Skip to main content
Warning: You are using the test version of PyPI. This is a pre-production deployment of Warehouse. Changes made here affect the production instance of TestPyPI (testpypi.python.org).
Help us improve Python packaging - Donate today!

Periodic light curve analysis tools based on Information Theory

Project Description

Description

P4J is a python package for periodicity analysis of irregularly sampled time series based on Information Theoretic objective functions. P4J was developed for astronomical light curves, irregularly sampled time series of stellar magnitude or flux. These routines are build on the concept of correntropy [1], a generalized correlation function that incorporates higher order statistics of the process, lifting the assumption of Gaussianity. Correntropy has been used in astronomical time series problems in [2, 4].

Contents

  • Regression using the Weighted Maximum Correntropy Criterion (WMCC)
  • Robust periodogram based on WMCC
  • False alarm probability for periodogram peaks based on extreme value statistics
  • Basic synthetic light curve generator

Instalation

pip install P4J

Example

https://github.com/phuijse/P4J/blob/master/examples/periodogram_demo.ipynb

TODO

  • Cython backend for WMCC
  • Multidimensional time series support

Authors

  • Pablo Huijse pablo.huijse@gmail.com (Millennium Institute of Astrophysics and Universidad de Chile)
  • Pavlos Protopapas (Harvard Institute of Applied Computational Sciences)
  • Pablo A. Estévez (Millennium Institute of Astrophysics and Universidad de Chile)
  • Pablo Zegers (Universidad de los Andes, Chile)
  • José C. Príncipe (University of Florida)

(P4J = Four Pablos and one Jose)

References

  1. José C. Príncipe, “Information Theoretic Learning: Renyi’s Entropy and Kernel Perspectives”, Springer, 2010
  2. Pavlos Protopapas et al., “A Novel, Fully Automated Pipeline for Period Estimation in the EROS 2 Data Set”, The Astrophysical Journal Supplement, 216 (2), 2015
  3. Pablo Huijse et al., “Computational Intelligence Challenges and Applications on Large-Scale Astronomical Time Series Databases”, IEEE Mag. Computational Intelligence, 2014
  4. Pablo Huijse et al., “An Information Theoretic Algorithm for Finding Periodicities in Stellar Light Curves”, IEEE Trans. Signal Processing 60(10), pp. 5135-5145, 2012
Release History

Release History

This version
History Node

0.5

History Node

0.3

History Node

0.2

History Node

0.1

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting