The datasets in this package support the namesex package. The namesex package provides validated ML models to estimate sex of the person based on first name using the data in this package.
- Indian Politician Data
- Brazilian Politician Data
- Swedish Politician Data
- Indian Names Google Photo and Clarifai Data
To get the current development version from GitHub:
# install.packages("devtools")
devtools::install_github("appeler/namesexdata")The raw Brazilian candidate files in data-raw/br/data/rawData/ are archived
TSE (Tribunal Superior Eleitoral) exports. Their direct identifiers — CPF,
título eleitoral, and e-mail — have been blanked, here and throughout the
repository's history. The package uses only first name and sex; the blanked
columns were never read, and the shipped datasets are unchanged. To request
removal of other personal data, open an issue or e-mail the maintainer listed
in DESCRIPTION.
Scripts are released under the MIT License.