ethnicolr2 and ethnicolr
Ethnicolr2 is a modernized PyTorch reimplementation of the original Ethnicolr library, making them successive versions in the same project lineage rather than independent tools.
About ethnicolr2
appeler/ethnicolr2
Ethnicolr implementation with new models in pytorch
About ethnicolr
appeler/ethnicolr
Predict Race and Ethnicity Based on the Sequence of Characters in a Name
Provides multiple prediction models trained on US Census, Florida voter registration, and Wikipedia data, with varying ethnic granularity depending on source. Uses TensorFlow 2.x neural networks to infer probabilities across demographic categories from first and/or last names, supporting both lookup tables for exact census matches and learned models for names absent from training data. Offers a modern Click-based CLI for batch processing, model management, and confidence interval estimation via Monte Carlo sampling, alongside a Python API for pandas DataFrames.
Scores updated daily from GitHub, PyPI, and npm data. How scores work