Compute only subset of SPIs in Calculator

[LuRoe7]

First of all: great preprint, great package!! It will facilitate the research at our lab essentially!!!

I was wondering how to tell the Calculator function to compute only a few SPIs that I am interested in in order to save processing time?

Best, Lukas

[olivercliff]

Hi Lukas,

Thank you! I'm working on documentation that illustrates how to use all the toolkit's functionality like this. In the meantime, I'll put some details here.

You can easily use a subset of the SPIs by editing the configuration file, config.yaml, to only include statistics that you want. I tried to make the names in the configuration file as user-friendly as possible, but if you're unsure of what any of them are, you should be able to cross-reference them with the supplementary material in the preprint (or simply ask me).

To make sure you don't override the original config.yaml, though, I would probably suggest editing a local copy of the file (details below).

Say you've cloned the repository to ~/toolkits/pyspi, and you're working in the directory ~/workspace. First, copy the config.yaml file to your working directory:

cp ~/toolkits/pyspi/pyspi/config.yaml ~/workspace/myconfig.yaml

Once you've got your local version, edit the myconfig.yaml file to remove any SPIs you're not interested in. A minimal myconfig.yaml might look like the following if you're only interested in computing a covariance matrix using the maximum likelihood estimator:

# Basic statistics
.statistics.basic:

  # Covariance
  covariance:

    # Maximum likelihood estimator
    - estimator: EmpiricalCovariance

Now, when you instantiate the calculator, instead of using the default config.yaml, you can input your bespoke file:

from pyspi.calculator import Calculator

calc = Caculator(dataset=dataset,configfile='~/workspace/myconfig.yaml')
calc.compute()

[LuRoe7]

Thank you! And again: amazing work :)