BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085743Z
LOCATION:HG F 3
DTSTART;TZID=Europe/Stockholm:20190612T160000
DTEND;TZID=Europe/Stockholm:20190612T163000
UID:submissions.pasc-conference.org_PASC19_sess129_msa228@linklings.com
SUMMARY:Scaling Interactive Data Analysis in Python with Dask
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Engin
 eering\n\nScaling Interactive Data Analysis in Python with Dask\n\nRocklin
 \n\nThis gives an overview of Dask, a framework for scalable computing wit
 hin Python. We give context around the SciPy ecosystem, an overview of the
  architecture, and examples of use on scientific problems today. The SciPy
 /PyData stack is popular among scientists today. Unfortunately it lacks sc
 alability, and was designed to run on a single core on data that fits in m
 emory. Users wanting to scale out their analyses often encounter frustrati
 on, and need to rewrite in MPI or Spark, which may cause challenges for us
 ers, IT administrators, or both. Dask is a Python-native distributed syste
 m that scales the scientific Python ecosystem. It is developed by core dev
 elopers in the NumPy, Pandas, Scikit-learn, and Jupyter projects, and inte
 grates well into that ecosystem, scaling up to a few thousand cores. Due t
 o the integration with the Python stack it is well suited to common scient
 ific workflows and data formats, and deploys well on widely deployed HPC j
 ob schedulers like SLURM and PBS. This talk gives an overview of Dask, exa
 mples of its use, and lessons learned from deploying it within HPC centres
  over the last few years, focusing on interactive use cases.
END:VEVENT
END:VCALENDAR