Examples and Tutorials

This section contains Jupyter notebook examples that demonstrate the key features of pytidycensus. These notebooks are Python ports of the original tidycensus R vignettes, adapted for the Python ecosystem.

Getting Started

All examples require a free Census API key. Get one at: https://api.census.gov/data/key_signup.html

To run these notebooks locally:

pip install pytidycensus matplotlib seaborn jupyter
jupyter notebook examples/

Basic Usage

• Basic usage of pytidycensus

Learn the fundamentals of accessing Census data with pytidycensus:

• Setting up your Census API key

• Using get_decennial() and get_acs() functions

• Understanding data formats (tidy vs wide)

• Working with different geographic levels

• Searching for variables

Time Series Data

• Simple Time Series Analysis with Census Data
• Advanced Time Series Analysis: Handling Boundary Changes

Analyze trends over time with ACS data: * Fetching multi-year ACS data * Visualizing changes in demographics * Handling variable availability across years * Creating time series plots with matplotlib and seaborn

Spatial Data and Mapping

• Spatial data in pytidycensus
• Simple Migration Flows with pytidycensus
• Flow Brush Map API - Interactive Migration Visualization

Explore mapping and spatial analysis capabilities:

• Retrieving Census data with geometry

• Creating choropleth maps with matplotlib and geopandas

• Faceted mapping for multiple variables

• Working with coordinate reference systems

• Spatial data visualization best practices

• Interactive migration flow visualization with BrushingExtension (09_flow_brushmap_api)

Margins of Error

• Margins of error in the ACS

Understanding uncertainty in American Community Survey data:

• Working with estimates and margins of error

• Visualizing uncertainty in data

• Aggregating estimates and calculating derived margins of error

• Using margin of error functions for proper statistical analysis

Other Census Datasets

• Other Census Bureau datasets

Accessing additional Census datasets:

• Population Estimates Program data with get_estimates()

• Migration flows data with get_flows()

• Components of population change

• Housing estimates and characteristics

For interactive migration flow visualization, see the Flow Brushmap API example in the Spatial Data and Mapping section above.

Census Microdata

• Working with Census microdata

Advanced analysis with Public Use Microdata Sample (PUMS):

• Understanding microdata vs. aggregated data

• Working with Public Use Microdata Areas (PUMAs)

• Using survey weights for proper statistical inference

• Creating custom estimates from individual-level data

Additional Resources

• pytidycensus GitHub Repository

• Census API Documentation

• GeoPandas Documentation

• Original R tidycensus

Running Examples Online

All examples include “Open in Colab” badges for easy execution in Google Colab without local installation.

Contributing Examples

Have an interesting use case or analysis? We welcome contributions of additional examples:

1. Create a new Jupyter notebook following the existing format

2. Add descriptive markdown cells explaining the analysis

3. Include proper citations and data sources

4. Submit a pull request to the repository

For questions or suggestions about the examples, please open an issue on GitHub.

Come study with us at The George Washington University