timecorr

timecorr copied to clipboard

default parameters passed to python functions should be __immutable__. probably does not matter for this particular case but wanted to document in case a bug pops up related to this....

andrewheusser

Allow the user to pass an s by s by t matrix of weights to wisfc that defines weights on a per-timepoint basis. (In addition to continuing to support an...

jeremymanning

Data Mining - Optimal Level of Different Kinds of Systems

1

Optimal levels of various datasets (biological, physical, man-made) Plot optimal level of human brain data (perhaps in different states) relative to the optimal levels of other kinds of systems

KirstensGitHub

Use time steps (in dataframes) instead of numpy arrays. index argument that can pass a dataframe (inferred or explicitly specified which would override) or a numpy array with index (if...

lucywowen

An issue that's been raised at prior lab meetings is that correlation matrices (and higher order correlation matrices) fundamentally characterize *pairs* of interactions (or pairs of pairs of interactions, etc.)...

jeremymanning

- should be passed to timecorr and wcorr - options: `right`, `left`, or `both` (default) - behavior: - if `both`, leave weights unchanged - if `right`, set all weights for...

jeremymanning

Predict function

1

Do we still want to do this? With `matheron`?

jeremymanning

support np.ndarray for corrmean_combine and mean_combine

1

only supports list right now

lucywowen

we could consider (in a future release) wrapping or extending some of the functions in this toolbox: https://diviyan-kalainathan.github.io/CausalDiscoveryToolbox/html/index.html

jeremymanning