Here are files for a project in statistical machine learning Boosting_algorithm.py uses booth AdaBoost and GradientBoosting with an ensamble of n=100 and important parameters found from featureimportance.py

featureimportance.py uses randomforests to find the most important features, prints it in order as well as plots it together with its standard deviation from.

Dataset is made to training and validation from splittning and using k-fold crossvalidation with k=10.

Testing_Features randomizes parameters n amounts of times, using Adaboost or GradientBoosting classification, depending on input in the function "boostingparameters".