Mono- and Multi-view classification benchmark

This project aims to be an easy-to use solution to run a prior benchmark on a dataset abd evaluate mono- and multi-view algorithms capacity to classify it correctly.

Getting Started

In order to run it you'll need to try on simulated data with the command

python multiview-machine-learning-omis/Code/MonoMultiViewClassifiers/ExecClassif.py -log

Results will be stored in multiview-machine-learning-omis/Code/MonoMultiViewClassifiers/Results/

Prerequisites

To be able to use this project, you'll need :

• Python 2.7 - The web framework used

And the following python modules :

• pyscm - Set Covering Machine, Marchand, M., & Taylor, J. S. (2003) by A.Drouin, F.Brochu, G.Letarte St-Pierre, M.Osseni, P-L.Plante
• numpy, scipy
• matplotlib - Used to plot results
• sklearn - Used for the monoview classifiers
• joblib - Used to compute on multiple threads
• h5py - Used to generate HDF5 datasets on hard drive and use them to sapre RAM
• (argparse - Used to parse the input args)
• (logging - Used to generate log)

They are all tested in multiview-machine-mearning-omis/Code/MonoMutliViewClassifiers/Versions.py which is automatically checked each time you run the ExecClassif script

Installing

No installation is needed, just the prerequisites.

Running the tests

In order to run it you'll need to try on simulated data with the command

python multiview-machine-learning-omis/Code/MonoMultiViewClassifiers/ExecClassif.py -log

Results will be stored in multiview-machine-learning-omis/Code/MonoMultiViewClassifiers/Results/

Authors

• Baptiste BAUVIN