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
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: aa99d456a6830308c836e57111372208f78e36a2
|
4
|
+
data.tar.gz: f8c80d07a992c47ea428e3ca6cb25a692ea943c7
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1ba504e82579953533021939a55ed60ce5e6cefe94827cfd726ac727cfa0a03fcb8eb2a37cc9708bd3c44485740b092a45d0213176c49174b2a2e567316f1f98
|
7
|
+
data.tar.gz: 47ebb31b8993ce742aaa340d9faf2c72859d8f876e4df917c0ccc74e28950f399cf2128f1b99bcd88032336d70895225bb346e3891a519c320168ec6a0073677
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, and in the interest of
|
4
|
+
fostering an open and welcoming community, we pledge to respect all people who
|
5
|
+
contribute through reporting issues, posting feature requests, updating
|
6
|
+
documentation, submitting pull requests or patches, and other activities.
|
7
|
+
|
8
|
+
We are committed to making participation in this project a harassment-free
|
9
|
+
experience for everyone, regardless of level of experience, gender, gender
|
10
|
+
identity and expression, sexual orientation, disability, personal appearance,
|
11
|
+
body size, race, ethnicity, age, religion, or nationality.
|
12
|
+
|
13
|
+
Examples of unacceptable behavior by participants include:
|
14
|
+
|
15
|
+
* The use of sexualized language or imagery
|
16
|
+
* Personal attacks
|
17
|
+
* Trolling or insulting/derogatory comments
|
18
|
+
* Public or private harassment
|
19
|
+
* Publishing other's private information, such as physical or electronic
|
20
|
+
addresses, without explicit permission
|
21
|
+
* Other unethical or unprofessional conduct
|
22
|
+
|
23
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
24
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
25
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
26
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
27
|
+
threatening, offensive, or harmful.
|
28
|
+
|
29
|
+
By adopting this Code of Conduct, project maintainers commit themselves to
|
30
|
+
fairly and consistently applying these principles to every aspect of managing
|
31
|
+
this project. Project maintainers who do not follow or enforce the Code of
|
32
|
+
Conduct may be permanently removed from the project team.
|
33
|
+
|
34
|
+
This code of conduct applies both within project spaces and in public spaces
|
35
|
+
when an individual is representing the project or its community.
|
36
|
+
|
37
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
38
|
+
reported by contacting a project maintainer at cafedomancer@gmail.com. All
|
39
|
+
complaints will be reviewed and investigated and will result in a response that
|
40
|
+
is deemed necessary and appropriate to the circumstances. Maintainers are
|
41
|
+
obligated to maintain confidentiality with regard to the reporter of an
|
42
|
+
incident.
|
43
|
+
|
44
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
45
|
+
version 1.3.0, available at
|
46
|
+
[http://contributor-covenant.org/version/1/3/0/][version]
|
47
|
+
|
48
|
+
[homepage]: http://contributor-covenant.org
|
49
|
+
[version]: http://contributor-covenant.org/version/1/3/0/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 cafedomancer
|
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 +1,41 @@
|
|
1
|
+
# Word2Vec
|
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/word2vec`. 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 'word2vec'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install word2vec
|
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 spec` 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]/word2vec. 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.
|
36
|
+
|
37
|
+
|
38
|
+
## License
|
39
|
+
|
40
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
41
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "word2vec"
|
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
|
data/bin/setup
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
|
2
|
+
Apache License
|
3
|
+
Version 2.0, January 2004
|
4
|
+
http://www.apache.org/licenses/
|
5
|
+
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
7
|
+
|
8
|
+
1. Definitions.
|
9
|
+
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
12
|
+
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
14
|
+
the copyright owner that is granting the License.
|
15
|
+
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
17
|
+
other entities that control, are controlled by, or are under common
|
18
|
+
control with that entity. For the purposes of this definition,
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
20
|
+
direction or management of such entity, whether by contract or
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
23
|
+
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
25
|
+
exercising permissions granted by this License.
|
26
|
+
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
28
|
+
including but not limited to software source code, documentation
|
29
|
+
source, and configuration files.
|
30
|
+
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
32
|
+
transformation or translation of a Source form, including but
|
33
|
+
not limited to compiled object code, generated documentation,
|
34
|
+
and conversions to other media types.
|
35
|
+
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
37
|
+
Object form, made available under the License, as indicated by a
|
38
|
+
copyright notice that is included in or attached to the work
|
39
|
+
(an example is provided in the Appendix below).
|
40
|
+
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
47
|
+
the Work and Derivative Works thereof.
