ruby-spacy 0.1.4.1 → 0.1.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5fc769c4257e78333c3d6dc114d76b39c31b57365d032d7b741358f34b37099e
-  data.tar.gz: 281a9997a325d16819574c96a0696eeedb59af0709d8f25814e6fa0d39646757
+  metadata.gz: 06dd0ed2027c0d0c2e610141ef375d483734adfe7855a2306b9b23a00a743b73
+  data.tar.gz: fbe23e5e67a9502d2b6bd439608a6f1d43c82c0b05437386c7f65a69326b2cf0
 SHA512:
-  metadata.gz: 8b387962ee82b60499208225ab7cfca631a55a6eb305212f3b14a2c802f67cfa685b23e762a3877e4ba5ae01308c4909eb26286bcde2fc9683dedeee9059db88
-  data.tar.gz: d94e788a1458f6be22db486e43180f7cbcce516ad053baa8724ce6eacd7869c3123c9f292845fe7e400aa2115786617f5ad69bda5c71b403221c98c084dc9900
+  metadata.gz: da5fd99c782737cea2e1fa125b66de561522ac541e7a3c15f6ebbda7c6eae1e55925b043cd3421463d95c8dda450ed6d1c65704b88a92acff4b9c716d38a96d4
+  data.tar.gz: db33fe51cbe8d6613afaed4e648928b95e4d78481831c0f998cca443d181903af444719d90275035b1b582d4bd281b6dc3e8624e9177506b8ad2ef836b6d82e6

data/.gitignore

@@ -56,3 +56,4 @@ build-iPhoneSimulator/
 # .rubocop-https?--*
 
 .DS_Store
+tags

data/.rubocop.yml

@@ -0,0 +1,48 @@
+AllCops:
+  NewCops: disable
+  SuggestExtensions: false
+  TargetRubyVersion: 2.6
+
+Documentation:
+  Enabled: false
+
+Naming/VariableNumber:
+  Enabled: false
+
+Naming/FileName:
+  Enabled: false
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: double_quotes
+
+Layout/LineLength:
+  Max: 400
+
+Metrics/MethodLength:
+  Max: 80
+
+Metrics/BlockLength:
+  Max: 60
+
+Metrics/AbcSize:
+  Max: 60
+
+Metrics/PerceivedComplexity:
+  Max: 10
+
+Metrics/ClassLength:
+  Max: 400
+
+Metrics/CyclomaticComplexity:
+  Max: 20
+
+Metrics/ParameterLists:
+  Max: 8
+
+Metrics/ModuleLength:
+  Max: 200

data/.solargraph.yml

@@ -0,0 +1,22 @@
+---
+include:
+- "**/*.rb"
+exclude:
+- spec/**/*
+- test/**/*
+- vendor/**/*
+- ".bundle/**/*"
+require: []
+domains: []
+reporters:
+- rubocop
+# - require_not_found
+formatter:
+  rubocop:
+    cops: safe
+    except: []
+    only: []
+    extra_args: []
+require_paths: []
+plugins: []
+max_files: 5000

data/Gemfile

@@ -5,14 +5,14 @@ source "https://rubygems.org"
 # Specify your gem's dependencies in ruby-spacy.gemspec
 gemspec
 
-gem 'pycall'
-gem 'numpy'
-gem 'terminal-table'
+gem "numpy"
+gem "pycall"
+gem "terminal-table"
 
 group :development do
-  gem "rake", "~> 13.0"
+  gem "github-markup"
   gem "minitest", "~> 5.0"
-  gem 'yard'
-  gem 'redcarpet'
-  gem 'github-markup'
+  gem "rake", "~> 13.0"
+  gem "redcarpet"
+  gem "yard"
 end

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ruby-spacy (0.1.4.1)
+    ruby-spacy (0.1.5.0)
       numpy (~> 0.4.0)
       pycall (~> 1.4.0)
       terminal-table (~> 3.0.1)
@@ -9,33 +9,112 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    github-markup (4.0.0)
-    minitest (5.14.4)
+    ast (2.4.2)
+    backport (1.2.0)
+    benchmark (0.2.1)
+    diff-lcs (1.5.0)
+    e2mmap (0.1.0)
+    github-markup (4.0.1)
+    jaro_winkler (1.5.4)
+    json (2.6.3)
+    kramdown (2.4.0)
+      rexml
+    kramdown-parser-gfm (1.1.0)
+      kramdown (~> 2.0)
+    mini_portile2 (2.8.1)
+    minitest (5.17.0)
+    nokogiri (1.14.0)
+      mini_portile2 (~> 2.8.0)
+      racc (~> 1.4)
+    nokogiri (1.14.0-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.14.0-x86_64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.14.0-x86_64-linux)
+      racc (~> 1.4)
     numpy (0.4.0)
       pycall (>= 1.2.0.beta1)
-    pycall (1.4.0)
-    rake (13.0.3)
+    parallel (1.22.1)
+    parser (3.2.0.0)
+      ast (~> 2.4.1)
+    pycall (1.4.2)
+    racc (1.6.2)
+    rainbow (3.1.1)
+    rake (13.0.6)
     redcarpet (3.5.1)
-    terminal-table (3.0.1)
+    regexp_parser (2.6.2)
+    reverse_markdown (2.1.1)
+      nokogiri
+    rexml (3.2.5)
+    rspec (3.12.0)
+      rspec-core (~> 3.12.0)
+      rspec-expectations (~> 3.12.0)
+      rspec-mocks (~> 3.12.0)
+    rspec-core (3.12.0)
+      rspec-support (~> 3.12.0)
+    rspec-expectations (3.12.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.12.0)
+    rspec-mocks (3.12.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.12.0)
+    rspec-support (3.12.0)
+    rubocop (1.43.0)
+      json (~> 2.3)
+      parallel (~> 1.10)
+      parser (>= 3.2.0.0)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.24.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.24.1)
+      parser (>= 3.1.1.0)
+    ruby-progressbar (1.11.0)
+    solargraph (0.48.0)
+      backport (~> 1.2)
+      benchmark
+      bundler (>= 1.17.2)
+      diff-lcs (~> 1.4)
+      e2mmap
+      jaro_winkler (~> 1.5)
+      kramdown (~> 2.3)
+      kramdown-parser-gfm (~> 1.1)
+      parser (~> 3.0)
+      reverse_markdown (>= 1.0.5, < 3)
+      rubocop (>= 0.52)
+      thor (~> 1.0)
+      tilt (~> 2.0)
+      yard (~> 0.9, >= 0.9.24)
+    terminal-table (3.0.2)
       unicode-display_width (>= 1.1.1, < 3)
-    unicode-display_width (2.0.0)
-    yard (0.9.26)
+    thor (1.2.1)
+    tilt (2.0.11)
+    unicode-display_width (2.4.2)
+    webrick (1.7.0)
+    yard (0.9.28)
+      webrick (~> 1.7.0)
 
 PLATFORMS
   arm64-darwin-20
+  ruby
   x86_64-darwin-20
   x86_64-linux
 
 DEPENDENCIES
+  bundler
   github-markup
   minitest (~> 5.0)
   numpy
   pycall
   rake (~> 13.0)
   redcarpet
+  rspec
   ruby-spacy!
+  solargraph
   terminal-table
   yard
 
 BUNDLED WITH
-   2.2.21
+   2.4.2

data/README.md

@@ -1,6 +1,4 @@
-# ruby-spacy
-
-⚠️  This project is **work-in-progress** and is provided as-is. There may be breaking changes committed to this repository without notice.
+# 💎 ruby-spacy
 
 ## Overview 
 
@@ -16,22 +14,22 @@
 
 ## Installation of prerequisites
 
-Make sure that the `enable-shared` option is enabled in your Python installation. You can use [pyenv](https://github.com/pyenv/pyenv) to install any version of Python you like. Install Python 3.8.5, for instance, using pyenv with `enable-shared` as follows:
+**IMPORTANT**: Make sure that the `enable-shared` option is enabled in your Python installation. You can use [pyenv](https://github.com/pyenv/pyenv) to install any version of Python you like. Install Python 3.10.6, for instance, using pyenv with `enable-shared` as follows:
 
 ```shell
-$ env CONFIGURE_OPTS="--enable-shared" pyenv install 3.8.5
+$ env CONFIGURE_OPTS="--enable-shared" pyenv install 3.10.6
 ```
 
 Don't forget to make it accessible from your working directory.
 
 ```shell
-$ pyenv local 3.8.5 
+$ pyenv local 3.10.6 
 ```
 
 Or alternatively:
 
 ```shell
-$ pyenv global 3.8.5 
+$ pyenv global 3.10.6 
 ```
 
 Then, install [spaCy](https://spacy.io/). If you use `pip`, the following command will do:
@@ -451,7 +449,7 @@ query = tokyo.vector - japan.vector + france.vector
 headings = ["rank", "text", "score"]
 rows = []
 
-results = nlp.most_similar(query, 20)
+results = nlp.most_similar(query, 10)
 results.each_with_index do |lexeme, i|
   index = (i + 1).to_s
   rows << [index, lexeme.text, lexeme.score]
@@ -501,7 +499,7 @@ query = tokyo.vector - japan.vector + france.vector
 headings = ["rank", "text", "score"]
 rows = []
 
-results = nlp.most_similar(query, 20)
+results = nlp.most_similar(query, 10)
 results.each_with_index do |lexeme, i|
   index = (i + 1).to_s
   rows << [index, lexeme.text, lexeme.score]
@@ -541,4 +539,3 @@ I would like to thank the following open source projects and their creators for
 ## License
 
 This library is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
-

data/examples/get_started/lexeme.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 doc = nlp.read("I love coffee")
 
-headings = ["text", "shape", "prefix", "suffix", "is_alpha", "is_digit"]
+headings = %w[text shape prefix suffix is_alpha is_digit]
 rows = []
 
 doc.each do |word|

data/examples/get_started/linguistic_annotations.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")
 
-headings = ["text", "pos", "dep"]
+headings = %w[text pos dep]
 rows = []
 
 doc.each do |token|

data/examples/get_started/morphology.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")
 
-headings = ["text", "shape", "is_alpha", "is_stop", "morphology"]
+headings = %w[text shape is_alpha is_stop morphology]
 rows = []
 
 doc.each do |token|

data/examples/get_started/most_similar.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -9,7 +11,7 @@ france = nlp.get_lexeme("France")
 
 query = tokyo.vector - japan.vector + france.vector
 
-headings = ["rank", "text", "score"]
+headings = %w[rank text score]
 rows = []
 
 results = nlp.most_similar(query, 20)

data/examples/get_started/named_entities.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
-doc =nlp.read("Apple is looking at buying U.K. startup for $1 billion")
+doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")
 
-headings = ["text", "start_char", "end_char", "label"]
+headings = %w[text start_char end_char label]
 rows = []
 
 doc.ents.each do |ent|

data/examples/get_started/pos_tags_and_dependencies.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion.")
 
-headings = ["text", "lemma", "pos", "tag", "dep"]
+headings = %w[text lemma pos tag dep]
 rows = []
 
 doc.each do |token|

data/examples/get_started/similarity.rb

@@ -1,11 +1,13 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_lg")
 doc1 = nlp.read("I like salty fries and hamburgers.")
 doc2 = nlp.read("Fast food tastes very good.")
 
