seg1d: A Python package for Automated segmentation of one-dimensional (1D) data
Mathew Schwartz, Todd C. Pataky, Cyril John William Donnelly · The Journal of Open Source Software · 2020
The term segmentation refers to the division of a data series into segments.In this paper, segments refer to a contiguous time series which is a subset of another time series (Bouchard, 2006).Identifying these segments requires a reference series to be found in the larger series, which can be an exact copy or an approximation.When an approximation of the desired segment is used, the metric and method for identifying similarity of all subsets are essential to achieving the desired result.Additionally, multiple references may be desired to further describe the aspects of segment similarity, some of which may be more important than others.