BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//talk//TL88MJ
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pydata-london-2026-TL88MJ@pretalx.com
DTSTART;TZID=GMT:20260607T153000
DTEND;TZID=GMT:20260607T161500
DESCRIPTION:Residential energy models like NREL’s ResStock generate the k
 ind of data most humans run from: thousands of buildings\, dozens of colum
 ns\, and at least 8\,760 rows per column. Great for research\, but difficu
 lt for anyone who just wants to ask\, “What happens to electricity deman
 d in Texas if homes used solar water heating?” or “How do HVAC upgrade
 s change my annual cooling costs in North Carolina?”\n\nJoin us for this
  session as a University of Texas energy researcher and a Red Hat engineer
  team up to see what large language models can realistically do with this 
 kind of messy\, domain-heavy data using Python. We’ll show how we sample
 \, reshape\, and describe large datasets so LLMs can help generate and ref
 ine pandas/DuckDB queries\, explain upgrade scenarios in plain English\, a
 nd guide non-experts through “what if” electrification questions. This
  and more\, all while being honest about where the models break down and w
 hy humans still need to do the science.
DTSTAMP:20260602T223228Z
LOCATION:Hardwick Hub
SUMMARY:What Can LLMs Do with Messy Residential Electrification Data? - Ced
 ric Clyburn\, Andrew Igdal
URL:https://pretalx.com/pydata-london-2026/talk/TL88MJ/
END:VEVENT
END:VCALENDAR