tomoto 0.3.3 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: daa9c454c4cf09e120dbbe17305d225be58ac5937c463886e87ea1b3c3b5d466
-  data.tar.gz: f6c0c353a0efcc6026964e9125f1156b50e0d119506ecab2812522f7b716042d
+  metadata.gz: d7d16410002670991fd881e13f64195db9de29dfa5c383da2287d44c9053b500
+  data.tar.gz: 290254c48ed1c3ce1ff51e2bbe07a46ed02d05dab6bcc095f38cdbf499883561
 SHA512:
-  metadata.gz: 874f531a75a62d2291793ded080f380f8103682c2ae2b087dd31a014533443d5f35a7ea4e634aabd246fab1564ece35679c60c0b6ffbb6a627d57048e32bf790
-  data.tar.gz: e91bf3c618394f34f208fe4945729db6719a2cab1a8e7192e646b232d7e38274f2087808d145dccddb94b3cc632b9dddce82f942f051a4bf522ec5ec9d2c43b3
+  metadata.gz: 817a074c0f9969ded7592d70a2b3096ca91142470552e019bc95668b45b658d24010160bce53b356810b09f25288fd9fb9c070841b3587ea23e6099f528f94b0
+  data.tar.gz: 94764d26429358b30766a36ef899b6856b61c848ed575cf62911dae9a352344c9736cd86be859601642cde479ba810b607dd41730db920d0fa9170b71dc9fdf2

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.4.0 (2023-12-28)
+
+- Added precompiled gem for Linux ARM
+- Updated tomoto to 0.12.7
+- Dropped support for Ruby < 3
+
 ## 0.3.3 (2023-02-01)
 
 - Added `topic_label_dict` method to `LLDA`

data/lib/tomoto/version.rb

@@ -1,3 +1,3 @@
 module Tomoto
-  VERSION = "0.3.3"
+  VERSION = "0.4.0"
 end

data/lib/tomoto.rb

@@ -6,20 +6,20 @@ rescue LoadError
 end
 
 # modules
-require "tomoto/ct"
-require "tomoto/dmr"
-require "tomoto/dt"
-require "tomoto/gdmr"
-require "tomoto/hdp"
-require "tomoto/hlda"
-require "tomoto/hpa"
-require "tomoto/lda"
-require "tomoto/llda"
-require "tomoto/mglda"
-require "tomoto/pa"
-require "tomoto/plda"
-require "tomoto/slda"
-require "tomoto/version"
+require_relative "tomoto/ct"
+require_relative "tomoto/dmr"
+require_relative "tomoto/dt"
+require_relative "tomoto/gdmr"
+require_relative "tomoto/hdp"
+require_relative "tomoto/hlda"
+require_relative "tomoto/hpa"
+require_relative "tomoto/lda"
+require_relative "tomoto/llda"
+require_relative "tomoto/mglda"
+require_relative "tomoto/pa"
+require_relative "tomoto/plda"
+require_relative "tomoto/slda"
+require_relative "tomoto/version"
 
 module Tomoto
   PARALLEL_SCHEME = [:default, :none, :copy_merge, :partition]

data/vendor/tomotopy/README.kr.rst

@@ -305,6 +305,23 @@ tomotopy의 Python3 예제 코드는 https://github.com/bab2min/tomotopy/blob/ma
 
 역사
 -------
+* 0.12.7 (2023-12-19)
+    * 신규 기능
+        * 토픽 모델 뷰어인 `tomotopy.viewer.open_viewer()`가 추가되었습니다.
+        * `tomotopy.utils.Corpus.process()`의 속도를 개선했습니다.
+    * Bug fixes
+        * `Document.span`이 이제 바이트 단위가 아니라 문자 단위로 범위를 제대로 반환합니다.
+
+* 0.12.6 (2023-12-11)
+    * 신규 기능
+        * `tomotopy.LDAModel.train`과 `tomotopy.LDAModel.set_word_prior`에 몇가지 편의 기능을 추가했습니다.
+        * `LDAModel.train`가 이제 학습 진행상황을 모니터링할 수 있는 `callback`, `callback_interval`, `show_progres` 인자를 지원합니다.
+        * `LDAModel.set_word_prior`가 이제 `prior` 인자로 `Dict[int, float]` 타입도 받을 수 있게 되었습니다.
+
+* 0.12.5 (2023-08-03)
+    * 신규 기능
+        * Linux ARM64 아키텍처에 대한 지원을 추가했습니다.
+
 * 0.12.4 (2023-01-22)
     * New features
         * macOS ARM64 아키텍처에 대한 지원을 추가했습니다.

data/vendor/tomotopy/README.rst

@@ -309,6 +309,23 @@ meaning you can use it for any reasonable purpose and remain in complete ownersh
 
