Skip to main content

Package for 'Towards better dynamic link prediction' paper at NeurIPS 2022, the code provides download, processing, dataloading and evaluation code for a suite of dynamic graph datasets.

Project description

Dynamic Graph Processing


  1. A data-loader to download a suite of dynamic graph datasets.
  2. An evaluator for the suit of dynamic graph datasets
  3. Tools to benchmark graph models, example code snippets, tutorials, etc. (ongoing...)

To install

use pip for Python, make sure version python version is 3.6+

>>> pip install dgb

Code examples

Code snippet to import the module::

import dgb

Code snippets to download a dataset::

enron = dgb.TemporalDataSets(data_name="enron")
enron_dict = enron.process()
train = enron_dict["train"]
test  = enron_dict["test"]
val   = enron_dict["validation"]

to print all possible datasets::

data_list = dgb.list_all()
for data_name in data_list:

to download all possible datasets that have not been downloaded yet::


to force redownload all datasets::


to skip download prompts and dataset statistics when processing::

dgb.TemporalDataSets(data_name="enron", skip_download_prompt=True, data_set_statistics=False)


MIT License

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dgb-0.2.tar.gz (21.7 kB view hashes)

Uploaded source

Built Distribution

dgb-0.2-py3-none-any.whl (20.4 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page