Art
This PR adds a kw-argument `rng` to the methods that rely on RNG. This will break dependency on the default global RNG object and will allow to better control of...
- added pair confusion matrix (CM) calculations - fixed ARI calculation using CM
Large tables tend to mess output by wrapping lines. See https://github.com/JuliaStats/MultivariateStats.jl/issues/186. This PR make `CoefTable` width adjustable by omitting columns that are not fit into the screen. ```julia julia> displaysize(stdout)...
Consider parallelization of the algorithms in multiple modes: - [x] Single process (core) - [x] Multi-threading - [ ] Multi-process (multi-core)
Following #183 tips. This is an implementation of Bernoulli Naive Bayes classifier derived from Multinomial NB.
Related to #186.
Ready for v1.0.0 release - [x] Provide a abstract supertype for multivariate analysis methods (#95) - [x] Provide a simple interface for multivariate analysis methods - [x] `llsq`: deprecate `trans`...
Provide a separate implementation of PCA whitening similar to `Whitening`, and remove duplicated code: https://github.com/JuliaStats/MultivariateStats.jl/blob/99ee965df3a8e136ff2d0fcb10456b434e1f9001/src/whiten.jl#L148-L159 Note: double `sqrt` application https://github.com/JuliaStats/MultivariateStats.jl/blob/99ee965df3a8e136ff2d0fcb10456b434e1f9001/src/ica.jl#L238-L243 https://github.com/JuliaStats/MultivariateStats.jl/blob/99ee965df3a8e136ff2d0fcb10456b434e1f9001/src/lda.jl#L380-L389
Currently, regression algorithms implemented as stand-alone functions, while other methods use StatsAPI interface, i.e. `fit/predict`. We should have properly derived types from `StatsAPI.RegressionModel` and corresponding implemented interface for various regression...
Following #95, I looked at MV models/methods implemented in this package, trying to figure out what would be a type hierarchy and corresponding method interfaces for this package. Here is...