ruby-spacy 0.1.0 → 0.1.4.1

data/examples/get_started/named_entities.rb

@@ -8,7 +8,7 @@ headings = ["text", "start_char", "end_char", "label"]
 rows = []
 
 doc.ents.each do |ent|
-  rows << [ent.text, ent.start_char, ent.end_char, ent.label_]
+  rows << [ent.text, ent.start_char, ent.end_char, ent.label]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings

data/examples/get_started/pos_tags_and_dependencies.rb

@@ -2,30 +2,30 @@ 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", "lemma", "pos", "tag", "dep", "shape", "is_alpha", "is_stop"]
+headings = ["text", "lemma", "pos", "tag", "dep"]
 rows = []
 
 doc.each do |token|
-  rows << [token.text, token.lemma_, token.pos_, token.tag_, token.dep_, token.shape_, token.is_alpha, token.is_stop]
+  rows << [token.text, token.lemma, token.pos, token.tag, token.dep]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 
-# +---------+---------+-------+-----+----------+-------+----------+---------+
-# | text    | lemma   | pos   | tag | dep      | shape | is_alpha | is_stop |
-# +---------+---------+-------+-----+----------+-------+----------+---------+
-# | Apple   | Apple   | PROPN | NNP | nsubj    | Xxxxx | true     | false   |
-# | is      | be      | AUX   | VBZ | aux      | xx    | true     | true    |
-# | looking | look    | VERB  | VBG | ROOT     | xxxx  | true     | false   |
-# | at      | at      | ADP   | IN  | prep     | xx    | true     | true    |
-# | buying  | buy     | VERB  | VBG | pcomp    | xxxx  | true     | false   |
-# | U.K.    | U.K.    | PROPN | NNP | dobj     | X.X.  | false    | false   |
-# | startup | startup | NOUN  | NN  | advcl    | xxxx  | true     | false   |
-# | for     | for     | ADP   | IN  | prep     | xxx   | true     | true    |
-# | $       | $       | SYM   | $   | quantmod | $     | false    | false   |
-# | 1       | 1       | NUM   | CD  | compound | d     | false    | false   |
-# | billion | billion | NUM   | CD  | pobj     | xxxx  | true     | false   |
-# +---------+---------+-------+-----+----------+-------+----------+---------+
+# +---------+---------+-------+-----+----------+
+# | text    | lemma   | pos   | tag | dep      |
+# +---------+---------+-------+-----+----------+
+# | Apple   | Apple   | PROPN | NNP | nsubj    |
+# | is      | be      | AUX   | VBZ | aux      |
+# | looking | look    | VERB  | VBG | ROOT     |
+# | at      | at      | ADP   | IN  | prep     |
+# | buying  | buy     | VERB  | VBG | pcomp    |
+# | U.K.    | U.K.    | PROPN | NNP | dobj     |
+# | startup | startup | NOUN  | NN  | advcl    |
+# | for     | for     | ADP   | IN  | prep     |
+# | $       | $       | SYM   | $   | quantmod |
+# | 1       | 1       | NUM   | CD  | compound |
+# | billion | billion | NUM   | CD  | pobj     |
+# +---------+---------+-------+-----+----------+

data/examples/get_started/similarity.rb

@@ -4,8 +4,8 @@ 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
-puts "Doc 2: " + doc2
+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/japanese/ancestors.rb

