Skip to main content

Synchrosqueezing, wavelet transforms, and time-frequency analysis in Python

Project description

Synchrosqueezing in Python

Build Status Coverage Status PyPI version Codacy Badge License: MIT

Synchrosqueezing is a powerful reassignment method that focuses time-frequency representations, and allows extraction of instantaneous amplitudes and frequencies. Friendly overview.

Features

  • Forward & inverse CWT-based Synchrosqueezing
  • Forward & inverse Continuous Wavelet Transform (CWT)
  • Clean code with explanations and learning references
  • Wavelet visualizations

Coming soon

  • Forward & inverse Short-Time Fourier Transform (STFT)
  • STFT-based Synchrosqueezing
  • Generalized Morse Wavelets

Installation

pip install ssqueezepy. Or, for latest version (most likely stable):

pip install git+https://github.com/OverLordGoldDragon/ssqueezepy

Examples

1. Signal recovery under severe noise

image

2. Medical: EEG

Introspection

ssqueezepy is equipped with a visualization toolkit, useful for exploring wavelet behavior across scales and configurations. (Also see explanations and code)



Minimal example

import numpy as np
import matplotlib.pyplot as plt
from ssqueezepy import ssq_cwt

def viz(x, Tx, Wx):
    plt.plot(x);  plt.show()    
    plt.imshow(np.abs(Wx), aspect='auto', cmap='jet')
    plt.show()
    plt.imshow(np.flipud(np.abs(Tx)), aspect='auto', vmin=0, vmax=.1, cmap='jet')
    plt.show()   

#%%# Define signal ####################################    
N = 2048
t = np.linspace(0, 10, N, endpoint=False)
xo = np.cos(2 * np.pi * np.exp(t / 3))
x = xo + np.sqrt(4) * np.random.randn(N)

#%%# SSQ CWT + CWT ####################################
Txo, _, Wxo, scales_xo, _ = ssq_cwt(xo, 'morlet')
Wxo /= np.sqrt(scales_xo)  # L1 norm
viz(xo, Txo, Wxo)

Tx, _, Wx, scales_x, _ = ssq_cwt(x, 'morlet')
Wx /= np.sqrt(scales_x)  # L1 norm 
viz(x, Tx, Wx)

References

ssqueezepy was originally ported from MATLAB's Synchrosqueezing Toolbox, authored by E. Brevdo and G. Thakur [1]. Synchrosqueezed Wavelet Transform was introduced by I. Daubechies and S. Maes [2], which was followed-up in [3]. Many implementation details draw from [4].

  1. G. Thakur, E. Brevdo, N.-S. Fučkar, and H.-T. Wu. "The Synchrosqueezing algorithm for time-varying spectral analysis: robustness properties and new paleoclimate applications", Signal Processing 93:1079-1094, 2013.
  2. I. Daubechies, S. Maes. "A Nonlinear squeezing of the CWT Based on Auditory Nerve Models".
  3. I. Daubechies, J. Lu, H.T. Wu. "Synchrosqueezed Wavelet Transforms: a Tool for Empirical Mode Decomposition", Applied and Computational Harmonic Analysis 30(2):243-261, 2011.
  4. Mallat, S. "Wavelet Tour of Signal Processing 3rd ed".

License

ssqueezepy is MIT licensed, as found in the LICENSE file. Some source functions may be under other authorship/licenses; see NOTICE.txt.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ssqueezepy-0.5.0.tar.gz (39.8 kB view hashes)

Uploaded Source

Built Distribution

ssqueezepy-0.5.0-py3-none-any.whl (47.7 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page