/Random_forest_theoretical_practical_application

This brief project explores first the theoretical background behind Random Forest, followed by its application with the Boston Housing dataset

Primary LanguageJupyter Notebook

Random Forest application

Introduction

This project goes from the theorical explination about how Random Forests work, to a basic application of it.

What you'll find in this repository

  • What's Random Forest algorithm
  • Feature bagging concept explanation
  • Random Forest explained in 3 simple steps
  • How do we use Random Forest?
  • The out-of-bag sample

Practical application?

The practical application has been done with the one and only Boston Housing dataset. Revisiting how to load it from those who never worked with it, to later split it and rescale it in order to work with it.

Afterwards, you'll find the following techniques applied:

  • Fitting the data using a decision tree regressor
  • Performing Grid Search varying several features
  • Using ensemble methods to fit decision trees, including Bagging Regressor and of course, Random Forest