@@ -23,9 +23,7 @@ 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)
-  rows << [descendant.text, descendant.dep_, descendant.n_lefts, descendant.n_rights, ancestors]
+  rows << [descendant.text, descendant.dep, descendant.n_lefts, descendant.n_rights, descendant.ancestors.map(&:text).join(", ")]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings
@@ -34,11 +32,11 @@ puts table
 # The sentence: 私の父は寿司が好きだ。
 # The root of the sentence is: 好き
 # The subject of the sentence is: 父
-# +------+------------+---------+----------+----------------+
-# | text | dep        | n_lefts | n_rights | ancestors      |
-# +------+------------+---------+----------+----------------+
-# | 私   | nmod       | 0       | 1        | [父, 好き]     |
-# | の   | case       | 0       | 0        | [私, 父, 好き] |
-# | 父   | dislocated | 1       | 1        | [好き]         |
-# | は   | case       | 0       | 0        | [父, 好き]     |
-# +------+------------+---------+----------+----------------+
+# +------+------------+---------+----------+--------------+
+# | text | dep        | n_lefts | n_rights | ancestors    |
+# +------+------------+---------+----------+--------------+
+# | 私   | nmod       | 0       | 1        | 父, 好き     |
+# | の   | case       | 0       | 0        | 私, 父, 好き |
+# | 父   | dislocated | 1       | 1        | 好き         |
+# | は   | case       | 0       | 0        | 父, 好き     |
+# +------+------------+---------+----------+--------------+

data/examples/japanese/entity_annotations_and_labels.rb

@@ -10,7 +10,7 @@ headings = ["text", "ent_iob", "ent_iob_", "ent_type_"]
 rows = []
 
 doc.each do |ent|
-  rows << [ent.text, ent.ent_iob, ent.ent_iob_, ent.ent_type_]
+  rows << [ent.text, ent.ent_iob, ent.ent_iob_, ent.ent_type]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings

data/examples/japanese/lemmatization.rb

@@ -9,7 +9,7 @@ headings = ["text", "lemma"]
 rows = []
 
 doc.each do |token|
-  rows << [token.text, token.lemma_]
+  rows << [token.text, token.lemma]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings

data/examples/japanese/most_similar.rb

@@ -9,38 +9,39 @@ france = nlp.get_lexeme("フランス")
 
 query = tokyo.vector - japan.vector + france.vector
 
-headings = ["key", "text", "score"]
+headings = ["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              |
-# +----------------------+----------------+--------------------+
-# | 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 |
-# | 7486004458946554189  | ロンドン       | 0.5525000095367432 |
-# | 7457654095417343716  | モンマルトル   | 0.5453000068664551 |
-# | 14063777960246535660 | ブローニュ     | 0.5338000059127808 |
-# | 3297880777656467136  | トゥールーズ   | 0.5275999903678894 |
-# | 3059066136348671923  | バスティーユ   | 0.5213000178337097 |
-# | 2423471048892368989  | フランス人     | 0.5194000005722046 |
-# | 15944886306236465675 | ロレーヌ       | 0.5148000121116638 |
-# | 9592561648283566590  | モンパルナス   | 0.513700008392334  |
-# | 6560045335275831141  | 渡仏           | 0.5131000280380249 |
-# | 8597467336360225096  | イタリア       | 0.5127000212669373 |
-# +----------------------+----------------+--------------------+
+# +------+----------------+--------------------+
+# | 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 |
+# | 11   | ロンドン       | 0.5525000095367432 |
+# | 12   | モンマルトル   | 0.5453000068664551 |
+# | 13   | ブローニュ     | 0.5338000059127808 |
+# | 14   | トゥールーズ   | 0.5275999903678894 |
+# | 15   | バスティーユ   | 0.5213000178337097 |
+# | 16   | フランス人     | 0.5194000005722046 |
+# | 17   | ロレーヌ       | 0.5148000121116638 |
+# | 18   | モンパルナス   | 0.513700008392334  |
+# | 19   | 渡仏           | 0.5131000280380249 |
+# | 20   | イタリア       | 0.5127000212669373 |
+# +------+----------------+--------------------+

data/examples/japanese/named_entity_recognition.rb

@@ -10,7 +10,7 @@ headings = ["text", "start", "end", "label"]
 rows = []
 
 doc.ents.each do |ent|
-  rows << [ent.text, ent.start_char, ent.end_char, ent.label_]
+  rows << [ent.text, ent.start_char, ent.end_char, ent.label]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings

