oddstream (version 0.5.0)

extract_tsfeatures: Extract features from a collection of time series

Description

This function extract time series features from a collection of time series. This is a modification oftsmeasures function of anomalous package package .

Usage

extract_tsfeatures(y, normalise = TRUE, width = ifelse(frequency(y) >
  1, frequency(y), 10), window = width)

Arguments

y

A multivariate time serie

normalise

If TRUE, each time series is scaled to be normally distributed with mean 0 and sd 1

width

A window size for variance change, level shift and lumpiness

window

A window size for KLscore

Value

An object of class features with the following components:

mean

Mean

variance

Variance

lumpiness

Variance of annual variances of remainder

lshift

Level shift using rolling window

vchange

Variance change

linearity

Strength of linearity

curvature

Strength of curvature

spikiness

Strength of spikiness

season

Strength of seasonality

peak

Strength of peaks

trough

Strength of trough

BurstinessFF

Burstiness of time series using Fano Factor

minimum

Minimum value

maximum

Maximum value

rmeaniqmean

Ratio between interquartile mean and the arithmetic mean

moment3

Third moment

highlowmu

Ratio between the means of data that is below and upper the global mean

References

Hyndman, R. J., Wang, E., & Laptev, N. (2015). Large-scale unusual time series detection. In 2015 IEEE International Conference on Data Mining Workshop (ICDMW), (pp. 1616-1619). IEEE.

Fulcher, B. D. (2012). Highly comparative time-series analysis. PhD thesis, University of Oxford.

See Also

find_odd_streams, get_pc_space, set_outlier_threshold, gg_featurespace

Examples

# NOT RUN {
mvtsplot::mvtsplot(anomalous_stream, levels=8, gcol=2, norm="global")
features <- extract_tsfeatures(anomalous_stream[500:550, ])
plot.ts(features[, 1:10])
# }
# NOT RUN {
# }