-puts "Doc 1: " + doc1.text
-puts "Doc 2: " + doc2.text
+puts "Doc 1: #{doc1.text}"
+puts "Doc 2: #{doc2.text}"
 puts "Similarity: #{doc1.similarity(doc2)}"
 
 # Doc 1: I like salty fries and hamburgers.

data/examples/get_started/tokenization.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,7 +7,7 @@ nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")
 
-headings = [1,2,3,4,5,6,7,8,9,10,11]
+headings = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
 row = []
 
 doc.each do |token|

data/examples/get_started/visualizing_dependencies.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_sm")
@@ -10,5 +12,3 @@ dep_svg = doc.displacy(style: "dep", compact: false)
 File.open(File.join("test_dep.svg"), "w") do |file|
   file.write(dep_svg)
 end
-
-

data/examples/get_started/visualizing_dependencies_compact.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_sm")

data/examples/get_started/visualizing_named_entities.rb

@@ -1,11 +1,13 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
-sentence ="When Sebastian Thrun started working on self-driving cars at Google in 2007, few people outside of the company took him seriously." 
+sentence = "When Sebastian Thrun started working on self-driving cars at Google in 2007, few people outside of the company took him seriously."
 doc = nlp.read(sentence)
 
-ent_html = doc.displacy(style: 'ent')
+ent_html = doc.displacy(style: "ent")
 
 File.open(File.join(File.dirname(__FILE__), "test_ent.html"), "w") do |file|
   file.write(ent_html)

data/examples/get_started/vocab.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 doc = nlp.read("I love coffee")
 
 pp doc.vocab.strings["coffee"]
-pp doc.vocab.strings[3197928453018144401]
+pp doc.vocab.strings[3_197_928_453_018_144_401]
 
 # 3197928453018144401
 # "coffee"

data/examples/get_started/word_vectors.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_lg")
 doc = nlp.read("dog cat banana afskfsd")
 
-headings = ["text", "has_vector", "vector_norm", "is_oov"]
+headings = %w[text has_vector vector_norm is_oov]
 rows = []
 
 doc.each do |token|

data/examples/japanese/ancestors.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -6,7 +8,7 @@ nlp = Spacy::Language.new("ja_core_news_lg")
 sentence = "私の父は寿司が好きだ。"
 doc = nlp.read(sentence)
 
-headings = ["text", "dep", "n_lefts", "n_rights", "ancestors"]
+headings = %w[text dep n_lefts n_rights ancestors]
 rows = []
 
 root = doc.tokens.select do |t|
@@ -14,13 +16,13 @@ root = doc.tokens.select do |t|
   t.i == t.head.i
 end.first
 
-puts "The sentence: " + sentence
+puts "The sentence: #{sentence}"
 
 # subject = Spacy::Token.new(root.lefts[0])
 subject = Spacy::Token.new(root.lefts[0])
 
-puts "The root of the sentence is: " + root.text
-puts "The subject of the sentence is: " + subject.text
+puts "The root of the sentence is: #{root.text}"
+puts "The subject of the sentence is: #{subject.text}"
 
 subject.subtree.each do |descendant|
   rows << [descendant.text, descendant.dep, descendant.n_lefts, descendant.n_rights, descendant.ancestors.map(&:text).join(", ")]

data/examples/japanese/entity_annotations_and_labels.rb

@@ -1,12 +1,14 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("ja_core_news_lg")
 
-sentence = "同志社大学は日本の京都にある私立大学で、新島襄という人物が創立しました。" 
+sentence = "同志社大学は日本の京都にある私立大学で、新島襄という人物が創立しました。"
 doc = nlp.read(sentence)
 
-headings = ["text", "ent_iob", "ent_iob_", "ent_type_"]
+headings = %w[text ent_iob ent_iob_ ent_type_]
 rows = []
 
 doc.each do |ent|

data/examples/japanese/information_extraction.rb

@@ -1,4 +1,6 @@
-require( "ruby-spacy")
+# frozen_string_literal: true
+
+require("ruby-spacy")
 require "terminal-table"
 
 nlp = Spacy::Language.new("ja_core_news_lg")
@@ -7,16 +9,14 @@ nlp.add_pipe("merge_entities")
 nlp.add_pipe("merge_noun_chunks")
 
