cents-ml 1.0.0

A library for generating contextual timeseries data.

An open source project from Data to AI Lab at MIT.

Cents

A library for generative modeling and evaluation of synthetic household-level electricity load timeseries. This package is still under active development.

• Documentation: (tbd)

Overview

Cents is a library built for generating synthetic household-level electric load and generation timeseries. Cents supports several generative time series models that can be used to train a time series data generator from scratch on a user-defined dataset. Additionally, Cents provides functionality for loading pre-trained model checkpoints that can be used to generate data instantly. Trained models can be evaluated using a series of metrics and visualizations also implemented here.

These currently supported models are:

• Diffusion-TS
• ACGAN

Feel free to look at our tutorial notebooks to get started.

Install

Requirements

Cents has been developed and tested on Python 3.9, Python 3.10 and Python 3.11.

Also, although it is not strictly required, the usage of a virtualenv is highly recommended in order to avoid interfering with other software installed in the system in which Cents is run.

These are the minimum commands needed to create a virtualenv using python3.8 for Cents:

pip install virtualenv
virtualenv -p $(which python3.9) cents-venv

Afterwards, you have to execute this command to activate the virtualenv:

source cents-venv/bin/activate

Remember to execute it every time you start a new console to work on Cents!

Install from PyPI

After creating the virtualenv and activating it, we recommend using pip in order to install Cents:

pip install cents

This will pull and install the latest stable release from PyPI. -->

Datasets

If you want to reproduce our models from scratch, you will need to download the PecanStreet DataPort dataset and place it under the path specified in pecanstreet.yaml. Specifically you will require the following files:

• 15minute_data_austin.csv
• 15minute_data_california.csv
• 15minute_data_newyork.csv
• metadata.csv

What's next?

New models, new evaluation functionality and new datasets coming soon!