tfidf 0.0.1 → 0.0.2

data/examples/demo_tf.rb

@@ -2,6 +2,7 @@
 require 'tfidf'
 require 'pp'
 require 'ruby-debug'
+require 'mongo_mapper'
 Debugger.settings[:autoeval] = true
 Debugger.start
 Debugger.post_mortem
@@ -119,7 +120,7 @@ Robison, a veteran deep-sea ecologist, said that whatever does live in the trenc
 Much of the deepest ocean is unreachable via state-owned submersibles, which at this point can dive no more than 21,000 feet (6,500 m). Only Japan's Shinkai 6500 has reached such depths. The United States is refurbishing Alvin, its deepest-diving craft, to be able to reach 21,000 feet within th_         ]
 
 tfidf = TFIDF.new corpus
-
+=begin
 puts "Documents in the corpus:"
 tfidf.docs.each {|k,v| puts "Document ID: #{k} => term: #{v}"}
 
@@ -143,6 +144,7 @@ puts tfidf.tfidf("octocat","7e38fa195cee92d2e7d834095d6938a89b5fdd58")
 
 puts "DTM in dense matrix"
 puts tfidf.dense
-
-
-
+=end
+tfidf_mongo = Object.to_mongo tfidf
+debugger
+puts tfidf_mongo.class

data/lib/tfidf.rb

@@ -14,7 +14,7 @@ class TFIDF
   def self.hash_func(obj)
     return Digest::SHA1.hexdigest obj
   end
-
+  
   #=Arguments
   #  corpus: an array of strings, one string per document
   #=Returns
@@ -73,6 +73,19 @@ class TFIDF
       @idf[k] = TFIDF.idf(v.size, @cardinality)}
   end
 
+  #TODO: really make this work as intended
+  def self.from_tf(tf_in_hash)
+    @dtm = OrderedHash.new
+    @docs = OrderedHash.new
+    @terms = SortedSet.new
+    tf_in_hash.map {|e|
+      id = TFIDF.hash_func Time.now
+      @dtm[id] = e
+      @docs[id] = "Place holder"
+      e.keys.map {|t| @terms.add t}
+    }
+  end
+
   #Build a TF vector out of a single document(String)
   #=Argument:
   #  String valued document
@@ -170,6 +183,24 @@ class TFIDF
     return tf(term,doc) * idf(term)
   end
 
+  def self.sparse_to_dense(array_of_ordered_hashes)
+    terms = SortedSet.new
+    array_of_ordered_hashes.each {|ordered_hash|
+      ordered_hash.keys.each {|k| terms.add(k)}}
+    terms = terms.to_a
+    n = array_of_ordered_hashes.length
+    d = terms.length
+    dense_matrix = GSL::Matrix.alloc(n,d)
+    (0...n).each do |i|
+      array_of_ordered_hashes[i].each do |term, freq|
+        idx = terms.index term
+        dense_matrix.set([i,idx], freq)
+      end
+    end
+    return dense_matrix
+  end    
+    
+
   #Access, or calculate if not present, a dense DTM in GSL::Matrix
   #Each row corresponds to a document, each column a term
   #Use TFIDF#terms.values and TFIDF#docs.values to find column/row index of a specific document/term

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tfidf
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -64,3 +64,4 @@ signing_key:
 specification_version: 3
 summary: A W.I.P implementation of TF-IDF
 test_files: []
+has_rdoc: