Sparticles
Manipulate collision events via graphs and graph neural networks.
TL;DR
The EventsDataset, a Pytorch Geometric Dataset, allows you to download a dataset of graphs representing collisions.
from dataset import EventsDataset
graphs = EventsDataset(
root='/Users/alessiodevoto/Desktop/test_dataset3',
delete_raw_archive=False,
event_subsets={'signal': 100, 'singletop': 100, 'ttbar': 100},
url='<secret_url>')
graphs
EventsDataset(300)
Each event is a graph with 6/7 nodes. Each node is built from the raw file as follows:
| Particle | Feature 1 | Feature 2 | Feature 3 | Feature 4 | Feature 5 | Feature 6 |
|---|---|---|---|---|---|---|
| jet1 | 'pTj1' | 'etaj1' | 'phij1' | 'j1_quantile' | nan | nan |
| jet2 | 'pTj2' | 'etaj2' | 'phij2' | 'j2_quantile' | nan | nan |
| jet3 (optional) | 'pTj3' | 'etaj3' | 'phij3' | 'j3_quantile' | nan | nan |
| b1 | 'pTb1' | 'etab1' | 'phib1' | 'b1_quantile' | 'b1m' | nan |
| b2 | 'pTb2' | 'etab2' | 'phib2' | 'b2_quantile' | 'b2m' | nan |
| lepton | 'pTl1' | 'etal1' | 'phil1' | nan | nan | nan |
| energy | 'ETMiss' | nan | 'ETMissPhi' | nan | nan | 'metsig_New' |
g = graphs[0]
print(g)
Data(x=[6, 6], edge_index=[2, 30], y=[1], event_id='signal_6350')
from visualize import plot_event_2d
plot_event_2d(graphs[100])
a_list_of_graphs = [graphs[i] for i in range(0, 300, 30)]
plot_event_2d(a_list_of_graphs, height=1500)
Changelog
- version 0.0.4.3. Now the plotting function allows you to pass a show_edges and edges_weights parameters to display edges. Useful for visualizing attention maps.
1 maintainer
Metadata
1 maintainer
Release files for sparticles 0.0.4.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| sparticles-0.0.4.5.tar.gz | 12.0 kB | Without provenance | Details for sparticles-0.0.4.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| sparticles-0.0.4.5-py3-none-any.whl | Python 3 | none | any | Details for sparticles-0.0.4.5-py3-none-any.whl |
Total release size: 24.6 kB
Release files / sparticles-0.0.4.5.tar.gz
| Download URL | sparticles-0.0.4.5.tar.gz |
|---|---|
| Size | 12.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
05e68e1d758ce28b48887aa6da035f4f563a02d3eaa7b9bcabb41ed176763a24
|
|
BLAKE2b-256 checksum How to use checksums |
381c8089a6c0825f4e92c635dae1566da4ac92327cc9c08e920c9be2a66ab435
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.13
|
Release files / sparticles-0.0.4.5-py3-none-any.whl
| Download URL | sparticles-0.0.4.5-py3-none-any.whl |
|---|---|
| Size | 12.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
001a15ac05a856b6990fb8e8f6cd83931b8437261118346946657b9b51bf6dc4
|
|
BLAKE2b-256 checksum How to use checksums |
d3870085d13b21d4fe01fdf1a081b0e7439eff490a5943d9f7d5dc6a82d59eb2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.13
|
Security for sparticles 0.0.4.5
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
