Código CNEFE 2010: An open pipeline for spatializing and categorizing the 2010 CNEFE in Brazil

CNEFE-Faces is an open-source Python pipeline designed to work with the Cadastro Nacional de Endereços para Fins Estatísticos (CNEFE 2010), produced by IBGE.

The software automates the process of:

1. Reading raw fixed-width TXT files (FWF) from the CNEFE 2010 database.
2. Building standardized geographic identifiers (ID_municipio, ID_setor, ID_face).
3. Categorizing addresses by their official usage codes (1–7).
4. Refining “Other establishments” (code 6) through keyword-based classification using the establishment description.
5. Linking TXT records directly with IBGE block-face shapefiles.
6. Exporting results as GeoPackage (GPKG) and CSV for GIS and urban analysis workflows.

This tool supports researchers in urban planning, geography, demography, and data science who need reproducible, documented, and extensible workflows for socio-spatial analysis.