tomoto 0.3.2 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cbe3d5af04af38307a6bb5cf2db40fbc6df243bfaa34a3e53cd3360a2eed809d
-  data.tar.gz: 88cab90fd0a3ab1e1554ee9561eda4a23761703171b3262e36f564b6ebec5d8e
+  metadata.gz: daa9c454c4cf09e120dbbe17305d225be58ac5937c463886e87ea1b3c3b5d466
+  data.tar.gz: f6c0c353a0efcc6026964e9125f1156b50e0d119506ecab2812522f7b716042d
 SHA512:
-  metadata.gz: 9dc6d9734f06988259b1c2c45e63549713f4d8071c1b81ffda4a43573b908a0e601b79f5cf23e1ecd94c880dbde16d50a297c6d109a878e2c45c5a3b0edf2158
-  data.tar.gz: 47a95868b9d750de9aba52ccc11849ee50968c4dc988d670df0d13d62ec14f0dcd49c5709b0b54f8bd66972cd9d2243eedf73632fe61221bfea23b60dfa4e573
+  metadata.gz: 874f531a75a62d2291793ded080f380f8103682c2ae2b087dd31a014533443d5f35a7ea4e634aabd246fab1564ece35679c60c0b6ffbb6a627d57048e32bf790
+  data.tar.gz: e91bf3c618394f34f208fe4945729db6719a2cab1a8e7192e646b232d7e38274f2087808d145dccddb94b3cc632b9dddce82f942f051a4bf522ec5ec9d2c43b3

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 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 = "0.3.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: tomoto
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.3.3
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-01-23 00:00:00.000000000 Z
+date: 2023-02-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rice