chakin-rb 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +11 -0
- data/.rspec +3 -0
- data/.travis.yml +7 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +54 -0
- data/LICENSE.txt +21 -0
- data/README.md +74 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/chakin-rb.gemspec +43 -0
- data/lib/chakin-rb/chakin.rb +71 -0
- data/lib/chakin-rb/datasets.csv +24 -0
- data/lib/chakin-rb/version.rb +3 -0
- metadata +147 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 0c29f5d7e52fff4041261147ae8045b6e88521bbd166d1b311ffb719f291f446
|
4
|
+
data.tar.gz: 316b44e8d644ef6f83a5c938db10de66931c9872ed2aaf5b30f1ff975bae915c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 06bae0cd7aa9919134ccbacf995a1d99a191045241f5e512a84297d3f1ce1c1e0b64064f364432c56730c4f3d13997de4554c0f2e3ed8b802349060c459b75d1
|
7
|
+
data.tar.gz: c87eeba3da4685889f9370a425dcaec4f1ef81af73493315c19b286e48c8e3c8a5840a23b091bdbb52604fff29ecb0e1777bbcae5eee8852cb7713d8081e276e
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at joseph.dayo@gmail.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
chakin-rb (0.1.0)
|
5
|
+
daru
|
6
|
+
ruby-progressbar
|
7
|
+
|
8
|
+
GEM
|
9
|
+
remote: https://rubygems.org/
|
10
|
+
specs:
|
11
|
+
backports (3.12.0)
|
12
|
+
byebug (10.0.2)
|
13
|
+
coderay (1.1.2)
|
14
|
+
daru (0.2.1)
|
15
|
+
backports
|
16
|
+
packable (~> 1.3.9)
|
17
|
+
diff-lcs (1.3)
|
18
|
+
method_source (0.9.2)
|
19
|
+
packable (1.3.10)
|
20
|
+
backports
|
21
|
+
pry (0.12.2)
|
22
|
+
coderay (~> 1.1.0)
|
23
|
+
method_source (~> 0.9.0)
|
24
|
+
pry-byebug (3.6.0)
|
25
|
+
byebug (~> 10.0)
|
26
|
+
pry (~> 0.10)
|
27
|
+
rake (10.5.0)
|
28
|
+
rspec (3.8.0)
|
29
|
+
rspec-core (~> 3.8.0)
|
30
|
+
rspec-expectations (~> 3.8.0)
|
31
|
+
rspec-mocks (~> 3.8.0)
|
32
|
+
rspec-core (3.8.0)
|
33
|
+
rspec-support (~> 3.8.0)
|
34
|
+
rspec-expectations (3.8.2)
|
35
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
36
|
+
rspec-support (~> 3.8.0)
|
37
|
+
rspec-mocks (3.8.0)
|
38
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
39
|
+
rspec-support (~> 3.8.0)
|
40
|
+
rspec-support (3.8.0)
|
41
|
+
ruby-progressbar (1.10.0)
|
42
|
+
|
43
|
+
PLATFORMS
|
44
|
+
ruby
|
45
|
+
|
46
|
+
DEPENDENCIES
|
47
|
+
bundler (~> 1.17)
|
48
|
+
chakin-rb!
|
49
|
+
pry-byebug
|
50
|
+
rake (~> 10.0)
|
51
|
+
rspec (~> 3.0)
|
52
|
+
|
53
|
+
BUNDLED WITH
|
54
|
+
1.17.2
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2019 Joseph Emmanuel Dayo
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Chakin-rb
|
2
|
+
|
3
|
+
A port of the python chakin library that downloads pre-trained word vectors without much fuss.
