nltools
nltools copied to clipboard
cosanlab
Python toolbox for analyzing imaging data
Several things to note and they might be related to https://github.com/cosanlab/nltools/issues/310: 1) The way `iplot` works is that it calls `nilearn.plotting.view_image` under the hood which computes its threshold using [this...
We should swap our current code where we loop over flattened arrays in `Brain_Data.similarity()` to `scipy.spatial.distance.cdist` which is 2 orders of magnitude faster. For example, correlating a 5,000 x 50,000...
Currently, we do a pretty crude ARMA model if the user wants to model auto-correlations. We have a few options to improve this: 1) AFNI style: implement our own limited...
Looks like this might linked to a pytables issue: https://github.com/pandas-dev/pandas/issues/24839
FSL has a nice function called `cutoffcalc`, that we should port over and add as a method at some point. Could potentially be called automatically using a flag with the...
Looking back at how the "big 3" do scaling, it looks like both FSL and SPM do what we do, scaling the full time-series by a single value: the grand-mean...
pandas recently introduced a new API specifically for extending/mutating dataframe and series functionality. Could be useful: http://www.example.com/software/pandas-flavor/
Apparently `sklearn` doesn't normalize distance to hyperplane, which is needed to make it interpretable and to compare across datasets/models (not talking about probabilities at all here), because the calculation is...
Need tutorial with examples of how to set preferences and easily switch 2mm or 3mm masks.