torch_timeseries.dataset.ILI

class ILI(root: str = './data')[source]

Bases: TimeSeriesDataset

ILI (Influenza-Like Illness) records the weekly ratio of influenza-like illness patients versus the total patients by the Centers for Disease Control and Prevention (CDC) of the United States from 2002 to 2021.

This dataset contains 966 data points, each with 7 features, and the data frequency is hourly (‘h’).

Collected from: https://gis.cdc.gov/grasp/fluview/fluportaldashboard.html.

name

Name of the dataset, it is ‘ILI’.

Type:: str

num_features

Number of features in the dataset, it is 7.

Type:: int

length

Total length of the dataset, it is 966.

Type:: int

freq

Frequency of the data points, it is ‘h’.

Type:: str

Parameters:: TimeSeriesDataset (_type_) – The base class for time series datasets.
Returns:: The data loaded from the CSV file.
Return type:: np.ndarray

download()[source]: Downloads and extracts the dataset archive from the specified URL.

_load() → np.ndarray[source]: Loads the data from the CSV file and returns it as a numpy array.

_summary_

Parameters:: root (str) – data save location