|
4
|
+
|
5
|
+
This gem is a port of https://github.com/chakki-works/chakin
|
6
|
+
|
7
|
+
Which makes selecting and downloading pre trained word vectors super easy
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
Add this line to your application's Gemfile:
|
12
|
+
|
13
|
+
```ruby
|
14
|
+
gem 'chakin-rb'
|
15
|
+
```
|
16
|
+
|
17
|
+
And then execute:
|
18
|
+
|
19
|
+
$ bundle
|
20
|
+
|
21
|
+
Or install it yourself as:
|
22
|
+
|
23
|
+
$ gem install chakin-ruby
|
24
|
+
|
25
|
+
## Usage
|
26
|
+
|
27
|
+
Get a list of available datasets
|
28
|
+
|
29
|
+
```ruby
|
30
|
+
require "chakin-rb/chakin"
|
31
|
+
|
32
|
+
Chakin::Vectors.search('English')
|
33
|
+
=>
|
34
|
+
#<Daru::DataFrame(12x7)>
|
35
|
+
Name Dimension Corpus Vocabulary Method Language Author
|
36
|
+
2 fastText(e 300 Wikipedia 2.5M fastText English Facebook
|
37
|
+
11 GloVe.6B.5 50 Wikipedia+ 400K GloVe English Stanford
|
38
|
+
12 GloVe.6B.1 100 Wikipedia+ 400K GloVe English Stanford
|
39
|
+
13 GloVe.6B.2 200 Wikipedia+ 400K GloVe English Stanford
|
40
|
+
14 GloVe.6B.3 300 Wikipedia+ 400K GloVe English Stanford
|
41
|
+
15 GloVe.42B. 300 Common Cra 1.9M GloVe English Stanford
|
42
|
+
16 GloVe.840B 300 Common Cra 2.2M GloVe English Stanford
|
43
|
+
17 GloVe.Twit 25 Twitter(27 1.2M GloVe English Stanford
|
44
|
+
18 GloVe.Twit 50 Twitter(27 1.2M GloVe English Stanford
|
45
|
+
19 GloVe.Twit 100 Twitter(27 1.2M GloVe English Stanford
|
46
|
+
20 GloVe.Twit 200 Twitter(27 1.2M GloVe English Stanford
|
47
|
+
21 word2vec.G 300 Google New 3.0M word2vec English Google
|
48
|
+
```
|
49
|
+
|
50
|
+
Download a dataset locally
|
51
|
+
|
52
|
+
```ruby
|
53
|
+
require "chakin-rb/chakin"
|
54
|
+
|
55
|
+
Chakin::Vectors.download(number: 2, save_dir: './') # select fastText(en)
|
56
|
+
```
|
57
|
+
|
58
|
+
## Development
|
59
|
+
|
60
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
61
|
+
|
62
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
63
|
+
|
64
|
+
## Contributing
|
65
|
+
|
66
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/chakin-ruby. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
67
|
+
|
68
|
+
## License
|
69
|
+
|
70
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
71
|
+
|
72
|
+
## Code of Conduct
|
73
|
+
|
74
|
+
Everyone interacting in the Chakin::Ruby project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/chakin-ruby/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "chakin/ruby"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/chakin-rb.gemspec
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "chakin-rb/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "chakin-rb"
|
8
|
+
spec.version = Chakin::VERSION
|
9
|
+
spec.authors = ["Joseph Emmanuel Dayo"]
|
10
|
+
spec.email = ["joseph.dayo@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{A port of the python chakin library that downloads pre-trained word vectors without much fuss}
|
13
|
+
spec.description = %q{A port of the python chakin library that downloads pre-trained word vectors without much fuss}
|
14
|
+
spec.homepage = "https://github.com/jedld/chakin-ruby"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
18
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
19
|
+
if spec.respond_to?(:metadata)
|
20
|
+
spec.metadata["allowed_push_host"] = "https://rubygems.org"
|
21
|
+
|
22
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
23
|
+
spec.metadata["source_code_uri"] = "https://github.com/jedld/chakin-ruby"
|
24
|
+
else
|
25
|
+
raise "RubyGems 2.0 or newer is required to protect against " \
|
26
|
+
"public gem pushes."
