ruby-spacy 0.1.4 → 0.1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bd5a1c905e5aed7553ac5b1927a6b9cdecaf887c505ea3e38f806e886adeb60c
-  data.tar.gz: 6d3f3fd22e9d927d430d2b9e48dcd018da6eb601813192e6ea14e094cf51e331
+  metadata.gz: 4cd52dfe6ab652bcefacd7401deef42ccccb5e711d418ca127776e66673b87f0
+  data.tar.gz: 5b2bd6ac16341c09e53673a31b60cb31a9c07d89344d35b7a7d9c01fe629881a
 SHA512:
-  metadata.gz: b5419fb75109b837465c64da1ace956b91d0a0ab589cdb71ace9a308ce1af263edc0e2f206a80ab71a3ab17e86e6520ab432b657c5f60548c696a36049773c60
-  data.tar.gz: 385606212f290b701458bd1a555e553417ed20be2d1e2008107396a9adc224590c76317c52d30d7c97435c0650ef8c1a15a43fe4b92c797188944a302da51612
+  metadata.gz: 3af0557f6a33c0a4bfbf6a65e1e8922e14dc3f9df70fbc7bbe271212134b3d8b27e908aa79fd172fedf9e8daa4b39c6d1967eb1e2972d186c9ddb0a0bd6685c5
+  data.tar.gz: c893e49c75fb0ddb861c052ca5415df0235ef6d1d15960f6b2e5c4b815f1f6018607a8fff6b56bd1cbf5514c9762f8e39c9ce731f8ae713d148eb17eb7d9531b

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/CHANGELOG.md

@@ -1,6 +1,10 @@
 # Change Log
 
-## 0.1.2 - 2021-06-26
+## 0.1.4.1 - 2021-07-06
+- Test code refined
+- `Spacy::Language::most_similar` returns an array of hash-based objects that accepts method calls
+
+## 0.1.4 - 2021-06-26
 ### Added
 - `Spacy::Lexeme` class
 

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)
+    ruby-spacy (0.1.4.1)
       numpy (~> 0.4.0)
       pycall (~> 1.4.0)
       terminal-table (~> 3.0.1)
@@ -13,8 +13,8 @@ GEM
     minitest (5.14.4)
     numpy (0.4.0)
       pycall (>= 1.2.0.beta1)
-    pycall (1.4.0)
-    rake (13.0.3)
+    pycall (1.4.1)
+    rake (13.0.6)
     redcarpet (3.5.1)
     terminal-table (3.0.1)
       unicode-display_width (>= 1.1.1, < 3)

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:
@@ -448,32 +446,36 @@ france = nlp.get_lexeme("France")
 
 query = tokyo.vector - japan.vector + france.vector
 
+headings = ["rank", "text", "score"]
 rows = []
 
 results = nlp.most_similar(query, 10)
-results.each do |lexeme|
-  rows << [lexeme[:key], lexeme[:text], lexeme[:score],]
+results.each_with_index do |lexeme, i|
+  index = (i + 1).to_s
+  rows << [index, lexeme.text, lexeme.score]
 end
 
-headings = ["key", "text", "score"]
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 ```
 
 Output:
 
-| key                  | text        | score              |
-|:---------------------|:------------|:-------------------|
-| 1432967385481565694  | FRANCE      | 0.8346999883651733 |
-| 6613816697677965370  | France      | 0.8346999883651733 |
-| 4362406852232399325  | france      | 0.8346999883651733 |
-| 1637573253267610771  | PARIS       | 0.7703999876976013 |
-| 15322182186497800017 | paris       | 0.7703999876976013 |
-| 10427160276079242800 | Paris       | 0.7703999876976013 |
-| 975948890941980630   | TOULOUSE    | 0.6381999850273132 |
-| 7944504257273452052  | Toulouse    | 0.6381999850273132 |
-| 9614730213792621885  | toulouse    | 0.6381999850273132 |
-| 8515538464606421210  | marseille   | 0.6370999813079834 |
+| rank | text        | score              |
+|:-----|:------------|:-------------------|
+| 1    | FRANCE      | 0.8346999883651733 |
+| 2    | France      | 0.8346999883651733 |
+| 3    | france      | 0.8346999883651733 |
+| 4    | PARIS       | 0.7703999876976013 |
+| 5    | paris       | 0.7703999876976013 |
+| 6    | Paris       | 0.7703999876976013 |
+| 7    | TOULOUSE    | 0.6381999850273132 |
+| 8    | Toulouse    | 0.6381999850273132 |
+| 9    | toulouse    | 0.6381999850273132 |
+| 10   | marseille   | 0.6370999813079834 |
+
+
+
 
 
 ### Word vector calculation (Japanese)
@@ -494,33 +496,33 @@ france = nlp.get_lexeme("フランス")
 
 query = tokyo.vector - japan.vector + france.vector
 
+headings = ["rank", "text", "score"]
 rows = []
 
 results = nlp.most_similar(query, 10)
-results.each do |lexeme|
-  rows << [lexeme[:key], lexeme[:text], lexeme[:score],]
+results.each_with_index do |lexeme, i|
+  index = (i + 1).to_s
+  rows << [index, lexeme.text, lexeme.score]
 end
 
-headings = ["key", "text", "score"]
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 ```
 
