n_sample -> N - Githubissues

ModelOriented / ingredients

Effects and Importances of Model Ingredients

https://modeloriented.github.io/ingredients/

GNU General Public License v3.0

37 stars 19 forks source link

n_sample -> N #113

Closed hbaniecki closed 4 years ago

hbaniecki commented 4 years ago

Following https://github.com/ModelOriented/DALEX/issues/175 I want to deprecate n_samples. Additionally, @pbiecek why is this sampling using replace? https://github.com/ModelOriented/ingredients/blob/9f8f82f05ddb87e4abf2fb20846f097113522a33/R/feature_importance.R#L196

No such behaviour here: https://github.com/ModelOriented/ingredients/blob/9f8f82f05ddb87e4abf2fb20846f097113522a33/R/partial_dependence.R#L109

pbiecek commented 4 years ago

replace = TRUE means that nrow(data) can be smaller than n_sample (because some observations ill be reused). On average it shall not make any difference if we use sampling with/without replacement.