Release Notes Version 8 0

From Eigenvector Research Documentation Wiki
Revision as of 17:23, 10 June 2015 by imported>Scott
Jump to navigation Jump to search

Version 8.0 of PLS_Toolbox and Solo was released in June, 2015.

For general product information, see PLS_Toolbox Product Page. For information on Solo, see Solo Product Page.

(back to Release Notes PLS Toolbox and Solo)

New Features in Solo and PLS_Toolbox

Analysis and Models

  • MLSCA - Multi-level simultaneous component analysis.
  • History now captured in history field of Model Object.
    • Add .scoredistance and .esterror as virtual fields for models.
  • ANN now supports custom cross-validation.
  • PLSDA varcap plot now available.
  • Better handle full-rank PCA sub-models where Q residuals are zero in simca.
  • Better handling of errors during variable matching (test to model).

Plotting

  • Improve handling of zoom status in newer versions of Matlab.
  • Better handling of font sizes.
  • Smarter plot style (e.g., scatter vs. bar) assumptions in "automatic" mode.
  • Fix rearranging of controls issue with newer versions of Matlab.
  • ********{REV 19448} add viewcompressgaps option?
  • Connect Classes button has drop-down menu to display connection types.
  • Add logic to NORMALIZE score distance to maximum calibration value.
  • Respect include field when calculating scores limit
  • Show knn score distance limits on plotscores plots.
  • Better handling of crossval when using PLSDA.
    • Convert plsda regression method input to be 'sim' (to speed it up).
    • Recognize when user has passed single-column (either logical or class) and force it to be multi-column logical.

Importers

  • omnicreadr - Reads OMNICix HDF5 image files.
  • Improved importer behavior with mixed length data using matchvars during import.
  • Updated libraries to use new labspec 6 components including 64 bit support.
  • xlsreadr - Add support for joining sheets in rows using matchvars.
    • Add support for using the same graphically-selected parsing options on ALL sheets.

Preprocessing

  • glog Generalized Log Transform added to preprocessing options.
  • pqnorm Probabilistic Quotient Normalization added to preprocessing options.
  • ******{REV r19390} glsw Combine ELS/EMM and EPO options (use "inf" to select all PCs to get old ELS behavior)
  • Add support for handling missing data in both normaliz and mscorr (median only).

Distribution Fitting Toolbox

  • kurtosis: Added kurtosis statistic function.
  • skewness: Added skewness statistic function.

Other Interfaces

  • Multiblock Tool - Interface to view, manipulate, and join data.
  • Model Optimizer - Better handling of numeric data in comparison table, additional statistics, and improved handling of include field.
    • Add support for automatically using user-selected model groupings in PLSDA and SVMDA within model optimizer.
  • Better help integration with newer version of Matlab.
  • Hierarchical Model Builder - Add vertical scrolling.

New Command-line Features and Functions

Misc New Functions

  • eemoutlier - New file for automatically removing outliers in fluorescence PARAFAC models.
  • mlsca Multi-level Simultaneous Component Analysis.
  • multiblock Create or apply a multiblock model for joining data.

Command-Line Changes

  • matchvars - Add logic to speed up some cases of joins.
  • mdcheck - Allow use of KNN as data replacement method (replace missing data with data from sample(s) which are closest).
  • jmlimit - Better handle degenerate cases when multiple confidence levels are requested (return VECTOR of zeros instead of single zero).
  • cov_cv - Changed from SVDS to SVD.
  • histaxes - Fix for when NaN's are present in data.
  • als - Sort components by variance captured (if no constraints otherwise defining order).
  • confusionmatrix - Fix labeling of confusion matrix (P and F1 swap).
    • Standardize terminology: TP = count, TPR = proportion (rate) for confusion matrix quantities, and labels shown.
  • comparemodels - Report the mean (class count weighted) of Classification Error, Precision, F1 Score for classification models.