This repository contains materials for a Machine Learning tutorial given at HSF-India. It is structured as follows:
-
Notebooks: The main content of the tutorial is contained in Jupyter notebooks. These are interactive documents that combine text, equations, and executable code. They are named in the order they should be completed:
00-intro.ipynb: An introduction to the tutorial, organized as slides.01-tutorial-exercise-1.ipynb: The first exercise - a boosted decision tree tutorial based onxgboots.02-tutorial-exercise-2.ipynb: The second exercise - a fully connected NN based on TensorFlow.
-
Data: The file
dataWW_d1.rootcontains the data used in the exercises. -
Binder: The
binder/directory contains files used to create a Binder environment for this repository. Binder allows you to run Jupyter notebooks in your web browser without any setup. This was used with binder resources on the IRIS-HEP SSL. -
Requirements: The
requirements.txtfile lists the Python packages that need to be installed to run the notebooks to run locally on your laptop.
Please see the Installation and Usage sections for instructions on how to set up and use this project.
To install locally create a new python environment and load in all the packages in requirements.txt: pip install -r requirements.txt.
To run locally, start jupyter-lab from the command line with the jupyter-lab command, and connect with a browser at the given URL. You can then open the slides or exercise. You won't need a GPU to complete this work.