No project description provided
Project description
Agas defines similarity as the absolute difference between pairs of output scores from an aggregation function applied to the input series. The default behavior of Agas is to maximize similarity on a single dimension (e.g., means of the series in the input matrix) while minimizing similarity on another dimension (e.g., the variance of the series).
The main motivation for this library is to provide a data description tool for depicting time-series. It is customary to plot pairs of time series, where the pair is composed of data which is similar on one dimension (e.g., mean value) but dissmilar on another dimension (e.g., standard deviation).
The library name Agas is abbreviation for aggregated-series. Also, ‘Agas’ is Hebrew for ‘Pear’.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
