We are like tenant farmers chopping down the fence around our house for fuel when we should be using Nature's inexhaustible sources of energy -- sun, wind and tide.... I'd put my money on the sun and solar energy. What a source of power! I hope we don't have to wait until oil and coal run out before we tackle that.

This codebase tries to predict the output of solar panels based on properties and historic output of the panel, and the weather report. This is done using different kinds of regression algorithms, a recurrent neural network and a fully connected neural network

Contains weather and solar panel data of several postal codes and years, also contains the code used to generate this data (match.py)

Contains the main function to test and train in the data

Contains all the SCRUM meeting held during this project, and information about the most important decisions made during th project

Data to train on can be placed here

Data to test on can be placed here