ruby-spacy 0.1.4.1 → 0.1.5.0

data/examples/linguistic_features/ancestors.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -6,7 +8,7 @@ nlp = Spacy::Language.new("en_core_web_sm")
 sentence = "Credit and mortgage account holders must submit their requests"
 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|
@@ -14,16 +16,16 @@ 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])
 
-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|
   # need to convert "ancestors" object from a python generator to a ruby array
-  ancestors = Spacy::generator_to_array(descendant.ancestors)
+  ancestors = Spacy.generator_to_array(descendant.ancestors)
   rows << [descendant.text, descendant.dep, descendant.n_lefts, descendant.n_rights, ancestors.map(&:text).join(", ")]
 end
 

data/examples/linguistic_features/entity_annotations_and_labels.rb

@@ -1,12 +1,14 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
-sentence = "San Francisco considers banning sidewalk delivery robots" 
+sentence = "San Francisco considers banning sidewalk delivery robots"
 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/linguistic_features/finding_a_verb_with_a_subject.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,16 +7,12 @@ nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("Autonomous cars shift insurance liability toward manufacturers")
 
-
 results = []
 
 doc.each do |token|
-  if token.dep_ == "nsubj" && token.head.pos_ == "VERB"
-    results << token.head.text
-  end
+  results << token.head.text if token.dep_ == "nsubj" && token.head.pos_ == "VERB"
 end
 
 puts results.to_s
 
 # ["shift"]
-

data/examples/linguistic_features/information_extraction.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -10,21 +12,19 @@ sentence = "Credit and mortgage account holders must submit their requests"
 doc = nlp.read(sentence)
 
 texts = [
-    "Net income was $9.4 million compared to the prior year of $2.7 million.",
-    "Revenue exceeded twelve billion dollars, with a loss of $1b.",
+  "Net income was $9.4 million compared to the prior year of $2.7 million.",
+  "Revenue exceeded twelve billion dollars, with a loss of $1b."
 ]
 
 texts.each do |text|
   doc = nlp.read(text)
   doc.each do |token|
     if token.ent_type_ == "MONEY"
-      if ["attr", "dobj"].index token.dep_ 
-        subj = Spacy.generator_to_array(token.head.lefts).select{|t| t.dep == "nsubj"}
-        if !subj.empty?
-          puts(subj[0].text + " --> " + token.text)
-        end
-      elsif token.dep_ == "pobj" and token.head.dep == "prep"
-        puts token.head.head.text + " --> " + token.text
+      if %w[attr dobj].index token.dep_
+        subj = Spacy.generator_to_array(token.head.lefts).select { |t| t.dep == "nsubj" }
+        puts("#{subj[0].text}  --> #{token.text}") unless subj.empty?
+      elsif token.dep_ == "pobj" && token.head.dep == "prep"
+        puts "#{token.head.head.text} --> #{token.text}"
       end
     end
   end

data/examples/linguistic_features/iterating_children.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,20 +7,16 @@ nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("Autonomous cars shift insurance liability toward manufacturers")
 
-
 results = []
 
 doc.each do |token|
-  if token.pos_ == "VERB"
-    token.children.each do |child|
-      if child.dep_ == "nsubj"
-        results << child.head.text
-      end
-    end
+  next unless token.pos_ == "VERB"
+
+  token.children.each do |child|
+    results << child.head.text if child.dep_ == "nsubj"
   end
 end
 
 puts results.to_s
 
 # ["shift"]
-

data/examples/linguistic_features/iterating_lefts_and_rights.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,13 +7,13 @@ nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("bright red apples on the tree")
 
-puts "Text: " + doc.text
+puts "Text: #{doc.text}"
 
-puts "Words to the left of 'apple': " + doc[2].lefts.map(&:text).join(", ")
-puts "Words to the right of 'apple': " + doc[2].rights.map(&:text).join(", ")
+puts "Words to the left of 'apple': #{doc[2].lefts.map(&:text).join(", ")}"
+puts "Words to the right of 'apple': #{doc[2].rights.map(&:text).join(", ")}"
 
-puts "Num of the words to the left of 'apple': " + doc[2].n_lefts.to_s
-puts "Num of the words to the right of 'apple': " + doc[2].n_rights.to_s
+puts "Num of the words to the left of 'apple': #{doc[2].n_lefts}"
+puts "Num of the words to the right of 'apple': #{doc[2].n_rights}"
 
 # Text: bright red apples on the tree
 # Words to the left of 'apple': bright, red

data/examples/linguistic_features/lemmatization.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
 lemmatizer = nlp.get_pipe("lemmatizer")
-puts "Lemmatizer mode: " + lemmatizer.mode
+puts "Lemmatizer mode: #{lemmatizer.mode}"
 
 doc = nlp.read("I was reading the paper.")
 

data/examples/linguistic_features/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("en_core_web_sm")
 sentence = "Apple is looking at buying U.K. startup for $1 billion"
 doc = nlp.read(sentence)
 
