EPFL Machine Learning Higgs is a project that was launched in 2014 by the CERN and is aimed to determine the presence of a Higgs Boson with measurements. To do so, a model has to be defined through machine learning methods, with a supplied training data.
After the model is determined with the training data, the results are submitted on the AIcrowd platform, in order to measure the accuracy of the model's predictions.
This version was designed for python 3.6.6 or higher. To run the model's calculation, it is only needed to execute the file run.py. On the terminal, the command is python run.py. The code should return a results.csv file with all its predictions, from the test data.
A train data and a testing data, where the results are unknown, are needed in .csv format. These data are available on the Resources of AIcrowd platform. Both files should be placed in a folder named data to run properly the code.
To avoid dysfunctions, the code need the files:
implementation.pydata_analysis.pyoptimization.pyproj1_helpers.py
Those files contain functions that are used by the main code run.py.
The folder Test_implementations also contains the testing of the different functions implemented in implementation.py, under different conditions. To run those files, the same files as before are needed.
The file ML_Projet1.pdf correspond to the documentation of the project.
- Class Project 1 : Description of the project.
- Resources: Datas for the training and testing.
- Group name: MLBudget
- Members: Aubet Louise, Cadillon Alexandre, Hoggett Emma
The project was submitted on the 28 October 2019, as part of the Machine Learning course.