Random forest algorithm pipeline produced to participate to data challenge from ENS : https://challengedata.ens.fr/challenges/34 as part of the Machine Learning course project.
We also tried different NN and regressions to solve the problem and compare the results as part of the project. I only publish the random forest one which I produced on my own.
The main.ipynb contains the whole pipeline and tests.
The necessary datasets need to be downloaded and setup for the code to work as intended. See the data import section for more details.