Created
June 11, 2021 01:19
-
-
Save yueyericardo/613c9c4ac1de3c53284514820e0e79ab to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from torchani.datasets import AniH5Dataset | |
import os | |
import cudf | |
try: | |
path = os.path.dirname(os.path.realpath(__file__)) | |
except NameError: | |
path = os.getcwd() | |
h5file = os.path.join(path, '../dataset/ani-1x/sample.h5') | |
dataset = AniH5Dataset(h5file) | |
print(list(dataset.keys())) | |
print(list(dataset['C01H01N03O02'])) | |
print(dataset['C01H01N03O02']['species']) | |
conformers = dataset.get_conformers('C01H01N03O02', raw_output=False) | |
print(conformers['species'].shape) | |
print(conformers['coordinates'].shape) | |
print(conformers['energies'].shape) | |
print(conformers['forces'].shape) | |
num_conf = conformers['species'].shape[0] | |
df = cudf.DataFrame({'energies': conformers['energies']}) | |
species = cudf.Series(conformers['species'].tolist()) | |
coordinates = cudf.Series(conformers['coordinates'].reshape(num_conf, -1).tolist()) | |
df['species'] = species | |
df['coordinates'] = coordinates | |
df.to_parquet('test.pq') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment