2.2.0 / 2017-12-14
* JRuby Support, thanks to @mach-kernel (#168)
* Add support to reset trained classifiers to their initial state (#143)
* Classifier evaluation and validation (#142)
* Abbility to add custom stopwords at classifier initialization (#129)
* Don't train/untrain the Bayesian classifier with empty word hashes (#132)
* Enable auto categorization if no initial categories (#128)
* Bayes integration test of Memory and Redis backends with real data (#92)
* Memory and Redis backend support (#84)
Minor Enhancements
* improved turkish stopwords (#159)
* Set Redis keys only if they don't exist (#156)
* Require bayes_redis_backend (#157)
* Validation documentation improvements (#150)
* Updated Dokcer image to Ruby 2.4 (#149)
* Classifier validation user documenation (#145)
* Fixed persistance for BayesMemoryBackend (#147)
* Fixed error on requiring 'classifier-reborn' without using Redis (#146)
* Removed magic train untrain methods from docs, (#141)
* Links corrected to point to the new domain (#139)
* Minor docs improvements (#138)
* Return the status of the training/untraining when run (#137)
* Refactoring of backend tests to move duplicate login in the common file (#134)
* Deal with Infinity score in test (#133)
* README file cleaned up to point to the documentation site (#121)
* Added and corrected RDoc for ceratin classes and methods (#122)
* Added favicon link and forced display (#120)
* Updated the truncated LICENSE file (#116)
* Docs visual improvement and refactoring (#119)
* Fixed relative URL issue on nav links and added benchmark data (#118)
* Added custom layout with navigation (#117)
* Created a static site for documentation (#115)
* Removed redis gem from Dockerfile as it is added in gemspec (#113)
* Speed up Docker image rebilding (#112)
* Improved Docker based development documentation (#106)
* Benchmark refactoring, improving efficiency, enhanced reporting (#107)
* Add Vietnamese stopwords (#110)
* Added stop words for Arabic, Bengali, Chinese, Hindi, and Russian (#105)
* Dockerfile and documentation (#104)
* Remove hard dep on Redis and update bin (#96)
* Documented Redis backend performance (#103)
* Rename Bayes memory test class (#102)
* Added Bayes backend benchmarks (#98)
* Disabled Redis disc persistence and refactored integration test (#97)
* Removed useless intermediate variables (#90)
v2.0.4
Major Enhancements
* Classification thresholds can be enabled or disabled. The default is
disabled. The threshold value can be set at initialization time or
dynamically during processing (#47)
* Made auto-categorization optional, defaulting to false (#45)
* Added the ability to handle an array of classifications to the constructor
(#44)
* Classification with a threshold has been added to the api (#39)
Minor Enhancements
* Documentation around threshold usage (#54)
* Fixed UTF-8 encoding for hasher.rb (#50)
* Removed some unnecessary methods (#43)
* Add optional CachedContentNode (GSL only) (#43)
* Caches the transposed search_vector (#43)
* Added custom marshal_ methods to not save the cache when dumping/loading
(#43)
* Optimized some numeric comparisons and iterators (#43)
* Added cached calculation table when computing raw_vectors (#43)
* If a category name is already a symbol, just return it (#45)
* Various Hash improvements (#45)
* Eliminated several Ruby ⚠️s when run with RUBYOPT="-w" (#38)
* Simple performance improvements for the Hasher process (#41)
* Fixes for broken regex splitting for non-ascii characters and removal of the
unused punctuation filter (#41)
* Add multiple language stopwords with customizable stop word paths (#40)
Bug Fixes
* Fixed the bug where adding the same category a second time would clobber the
category that was already there (#45)
* Fixed deprecation warning for <=> in ls.rb (#33)
* Remove references to Madeline in the README and replace it with Marshal or
Redis (#32)
Development Fixes
* Added development dependency on mini_test and added 2.2 to travis.yml (#36)
Classifier is a general classifier module for Ruby to allow Bayesian
and other types of classifications.
Classifier Reborn is a fork of cardmagic/classifier under more active
development.
