Analytics WG meeting

Europe/Zurich
31/S-023 (CERN)

31/S-023

CERN

22
Show room on map

News

  • Dirk and Christian are preparing a CHEP paper about the work of the group, it will be presented before the conference to allow for feedback
  • The IT Hadoop cluster is fully operational again, after an update to the newest cloudera version
  • There will be a discussion about how to best integrate the CMS file popularity adata into the Hadoop cluster

ATLAS analytics

  • Iliya found it difficult to get information on the status of hadoop jobs and the hadoop cluster. Rainer will add a short description on how to get some information to the TWiki page.
    We should have a Tutorial session onthis.
  • There is a problem with inconsistent information on the current 2 xroot collectors. The concerned parties will discuss "offline" how to best deal with this, by comparing the results to a 3rd collector prototype Iliya created.

 

Statistics Introduction and Tools

  • The presented IPython Notebook should also work with e.g. Spark access to the Hadoop cluster.
  • Domenico and Andrea are open for specific questions or problems to be covered in the second part of their statistics tutorial
There are minutes attached to this event. Show them.
    • 14:00 14:05
      Minutes & News 5m
      Speaker: Dirk Duellmann (CERN)
    • 14:05 14:15
      Overview ATLAS Analytics 10m
      Speaker: Ilija Vukotic (University of Chicago (US))
      Slides
    • 14:15 14:55
      Statistics Introduction 40m
      Speakers: Dr Andrea Valassi (CERN), Dr Domenico Giordano (CERN)
      Slides