|
27
|
+
end
|
28
|
+
|
29
|
+
# Specify which files should be added to the gem when it is released.
|
30
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
31
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
32
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
33
|
+
end
|
34
|
+
spec.bindir = "exe"
|
35
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
36
|
+
spec.require_paths = ["lib"]
|
37
|
+
spec.add_dependency "daru"
|
38
|
+
spec.add_dependency "ruby-progressbar"
|
39
|
+
spec.add_development_dependency "bundler", "~> 1.17"
|
40
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
41
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
42
|
+
spec.add_development_dependency "pry-byebug"
|
43
|
+
end
|
@@ -0,0 +1,71 @@
|
|
1
|
+
require "chakin-rb/version"
|
2
|
+
require 'csv'
|
3
|
+
require 'daru'
|
4
|
+
require 'ruby-progressbar'
|
5
|
+
require 'net/http'
|
6
|
+
|
7
|
+
module Chakin
|
8
|
+
class Error < StandardError; end
|
9
|
+
module Downloader
|
10
|
+
def load_datasets(path = File.join(__dir__, 'datasets.csv'))
|
11
|
+
Daru::DataFrame.from_csv(path)
|
12
|
+
end
|
13
|
+
|
14
|
+
##
|
15
|
+
# Download pre-trained word vector
|
16
|
+
def download(number: nil, name: '', save_dir: './')
|
17
|
+
df = load_datasets
|
18
|
+
|
19
|
+
row = if !number.nil?
|
20
|
+
df.row[number]
|
21
|
+
elsif name
|
22
|
+
df.df.where(df['Name'].eq(name))
|
23
|
+
end
|
24
|
+
|
25
|
+
url = row['URL']
|
26
|
+
raise 'The word vector you specified was not found. Please specify correct name.' if url.nil?
|
27
|
+
|
28
|
+
progressbar = ProgressBar.create
|
29
|
+
file_name = url.split('/')[-1]
|
30
|
+
|
31
|
+
File.mkdir(save_dir) unless File.exist?(save_dir)
|
32
|
+
|
33
|
+
save_path = File.join(save_dir, file_name)
|
34
|
+
|
35
|
+
f = File.open(save_path, 'wb')
|
36
|
+
begin
|
37
|
+
my_uri = URI.parse(url)
|
38
|
+
|
39
|
+
Net::HTTP.start(my_uri.host) do |http|
|
40
|
+
http.request_get(my_uri.path) do |resp|
|
41
|
+
total_size = resp.content_length
|
42
|
+
progressbar.total = total_size
|
43
|
+
|
44
|
+
resp.read_body do |segment|
|
45
|
+
progressbar.progress += segment.size
|
46
|
+
f.write(segment)
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
50
|
+
ensure
|
51
|
+
f.close
|
52
|
+
end
|
53
|
+
|
54
|
+
save_path
|
55
|
+
end
|
56
|
+
|
57
|
+
def search(lang = '')
|
58
|
+
df = load_datasets
|
59
|
+
if lang == ''
|
60
|
+
puts df.inspect
|
61
|
+
else
|
62
|
+
rows = df.where(df['Language'].eq(lang))
|
63
|
+
puts rows['Name', 'Dimension', 'Corpus', 'VocabularySize', 'Method', 'Language', 'Author'].inspect
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
class Vectors
|
69
|
+
extend Downloader
|
70
|
+
end
|
71
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
Name,Dimension,Corpus,VocabularySize,Method,Language,Paper,Author,URL
|
2
|
+
fastText(ar),300,Wikipedia,610K,fastText,Arabic,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ar.300.vec.gz
|
3
|
+
fastText(de),300,Wikipedia,2.3M,fastText,German,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.de.300.vec.gz
|
4
|
+
fastText(en),300,Wikipedia,2.5M,fastText,English,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.vec.gz
|
5
|
+
fastText(es),300,Wikipedia,985K,fastText,Spanish,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.es.300.vec.gz
|
6
|
+
fastText(fr),300,Wikipedia,1.2M,fastText,French,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fr.300.vec.gz
|
7
|
+
fastText(it),300,Wikipedia,871K,fastText,Italian,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.it.300.vec.gz
|
8
|
+
fastText(ja),300,Wikipedia,580K,fastText,Japanese,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ja.300.vec.gz
|
9
|
+
fastText(ko),300,Wikipedia,880K,fastText,Korean,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ko.300.vec.gz
|
10
|
+
fastText(pt),300,Wikipedia,592K,fastText,Portuguese,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.pt.300.vec.gz
|
11
|
+
fastText(ru),300,Wikipedia,1.9M,fastText,Russian,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.ru.300.vec.gz
|
12
|
+
fastText(zh),300,Wikipedia,330K,fastText,Chinese,Enriching Word Vectors with Subword Information,Facebook,https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.zh.300.vec.gz
