What is a default split_size in model training?


When splitting the data into the test and training data what split size should I choose?

I was told that set by default is 80 % for training data,and 20 % for test data, can somebody ensure me?


The default split size in sklearn.model_selection.train_test_split is 75% training and 25% testing data split. Data splits should depend on the task at hand.

The rule of thumb is that you have enough representative data that represent your problem to train a model and a enough representative data to validate your trained model.

Answered By – Prayson W. Daniel

This Answer collected from stackoverflow, is licensed under cc by-sa 2.5 , cc by-sa 3.0 and cc by-sa 4.0

Leave a Reply

(*) Required, Your email will not be published