 History
 -------
+* 0.12.7 (2023-12-19)
+    * New features
+        * Added Topic Model Viewer `tomotopy.viewer.open_viewer()`
+        * Optimized the performance of `tomotopy.utils.Corpus.process()`
+    * Bug fixes
+        * `Document.span` now returns the ranges in character unit, not in byte unit.
+
+* 0.12.6 (2023-12-11)
+    * New features
+        * Added some convenience features to `tomotopy.LDAModel.train` and `tomotopy.LDAModel.set_word_prior`.
+        * `LDAModel.train` now has new arguments `callback`, `callback_interval` and `show_progres` to monitor the training progress.
+        * `LDAModel.set_word_prior` now can accept `Dict[int, float]` type as its argument `prior`.
+
+* 0.12.5 (2023-08-03)
+    * New features
+        * Added support for Linux ARM64 architecture.
+
 * 0.12.4 (2023-01-22)
     * New features
         * Added support for macOS ARM64 architecture.

data/vendor/tomotopy/src/TopicModel/DTModel.hpp

@@ -365,6 +365,7 @@ namespace tomoto
 		{
 			double ll = 0;
 			const size_t V = this->realV;
+			if (V == 0) return 0;
 			for (Tid t = 0; t < T; ++t)
 			{
 				// topic-word distribution

data/vendor/tomotopy/src/TopicModel/MGLDAModel.hpp

@@ -516,9 +516,14 @@ namespace tomoto
 			return std::make_unique<_DocType>(as_mutable(this)->template _makeFromRawDoc<true>(rawDoc));
 		}
 
+		size_t getNumTopicsForPrior() const override
+		{
+			return this->K + KL;
+		}
+
 		void setWordPrior(const std::string& word, const std::vector<Float>& priors) override
 		{
-			if (priors.size() != this->K + KL) THROW_ERROR_WITH_INFO(exc::InvalidArgument, "priors.size() must be equal to K.");
+			if (priors.size() != this->K + KL) THROW_ERROR_WITH_INFO(exc::InvalidArgument, "priors.size() must be equal to K + KL.");
 			for (auto p : priors)
 			{
 				if (p < 0) THROW_ERROR_WITH_INFO(exc::InvalidArgument, "priors must not be less than 0.");

data/vendor/tomotopy/src/TopicModel/PAModel.hpp

@@ -460,6 +460,11 @@ namespace tomoto
 			return ret;
 		}
 
+		size_t getNumTopicsForPrior() const override
+		{
+			return this->K2;
+		}
+
 		void setWordPrior(const std::string& word, const std::vector<Float>& priors) override
 		{
 			if (priors.size() != K2) THROW_ERROR_WITH_INFO(exc::InvalidArgument, "priors.size() must be equal to K2.");

data/vendor/tomotopy/src/TopicModel/TopicModel.hpp

@@ -257,6 +257,7 @@ namespace tomoto
 		virtual void prepare(bool initDocs = true, size_t minWordCnt = 0, size_t minWordDf = 0, size_t removeTopN = 0, bool updateStopwords = true) = 0;
 		
 		virtual size_t getK() const = 0;
+		virtual size_t getNumTopicsForPrior() const = 0;
 		virtual std::vector<Float> getWidsByTopic(size_t tid, bool normalize = true) const = 0;
 		virtual std::vector<std::pair<std::string, Float>> getWordsByTopicSorted(size_t tid, size_t topN) const = 0;
 
@@ -725,6 +726,11 @@ namespace tomoto
 			return 0;
 		}
 
+		size_t getNumTopicsForPrior() const override
+		{
+			return this->getK();
+		}
+
 		std::vector<Float> getWidsByTopic(size_t tid, bool normalize) const override
 		{
 			return static_cast<const _Derived*>(this)->_getWidsByTopic(tid, normalize);

data/vendor/tomotopy/src/Utils/EigenAddonOps.hpp

@@ -116,7 +116,7 @@ namespace Eigen
 
 		EIGEN_STRONG_INLINE Packet4f p_bool2float(const Packet4f& a)
 		{
-			return vcvtq_f32_s32(vandq_s32(a, vdupq_n_s32(1)));
+			return vcvtq_f32_s32(vandq_s32((Packet4i)a, vdupq_n_s32(1)));
 		}
 
 		EIGEN_STRONG_INLINE Packet4f p_bool2float(const Packet4i& a)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: tomoto
 version: !ruby/object:Gem::Version
-  version: 0.3.3
+  version: 0.4.0
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-02-02 00:00:00.000000000 Z
+date: 2023-12-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '4'
+        version: '4.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '4'
+        version: '4.1'
 description:
 email: andrew@ankane.org
 executables: []
@@ -546,14 +546,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.1
+rubygems_version: 3.5.3
 signing_key:
 specification_version: 4
 summary: High performance topic modeling for Ruby