sciquence.representation.sax

sciquence.representation.sax(sequence, window, alphabet_size=5, adjust=True)[source]

Symbolic Aggregate Approximation.

Transform time series into a string.

Parameters:
  • sequence (numpy.ndarray) – One-dimensional numpy array of arbitrary length
  • window (int) – Length of sliding window
  • alphabet_size (int) – Number of Gaussian breakpoints
  • adjust (bool, default True) – Compute only for equal-size chunks
Returns:

sax_representation – A SAX representation

Return type:

str

Examples

>>> import numpy as np
>>> from sciquence.representation import sax
>>> np.random.seed(42)
>>> random_time_series = np.random.rand(50)
>>> print sax(random_time_series, 10, alphabet_size=5)
dcccc

References

[1]

Lin, J., Keogh, E., Lonardi, S., & Chiu, B. (2003). A Symbolic Representation of Time Series, with Implications for Streaming Algorithms. In proceedings of the 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery.

http://www.cs.ucr.edu/~eamonn/SAX.pdf

[2]http://www.cs.ucr.edu/~eamonn/SAX.htm
[3]https://jmotif.github.io/sax-vsm_site/morea/algorithm/SAX.html