If I use the command in the graph,I will get ten split files,but there are not enough data in every file,because you set the val_frac and test_frac as 0.1,which will make the portion of the remaining samples are (1-0.1-0.1)*0.75=0.6,losing 20% original data.
If I use the command in the graph,I will get ten split files,but there are not enough data in every file,because you set the val_frac and test_frac as 0.1,which will make the portion of the remaining samples are (1-0.1-0.1)*0.75=0.6,losing 20% original data.