word2vec 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +49 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +41 -0
- data/Rakefile +12 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/ext/word2vec/LICENSE +202 -0
- data/ext/word2vec/README.txt +21 -0
- data/ext/word2vec/compute-accuracy.c +143 -0
- data/ext/word2vec/demo-analogy.sh +11 -0
- data/ext/word2vec/demo-classes.sh +8 -0
- data/ext/word2vec/demo-phrase-accuracy.sh +11 -0
- data/ext/word2vec/demo-phrases.sh +11 -0
- data/ext/word2vec/demo-train-big-model-v1.sh +100 -0
- data/ext/word2vec/demo-word-accuracy.sh +8 -0
- data/ext/word2vec/demo-word.sh +7 -0
- data/ext/word2vec/distance.c +143 -0
- data/ext/word2vec/extconf.rb +0 -0
- data/ext/word2vec/makefile +22 -0
- data/ext/word2vec/questions-phrases.txt +3223 -0
- data/ext/word2vec/questions-words.txt +19558 -0
- data/ext/word2vec/word-analogy.c +145 -0
- data/ext/word2vec/word2phrase.c +292 -0
- data/ext/word2vec/word2vec.c +702 -0
- data/lib/word2vec.rb +6 -0
- data/lib/word2vec/io.rb +27 -0
- data/lib/word2vec/scripts_interface.rb +97 -0
- data/lib/word2vec/utils.rb +9 -0
- data/lib/word2vec/version.rb +3 -0
- data/lib/word2vec/word_clusters.rb +36 -0
- data/lib/word2vec/word_vectors.rb +182 -0
- data/word2vec.gemspec +29 -0
- metadata +151 -0
data/lib/word2vec.rb
ADDED
data/lib/word2vec/io.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
module Word2Vec
|
2
|
+
def self.load(fname, *args, kind: 'auto', **kwargs)
|
3
|
+
if kind == 'auto'
|
4
|
+
if fname.end_with?('.bin')
|
5
|
+
kind = 'bin'
|
6
|
+
elsif fname.end_with?('.txt')
|
7
|
+
kind = 'txt'
|
8
|
+
else
|
9
|
+
raise 'Could not identify kind'
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
if kind == 'bin'
|
14
|
+
Word2Vec::WordVectors.from_binary(fname, *args, **kwargs)
|
15
|
+
elsif kind == 'txt'
|
16
|
+
Word2Vec::WordVectors.from_text(fname, *args, **kwargs)
|
17
|
+
elsif kind == 'mmap'
|
18
|
+
Word2Vec::WordVectors.from_mmap(fname, *args, **kwargs)
|
19
|
+
else
|
20
|
+
raise 'Unknown kind'
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.load_clusters(fname)
|
25
|
+
Word2Vec::WordClusters.from_text(fname)
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,97 @@
|
|
1
|
+
module Word2Vec
|
2
|
+
def self.word2vec(train, output, size: 100, window: 5, sample: '1e-3', hs: 0,
|
3
|
+
negative: 5, threads: 12, iter_: 5, min_count: 5, alpha: 0.025,
|
4
|
+
debug: 2, binary: 1, cbow: 1, save_vocab: nil, read_vocab: nil,
|
5
|
+
verbose: false)
|
6
|
+
ext = File.expand_path('../../../ext/word2vec', __FILE__)
|
7
|
+
command = [File.join(ext, 'word2vec')]
|
8
|
+
args = ['-train', '-output', '-size', '-window', '-sample', '-hs',
|
9
|
+
'-negative', '-threads', '-iter', '-min-count', '-alpha', '-debug',
|
10
|
+
'-binary', '-cbow']
|
11
|
+
values = [train, output, size, window, sample, hs, negative, threads,
|
12
|
+
iter_, min_count, alpha, debug, binary, cbow]
|
13
|
+
|
14
|
+
args.zip(values).each do |arg, value|
|
15
|
+
command << arg
|
16
|
+
command << value.to_s
|
17
|
+
end
|
18
|
+
if save_vocab != nil
|
19
|
+
command << '-save-vocab'
|
20
|
+
command << save_vocab.to_s
|
21
|
+
end
|
22
|
+
if read_vocab != nil
|
23
|
+
command << '-read-vocab'
|
24
|
+
command << read_vocab.to_s
|
25
|
+
end
|
26
|
+
|
27
|
+
run_cmd(command, verbose: verbose)
|
28
|
+
end
|
29
|
+
|
30
|
+
def self.word2clusters(train, output, classes, size: 100, window: 5, sample: '1e-3',
|
31
|
+
hs: 0, negative: 5, threads: 12, iter_: 5, min_count: 5,
|
32
|
+
alpha: 0.025, debug: 2, binary: 1, cbow: 1,
|
33
|
+
save_vocab: nil, read_vocab: nil, verbose: false)
|
34
|
+
