repr_pip {TSrepr}

PIP representation

Description

The repr_pip computes PIP (Perceptually Important Points) representation from a time series.

Usage

repr_pip(x, times = 10, return = "points")

Arguments

x

the numeric vector (time series)

times

the number of important points to extract (default 10)

return

what to return? Can be important points ("points"), places of important points in a vector ("places") or "both" (data.frame).

Value

the values based on the argument return (see above)

Author(s)

Peter Laurinec, <[e-mail]>

References

Fu TC, Chung FL, Luk R, and Ng CM (2008) Representing financial time series based on data point importance. Engineering Applications of Artificial Intelligence, 21(2):277-300

Examples

repr_pip(rnorm(100), times = 12, return = "both")