Analyzing US Census Data in Python

Learn to use the Census API to work with demographic and socioeconomic data.

Data scientists in diverse fields, from marketing to public health to civic hacking, need to work with demographic and socioeconomic data. Government census agencies offer richly detailed, high-quality datasets, but the number of variables and intricacies of administrative geographies (what is a Census tract anyway?) can make approaching this goldmine a daunting process. This course will introduce you to the Decennial Census and the annual American Community Survey, and show you where to find data on household income, commuting, race, family structure, and other topics that may interest you. You will use Python to request this data using the Census API for large and small geographies. You will manipulate the data using pandas, and create derived data such as a measure of segregation. You will also get a taste of the mapping capabilities of geopandas.

• Decennial Census of Population and Housing
• Start exploring Census data products with the Decennial Census. Use the Census API and the requests package to retrieve data, load into pandas data frames, and conduct exploratory visualization in seaborn. Learn about important Census geographies, including states, counties, and tracts.
• American Community Survey
• Explore topics such as health insurance coverage and gentrification using the American Community Survey. Calculate Margins of Error and explore change over time. Create choropleth maps using geopandas.
• Measuring Segregation
• Explore racial segregation in America. Calculate the Index of Dissimilarity, and important measure of segregation. Learn about and use Metropolitan Statistical Areas, and important geography for urban research. Study segregation changes over time in Chicago.
• Exploring Census Topics
• In this chapter, you will apply what you have learned to four topical studies. Explore unemployment by race and ethnicity; commuting patterns and worker density; immigration and state-to-state population flows; and rent burden in San Francisco.