nltools
nltools copied to clipboard
Python toolbox for analyzing imaging data
Currently `Brain_Data.randomise` has a naive implementation that's a bit slow and requires manually thresholding results afterwards. FSL's randomise on the other hand automatically computes TFCE maps or voxel-wise FWER maps....
Currently, ISC uses correlation, but we may want to pass in different types of distance metrics, easy fix to add a new keyword.
I believe we already have a regression method to do most of the stats implemented in this cool matlab [toolbox](https://sites.google.com/site/bctnet/comparison/nbs), but I would like to incorporate how they compute p-values...
Dear all, it would be nice to have an option to suppress predict's console output. Cheers Jens def predict(self, algorithm=None, cv_dict=None, plot=True, silent=False, **kwargs): . . . if not silent:...
Sometimes we want to append images but avoid pandas errors if .X or .Y dont have the same number of columns
I tried to use Brain_Data to load a mask based on DiFuMo atlas (https://parietal-inria.github.io/DiFuMo/) Using the standard method (loading mask with Brain_Data and using expand_mask) doesn't work. When looking at...
This hasn't resulted in any test errors but I think I may have formatted something weird here, because vscode gives me an error that `dm` isn't defined in this else...
ROC plot has been having a lot of problems. Right now forced choice accuracy doesn't seem to be always correct. We should refactor this and write proper tests. Also need...
```python --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in ----> 1 Adjacency((adjs[ep_num])) ~/Documents/pypackages/nltools/nltools/data/adjacency.py in __init__(self, data, Y, matrix_type, labels, **kwargs) 115 self.is_single_matrix = False 116 elif (isinstance(data, str) or isinstance(data,...