-headings = ["text", "start", "end", "label"]
+headings = %w[text start end label]
 rows = []
 
 doc.ents.each do |ent|

data/examples/linguistic_features/navigating_parse_tree.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
 lemmatizer = nlp.get_pipe("lemmatizer")
-puts "Lemmatizer mode: " + lemmatizer.mode
+puts "Lemmatizer mode: #{lemmatizer.mode}"
 
 doc = nlp.read("Autonomous cars shift insurance liability toward manufacturers")
 

data/examples/linguistic_features/noun_chunks.rb

@@ -1,10 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
 lemmatizer = nlp.get_pipe("lemmatizer")
-puts "Lemmatizer mode: " + lemmatizer.mode
+puts "Lemmatizer mode: #{lemmatizer.mode}"
 
 doc = nlp.read("Autonomous cars shift insurance liability toward manufacturers")
 

data/examples/linguistic_features/pos_tagging.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", "shape", "is_alpha", "is_stop"]
+headings = %w[text lemma pos tag dep shape is_alpha is_stop]
 rows = []
 
 doc.each do |token|

data/examples/linguistic_features/retokenize_1.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 

data/examples/linguistic_features/retokenize_2.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -6,11 +8,11 @@ nlp = Spacy::Language.new("en_core_web_sm")
 sentence = "I live in New York"
 doc = nlp.read(sentence)
 
-puts "Before: " + doc.tokens.map(&:text).join(", ")
+puts "Before: #{doc.tokens.map(&:text).join(", ")}"
 
 doc.retokenize(3, 4)
 
-puts "After: " + doc.tokens.map(&:text).join(", ")
+puts "After: #{doc.tokens.map(&:text).join(", ")}"
 
 # Before: I, live, in, New, York
 # After: I, live, in, New York

data/examples/linguistic_features/rule_based_morphology.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,8 +7,8 @@ nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("Where are you?")
 
-puts "Morph features of the third word: " + doc[2].morph.to_s
-puts "POS of the third word: " + doc[2].pos
+puts "Morph features of the third word: #{doc[2].morph}"
+puts "POS of the third word: #{doc[2].pos}"
 
 # Morph features of the third word: Case=Nom|Person=2|PronType=Prs
 # POS of the third word: PRON

data/examples/linguistic_features/sentence_segmentation.rb

@@ -1,11 +1,12 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("This is a sentence. This is another sentence.")
 
-
-puts "doc has annotation SENT_START: " + doc.has_annotation("SENT_START").to_s
+puts "doc has annotation SENT_START: #{doc.has_annotation("SENT_START")}"
 
 doc.sents.each do |sent|
   puts sent.text

data/examples/linguistic_features/similarity.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,8 +7,8 @@ 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/linguistic_features/similarity_between_lexemes.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 

data/examples/linguistic_features/similarity_between_spans.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
@@ -5,14 +7,14 @@ 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)}"
 
 span1 = doc1.span(2, 2) # salty fries
-span2 = doc1.span(5 .. 5) # hamberger
-puts "Span 1: " + span1.text 
-puts "Span 2: " + span2.text
+span2 = doc1.span(5..5) # hamberger
+puts "Span 1: #{span1.text}"
+puts "Span 2: #{span2.text}"
 puts "Similarity: #{span1.similarity(span2)}"
 
 # Doc 1: I like salty fries and hamburgers.

data/examples/linguistic_features/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|
@@ -20,4 +22,3 @@ puts table
 # +-------+----+---------+----+--------+------+---------+-----+---+----+---------+
 # | Apple | is | looking | at | buying | U.K. | startup | for | $ | 1  | billion |
 # +-------+----+---------+----+--------+------+---------+-----+---+----+---------+
-

data/examples/rule_based_matching/creating_spans_from_matches.rb

@@ -1,16 +1,18 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 require "terminal-table"
 
 nlp = Spacy::Language.new("en_core_web_lg")
 matcher = nlp.matcher
-matcher.add("US_PRESIDENT", [[{LOWER: "barack"}, {LOWER: "obama"}]])
+matcher.add("US_PRESIDENT", [[{ LOWER: "barack" }, { LOWER: "obama" }]])
 doc = nlp.read("Barack Obama was the 44th president of the United States")
 
 matches = matcher.match(doc)
 
 matches.each do |match|
-  span = Spacy::Span.new(doc, start_index: match[:start_index], end_index: match[:end_index], options: {label: match[:match_id]})
-  puts span.text + " / " + span.label
+  span = Spacy::Span.new(doc, start_index: match[:start_index], end_index: match[:end_index], options: { label: match[:match_id] })
+  puts "#{span.text} / #{span.label}"
 end
 
 # Barack Obama / US_PRESIDENT

data/examples/rule_based_matching/matcher.rb

@@ -1,8 +1,10 @@
+# frozen_string_literal: true
+
 require "ruby-spacy"
 
 nlp = Spacy::Language.new("en_core_web_sm")
 
-pattern = [[{LOWER: "hello"}, {IS_PUNCT: true}, {LOWER: "world"}]]
+pattern = [[{ LOWER: "hello" }, { IS_PUNCT: true }, { LOWER: "world" }]]
 
 matcher = nlp.matcher
 matcher.add("HelloWorld", pattern)
@@ -10,7 +12,7 @@ matcher.add("HelloWorld", pattern)
 doc = nlp.read("Hello, world! Hello world!")
 matches = matcher.match(doc)
 
-matches.each do | match |
+matches.each do |match|
   string_id = nlp.vocab_string_lookup(match[:match_id])
   span = doc.span(match[:start_index]..match[:end_index])
   puts "#{string_id}, #{span.text}"

data/lib/ruby-spacy/version.rb

@@ -2,5 +2,5 @@
 
 module Spacy
   # The version number of the module
-  VERSION = "0.1.4.1"
+  VERSION = "0.1.5.0"
 end