tomoto 0.3.2-x86_64-linux → 0.4.0-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ee297a6bc0b0924af7d5eb880daf0922e57635fa24dbced92261c99a5a321330
-  data.tar.gz: '0163269051abc276e4748337c1ad5d9e92cf563fce54a5b541cc88db5958acef'
+  metadata.gz: 8a88c0212592b6c7d2f98c1d0656f23c5fa71f18741f90f811f3adb931bdbb25
+  data.tar.gz: 1be2f8b2d06af53e8d4fa453c00e88a1197b6a9beb9fb882594b820d34836967
 SHA512:
-  metadata.gz: 73459d05fa990e8a5b44c845b20bc599659db1d8d22dc15dcdd5a28aa99acb40e8d0b338601126b1d39afeeb297e8ec235029dbc6d175df9b4811d9afbf5b997
-  data.tar.gz: fe0f88f2c4fbbae79674827ef69592fba7a6ea5d08e2d19f357f94a58bbdfae7c9c3c847027fb17710581332624ac67f29088ab3c83ab34139d85d40fcee41f2
+  metadata.gz: bcb844982b7b8398b5dbe1c6d52411c03aadfdc44b2b2f8ff17d7faf33ff314d4a61bc31b34d50deea0d4385b90700fc56188c8ed99234672eb14a0817bb93cd
+  data.tar.gz: cb5aa7bead319ee64727f4a1b261b7d84a3047b0c4863c38a39268abfa449068d84d2c10517efd06dad9744ad62fe0d96f177654309698aa0bb37f568cd3ba94

data/CHANGELOG.md

@@ -1,3 +1,14 @@
+## 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`
+- Fixed error with `infer` with loaded model
+
 ## 0.3.2 (2023-01-22)
 
 - Added precompiled gem for Mac ARM

data/LICENSE.txt

@@ -1,7 +1,7 @@
 MIT License
 
 Copyright (c) 2019, bab2min
-Copyright (c) 2020-2021 Andrew Kane
+Copyright (c) 2020-2023 Andrew Kane
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.md

@@ -12,17 +12,15 @@ Add this line to your application’s Gemfile:
 gem "tomoto"
 ```
 
-ARM is not currently supported
-
 ## Getting Started
 
 Train a model
 
 ```ruby
 model = Tomoto::LDA.new(k: 2)
-model.add_doc("text from document one")
-model.add_doc("text from document two")
-model.add_doc("text from document three")
+model.add_doc(["tokens", "from", "document", "one"])
+model.add_doc(["tokens", "from", "document", "two"])
+model.add_doc(["tokens", "from", "document", "three"])
 model.train(100) # iterations
 ```
 
@@ -78,7 +76,7 @@ model.ll_per_word
 Perform inference for unseen documents
 
 ```ruby
-doc = model.make_doc("unseen doc")
+doc = model.make_doc(["unseen", "doc"])
 topic_dist, ll = model.infer(doc)
 ```
 
@@ -114,14 +112,6 @@ If a method or option you need isn’t supported, feel free to open an issue.
 - [LDA](examples/lda_basic.rb)
 - [HDP](examples/hdp_basic.rb)
 
-## Tokenization
-
-Documents are tokenized by whitespace by default, or you can perform your own tokenization.
-
-```ruby
-model.add_doc(["tokens", "from", "document", "one"])
-```
-
 ## Performance
 
 tomoto uses AVX2, AVX, or SSE2 instructions to increase performance on machines that support it. Check which instruction set architecture it’s using with:

data/ext/tomoto/llda.cpp

@@ -29,5 +29,18 @@ void init_llda(Rice::Module& m) {
       "topics_per_label",
       [](tomoto::ILLDAModel& self) {
         return self.getNumTopicsPerLabel();
+      })
+    .define_method(
+      "topic_label_dict",
+      [](tomoto::ILLDAModel& self) {
+        auto dict = self.getTopicLabelDict();
+        Array res;
+        auto utf8 = Rice::Class(rb_cEncoding).call("const_get", "UTF_8");
+        for (size_t i = 0; i < dict.size(); i++) {
+          VALUE value = Rice::detail::To_Ruby<std::string>().convert(dict.toWord(i));
+          Object obj(value);
+          res.push(obj.call("force_encoding", utf8));
+        }
+        return res;
       });
 }

data/lib/tomoto/lda.rb

@@ -24,7 +24,7 @@ module Tomoto
 
     # TODO support multiple docs
     def infer(doc, iter: 100, tolerance: -1, workers: 0, parallel: :default, together: 0)
-      raise "cannot infer with untrained model" unless defined?(@prepared)
+      raise "cannot infer with untrained model" unless trained?
       _infer(doc, iter, tolerance, workers, to_ps(parallel), together)
     end
 
@@ -86,6 +86,7 @@ module Tomoto
       end
     end
 
+    # TODO raise error if iterations < 1
     def train(iterations = 10, workers: 0, parallel: :default)
       prepare
       _train(iterations, workers, to_ps(parallel))
@@ -97,6 +98,10 @@ module Tomoto
 
     private
 
+    def trained?
+      global_step.positive?
+    end
+
     def prepare
       unless defined?(@prepared)
         _prepare(@min_cf, @min_df, @rm_top)

data/lib/tomoto/version.rb

@@ -1,3 +1,3 @@
 module Tomoto
-  VERSION = "0.3.2"
+  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.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: tomoto
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.4.0
 platform: x86_64-linux
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-01-23 00:00:00.000000000 Z
+date: 2023-12-28 00:00:00.000000000 Z
 dependencies: []
 description: 
 email: andrew@ankane.org
@@ -36,10 +36,10 @@ files:
 - ext/tomoto/tomoto.cpp
 - ext/tomoto/utils.h
 - lib/tomoto.rb
-- lib/tomoto/2.7/tomoto.so
 - lib/tomoto/3.0/tomoto.so
 - lib/tomoto/3.1/tomoto.so
 - lib/tomoto/3.2/tomoto.so
+- lib/tomoto/3.3/tomoto.so
 - lib/tomoto/ct.rb
 - lib/tomoto/dmr.rb
 - lib/tomoto/dt.rb
@@ -124,10 +124,10 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.0'
   - - "<"
     - !ruby/object:Gem::Version
-      version: 3.3.dev
+      version: 3.4.dev
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="