rjspotter-basset 1.0.5
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +7 -0
- data/License.txt +20 -0
- data/Manifest.txt +21 -0
- data/README.rdoc +58 -0
- data/Rakefile +63 -0
- data/VERSION.yml +4 -0
- data/basset.gemspec +38 -0
- data/examples/example.rb +25 -0
- data/lib/basset.rb +9 -0
- data/lib/basset/classification_evaluator.rb +170 -0
- data/lib/basset/classifier.rb +188 -0
- data/lib/basset/core_extensions.rb +93 -0
- data/lib/basset/document.rb +84 -0
- data/lib/basset/document_override_example.rb +11 -0
- data/lib/basset/feature.rb +26 -0
- data/lib/basset/feature_extractor.rb +52 -0
- data/lib/basset/feature_selector.rb +126 -0
- data/lib/basset/naive_bayes.rb +151 -0
- data/lib/basset/svm.rb +180 -0
- data/lib/basset/yaml_serialization.rb +41 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +12 -0
- data/spec/unit/classifier_spec.rb +166 -0
- data/spec/unit/core_extension_spec.rb +33 -0
- data/spec/unit/document_spec.rb +59 -0
- data/spec/unit/feature_extractor_spec.rb +33 -0
- data/spec/unit/feature_selector_spec.rb +108 -0
- data/spec/unit/feature_spec.rb +40 -0
- data/spec/unit/naive_bayes_spec.rb +119 -0
- data/spec/unit/svm_spec.rb +83 -0
- metadata +115 -0
@@ -0,0 +1,33 @@
|
|
1
|
+
require File.join(File.dirname(__FILE__), "..", "spec_helper")
|
2
|
+
|
3
|
+
describe FeatureExtractor do
|
4
|
+
DocumentMock = Struct.new(:vector_of_features)
|
5
|
+
|
6
|
+
it "should save to file"
|
7
|
+
|
8
|
+
it "should be loadable from file"
|
9
|
+
|
10
|
+
it "should return number of features" do
|
11
|
+
FeatureExtractor.new(%w[one two]).number_of_features.should == 2
|
12
|
+
end
|
13
|
+
|
14
|
+
it "should throw away extra features" do
|
15
|
+
doc = DocumentMock.new([Feature.new("keep"), Feature.new("throwaway")])
|
16
|
+
FeatureExtractor.new(%w[keep]).extract(doc).should == [Feature.new("keep")]
|
17
|
+
end
|
18
|
+
|
19
|
+
it "should extract no features from a doc with no features" do
|
20
|
+
FeatureExtractor.new(%w[keep]).extract(DocumentMock.new([])).should == []
|
21
|
+
end
|
22
|
+
|
23
|
+
it "should extract numbered features" do
|
24
|
+
doc = DocumentMock.new([Feature.new("keep", 0)])
|
25
|
+
FeatureExtractor.new(%w[keep]).extract_numbered(doc).should == [Feature.new(1, 0)]
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should sort extracted numbered features" do
|
29
|
+
feature_extractor = FeatureExtractor.new(%w[keep1 keep2])
|
30
|
+
doc = DocumentMock.new([Feature.new("keep2", 10), Feature.new("keep1", 20)])
|
31
|
+
feature_extractor.extract_numbered(doc).should == [Feature.new(1, 20), Feature.new(2, 10)]
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,108 @@
|
|
1
|
+
require File.join(File.dirname(__FILE__), "..", "spec_helper")
|
2
|
+
|
3
|
+
describe FeatureSelector do
|
4
|
+
DocumentMock = Struct.new(:vector_of_features, :classification)
|
5
|
+
|
6
|
+
it "should count documents" do
|
7
|
+
feature_selector = FeatureSelector.new
|
8
|
+
feature_selector.docs.should == 0
|
9
|
+
feature_selector.add_document(DocumentMock.new([]))
|
10
|
+
feature_selector.docs.should == 1
|
11
|
+
end
|
12
|
+
|
13
|
+
it "should return all feature names" do
|
14
|
+
