SugiharaLab/pyEDM

Empirical Dynamic Modeling (EDM)

This package provides a Python/Pandas DataFrame interface to the cppEDM library for EDM analysis. Introduction and documentation are are avilable online, or in the package API docs. A Jupyter notebook interface is available at jpyEDM.

Functionality includes:

• Simplex projection (Sugihara and May 1990)
• Sequential Locally Weighted Global Linear Maps (S-Map) (Sugihara 1994)
• Multivariate embeddings (Dixon et. al. 1999)
• Convergent cross mapping (Sugihara et. al. 2012)
• Multiview embedding (Ye and Sugihara 2016)

Installation

Python Package Index (PyPI)

Certain MacOS, Linux and Windows platforms are supported with prebuilt binary distributions hosted on PyPI pyEDM.

Command line using the Python pip module: python -m pip install pyEDM

Manual Install

If a pre-built binary distribution is not available the user can build the cppEDM library, then install the Python package using pip. On OSX and Linux this requires g++. On Windows, the mingw-w64 GCC is available as in MSYS2.

Note the LAPACK library is required to build cppEDM and pyEDM. As of version 1.15.1, LAPACK is not required on Windows.

OSX and Linux

1. Download pyEDM: git clone https://github.com/SugiharaLab/pyEDM
2. Build cppEDM library: cd pyEDM/cppEDM/src; make
3. Build and install package: cd ../..; python -m pip install . --user

Windows

0. If a Windows binary is not available, these suggestions may be useful.
1. mingw-w64 GCC is available in MSYS2.
2. Prior to version 1.15.1, gfortran and OpenBLAS libraries are required.
3. Download pyEDM: git clone https://github.com/SugiharaLab/pyEDM
4. Build cppEDM library: cd pyEDM\cppEDM\src; make
5. Adjust paths to find gfortran and openblas libraries (pyEDM/pyEDM/etc/windows/libopenblas.a). You may need to rename libEDM.a to EDM.lib, and openblas.a to openblas.lib.
6. Build and install package in pyEDM\: python -m pip install . --user

Usage

Example usage at the python prompt:

>>> import pyEDM
>>> pyEDM.Examples()

References

Sugihara G. and May R. 1990. Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series. Nature, 344:734–741.

Sugihara G. 1994. Nonlinear forecasting for the classification of natural time series. Philosophical Transactions: Physical Sciences and Engineering, 348 (1688) : 477–495.

Dixon, P. A., M. Milicich, and G. Sugihara, 1999. Episodic fluctuations in larval supply. Science 283:1528–1530.

Sugihara G., May R., Ye H., Hsieh C., Deyle E., Fogarty M., Munch S., 2012. Detecting Causality in Complex Ecosystems. Science 338:496-500.

Ye H., and G. Sugihara, 2016. Information leverage in interconnected ecosystems: Overcoming the curse of dimensionality. Science 353:922–925.