ruby-spacy 0.1.0 → 0.1.4.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +23 -0
- data/Gemfile.lock +3 -1
- data/README.md +123 -77
- data/examples/get_started/lexeme.rb +2 -2
- data/examples/get_started/linguistic_annotations.rb +1 -1
- data/examples/get_started/morphology.rb +45 -0
- data/examples/get_started/most_similar.rb +28 -27
- data/examples/get_started/named_entities.rb +1 -1
- data/examples/get_started/pos_tags_and_dependencies.rb +18 -18
- data/examples/get_started/similarity.rb +2 -2
- data/examples/japanese/ancestors.rb +9 -11
- data/examples/japanese/entity_annotations_and_labels.rb +1 -1
- data/examples/japanese/lemmatization.rb +1 -1
- data/examples/japanese/most_similar.rb +28 -27
- data/examples/japanese/named_entity_recognition.rb +1 -1
- data/examples/japanese/navigating_parse_tree.rb +18 -18
- data/examples/japanese/noun_chunks.rb +1 -1
- data/examples/japanese/pos_tagging.rb +20 -20
- data/examples/japanese/visualizing_dependencies.rb +2 -2
- data/examples/japanese/visualizing_named_entities.rb +1 -1
- data/examples/linguistic_features/ancestors.rb +13 -10
- data/examples/linguistic_features/entity_annotations_and_labels.rb +1 -1
- data/examples/linguistic_features/finding_a_verb_with_a_subject.rb +2 -2
- data/examples/linguistic_features/information_extraction.rb +2 -2
- data/examples/linguistic_features/iterating_children.rb +2 -2
- data/examples/linguistic_features/iterating_lefts_and_rights.rb +5 -5
- data/examples/linguistic_features/lemmatization.rb +1 -1
- data/examples/linguistic_features/named_entity_recognition.rb +1 -1
- data/examples/linguistic_features/navigating_parse_tree.rb +12 -12
- data/examples/linguistic_features/noun_chunks.rb +1 -1
- data/examples/linguistic_features/pos_tagging.rb +1 -1
- data/examples/linguistic_features/retokenize_1.rb +1 -1
- data/examples/linguistic_features/retokenize_2.rb +2 -2
- data/examples/linguistic_features/rule_based_morphology.rb +1 -1
- data/examples/linguistic_features/similarity.rb +2 -2
- data/examples/linguistic_features/similarity_between_lexemes.rb +18 -0
- data/examples/linguistic_features/similarity_between_spans.rb +2 -2
- data/examples/rule_based_matching/creating_spans_from_matches.rb +1 -1
- data/lib/ruby-spacy.rb +493 -300
- data/lib/ruby-spacy/version.rb +1 -1
- data/ruby-spacy.gemspec +1 -1
- metadata +6 -5
- data/examples/linguistic_features/morphology.rb +0 -17
- data/examples/linguistic_features/special_case_tokenization_rules.rb +0 -19
data/lib/ruby-spacy/version.rb
CHANGED
data/ruby-spacy.gemspec
CHANGED
@@ -10,7 +10,7 @@ Gem::Specification.new do |spec|
|
|
10
10
|
|
11
11
|
spec.summary = "A wrapper module for using spaCy natural language processing library from the Ruby programming language using PyCall"
|
12
12
|
spec.description =<<EOD
|
13
|
-
ruby-spacy
|
13
|
+
ruby-spacy is a wrapper module for using spaCy from the Ruby programming language via PyCall. This module aims to make it easy and natural for Ruby programmers to use spaCy. This module covers the areas of spaCy functionality for using many varieties of its language models, not for building ones.
|
14
14
|
EOD
|
15
15
|
|
16
16
|
spec.homepage = "https://github.com/yohasebe/ruby-spacy"
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ruby-spacy
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.4.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Yoichiro Hasebe
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2021-06
|
11
|
+
date: 2021-07-06 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: pycall
|
@@ -52,7 +52,7 @@ dependencies:
|
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: 3.0.1
|
55
|
-
description: 'ruby-spacy
|
55
|
+
description: 'ruby-spacy is a wrapper module for using spaCy from the Ruby programming
|
56
56
|
language via PyCall. This module aims to make it easy and natural for Ruby programmers
|
57
57
|
to use spaCy. This module covers the areas of spaCy functionality for using many
|
58
58
|
varieties of its language models, not for building ones.
|
@@ -66,6 +66,7 @@ extra_rdoc_files: []
|
|
66
66
|
files:
|
67
67
|
- ".gitignore"
|
68
68
|
- ".yardopts"
|
69
|
+
- CHANGELOG.md
|
69
70
|
- Gemfile
|
70
71
|
- Gemfile.lock
|
71
72
|
- LICENSE.txt
|
@@ -75,6 +76,7 @@ files:
|
|
75
76
|
- bin/setup
|
76
77
|
- examples/get_started/lexeme.rb
|
77
78
|
- examples/get_started/linguistic_annotations.rb
|
79
|
+
- examples/get_started/morphology.rb
|
78
80
|
- examples/get_started/most_similar.rb
|
79
81
|
- examples/get_started/named_entities.rb
|
80
82
|
- examples/get_started/outputs/test_dep.svg
|
@@ -111,7 +113,6 @@ files:
|
|
111
113
|
- examples/linguistic_features/iterating_children.rb
|
112
114
|
- examples/linguistic_features/iterating_lefts_and_rights.rb
|
113
115
|
- examples/linguistic_features/lemmatization.rb
|
114
|
-
- examples/linguistic_features/morphology.rb
|
115
116
|
- examples/linguistic_features/named_entity_recognition.rb
|
116
117
|
- examples/linguistic_features/navigating_parse_tree.rb
|
117
118
|
- examples/linguistic_features/noun_chunks.rb
|
@@ -122,8 +123,8 @@ files:
|
|
122
123
|
- examples/linguistic_features/rule_based_morphology.rb
|
123
124
|
- examples/linguistic_features/sentence_segmentation.rb
|
124
125
|
- examples/linguistic_features/similarity.rb
|
126
|
+
- examples/linguistic_features/similarity_between_lexemes.rb
|
125
127
|
- examples/linguistic_features/similarity_between_spans.rb
|
126
|
-
- examples/linguistic_features/special_case_tokenization_rules.rb
|
127
128
|
- examples/linguistic_features/tokenization.rb
|
128
129
|
- examples/rule_based_matching/creating_spans_from_matches.rb
|
129
130
|
- examples/rule_based_matching/matcher.rb
|
@@ -1,17 +0,0 @@
|
|
1
|
-
require "ruby-spacy"
|
2
|
-
require "terminal-table"
|
3
|
-
|
4
|
-
nlp = Spacy::Language.new("en_core_web_sm")
|
5
|
-
|
6
|
-
puts "Pipeline: " + nlp.pipe_names.to_s
|
7
|
-
|
8
|
-
doc = nlp.read("I was reading the paper.")
|
9
|
-
|
10
|
-
token = doc[0]
|
11
|
-
|
12
|
-
puts "Morph features of the first word: " + token.morph.to_s
|
13
|
-
puts "PronType of the word: " + token.morph.get("PronType").to_s
|
14
|
-
|
15
|
-
# Pipeline: ["tok2vec", "tagger", "parser", "ner", "attribute_ruler", "lemmatizer"]
|
16
|
-
# Morph features of the first word: Case=Nom|Number=Sing|Person=1|PronType=Prs
|
17
|
-
# PronType of the word: ['Prs']
|
@@ -1,19 +0,0 @@
|
|
1
|
-
require "ruby-spacy"
|
2
|
-
require "terminal-table"
|
3
|
-
|
4
|
-
nlp = Spacy::Language.new("en_core_web_sm")
|
5
|
-
|
6
|
-
doc = nlp.read("gimme that")
|
7
|
-
|
8
|
-
puts doc.tokens.join(" ")
|
9
|
-
|
10
|
-
# Add special case rule
|
11
|
-
special_case = [{ORTH: "gim"}, {ORTH: "me"}]
|
12
|
-
tokenizer = nlp.tokenizer
|
13
|
-
tokenizer.add_special_case("gimme", special_case)
|
14
|
-
|
15
|
-
# Check new tokenization
|
16
|
-
puts nlp.read("gimme that").tokens.join(" ")
|
17
|
-
|
18
|
-
# gimme that
|
19
|
-
# gim me that
|