|
48
|
+
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
50
|
+
the original version of the Work and any modifications or additions
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
62
|
+
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
65
|
+
subsequently incorporated within the Work.
|
66
|
+
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
73
|
+
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
79
|
+
where such license applies only to those patent claims licensable
|
80
|
+
by such Contributor that are necessarily infringed by their
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
83
|
+
institute patent litigation against any entity (including a
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
86
|
+
or contributory patent infringement, then any patent licenses
|
87
|
+
granted to You under this License for that Work shall terminate
|
88
|
+
as of the date such litigation is filed.
|
89
|
+
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
92
|
+
modifications, and in Source or Object form, provided that You
|
93
|
+
meet the following conditions:
|
94
|
+
|
95
|
+
(a) You must give any other recipients of the Work or
|
96
|
+
Derivative Works a copy of this License; and
|
97
|
+
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
99
|
+
stating that You changed the files; and
|
100
|
+
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
103
|
+
attribution notices from the Source form of the Work,
|
104
|
+
excluding those notices that do not pertain to any part of
|
105
|
+
the Derivative Works; and
|
106
|
+
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
109
|
+
include a readable copy of the attribution notices contained
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
112
|
+
of the following places: within a NOTICE text file distributed
|
113
|
+
as part of the Derivative Works; within the Source form or
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
115
|
+
within a display generated by the Derivative Works, if and
|
116
|
+
wherever such third-party notices normally appear. The contents
|
117
|
+
of the NOTICE file are for informational purposes only and
|
118
|
+
do not modify the License. You may add Your own attribution
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
121
|
+
that such additional attribution notices cannot be construed
|
122
|
+
as modifying the License.
|
123
|
+
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
125
|
+
may provide additional or different license terms and conditions
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
129
|
+
the conditions stated in this License.
|
130
|
+
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
134
|
+
this License, without any additional terms or conditions.
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
136
|
+
the terms of any separate license agreement you may have executed
|
137
|
+
with Licensor regarding such Contributions.
|
138
|
+
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
141
|
+
except as required for reasonable and customary use in describing the
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
143
|
+
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
153
|
+
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
159
|
+
incidental, or consequential damages of any character arising as a
|
160
|
+
result of this License or out of the use or inability to use the
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
163
|
+
other commercial damages or losses), even if such Contributor
|
164
|
+
has been advised of the possibility of such damages.
|
165
|
+
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
169
|
+
or other liability obligations and/or rights consistent with this
|
170
|
+
License. However, in accepting such obligations, You may act only
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
175
|
+
of your accepting any such warranty or additional liability.
|
176
|
+
|
177
|
+
END OF TERMS AND CONDITIONS
|
178
|
+
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
180
|
+
|
181
|
+
To apply the Apache License to your work, attach the following
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
183
|
+
replaced with your own identifying information. (Don't include
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
185
|
+
comment syntax for the file format. We also recommend that a
|
186
|
+
file or class name and description of purpose be included on the
|
187
|
+
same "printed page" as the copyright notice for easier
|
188
|
+
identification within third-party archives.
|
189
|
+
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
191
|
+
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
193
|
+
you may not use this file except in compliance with the License.
|
194
|
+
You may obtain a copy of the License at
|
195
|
+
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
197
|
+
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
201
|
+
See the License for the specific language governing permissions and
|
202
|
+
limitations under the License.
|
@@ -0,0 +1,21 @@
|
|
1
|
+
Tools for computing distributed representtion of words
|
2
|
+
------------------------------------------------------
|
3
|
+
|
4
|
+
We provide an implementation of the Continuous Bag-of-Words (CBOW) and the Skip-gram model (SG), as well as several demo scripts.
|
5
|
+
|
6
|
+
Given a text corpus, the word2vec tool learns a vector for every word in the vocabulary using the Continuous
|
7
|
+
Bag-of-Words or the Skip-Gram neural network architectures. The user should to specify the following:
|
8
|
+
- desired vector dimensionality
|
9
|
+
- the size of the context window for either the Skip-Gram or the Continuous Bag-of-Words model
|
10
|
+
- training algorithm: hierarchical softmax and / or negative sampling
|
11
|
+
- threshold for downsampling the frequent words
|
12
|
+
- number of threads to use
|
13
|
+
- the format of the output word vector file (text or binary)
|
14
|
+
|
15
|
+
Usually, the other hyper-parameters such as the learning rate do not need to be tuned for different training sets.
|
16
|
+
|
17
|
+
The script demo-word.sh downloads a small (100MB) text corpus from the web, and trains a small word vector model. After the training
|
18
|
+
is finished, the user can interactively explore the similarity of the words.
