how is the data set split into training data and test data?

I notice the proportion is 3: 1, is there other criteria, like stratified by subject ID or outcome (on_off, dyskinesia, tremor), or just split by hand. I want to apply the same criteria of split on the training data set, which can help to get better generalization

Created by Jingan Qu Jingan_Qu
Data were split within subject to maintain the same class distributions across all 3 phenotypes.

Your web browser must have JavaScript enabled in order for this application to display correctly.
If you are an automated web crawler from a search engine, follow this AJAX application crawl link

I notice the proportion is 3: 1, is there other criteria, like stratified by subject ID or outcome (on_off, dyskinesia, tremor), or just split by hand. I want to apply the same criteria of split on the training data set, which can help to get better generalization

Drop files to upload

how is the data set split into training data and test data? page is loading…