|
13
|
+
GloVe.6B.50d,50,Wikipedia+Gigaword 5 (6B),400K,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.6B.zip
|
14
|
+
GloVe.6B.100d,100,Wikipedia+Gigaword 5 (6B),400K,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.6B.zip
|
15
|
+
GloVe.6B.200d,200,Wikipedia+Gigaword 5 (6B),400K,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.6B.zip
|
16
|
+
GloVe.6B.300d,300,Wikipedia+Gigaword 5 (6B),400K,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.6B.zip
|
17
|
+
GloVe.42B.300d,300,Common Crawl(42B),1.9M,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.42B.300d.zip
|
18
|
+
GloVe.840B.300d,300,Common Crawl(840B),2.2M,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.840B.300d.zip
|
19
|
+
GloVe.Twitter.25d,25,Twitter(27B),1.2M,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.twitter.27B.zip
|
20
|
+
GloVe.Twitter.50d,50,Twitter(27B),1.2M,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.twitter.27B.zip
|
21
|
+
GloVe.Twitter.100d,100,Twitter(27B),1.2M,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.twitter.27B.zip
|
22
|
+
GloVe.Twitter.200d,200,Twitter(27B),1.2M,GloVe,English,GloVe: Global Vectors for Word Representation,Stanford,http://nlp.stanford.edu/data/glove.twitter.27B.zip
|
23
|
+
word2vec.GoogleNews,300,Google News(100B),3.0M,word2vec,English,Efficient Estimation of Word Representations in Vector Space,Google,https://s3.amazonaws.com/dl4j-distribution/GoogleNews-vectors-negative300.bin.gz
|
24
|
+
word2vec.Wiki-NEologd.50d,50,Wikipedia,335K,word2vec + NEologd,Japanese,Efficient Estimation of Word Representations in Vector Space,Shiroyagi Corporation,http://public.shiroyagi.s3.amazonaws.com/latest-ja-word2vec-gensim-model.zip
|
metadata
ADDED
@@ -0,0 +1,147 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: chakin-rb
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Joseph Emmanuel Dayo
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2019-04-03 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: daru
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: ruby-progressbar
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.17'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.17'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '10.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '10.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rspec
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '3.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: pry-byebug
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description: A port of the python chakin library that downloads pre-trained word vectors
|
98
|
+
without much fuss
|
99
|
+
email:
|
100
|
+
- joseph.dayo@gmail.com
|
101
|
+
executables: []
|
102
|
+
extensions: []
|
103
|
+
extra_rdoc_files: []
|
104
|
+
files:
|
105
|
+
- ".gitignore"
|
106
|
+
- ".rspec"
|
107
|
+
- ".travis.yml"
|
108
|
+
- CODE_OF_CONDUCT.md
|
109
|
+
- Gemfile
|
110
|
+
- Gemfile.lock
|
111
|
+
- LICENSE.txt
|
112
|
+
- README.md
|
113
|
+
- Rakefile
|
114
|
+
- bin/console
|
115
|
+
- bin/setup
|
116
|
+
- chakin-rb.gemspec
|
117
|
+
- lib/chakin-rb/chakin.rb
|
118
|
+
- lib/chakin-rb/datasets.csv
|
119
|
+
- lib/chakin-rb/version.rb
|
120
|
+
homepage: https://github.com/jedld/chakin-ruby
|
121
|
+
licenses:
|
122
|
+
- MIT
|
123
|
+
metadata:
|
124
|
+
allowed_push_host: https://rubygems.org
|
125
|
+
homepage_uri: https://github.com/jedld/chakin-ruby
|
126
|
+
source_code_uri: https://github.com/jedld/chakin-ruby
|
127
|
+
post_install_message:
|
128
|
+
rdoc_options: []
|
129
|
+
require_paths:
|
130
|
+
- lib
|
131
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ">="
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '0'
|
136
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
137
|
+
requirements:
|
138
|
+
- - ">="
|
139
|
+
- !ruby/object:Gem::Version
|
140
|
+
version: '0'
|
141
|
+
requirements: []
|
142
|
+
rubygems_version: 3.0.3
|
143
|
+
signing_key:
|
144
|
+
specification_version: 4
|
145
|
+
summary: A port of the python chakin library that downloads pre-trained word vectors
|
146
|
+
without much fuss
|
147
|
+
test_files: []
|