web_traffic_train {setartree}

A dataframe of training instances

Description

A dataframe containing 120 instances that can be used to train the SETAR-Tree and SETAR-Forest models. The data are related to the number of hits or web traffic of a set of Wikipedia pages. Each instance in the dataframe consists of 10 time series lags (Lag1 to Lag10), a categorical covariate (Project) and the corresponding true outputs (y). The data were downloaded from the Wikimedia REST API (Wikimedia, 2022).

Format

A dataframe containing 120 training instances.

References

Wikimedia Analytics Team (2022). Wikistats: Pageview complete dumps.
URL https://dumps.wikimedia.org/other/pageview_complete

Examples

web_traffic_train