1 files changed, 18 insertions, 48 deletions
diff --git a/rerank.rb b/rerank.rb
index 900e0f2..9e2a708 100755
--- a/rerank.rb
+++ b/rerank.rb
@@ -3,72 +3,42 @@
 require 'zipf'
 
 class KbestItem
-  attr_accessor :rank, :model, :gold, :f, :id
+  attr_accessor :rank, :model, :gold, :f, :model_orig
   def initialize s
     a = s.split "\t"
     @rank = a[0].to_i
     @gold = a[1].to_f
     @model = a[2].to_f
+    @model_orig = @model
     @f = SparseVector.from_kv a[3], "=", " "
-    @id = -1
   end
-end
-
-
-
 
-
-
-def dot v, w
-  sum = 0.0
-  v.each_with_index { |k,i|
-   sum += k * w[i]
-  }
-
-  return sum
-end
-
-def elen v
-  len = 0.0
-  v.each { |i| len += i**2 }
-  return Math.sqrt len
-end
-
-def norm v
-  len = elen v
-  return v.map { |i| i/len }
+  def to_s
+    return "#{@model}\t#{@gold}"
+  end
 end
 
-STDERR.write "loading feature dict\n"
-fd = Marshal.load ReadFile.read ARGV[0]
-d = fd.size
-STDERR.write "#{d}\n"
-
-STDERR.write "loading model\n"
-w = Marshal.load ReadFile.read ARGV[1]
+`mkdir rrkb`
+w = SparseVector.from_kv ReadFile.new(ARGV[0]).read, "\t", "\n"
 
 STDERR.write "reranking..\n"
-kbest_lists = []
 cur = []
+k_sum = 0
+j = 0
 while line = STDIN.gets
   item = KbestItem.new line.strip
-  x = [0.0] * d
-  line.split("\t")[3].split.each { |i|
-    k,v = i.split '=', 2
-    x[fd[k]] = v.to_f
-  }
-  m = dot(w, norm(x))
-  item.model = m
+  item.model = w.dot(item.f)
   if item.rank == 0 && cur.size > 0
-    kbest_lists << cur
+    cur.sort! { |i,j| j.model <=> i.model }
+    f = WriteFile.new "rrkb/#{j}.gz"
+    f.write cur.map{|x| x.to_s}.join("\n")
+    f.close
+    puts "RERANKED\t#{cur.first.gold}"
     cur = []
+    j += 1
   end
   cur << item
 end
-kbest_lists << cur
-
-kbest_lists.each { |l|
-  puts "RERANKED\t#{l.sort { |i,j| j.model <=> i.model }.first.gold}"
-}
-
+cur.sort! { |i,j| j.model <=> i.model }
+puts "RERANKED\t#{cur.first.gold}"