feature_selector = FeatureSelector.new
|
15
|
+
feature_selector.all_feature_names.should == []
|
16
|
+
feature_selector.add_document(DocumentMock.new([Feature.new("a")]))
|
17
|
+
feature_selector.add_document(DocumentMock.new([Feature.new("b")]))
|
18
|
+
feature_selector.all_feature_names.should == %w[a b]
|
19
|
+
end
|
20
|
+
|
21
|
+
# TODO
|
22
|
+
# it "should return_all_features_as_best
|
23
|
+
# feature_selector = FeatureSelector.new
|
24
|
+
# feature_selector.add_document(DocumentMock.new([Feature.new("a")], :test))
|
25
|
+
# assert_equal %w[a], feature_selector.best_features_for_classification(:test, 10)
|
26
|
+
# end
|
27
|
+
|
28
|
+
it "should count docs with feature and class" do
|
29
|
+
feature_selector = FeatureSelector.new
|
30
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
31
|
+
feature_selector.add_document(doc([Feature.new("puppy", 1)], :ham))
|
32
|
+
feature_selector.__send__(:docs_with_feature_and_class, "viagra", :spam).should == 1
|
33
|
+
feature_selector.__send__(:docs_with_feature_and_class, "viagra", :ham).should == 0
|
34
|
+
end
|
35
|
+
|
36
|
+
it "should count docs with feature and not class" do
|
37
|
+
feature_selector = FeatureSelector.new
|
38
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
39
|
+
feature_selector.add_document(doc([Feature.new("puppy", 1)], :ham))
|
40
|
+
feature_selector.__send__(:docs_with_feature_and_not_class, "puppy", :spam).should == 1
|
41
|
+
feature_selector.__send__(:docs_with_feature_and_not_class,"puppy", :ham).should == 0
|
42
|
+
end
|
43
|
+
|
44
|
+
it "should count docs with class and not feature" do
|
45
|
+
feature_selector = FeatureSelector.new
|
46
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
47
|
+
feature_selector.add_document(doc([Feature.new("puppy", 1)], :ham))
|
48
|
+
feature_selector.__send__(:docs_with_class_and_not_feature, :spam, "puppy").should == 1
|
49
|
+
feature_selector.__send__(:docs_with_class_and_not_feature, :spam, "viagra").should == 0
|
50
|
+
end
|
51
|
+
|
52
|
+
it "should count docs without feature or class" do
|
53
|
+
feature_selector = FeatureSelector.new
|
54
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
55
|
+
feature_selector.add_document(doc([Feature.new("puppy", 1)], :ham))
|
56
|
+
feature_selector.__send__(:docs_without_feature_or_class, "viagra", :spam).should == 1
|
57
|
+
feature_selector.__send__(:docs_without_feature_or_class, "viagra", :ham).should == 0
|
58
|
+
end
|
59
|
+
|
60
|
+
it "should return zero chi if all docs contain feature" do
|
61
|
+
feature_selector = FeatureSelector.new
|
62
|
+
the = Feature.new("the", 1)
|
63
|
+
feature_selector.add_document(doc([the], :spam))
|
64
|
+
feature_selector.add_document(doc([the], :ham))
|
65
|
+
feature_selector.features_with_chi(:spam).should == [Feature.new("the", 0.0)]
|
66
|
+
end
|
67
|
+
|
68
|
+
it "should compute chi squared" do
|
69
|
+
feature_selector = FeatureSelector.new
|
70
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
71
|
+
feature_selector.add_document(doc([Feature.new("puppy", 1)], :ham))
|
72
|
+
feature_selector.features_with_chi(:spam).should == [Feature.new("viagra", 2.0), Feature.new("puppy", 2.0)]
|
73
|
+
end
|
74
|
+
|
75
|
+
it "should not select any features if they are all insignificant" do
|
76
|
+
feature_selector = FeatureSelector.new
|
77
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
78
|
+
feature_selector.add_document(doc([Feature.new("puppy", 1)], :ham))
|
79
|
+
feature_selector.select_features.should == []
|
80
|
+
end
|
81
|
+
|
82
|
+
it "should not select features in only one doc" do
|
83
|
+
feature_selector = FeatureSelector.new
|
84
|
+
the = Feature.new("the", 1)
|
85
|
+
feature_selector.add_document(doc([the, Feature.new("viagra", 1)], :spam))
|
86
|
+
feature_selector.add_document(doc([the, Feature.new("puppy", 1)], :ham))
|
87
|
+
feature_selector.select_features.should == []
|
88
|
+
end
|
89
|
+
|
90
|
+
it "should select significant features occuring in more than one doc" do
|
91
|
+
feature_selector = FeatureSelector.new
|
92
|
+
the = Feature.new("the", 1)
|
93
|
+
feature_selector.add_document(doc([the, Feature.new("viagra", 1)], :spam))
|
94
|
+
feature_selector.add_document(doc([Feature.new("viagra", 1)], :spam))
|
95
|
+
feature_selector.add_document(doc([the, Feature.new("puppy", 1)], :ham))
|
96
|
+
feature_selector.select_features.should == %w[viagra]
|
97
|
+
end
|
98
|
+
|
99
|
+
it "should return selected features sorted by chi squared descending"
|
100
|
+
it "should select based on first feature by default"
|
101
|
+
it "should select with a chi squared of 1 by default"
|
102
|
+
|
103
|
+
private
|
104
|
+
|
105
|
+
def doc(*args)
|
106
|
+
DocumentMock.new(*args)
|
107
|
+
end
|
108
|
+
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
require File.join(File.dirname(__FILE__), "..", "spec_helper")
|
2
|
+
|
3
|
+
describe Feature do
|
4
|
+
it "should store name" do
|
5
|
+
Feature.new("hello").name.should == "hello"
|
6
|
+
end
|
7
|
+
|
8
|
+
it "should require name" do
|
9
|
+
lambda { Feature.new }.should raise_error(ArgumentError)
|
10
|
+
end
|
11
|
+
|
12
|
+
it "should store values" do
|
13
|
+
Feature.new("name", 2).value.should ==2
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should default value to zero" do
|
17
|
+
Feature.new("name").value.should == 0
|
18
|
+
end
|
19
|
+
|
20
|
+
it "should be equal with same name and no value" do
|
21
|
+
Feature.new("hello").should == Feature.new("hello")
|
22
|
+
end
|
23
|
+
|
24
|
+
it "should be equal with same name and same value" do
|
25
|
+
Feature.new("hello", 1).should == Feature.new("hello", 1)
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should not be equal with different name" do
|
29
|
+
Feature.new("hello").should_not == Feature.new("test")
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should not be equal with same name and different value" do
|
33
|
+
Feature.new("hello", 1).should_not == Feature.new("hello", 2)
|
34
|
+
end
|
35
|
+
|
36
|
+
it "should sort by name ascending then value ascending" do
|
37
|
+
[Feature.new("b", 3), Feature.new("a", 2), Feature.new("a", 1)].sort.should ==
|
38
|
+
[Feature.new("a", 1), Feature.new("a", 2), Feature.new("b", 3)]
|
39
|
+
end
|
40
|
+
end
|
@@ -0,0 +1,119 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../spec_helper'
