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:pig"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://tech.backtype.com/the-dark-side-of-hadoop">
    <title>The dark side of Hadoop - BackType Technology</title>
    <dc:date>2011-04-22T21:23:57+00:00</dc:date>
    <link>http://tech.backtype.com/the-dark-side-of-hadoop</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[These are the kinds of things that you don't find out until you've been knee deep in something for awhile.]]></description>
<dc:subject>hadoop apache java mapreduce map-reduce</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:5b6b6e5316e9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map-reduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.basho.com/2011/03/30/why-mapreduce-is-easy/">
    <title>The Basho Blog: Why MapReduce is Easy</title>
    <dc:date>2011-04-05T04:41:27+00:00</dc:date>
    <link>http://blog.basho.com/2011/03/30/why-mapreduce-is-easy/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[It's not that hard, silly.]]></description>
<dc:subject>javascript learning mapreduce programming riak</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:7ec0ddd7d9f5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:riak"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://code.google.com/p/appengine-pipeline/">
    <title>appengine-pipeline - Project Hosting on Google Code</title>
    <dc:date>2011-03-13T06:37:10+00:00</dc:date>
    <link>http://code.google.com/p/appengine-pipeline/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Data processing pipelines on Appengine using Python.  Looks super useful.]]></description>
<dc:subject>appengine google mapreduce workflow</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:5290d8400852/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:appengine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:workflow"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.cloudant.com/39351506">
    <title>MapReduce from the basics to the actually useful (in under 30 minutes) - Cloudant</title>
    <dc:date>2011-01-24T07:12:35+00:00</dc:date>
    <link>http://blog.cloudant.com/39351506</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A really solid Map/Reduce primer using aviation data.]]></description>
<dc:subject>couchdb database mapreduce tutorial nosql aviation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:28d2c856069d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:couchdb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aviation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://brandynwhite.com/">
    <title>Brandyn White - Computer Vision, Hadoop, Mobile Computing, Kinect, and Big Data</title>
    <dc:date>2011-01-24T06:53:41+00:00</dc:date>
    <link>http://brandynwhite.com/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A Cython-based MapReduce library.]]></description>
<dc:subject>python cython hadoop mapreduce</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mcroydon/b:4333e0d1b17d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cython"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://engineeringblog.yelp.com/2010/10/mrjob-distributed-computing-for-everybody.html">
    <title>Yelp Engineering Blog: mrjob: Distributed Computing for Everybody</title>
    <dc:date>2010-11-19T15:48:48+00:00</dc:date>
    <link>http://engineeringblog.yelp.com/2010/10/mrjob-distributed-computing-for-everybody.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A really nice wrapper around EMR.
]]></description>
<dc:subject>algorithms amazon aws cloudcomputing computing data hadoop framework distributed dist development datamining library map-reduce map mapreduce nosql opensource yelp webservices search reduce python programming aa elasticmapreduce logs emr mrjob</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:1d48bdd4a112/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:framework"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dist"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map-reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:yelp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:webservices"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aa"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:elasticmapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:logs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:emr"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mrjob"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://s4.io/">
    <title>s4: distributed stream computing platform</title>
    <dc:date>2010-11-14T19:44:49+00:00</dc:date>
    <link>http://s4.io/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA["S4 is a general-purpose, distributed, scalable, partially fault-tolerant, pluggable platform that allows programmers to easily develop applications for processing continuous unbounded streams of data."
]]></description>
<dc:subject>apache bigdata cloud cloudcomputing cluster computing mapreduce map java hadoop framework distributed data opensource processing platform programming real-time streaming stream software scalability reduce realtime streamprocessing yahoo tool s4 streams</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:a494420d52a7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:framework"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:platform"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:real-time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:streaming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:stream"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:realtime"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:streamprocessing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:yahoo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tool"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:s4"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:streams"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.dist-systems.bbn.com/people/krohloff/papers/2010/SHARD_Rohloff_Kurt_HadoopWorld_2010.pdf">
    <title>SHARD: Storing and Querying Large-Scale SemWeb Data</title>
    <dc:date>2010-11-01T16:55:07+00:00</dc:date>
    <link>http://www.dist-systems.bbn.com/people/krohloff/papers/2010/SHARD_Rohloff_Kurt_HadoopWorld_2010.pdf</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[An excellent slide deck presenting SHARD at HadoopWorld.
]]></description>
<dc:subject>rdf triplestore hadoop hdfs mapreduce lubm</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:d84f9c68c474/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:triplestore"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hdfs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lubm"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.dist-systems.bbn.com/people/krohloff/shard.shtml">
    <title>SHARD Triple-Store</title>
    <dc:date>2010-10-31T02:00:39+00:00</dc:date>
    <link>http://www.dist-systems.bbn.com/people/krohloff/shard.shtml</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA["SHARD is a proof-of-concept use of high-performance, low-cost distributed computing technology to develop a highly scalable triple-store. SHARD is released as an open-source project on the BSD license."
]]></description>
<dc:subject>database db cloud distributed hadoop lubm mapreduce rdf store sparql storage shard semweb semanticweb scalability triple-store</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:41e1d4df6da6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lubm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:store"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sparql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:shard"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:semweb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:semanticweb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:triple-store"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.theregister.co.uk/2010/09/09/google_caffeine_explained/">
    <title>Google search index splits with MapReduce • The Register</title>
    <dc:date>2010-09-14T14:16:36+00:00</dc:date>
    <link>http://www.theregister.co.uk/2010/09/09/google_caffeine_explained/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Teach the world to Zig then Zag.
]]></description>
<dc:subject>algorithms architecture bigdata article bigtable gfs distributed database computing computers caffeine google grid hadoop index indexing mapreduce technology search scalability research programming colossus gfs2 news</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:45c601cf2c30/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:article"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigtable"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gfs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:caffeine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:grid"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:index"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:indexing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:colossus"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gfs2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:news"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://code.google.com/p/appengine-mapreduce/">
    <title>appengine-mapreduce - Project Hosting on Google Code</title>
    <dc:date>2010-07-18T03:14:46+00:00</dc:date>
    <link>http://code.google.com/p/appengine-mapreduce/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Pretty slick that it's built atop vanilla appengine.
]]></description>
<dc:subject>appengine cloud cloud-computing google gae hadoop saas python optimization nosql mapreduce scalability webdev develop</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:b099bb1b7140/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:appengine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gae"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:saas"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:webdev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:develop"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.google.com/buzz/bslatkin/6SXDRWXFWkN">
    <title>Buzz by Brett Slatkin from One Big Fluke</title>
    <dc:date>2010-07-07T18:29:27+00:00</dc:date>
    <link>http://www.google.com/buzz/bslatkin/6SXDRWXFWkN</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Impressive.
]]></description>
<dc:subject>gae mapreduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:eb868cc94cf3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gae"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/blog/2010/03/how-raytheon-researchers-are-using-hadoop-to-build-a-scalable-distributed-triple-store/">
    <title>How Raytheon Researchers are Using Hadoop to Build a Scalable, Distributed Triple Store « Cloudera » Apache Hadoop for the Enterprise</title>
    <dc:date>2010-03-22T16:45:33+00:00</dc:date>
    <link>http://www.cloudera.com/blog/2010/03/how-raytheon-researchers-are-using-hadoop-to-build-a-scalable-distributed-triple-store/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Triplestores and Hadoop.  Together.
]]></description>
<dc:subject>hadoop triplestore article articles cloud cloudcomputing cloudera database hdfs graphs graph distributed development mapreduce nosql programming repository rdf scalability toread sparql semanticweb shard semantic_web semantic triple web</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:8f32556cdbb5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:triplestore"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:article"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:articles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hdfs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:repository"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sparql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:semanticweb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:shard"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:semantic_web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:semantic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:triple"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.lucidimagination.com/blog/2010/03/16/integrating-apache-mahout-with-apache-lucene-and-solr-part-i-of-3/">
    <title>Lucid Imagination » Integrating Apache Mahout with Apache Lucene and Solr – Part I (of 3)</title>
    <dc:date>2010-03-18T18:08:24+00:00</dc:date>
    <link>http://www.lucidimagination.com/blog/2010/03/16/integrating-apache-mahout-with-apache-lucene-and-solr-part-i-of-3/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[It looks like it's pretty darn easy to hook up Solr and Mahout.  I can't wait to read more.
]]></description>
<dc:subject>analysis apache learning hadoop lucene machinelearning solr searchengine opensource mapreduce ml nlp mahout textmining toread</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:60926e146580/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lucene"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:solr"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:searchengine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ml"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mahout"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:textmining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.larsgeorge.com/">
    <title>Lineland</title>
    <dc:date>2010-03-15T14:39:16+00:00</dc:date>
    <link>http://www.larsgeorge.com/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Scroll through for lots and lots of HBase internals.
]]></description>
<dc:subject>blog distributed hadoop hbase nosql mapreduce programming systems storage reference</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:1d6d8b575857/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hbase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://glinden.blogspot.com/2010/03/gfs-and-its-evolution.html">
    <title>Geeking with Greg: GFS and its evolution</title>
    <dc:date>2010-03-15T03:08:55+00:00</dc:date>
    <link>http://glinden.blogspot.com/2010/03/gfs-and-its-evolution.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Interesting problems in light of how many people have copied parts of GFS, BigTable, and MapReduce.
]]></description>
<dc:subject>via:chl google gfs mapreduce bigtable</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:a6ed7c839c51/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:via:chl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gfs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigtable"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/blog/2010/03/why-europes-largest-ad-targeting-platform-uses-hadoop/">
    <title>Why Europe’s Largest Ad Targeting Platform Uses Hadoop « Cloudera » Apache Hadoop for the Enterprise</title>
    <dc:date>2010-03-10T22:46:55+00:00</dc:date>
    <link>http://www.cloudera.com/blog/2010/03/why-europes-largest-ad-targeting-platform-uses-hadoop/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Moving from Postgres to HDFS + Pig and MapReduce for large data storage, analysis, and aggregation.
