Fix the corner cases (#173)

* Avoid zero division

* Fix a bug caused by indeterminate form

* Fix a bug occurring when a zero vector try normalizing itself

* Fix a bug

* Revert "Fix a bug"

This reverts commit 151e9f8.

* Revert "Revert "Fix a bug""

This reverts commit 02b98d8.

* add a test that may raise ZeroDivisionError

* add a test for zero vectors

* add a test that may raise Vector::ZeroVectorError

* fix cutoff

Author: sueka

lib/classifier-reborn/extensions/vector.rb

@@ -31,7 +31,11 @@ def SV_decomp(maxSweeps = 20)
         (1..qrot.row_size - 1).each do |col|
           next if row == col
 
-          h = Math.atan((2 * qrot[row, col]) / (qrot[row, row] - qrot[col, col])) / 2.0
+          if (2.0 * qrot[row, col]) == (qrot[row, row] - qrot[col, col])
+            h = Math.atan(1) / 2.0
+          else
+            h = Math.atan((2.0 * qrot[row, col]) / (qrot[row, row] - qrot[col, col])) / 2.0
+          end
           hcos = Math.cos(h)
           hsin = Math.sin(h)
           mzrot = Matrix.identity(qrot.row_size)

lib/classifier-reborn/extensions/zero_vector.rb

@@ -0,0 +1,5 @@
+class Vector
+  def zero?
+    self.all? {|_| _ == 0}
+  end
+end

lib/classifier-reborn/lsi.rb

@@ -12,6 +12,7 @@
 rescue LoadError
   $GSL = false
   require_relative 'extensions/vector'
+  require_relative 'extensions/zero_vector'
 end
 
 require_relative 'lsi/word_list'
@@ -142,9 +143,13 @@ def build_index(cutoff = 0.75)
         tdm = Matrix.rows(tda).trans
         ntdm = build_reduced_matrix(tdm, cutoff)
 
-        ntdm.row_size.times do |col|
+        ntdm.column_size.times do |col|
           doc_list[col].lsi_vector = ntdm.column(col) if doc_list[col]
-          doc_list[col].lsi_norm = ntdm.column(col).normalize if doc_list[col]
+          if ntdm.column(col).zero?
+            doc_list[col].lsi_norm = ntdm.column(col) if doc_list[col]
+          else
+            doc_list[col].lsi_norm = ntdm.column(col).normalize if doc_list[col]
+          end
         end
       end
 

test/extensions/matrix_test.rb

@@ -0,0 +1,6 @@
+class MatrixTest < Minitest::Test
+  def test_zero_division
+    matrix = Matrix[[1, 0], [0, 1]]
+    matrix.SV_decomp
+  end
+end

test/extensions/zero_vector_test.rb

@@ -0,0 +1,10 @@
+class ZeroVectorTest < Minitest::Test
+  def test_zero?
+    vec0 = Vector[]
+    vec1 = Vector[0]
+    vec10 = Vector.elements [0] * 10
+    assert vec0.zero?
+    assert vec1.zero?
+    assert vec10.zero?
+  end
+end

test/lsi/lsi_test.rb

@@ -30,6 +30,14 @@ def test_not_auto_rebuild
     assert !lsi.needs_rebuild?
   end
 
+  def test_zero_vector_normalization
+    lsi = ClassifierReborn::LSI.new auto_rebuild: false
+    lsi.add_item @str1[0...8], 'Dog'
+    lsi.add_item @str2, 'Dog'
+    lsi.add_item @str3, 'Cat'
+    lsi.build_index(0.75)
+  end
+
   def test_basic_categorizing
     lsi = ClassifierReborn::LSI.new
     lsi.add_item @str2, 'Dog'