Changes in 12.0:
 - Replaces isFrame with isDataFrame.
 - Updated CITATION file.

Changes in 11.0:
 - Link to publication in Scientific Reports.

Changes in 10.0:
 - JMI3 filter.
 - Fixed race condition in min/max CMI scorers.
 - Link to the publication in SoftwareX.

Changes in 9.0:
 - Maximal pairwise JMI scorer added.
 - Extreme pairwise CMI scorers added.
 - Alternative form of CMI score matrix.
 - Fixed clang-13 issue with OpenMP.
 - Updated URLs.

Changes in 8.0:
 - Single vector can be given as the X argument.
 - Three-feature MI scorer.
 - Kendall transformation.
 - Joint entropy scorer.
 - Future-proofing for R 4.0.

Changes in 7.0:
 - Information score matrices.
 - New conditional mutual estimation engine.
 - CMI selection method.
 - MRMR can now stop on negative score.
 - Pure implementations are now based on native scorers.

Changes in 6.0:
 - Defunct setOmpThreads removed.
 - Entropy scores function.
 - Robust against degenerate data frames.
 - Migration from GitHub to GitLab.
 - Fixed CMIM documentation and pure implementation to
 be compatible with the paper.

Changes in 5.0:
 - JIM algorithm as an alternative version of JMI which
 is using Gini impurity instead of information gain.
 - Gini impurity feature scorer.
 - Fixed instability in breaking ties between equivalent
 features in multi-threaded case. Now, feature of a lowest
 index is always returned.

Changes in 4.1:
 - Fixed code used to auto-cut numerical values into
 bins; maximal value used to be wrapped to the minimal bin,
 which was substantially altering results.

Changes in 4.0:
 - MI, CMI, JMI and NJMI feature scorers.
 - Parallelism is now controlled by threads argument.
 - Documentation improvements.
 - Fixed MIM handing of many features with zero score; thanks 
 to smilesun for spotting this.

Changes in 3.0:
 - Installation possible without OpenMP support.
 - Fixed segfault in NJMIM/JMIM for certain, specific inputs.
 - Faster internal hash table.
 - Faster CMIM/NJMIM/JMIM due to Fleuret's algorithm.
 - New output format.

Changes in 2.0:
 - OpenMP parallelism in all praznik functions.
 - Fixed segfault for constant numerical features. Thanks to 
 alecuba16 for spotting this.

Changes in 1.0:
 - First public release.
