tidytitanic - Dataframes Based on Titanic Passengers and Crew
The tidytitanic package provides a version of the Titanic
data tailored for people analytics demonstrations and practice.
Unlike other packages such as titanic, which reproduce the
Kaggle competition files with minimal preprocessing,
tidytitanic combines and tidies the train and test datasets
into a single unified dataset, `passengers`, facilitating
exploration across the full set of individuals. It also
extracts meaningful personal identifiers—such as first names,
last names, and titles—from the raw Name field, enabling richer
demographic analysis and grouping. The `passengers` data does
not cover the crew, however. Therefore the package also
provides a flat and uncounted version of the `Titanic` dataset
which contains crew information for futher practice. This
human-centered data package is designed to support exploratory
data analysis, feature engineering, and pedagogical use cases.