]]></description>
<dc:subject>clojure data cloud database development hadoop mapreduce web nosql</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:e8e920e306cb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:clojure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.umiacs.umd.edu/~jimmylin/book.html">
    <title>Data-Intensive Text Processing with MapReduce</title>
    <dc:date>2010-02-23T17:10:37+00:00</dc:date>
    <link>http://www.umiacs.umd.edu/~jimmylin/book.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[I flipped through this during the conference and need to read through it more thoroughly.
]]></description>
<dc:subject>programming design data reference book free books geek pdf text hadoop distributed online algorithm algorithms mapreduce datamining to-read ebooks nlp ir textmining distributedcomputing text-mining developers draft</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:751b6d5ad729/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:book"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:free"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:geek"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:text"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:online"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:to-read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ebooks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ir"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:textmining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributedcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:developers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:draft"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.larsgeorge.com/2009/11/hbase-vs-bigtable-comparison.html">
    <title>Lineland: HBase vs. BigTable Comparison</title>
    <dc:date>2009-11-27T13:54:47+00:00</dc:date>
    <link>http://www.larsgeorge.com/2009/11/hbase-vs-bigtable-comparison.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice feature rundown as compared to BigTable.
]]></description>
<dc:subject>google reference database toread storage hadoop distributed bigtable comparison mapreduce nosql hbase compare</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:cc9df35153c7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigtable"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:comparison"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hbase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:compare"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/hadoop-world-nyc">
    <title>Hadoop World: NYC 2009 | Cloudera</title>
    <dc:date>2009-11-25T15:54:58+00:00</dc:date>
    <link>http://www.cloudera.com/hadoop-world-nyc</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[All of the presentation decks in one place.  Handy.
]]></description>
<dc:subject>hadoop presentation yahoo mapreduce cloud list slides conference 2009 presentations event cloudera foss world new conferences nyc hadoopworld</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:4485a258793e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:presentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:yahoo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:list"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:slides"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:conference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:2009"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:presentations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:event"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:foss"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:world"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:new"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:conferences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nyc"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoopworld"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.larsgeorge.com/2009/10/hive-vs-pig.html">
    <title>Lineland: Hive vs. Pig</title>
    <dc:date>2009-11-19T16:52:10+00:00</dc:date>
    <link>http://www.larsgeorge.com/2009/10/hive-vs-pig.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Different tools for different jobs, but it's hard choosing sometimes when you're in the Hadoop ecosystem.
]]></description>
<dc:subject>database hadoop mapreduce comparison hive pig</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:d84d7e7e1ae8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:comparison"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:pig"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/hadoop-data-intensive-application-tutorial">
    <title>Building a Data Intensive Web Application with Cloudera, Hadoop, Hive, Pig, and EC2 | Cloudera</title>
    <dc:date>2009-11-19T16:42:58+00:00</dc:date>
    <link>http://www.cloudera.com/hadoop-data-intensive-application-tutorial</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice look at end-to-end data analysis of big datasets using things like Pig and Hive.
]]></description>
<dc:subject>programming web data database tools webdev business toread howto tutorial amazon dev scalability hadoop architecture aws computing cluster ec2 pig trends hive cloudera cloudcomputing analytics datamining mapreduce cloud application</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:6affcd635d71/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:webdev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:business"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:pig"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:trends"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:application"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://wiki.apache.org/hama/GraphPackage">
    <title>GraphPackage - Hama Wiki</title>
    <dc:date>2009-11-05T21:45:19+00:00</dc:date>
    <link>http://wiki.apache.org/hama/GraphPackage</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Graph + Hadoop.
]]></description>
<dc:subject>hadoop scalability graph mapreduce graphs networks open_source academia graphdb</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:63d2aaedd96c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:open_source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:academia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graphdb"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.slideshare.net/kevinweil/hadoop-pig-and-twitter-nosql-east-2009">
    <title>Hadoop, Pig, and Twitter (NoSQL East 2009)</title>
    <dc:date>2009-11-04T15:18:22+00:00</dc:date>
    <link>http://www.slideshare.net/kevinweil/hadoop-pig-and-twitter-nosql-east-2009</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[An awesome deck showing of Pig and how Twitter uses it.
]]></description>
<dc:subject>programming data database howto server dev search statistics hadoop presentation mapreduce datamining twitter analytics slides presentations nosql bigdata socialnetworks slideshare hdfs pig big functional data_mining</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:ca5b09a21ac8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:server"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:presentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:twitter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:slides"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:presentations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:socialnetworks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:slideshare"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hdfs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:pig"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:big"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:functional"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data_mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://cluster-fork.info/index.php?title=Main_Page">
    <title>GoodDoop</title>
    <dc:date>2009-10-22T17:33:24+00:00</dc:date>
    <link>http://cluster-fork.info/index.php?title=Main_Page</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice set of recipes for Hadoop that probably translate well to other Map/Reduce architectures.
