Skip to main content

DOI PyPI Python

StarCraft II Datasets

Library can be used to interface with datasets that were pre-processed with our pipeline as described in:

Currently we have exposed PyTorch and PyTorch Lightning API. Our goal is to provide infrastructure used for StarCraft II analytics.

Please refer to the official documentation, or contact contributors directly for all of the details.

Supported Datasets

SC2EGSet: StarCraft II Esport Game State Dataset

This project contains official API implementation for the works introduced in the following article: SC2EGSet: StarCraft II Esport Replay and Game-state Dataset, namely; Zenodo, SC2EGSet: StarCraft II Esport Game State Dataset, built based on Zenodo, SC2ReSet: StarCraft II Esport Replaypack Set. Contents of this library provide PyTorch and PyTorch Lightning API for pre-processed StarCraft II dataset.

Installation

  1. Manually install PyTorch with minimal version of ^1.11.0+cu116.
  2. Perform the following command:
$ pip install sc2_datasets

Usage

Basic example usage can be seen below. For advanced interactions with the datasets please refer to the documentation.

Use SC2EGSet with PyTorch:

from sc2_datasets.torch.sc2_egset_dataset import SC2EGSetDataset
from sc2_datasets.available_replaypacks import EXAMPLE_SYNTHETIC_REPLAYPACKS

if __name__ == "__main__":
    # Initialize the dataset:
    sc2_egset_dataset = SC2EGSetDataset(
        unpack_dir="./unpack_dir_path",           # Specify existing directory path, where the data will be unpacked.
        download_dir="./download_dir_path",       # Specify existing directory path, where the data will be downloaded.
        download=True,
        names_urls=EXAMPLE_SYNTHETIC_REPLAYPACKS, # Use a synthetic replaypack containing 1 replay.
    )

    # Iterate over instances:
    for i in range(len(sc2_egset_dataset)):
        sc2_egset_dataset[i]

Use SC2EGSet with PyTorch Lightning:

from sc2_datasets.lightning.sc2_egset_datamodule import SC2EGSetDataModule
from sc2_datasets.available_replaypacks import EXAMPLE_SYNTHETIC_REPLAYPACKS

if __name__ == "__main__":
    sc2_egset_datamodule = SC2EGSetDataModule(
                unpack_dir="./unpack_dir_path",            # Specify existing directory path, where the data will be unpacked.
                download_dir="./download_dir_path",        # Specify existing directory path, where the data will be downloaded.
                download=True,
                replaypacks=EXAMPLE_SYNTHETIC_REPLAYPACKS, # Use a synthetic replaypack containing 1 replay.
            )
    sc2_egset_datamodule.prepare_data()
    sc2_egset_datamodule.setup()

Contributing

Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Contributor License Agreement (CLA) and a Code of Conduct. By contributing to this project, you agree to abide by its terms.

License

sc2_datasets project was created by Andrzej Białecki. It is licensed under the terms of the GNU General Public License v3.0 license.

Cite

Dataset Description Article

To cite the article that introduces SC2ReSet and SC2EGSet use this:

@article{Bialecki2023,
  author   = {Bia{\l}ecki, Andrzej
              and Jakubowska, Natalia
              and Dobrowolski, Pawe{\l}
              and Bia{\l}ecki, Piotr
              and Krupi{\'{n}}ski, Leszek
              and Szczap, Andrzej
              and Bia{\l}ecki, Robert
              and Gajewski, Jan},
  title    = {SC2EGSet: StarCraft II Esport Replay and Game-state Dataset},
  journal  = {Scientific Data},
  year     = {2023},
  month    = {Sep},
  day      = {08},
  volume   = {10},
  number   = {1},
  pages    = {600},
  issn     = {2052-4463},
  doi      = {10.1038/s41597-023-02510-7},
  url      = {https://doi.org/10.1038/s41597-023-02510-7}
}

Release files for sc2-datasets 2.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sc2-datasets 2.1.0
File Size Uploaded
sc2_datasets-2.1.0.tar.gz 57.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for sc2-datasets 2.1.0
File Interpreter ABI Platform
sc2_datasets-2.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 159.8 kB

Release files / sc2_datasets-2.1.0.tar.gz

Download URL sc2_datasets-2.1.0.tar.gz
Size 57.5 kB
Tags Source
SHA-256 checksum
How to use checksums
3abb0c4817179516cb91774404951b34ff9c758f8ce090832649d51ebe84bcd7
BLAKE2b-256 checksum
How to use checksums
47430f53532e078e2cf89d502d15f02b10e9e22cc8ca2ffdc3ba2763ad1aabd7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jan 11, 2026.

Transparency log

Release files / sc2_datasets-2.1.0-py3-none-any.whl

Download URL sc2_datasets-2.1.0-py3-none-any.whl
Size 102.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
58766cec504763eb7bba705bfffd5af38606e420dbe029c055ad12a486dd7de3
BLAKE2b-256 checksum
How to use checksums
4edb7f1a123d1e8fd7a02e4100a48d0362f6d52ae704a788fe7c76ae06e9e5a1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jan 11, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

2.1.0 This release

2 release files

2.0.1

2 release files

1.1.0

2 release files

1.0.2

2 release files

1.0.1

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page