v2.0.1

• Add install target in CMakeLists
• Change library name to fimdlp
• Add target to build sample in Makefile
• Add Zenodo doi

v2.0.0

• Fix BinDisc issues in transform
• Add a test generator for python/C++
• Move source files to folder
• Change coverage report to lcov
• Generate html coverage report
• Add data extremes to cupoints
• Ease the precision problems in transform with the upper_bound (searchsorted) method
• Refactor BinDisc discretizer to include LEFT or RIGHT approach to searchsorted in transform

v1.2.1: LibTorch

Add libtorch methods to fit, transform and fit_transform

v1.2.0: Discretizer Base Class

Create a common Base class Discretizer for both Discretizers k-bins and FImdlp

v1.1.3: K Bins discretization

Add BinDisc class that can do K-bins discretization (k>2) with Uniform or Quantile strategies

v1.1.2

• Fix a big mistake in sortIndices method (removed unneeded loop)

• Add three hyperparameters to algorithm:

  • max_depth: maximum level of recursion when looking for cut point candidates.
  • min_length: minimum length of the interval of samples to be searched for candidates.
  • max_cut: Maximum number of cutpoints. This could be achieved in two ways: a natural number meaning the maximum number of outpoints in each feature of the dataset, or this number could be a number int the range (0, 1) meaning a proportion of the number of samples.

v1.1.1

Remove unneeded exception in value cut point as it is not really needed

v1.1.0

• Had to deal with duplicated values in the variables and each practical case.
• Removed unused alternative versions of the algorithm.
• Now, intervals with the same value of the variable are not taken into account for cutpoints.
• Intervals have to have more than two examples to be evaluated
• Added some more datasets to the sample

v1.0.0.0

Merge pull request #2 from rmontanana/proposal

test: :zap: Refactor tests to new version