Artificial intelligence and machine learning may be the focus of popular and media attention, but data scientists spend most of their time “wrangling” and “cleaning” data so that computers can produce useful information.
A public workshop on Tuesday, Oct. 2, will offer insights into this tedious but fundamental challenge. Thomas Donoghue of UC San Diego’s Department of Cognitive Science will explain the concepts behind data wrangling and cleaning — getting data loaded and checking it for quality.
The workshop at 6 p.m. at Downtown Works will explain how to use programs like Anaconda and Jupyter to scrape data from the Web and integrate data sets from multiple sources. Examples will be drawn from City of San Diego data.
Attendees should have a working knowledge of Python, a laptop with the required software installed and an interest in urban issues.