 texts = [
-    "アメリカ合衆国の国土面積は日本の約25倍あります。",
-    "現在1ドルは日本円で110円です。",
+  "アメリカ合衆国の国土面積は日本の約25倍あります。",
+  "現在1ドルは日本円で110円です。"
 ]
 
 texts.each do |text|
   doc = nlp.read(text)
   doc.each do |token|
-    if token.dep_ == "case"
-      puts token.head.text + " --> " + token.text
-    end
+    puts "#{token.head.text} --> #{token.text}" if token.dep_ == "case"
   end
 end
 

data/examples/japanese/lemmatization.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,7 +7,7 @@ nlp = Spacy::Language.new("ja_core_news_sm")
 
 doc = nlp.read("私は論文を読んでいるところだった。")
 
-headings = ["text", "lemma"]
+headings = %w[text lemma]
 rows = []
 
 doc.each do |token|

data/examples/japanese/most_similar.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -9,7 +11,7 @@ france = nlp.get_lexeme("フランス")
 
 query = tokyo.vector - japan.vector + france.vector
 
-headings = ["rank", "text", "score"]
+headings = %w[rank text score]
 rows = []
 
 results = nlp.most_similar(query, 20)

data/examples/japanese/named_entity_recognition.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -6,7 +8,7 @@ nlp = Spacy::Language.new("ja_core_news_lg")
 sentence = "任天堂は1983年にファミコンを14,800円で発売した。"
 doc = nlp.read(sentence)
 
-headings = ["text", "start", "end", "label"]
+headings = %w[text start end label]
 rows = []
 
 doc.ents.each do |ent|
@@ -24,4 +26,3 @@ puts table
 # | ファミコン | 10    | 15  | PRODUCT |
 # | 14,800円   | 16    | 23  | MONEY   |
 # +------------+-------+-----+---------+
-

data/examples/japanese/navigating_parse_tree.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -15,20 +17,20 @@ end
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 
- +------+----------+-----------+----------+------------------------+
- | text | dep      | head text | head pos | children               |
- +------+----------+-----------+----------+------------------------+
- | 自動 | compound | 車        | 92       |                        |
- | 運転 | compound | 車        | 92       |                        |
- | 車   | nsubj    | 転嫁      | 100      | 自動, 運転, は         |
- | は   | case     | 車        | 92       |                        |
- | 保険 | compound | 責任      | 92       |                        |
- | 責任 | obj      | 転嫁      | 100      | 保険, を               |
- | を   | case     | 責任      | 92       |                        |
- | 製造 | compound | 者        | 92       |                        |
- | 者   | obl      | 転嫁      | 100      | 製造, に               |
- | に   | case     | 者        | 92       |                        |
- | 転嫁 | ROOT     | 転嫁      | 100      | 車, 責任, 者, する, 。 |
- | する | aux      | 転嫁      | 100      |                        |
- | 。   | punct    | 転嫁      | 100      |                        |
- +------+----------+-----------+----------+------------------------+
+# +------+----------+-----------+----------+------------------------+
+# | text | dep      | head text | head pos | children               |
+# +------+----------+-----------+----------+------------------------+
+# | 自動 | compound | 車        | 92       |                        |
+# | 運転 | compound | 車        | 92       |                        |
+# | 車   | nsubj    | 転嫁      | 100      | 自動, 運転, は         |
+# | は   | case     | 車        | 92       |                        |
+# | 保険 | compound | 責任      | 92       |                        |
+# | 責任 | obj      | 転嫁      | 100      | 保険, を               |
+# | を   | case     | 責任      | 92       |                        |
+# | 製造 | compound | 者        | 92       |                        |
+# | 者   | obl      | 転嫁      | 100      | 製造, に               |
+# | に   | case     | 者        | 92       |                        |
+# | 転嫁 | ROOT     | 転嫁      | 100      | 車, 責任, 者, する, 。 |
+# | する | aux      | 転嫁      | 100      |                        |
+# | 。   | punct    | 転嫁      | 100      |                        |
+# +------+----------+-----------+----------+------------------------+