pyspi.calculator.Calculator

class pyspi.calculator.Calculator(dataset=None, name=None, labels=None, fast=False, sonnet=False, configfile=None, normalise=True)

Compute all pairwise interactions.

The calculator takes in a multivariate time-series dataset, computes and stores all pairwise interactions for the dataset. It uses a YAML configuration file that can be modified in order to compute a reduced set of pairwise methods.

Example

import numpy as np

dataset = np.random.randn(5,500)   # create a random multivariate time series (MTS)
calc = Calculator(dataset=dataset) # Instantiate the calculator
calc.compute()                     # Compute all pairwise interactions

Parameters

Description

dataset (Data, array_like, optional) – The multivariate time series of M processes and T observations, defaults to None name (str, optional) – The name of the calculator. Mainly used for printing the results but can be useful if you have multiple instances, defaults to None. labels (array_like, optional) – Any set of strings by which you want to label the calculator. This can be useful later for classification purposes, defaults to None. subset (str, optional) - A pre-configured subset of SPIs to use. Options are "all", "fast", "sonnet", "octaveless", or "fabfour", defaults to "all". configfile (str, optional) – The location of the YAML configuration file. See Using a reduced SPI set, defaults to '</path/to/pyspi>/pyspi/config.yaml' normalise (bool, optional) - Normalise the dataset along the time axis before computing SPIs, defaults to True.

__init__(dataset=None, name=None, labels=None, subset=None, configfile=None, normalise=True)

Methods

Method	Description
__init__([dataset, name, labels, fast, ...])
compute()	Compute the SPIs on the MVTS dataset.
load_dataset(dataset)	Load a new dataset into existing instance.
set_group(classes)	Assigns a numeric value to a Calculator instance based on a list of classes.
_rmin()	Iterate through all SPIs are remove the minimum. Fixes absolute errors when correlating.
get_stat_labels()	Get the keywords for each SPI.
_get_correlation_df(with_labels=False, rmin=False)	Generates a DataFrame showing correlations between SPIs.

Attributes

Attribute	Description
dataset	Dataset as a data object.
group	The numerical group assigned during set_group()
group_name	The group name assigned during set_group().
labels	List of calculator labels.
n_spis	Number of SPIs in the calculator.
name	Name of the calculator.
spis	Dict of SPIs.
table	Results table for all pairwise interactions (each represented as an MPI).