ext = File.expand_path('../../../ext/word2vec', __FILE__)
|
35
|
+
command = [File.join(ext, 'word2vec')]
|
36
|
+
|
37
|
+
args = ['-train', '-output', '-size', '-window', '-sample', '-hs',
|
38
|
+
'-negative', '-threads', '-iter', '-min-count', '-alpha', '-debug',
|
39
|
+
'-binary', '-cbow', '-classes']
|
40
|
+
values = [train, output, size, window, sample, hs, negative, threads,
|
41
|
+
iter_, min_count, alpha, debug, binary, cbow, classes]
|
42
|
+
|
43
|
+
args.zip(values).each do |arg, value|
|
44
|
+
command << arg
|
45
|
+
command << value.to_s
|
46
|
+
end
|
47
|
+
|
48
|
+
if save_vocab != nil
|
49
|
+
command << '-save-vocab'
|
50
|
+
command << save_vocab.to_s
|
51
|
+
end
|
52
|
+
if read_vocab != nil
|
53
|
+
command << '-read-vocab'
|
54
|
+
command << read_vocab.to_s
|
55
|
+
end
|
56
|
+
|
57
|
+
run_cmd(command, verbose: verbose)
|
58
|
+
end
|
59
|
+
|
60
|
+
def self.word2phrase(train, output, min_count: 5, threshold: 100, debug: 2,
|
61
|
+
verbose: false)
|
62
|
+
ext = File.expand_path('../../../ext/word2vec', __FILE__)
|
63
|
+
command = [File.join(ext, 'word2phrase')]
|
64
|
+
|
65
|
+
args = ['-train', '-output', '-min-count', '-threshold', '-debug']
|
66
|
+
values = [train, output, min_count, threshold, debug]
|
67
|
+
args.zip(values).each do |arg, value|
|
68
|
+
command << arg
|
69
|
+
command << value.to_s
|
70
|
+
end
|
71
|
+
|
72
|
+
run_cmd(command, verbose: verbose)
|
73
|
+
end
|
74
|
+
|
75
|
+
def self.doc2vec(train, output, size: 100, window: 5, sample: '1e-3', hs: 0, negative: 5,
|
76
|
+
threads: 12, iter_: 5, min_count: 5, alpha: 0.025, debug: 2, binary: 1,
|
77
|
+
cbow: 1,
|
78
|
+
save_vocab: nil, read_vocab: nil, verbose: nil)
|
79
|
+
raise NotImplementedError
|
80
|
+
end
|
81
|
+
|
82
|
+
def self.run_cmd(command, verbose: false)
|
83
|
+
p command.join(' ')
|
84
|
+
system(command.join(' '))
|
85
|
+
|
86
|
+
# TODO: implement it later
|
87
|
+
# if verbose
|
88
|
+
# while line = stdout.readline
|
89
|
+
# $stdout.write(line)
|
90
|
+
# if line.include?('ERROR:')
|
91
|
+
# raise Exception(line)
|
92
|
+
# end
|
93
|
+
# $stdout.flush
|
94
|
+
# end
|
95
|
+
# end
|
96
|
+
end
|
97
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require "csv"
|
2
|
+
|
3
|
+
module Word2Vec
|
4
|
+
class WordClusters
|
5
|
+
attr_accessor :vocab, :clusters
|
6
|
+
|
7
|
+
def initialize(vocab:, clusters:)
|
8
|
+
self.vocab = vocab
|
9
|
+
self.clusters = clusters
|
10
|
+
end
|
11
|
+
|
12
|
+
def ix(word)
|
13
|
+
raise NotImplementedError
|
14
|
+
end
|
15
|
+
|
16
|
+
def [](word)
|
17
|
+
raise NotImplementedError
|
18
|
+
end
|
19
|
+
|
20
|
+
def get_cluster(word)
|
21
|
+
raise NotImplementedError
|
22
|
+
end
|
23
|
+
|
24
|
+
def get_words_on_cluster(cluster)
|
25
|
+
indices = clusters.each_with_index.map { |clst, i| i if clst == cluster }.compact
|
26
|
+
self.vocab.values_at(*indices)
|
27
|
+
end
|
28
|
+
|
29
|
+
def self.from_text(fname)
|
30
|
+
csv = CSV.read(fname, col_sep: " ")
|
31
|
+
vocab = csv.transpose[0]
|
32
|
+
clusters = csv.transpose[1].map(&:to_i)
|
33
|
+
self.new(vocab: vocab, clusters: clusters)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,182 @@
|
|
1
|
+
require "nmatrix"
|
2
|
+
|
3
|
+
require "word2vec/utils"
|
4
|
+
|
5
|
+
module Word2Vec
|
6
|
+
class WordVectors
|
7
|
+
attr_accessor :vocab, :vectors, :clusters, :vocab_hash
|
8
|
+
|
9
|
+
def initialize(vocab:, vectors:, clusters: nil)
|
10
|
+
@vocab = vocab
|
11
|
+
@vectors = vectors
|
12
|
+
@clusters = clusters
|
13
|
+
|
14
|
+
@vocab_hash = {}
|
15
|
+
vocab.each_with_index do |word, i|
|
16
|
+
@vocab_hash[word] = i
