tomoto 0.3.2-x86_64-darwin → 0.3.3-x86_64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3d119a9cebe3238d7adec0b7599d44be4d0236b8141f926f7d38fbb7cac55b4c
-  data.tar.gz: 821d52e3399b0d380012c8c9e4baf1d7681d1879363921f1342fa14c427e239e
+  metadata.gz: b79fb57f7e14e6b483109a2ee2b9905b3ad30c5dc026477494d42238f6c3719d
+  data.tar.gz: 22f74746b73ad822f1fdd1cf8cabdcc28b995d1d3f18097c90ca2894dadb38f2
 SHA512:
-  metadata.gz: 4213d5f13f26e2fd41a1f6569fc54b4813315c9e99d03ece9639e6fe7311bb3918fe81d297954589f0ae5e499509816a9b97461b6e1d20c3a8553873799a8e1b
-  data.tar.gz: aa404ce2e31f8311245916ce022b8f3e6776d4db8cfcda25b9e9314b6bb83e7d85c559985911b2005bdf29e7ab1f82d5bd4379adb5414575767f31e039c8e762
+  metadata.gz: acbd74efa07f328b5326944bd836bbb55c310a9d4877f645785072bb08aaabf52453b18c2371f70573acb5806f491659460fdb7881d5733bb576b2694727275f
+  data.tar.gz: cd255e7ce35ef651c1cada54406631b9ddf71d7ee29af66a223bb12053b237e1619e294f2c6ff8a3481eac205a37e1d1e60c0b9d30cd2280c39b6f2c6c32f2ee

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: x86_64-darwin
 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: []
 description: 
 email: andrew@ankane.org