|
2
|
+
|
3
|
+
describe NaiveBayes::FeatureCount do
|
4
|
+
|
5
|
+
it "should be equal to another feature count if the feature name and counts per class are equal" do
|
6
|
+
NaiveBayes::FeatureCount.new("rspec", :sweet, 1).should == NaiveBayes::FeatureCount.new("rspec", :sweet, 1)
|
7
|
+
end
|
8
|
+
|
9
|
+
it "should give the sum of all occurrences of a feature for a given class" do
|
10
|
+
fc = NaiveBayes::FeatureCount.new("rspec", :sweet, 1)
|
11
|
+
fc.add_count_for_class(2, :sweet)
|
12
|
+
fc.add_count_for_class(6, :super_sweet)
|
13
|
+
fc.count_for_class(:sweet).should == 3
|
14
|
+
fc.count_for_class(:super_sweet).should == 6
|
15
|
+
end
|
16
|
+
|
17
|
+
end
|
18
|
+
|
19
|
+
describe NaiveBayes do
|
20
|
+
|
21
|
+
before(:each) do
|
22
|
+
@nbayes = NaiveBayes.new
|
23
|
+
@doc = Document.new("here are some interesting words", :interesting)
|
24
|
+
@feature_vectors = @doc.feature_vectors
|
25
|
+
@other_vectors = Document.new("these words are interesting", :interesting).feature_vectors
|
26
|
+
@test_vectors = Document.new("this word seems interesting", :interesting).feature_vectors
|
27
|
+
end
|
28
|
+
|
29
|
+
def feature_counts_for(classification, *feature_count_tuples)
|
30
|
+
feature_counts = {}
|
31
|
+
feature_count_tuples.each do |tuple|
|
32
|
+
feature_counts[tuple.first] = NaiveBayes::FeatureCount.new(tuple.first, classification, tuple.last)
|
33
|
+
end
|
34
|
+
feature_counts
|
35
|
+
end
|
36
|
+
|
37
|
+
def add_interesting_docs
|
38
|
+
@nbayes.add_document(:interesting, @feature_vectors)
|
39
|
+
@nbayes.add_document(:interesting, @other_vectors)
|
40
|
+
end
|
41
|
+
|
42
|
+
def add_boring_docs
|
43
|
+
@nbayes.add_document(:boring, Document.new("yawn lets go flame").feature_vectors)
|
44
|
+
@nbayes.add_document(:boring, Document.new("yawn lets flame and troll").feature_vectors)
|
45
|
+
end
|
46
|
+
|
47
|
+
it "should keep track of the total docs and total docs for class when adding new docs" do
|
48
|
+
@nbayes.add_document(:interesting, @feature_vectors)
|
49
|
+
@nbayes.total_docs.should == 1
|
50
|
+
@nbayes.total_docs_in_class[:interesting].should == 1
|
51
|
+
end
|
52
|
+
|
53
|
+
it "should create a feature count for each feature with the # of occurances and class" do
|
54
|
+
@nbayes.add_document(:interesting, @feature_vectors)
|
55
|
+
expected = feature_counts_for(:interesting, ["here", 1], ["ar", 1],["some", 1],["interest", 1],["word", 1])
|
56
|
+
@nbayes.feature_counts.should == expected
|
57
|
+
end
|
58
|
+
|
59
|
+
it "should sum the number of all occurances of all features for a given class" do
|
60
|
+
@nbayes.add_document(:interesting, @feature_vectors)
|
61
|
+
@nbayes.occurrences_of_all_features_in_class(:interesting).should == 5
|
62
|
+
add_boring_docs
|
63
|
+
@nbayes.occurrences_of_all_features_in_class(:interesting).should == 5
|
64
|
+
end
|
65
|
+
|
66
|
+
it "should give a list of classes it knows about" do
|
67
|
+
@nbayes.add_document(:interesting, @feature_vectors)
|
68
|
+
@nbayes.add_document(:kinda_interesting, @feature_vectors)
|
69
|
+
@nbayes.classes.sort_to_s.should == [:kinda_interesting, :interesting].sort_to_s