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def ix(word)
|
21
|
+
self.vocab_hash[word]
|
22
|
+
end
|
23
|
+
|
24
|
+
def word(ix)
|
25
|
+
self.vocab[ix]
|
26
|
+
end
|
27
|
+
|
28
|
+
def [](word)
|
29
|
+
self.get_vector(word)
|
30
|
+
end
|
31
|
+
|
32
|
+
def include?(word)
|
33
|
+
raise NotImplementedError
|
34
|
+
end
|
35
|
+
|
36
|
+
def get_vector(word)
|
37
|
+
idx = self.ix(word)
|
38
|
+
self.vectors[idx]
|
39
|
+
end
|
40
|
+
|
41
|
+
def cosine(word, n: 10)
|
42
|
+
metrics = NMatrix[*self.vectors, dtype: :float32].dot(NMatrix[self[word], dtype: :float32].transpose)
|
43
|
+
best = metrics.sorted_indices.reverse[1..n]
|
44
|
+
best_metrics = metrics.to_a.values_at(*best).flatten
|
45
|
+
[best, best_metrics]
|
46
|
+
end
|
47
|
+
|
48
|
+
def analogy(pos:, neg:, n: 10)
|
49
|
+
exclude = pos + neg
|
50
|
+
pos = pos.map { |word| [word, 1.0] }
|
51
|
+
neg = neg.map { |word| [word, -1.0] }
|
52
|
+
|
53
|
+
mean = []
|
54
|
+
(pos + neg).each do |word, direction|
|
55
|
+
mean << (NMatrix[*self[word], dtype: :float32] * direction).to_a
|
56
|
+
end
|
57
|
+
mean = NMatrix[*mean, dtype: :float32].mean
|
58
|
+
|
59
|
+
metrics = NMatrix[*self.vectors, dtype: :float32].dot(mean.transpose)
|
60
|
+
best = metrics.sorted_indices.reverse[0...(n + exclude.size)]
|
61
|
+
|
62
|
+
exclude_idx = []
|
63
|
+
exclude.each do |word|
|
64
|
+
if best.include?(self.ix(word))
|
65
|
+
exclude_idx << best.each_index.select { |i| best[i] == self.ix(word) }
|
66
|
+
end
|
67
|
+
end
|
68
|
+
exclude_idx.flatten.uniq.each do |index|
|
69
|
+
best.delete_at(index)
|
70
|
+
end
|
71
|
+
new_best = best
|
72
|
+
best_metrics = metrics.to_a.flatten.values_at(*new_best)
|
73
|
+
[new_best[0...n], best_metrics[0...n]]
|
74
|
+
end
|
75
|
+
|
76
|
+
def generate_response(indices, metrics, clusters: true)
|
77
|
+
if self.clusters && clusters
|
78
|
+
self.vocab.values_at(*indices)
|
79
|
+
.zip(metrics, self.clusters.clusters.values_at(*indices))
|
80
|
+
else
|
81
|
+
self.vocab.values_at(*indices).zip(metrics)
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
def to_mmap(fname)
|
86
|
+
raise NotImplementedError
|
87
|
+
end
|
88
|
+
|
89
|
+
def self.from_binary(fname, vocab_unicode_size: 78, desired_vocab: nil, encoding: "utf-8")
|
90
|
+
vocab = nil
|
91
|
+
vectors = nil
|
92
|
+
|
93
|
+
File.open(fname, 'rb') do |fin|
|
94
|
+
header = fin.readline
|
95
|
+
vocab_size, vector_size = header.split.map(&:to_i)
|
96
|
+
|
97
|
+
# TODO: replace numpy with nmatrix
|
98
|
+
# little-endian (<), Unicode (U), 78 characters == 2496 bytes (78)
|
99
|
+
# vocab = numpy.empty(vocab_size, dtype = '<U%s' % vocab_unicode_size)
|
100
|
+
# vectors = numpy.empty([vocab_size, vector_size], dtype = np.float)
|
101
|
+
# binary_len = numpy.dtype(np.float32).itemsize * vector_size
|
102
|
+
|
103
|
+
vocab = NMatrix.new([vocab_size], "", dtype: :object).to_a
|
104
|
+
vectors = NMatrix.random([vocab_size, vector_size], dtype: :float64).to_a
|
105
|
+
binary_len = 4 * vector_size # need to calculate from a data type
|
106
|
+
|
107
|
+
vocab_size.times do |i|
|
108
|
+
word = ''
|
109
|
+
while true
|
110
|
+
ch = fin.read(1)
|
111
|
+
if ch == ' '
|
112
|
+
break
|
113
|
+
end
|
114
|
+
word += ch
|
115
|
+
end
|
116
|
+
inklude = desired_vocab == nil || desired_vocab.include?(word)
|
117
|
+
if inklude
|
118
|
+
vocab[i] = word.force_encoding(encoding)
|
119
|
+
end
|
120
|
+
|
121
|
+
# read vector
|
122
|
+
vector = NMatrix[*fin.read(binary_len).unpack('f*'), dtype: :float32].to_a
|
123
|
+
if inklude
|
124
|
+
vectors[i] = unitvec(vector)
|
125
|
+
end
|
126
|
+
fin.read(1) # newline
|
127
|
+
end
|
128
|
+
|
129
|
+
if desired_vocab != nil
|
130
|
+
indices = vocab.each_with_index.map { |word, i| i if vocab != nil }.compact
|
131
|
+
vectors = vectors.values_at(*indices)
|
132
|
+
vocab = vocab.values_at(*indices)
|
133
|
+
end
|
134
|
+
end
|
135
|
+
|
136
|
+
self.new(vocab: vocab, vectors: vectors)
|
137
|
+
end
|
138
|
+
|
139
|
+
def self.from_text(fname, vocab_unicode_size: 78, desired_vocab: nil, encoding: "utf-8")
|
140
|
+
vocab = nil
|
141
|
+
vectors = nil
|
142
|
+
|
143
|
+
File.open(fname, 'rb') do |fin|
|
144
|
+
header = fin.readline
|
145
|
+
vocab_size, vector_size = header.split.map(&:to_i)
|
146
|
+
|
147
|
+
# TODO: replace numpy with nmatrix
|
148
|
+
# little-endian (<), Unicode (U), 78 characters == 2496 bytes (78)
|
149
|
+
# vocab = numpy.empty(vocab_size, dtype = '<U%s' % vocab_unicode_size)
|
150
|
+
# vectors = numpy.empty([vocab_size, vector_size], dtype = np.float)
|
151
|
+
# binary_len = numpy.dtype(np.float32).itemsize * vector_size
|
152
|
+
|
153
|
+
vocab = NMatrix.new([vocab_size], "", dtype: :object).to_a
|
154
|
+
vectors = NMatrix.random([vocab_size, vector_size], dtype: :float64).to_a
|
155
|
+
|
156
|
+
fin.each_line.with_index do |line, i|
|
157
|
+
line = line.force_encoding(encoding).strip
|
158
|
+
parts = line.split(" ")
|
159
|
+
word = parts[0]
|
160
|
+
inklude = desired_vocab == nil || desired_vocab.include?(word)
|
161
|
+
if inklude
|
162
|
+
vector = parts[1..-1].map(&:to_f)
|
163
|
+
vocab[i] = word
|
164
|
+
vectors[i] = unitvec(vector)
|
165
|
+
end
|
166
|
+
end
|
167
|
+
|
168
|
+
if desired_vocab != nil
|
169
|
+
indices = vocab.each_with_index.map { |word, i| i if vocab != nil }.compact
|
170
|
+
vectors = vectors.values_at(*indices)
|
171
|
+
vocab = vocab.values_at(*indices)
|
172
|
+
end
|
173
|
+
end
|
174
|
+
|
175
|
+
self.new(vocab: vocab, vectors: vectors)
|
176
|
+
end
|
177
|
+
|
178
|
+
def self.from_mmap(fname)
|
179
|
+
raise NotImplementedError
|
180
|
+
end
|
181
|
+
end
|
182
|
+
end
|
data/word2vec.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'word2vec/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "word2vec"
|
8
|
+
spec.version = Word2Vec::VERSION
|
9
|
+
spec.authors = ["cafedomancer"]
|
10
|
+
spec.email = ["cafedomancer@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{A simple wrapper for word2vec.}
|
13
|
+
spec.description = %q{A simple wrapper for word2vec.}
|
14
|
+
spec.homepage = "https://github.com/cafedomancer/word2vec"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
spec.extensions = ["ext/word2vec/extconf.rb"]
|
22
|
+
|
23
|
+
spec.add_runtime_dependency "nmatrix", "~> 0.2.3"
|
24
|
+
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.12"
|
26
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
27
|
+
spec.add_development_dependency "rake-compiler", "~> 1.0"
|
28
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,151 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: word2vec
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- cafedomancer
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-11-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nmatrix
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.2.3
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.2.3
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.12'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.12'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake-compiler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.0'
|
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
|
+
description: A simple wrapper for word2vec.
