Tackling Homelessness with Open Data
summary
San Diego regional data library scrapes HUD and local PDFs, builds a reproducible pipeline with a Python image extractor plus OCR, issues GitHub tickets and uses the VIA annotation tool to georeference 350 monthly downtown maps into ~20,000 annotations, producing a digitized time series (about 3,600 unsheltered and ~8,000 total downtown). Students find a cluster tied to a theater closure. Exploratory analyses use GeoPandas, Google Colab and FFTs and yield no strong correlations with crime or pedestrian counts; the workflow largely succeeds but several months remain missing.
AI-written summary · about
chapters (11)
- 0:00Homelessness data work
- 2:18Point-in-time homeless counts
- 6:29Homelessness data sources
- 9:18Digitizing homelessness maps
- 13:10Homelessness clustering project
- 15:57Map digitization with Python
- 18:49San Diego homelessness trends
- 23:08Homelessness and pedestrian traffic
- 27:07Crime patterns and homelessness
- 31:16Open questions on homelessness data
- 35:33Q&A
related talks
38mCombining datasets to find solutions to homelessness
10mCivic Hacking & Urban Informatics: Mapping Data with GeoPandas
42mOpen Data & Maps As Tools for More Impact
51mWhat is a Data Desk?
42mData, Design, Code with Shirley Wu
18mAutomate Your City Data with Python
42mVisualizing COVID-19 Data
35mDesigning for Impact in Civic Data Science