HouseElectricityPrediction

Authors : Sivane Marciano - Oumane Seydina Niang - Yanis Fellah - Lounes Guergous - Marvin Tordjamn - Sajjad Mahdavi

In this project, the objective is to predict the electricity consumption in Watt-hours of a Belgian low energy house. The explanatory variables are temperature and humidity measurements from sensors in the house, as well as weather data from a nearby station and the global consumption of the country.

Getting started

Install

To run a submission and the notebook you will need the dependencies listed in requirements.txt. You can install the dependencies with the following command-line:

pip install -U -r requirements.txt

If you are using conda, we provide an environment.yml file for similar usage.

Challenge description

Get started with the dedicated notebook. It contains the following:

Table of Contents

1. Problem statement

2. Data Exploration

• Features Explanation
• Features Exploration

3. Data pre-processing

• Categorical Features
• Missing Values

3. Workflow

4. Submission details

5. RAMP submission

Test a submission

The submissions need to be located in the submissions folder. For instance for my_submission, it should be located in submissions/my_submission.

To run a specific submission, you can use the ramp-test command line:

ramp-test --submission my_submission

You can get more information regarding this command line:

ramp-test --help

To go further

You can find more information regarding ramp-workflow in the dedicated documentation