===== Machine Learning with Python (M2DSSAF) =====

=== Slides ===
{{:members:aguilloux:enseignements:machinelearningpython:cours_boosting.pdf|Boosting}}
{{:members:aguilloux:enseignements:machinelearningpython:cours_random_forests.pdf| Random forest}}
=== Labs ===
== Lab 1==
  * {{:members:aguilloux:enseignements:machinelearningpython:ml_lab_1.ipynb.zip| Lab 1}}
  * {{:members:aguilloux:enseignements:machinelearningpython:ml_lab_1_corrected.ipynb.zip| Lab 1 corrected}}
== Lab 2 ==
  * {{:members:aguilloux:enseignements:machinelearningpython:mnist.ipynb.zip| Lab 2}}
== Lab 3 ==
  * Lab 3 : comparer les algorithmes de ML sur https://archive.ics.uci.edu/ml/datasets/spambase
  * https://codeshare.io/5zPpwk


=== Challenge ===
The course will be evaluated via the Kaggle competition https://www.kaggle.com/c/porto-seguro-safe-driver-prediction#timeline. Vous devez former des équipes de 3 personnes maximum. Vous devrez rendre un rapport de 10 pages maximum (hors annexes) expliquant votre démarche.
Your reports have to be send by **January 12.**