svmredlight 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/Gemfile +14 -0
- data/Gemfile.lock +35 -0
- data/LICENSE.txt +20 -0
- data/README.rdoc +44 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/examples/example1/example.rb +76 -0
- data/examples/example1/test.dat +601 -0
- data/examples/example1/train.dat +2001 -0
- data/examples/example1/words +9947 -0
- data/ext/extconf.rb +6 -0
- data/ext/svmredlight.c +762 -0
- data/lib/svmredlight/document.rb +23 -0
- data/lib/svmredlight/model.rb +22 -0
- data/lib/svmredlight.rb +4 -0
- data/svmredlight.gemspec +73 -0
- data/test/assets/model +3888 -0
- data/test/helper.rb +19 -0
- data/test/test_document.rb +55 -0
- data/test/test_model.rb +114 -0
- metadata +134 -0
@@ -0,0 +1,23 @@
|
|
1
|
+
module SVMLight
|
2
|
+
# A document is the Ruby representation of a DOC structure in SVMlight, it contains a
|
3
|
+
# queryid, a slackid, a costfactor ( c ) and a vector with feature numbers and their
|
4
|
+
# correspondent weights.
|
5
|
+
class Document
|
6
|
+
|
7
|
+
# @param [Hash] vector a hash where the keys are feature numbers and the values its weights
|
8
|
+
# @param [Hash] opts the options coincide with SVMLight parameters to the create_example function, the default values for all the options are 0
|
9
|
+
# @option [:docnum] Numeric docum
|
10
|
+
# @option [:costfactor] Numeric costfactor
|
11
|
+
# @option [:slackid] Numeric slackid
|
12
|
+
# @option [:queryid] Numeric queryid
|
13
|
+
def self.new(vector, opts={})
|
14
|
+
opts.default = 0
|
15
|
+
docnum = opts[:docnum]
|
16
|
+
costfactor = opts[:costfactor]
|
17
|
+
slackid = opts[:slackid]
|
18
|
+
queryid = opts[:queryid]
|
19
|
+
|
20
|
+
create(docnum, costfactor, slackid, queryid, vector.to_a)
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module SVMLight
|
2
|
+
# A model is the product of training a SVM, once created it can take documents as inputs
|
3
|
+
# and act of them (by for instance classifying them). Models can also be read from files
|
4
|
+
# created by svm_learn.
|
5
|
+
class Model
|
6
|
+
TYPES = [:classification]
|
7
|
+
|
8
|
+
# Learns a model from a set of labeled documents.
|
9
|
+
# @param [Symbol] type, what kind of model is this, classification, regression, etc. for now the only valid value is classification.
|
10
|
+
# @param [Array] documents_and_lables documents and labels is an array of arrays where each inner array must have two elements, the first, a Document and the second a classification (normally +1 and -1)
|
11
|
+
# @param [Hash] learn_params each key of learn_params is a string it that maps to a field of the LEARN_PARM struct in SVMLight
|
12
|
+
# @param [Hash] kernel_params each key of kernel_params is a string it that maps to a field of the KERNEL_PARM struct in SVMLight
|
13
|
+
# @param [Array|Nil] alphas an array of alpha values
|
14
|
+
def self.new(type, documents_and_lables, learn_params, kernel_params, alphas = nil )
|
15
|
+
raise ArgumentError, "Supporte types are (for now) #{TYPES}" unless TYPES.include? type
|
16
|
+
|
17
|
+
learn_classification(documents_and_lables, learn_params, kernel_params, false, alphas)
|
18
|
+
end
|
19
|
+
|
20
|
+
private_class_method :learn_classification
|
21
|
+
end
|
22
|
+
end
|
data/lib/svmredlight.rb
ADDED
data/svmredlight.gemspec
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{svmredlight}
|
8
|
+
s.version = "0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Camilo Lopez"]
|
12
|
+
s.date = %q{2011-09-11}
|
13
|
+
s.description = %q{Ruby interface to SVMLight}
|
14
|
+
s.email = %q{camilo@camilolopez.com}
|
15
|
+
s.extensions = ["ext/extconf.rb"]
|
16
|
+
s.extra_rdoc_files = [
|
17
|
+
"LICENSE.txt",
|
18
|
+
"README.rdoc"
|
19
|
+
]
|
20
|
+
s.files = [
|
21
|
+
".document",
|
22
|
+
"Gemfile",
|
23
|
+
"Gemfile.lock",
|
24
|
+
"LICENSE.txt",
|
25
|
+
"README.rdoc",
|
26
|
+
"Rakefile",
|
27
|
+
"VERSION",
|
28
|
+
"examples/example1/example.rb",
|
29
|
+
"examples/example1/test.dat",
|
30
|
+
"examples/example1/train.dat",
|
31
|
+
"examples/example1/words",
|
32
|
+
"ext/extconf.rb",
|
33
|
+
"ext/svmredlight.c",
|
34
|
+
"lib/svmredlight.rb",
|
35
|
+
"lib/svmredlight/document.rb",
|
36
|
+
"lib/svmredlight/model.rb",
|
37
|
+
"svmredlight.gemspec",
|
38
|
+
"test/assets/model",
|
39
|
+
"test/helper.rb",
|
40
|
+
"test/test_document.rb",
|
41
|
+
"test/test_model.rb"
|
42
|
+
]
|
43
|
+
s.homepage = %q{http://github.com/camilo/svmredlight}
|
44
|
+
s.licenses = ["MIT"]
|
45
|
+
s.require_paths = ["lib"]
|
46
|
+
s.rubygems_version = %q{1.5.0}
|
47
|
+
s.summary = %q{Ruby interface to SVMLight}
|
48
|
+
|
49
|
+
if s.respond_to? :specification_version then
|
50
|
+
s.specification_version = 3
|
51
|
+
|
52
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
53
|
+
s.add_development_dependency(%q<shoulda>, [">= 0"])
|
54
|
+
s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
|
55
|
+
s.add_development_dependency(%q<jeweler>, ["~> 1.6.0"])
|
56
|
+
s.add_development_dependency(%q<ZenTest>, [">= 0"])
|
57
|
+
s.add_development_dependency(%q<ruby-debug19>, [">= 0"])
|
58
|
+
else
|
59
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
60
|
+
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
61
|
+
s.add_dependency(%q<jeweler>, ["~> 1.6.0"])
|
62
|
+
s.add_dependency(%q<ZenTest>, [">= 0"])
|
63
|
+
s.add_dependency(%q<ruby-debug19>, [">= 0"])
|
64
|
+
end
|
65
|
+
else
|
66
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
67
|
+
s.add_dependency(%q<bundler>, ["~> 1.0.0"])
|
68
|
+
s.add_dependency(%q<jeweler>, ["~> 1.6.0"])
|
69
|
+
s.add_dependency(%q<ZenTest>, [">= 0"])
|
70
|
+
s.add_dependency(%q<ruby-debug19>, [">= 0"])
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|