The package contains operator-theoretic models that can
Project description
identify dynamical systems from time series data and infer geometrical structures from point clouds. Home-page: https://datafold-dev.gitlab.io/datafold Author: datafold development team Author-email: daniel.lehmberg@hm.edu License: MIT Description: Main models in datafold:
(Extended-) Dynamic Mode Decomposition (E-DMD) to approximate the Koopman operator from time series data or collections thereof.
Diffusion Map (DMAP) to find meaningful geometric descriptions in point clouds, such as the eigenfunctions of the Laplace-Beltrami operator.
Out-of-sample extensions to interpolate functions on point cloud manifolds, such as Geometric Harmonics interpolator and (auto-tuned) Laplacian Pyramids.
Data structure for time series collections (TSCDataFrame) and data transformations, such as time-delay embeddings (TSCTakensEmbedding). The data structures operates with both E-DMD and DMAP (internally or as input).
Keywords: mathematics, machine learning, dynamical system, data-driven, time series, regression, forecasting, manifold learning, diffusion map, koopman operator, nonlinear Platform: UNKNOWN Classifier: Intended Audience :: Science/Research Classifier: License :: OSI Approved :: MIT License Classifier: Operating System :: OS Independent Classifier: Programming Language :: Python :: 3 :: Only Classifier: Topic :: Scientific/Engineering Requires-Python: >=3.7 Description-Content-Type: text/x-rst
Project details
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.