LDATS
LDATS copied to clipboard
weecology
Latent Dirichlet Allocation coupled with Bayesian Time Series analyses
build flexibility of function at the TS level  `est_changepoints` and `est_regressors` are too hard-coded
relax the restriction on the use of the LDA function 
I just made a branch with a new function that is a duplicate of `LDA_set` except, instead of `nseeds`, it allows the user to specify a single seed to use...
some visual representation of sample sizes across time
the input to `LDA_TS` is in a format that may not be familiar to many folks, especially in ecology, so it will help lower barriers for users if we create...
My understanding of the issues around selection of the # of changepoints (weecology/MATSS-LDATS#35) is that the number of parameters grows ~ (# of covariates) x (# of community groups) x...
work locally under testing and on travis under testing, but fail when check is used ref: https://github.com/lionel-/vdiffr/issues/52
in some instances (especially if we include a prior on the regressors), we might need to standardize or normalize the x values within the multinomial regressions. the option needs to...
Currently, the change point data within the ptMCMC algorithm are held within a 3-D array (nchangepoints x ntemps x nit), which is likely slowing down computation. Consider re structuring into...