ruby_fast_text 0.3.5
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 +7 -0
- data/.gitignore +9 -0
- data/.rake_tasks~ +7 -0
- data/.travis.yml +5 -0
- data/Gemfile +6 -0
- data/README.md +35 -0
- data/Rakefile +17 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/ruby_fast_text.rb +10 -0
- data/lib/ruby_fast_text/cbow.rb +13 -0
- data/lib/ruby_fast_text/classifier.rb +55 -0
- data/lib/ruby_fast_text/commands.rb +14 -0
- data/lib/ruby_fast_text/nn.rb +45 -0
- data/lib/ruby_fast_text/skipgram.rb +13 -0
- data/lib/ruby_fast_text/version.rb +3 -0
- data/lib/ruby_fast_text/word_vectors.rb +24 -0
- data/ruby_fast_text.gemspec +29 -0
- metadata +103 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: c8a62041da945594d545e6d0f45a3349dd9d6dd1
|
4
|
+
data.tar.gz: d75c61b72631f67669d347a42705a18983c02567
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 83244f07a1cec29a4c03f796682c96bd6a7124d232b8ec35d735afe0fd6da66168596a0fdf4efbe1e91f0d6e870406d86cb5d7e23cfe35dd67831d1126c04211
|
7
|
+
data.tar.gz: 0aaab9dd2d5edb8bec947fa06c4eda27442ea5b3684cd52b83b86114d438fda97defd044ff831dcdb8adc2105e6ef7e93adf7a8206fd3e9e6b0496f8f2a748b4
|
data/.gitignore
ADDED
data/.rake_tasks~
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# RubyFastText
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/ruby_fast_text`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'ruby_fast_text'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install ruby_fast_text
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
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).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/ruby_fast_text.
|
data/Rakefile
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
2
|
+
require "rake/testtask"
|
3
|
+
|
4
|
+
Rake::TestTask.new(:test) do |t|
|
5
|
+
t.libs << "test"
|
6
|
+
t.libs << "lib"
|
7
|
+
t.test_files = FileList["test/**/*_test.rb"]
|
8
|
+
end
|
9
|
+
|
10
|
+
task :default => :test
|
11
|
+
|
12
|
+
namespace :install do
|
13
|
+
task :fast_text do
|
14
|
+
`git clone https://github.com/facebookresearch/fastText.git`
|
15
|
+
`cd fastText && make`
|
16
|
+
end
|
17
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "ruby_fast_text"
|
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
@@ -0,0 +1,10 @@
|
|
1
|
+
module RubyFastText
|
2
|
+
# Your code goes here...
|
3
|
+
require "ruby_fast_text/version"
|
4
|
+
require "ruby_fast_text/commands"
|
5
|
+
require "ruby_fast_text/classifier"
|
6
|
+
require "ruby_fast_text/word_vectors"
|
7
|
+
require "ruby_fast_text/skipgram"
|
8
|
+
require "ruby_fast_text/cbow"
|
9
|
+
require "ruby_fast_text/nn"
|
10
|
+
end
|
@@ -0,0 +1,55 @@
|
|
1
|
+
module RubyFastText
|
2
|
+
class Classifier
|
3
|
+
attr_accessor :classifier
|
4
|
+
|
5
|
+
attr_reader :probability
|
6
|
+
alias probability? probability
|
7
|
+
|
8
|
+
extend RubyFastText::Commands
|
9
|
+
|
10
|
+
def initialize(params)
|
11
|
+
path = params[:path]
|
12
|
+
model = params[:model]
|
13
|
+
labels_number = params.fetch(:labels_number, 1)
|
14
|
+
@probability = params[:probability]
|
15
|
+
probability_param = probability ? 'predict-prob' : 'predict'
|
16
|
+
#p File.expand_path File.dirname(__FILE__)
|
17
|
+
#p $0
|
18
|
+
@classifier = Dir.chdir(path) do
|
19
|
+
IO.popen("fasttext #{probability_param} #{model} - #{labels_number}", 'r+')
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def predict(sentence)
|
24
|
+
classifier.puts(sentence)
|
25
|
+
format_result(classifier.gets)
|
26
|
+
end
|
27
|
+
|
28
|
+
def self.train(params)
|
29
|
+
path = params[:path]
|
30
|
+
Dir.chdir(path) do
|
31
|
+
system("fasttext supervised #{params_to_s(params)}")
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
def self.test(params)
|
36
|
+
path = params[:path]
|
37
|
+
model = params[:model]
|
38
|
+
test_data = params[:test_data]
|
39
|
+
k = params.fetch(:k, 1)
|
40
|
+
Dir.chdir(path) do
|
41
|
+
system("fasttext test #{model} #{test_data} #{k}")
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
|
46
|
+
private
|
47
|
+
def format_result(result)
|
48
|
+
if probability?
