| Type: | Package |
| Title: | Parameter-Free Domain-Agnostic Season Length Detection in Time Series |
| Version: | 2.0.2 |
| Description: | Spectral and Average Autocorrelation Zero Distance Density ('sazed') is a method for estimating the season length of a seasonal time series. 'sazed' is aimed at practitioners, as it employs only domain-agnostic preprocessing and does not depend on parameter tuning or empirical constants. The computation of 'sazed' relies on the efficient autocorrelation computation methods suggested by Thibauld Nion (2012, URL: https://etudes.tibonihoo.net/literate_musing/autocorrelations.html) and by Bob Carpenter (2012, URL: https://lingpipe-blog.com/2012/06/08/autocorrelation-fft-kiss-eigen/). |
| License: | GPL-2 |
| URL: | https://github.com/mtoller/autocorr_season_length_detection/ |
| Encoding: | UTF-8 |
| LazyData: | true |
| Imports: | bspec (≥ 1.5), dplyr (≥ 0.8.0.1), fftwtools (≥ 0.9.8), pracma (≥ 2.1.4), zoo (≥ 1.8-3) |
| RoxygenNote: | 6.1.1 |
| NeedsCompilation: | no |
| Packaged: | 2020-09-29 18:09:12 UTC; rstudio |
| Author: | Maximilian Toller [aut], Tiago Santos [aut, cre], Roman Kern [aut] |
| Maintainer: | Tiago Santos <teixeiradossantos@tugraz.at> |
| Repository: | CRAN |
| Date/Publication: | 2020-09-29 18:30:02 UTC |
sazedR: A package for for estimating the season length of a seasonal time series.
Description
The sazedR package provides the main function to compute season length, sazed, which is an ensemble of many season length estimation methods, also included in this package.
Compute the S component of the SAZED ensemble
Description
S computes the spectral density of its argument, and then derives the
season length from it.
Usage
S(y, preprocess = T)
Arguments
y |
The input time series. |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The S season length estimate of y.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
S(y)
S(y, preprocess = FALSE)
Compute the SA component of the SAZED ensemble
Description
Sa computes the autocorrelation of its argument, and then derives the
season length from its spectral density.
Usage
Sa(y, preprocess = T)
Arguments
y |
The input time series. |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The SA season length estimate of y.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
Sa(y)
Sa(y, preprocess = FALSE)
Compute the AZE component of the SAZED ensemble
Description
aze estimates the season length of its argument from the mean autocorrelation zero
distance
Usage
aze(y, preprocess = T)
Arguments
y |
The input time series. |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The AZE season length estimate of y.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
aze(y)
aze(y, preprocess = FALSE)
Compute the AZED component of the SAZED ensemble
Description
azed computes the autocorrelation of its argument, and then derives the
season length from its the autocorrelations zero density.
Usage
azed(y, preprocess = T)
Arguments
y |
The input time series. |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The AZED season length estimate of y.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
azed(y)
azed(y, preprocess = FALSE)
Compute and shorten autocorrelation
Description
computeAcf computes the autocorrelation function of its argument and discards
the zero lag and all lags greater than 2/3 of the argument's length
Usage
computeAcf(y)
Arguments
y |
The input time series. |
Value
The shortened autocorrelation
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
computeAcf(y)
Downsample Time Series
Description
downsample samples down a time series with a rolling mean.
Usage
downsample(data, window_size = 2)
Arguments
data |
The input time series. |
window_size |
The size of the rolling mean window used. |
Value
The downsampled time series.
Preprocess Time Series for SAZED ensemble
Description
preprocessTs detrends and z-normalizes its argument.
Usage
preprocessTs(y)
Arguments
y |
The input time series. |
Value
The detrended and z-normalized time series.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
preprocessTs(y)
SAZED Ensemble (Optimum)
Description
sazed estimates a time series' season length by combining 3 different estimates
computed on an input time series and its 10-fold self-composed autocorrelation.
Usage
sazed(y)
Arguments
y |
The input time series. |
Value
The season length of the input time series.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
sazed(y)
SAZED Ensemble (Majority)
Description
sazed.maj estimates a time series' season length by computing 6 different
estimates and taking a majority vote.
Usage
sazed.maj(y, iter = 0, method = "down", preprocess = T)
Arguments
y |
The input time series. |
iter |
The recursion depth. |
method |
The method used for breaking ties. One of |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The season length of the input time series.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
sazed.maj(y)
Compute the ZE component of the SAZED ensemble
Description
ze estimates the season length of its argument from the mean zero distance
Usage
ze(y, preprocess = T)
Arguments
y |
The input time series. |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The ZE season length estimate of y.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
ze(y)
ze(y, preprocess = FALSE)
Compute the ZED component of the SAZED ensemble
Description
zed computes the zero density of its argument, and then derives the
season length from it.
Usage
zed(y, preprocess = T)
Arguments
y |
The input time series. |
preprocess |
If true, y is detrended and z-normalized before computation. |
Value
The ZED season length estimate of y.
Examples
season_length <- 26
y <- sin(1:400*2*pi/season_length)
zed(y)
zed(y, preprocess = FALSE)