[Tutor] Explanation of one - hot encoding

[Tariq Khasiri]

This following line is from a kernel I am trying to replicate from Spotify
songs data. Could anyone kindly explain what this line means ?

“ In terms of encoding our artists and our genres we see one-hot encoding
is a bad idea here considering the cardinality of those features therefore
we will dummy encode the genres and replace the artist names with numerical
values closer to the model selection stage. ”