API Reference

symbolix_debug.JS_C(data_1, data_2, delay, dim)

Calculate the Jensen-Shannon divergence between order-class distributions of two time series.

Parameters

data_1numpy.ndarray

First time series.

data_2numpy.ndarray

Second time series.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

float

Jensen-Shannon divergence.

symbolix_debug.JS_d(data_1, data_2, delay, dim, metric)

Calculate the Jensen-Shannon divergence of symbolic distance distributions between two time series.

Parameters

data_1numpy.ndarray

First time series.

data_2numpy.ndarray

Second time series.

delayint

Embedding delay.

dimint

Embedding dimension.

metricstr

Distance metric to use. Either 'kendall' or 'cayley'.

Returns

float

Jensen-Shannon divergence.

symbolix_debug.SKL_C(data_1, data_2, delay, dim)

Calculate the symmetrized Kullback-Leibler distance between two time series.

Parameters

data_1numpy.ndarray

First time series.

data_2numpy.ndarray

Second time series.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

float

Symmetrized Kullback-Leibler distance.

symbolix_debug.circulance(data, delays=None)

Calculate the circulance (Ϙ) of a time series.

Parameters

datanumpy.ndarray

1D array of time series data.

delaysint or array-like or None, optional

Embedding delays used for constructing ordinal patterns.

  • If an integer is provided, calculate circulance for that delay.

  • If an array-like object is provided, calculate circulance for all specified delays.

  • If None, evaluate all possible delays and return the minimum circulance.

Returns

float

Minimum circulance for the given delays.

int

Embedding delay corresponding to the minimum circulance.

list

Circulance values for all evaluated delays.

symbolix_debug.coupling_complexity(data, delay, dim)

Calculate coupling complexity between multiple signals.

Parameters

datanumpy.ndarray

2D array of time series with shape (num_dpoints, num_ts).

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

float

Coupling complexity.

symbolix_debug.coupling_complexity_symbols()

delay_vectors(data, delay, dim) –

Generate delay vectors from a time series.

Parameters

datanumpy.ndarray

2D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

numpy.ndarray

Array of delay vectors.

symbolix_debug.delay_vectors(data, delay, dim)

Generate delay vectors from a time series.

Parameters

datanumpy.ndarray

2D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

numpy.ndarray

Array of delay vectors.

symbolix_debug.dists(data_1, data_2, delay, dim, metric)

Calculate symbolic distances between two time series.

Parameters

data_1numpy.ndarray

First 1D time series.

data_2numpy.ndarray

Second 1D time series.

delayint

Embedding delay.

dimint

Embedding dimension.

metricstr

Distance metric to use. One of 'euclidean', 'cayley', 'kendall', or 'manhattan'.

Returns

numpy.ndarray

Array of symbolic distances.

symbolix_debug.find_order_class()

delay_vectors(data, delay, dim) –

Generate delay vectors from a time series.

Parameters

datanumpy.ndarray

2D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

numpy.ndarray

Array of delay vectors.

symbolix_debug.find_order_classes()

ocs_from_symbol_series(symbols) –

Calculate order classes from an ordinal pattern series.

Parameters

symbolsnumpy.ndarray

2D ordinal-pattern series.

Returns

numpy.ndarray

1D array of order classes.

symbolix_debug.get_transcripts(data_1, data_2, delay, dim)

Calculate transcripts between two time series.

Parameters

data_1numpy.ndarray

First 1D time series.

data_2numpy.ndarray

Second 1D time series.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

numpy.ndarray

2D array of transcripts.

symbolix_debug.ocs_from_symbol_series(symbols)

Calculate order classes from an ordinal pattern series.

Parameters

symbolsnumpy.ndarray

2D ordinal-pattern series.

Returns

numpy.ndarray

1D array of order classes.

symbolix_debug.optn_adj(data, delay, dim, ranked=False, weighted=False)

Create an ordinal partition transition network adjacency matrix.

Parameters

datanumpy.ndarray

1D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

rankedbool, optional

If True, assign adjacency indices according to permutation rank instead of order of occurrence.

weightedbool, optional

If True, use edge weights defined by the number of observed transitions.

Returns

numpy.ndarray

Adjacency matrix.

symbolix_debug.ordinal_patterns()

delay_vectors(data, delay, dim) –

Generate delay vectors from a time series.

Parameters

datanumpy.ndarray

2D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

numpy.ndarray

Array of delay vectors.

symbolix_debug.permutation_entropy(data, delay, dim)

Calculate the permutation entropy of a signal.

Parameters

datanumpy.ndarray

1D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

float

Permutation entropy.

symbolix_debug.statistical_complexity(data, delay, dim)

Calculate statistical complexity of a signal.

Parameters

data (numpy.ndarray): 2D array of time series, shape (num_dpoints, num_ts). delay (int): Embedding delay. dim (int): Embedding dimension.

Returns

SC (float): Statistical complexity

symbolix_debug.symbol_ranks()

delay_vectors(data, delay, dim) –

Generate delay vectors from a time series.

Parameters

datanumpy.ndarray

2D array of time series data.

delayint

Embedding delay.

dimint

Embedding dimension.

Returns

numpy.ndarray

Array of delay vectors.

symbolix_debug.time_reversibility()

ocs_from_symbol_series(symbols) –

Calculate order classes from an ordinal pattern series.

Parameters

symbolsnumpy.ndarray

2D ordinal-pattern series.

Returns

numpy.ndarray

1D array of order classes.

symbolix_debug.transcript_mi()

Calculate transcripts mutual information between two signals.

Args:

data_1 (numpy.ndarray): 1D time series. data_2 (numpy.ndarray): 1D time series. time_delay (numpy.ndarray): Time delay for comparing with past data. delay (numpy.ndarray): Embedding delay. dim (numpy.ndarray): Embedding dimension.

Returns:

TMI (float): Transcript mutual info.