]]></description>
<dc:subject>wiki algorithms algorithm hadoop mapreduce examples recipe</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:6eace2609fbf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:wiki"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:recipe"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://databeta.wordpress.com/2009/10/18/mapreduce-online/">
    <title>MapReduce Online! (and some gimmes) « Data Beta</title>
    <dc:date>2009-10-20T01:15:44+00:00</dc:date>
    <link>http://databeta.wordpress.com/2009/10/18/mapreduce-online/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A potential game-changer?
]]></description>
<dc:subject>dataprocessing berkeley hop google database research performance online distributed hadoop streaming realtime stream analytics parallel optimization mapreduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:635bbe171905/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dataprocessing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:berkeley"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:online"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:streaming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:realtime"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:stream"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:parallel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.manamplified.org/archives/2008/11/hadoop-is-about-scalability.html">
    <title>Hadoop Is About Scalability, Not Performance - manAmplified</title>
    <dc:date>2009-10-19T13:06:48+00:00</dc:date>
    <link>http://www.manamplified.org/archives/2008/11/hadoop-is-about-scalability.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Word.
]]></description>
<dc:subject>programming google java scalability performance hadoop mapreduce concurrency cascading unread</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:78b09f97a4ae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:concurrency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cascading"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:unread"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/blog/2009/10/15/analyzing-human-genomes-with-hadoop/">
    <title>Analyzing Human Genomes with Hadoop » Cloudera Hadoop &amp; Big Data Blog</title>
    <dc:date>2009-10-17T19:48:01+00:00</dc:date>
    <link>http://www.cloudera.com/blog/2009/10/15/analyzing-human-genomes-with-hadoop/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A fantastic writeup of absurdly fast sequencing software that can analyze a human genome in about 3 hours for less than $100 of AWS resources.  Pretty darned impressive.
]]></description>
<dc:subject>data opensource computer amazon algorithms aws hadoop ec2 mapreduce dna bioinformatics cloudera trend genetics genome foss genomics</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:9269c592c357/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dna"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:trend"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:genome"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:foss"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:genomics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/desktop">
    <title>Cloudera Desktop | Cloudera</title>
    <dc:date>2009-10-12T15:02:24+00:00</dc:date>
    <link>http://www.cloudera.com/desktop</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A GUI for scheduling jobs and checking in on your cluster.
]]></description>
<dc:subject>programming web software development tools distributed ui management computing hadoop cloud cluster clustering mapreduce os gui tool backup desktop admin cloudera monitor operations</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:3b37f2a712a0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ui"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:management"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:os"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gui"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tool"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:backup"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:desktop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:admin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:monitor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:operations"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://riak.basho.com/">
    <title>Riak - A Decentralized Database</title>
    <dc:date>2009-10-08T21:08:11+00:00</dc:date>
    <link>http://riak.basho.com/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA["Riak combines a decentralized key-value store, a flexible map/reduce engine, and a friendly HTTP/JSON query interface to provide a database ideally suited for Web applications." Erlang under the hood.
]]></description>
<dc:subject>programming web development key-value database webdev opensource erlang storage scalability distributed rest databases http mapreduce json db couchdb store kvstore datastore keyvalue nosql document cloudcomputing riak decentralized basho documentoriented key-value-store</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:dbe6bca299bb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:key-value"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:webdev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:erlang"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rest"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:http"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:json"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:couchdb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:store"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:kvstore"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datastore"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:keyvalue"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:document"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:riak"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:decentralized"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:basho"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:documentoriented"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:key-value-store"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/blog/2009/07/31/tracking-trends-with-hadoop-and-hive-on-ec2/">
    <title>Tracking Trends with Hadoop and Hive on EC2 » Cloudera Hadoop &amp; Big Data Blog</title>
    <dc:date>2009-08-10T17:50:33+00:00</dc:date>
    <link>http://www.cloudera.com/blog/2009/07/31/tracking-trends-with-hadoop-and-hive-on-ec2/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A detailed run through of data warehousing and creating trending results for wikipedia data.
]]></description>
<dc:subject>python data database howto tutorial wikipedia rails scaling hadoop aws resources ec2 cloud mapreduce datamining sparklines rubyonrails trends hive cloudera bigdata log t trendingtopics</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:536b7f01e471/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:wikipedia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:resources"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sparklines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rubyonrails"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:trends"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:log"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:t"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:trendingtopics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.umiacs.umd.edu/~jimmylin/cloud-computing/NAACL-HLT-2009/index.html">
    <title>NAACL/HLT 2009 Tutorial: Data-Intensive Text Processing with MapReduce</title>
    <dc:date>2009-08-04T12:27:14+00:00</dc:date>
    <link>http://www.umiacs.umd.edu/~jimmylin/cloud-computing/NAACL-HLT-2009/index.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA["This half-day tutorial introduces participants to data-intensive text processing with the MapReduce programming model (Dean and Ghemawat, 2004), using the open-source Hadoop implementation."
