DAG-UPB/lotsa_energy

---
license: apache-2.0
configs:
- config_name: default
data_files:
- split: train
path: "*/*.arrow"
- config_name: "australian_electricity_demand"
data_files:
- split: train
path: "australian_electricity_demand/*.arrow"
- config_name: "bdg-2_bear"
data_files:
- split: train
path: "bdg-2_bear/*.arrow"
- config_name: "bdg-2_fox"
data_files:
- split: train
path: "bdg-2_fox/*.arrow"
- config_name: "bdg-2_panther"
data_files:
- split: train
path: "bdg-2_panther/*.arrow"
- config_name: "bdg-2_rat"
data_files:
- split: train
path: "bdg-2_rat/*.arrow"
- config_name: "borealis"
data_files:
- split: train
path: "borealis/*.arrow"
- config_name: "buildings_900k"
data_files:
- split: train
path: "buildings_900k/*.arrow"
- config_name: "bull"
data_files:
- split: train
path: "bull/*.arrow"
- config_name: "cockatoo"
data_files:
- split: train
path: "cockatoo/*.arrow"
- config_name: "covid19_energy"
data_files:
- split: train
path: "covid19_energy/*.arrow"
- config_name: "elecdemand"
data_files:
- split: train
path: "elecdemand/*.arrow"
- config_name: "elf"
data_files:
- split: train
path: "elf/*.arrow"
- config_name: "era5_2018"
data_files:
- split: train
path: "era5_2018/*.arrow"
- config_name: "gfc12_load"
data_files:
- split: train
path: "gfc12_load/*.arrow"
- config_name: "gfc14_load"
data_files:
- split: train
path: "gfc14_load/*.arrow"
- config_name: "gfc17_load"
data_files:
- split: train
path: "gfc17_load/*.arrow"
- config_name: "hog"
data_files:
- split: train
path: "hog/*.arrow"
- config_name: "ideal"
data_files:
- split: train
path: "ideal/*.arrow"
- config_name: "kdd2022"
data_files:
- split: train
path: "kdd2022/*.arrow"
- config_name: "kdd_cup_2018_with_missing"
data_files:
- split: train
path: "kdd_cup_2018_with_missing/*.arrow"
- config_name: "lcl"
data_files:
- split: train
path: "lcl/*.arrow"
- config_name: "london_smart_meters_with_missing"
data_files:
- split: train
path: "london_smart_meters_with_missing/*.arrow"
- config_name: "oikolab_weather"
data_files:
- split: train
path: "oikolab_weather/*.arrow"
- config_name: "pdb"
data_files:
- split: train
path: "pdb/*.arrow"
- config_name: "residential_load_power"
data_files:
- split: train
path: "residential_load_power/*.arrow"
- config_name: "residential_pv_power"
data_files:
- split: train
path: "residential_pv_power/*.arrow"
- config_name: "sceaux"
data_files:
- split: train
path: "sceaux/*.arrow"
- config_name: "smart"
data_files:
- split: train
path: "smart/*.arrow"
- config_name: "solar_power"
data_files:
- split: train
path: "solar_power/*.arrow"
- config_name: "spain"
data_files:
- split: train
path: "spain/*.arrow"
- config_name: "subseasonal"
data_files:
- split: train
path: "subseasonal/*.arrow"
- config_name: "subseasonal_precip"
data_files:
- split: train
path: "subseasonal_precip/*.arrow"
- config_name: "weather"
data_files:
- split: train
path: "weather/*.arrow"
- config_name: "wind_farms_with_missing"
data_files:
- split: train
path: "wind_farms_with_missing/*.arrow"
- config_name: "wind_power"
data_files:
- split: train
path: "wind_power/*.arrow"
---
# LOTSA Energy Data

This dataset is a filtered subset of the [Large-scale Open Time Series Archive (LOTSA)](https://huggingface.co/datasets/Salesforce/lotsa_data), which is a collection of open time series datasets for time series forecasting originally collected for pre-training Large Time Series Models.

## Dataset Description

This dataset contains only energy-related time series data extracted from the original LOTSA collection. The data has been:
- **Filtered** for energy-related datasets
- **Interpolated** linearly to fill missing values

## Citation

If you're using this dataset in your research or applications, please cite both this work and the original LOTSA dataset:

**This Work:**

```bibtex
@article{TODO,
title={TODO},
author={TODO},
journal={TODO},
year={TODO}
}
```

**Original LOTSA Dataset:**

```bibtex
@article{woo2024unified,
title={Unified Training of Universal Time Series Forecasting Transformers},
author={Woo, Gerald and Liu, Chenghao and Kumar, Akshat and Xiong, Caiming and Savarese, Silvio and Sahoo, Doyen},
journal={arXiv preprint arXiv:2402.02592},
year={2024}
}
```

See the [paper](https://arxiv.org/abs/2402.02592) and [codebase](https://github.com/SalesforceAIResearch/uni2ts) for more information about the original LOTSA dataset.

## Ethical Considerations

This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people's lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.