|
70
|
+
end
|
71
|
+
|
72
|
+
it "should not divide by zero or nil when determining the probability of a feature vector for a class" do
|
73
|
+
@nbayes.occurrences_of_all_features_in_class(:interesting).should be_nil
|
74
|
+
probability_computation = lambda {@nbayes.probability_of_vector_for_class(@test_vectors.first, :interesting)}
|
75
|
+
probability_computation.should_not raise_error
|
76
|
+
end
|
77
|
+
|
78
|
+
it "should compute the probability that a given (singular) feature vector belongs to a given class" do
|
79
|
+
@nbayes.add_document(:interesting, @feature_vectors)
|
80
|
+
probablity = @nbayes.probability_of_vector_for_class(@test_vectors.first, :interesting)
|
81
|
+
probablity.should be_a Float
|
82
|
+
probablity.round.should == -1
|
83
|
+
end
|
84
|
+
|
85
|
+
it "should compute the probability that a given set of feature vectors belongs to a given class" do
|
86
|
+
add_interesting_docs
|
87
|
+
probability = @nbayes.probability_of_vectors_for_class(@test_vectors, :interesting)
|
88
|
+
probability.should be_a(Float)
|
89
|
+
probability.round.should == -5
|
90
|
+
end
|
91
|
+
|
92
|
+
it "should compute a probability of a class for a set of vectors normalized by the number of features" do
|
93
|
+
add_interesting_docs
|
94
|
+
probability = @nbayes.probability_of_vectors_for_class(@test_vectors, :interesting, :normalize => true)
|
95
|
+
probability.should be_a Float
|
96
|
+
probability.round.should == -1
|
97
|
+
end
|
98
|
+
|
99
|
+
it "should determine the most likely class of a set feature vectors" do
|
100
|
+
add_interesting_docs
|
101
|
+
add_boring_docs
|
102
|
+
test_vectors = Document.new("some interesting words").feature_vectors
|
103
|
+
classification = @nbayes.classify(test_vectors, :normalize_classes => false)
|
104
|
+
classification.last.should == :interesting
|
105
|
+
classification.first.should be_a Float
|
106
|
+
classification.first.round.should == -2
|
107
|
+
end
|
108
|
+
|
109
|
+
it "should account for the relative probabilities of classes by default when classifying" do
|
110
|
+
add_interesting_docs
|
111
|
+
add_boring_docs
|
112
|
+
vectors = Document.new("some interesting words").feature_vectors
|
113
|
+
classification = @nbayes.classify(vectors)
|
114
|
+
classification.last.should == :interesting
|
115
|
+
classification.first.should be_a Float
|
116
|
+
classification.first.round.should == -2
|
117
|
+
end
|
118
|
+
|
119
|
+
end
|
@@ -0,0 +1,83 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../spec_helper'
|
2
|
+
|
3
|
+
describe Svm do
|
4
|
+
|
5
|
+
before(:each) do
|
6
|
+
@svm = Svm.new
|
7
|
+
@doc = Document.new("here are some interesting words", :interesting)
|
8
|
+
@feature_vectors = @doc.feature_vectors
|
9
|
+
@negative_doc = Document.new("let's eat some spamiagra", :uninteresting)
|
10
|
+
@negative_fvs = @negative_doc.feature_vectors
|
11
|
+
end
|
12
|
+
|
13
|
+
def add_simple_docs_to_svm
|
14
|
+
@svm.add_document(:interesting, @feature_vectors)
|
15
|
+
@svm.add_document(:uninteresting, @negative_fvs)
|
16
|
+
end
|
17
|
+
|
18
|
+
it "should list document classes it knows about" do
|
19
|
+
add_simple_docs_to_svm
|
20
|
+
