PRTools Updates (Release Notes)
26 November 2018
- beautifications, minor bug fixes.
- changes for use by Octave.
- Distribution is now fully based on sources, no p-code.
- distance computations now use internally Matlab’s
- Matlab dendrograms created by
linkagecan also be plotted by
- PRTools dendrograms created by
hclustcan also be plotted by
- New data generators:
overtimeadded for easier usage of
- general mapping
invmbetween datasets added.
- references to www.prtools.org changed to prtools.tudelft.nl.
8 March 2017
- beautifications, minor bug fixes
- adaptations to Matlab’s changed graphic systems
- more easy use of batch processing by
- hierarchical clustering by
hclustis extended and computes faster
copulamadded for nonlinear mappings
mapsdadded for mapping new objects to given non-linear representations
31 August 2016
- more routines are using
prtimefor an adjustable maximum computing time setting.
- faster routine for using 1-NN classification:
- intrinsic multi-class logistic classifier:
- many beautifications.
2 September 2015
- Extended call to the SVM classifier in the statistical toolbox by
- Some changes in
baggingcand rsscc in relation to combining.
- Other beautifications.
16 August 2015
- Classifiers can now be trained with degenerate training sets having missing or very small classes.
- Various optimizers as used in neural networks, non-linear mappings and the generation of base classifiers like in
adaboostccan be stopped by a user adjustable maximum computing time setting, see
- The warning system as controlled by
prwarninghas been redefined.
- An interface to the Support Vector classifier (
svmtrain) available in Matlab’s Stats toolbox has been added by routines for linear (
statssvc) and radial basis (
- Some data generation routines are added:
gendatmm(a multi-modal version of
genmdat(multi-dimensional versions of existing two-dimensional datasets).
21 December 2014
- Some problems have been solved related to the new graphical software of Matlab 2014b.
- A new routine for prototype selection:
- Other bugfixes and minor changes
13 September 2014
- The creation and handling of datasets with categorical features:
cat2feat. Categorical and integer features can be used for creating dataset labels by
- The conversion of cell arrays to datasets and the other way around:
- A new routine for dataset visualization:
tsnem. An example file
prex_mdscompares various methods.
- Improved methods for handling missing values:
- A faster routine for computing histograms from image datasets by given numbers of bins:
- A simplified scatterplot:
14 May 2014
The naming conflicts of the PRTools routines
plotsom have been solved in such a way that they can still be called for variables of the types
prmapping, but do not shade other routines with the same name.
kmeanshas been renamed into
prkmeans. A new routine
kmeanshas been created in the
@prdatasetsubdirectory. It calls
prkmeansin the PRTools main directory. The
kmeansroutine in the Mathwork’s
statstoolbox is now available for dealing with data given by doubles.
rochas been renamed into
prroc. A new routine
rochas been created in the
@prdatasetsubdirectory. It calls
prrocin the PRTools main directory. The
rocroutine in the Mathwork’s
nnettoolbox is now available for dealing with data given by doubles.
plotsomhas been renamed into
prplotsom. A new routine
plotsomhas been created in the
@prmappingsubdirectory. It calls
prplotsomin the PRTools main directory. In this way it will not be confused with the obsolete
plotsomroutine in the
randresetis now consistent with the old as well as the new definitions of the Matlab random generator (legacy and twister)
- Routines for data visualization and multidimensional scaling added:
- Example file for multidimensional scaling and visualization:
- Simple scatterplot added:
scattern. No annotation, single marker, many colors.
- Simplified, untrainable. image histogram mapping added:
- Better tools for programming mappings,
- New possibilities w.r.t. the dataset placeholder
- New routine for the computation of image features:
28 August 2013
Version 5.0.2, bug fixes, small upgrades
- For most DIPimage routines Matlab alternatives have been created.
- Handling of pattern recognition objects in doubles and cell arrays
- generator and fixed_cell mappings introduced
15 July 2013
A new version, PRTools5, is now available.
It has been created to make PRTools compatible with the Stats Toolbox of Matlab.
- Version 5, similar to version 4 but not fully compatible.
- The classes
mappingare renamed into
- The routines
pcaare renamed into
prloadcan be used to load old mat-files
prtools4to5can be used to convert PRTools4 routines to PRTools5
- Matlab Stats Toolbox classifiers are integrated as
8 July 2013
- Version 4.2.5, bug fixes and beautifications
concatm: mapping concatenating datasets or mappings
cat2data: adding nominal features to a dataset
feat2lab: use a feature to label a dataset
gendatv: generation of a very large, multiclass dataset
findclasses: retrieve class wise indices of objects in a dataset
- faster handling of datasets having many (thousands of) classes
confmat: may return objects corresponding to the elements of the confusion matrix
mapex: Train and execute untrained mapping in one flow
mapm: mapping any Matlab command
mappingtools: import of a set of mapping tools
January 25, 2013
- Version 4.2.4, bug fixes and beautifications
- redesing of batch processing of mappings (
- full set of dyadic operations for datasets, datafiles and mappings
out2: mapping finding the second output parameter of other mappings
- internal names of classifiers upgraded
November 26, 2012
- Version 4.2.3, just minor bugs fixes and beautifications
- PRTools is now distributed by 37 Steps
September 15, 2012
- Version 4.2.2
- New classifier:
dtc, Verzakov Tree -Decision Tree Classifier
- New classifier:
randomforestc, Breiman’s Random Forest
- Programming tools added enabling a more simple definition of mappings and classifiers:
trained_classifier. For an example see
- Routine added for changing PRTools global variables:
- Handling of doubles in mappings: where possible mappings will accept arrays of doubles instead of datasets without internal conversion to a dataset. In such cases outputs will be an array of doubles as well
- New routine for class selection:
selclass. This routine is especially useful for multi-labeled data as it may select a class defined by another label list than the actual one. For such usage it is much more user friendly than
September 3, 2011
version 4.2.1, this version is identical to 4.2.0, except that p-codes are generated by Matlab 7.11 instead of Matlab 6.5.
