pyhctsa.operations.correlation.add_noise¶
-
pyhctsa.operations.correlation.add_noise(y, tau=
1, ami_method='even', extra_param=None, random_seed=None)¶ Changes in the automutual information with the addition of noise.
Adds Gaussian-distributed noise to the time series with increasing standard deviation, eta, across the range eta = 0, 0.1, …, 2, and measures the mutual information at each point. Can be measured using histograms with extra_param bins or using the Information Dynamics Toolkit. The output is a set of statistics on the resulting set of automutual information estimates, including a fit to an exponential decay, since the automutual information decreases with the added white noise. This algorithm is quite different, but was based on the idea in [1].
References
- Parameters:¶
- y : ArrayLike¶
Input time series (should be z-scored prior to analysis).
- tau : int or str, optional¶
Time delay used to compute AMI.
If an
int, computes AMI at that lag.If
"ac"or"tau", uses the first zero-crossing of the
autocorrelation function.
Default is
1.- ami_method : str, optional¶
Estimation method for AMI.
Histogram-based estimators:
"std1""std2""quantiles""even"
JIDT-based estimators:
"gaussian""kernel""kraskov1""kraskov2"
Default is
"even".- extra_param : int, optional¶
Additional parameter for the AMI estimator.
For histogram methods: number of bins.
For JIDT methods: estimator-specific parameter.
Default is
10.- random_seed : int or None, optional¶
Seed controlling noise realisations. If
None, defaults internally to0.
- Returns:¶
Summary statistics of the AMI–noise curve, including exponential decay fit parameters and descriptive measures.
- Return type:¶
dict