hannesdatta/musiclabels: Work with metadata frequently encountered in music datasets (e.g., classify clear-text names of music labels into (major-label) parent labels)

Collection of functions to more efficiently deal with metadata frequently encountered in music datasets (e.g., collected by Spotify Web API, Chartmetric, Musicbrainz, Discogs). Currently features a regular-expression based algorithm to classify clear-text names of music labels into one (or multiple) of their major-label parent labels (Sony, Warner, Universal). Algorithm validated on external training data provided by Chartmetric.com.

install.packages("remotes")
remotes::install_github("hannesdatta/musiclabels")