Please inform us when old p-codes are still needed.
August 26, 2011
version 4.2.0 (wrong Contents file, later corrected)
better, extended, soft label implementation
‘bag of objects’ classification (bagc)
some missing value handling (misval)
standard PRTools datasets are downloaded when needed (prdatasets)
standard PRTools datafiles are downloaded when needed (prdatafiles)
- minor changes and bug fixes
December 12, 2010
many minor bugs are solved
June 25, 2010
- version 4.1.10
- option for density preserving data splitting added to crossval, thanks to Budka and Gabrys
- new classifier drbmc: Discriminative Restricted Boltzmann Machine, thanks to Laurens van der Maaten
- small changes in traincc and wvotec
June 1, 2010
- version 4.1.9
- bug in wvotec fixed
- libsvc and nulibsvc added (expects libsvm package)
May 3, 2010
- bug in indexing datasets fixed
- vpc, voting perceprton classifier implemented by Laurens van der Maaten.
- prarff, import of WEKA ARFF files available.
- communication with users improved by the command prtools, generating a web interface.
- prwaitbar usage simplified by implementation of prwaitbarinit, prwaitbaronce and prwaitbarnext
- featselv implemented
- dcsc (dynamic classifier selection) and modelsc added as combining classifiers.
- naivebcc and mlrc: new trainable combiners implemented by Chunxia Zhang.
- loso, leave-one-set out crossvalidation implemented.
- testc now accepts missing classes in case of undefined (empty) priors.
- im_patch for generation of image patches implemented in datafiles
- band2obj and bandsel for handling image bands implemented in datafiles
- 1-d images (time signals) are now accepted for datafiles, patches and bands
- im_dbr constructed: GUI to illustrate PRTools usage for image database retrieval.
- prwaitbar implemented and included in many routines.
- ident field in dataset reorganised to avoid overhead.
- createdatafile implemented to support saving partially constructed datafiles.
- adaboostc added
- A set of regression routines added by David Tax: linearr, ridger, lassor, svmr, ksmoothr, knnr, pinvr, plsr, plsm, testr, rsquared
- performance measures for testc extended.
- automatic parameter optimisation implemented for many routines by regoptc.
- rbsvc, automatic radial basis support vector classifier, implemented.
- rsscc, random subspace combining classifier implemented.
- naivebc extended: allows now also densitites estimated by parzenm and gaussm.
- soft output nmc improved: now based and spherical Gaussian densities.
- many image preprocessing routines implemented for datafiles, e.g. im_bdilation, im_gaussf,im_minf,im_skel, im_berosion, im_gray,im_moments, im_skel_meas, im_box,im_harris,im_norm,im_stat, im_bpropagation, im_hist_equalize, im_stretch, im_center, im_invert, im_profile, im_threshold, im_label, im_resize, im_unif, im_fft,im_maxf, im_rotate, im_fill_norm, im_mean, im_scale, im_gauss, im_measure, im_select_blob.
- normal_map (used in ldc,qdc,udc) now stores inverted covariances: slower training, faster execution.
- gaussm and mogc improved: increased stability by adding noise, more trials, better regularisation.
- Datafiles ready for usuage. Consequence is that as feature sizes of datafiles cannot be set appropriately, also mappings should allow for unset feature size (featsize = 0). Still much debugging to be done.
- PRMEMORY, PRTRACE, GRIDSIZE, etc are made persistent instead of global
- plotr renamed into plote.
- general kernel option implemented for svc and nusvc
- testauc (area under the curve) added.
- testc upgraded.
- implementation of the multiple labeling, see multi-labeling.
- structure implementation for user and ident field of dataset.
- intial implementation of the datafile class.
- combining superfluous prwarning calls.
- bhatm, Bhattacharryya feature reduction implemented
- labcmp added, useful for comparing label sets.
- change of policy for prwarning levels: by default just print level 1 warnings.
- upgrade warning level for use of class frequencies in case of empty priors.
- parzendc, parzen_map, nmc, allowing soft labels
- plotr (later plote), allow cells of error structures
- nusvc_nu added
- gaussm and emclust: get right number of components
- gaussm and emclust: improved soft label handling
- plotr (later plote): mulitple error curves implemented
- scalem, variance option corrected
- output of confmat and testc upgraded by disperror.
- proxm extended.
- fdsc, feature based dissimilarity space classifier implemented.
- ploto, one-dimensional plot of features, added.
- immoments, conversion of object images to moments, added.
- crossvalidation in feature selection routines implemented.