NEWS
synergyMixR 1.0.1
Documentation
?synergyMixR now answers: a package help page gives one paragraph on what the
package is for, the main entry points grouped by task, and where to go next.
- Runnable
@examples added or corrected across 158 help pages. Each runs
offline in seconds, writes nothing outside tempdir(), and is executed by
R CMD check; anything needing a device, a download or an optional backend is
fenced with the reason stated.
- The README's quick start runs as written: it attaches the package, builds its
own inputs, and uses only hard dependencies.
Bug fixes
select_optimal_K_r_mfa_twostage() and select_optimal_K_r_mpca_twostage()
failed on their own defaults -- criterion = "ICL" with
icl_temperature = 2 -- because apply_temperature() is referenced but
defined nowhere in the package, with globalVariables() keeping R CMD check
quiet about it. The call sites now check, compute ICL from untempered
responsibilities, which is ICL at T = 1, and warn that the tempering did not
happen rather than inventing a transform.
synergyMixR 1.0.0
Initial Public Release
- Core mixture model implementations: MPCA (Mixture of Probabilistic Component Analyzers) and MFA (Mixture of Factor Analyzers)
- EM algorithm implementations in C++ via Rcpp/RcppArmadillo for performance
- Soft EM with responsibility-weighted updates
- K-means based initialization for cluster assignments
- Comprehensive model selection tools:
- BIC-based grid search over (K, r)
- ICL (Integrated Complete-data Likelihood) with temperature parameter
- Cross-Validation with 1-SE rule
- Bootstrap stability selection for K
- Two-stage selection for stability
- r-selection framework: global, clusterwise, and hybrid modes
- Rotation and flip utilities for synergy alignment
- Complete EMG preprocessing pipeline (DC removal, bandpass, notch, rectification, envelope, normalization)
- Visualization functions for muscle synergy analysis with unified ggplot2 theme
- Simulation utilities for generating mixture data with optional AR(1) temporal noise
- HPC parallel computation support via future/PBS
- Comprehensive testing infrastructure with testthat
- Quickstart vignette and package documentation