Skip to main content

Particle Dataset Downloader (v0.0.7)

A package for downloading a repository of particle physics datasets. All datasets can be accessed with a single line:

from particleloader import load
Data = load(DATASET_NAME, N_samples, cache_dir=dir)

See example.ipynb for detailed example usage.

Public Datasets:

As of the latest release, the public datasets are:

  • Quark/Gluon Jets: qg_jets, a dataset of quark and gluon jets with labels generated in Pythia or Herwig, with the option of including b and c quarks.
  • Top/QCD Jets: topqcd_jets, a dataset of quark and gluon jets with labels generated in Pythia or Herwig.
  • SPECTER LEP dijets: SPECTER_ee_dijets, a dataset of LEP-like e+e- collisions to hadrons generated in Pythia, as used in arxiv:2410:XXXXX
  • SPECTER QCD jets: SPECTER_qcd_jets, a dataset of QCD jets generated in Pythia, as used in arxiv:2410:XXXXX
  • SPECTER Top jets: SPECTER_top_jets, a dataset of top jets generated in Pythia, as used in arxiv:2410:XXXXX

It is relatively straightforward to add new datasets. If you have a dataset you would like to add, please let me know!

Installation

From this repository locally

In your Python environment from the top level of this repository run

python -m pip install .

From GitHub

In your Python environment run

python -m pip install "particleloader @ git+https://github.com/rikab/ParticleLoader.git"

Dependencies

The following python packages are required by the data formatter:

  • numpy
  • urllib3

Changelog

  • v0.0.7: 8 October 2024. SPECTER Datasets.
  • v0.0.6: 26 August 2024. SPECTER e+e- dijets.
  • v0.0.5: 14 August 2024. Overhaul, multiple datasets (top/qcd and q/g).
  • v0.0.3: 9 August 2023. Minor Bug Fixes.
  • v0.0.2: 8 August 2023. Pip-installable.
  • v0.0.1: 31 July 2023. Initial release.

Download files

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

Source Distribution

particleloader-0.0.7.post4.tar.gz (17.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

particleloader-0.0.7.post4-py3-none-any.whl (21.0 kB view details)

Uploaded Python 3

File details

Details for the file particleloader-0.0.7.post4.tar.gz.

File metadata

  • Download URL: particleloader-0.0.7.post4.tar.gz
  • Upload date:
  • Size: 17.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.8.16

File hashes

Hashes for particleloader-0.0.7.post4.tar.gz
Algorithm Hash digest
SHA256 fed231af5adb86052e11bf8a5247302a925759a06adacc1e475c0292caf7b95c
MD5 63f8e5d4c1803fb65b01bfa6758f245b
BLAKE2b-256 255f758635fac75ce3ff7a2da4648e0cb6f281dfc75ffcf45abd373f38b4afbc

See more details on using hashes here.

File details

Details for the file particleloader-0.0.7.post4-py3-none-any.whl.

File metadata

File hashes

Hashes for particleloader-0.0.7.post4-py3-none-any.whl
Algorithm Hash digest
SHA256 c2940fd62c932d89713be7f5796c440ff0f2f66322f8668739ee8393337ac3ad
MD5 5efd154be2341d7abf8fc42ebb0a329c
BLAKE2b-256 dc292d097ce018a658a8f6d13a205a586e04adc226df759790e821bd73e3bd56

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.0.7.post4 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page