pmdarima.datasets.load_taylor

pmdarima.datasets.load_taylor(as_series=False, dtype=<class 'numpy.float64'>)[source][source]

Half-hourly electricity demand

Half-hourly electricity demand in England and Wales from Monday, 5 June, 2000 to Sunday, 27 August, 2000. Discussed in Taylor (2003), and kindly provided by James W Taylor. Units: Megawatts

Parameters:

as_series : bool, optional (default=False)

Whether to return a Pandas series. If True, the index will be set to the observed years. If False, will return a 1d numpy array.

dtype : type, optional (default=np.float64)

The type to return for the array. Default is np.float64, which is used throughout the package as the default type.

Returns:

taylor : array-like, shape=(n_samples,)

The Taylor dataset. There are 4032 observations.

Notes

This is annual data and not seasonal in nature (i.e., \(m=1\))

References

[R84]Taylor, J.W. (2003) Short-term electricity demand forecasting using double seasonal exponential smoothing. Journal of the Operational Research Society, 54, 799-805.
[R85]https://www.rdocumentation.org/packages/forecast/versions/8.9/topics/taylor

Examples

>>> from pmdarima.datasets import load_taylor
>>> load_taylor()[:10]
array([22262., 21756., 22247., 22759., 22549., 22313., 22128., 21860.,
       21751., 21336.])
>>> load_taylor(True).head()
0    22262.0
1    21756.0
2    22247.0
3    22759.0
4    22549.0
dtype: float64