frites.core.cmi_nd_ggg#
- frites.core.cmi_nd_ggg(x, y, z, mvaxis=None, traxis=- 1, biascorrect=True, demeaned=False, shape_checking=True)[source]#
Multi-dimentional MI between three Gaussian variables in bits.
This function is based on ANOVA style model comparison.
- Parameters
- x, y, znumpy:array_like
Arrays to consider for computing the Mutual Information. The three input variables x, y and z should have the same shape except on the mvaxis (if needed).
- mvaxis
python:int|python:None Spatial location of the axis to consider if multi-variate analysis is needed
- traxis
python:int| -1 Spatial location of the trial axis. By default the last axis is considered
- biascorrectbool |
python:True Specifies whether bias correction should be applied to the estimated MI
- demeanedbool |
python:False Specifies whether the input data already has zero mean (true if it has been copula-normalized)
- shape_checkingbool |
python:True Perform a reshape and check that x and y shapes are consistents. For high performances and to avoid extensive memory usage, it’s better to already have x and y with a shape of (…, mvaxis, traxis) and to set this parameter to False
- Returns
- minumpy:array_like
The mutual information with the same shape as x, y and z without the mvaxis and traxis