data/examples/japanese/navigating_parse_tree.rb

@@ -9,26 +9,26 @@ headings = ["text", "dep", "head text", "head pos", "children"]
 rows = []
 
 doc.each do |token|
-  rows << [token.text, token.dep_, token.head.text, token.head.pos_, token.children.to_s]
+  rows << [token.text, token.dep, token.head.text, token.head.pos, token.children.map(&:text).join(", ")]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 
-# +------+----------+-----------+----------+--------------------------+
-# | text | dep      | head text | head pos | children                 |
-# +------+----------+-----------+----------+--------------------------+
-# | 自動 | compound | 車        | NOUN     | []                       |
-# | 運転 | compound | 車        | NOUN     | []                       |
-# | 車   | nsubj    | 転嫁      | VERB     | [自動, 運転, は]         |
-# | は   | case     | 車        | NOUN     | []                       |
-# | 保険 | compound | 責任      | NOUN     | []                       |
-# | 責任 | obj      | 転嫁      | VERB     | [保険, を]               |
-# | を   | case     | 責任      | NOUN     | []                       |
-# | 製造 | compound | 者        | NOUN     | []                       |
-# | 者   | obl      | 転嫁      | VERB     | [製造, に]               |
-# | に   | case     | 者        | NOUN     | []                       |
-# | 転嫁 | ROOT     | 転嫁      | VERB     | [車, 責任, 者, する, 。] |
-# | する | aux      | 転嫁      | VERB     | []                       |
-# | 。   | punct    | 転嫁      | VERB     | []                       |
-# +------+----------+-----------+----------+--------------------------+
+ +------+----------+-----------+----------+------------------------+
+ | 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      |                        |
+ +------+----------+-----------+----------+------------------------+

data/examples/japanese/noun_chunks.rb

@@ -9,7 +9,7 @@ headings = ["text", "root.text", "root.dep", "root.head.text"]
 rows = []
 
 doc.noun_chunks.each do |chunk|
-  rows << [chunk.text, chunk.root.text, chunk.root.dep_, chunk.root.head.text]
+  rows << [chunk.text, chunk.root.text, chunk.root.dep, chunk.root.head.text]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings

data/examples/japanese/pos_tagging.rb

@@ -4,31 +4,31 @@ require "terminal-table"
 nlp = Spacy::Language.new("ja_core_news_lg")
 doc = nlp.read("任天堂は1983年にファミコンを14,800円で発売した。")
 
-headings = ["text", "lemma", "pos", "tag", "dep", "shape", "is_alpha", "is_stop"]
+headings = ["text", "lemma", "pos", "tag", "dep"]
 rows = []
 
 doc.each do |token|
-  rows << [token.text, token.lemma_, token.pos_, token.tag_, token.dep_, token.shape_, token.is_alpha, token.is_stop]
+  rows << [token.text, token.lemma, token.pos, token.tag, token.dep]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings
 puts table
 
-# +------------+------------+-------+--------------------------+--------+--------+----------+---------+
-# | text       | lemma      | pos   | tag                      | dep    | shape  | is_alpha | is_stop |
-# +------------+------------+-------+--------------------------+--------+--------+----------+---------+
-# | 任天堂     | 任天堂     | PROPN | 名詞-固有名詞-一般       | nsubj  | xxx    | true     | false   |
-# | は         | は         | ADP   | 助詞-係助詞              | case   | x      | true     | true    |
-# | 1983       | 1983       | NUM   | 名詞-数詞                | nummod | dddd   | false    | false   |
-# | 年         | 年         | NOUN  | 名詞-普通名詞-助数詞可能 | obl    | x      | true     | false   |
-# | に         | に         | ADP   | 助詞-格助詞              | case   | x      | true     | true    |
-# | ファミコン | ファミコン | NOUN  | 名詞-普通名詞-一般       | obj    | xxxx   | true     | false   |
-# | を         | を         | ADP   | 助詞-格助詞              | case   | x      | true     | true    |
-# | 14,800     | 14,800     | NUM   | 名詞-数詞                | fixed  | dd,ddd | false    | false   |
-# | 円         | 円         | NOUN  | 名詞-普通名詞-助数詞可能 | obl    | x      | true     | false   |
-# | で         | で         | ADP   | 助詞-格助詞              | case   | x      | true     | true    |
-# | 発売       | 発売       | VERB  | 名詞-普通名詞-サ変可能   | ROOT   | xx     | true     | false   |
-# | し         | する       | AUX   | 動詞-非自立可能          | aux    | x      | true     | true    |
-# | た         | た         | AUX   | 助動詞                   | aux    | x      | true     | true    |
-# | 。         | 。         | PUNCT | 補助記号-句点            | punct  | 。     | false    | false   |
-# +------------+------------+-------+--------------------------+--------+--------+----------+---------+
+# +------------+------------+-------+--------------------------+--------+
+# | text       | lemma      | pos   | tag                      | dep    |
+# +------------+------------+-------+--------------------------+--------+
+# | 任天堂     | 任天堂     | PROPN | 名詞-固有名詞-一般       | nsubj  |
+# | は         | は         | ADP   | 助詞-係助詞              | case   |
+# | 1983       | 1983       | NUM   | 名詞-数詞                | nummod |
+# | 年         | 年         | NOUN  | 名詞-普通名詞-助数詞可能 | obl    |
+# | に         | に         | ADP   | 助詞-格助詞              | case   |
+# | ファミコン | ファミコン | NOUN  | 名詞-普通名詞-一般       | obj    |
+# | を         | を         | ADP   | 助詞-格助詞              | case   |
+# | 14,800     | 14,800     | NUM   | 名詞-数詞                | fixed  |
+# | 円         | 円         | NOUN  | 名詞-普通名詞-助数詞可能 | obl    |
+# | で         | で         | ADP   | 助詞-格助詞              | case   |
+# | 発売       | 発売       | VERB  | 名詞-普通名詞-サ変可能   | ROOT   |
+# | し         | する       | AUX   | 動詞-非自立可能          | aux    |
+# | た         | た         | AUX   | 助動詞                   | aux    |
+# | 。         | 。         | PUNCT | 補助記号-句点            | punct  |
+# +------------+------------+-------+--------------------------+--------+

data/examples/japanese/visualizing_dependencies.rb

@@ -6,8 +6,8 @@ nlp = Spacy::Language.new("ja_core_news_sm")
 sentence = "自動運転車は保険責任を製造者に転嫁する。"
 doc = nlp.read(sentence)
 
-dep_svg = doc.displacy('dep', false)
+dep_svg = doc.displacy(style: 'dep', compact: false)
 
-File.open(File.join(File.dirname(__FILE__), "outputs/test_dep.svg"), "w") do |file|
+File.open(File.join(File.dirname(__FILE__), "test_dep.svg"), "w") do |file|
   file.write(dep_svg)
 end

data/examples/japanese/visualizing_named_entities.rb

@@ -7,7 +7,7 @@ sentence ="セバスチアン・スランが2007年にグーグルで自動運
 
 doc = nlp.read(sentence)
 
-ent_html = doc.displacy('ent')
+ent_html = doc.displacy(style: 'ent')
 
 File.open(File.join(File.dirname(__FILE__), "outputs/test_ent.html"), "w") do |file|
   file.write(ent_html)

data/examples/linguistic_features/ancestors.rb

@@ -24,18 +24,21 @@ 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)
-  rows << [descendant.text, descendant.dep_, descendant.n_lefts, descendant.n_rights, ancestors]
+  rows << [descendant.text, descendant.dep, descendant.n_lefts, descendant.n_rights, ancestors.map(&:text).join(", ")]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings
 print table
 
