bsm4tops-gnn
  • BSM4tops machine learning project
  • Introduction
  • Problem description
  • Concepts
    • Exotic heavy particles in four-top final states
    • Artificial neural networks
    • Graph neural networks
  • Hands-on: simple problem
    • Diving into python
    • Simulation of a four-top-quark process
    • Exploring the dataset
    • Creating a classifier
    • Artificial neural networks for classification
    • Graph neural networks for classification
Powered by GitBook
On this page
  • Introduction to python
  • Specific packages for High Energy Physics analysis:
  • Specific packages for data analysis:

Was this helpful?

  1. Hands-on: simple problem

Diving into python

PreviousGraph neural networksNextSimulation of a four-top-quark process

Last updated 3 years ago

Was this helpful?

We will use the python programming language throughout this project. Python is not only widely used in data analysis and science but also features a rich ecosystem of packages which provide industry-standard tools.

Introduction to python

A very good start into learning python is this course:

Complementary to it, you can have a look into these notebooks if you want to brush up specific aspects, such as the numpy or matplotlib packages:

As a reference, you can refer to the freely available book "Think python":

Specific packages for High Energy Physics analysis:

Opening ROOT files

Creating histograms in python

Creating and manipulating four-vectors

Specialised plotting routines and custom plot styles

Specific packages for data analysis:

Handling of columnar datasets

Data visualisation

Scikit-learn

PyTorch

https://swcarpentry.github.io/python-novice-inflammation
https://nbviewer.jupyter.org/github/jrjohansson/scientific-python-lectures/blob/master/Lecture-1-Introduction-to-Python-Programming.ipynb
https://nbviewer.jupyter.org/github/jrjohansson/scientific-python-lectures/blob/master/Lecture-2-Numpy.ipynb
https://nbviewer.jupyter.org/github/jrjohansson/scientific-python-lectures/blob/master/Lecture-4-Matplotlib.ipynb
https://www.datacamp.com/community/tutorials/pandas-tutorial-dataframe-python
https://greenteapress.com/thinkpython/thinkpython.pdf
LogoGitHub - scikit-hep/uproot4: ROOT I/O in pure Python and NumPy.GitHub
LogoGitHub - scikit-hep/hist: Histogramming for analysis powered by boost-histogramGitHub
LogoGitHub - scikit-hep/vector: Vector classes and utilitiesGitHub
LogoGitHub - scikit-hep/mplhep: A set of helpers for matplotlib to more easily produce plots typically needed in HEP as well as style them in way that's compatible with current collaboration requirements (ROOT).GitHub
Logopandas - Python Data Analysis Library
Logoseaborn: statistical data visualization — seaborn 0.11.2 documentation
Logoscikit-learn: machine learning in Python — scikit-learn 1.0.2 documentation
LogoPyTorch