]]></description>
<dc:subject>tutorial hadoop graph slides mapreduce nlp machine_learning textmining via:pskomoroch</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:b3cac86bf2b1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:slides"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:textmining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:via:pskomoroch"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://db.cs.yale.edu/hadoopdb/hadoopdb.html">
    <title>HadoopDB Project</title>
    <dc:date>2009-07-27T15:39:58+00:00</dc:date>
    <link>http://db.cs.yale.edu/hadoopdb/hadoopdb.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Interesting approach, we'll see if it has legs.
]]></description>
<dc:subject>programming software development database java opensource research scalability distributed performance scaling hadoop cluster postgresql databases mysql hadoopdb map-reduce hive dbms rdbms 2009 analytics postgres db sql mapreduce yale vldb</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:0ca3fea1098f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:postgresql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mysql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoopdb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map-reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:2009"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:postgres"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:yale"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:vldb"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://dbmsmusings.blogspot.com/2009/07/announcing-release-of-hadoopdb-longer.html">
    <title>DBMS Musings: Announcing release of HadoopDB (longer version)</title>
    <dc:date>2009-07-21T15:41:59+00:00</dc:date>
    <link>http://dbmsmusings.blogspot.com/2009/07/announcing-release-of-hadoopdb-longer.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[/me increments the "databases atop hadoop" counter (and takes a sip).
]]></description>
<dc:subject>database opensource scalability research distributed performance hadoop cluster postgresql mapreduce project datawarehouse hadoopdb distributedcomputing</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:e1c2b6eef6f5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:postgresql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datawarehouse"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoopdb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributedcomputing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://project-voldemort.com/blog/2009/06/building-a-1-tb-data-cycle-at-linkedin-with-hadoop-and-project-voldemort/">
    <title>Project Voldemort Blog : Building a terabyte-scale data cycle at LinkedIn with Hadoop and Project Voldemort</title>
    <dc:date>2009-07-02T19:21:23+00:00</dc:date>
    <link>http://project-voldemort.com/blog/2009/06/building-a-1-tb-data-cycle-at-linkedin-with-hadoop-and-project-voldemort/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[More on what makes Voldemort tick.
]]></description>
<dc:subject>design development data database toread erlang java scalability storage architecture distributed performance scaling hadoop cluster grid cloud mapreduce db caching analytics arch key-value dht keyvalue scale voldemort batch linkedin datastore</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:8229cef4b60f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:erlang"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:grid"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:caching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:arch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:key-value"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dht"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:keyvalue"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scale"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:voldemort"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:batch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:linkedin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datastore"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://thinkvitamin.com/dev/should-you-go-beyond-relational-databases/">
    <title>Should you go Beyond Relational Databases? | Think Vitamin</title>
    <dc:date>2009-07-02T19:14:57+00:00</dc:date>
    <link>http://thinkvitamin.com/dev/should-you-go-beyond-relational-databases/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Includes links to a bunch of graph databases too.
]]></description>
<dc:subject>programming development web data reference database toread technology opensource dev scalability storage work hadoop article graph databases mysql nosql keyvalue bigtable rdbms resource reading couchdb comparison db mapreduce relational alternative</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:cc6b14ac1ac2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:work"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:article"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mysql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:keyvalue"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigtable"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:resource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reading"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:couchdb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:comparison"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:relational"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:alternative"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://rcrowley.org/2009/06/27/bashreduce">
    <title>BashReduce — Richard Crowley’s blog</title>
    <dc:date>2009-07-02T19:05:24+00:00</dc:date>
    <link>http://rcrowley.org/2009/06/27/bashreduce</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[More BashReduce awesomeness.
]]></description>
<dc:subject>programming data map hack hadoop distributed unix analysis mapreduce scripting shell reduce bash last.fm merge lib multicore script dist bashreduce rsync</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:e7395491eea6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hack"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:unix"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scripting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:shell"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bash"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:last.fm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:merge"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lib"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:multicore"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:script"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dist"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bashreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rsync"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.facebook.com/note.php?note_id=89508453919">
    <title>Engineering @ Facebook's Notes | Facebook</title>
    <dc:date>2009-06-23T17:05:39+00:00</dc:date>
    <link>http://www.facebook.com/note.php?note_id=89508453919</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Big big big data warehousing / data mining.
]]></description>
<dc:subject>design data database blog java map scalability storage distributed computing scaling article hadoop sql mapreduce db reading facebook analytics rdbms arch comment hive datawarehouse warehouse data-warehousing hdfs dw</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:276f269e387f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:article"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reading"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:facebook"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:arch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:comment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datawarehouse"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:warehouse"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data-warehousing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hdfs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dw"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.marcua.net/post/117671929/mit-database-systems-6-830-ta-course-notes">
    <title>MIT Database Systems (6.830) TA Course Notes - marcua's blog</title>
    <dc:date>2009-06-06T09:28:51+00:00</dc:date>
    <link>http://blog.marcua.net/post/117671929/mit-database-systems-6-830-ta-course-notes</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Good looking lightweight TA notes.
