similarity_tree 1.0.0 → 1.0.1

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    MzViYTMyMjQzZGU0ZTc2ZDc2OGI2NWI3NDYyNWYwZGM2MDFjMzc5MQ==
+    ZDMwNDI5ODQ4ZTU2NDhiYjM4NmViMDM2NTlhYTA1OGU2MzI4Yjk2Ng==
   data.tar.gz: !binary |-
-    MDJmOWI2N2QxOTA2YTcwZjA4NThjZDhjZjRjMjAxOTMzY2Y5MTcyMw==
+    ZDM2ZmI2OTY4M2Q4MTlkODQ0Yjg1NTlmMmFiMWQ2OTY5ZDE0MTk5NA==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    Mzk0ZTllMGRiOGJmOTI3OTAwNWQyN2U2ZjhiNWNlNGExMDczODc2YjUwYzJh
-    MTI3N2ZjNDM1ZTEyY2MzODEzNmUwYjgyODZkOTRlOTg0ODU5NDZlMGM5YmFi
-    MTU4NmNiYjE0NDM0ZmEwNGE4ZTgzZGJhNGRiY2U1ZWQ3OTJlYTA=
+    YjhlZmM2Y2M0MDFhYjcwODU0OWJkZDE4MmM3NGViOTVkNzg2NzI0MDNiOTVl
+    MzRjMzk2YTY2YzI5NTJjNDE1YjEwMmY0YjM5ZTJjNThkYjI4MDZiYzZkODcx
+    OWEzZTU4MDgxODAyOGVjNWFjZjE1NTgxMTgxYjdiOWNhMjNiOTk=
   data.tar.gz: !binary |-
-    MzE0YjkzOGI2NDQ5ODE4YmQwMmViMjQ2NjllZmZhOWQzNTU1MDVjNWVkMGY1
-    NTYzZGY3NjIwY2I2NDVhMjUyODllOTZkNWM5OTYwYWViMWIwMmU1OWUyM2Rh
-    YzMzNzE3ZmVhZGZiNDgxM2ExZDRkNDhjZDFjYTE4NmZkMDdjYjA=
+    NmUxNmVjOTMyMTdiYTU0Njk2MjY2YzAwNjI4NmUzMDQ4NzM5MTJlNDdmODUw
+    NjM3YTY2ZTkwZDRiYzc1ZWI2MGU1NTJjZGVhZjI3YjA0NTM4ZWY4YzI2Yzc1
+    NmJjMmM2NmFiZDZkNDVlODYyZmUxZjk0NTZkNDgyZjkwOTEwNzA=

data/README.md

@@ -43,27 +43,22 @@ You can operate directly on **strings** rather than files (in this case, the nod
     tree = SimilarityTree::SimilarityMatrix.new(documents).build_tree("CC-BY-3.0.html")
     put tree.to_s  # to_h and to_json are also available as other tree output formats
 
-    CC-BY-3.0.html
-    -CC-BY-NC-3.0.html (0.9197574893009985)
-    --CC-BY-NC-SA-3.0.html (0.9503146737330241)
-    --CC-BY-NC-ND-3.0.html (0.9456402772710689)
-    -CC-BY-ND-3.0.html (0.9434472109631346)
-
 Result:
+
     0
     -1 (0.9197574893009985)
     --3 (0.9503146737330241)
     --4 (0.9456402772710689)
     -2 (0.9434472109631346)
 
-Or, you can use any **enumerable list of objects** (eg. ActiveRecords) as the inputs. Consider:
+Or, you can use any **enumerable list of objects** (eg. ActiveRecords) as the inputs. Consider the model:
 
     class Document < ActiveRecord::Base
       attr_accessible :title, :text_filename
       ...
     end
 
-You can call:
+Generate the tree as follows:
 
     tree = SimilarityTree::SimilarityMatrix.new(Document.all,
         id_func: :title, content_func: :text_filename).build_tree(Document.first.title)
@@ -74,10 +69,9 @@ You can call:
 
 You can use either the **term frequency–inverse document frequency** (:tf_idf, the default) or **Dice's coefficient** from a
 standard unix-style diff to calculate the diff scores. Tf-idf works much better where a document has a lot of translations
-(that is, "cut and pastes" of sections of text into different locations) and is also often faster.  However, if your intent
+(that is, "cut and pastes" of sections of text into different locations) and is often faster.  However, if your intent
 is to show diffs of the text, the :diff option will correlate better to your diff rendering.
 
-    documents = Dir.glob('../../similarity_tree/test/cc_licences/*.html')
     tf_idf_tree = SimilarityTree::SimilarityMatrix.new(documents,
         calculation_method: :tf_idf).build_tree("CC-BY-3.0.html")
     diff_tree = SimilarityTree::SimilarityMatrix.new(documents,

data/lib/similarity_tree/similarity_matrix.rb

@@ -1,6 +1,7 @@
-require 'matrix'
+require 'gsl'
 require 'tf-idf-similarity'
 require 'fast_html_diff'
+require 'ruby-progressbar'
 
 module SimilarityTree
   # Table of the diff/similarity scores between different text documents
@@ -62,7 +63,7 @@ module SimilarityTree
         progress_bar.increment unless progress_bar.nil?
         id_of(source)
       end
-      model = TfIdfSimilarity::TfIdfModel.new(corpus, function: :tf_idf)
+      model = TfIdfSimilarity::TfIdfModel.new(corpus, function: :tf_idf, library: :gsl)
       similarity_matrix = model.similarity_matrix
 
       # compile the results into an ordinary m*n array

data/lib/similarity_tree/version.rb

@@ -1,3 +1,3 @@
 module SimilarityTree
-  VERSION = "1.0.0"
+  VERSION = "1.0.1"
 end

data/similarity_tree.gemspec

@@ -20,7 +20,8 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.3"
   spec.add_development_dependency "rake"
-  spec.add_runtime_dependency "fast_html_diff"
+  spec.add_runtime_dependency "fast_html_diff", "~> 0.8.1"
+  spec.add_runtime_dependency "gsl"
   spec.add_runtime_dependency "tf-idf-similarity"
   spec.add_runtime_dependency "ruby-progressbar"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: similarity_tree
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Kent Mewhort
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-04 00:00:00.000000000 Z
+date: 2013-07-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -40,6 +40,20 @@ dependencies:
         version: '0'
 - !ruby/object:Gem::Dependency
   name: fast_html_diff
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.8.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.8.1
+- !ruby/object:Gem::Dependency
+  name: gsl
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ! '>='