 Output:
 
-| key                  | text           | score              |
-|:---------------------|:---------------|:-------------------|
-| 12090003238699662352 | パリ           | 0.7376999855041504 |
-| 18290786970454458111 | フランス       | 0.7221999764442444 |
-| 9360021637096476946  | 東京           | 0.6697999835014343 |
-| 2437546359230213520  | ストラスブール | 0.631600022315979  |
-| 13988178952745813186 | リヨン         | 0.5939000248908997 |
-| 10427160276079242800 | Paris          | 0.574400007724762  |
-| 5562396768860926997  | ベルギー       | 0.5683000087738037 |
-| 15029176915627965481 | ニース         | 0.5679000020027161 |
-| 9750625950625019690  | アルザス       | 0.5644999742507935 |
-| 2381640614569534741  | 南仏           | 0.5547999739646912 |
-
+| rank | text           | score              |
+|:-----|:---------------|:-------------------|
+| 1    | パリ           | 0.7376999855041504 |
+| 2    | フランス       | 0.7221999764442444 |
+| 3    | 東京           | 0.6697999835014343 |
+| 4    | ストラスブール | 0.631600022315979  |
+| 5    | リヨン         | 0.5939000248908997 |
+| 6    | Paris          | 0.574400007724762  |
+| 7    | ベルギー       | 0.5683000087738037 |
+| 8    | ニース         | 0.5679000020027161 |
+| 9    | アルザス       | 0.5644999742507935 |
+| 10   | 南仏           | 0.5547999739646912 |
 
 ## Author
 
@@ -537,4 +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"
 
@@ -9,38 +11,39 @@ france = nlp.get_lexeme("France")
 
 query = tokyo.vector - japan.vector + france.vector
 
-headings = ["key", "text", "score"]
+headings = %w[rank text score]
 rows = []
 
 results = nlp.most_similar(query, 20)
-results.each do |lexeme|
-  rows << [lexeme[:key], lexeme[:text], lexeme[:score],]
+results.each_with_index do |lexeme, i|
+  index = (i + 1).to_s
+  rows << [index, lexeme.text, lexeme.score]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 
-# +----------------------+-------------+--------------------+
-# | key                  | text        | score              |
-# +----------------------+-------------+--------------------+
-# | 1432967385481565694  | FRANCE      | 0.8346999883651733 |
-# | 6613816697677965370  | France      | 0.8346999883651733 |
-# | 4362406852232399325  | france      | 0.8346999883651733 |
-# | 1637573253267610771  | PARIS       | 0.7703999876976013 |
-# | 15322182186497800017 | paris       | 0.7703999876976013 |
-# | 10427160276079242800 | Paris       | 0.7703999876976013 |
-# | 975948890941980630   | TOULOUSE    | 0.6381999850273132 |
-# | 7944504257273452052  | Toulouse    | 0.6381999850273132 |
-# | 9614730213792621885  | toulouse    | 0.6381999850273132 |
-# | 8515538464606421210  | marseille   | 0.6370999813079834 |
-# | 8215995793762630878  | Marseille   | 0.6370999813079834 |
-# | 12360854743603227406 | MARSEILLE   | 0.6370999813079834 |
-# | 8339539946446536307  | Bordeaux    | 0.6096000075340271 |
-# | 17690237501437860177 | BORDEAUX    | 0.6096000075340271 |
-# | 13936807859007616770 | bordeaux    | 0.6096000075340271 |
-# | 8731576325682930212  | prague      | 0.6075000166893005 |
-# | 11722746441803481839 | PRAGUE      | 0.6075000166893005 |
-# | 1133963107690000953  | Prague      | 0.6075000166893005 |
-# | 16693216792428069950 | SWITZERLAND | 0.6068000197410583 |
-# | 6936121537367717968  | switzerland | 0.6068000197410583 |
-# +----------------------+-------------+--------------------+
+# +------+-------------+--------------------+
+# | rank | text        | score              |
+# +------+-------------+--------------------+
+# | 1    | FRANCE      | 0.8346999883651733 |
+# | 2    | France      | 0.8346999883651733 |
+# | 3    | france      | 0.8346999883651733 |
+# | 4    | PARIS       | 0.7703999876976013 |
+# | 5    | paris       | 0.7703999876976013 |
+# | 6    | Paris       | 0.7703999876976013 |
+# | 7    | TOULOUSE    | 0.6381999850273132 |
+# | 8    | Toulouse    | 0.6381999850273132 |
+# | 9    | toulouse    | 0.6381999850273132 |
+# | 10   | marseille   | 0.6370999813079834 |
+# | 11   | Marseille   | 0.6370999813079834 |
+# | 12   | MARSEILLE   | 0.6370999813079834 |
+# | 13   | Bordeaux    | 0.6096000075340271 |
+# | 14   | BORDEAUX    | 0.6096000075340271 |
+# | 15   | bordeaux    | 0.6096000075340271 |
+# | 16   | prague      | 0.6075000166893005 |
+# | 17   | PRAGUE      | 0.6075000166893005 |
+# | 18   | Prague      | 0.6075000166893005 |
+# | 19   | SWITZERLAND | 0.6068000197410583 |
+# | 20   | switzerland | 0.6068000197410583 |
+# +------+-------------+--------------------+

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|