> ## Documentation Index
> Fetch the complete documentation index at: https://nixtla-old-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> Download and wrangling utility for long-horizon datasets.

# Long-Horizon Datasets

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L68" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### ETTm2

> ```text theme={null}
>  ETTm2 (freq:str='15T', name:str='ETTm2', n_ts:int=7, test_size:int=11520,
>         val_size:int=11520, horizons:Tuple[int]=(96, 192, 336, 720))
> ```

The ETTm2 dataset monitors an electricity transformer from a region of
a province of China including oil temperature and variants of load (such
as high useful load and high useless load) from July 2016 to July 2018
at a fifteen minute frequency.

Reference:

* [Zhou, et al. Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI 2021.](https://arxiv.org/abs/2012.07436)

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L52" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### ETTm1

> ```text theme={null}
>  ETTm1 (freq:str='15T', name:str='ETTm1', n_ts:int=7, test_size:int=11520,
>         val_size:int=11520, horizons:Tuple[int]=(96, 192, 336, 720))
> ```

*The ETTm1 dataset monitors an electricity transformer from a region of
a province of China including oil temperature and variants of load (such
as high useful load and high useless load) from July 2016 to July 2018
at a fifteen minute frequency.*

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L36" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### ETTh2

> ```text theme={null}
>  ETTh2 (freq:str='H', name:str='ETTh2', n_ts:int=1, test_size:int=11520,
>         val_size:int=11520, horizons:Tuple[int]=(96, 192, 336, 720))
> ```

*The ETTh2 dataset monitors an electricity transformer from a region of
a province of China including oil temperature and variants of load (such
as high useful load and high useless load) from July 2016 to July 2018
at an hourly frequency.*

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L20" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### ETTh1

> ```text theme={null}
>  ETTh1 (freq:str='H', name:str='ETTh1', n_ts:int=1, test_size:int=11520,
>         val_size:int=11520, horizons:Tuple[int]=(96, 192, 336, 720))
> ```

*The ETTh1 dataset monitors an electricity transformer from a region of
a province of China including oil temperature and variants of load (such
as high useful load and high useless load) from July 2016 to July 2018
at an hourly frequency.*

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L89" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### ECL

> ```text theme={null}
>  ECL (freq:str='15T', name:str='ECL', n_ts:int=321, test_size:int=5260,
>       val_size:int=2632, horizons:Tuple[int]=(96, 192, 336, 720))
> ```

The Electricity dataset reports the fifteen minute electricity
consumption (KWh) of 321 customers from 2012 to 2014. For comparability,
we aggregate it hourly.

Reference:

* [Li, S et al. Enhancing the locality and breaking the memory bottleneck of Transformer on time series forecasting. NeurIPS 2019.](http://arxiv.org/abs/1907.00235)

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon.py#L104" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### Exchange

> ```text theme={null}
>  Exchange (freq:str='D', name:str='Exchange', n_ts:int=8,
>            test_size:int=1517, val_size:int=760, horizons:Tuple[int]=(96,
>            192, 336, 720))
> ```

The Exchange dataset is a collection of daily exchange rates of eight
countries relative to the US dollar. The countries include Australia,
UK, Canada, Switzerland, China, Japan, New Zealand and Singapore from
1990 to 2016.

Reference:

* [Lai, G., Chang, W., Yang, Y., and Liu, H. Modeling Long and Short-Term Temporal Patterns with Deep Neural Networks. SIGIR 2018.](http://arxiv.org/abs/1703.07015)

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L109" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### TrafficL

> ```text theme={null}
>  TrafficL (freq:str='H', name:str='traffic', n_ts:int=862,
>            test_size:int=3508, val_size:int=1756, horizons:Tuple[int]=(96,
>            192, 336, 720))
> ```

This large Traffic dataset was collected by the California Department
of Transportation, it reports road hourly occupancy rates of 862
sensors, from January 2015 to December 2016.

Reference:

* [Lai, G., Chang, W., Yang, Y., and Liu, H. Modeling Long and Short-Term Temporal Patterns with Deep Neural Networks. SIGIR 2018.](http://arxiv.org/abs/1703.07015)
* [Wu, H., Xu, J., Wang, J., and Long, M. Autoformer: Decomposition Transformers with auto-correlation for long-term series forecasting. NeurIPS 2021](https://arxiv.org/abs/2106.13008)

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon.py#L150" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### ILI

> ```text theme={null}
>  ILI (freq:str='W', name:str='ili', n_ts:int=7, test_size:int=193,
>       val_size:int=97, horizons:Tuple[int]=(24, 36, 48, 60))
> ```

This dataset reports weekly recorded influenza-like illness (ILI)
patients from Centers for Disease Control and Prevention of the United
States from 2002 to 2021. It is measured as a ratio of ILI patients
versus the total patients in the week.

Reference:

* [Wu, H., Xu, J., Wang, J., and Long, M. Autoformer: Decomposition Transformers with auto-correlation for long-term series forecasting. NeurIPS 2021.](https://arxiv.org/abs/2106.13008)

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon2.py#L134" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### Weather

> ```text theme={null}
>  Weather (freq:str='10M', name:str='weather', n_ts:int=21,
>           test_size:int=10539, val_size:int=5270, horizons:Tuple[int]=(96,
>           192, 336, 720))
> ```

This Weather dataset contains the 2020 year of 21 meteorological
measurements recorded every 10 minutes from the Weather Station of the
Max Planck Biogeochemistry Institute in Jena, Germany.

Reference:

* [Wu, H., Xu, J., Wang, J., and Long, M. Autoformer: Decomposition Transformers with auto-correlation for long-term series forecasting. NeurIPS 2021. ](https://arxiv.org/abs/2106.13008)

***

<a href="https://github.com/Nixtla/datasetsforecast/blob/main/datasetsforecast/long_horizon.py#L200" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### LongHorizon

> ```text theme={null}
>  LongHorizon (source_url:str='https://nhits-
>               experiments.s3.amazonaws.com/datasets.zip')
> ```

This Long-Horizon datasets wrapper class, provides with utility to
download and wrangle the following datasets:\
ETT, ECL, Exchange, Traffic, ILI and Weather.

* Each set is normalized with the train data mean and standard
  deviation.
* Datasets are partitioned into train, validation and test splits.
* For all datasets: 70%, 10%, and 20% of observations are train,
  validation, test, except ETT that uses 20% validation.