Methods for the alignment and merging of partially or inexactly aligned time-series.

Details

The main alignment functions are named [type]_align and in intended to be used in the form:

ans <- _align(ts1, ts2, ...)

In the simplest cases ts1 is a vector to be used as a reference time-series and ts2 is a second time-series to be aligned with it. However, either can also be a data.frame in which case an extra argument by should be included to identify the data.frame columns to use, e.g. for df1 containing ts1 and df2 containing ts2:

ans <- _align(df1, df2, by=c("ts1", "ts2"), ...)

If the object to be aligned is a data.frame, all columns in that data.frame are modified according to the ts1/ts2 alignment.

alignments can also be applied within a single data, e.g. for df that contains both ts1 and ts2:

ans <- _align(df, by=c("ts1", "ts2"), ...)

(in which case only df$ts2 is aligned...)

The default output is typically a single data.frame containing the aligned data, but other outputs may also be generated, e.g. plots and summary reports. This behaviour can be changed using the common argument output, and options include "plot", "summary", "ans", and "alignment" (all outputs in the package object class, see also alignment.generics). Multiple output may also be requested but only the last is caught.

Example alignments include: n_align, cor_align and cow_align.

Although the main alignment functions require two time-series, some use sub-routines to reshape data, and these can also be applied directly.

Examples of these include: regularize and warp.

References

Carslaw, D.C., Ropkins, K., Laxen, D., Moorcroft, S., Marner, B. and Williams, M.L., 2008. Near-field commercial aircraft contribution to nitrogen oxides by engine, aircraft type, and airline by individual plume sampling. Environmental science & technology, 42(6), pp.1871-1876. https://doi.org/10.1021/es071926a.

Ropkins, K., Carlsaw, D.C., Goodman, P.S. and Tate, J.E., 2009. Application of non-linear time-alignment and integration methods to environmental time series. TrAC Trends in Analytical Chemistry, 28(3), pp.373-391. https://doi.org/10.1016/j.trac.2008.11.013.

Author

Maintainer: Karl Ropkins karl.ropkins@gmail.com

Authors: