natto2classifier 0.1.3 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.circleci/config.yml +24 -0
- data/Gemfile.lock +5 -1
- data/README.md +17 -5
- data/data/train.csv +1 -1
- data/lib/natto2classifier.rb +2 -17
- data/lib/natto2classifier/version.rb +1 -1
- data/natto2classifier.gemspec +1 -0
- metadata +17 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 51ad6e9876016e7a4202e0c5e97e2c1e67d208c4
|
4
|
+
data.tar.gz: 9684166a82e326f30b5b21a63658cd708540baad
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b2811c6898c36d2e5d37267023a2f6121e38fa953e3c3d7191225b8d704c0c1d83c651f20353a09530739c46a8d0239f1d638153ffc221cd21509f6785323e44
|
7
|
+
data.tar.gz: a9e57167f00b04feac3653cbe2a8362ac0cfc0946dad2e34912764173a03ca35c8db77404feb285cde009e8380a26033b8e501ab53b9a6e873d7cfc63be52e77
|
@@ -0,0 +1,24 @@
|
|
1
|
+
version: 2
|
2
|
+
jobs:
|
3
|
+
test:
|
4
|
+
docker:
|
5
|
+
- image: kanayannet/natto2classifier:latest
|
6
|
+
steps:
|
7
|
+
- checkout
|
8
|
+
- run: bundle install
|
9
|
+
- run: bundle exec ruby test/natto2classifier_test.rb
|
10
|
+
workflows:
|
11
|
+
version: 2
|
12
|
+
test:
|
13
|
+
jobs:
|
14
|
+
- test
|
15
|
+
scheduled-workflow:
|
16
|
+
triggers:
|
17
|
+
- schedule:
|
18
|
+
cron: "0 * * * *"
|
19
|
+
filters:
|
20
|
+
branches:
|
21
|
+
only:
|
22
|
+
- master
|
23
|
+
jobs:
|
24
|
+
- test
|
data/Gemfile.lock
CHANGED
@@ -1,9 +1,10 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
natto2classifier (0.
|
4
|
+
natto2classifier (0.2.0)
|
5
5
|
classifier-reborn
|
6
6
|
natto
|
7
|
+
rb-gsl
|
7
8
|
|
8
9
|
GEM
|
9
10
|
remote: https://rubygems.org/
|
@@ -13,6 +14,7 @@ GEM
|
|
13
14
|
coderay (1.1.2)
|
14
15
|
fast-stemmer (1.0.2)
|
15
16
|
ffi (1.9.23)
|
17
|
+
gsl (2.1.0.3)
|
16
18
|
method_source (0.9.0)
|
17
19
|
minitest (5.11.3)
|
18
20
|
natto (1.1.1)
|
@@ -21,6 +23,8 @@ GEM
|
|
21
23
|
coderay (~> 1.1.0)
|
22
24
|
method_source (~> 0.9.0)
|
23
25
|
rake (10.5.0)
|
26
|
+
rb-gsl (1.16.0.6)
|
27
|
+
gsl
|
24
28
|
|
25
29
|
PLATFORMS
|
26
30
|
ruby
|
data/README.md
CHANGED
@@ -12,7 +12,7 @@ gem 'natto2classifier'
|
|
12
12
|
|
13
13
|
And then execute:
|
14
14
|
|
15
|
-
$ bundle
|
15
|
+
$ bundle install
|
16
16
|
|
17
17
|
Or install it yourself as:
|
18
18
|
|
@@ -20,11 +20,23 @@ Or install it yourself as:
|
|
20
20
|
|
21
21
|
## Usage
|
22
22
|
|
23
|
+
### Baysian methods
|
24
|
+
|
25
|
+
```
|
26
|
+
bayes = Natto2classifier::Bayes.new '朝食', '夕食'
|
27
|
+
bayes.train '朝食', '今日の朝食は納豆だ'
|
28
|
+
bayes.train '夕食', '今日の夕食は湯豆腐だ'
|
29
|
+
bayes.classify '納豆はいつも朝食べている' #=> '朝食'
|
30
|
+
```
|
31
|
+
|
32
|
+
### LSI methods
|
33
|
+
|
23
34
|
```
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
35
|
+
lsi = Natto2classifier::LSI.new
|
36
|
+
lsi.add_item '今日の朝食は納豆だ', '朝食'
|
37
|
+
lsi.add_item '今日の夕食は湯豆腐だ', '夕食'
|
38
|
+
lsi.classify '納豆はいつも朝食べている' #=> '朝食'
|
39
|
+
lsi.find_related '納豆はいつも朝食べている' #=> ['今日 キョウ の ノ 朝食 チョウショク は ハ 納豆 ナットウ だ ダ', '今日 キョウ の ノ 夕食 ユウショク は ハ 湯豆腐 ユドウフ だ ダ']
|
28
40
|
```
|
29
41
|
|
30
42
|
## Development
|
data/data/train.csv
CHANGED
data/lib/natto2classifier.rb
CHANGED
@@ -1,20 +1,5 @@
|
|
1
1
|
require 'natto2classifier/version'
|
2
2
|
require 'natto2classifier/natto'
|
3
3
|
require 'classifier-reborn'
|
4
|
-
|
5
|
-
|
6
|
-
# It is a library that classifies Japanese language.
|
7
|
-
class Bayes < ClassifierReborn::Bayes
|
8
|
-
alias_method :__train__, :train
|
9
|
-
alias_method :__classify__, :classify
|
10
|
-
private :__train__, :__classify__
|
11
|
-
|
12
|
-
def train(category, word)
|
13
|
-
__train__ category, Natto2classifier::Natto.parse(word).join(' ')
|
14
|
-
end
|
15
|
-
|
16
|
-
def classify(word)
|
17
|
-
__classify__ Natto2classifier::Natto.parse(word).join(' ')
|
18
|
-
end
|
19
|
-
end
|
20
|
-
end
|
4
|
+
require 'natto2classifier/bayes'
|
5
|
+
require 'natto2classifier/lsi'
|
data/natto2classifier.gemspec
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: natto2classifier
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- kanayannet
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-04-
|
11
|
+
date: 2018-04-27 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -94,6 +94,20 @@ dependencies:
|
|
94
94
|
- - ">="
|
95
95
|
- !ruby/object:Gem::Version
|
96
96
|
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: rb-gsl
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
97
111
|
description: It is a library that classifies Japanese language. It depends on classifier-reborn
|
98
112
|
and natto.
|
99
113
|
email:
|
@@ -102,6 +116,7 @@ executables: []
|
|
102
116
|
extensions: []
|
103
117
|
extra_rdoc_files: []
|
104
118
|
files:
|
119
|
+
- ".circleci/config.yml"
|
105
120
|
- ".gitignore"
|
106
121
|
- ".travis.yml"
|
107
122
|
- CODE_OF_CONDUCT.md
|