]]></description>
<dc:subject>programming reference data database tutorial toread blog education free computing databases learning cs mapreduce sql db notes academic mit course lectures lecture courses class rdbms bigtable systems 6.830 10 ta</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:7a2d7c812759/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:toread"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:education"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:free"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:notes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:academic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:course"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lectures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:courses"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:class"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigtable"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:6.830"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:10"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ta"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/hadoop">
    <title>Cloudera's Distribution for Hadoop | Cloudera</title>
    <dc:date>2009-06-02T14:20:34+00:00</dc:date>
    <link>http://www.cloudera.com/hadoop</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Includes lots of feature tickets that are pretty stable but not yet in a Hadoop release.  It reminds me a lot of Debian unstable or Ubuntu a month or so before release.  Good stuff indeed.  Includes RPM and APT package management options.
]]></description>
<dc:subject>software data linux google search aws distributed computing ec2 hadoop cloud mapreduce cloudcomputing distribution clusters packaging cloudera cloud-computing rpm apt</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:cecfa4552c98/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:linux"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distribution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:clusters"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:packaging"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rpm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apt"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://cwiki.apache.org/confluence/display/MAHOUT/Mahout+on+Elastic+MapReduce">
    <title>Mahout on Elastic MapReduce - Apache Lucene Mahout - Apache Software Foundation</title>
    <dc:date>2009-05-26T18:34:55+00:00</dc:date>
    <link>http://cwiki.apache.org/confluence/display/MAHOUT/Mahout+on+Elastic+MapReduce</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Nice.
]]></description>
<dc:subject>mahout mapreduce hadoop</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:2a8ed9723fdd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mahout"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://huguk.org/2009/04/huguk-2-wrap-up.html">
    <title>Hadoop User Group UK: HUGUK #2 - Wrap up</title>
    <dc:date>2009-05-07T11:49:28+00:00</dc:date>
    <link>http://huguk.org/2009/04/huguk-2-wrap-up.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice collection of Hadoop decks/presentations.
]]></description>
<dc:subject>programming development java presentation framework hadoop apache community mapreduce slides uk london presentations videos class hbase 2009 last.fm mahout pagerank cloudera usergroup</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:64293891cbf0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:presentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:framework"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:community"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:slides"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:uk"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:london"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:presentations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:videos"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:class"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hbase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:2009"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:last.fm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mahout"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:pagerank"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudera"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:usergroup"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://pypi.python.org/pypi/hash_ring/1.2">
    <title>Python Package Index : hash_ring 1.2</title>
    <dc:date>2009-05-05T20:42:11+00:00</dc:date>
    <link>http://pypi.python.org/pypi/hash_ring/1.2</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Yay consistent hashing!
]]></description>
<dc:subject>python distributed memcached mapreduce hashing</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:ec6bf8dfc719/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:memcached"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hashing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.greenplum.com/">
    <title>Greenplum: the petabyte-scale database for data warehousing and business intelligence.</title>
    <dc:date>2009-05-01T13:16:45+00:00</dc:date>
    <link>http://www.greenplum.com/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Petabyte data mining and data warehousing.
]]></description>
<dc:subject>programming software development data database business technology opensource storage scalability performance cluster postgresql startup open postgres sql mapreduce datamining db analytics oss reporting rdbms intelligence bi businessintelligence datawarehouse greenplum bizgres</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:97d792e18079/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:business"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:postgresql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:startup"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:open"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:postgres"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:sql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:oss"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reporting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:businessintelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datawarehouse"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:greenplum"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bizgres"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lucene.apache.org/mahout/taste.html">
    <title>Apache Mahout - Taste Documentation</title>
    <dc:date>2009-04-29T20:47:34+00:00</dc:date>
    <link>http://lucene.apache.org/mahout/taste.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Collaborative filtering as part of the Mahout project.  Also includes a web services interface for interfacing with non-Java stuff.
]]></description>
<dc:subject>software java search algorithm cluster apache mapreduce machinelearning engine filtering recommendation webservice recommendations mahout</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:2bf20e73c089/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:engine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:recommendation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:webservice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:recommendations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mahout"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.dbms2.com/2009/04/15/cloudera-presents-the-mapreduce-bull-case/#more-751">
    <title>Cloudera presents the MapReduce bull case | DBMS2 -- DataBase Management System Services</title>
    <dc:date>2009-04-29T16:18:37+00:00</dc:date>
    <link>http://www.dbms2.com/2009/04/15/cloudera-presents-the-mapreduce-bull-case/#more-751</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Yay hadoop.
]]></description>
<dc:subject>hadoop mapreduce rdbms</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:308ffdd7b5ab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:rdbms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/blog/2009/04/22/using-hadoop-to-annotate-billions-of-web-documents-with-semantics/">
    <title>Cloudera Hadoop &amp; Big Data Blog » Blog Archive » Using Hadoop to Annotate Billions of Web Documents with Semantics</title>
    <dc:date>2009-04-23T14:52:29+00:00</dc:date>
    <link>http://www.cloudera.com/blog/2009/04/22/using-hadoop-to-annotate-billions-of-web-documents-with-semantics/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Not sure how much meat there is in this article, but what they're doing sounds awesome.
