Fix data split

[kntkb]

This PR fixes #150 and #149

import espaloma as esp

RANDOM_SEED = 1234
path = "../../../exploring-rna/refit-espaloma/openff-default/02-train/merge-data/openff-2.0.0_filtered/pepconf-dlc"
ds = esp.data.dataset.GraphDataset.load(path).shuffle(RANDOM_SEED)
ds_tr, ds_vl, ds_te = ds.split([0.8, 0.1, 0.1])
print(len(ds), len(ds_tr), len(ds_vl), len(ds_te))

>>557 445 56 56

[codecov-commenter]

Codecov Report

❗ No coverage uploaded for pull request base (main@7165038). Click here to learn what that means.
The diff coverage is n/a.