Metadata-Version: 2.1
Name: dgb
Version: 0.2
Summary: 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.
Author-email: Farimah Poursafaei <Farimah.poursafaei@mila.quebec>, Shenyang Huang <shenyang.huang@mail.mcgill.ca>, Abu bakar Daud <abubakar.daud@mail.mcgill.ca>
Project-URL: Homepage, https://github.com/fpour/TG_OpenSource
Project-URL: Bug Tracker, https://github.com/fpour/TG_OpenSource/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: args (==0.1.0)
Requires-Dist: idna (==3.4)
Requires-Dist: clint (==0.5.1)
Requires-Dist: jmespath (==1.0.1)
Requires-Dist: joblib (==1.2.0)
Requires-Dist: numpy (==1.23.4)
Requires-Dist: pandas (==1.5.1)
Requires-Dist: python-dateutil (==2.8.2)
Requires-Dist: pytz (==2022.6)
Requires-Dist: requests (==2.28.1)
Requires-Dist: scikit-learn (==1.1.3)
Requires-Dist: scipy (==1.9.3)
Requires-Dist: torch (==1.13.0)
Requires-Dist: tqdm (==4.64.1)
Requires-Dist: urllib3 (==1.26.12)
Requires-Dist: wget (==3.2)
Requires-Dist: zenodo-get (==1.3.4)
Requires-Dist: six (==1.16.0)
Requires-Dist: threadpoolctl (==3.1.0)
Requires-Dist: typing-extensions (==4.4.0)

Dynamic Graph Processing
=====
Provides
  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:
print(data_name)
```

to download all possible datasets that have not been downloaded yet::
```
dgb.download_all()
```

to force redownload all datasets::
```
dgb.force_download_all()
```

to skip download prompts and dataset statistics when processing::
```
dgb.TemporalDataSets(data_name="enron", skip_download_prompt=True, data_set_statistics=False)
```

## License

----------------------------
[MIT License](LICENSE)
