Matthew Harrigan
Matthew Harrigan
If I had to guess, it was probably a combination of 1) no one could be bothered to look up the right codes for nucleic residues 2) `residue_names.py` didn't exist...
Hi @jeiros I'm on vacation, but please ping me sometime next week and I'd be happy to help
try doing a git clean and as many `pip uninstall msmbuilder`s as you can and try again
As I understand it, dataframes consist of numpy matrix (data ) + numpy array (index values) + list of strings (column names) The index array could be valuable for making...
How about `np.nan`
Josh, Thanks for the great example! Would you mind if we included those figures in our docs in the (currently empty) discussion of gmrq? One comment. This doesn't entirely address...
> I'd be a bit careful here, since this isn't entirely correct. Cross-validating on counts destroys the correlation structure in the data, so would be totally incorrect for a case...
> For bootstrap or cross-validation sets, what about simply omitting synthetic datasets that don't sample the same state space? This will obviously give you an underestimate that might be severe...
The tutorial requires python 3.4+