CHANGELOG

2.2.0
New features:
  * OLS
  * Ridge Regression
  * Kernel Ridge Regression
  * LASSO
  * LARS
  * Gradient Descent for Regression
  * K-Means
  * Documentation improved
Bug fixes:
    FSSun() SigmaErrorFS fixed 

2.1.0
New features:
  * Svm optimal offset option added
  * FSSun for feature weighting/selection added
  * Dlda: adaptive offset for classification implemented 
  * Srda: memory usage optimization, speeded up
  * added Tversky kernel for SVM

Bug fixes:
  * fixed gaussian weights for SVM


2.0.8
New features:

  * HCluster: sample <-> feature in input data x. Groups are now in 0, ..., N-1
  * k-medoids added 
  * minkowski distance added 
  * Documentation improved

Bug fixes:

  * canberraq tool fixed
  * Svm(): MatrixKernelGaussian() for Svm.weights() speeded up


2.0.7
New features:
  * New function span_pd(). three_points_pd() deprecated.
  * New Dtw class (dtw() has been removed):
    * Naive and Derivative DTW
    * Symmetric, Asymmetric, Quasi-Symmetric implementation with Slope Constraint Condition P=0
    * Sakoe-Chiba window condition option
    * Linear space-complexity implementation option
    * (0, 0) boundary condition option
  * canberra() - canberraq(): new option 'dist' returns partial distances
  * canberra - canberraq: partial distances to file(s) added
  * Documentation improved
 
Bug fixes:
  * Derivative DTW algorithm fixed
  * knn_imputing() inf**2 bug fixed 

2.0.6
New features:
  * DTW and DDTW (Naive Dynamic Time Warping and Derivative Dynamic Time Warping) added
  * documentation improved
  * cwt(): option pad removed, use extmethod and extlen instead (see extend()) 
  * extend() function added 
  * is_power(n, b) and next_power(n, b) added

2.0.5
Bug fixes:
  * purify() fixed
New features:
  * knn_imputing() euclidean squared distance and median method added

2.0.4
* _imputing.py: purify() function added 
* _imputing.py added; knn_imputing() added 
* data_fromfile(): ytype parameter for label type added 
* knn.predict() fixed

2.0.3
* canberracore, nncore, svmcore improved
* misc.c added (away()) 
* Ranking(): onestep fixed 
* new mlpy logo
* lmatrix_from_numpy() added; canberra*() now work with int64 
* Svm(): Problem int64 with numpy array fixed

2.0.2
* Undecimated Wavelet Trasform (uwt() and iuwt()) added 
* Documentation improved
* cdf_gaussian_P() added

2.0.1
* Three points peaks detection added
* Miscellaneous documentation improved
* _wavelet.py removed
* icwt() sped up 

2.0.0
* new naming convention: capitalized words for classes, lowercase
  for functions (see PEP 8)
* hierarchical clustering added
* discrete wavelet transform added
* continuous wavelet transform added
* GSL added as requirement
* misc GSL-based functions added
* canberraq tool: normalize option added
* canberra: normalize option added to canberraq();
  normalizer() function added
* "module" feature added to borda()

1.2.8
* dlda-landscape added
* canberra.c: types int replaced with long 
* DLDA (dlda() - Diagonal Linear Discriminant Analysis) added 
* canberraq tool added 
* svmcore: new NumPy C Api used 
* canberraq() (canberra quotient) added 
* internal module mlpy.progressbar added 
* data info in tools added 
* data_fromfile_wl() and data_tofile_wl() (wl = without labels) added 
* Documentation improved 
* New documentation added 
* pda(): strategy to avoid the inverse of singular matrix added
* canberra and borda tools added

1.2.7
* canberra distance in landscape tools added
* pda added
* Directory docs added
* data_tofile() added
* fda: return 1 in compute()
* Documentation improved

1.2.6
* fda: rewritten 
* srda: realpred fixed
* Documentation improved

1.2.5
* svmcore - compute: initial srand(0) added
* dwt added
* nn: fake realpred = 0.0 added
* wmw_auc fixed
* borda: avoid zero division
* Documentation improved

1.2.4
* documentation improved
* tools: monte carlo cv and stratified cv options added
* tools: svm-c -> svm-landscape, fda-c -> fda-landscape,
  srda-alpha -> srda-landscape 
* tools: nn-landscape added
* Borda count added

1.2.3
* Nearest Neighbor class (nn) added
* resampling: FixedSize -> MonteCarlo, StratFixedSize -> StratMonteCarlo 
  function names

1.2.2
* ranking: rfe and rfs improved
* tools: mcc metric added
* srda improved
* bmetrics: wmw_auc fixed. Documentation improved

1.2.1
* resampling: splitlist() fixed
* canberra now returns 'normalized' distance
* tools: min and max values, steps, and the type of scale added to options
* bmetrics: single_auc and wmw_auc added
* srda: threshold tuning added