-# +----------+----------+---------+----------+------------------------------------+
-# | text     | dep      | n_lefts | n_rights | ancestors                          |
-# +----------+----------+---------+----------+------------------------------------+
-# | Credit   | nmod     | 0       | 2        | [holders, submit]                  |
-# | and      | cc       | 0       | 0        | [Credit, holders, submit]          |
-# | mortgage | compound | 0       | 0        | [account, Credit, holders, submit] |
-# | account  | conj     | 1       | 0        | [Credit, holders, submit]          |
-# | holders  | nsubj    | 1       | 0        | [submit]                           |
-# +----------+----------+---------+----------+------------------------------------+
+# The sentence: Credit and mortgage account holders must submit their requests
+# The root of the sentence is: submit
+# The subject of the sentence is: holders
+# +----------+----------+---------+----------+----------------------------------+
+# | text     | dep      | n_lefts | n_rights | ancestors                        |
+# +----------+----------+---------+----------+----------------------------------+
+# | Credit   | nmod     | 0       | 2        | holders, submit                  |
+# | and      | cc       | 0       | 0        | Credit, holders, submit          |
+# | mortgage | compound | 0       | 0        | account, Credit, holders, submit |
+# | account  | conj     | 1       | 0        | Credit, holders, submit          |
+# | holders  | nsubj    | 1       | 0        | submit                           |
+# +----------+----------+---------+----------+----------------------------------+

data/examples/linguistic_features/entity_annotations_and_labels.rb

@@ -10,7 +10,7 @@ headings = ["text", "ent_iob", "ent_iob_", "ent_type_"]
 rows = []
 
 doc.each do |ent|
-  rows << [ent.text, ent.ent_iob, ent.ent_iob_, ent.ent_type_]
+  rows << [ent.text, ent.ent_iob, ent.ent_iob_, ent.ent_type]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings

data/examples/linguistic_features/finding_a_verb_with_a_subject.rb

@@ -10,11 +10,11 @@ results = []
 
 doc.each do |token|
   if token.dep_ == "nsubj" && token.head.pos_ == "VERB"
-    results << token.head
+    results << token.head.text
   end
 end
 
 puts results.to_s
 
-# [shift]
+# ["shift"]
 

data/examples/linguistic_features/information_extraction.rb

@@ -19,11 +19,11 @@ texts.each do |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"}
+        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"
+      elsif token.dep_ == "pobj" and token.head.dep == "prep"
         puts token.head.head.text + " --> " + token.text
       end
     end

data/examples/linguistic_features/iterating_children.rb

@@ -12,7 +12,7 @@ doc.each do |token|
   if token.pos_ == "VERB"
     token.children.each do |child|
       if child.dep_ == "nsubj"
-        results << child.head
+        results << child.head.text
       end
     end
   end
@@ -20,5 +20,5 @@ end
 
 puts results.to_s
 
-# [shift]
+# ["shift"]
 

data/examples/linguistic_features/iterating_lefts_and_rights.rb

@@ -5,16 +5,16 @@ nlp = Spacy::Language.new("en_core_web_sm")
 
 doc = nlp.read("bright red apples on the tree")
 
-puts "Text: " + doc
+puts "Text: " + doc.text
 
-puts "Words to the left of 'apple': " + Spacy.generator_to_array(doc[2].lefts).to_s
-puts "Words to the right of 'apple': " + Spacy.generator_to_array(doc[2].rights).to_s
+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
 
 # Text: bright red apples on the tree
-# Words to the left of 'apple': [bright, red]
-# Words to the right of 'apple': [on]
+# Words to the left of 'apple': bright, red
+# Words to the right of 'apple': on
 # Num of the words to the left of 'apple': 2
 # Num of the words to the right of 'apple': 1

data/examples/linguistic_features/lemmatization.rb

@@ -12,7 +12,7 @@ headings = ["lemma"]
 rows = []
 
 doc.each do |token|
-  rows << [token.lemma_]
+  rows << [token.lemma]
 end
 
 table = Terminal::Table.new rows: rows, headings: headings