|
49
|
+
Hash[*result.strip.split.flatten]
|
50
|
+
else
|
51
|
+
result.strip.split
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
module RubyFastText
|
2
|
+
module Commands
|
3
|
+
def params_to_s(params)
|
4
|
+
commands = %i[input output verbose minCount minCountLabel
|
5
|
+
wordNgrams bucket minn mann maxn t label lr lrUpdateRate
|
6
|
+
dim ws epoch neg loss thread pretrainedVectors saveOutput
|
7
|
+
cutoff retrain qnorm qout dsub]
|
8
|
+
|
9
|
+
params.select { |k, _v| commands.include? k}
|
10
|
+
.map { |k,v| "-#{k.to_s} #{v}"}
|
11
|
+
.join(" ")
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,45 @@
|
|
1
|
+
module RubyFastText
|
2
|
+
class NN
|
3
|
+
attr_accessor :predictor
|
4
|
+
attr_reader :k
|
5
|
+
|
6
|
+
def initialize(params)
|
7
|
+
path = params[:path]
|
8
|
+
model = params[:model]
|
9
|
+
@k = params.fetch(:k, 10)
|
10
|
+
|
11
|
+
@predictor = Dir.chdir(path) do
|
12
|
+
IO.popen("fasttext nn #{model} #{k}", 'r+')
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
# TODO: Fix, only getting one line out of the result
|
17
|
+
def neighbours(word)
|
18
|
+
predictor.puts(word)
|
19
|
+
format_result(read_lines)
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
def read_lines
|
24
|
+
# Should be done with predictor.readlines
|
25
|
+
# but process gets blocked...
|
26
|
+
lines = ''
|
27
|
+
k.times {
|
28
|
+
lines << predictor.gets
|
29
|
+
}
|
30
|
+
lines
|
31
|
+
end
|
32
|
+
|
33
|
+
def format_result(result)
|
34
|
+
# Deletes CLI comment on first line
|
35
|
+
# Separates lines into array
|
36
|
+
# Transforms each line into hash entry
|
37
|
+
result.sub!('Query word? ', '')
|
38
|
+
.split("\n")
|
39
|
+
.each_with_object({}) do |item, res|
|
40
|
+
key, value = item.split
|
41
|
+
res[key] = value
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module RubyFastText
|
2
|
+
class WordVectors
|
3
|
+
attr_accessor :vectors
|
4
|
+
|
5
|
+
def initialize(params)
|
6
|
+
path = params[:path]
|
7
|
+
model = params[:model]
|
8
|
+
@vectors = Dir.chdir(path) do
|
9
|
+
IO.popen("fasttext print-word-vectors #{model}", 'r+')
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def get_vector(word)
|
14
|
+
vectors.puts(word)
|
15
|
+
format_result(vectors.gets)
|
16
|
+
end
|
17
|
+
|
18
|
+
private
|
19
|
+
def format_result(result)
|
20
|
+
result.split.drop(1)
|
21
|
+
end
|
22
|
+
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "ruby_fast_text/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ruby_fast_text"
|
8
|
+
spec.version = RubyFastText::VERSION
|
9
|
+
spec.authors = ["amval"]
|
10
|
+
spec.email = ["alberto.m.valdunciel@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Ruby wrapper for FastText using the CLI.}
|
13
|
+
spec.description = %q{Ruby wrapper for FastText using the CLI.}
|
14
|
+
|
15
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
16
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
17
|
+
|
18
|
+
|
19
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
20
|
+
f.match(%r{^(test|spec|features)/})
|
21
|
+
end
|
22
|
+
spec.bindir = "exe"
|
23
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
24
|
+
spec.require_paths = ["lib"]
|
25
|
+
|
26
|
+
spec.add_development_dependency "bundler", "~> 1.16"
|
27
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
28
|
+
spec.add_development_dependency "minitest", "~> 5.0"
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,103 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ruby_fast_text
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.5
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- amval
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-01-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.16'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.16'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: minitest
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '5.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '5.0'
|
55
|
+
description: Ruby wrapper for FastText using the CLI.
|
56
|
+
email:
|
57
|
+
- alberto.m.valdunciel@gmail.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- ".gitignore"
|
63
|
+
- ".rake_tasks~"
|
64
|
+
- ".travis.yml"
|
65
|
+
- ".vscode/tasks.json"
|
66
|
+
- Gemfile
|
67
|
+
- README.md
|
68
|
+
- Rakefile
|
69
|
+
- bin/console
|
70
|
+
- bin/setup
|
71
|
+
- lib/ruby_fast_text.rb
|
72
|
+
- lib/ruby_fast_text/cbow.rb
|
73
|
+
- lib/ruby_fast_text/classifier.rb
|
74
|
+
- lib/ruby_fast_text/commands.rb
|
75
|
+
- lib/ruby_fast_text/nn.rb
|
76
|
+
- lib/ruby_fast_text/skipgram.rb
|
77
|
+
- lib/ruby_fast_text/version.rb
|
78
|
+
- lib/ruby_fast_text/word_vectors.rb
|
79
|
+
- ruby_fast_text.gemspec
|
80
|
+
homepage:
|
81
|
+
licenses: []
|
82
|
+
metadata: {}
|
83
|
+
post_install_message:
|
84
|
+
rdoc_options: []
|
85
|
+
require_paths:
|
86
|
+
- lib
|
87
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - ">="
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '0'
|
92
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
requirements: []
|
98
|
+
rubyforge_project:
|
99
|
+
rubygems_version: 2.6.8
|
100
|
+
signing_key:
|
101
|
+
specification_version: 4
|
102
|
+
summary: Ruby wrapper for FastText using the CLI.
|
103
|
+
test_files: []
|