skNLA - Scikit Nonlinear Analysis
This package is an implementation of nonlinear time series analysis using an algorithmic flow similar in style to Python's scikit-learn. Briefly, the method reconstructs attractors within a dynamical phase space to analyze behavior and make forecasts. skNLA looks for past configurations of the system in the phase space that are similar to the present configuration. These past configurations are probed to make forecasts about future system evolution. The technique is described in depth in the book, "Nonlinear Time Series Analysis" by Kantz and Schreiber.
skCCM - Scikit Convergent Cross Mapping
This package is an implementation of convergent cross mapping (CCM) using an algorithmic flow similar in style to Python's scikit-learn. The details of this technique were first described by Sugihara et al. in the publication "Detecting Causality in Complex Ecosystems" in Science.
BuoyPy pulls data from the National Data Buoy Center, cleans it, and puts it into pandas dataframes.