|
84
|
+
email:
|
85
|
+
- cafedomancer@gmail.com
|
86
|
+
executables: []
|
87
|
+
extensions:
|
88
|
+
- ext/word2vec/extconf.rb
|
89
|
+
extra_rdoc_files: []
|
90
|
+
files:
|
91
|
+
- ".gitignore"
|
92
|
+
- ".rspec"
|
93
|
+
- ".travis.yml"
|
94
|
+
- CODE_OF_CONDUCT.md
|
95
|
+
- Gemfile
|
96
|
+
- LICENSE.txt
|
97
|
+
- README.md
|
98
|
+
- Rakefile
|
99
|
+
- bin/console
|
100
|
+
- bin/setup
|
101
|
+
- ext/word2vec/LICENSE
|
102
|
+
- ext/word2vec/README.txt
|
103
|
+
- ext/word2vec/compute-accuracy.c
|
104
|
+
- ext/word2vec/demo-analogy.sh
|
105
|
+
- ext/word2vec/demo-classes.sh
|
106
|
+
- ext/word2vec/demo-phrase-accuracy.sh
|
107
|
+
- ext/word2vec/demo-phrases.sh
|
108
|
+
- ext/word2vec/demo-train-big-model-v1.sh
|
109
|
+
- ext/word2vec/demo-word-accuracy.sh
|
110
|
+
- ext/word2vec/demo-word.sh
|
111
|
+
- ext/word2vec/distance.c
|
112
|
+
- ext/word2vec/extconf.rb
|
113
|
+
- ext/word2vec/makefile
|
114
|
+
- ext/word2vec/questions-phrases.txt
|
115
|
+
- ext/word2vec/questions-words.txt
|
116
|
+
- ext/word2vec/word-analogy.c
|
117
|
+
- ext/word2vec/word2phrase.c
|
118
|
+
- ext/word2vec/word2vec.c
|
119
|
+
- lib/word2vec.rb
|
120
|
+
- lib/word2vec/io.rb
|
121
|
+
- lib/word2vec/scripts_interface.rb
|
122
|
+
- lib/word2vec/utils.rb
|
123
|
+
- lib/word2vec/version.rb
|
124
|
+
- lib/word2vec/word_clusters.rb
|
125
|
+
- lib/word2vec/word_vectors.rb
|
126
|
+
- word2vec.gemspec
|
127
|
+
homepage: https://github.com/cafedomancer/word2vec
|
128
|
+
licenses:
|
129
|
+
- MIT
|
130
|
+
metadata: {}
|
131
|
+
post_install_message:
|
132
|
+
rdoc_options: []
|
133
|
+
require_paths:
|
134
|
+
- lib
|
135
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
136
|
+
requirements:
|
137
|
+
- - ">="
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: '0'
|
140
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
141
|
+
requirements:
|
142
|
+
- - ">="
|
143
|
+
- !ruby/object:Gem::Version
|
144
|
+
version: '0'
|
145
|
+
requirements: []
|
146
|
+
rubyforge_project:
|
147
|
+
rubygems_version: 2.6.8
|
148
|
+
signing_key:
|
149
|
+
specification_version: 4
|
150
|
+
summary: A simple wrapper for word2vec.
|
151
|
+
test_files: []
|