interconnect-explainability

** Visualizing Linear Regression and Random Forests insights on house hold data **

This repository contains examples of exploring explainability for two popular Machine Learning algorithms: Linear Regression and Random Forests. The dataset that we use for this demonstration is a combination of two publicly available datasets:

• The 'Konstanz' dataset comprising the energy consumption of various appliances from households (https://nbviewer.jupyter.org/github/isc-konstanz/household_data/blob/2020-04-15/main.ipynb)
• Weather data for Konstanz: https://www.worldweatheronline.com/konstanz-weather-history/baden-wurttemberg/de.aspx

Linear Regression is demonstrated here: https://github.com/rsiebes/interconnect-explainability/blob/main/Linear-regression-pumps.ipynb

Random Forests is demonstrated for three different heat pumps here:

• https://github.com/rsiebes/interconnect-explainability/blob/main/Random-forests-pumps1.ipynb
• https://github.com/rsiebes/interconnect-explainability/blob/main/Random-forests-pumps3.ipynb
• https://github.com/rsiebes/interconnect-explainability/blob/main/Random-forests-pumps6.ipynb