/neuralprophet-data

Datasets used for NeuralProphet tutorials

Primary LanguageJupyter NotebookMIT LicenseMIT

NeuralProphet Datasets

Here you can find the datasets used in the tutorials, including data preprocessing examples.

data sources: Energy Datasets

SF_PV

The SanFrancisco_PV solar data comes from DOE/NREL/ALLIANCE (https://nsrdb.nrel.gov/about/tmy.html)

The y values in the series correspond to GH illum (lx). The series contain a full year of hourly observations for 2015.

SF_hospital_load

SanFrancisco_Hospital load data comes from OpenEI (https://openei.org/doe-opendata/dataset/commercial-and-residential-hourly-load-profiles-for-all-tmy3-locations-in-the-united-states, or https://data.openei.org/submissions/153)

The y values in the series correspond to Electricity:Facility [kW](Hourly). The series contain a full year of hourly observations for 2015.

ERCOT load

ERCOT data comes from ERCOT http://www.ercot.com/gridinfo/load/load_hist.

The y value is the sum of all regions. The data is a hourly series from beginning of 2004 to September of 2021.

load RTE

Record of power consumption from French utility RTE: https://www.services-rte.com/en/download-data-published-by-rte.html?category=consumption&type=energy_consumption

hourly data from January 2017 to December 2018