@svm.classes.sort_to_s.should == [:interesting, :uninteresting].sort_to_s
|
21
|
+
end
|
22
|
+
|
23
|
+
it "should express classes as SVM friendly unit integer labels"do
|
24
|
+
add_simple_docs_to_svm
|
25
|
+
spam_doc = Document.new("make your junk repulsive to women with free v14gra")
|
26
|
+
@svm.add_document(:uninteresting, spam_doc.feature_vectors)
|
27
|
+
@svm.class_labels.should == {:interesting => 0, :uninteresting => 1}
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should create a feature dictionary based on training docs" do
|
31
|
+
add_simple_docs_to_svm
|
32
|
+
expected = (@feature_vectors + @negative_fvs).map { |fv| fv.name }.uniq
|
33
|
+
@svm.feature_dictionary.should == expected
|
34
|
+
end
|
35
|
+
|
36
|
+
it "should express documents as SVM friendly vectors using the binary method" do
|
37
|
+
# for a brief but usable description of binary, frequency, tf-idf, and
|
38
|
+
# Hadamard vector representations of documents, see section 2.1 (2nd page) of:
|
39
|
+
# http://jmlr.csail.mit.edu/papers/volume2/manevitz01a/manevitz01a.pdf
|
40
|
+
add_simple_docs_to_svm
|
41
|
+
@svm.vectorized_docs(:interesting).first.should == [1,1,1,1,1,0,0,0]
|
42
|
+
@svm.vectorized_docs(:uninteresting).first.should == [0,0,0,0,1,1,1,1]
|
43
|
+
end
|
44
|
+
|
45
|
+
it "should set SVM parameters to reasonable defaults and allow access via a block" do
|
46
|
+
@svm.parameters do |params|
|
47
|
+
params.C.should == 100
|
48
|
+
params.svm_type.should == NU_SVC
|
49
|
+
params.degree.should == 1
|
50
|
+
params.coef0.should == 0
|
51
|
+
params.eps.should == 0.001
|
52
|
+
params.kernel_type.should == RBF
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
it "should construct the list of labels and document feature vectors" do
|
57
|
+
add_simple_docs_to_svm
|
58
|
+
result = @svm.labels_and_document_vectors
|
59
|
+
result[:labels].sort.should == [0,1]
|
60
|
+
result[:features].sort.should == [[0,0,0,0,1,1,1,1], [1,1,1,1,1,0,0,0]]
|
61
|
+
# can't count on consistent Hash#each ordering, hence this:
|
62
|
+
expected_result_with_hash_ordering_workaround = {1 => [0,0,0,0,1,1,1,1], 0 => [1,1,1,1,1,0,0,0]}
|
63
|
+
stabilized_actual_result = {result[:labels].first => result[:features].first,
|
64
|
+
result[:labels].last => result[:features].last}
|
65
|
+
stabilized_actual_result.should == expected_result_with_hash_ordering_workaround
|
66
|
+
end
|
67
|
+
|
68
|
+
it "should classify unlabeled documents" do
|
69
|
+
# examples from http://www.igvita.com/2008/01/07/support-vector-machines-svm-in-ruby/
|
70
|
+
non_spam_texts = ["Peter and Stewie are hilarious", "New episode rocks, Peter and Stewie are hilarious",
|
71
|
+
"Peter is my fav!"]
|
72
|
+
spam_texts = ["FREE NATIONAL TREASURE", "FREE TV for EVERY visitor", "AS SEEN ON NATIONAL TV",
|
73
|
+
"FREE drugs"]
|
74
|
+
non_spam_texts.each { |t| @svm.add_document(:nonspam, Document.new(t, :nonspam).feature_vectors) }
|
75
|
+
spam_texts.each { |t| @svm.add_document(:spam, Document.new(t, :spam).feature_vectors) }
|
76
|
+
test_non_spams = ["Stewie is hilarious", "Poor Peter is hilarious"]
|
77
|
+
test_spam = "FREE lotterry for the NATIONAL TREASURE !!!"
