genderBR 1.4.0

This is a new version that introduces a new feature: asymmetrical thresholds for gender classification. In the previous versions, users could set a single threshold to classify names as female or male – and they could overlap if the threshold was too low. Now, users can set a different threshold for each sex, and there is a new check to prevent overlapping thresholds. The release also includes other improvements and bug fixes.

genderBR 1.3.0

This is a new version of the genderBR package that includes a new function: get_gender_nn(), which uses a character-level neural network to predict gender from Brazilian first names. This model can generalise to names not present in the IBGE census dataset, so it can be used as a complement to the existing functionality in the package. The release also includes some improvements, tests, and documentation updates.

genderBR 1.2.0

genderBR 1.1.1

In this version, a few improvements and bug fixed were introduced. Most important, connection errors now return informative messages to users.

genderBR 1.1.0

In this minor release, the genderBR package was improved in two ways. First, bugs and some minor issues were fixed, making the package’s functions more stable. Second, the package now contains an internal dataset with all the names reported by the IBGE’s Census that is used by the get_gender function to predict gender from Brazilian first names. Therefore, classifying a vector with more than 1,000 names takes no more than a few seconds now. Overall, these are the improvements: