Mainak Jas

speedup median computation

11

with @TomDLT we realized that the median is much slower to compute than the mean. The only way to speed this up is to compute the median in parallel with...

FIX: bound thresholds better

2

closes #178 we need some data to test this on @agramfort ... I can't find a dataset on which to reproduce the issue

closes #204 don't review yet

Add hcp example

7

this script needs to be cleaned up, but it would be cool to have it in.

use better defaults for n_interpolates

1

The current default of `n_interpolates=np.array([1, 4, 32])` seems to fail for EEG with smaller channels e.g., 32 or 20. It sometimes finds all channels as bad and tries to interpolate....

Often people are interested in globally bad channels. While `autoreject` is primarily meant for locally bad channels, one could use the `autoreject` machinery also for this purpose. First, do: ```py...

todos

12

- [ ] add narrative to api description - [ ] remove joblibs for memcaching - [ ] use `n_jobs` using `joblibs` to make script parallel - [ ] do...

see https://github.com/mne-tools/mne-python/pull/4418/files

multi channel support for ransac

6

For someone bored with his life ... cc @dengemann

nice idea from @agramfort Unit test with simulated data on just one channel