]]></description>
<dc:subject>search scaling hadoop mapreduce examples semantic</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:f9cb2f613a5e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:examples"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:semantic"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://developer.amazonwebservices.com/connect/entry!default.jspa?categoryID=265&amp;externalID=2294&amp;fromSearchPage=true">
    <title>Amazon Web Services Developer Community : Finding Similar Items with Amazon Elastic MapReduce, Python, and Hadoop Streaming</title>
    <dc:date>2009-04-03T05:05:31+00:00</dc:date>
    <link>http://developer.amazonwebservices.com/connect/entry!default.jspa?categoryID=265&amp;externalID=2294&amp;fromSearchPage=true</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Excellent tutorial on diving in to Hadoop streaming on AWS.
]]></description>
<dc:subject>python howto code amazon aws streaming ec2 hadoop netflix mapreduce recommendation similarity</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:ffed17087601/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:streaming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:netflix"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:recommendation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:similarity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://aws.amazon.com/elasticmapreduce/">
    <title>Amazon Elastic MapReduce</title>
    <dc:date>2009-04-02T12:32:37+00:00</dc:date>
    <link>http://aws.amazon.com/elasticmapreduce/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[!!!
]]></description>
<dc:subject>development data database amazon scalability s3 online aws computing analysis ec2 hadoop grid cloud mapreduce service cloudcomputing reduce amazing webservice jaylinks cloud-computing elastic</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:e4b7493121cc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:s3"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:online"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:aws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:grid"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:service"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:webservice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:jaylinks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:elastic"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://berkeley-mltea.pbwiki.com/Hadoop-for-Machine-Learning-Guide">
    <title>UC Berkeley Machine Learning Tea / Hadoop for Machine Learning Guide</title>
    <dc:date>2009-03-15T18:30:31+00:00</dc:date>
    <link>http://berkeley-mltea.pbwiki.com/Hadoop-for-Machine-Learning-Guide</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Nice and simple example of ML in Java with Hadoop from the Berkeley ML tea.
]]></description>
<dc:subject>research hadoop mapreduce datamining machinelearning machine_learning regression</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:794b77cb6a31/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.engr.uvic.ca/~seng474/">
    <title>Seng 474 - Spring2009, Course Outline, Alex Thomo</title>
    <dc:date>2009-03-11T04:15:11+00:00</dc:date>
    <link>http://www.engr.uvic.ca/~seng474/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[I love the smell of data mining in the spring.
]]></description>
<dc:subject>python code mapreduce slides datamining lectures machinelearning course</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:14fb902b4520/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:slides"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:lectures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:course"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jimbojw.com/wiki/index.php?title=Understanding_Hbase_and_BigTable">
    <title>Understanding HBase and BigTable - Jimbojw.com</title>
    <dc:date>2009-03-03T04:40:24+00:00</dc:date>
    <link>http://jimbojw.com/wiki/index.php?title=Understanding_Hbase_and_BigTable</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Excellent introduction to HBase.
]]></description>
<dc:subject>data google reference database howto tutorial java blog scalability architecture cluster distributed article hadoop grid mapreduce db cloudcomputing articles bigtable hbase overview differences relationaldb</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:e6e970b7662d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:article"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:grid"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:db"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloudcomputing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:articles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:bigtable"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hbase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:overview"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:relationaldb"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://bishop.camp.clarkson.edu/wiki/en/Annotated_Bibliography_of_Cloud_Computing_Papers">
    <title>Annotated Bibliography of Cloud Computing Papers - JAMWiki</title>
    <dc:date>2009-03-02T15:52:37+00:00</dc:date>
    <link>http://bishop.camp.clarkson.edu/wiki/en/Annotated_Bibliography_of_Cloud_Computing_Papers</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice list.
]]></description>
<dc:subject>cloud computing hadoop mapreduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:afe16957e1d3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://bishop.camp.clarkson.edu/wiki/en/EE694_21_-_Cloud_Computing_and_Hadoop">
    <title>EE694 21 - Cloud Computing and Hadoop - JAMWiki</title>
    <dc:date>2009-03-02T12:18:46+00:00</dc:date>
    <link>http://bishop.camp.clarkson.edu/wiki/en/EE694_21_-_Cloud_Computing_and_Hadoop</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice roundup of external links.
]]></description>
<dc:subject>hadoop course learning mapreduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:64938be698ca/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:course"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://horicky.blogspot.com/2009/01/solving-tf-idf-using-map-reduce.html">
    <title>Pragmatic Programming Techniques: Solving TF-IDF using Map-Reduce</title>
    <dc:date>2009-02-27T22:19:08+00:00</dc:date>
    <link>http://horicky.blogspot.com/2009/01/solving-tf-idf-using-map-reduce.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[This is pretty simple and would apply to CouchDB pretty easily.
]]></description>
<dc:subject>programming search algorithm mapreduce ir</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:2599ccbd08e0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:algorithm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ir"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.infosci.cornell.edu/hadoop/mac.html">
    <title>Cornell Web Lab: Hadoop</title>
    <dc:date>2009-02-25T12:35:02+00:00</dc:date>
    <link>http://www.infosci.cornell.edu/hadoop/mac.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Running Hadoop on OSX is relatively easy.
