https://github.com/dokato/dfa

Detrended Fluctuation Analysis
https://github.com/dokato/dfa

Last synced: 4 days ago
JSON representation

Detrended Fluctuation Analysis

• Host: GitHub
• URL: https://github.com/dokato/dfa
• Owner: dokato
• License: mit
• Created: 2015-10-13T20:39:06.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2021-04-29T09:02:14.000Z (over 3 years ago)
• Last Synced: 2024-11-01T04:35:56.366Z (11 days ago)
• Language: Jupyter Notebook
• Size: 257 KB
• Stars: 63
• Watchers: 7
• Forks: 19
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
Detrended Fluctuation Analysis

==============================

Simple python implementation of the DFA algorithm.

It bases on these two articles:

* Hardstone, R. et al. Detrended fluctuation analysis: A scale-free view on neuronal oscillations. Front. Physiol. 3 NOV, 1–13 (2012).

* Ihlen, E. a F. Introduction to multifractal detrended fluctuation analysis in Matlab. Front. Physiol. 3 JUN, 1–18 (2012).

You may test it using power law data generator from `generate.py`, or with the code below:

```python

from dfa import dfa

from generate import power_law_noise

true_exp = 0.8

x = power_law_noise(2**12, true_exp)

scales, fluct, alpha = dfa(x)

print("True scaling exponent: {}".format(true_exp))

print("Estimated DFA exponent: {}".format(alpha))

```

Requirements

------------

* numpy

* matplotlib