Skip to content

Add new chemistry datasets #52

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
robin-janssen merged 1 commit into from
Dec 22, 2025
+15 −1
Merged

Add new chemistry datasets #52

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion codes/utils/data_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -651,6 +651,9 @@ def update_to(self, b=1, bsize=1, tsize=None):
def download_data(dataset_name: str, path: str | None = None, verbose: bool = True):
"""
Download the specified dataset if it is not present, with a progress bar.
The downloaded file is always renamed to 'data.hdf5', regardless of the
filename served by the remote source.

Args:
dataset_name (str): The name of the dataset.
path (str, optional): The path to save the dataset. If None, the default data directory is used.
Expand All @@ -661,6 +664,7 @@ def download_data(dataset_name: str, path: str | None = None, verbose: bool = Tr
if path is None
else os.path.abspath(path)
)

if os.path.isfile(data_path):
if verbose:
print(f"Dataset '{dataset_name}' already exists at {data_path}.")
Expand All @@ -679,11 +683,16 @@ def download_data(dataset_name: str, path: str | None = None, verbose: bool = Tr

os.makedirs(os.path.dirname(data_path), exist_ok=True)

tmp_path = data_path + ".tmp"

print(f"Downloading dataset '{dataset_name}'...")
with DownloadProgressBar(
unit="B", unit_scale=True, miniters=1, desc=f"Downloading {dataset_name}"
) as t:
urllib.request.urlretrieve(url, data_path, reporthook=t.update_to)
urllib.request.urlretrieve(url, tmp_path, reporthook=t.update_to)

os.replace(tmp_path, data_path)

print(f"Dataset '{dataset_name}' downloaded successfully.")
if verbose:
print_data_info(data_path)
Expand Down
5 changes: 5 additions & 0 deletions datasets/data_sources.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,3 +10,8 @@ branca_large_myr: "https://zenodo.org/records/14243267/files/data.hdf5?download=
coupled_oscillators: "https://zenodo.org/records/14717175/files/data.hdf5?download=1"
lv_parametric: https://zenodo.org/records/15412214/files/data.hdf5?download=1
lv_parametric_no_params: https://zenodo.org/records/15412297/files/data.hdf5?download=1
cloud: https://zenodo.org/records/18018572/files/codes_cloud_data.hdf5?download=1
cloud_parametric: https://zenodo.org/records/18018572/files/codes_cloud_parametric_data.hdf5?download=1
primordial: https://zenodo.org/records/18018572/files/codes_primordial_data.hdf5?download=1
primordial_parametric: https://zenodo.org/records/18018572/files/codes_primordial_parametric_data.hdf5?download=1