|
78
|
+
@svm.classify(Document.new(test_non_spams.first).feature_vectors).should == :nonspam
|
79
|
+
@svm.classify(Document.new(test_non_spams.last).feature_vectors).should == :nonspam
|
80
|
+
@svm.classify(Document.new(test_spam).feature_vectors).should == :spam
|
81
|
+
end
|
82
|
+
|
83
|
+
end
|
metadata
ADDED
@@ -0,0 +1,115 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rjspotter-basset
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.5
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Paul Dix
|
8
|
+
- Bryan Helmkamp
|
9
|
+
- Daniel DeLeo
|
10
|
+
- R. Potter
|
11
|
+
autorequire:
|
12
|
+
bindir: bin
|
13
|
+
cert_chain: []
|
14
|
+
|
15
|
+
date: 2009-05-09 00:00:00 -07:00
|
16
|
+
default_executable:
|
17
|
+
dependencies:
|
18
|
+
- !ruby/object:Gem::Dependency
|
19
|
+
name: stemmer
|
20
|
+
type: :runtime
|
21
|
+
version_requirement:
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 1.0.1
|
27
|
+
version:
|
28
|
+
- !ruby/object:Gem::Dependency
|
29
|
+
name: tomz-libsvm-ruby-swig
|
30
|
+
type: :runtime
|
31
|
+
version_requirement:
|
32
|
+
version_requirements: !ruby/object:Gem::Requirement
|
33
|
+
requirements:
|
34
|
+
- - ">="
|
35
|
+
- !ruby/object:Gem::Version
|
36
|
+
version: 0.3.3
|
37
|
+
version:
|
38
|
+
- !ruby/object:Gem::Dependency
|
39
|
+
name: igrigorik-bloomfilter
|
40
|
+
type: :runtime
|
41
|
+
version_requirement:
|
42
|
+
version_requirements: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - ">="
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 0.1.2
|
47
|
+
version:
|
48
|
+
description: A library for machine learning and classification
|
49
|
+
email: rjspotter@gmail.com
|
50
|
+
executables: []
|
51
|
+
|
52
|
+
extensions: []
|
53
|
+
|
54
|
+
extra_rdoc_files:
|
55
|
+
- README.rdoc
|
56
|
+
files:
|
57
|
+
- History.txt
|
58
|
+
- License.txt
|
59
|
+
- Manifest.txt
|
60
|
+
- README.rdoc
|
61
|
+
- Rakefile
|
62
|
+
- VERSION.yml
|
63
|
+
- basset.gemspec
|
64
|
+
- examples/example.rb
|
65
|
+
- lib/basset.rb
|
66
|
+
- lib/basset/classification_evaluator.rb
|
67
|
+
- lib/basset/classifier.rb
|
68
|
+
- lib/basset/core_extensions.rb
|
69
|
+
- lib/basset/document.rb
|
70
|
+
- lib/basset/document_override_example.rb
|
71
|
+
- lib/basset/feature.rb
|
72
|
+
- lib/basset/feature_extractor.rb
|
73
|
+
- lib/basset/feature_selector.rb
|
74
|
+
- lib/basset/naive_bayes.rb
|
75
|
+
- lib/basset/svm.rb
|
76
|
+
- lib/basset/yaml_serialization.rb
|
77
|
+
- spec/spec.opts
|
78
|
+
- spec/spec_helper.rb
|
79
|
+
- spec/unit/classifier_spec.rb
|
80
|
+
- spec/unit/core_extension_spec.rb
|
81
|
+
- spec/unit/document_spec.rb
|
82
|
+
- spec/unit/feature_extractor_spec.rb
|
83
|
+
- spec/unit/feature_selector_spec.rb
|
84
|
+
- spec/unit/feature_spec.rb
|
85
|
+
- spec/unit/naive_bayes_spec.rb
|
86
|
+
- spec/unit/svm_spec.rb
|
87
|
+
has_rdoc: false
|
88
|
+
homepage: http://github.com/danielsdeleo/basset
|
89
|
+
post_install_message:
|
90
|
+
rdoc_options:
|
91
|
+
- --inline-source
|
92
|
+
- --charset=UTF-8
|
93
|
+
require_paths:
|
94
|
+
- - lib
|
95
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
96
|
+
requirements:
|
97
|
+
- - ">="
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: "0"
|
100
|
+
version:
|
101
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - ">="
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: "0"
|
106
|
+
version:
|
107
|
+
requirements: []
|
108
|
+
|
109
|
+
rubyforge_project:
|
110
|
+
rubygems_version: 1.2.0
|
111
|
+
signing_key:
|
112
|
+
specification_version: 3
|
113
|
+
summary: A library for machine learning and classification
|
114
|
+
test_files: []
|
115
|
+
|