Spectrum: a Spectral Analysis Library in Python

Spectrum contains tools to estimate Power Spectral Densities using methods based on Fourier transform, Parametric methods or eigenvalues analysis:

• The Fourier methods are based upon correlogram, periodogram and Welch estimates. Standard tapering windows (Hann, Hamming, Blackman) and more exotic ones are available (DPSS, Taylor, ...).
• The parametric methods are based on Yule-Walker, BURG, MA and ARMA, covariance and modified covariance methods.
• Non-parametric methods based on eigen analysis (e.g., MUSIC) and minimum variance analysis are also implemented.
• Multitapering is also available

Documentation

• 1. Installation
• 2. Quick Start
  • 2.1. QuickStart (Periodogram example)
  • 2.2. The object approach versus functional approach (ARMA example)
    • 2.2.1. Object approach
    • 2.2.2. Functional approach
• 3. Overview of available PSD methods
  • 3.1. Non-parametric classes
  • 3.2. Autoregressive spectral estimation
• 4. Tutorials
  • 4.1. Yule Walker example
  • 4.2. PBURG example
  • 4.3. Variance outputs
  • 4.4. Windowing
    • 4.4.1. Window object
    • 4.4.2. Simple window function call
    • 4.4.3. Window Visualisation
    • 4.4.4. Window Factory
  • 4.5. All PSD methods
  • 4.6. What is the Spectrum object ?
  • 4.7. Criteria for Parametric methods
    • 4.7.1. Example 1
    • 4.7.2. Example 2
• 5. Reference Guide
  • 5.1. Fourier Methods
    • 5.1.1. Power Spectrum Density based on Fourier Spectrum
    • 5.1.2. Tapering Windows
  • 5.2. Multitapering
  • 5.3. Parametric methods
    • 5.3.1. Power Spectrum Density based on Parametric Methods
    • 5.3.2. Criteria
  • 5.4. Other Power Spectral Density estimates
    • 5.4.1. Covariance method
    • 5.4.2. Eigen-analysis methods
    • 5.4.3. Minimum Variance estimator
    • 5.4.4. Modified Covariance method
  • 5.5. Tools and classes
    • 5.5.1. Classes
    • 5.5.2. Correlation
    • 5.5.3. Tools
    • 5.5.4. datasets
    • 5.5.5. Linear Algebra Tools
    • 5.5.6. Waveforms
• 6. todo list
• 7. ChangeLog Summary
  • 7.1. March 2012
  • 7.2. February 2012
  • 7.3. January 2012
  • 7.4. October 2011
  • 7.5. May 2011
  • 7.6. April 2011
  • 7.7. March 2011

License

Spectrum is released under a LGPL License.