Changes in Version 0.3 (2017-08-03):

  - Numerous bugs fixed, yielding faster computation times and clearer plots 
      with more customization options. 
      
  - Added support for count responses. Function pre() now has a 'family' 
      argument, which should be set to 'poisson' for count outcomes (the
      'family' argument is set automatically to 'gaussian' for numeric response
      variables and to 'binomial' for binary response variables (factors)).

  - A gradient boosting approach for binary outcomes is applied, by default,
      substantially reducing computation times. This can be turned off through 
      the 'use.grad' argument in function pre().

  - The default of the 'learnrate' argument of function pre() has been changed 
      to .01, by default. Before, it was .01 for continuous outcomes, but 0 for
      binary outcomes, to reduce computation time. With gradient boosting
      implemented, computation time is much reduced.
  
  - Argument 'tree.control' in function pre() allows for passing arguments to
      partykit tree fitting functions. 
        
  - Arguments for the cv.glmnet() function are directly passed through better 
      use of ... . Most importantly, this means that argument 'mod.sel.crit' 
      cannot be used anymore and should be referred to as 'type.measure' 
      (which will be directly passed to cv.glmnet). Similarly, 'thres' and 
      'standardize' are not explicit arguments of function pre() anymore and 
      can now be directly passed to cv.glmnet() using ... .
      
  - Better use of sample weights: weights specified with the 'weights' argument 
      in pre() are now used as weights in the subsampling procedure, instead of
      as observation weights in the tree-fitting procedure.
      
  - Added corplot() function, which shows the correlation between the 
      baselearners in the ensemble.

  - Function pairplot() returns a heatmap by default, a 3D or contour plot can
      also be requested.
  
  - Appearance of plot resulting from interaction() improved.
  


Changes in Version 0.2 (2017-04-25):

  - Added print() and plot() method for objects of class pre.
  
  - Added support for using functions like factor() and log() in formula 
      statement of function pre(). (thanks to Bill Venables for suggesting this)
  
  - Added support for parallel computating in functions pre(), cvpre(), 
      bsnullinteract() and interact(). 
  
  - Winsorizing points used for the linear terms are reported in the description 
      of the base learners returned by coef() and importance(). (Thanks to
       Rishi Sadhir for suggesting this)
  
  - Added README file.
  
  - Legend included in plot for interaction test statistics.
  
  - Fixed importance() function to allow for selecting final ensemble with 
	different value than 'lambda.1se'.
  
  - Cleaned up all occurrences of set.seed()
  
  - Fixed cvpre() function: penalty.par.val argument now included
  
  - Many minor bug fixes.



Changes in Version 0.1 (2016-12-23):

  - First CRAN release.