|
19
|
+
|
20
|
+
More information about the scripts is provided at https://code.google.com/p/word2vec/
|
21
|
+
|
@@ -0,0 +1,143 @@
|
|
1
|
+
// Copyright 2013 Google Inc. All Rights Reserved.
|
2
|
+
//
|
3
|
+
// Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
// you may not use this file except in compliance with the License.
|
5
|
+
// You may obtain a copy of the License at
|
6
|
+
//
|
7
|
+
// http://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
//
|
9
|
+
// Unless required by applicable law or agreed to in writing, software
|
10
|
+
// distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
// See the License for the specific language governing permissions and
|
13
|
+
// limitations under the License.
|
14
|
+
|
15
|
+
#include <stdio.h>
|
16
|
+
#include <stdlib.h>
|
17
|
+
#include <string.h>
|
18
|
+
#include <math.h>
|
19
|
+
/* #include <malloc.h> */
|
20
|
+
#include <ctype.h>
|
21
|
+
|
22
|
+
const long long max_size = 2000; // max length of strings
|
23
|
+
const long long N = 1; // number of closest words
|
24
|
+
const long long max_w = 50; // max length of vocabulary entries
|
25
|
+
|
26
|
+
int main(int argc, char **argv)
|
27
|
+
{
|
28
|
+
FILE *f;
|
29
|
+
char st1[max_size], st2[max_size], st3[max_size], st4[max_size], bestw[N][max_size], file_name[max_size], ch;
|
30
|
+
float dist, len, bestd[N], vec[max_size];
|
31
|
+
long long words, size, a, b, c, d, b1, b2, b3, threshold = 0;
|
32
|
+
float *M;
|
33
|
+
char *vocab;
|
34
|
+
int TCN, CCN = 0, TACN = 0, CACN = 0, SECN = 0, SYCN = 0, SEAC = 0, SYAC = 0, QID = 0, TQ = 0, TQS = 0;
|
35
|
+
if (argc < 2) {
|
36
|
+
printf("Usage: ./compute-accuracy <FILE> <threshold>\nwhere FILE contains word projections, and threshold is used to reduce vocabulary of the model for fast approximate evaluation (0 = off, otherwise typical value is 30000)\n");
|
37
|
+
return 0;
|
38
|
+
}
|
39
|
+
strcpy(file_name, argv[1]);
|
40
|
+
if (argc > 2) threshold = atoi(argv[2]);
|
41
|
+
f = fopen(file_name, "rb");
|
42
|
+
if (f == NULL) {
|
43
|
+
printf("Input file not found\n");
|
44
|
+
return -1;
|
45
|
+
}
|
46
|
+
fscanf(f, "%lld", &words);
|
47
|
+
if (threshold) if (words > threshold) words = threshold;
|
48
|
+
fscanf(f, "%lld", &size);
|
49
|
+
vocab = (char *)malloc(words * max_w * sizeof(char));
|
50
|
+
M = (float *)malloc(words * size * sizeof(float));
|
51
|
+
if (M == NULL) {
|
52
|
+
printf("Cannot allocate memory: %lld MB\n", words * size * sizeof(float) / 1048576);
|
53
|
+
return -1;
|
54
|
+
}
|
55
|
+
for (b = 0; b < words; b++) {
|
56
|
+
a = 0;
|
57
|
+
while (1) {
|
58
|
+
vocab[b * max_w + a] = fgetc(f);
|
59
|
+
if (feof(f) || (vocab[b * max_w + a] == ' ')) break;
|
60
|
+
if ((a < max_w) && (vocab[b * max_w + a] != '\n')) a++;
|
61
|
+
}
|
62
|
+
vocab[b * max_w + a] = 0;
|
63
|
+
for (a = 0; a < max_w; a++) vocab[b * max_w + a] = toupper(vocab[b * max_w + a]);
|
64
|
+
for (a = 0; a < size; a++) fread(&M[a + b * size], sizeof(float), 1, f);
|
65
|
+
len = 0;
|
66
|
+
for (a = 0; a < size; a++) len += M[a + b * size] * M[a + b * size];
|
67
|
+
len = sqrt(len);
|
68
|
+
for (a = 0; a < size; a++) M[a + b * size] /= len;
|
69
|
+
}
|
70
|
+
fclose(f);
|
71
|
+
TCN = 0;
|
72
|
+
while (1) {
|
73
|
+
for (a = 0; a < N; a++) bestd[a] = 0;
|
74
|
+
for (a = 0; a < N; a++) bestw[a][0] = 0;
|
75
|
+
scanf("%s", st1);
|
76
|
+
for (a = 0; a < strlen(st1); a++) st1[a] = toupper(st1[a]);
|
77
|
+
if ((!strcmp(st1, ":")) || (!strcmp(st1, "EXIT")) || feof(stdin)) {
|
78
|
+
if (TCN == 0) TCN = 1;
|
79
|
+
if (QID != 0) {
|
80
|
+
printf("ACCURACY TOP1: %.2f %% (%d / %d)\n", CCN / (float)TCN * 100, CCN, TCN);
|
81
|
+
printf("Total accuracy: %.2f %% Semantic accuracy: %.2f %% Syntactic accuracy: %.2f %% \n", CACN / (float)TACN * 100, SEAC / (float)SECN * 100, SYAC / (float)SYCN * 100);
|
82
|
+
}
|
83
|
+
QID++;
|
84
|
+
scanf("%s", st1);
|
85
|
+
if (feof(stdin)) break;
|
86
|
+
printf("%s:\n", st1);
|
87
|
+
TCN = 0;
|
88
|
+
CCN = 0;
|
89
|
+
continue;
|
90
|
+
}
|
91
|
+
if (!strcmp(st1, "EXIT")) break;
|
92
|
+
scanf("%s", st2);
|
93
|
+
for (a = 0; a < strlen(st2); a++) st2[a] = toupper(st2[a]);
|
94
|
+
scanf("%s", st3);
|
95
|
+
for (a = 0; a<strlen(st3); a++) st3[a] = toupper(st3[a]);
|
96
|
+
scanf("%s", st4);
|
97
|
+
for (a = 0; a < strlen(st4); a++) st4[a] = toupper(st4[a]);
|
98
|
+
for (b = 0; b < words; b++) if (!strcmp(&vocab[b * max_w], st1)) break;
|
99
|
+
b1 = b;
|
100
|
+
for (b = 0; b < words; b++) if (!strcmp(&vocab[b * max_w], st2)) break;
|
101
|
+
b2 = b;
|
102
|
+
for (b = 0; b < words; b++) if (!strcmp(&vocab[b * max_w], st3)) break;
|
103
|
+
b3 = b;
|
104
|
+
for (a = 0; a < N; a++) bestd[a] = 0;
|
105
|
+
for (a = 0; a < N; a++) bestw[a][0] = 0;
|
106
|
+
TQ++;
|
107
|
+
if (b1 == words) continue;
|
108
|
+
if (b2 == words) continue;
|
109
|
+
if (b3 == words) continue;
|
110
|
+
for (b = 0; b < words; b++) if (!strcmp(&vocab[b * max_w], st4)) break;
|
111
|
+
if (b == words) continue;
|
112
|
+
for (a = 0; a < size; a++) vec[a] = (M[a + b2 * size] - M[a + b1 * size]) + M[a + b3 * size];
|
113
|
+
TQS++;
|
114
|
+
for (c = 0; c < words; c++) {
|
115
|
+
if (c == b1) continue;
|
116
|
+
if (c == b2) continue;
|
117
|
+
if (c == b3) continue;
|
118
|
+
dist = 0;
|
119
|
+
for (a = 0; a < size; a++) dist += vec[a] * M[a + c * size];
|
120
|
+
for (a = 0; a < N; a++) {
|
121
|
+
if (dist > bestd[a]) {
|
122
|
+
for (d = N - 1; d > a; d--) {
|
123
|
+
bestd[d] = bestd[d - 1];
|
124
|
+
strcpy(bestw[d], bestw[d - 1]);
|
125
|
+
}
|
126
|
+
bestd[a] = dist;
|
127
|
+
strcpy(bestw[a], &vocab[c * max_w]);
|
128
|
+
break;
|
129
|
+
}
|
130
|
+
}
|
131
|
+
}
|
132
|
+
if (!strcmp(st4, bestw[0])) {
|
133
|
+
CCN++;
|
134
|
+
CACN++;
|
135
|
+
if (QID <= 5) SEAC++; else SYAC++;
|
136
|
+
}
|
137
|
+
if (QID <= 5) SECN++; else SYCN++;
|
138
|
+
TCN++;
|
139
|
+
TACN++;
|
140
|
+
}
|
141
|
+
printf("Questions seen / total: %d %d %.2f %% \n", TQS, TQ, TQS/(float)TQ*100);
|
142
|
+
return 0;
|
143
|
+
}
|