]]></description>
<dc:subject>reference mac tutorial java hadoop mapreduce install</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:4d8a4657eb47/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mac"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:install"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.ece.rutgers.edu/~parashar/Classes/08-09/ece572/slides.html">
    <title>ECE-572 Lecture Schedule &amp; Overheads</title>
    <dc:date>2009-02-24T05:00:05+00:00</dc:date>
    <link>http://www.ece.rutgers.edu/~parashar/Classes/08-09/ece572/slides.html</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A nice collection of Map/Reduce readings so far.
]]></description>
<dc:subject>mapreduce distributed computing course compsci</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:10165068eba2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:course"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:compsci"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cloudera.com/blog/2009/02/02/the-small-files-problem/">
    <title>Cloudera Hadoop &amp; Big Data Blog » Blog Archive » The Small Files Problem</title>
    <dc:date>2009-02-06T16:40:14+00:00</dc:date>
    <link>http://www.cloudera.com/blog/2009/02/02/the-small-files-problem/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Use a HARbl.
]]></description>
<dc:subject>filesystem performance hadoop mapreduce small file tips</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:5faa246c8836/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:filesystem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:small"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:file"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tips"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.princesspolymath.com/princess_polymath/2008/10/hadoop-and-aws-and-python-oh-m.html">
    <title>Hadoop and AWS and Python, Oh My! - Princess Polymath</title>
    <dc:date>2008-12-26T11:01:27+00:00</dc:date>
    <link>http://www.princesspolymath.com/princess_polymath/2008/10/hadoop-and-aws-and-python-oh-m.html</link>
    <dc:creator>mcroydon</dc:creator><dc:subject>python howto tutorial amazon ec2 hadoop mapreduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:351b8666fdd2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://github.com/tuulos/ringo/tree/master">
    <title>tuulos's ringo at master — GitHub</title>
    <dc:date>2008-12-18T18:30:19+00:00</dc:date>
    <link>http://github.com/tuulos/ringo/tree/master</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[immutable key/value store written on top of Disco, a map/reduce framework built by Nokia Research.
]]></description>
<dc:subject>python database nokia erlang storage scalability scaling distributed cache mogilefs parallel hash caching cloud distribution mapreduce dbms consistent hashing ringo dht dynamo</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:34a2231f3c91/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nokia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:erlang"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scaling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mogilefs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:parallel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hash"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:caching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distribution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dbms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:consistent"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hashing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ringo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dht"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dynamo"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://code.google.com/p/happy/">
    <title>happy - Google Code</title>
    <dc:date>2008-10-21T18:03:57+00:00</dc:date>
    <link>http://code.google.com/p/happy/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[I still think I like pure python + Hadoop streaming but I'll definitely keep this in mind.
]]></description>
<dc:subject>python programming software development google code howto library java dev scalability architecture apache cluster framework distributed opensource grid hadoop mapreduce concurrency nlp via:pskomoroch jython happy metaweb freebase map-reduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:f0004dfc34e3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:howto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:framework"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:grid"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:concurrency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:via:pskomoroch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:jython"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:happy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:metaweb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:freebase"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map-reduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.brandeis.edu/~cs147a/lab/hadoop-example/">
    <title>Hadoop Example Program</title>
    <dc:date>2008-10-11T20:50:14+00:00</dc:date>
    <link>http://www.cs.brandeis.edu/~cs147a/lab/hadoop-example/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[A simple Python Hadoop program that doesn't involve word counts!
]]></description>
<dc:subject>python programming tutorial java code distributed source hadoop todo mapreduce example via:pskomoroch</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:291ec1ccae48/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:todo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:example"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:via:pskomoroch"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://web.mit.edu/rabbah/www/conferences/08/stmcs/papers/catanzaro-stmcs08.pdf">
    <title>A Map Reduce Framework for Programming Graphics Processors</title>
    <dc:date>2008-09-10T20:27:06+00:00</dc:date>
    <link>http://web.mit.edu/rabbah/www/conferences/08/stmcs/papers/catanzaro-stmcs08.pdf</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[Map/Reduce in CUDA.  Thanks for the tip, Alex.
]]></description>
<dc:subject>cuda gpu map reduce mapreduce</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:d460a08a6c1d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cuda"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:gpu"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://discoproject.org/">
    <title>Disco</title>
    <dc:date>2008-09-04T15:26:48+00:00</dc:date>
    <link>http://discoproject.org/</link>
    <dc:creator>mcroydon</dc:creator><description><![CDATA[I think I need to change my pants.
]]></description>
<dc:subject>python programming software open-source development data nokia distributed-computing database erlang library dev map research scalability computing cluster distributed reduce mapreduce cloud opensource parallel concurrency hadoop ec2 framework</dc:subject>
<dc:identifier>https://pinboard.in/u:mcroydon/b:8ed7b65dc145/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:nokia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:erlang"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:dev"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:map"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cluster"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:mapreduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:cloud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:parallel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:concurrency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mcroydon/t:framework"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>