summaryrefslogtreecommitdiff
path: root/benchmark/bm_so_k_nucleotide.rb
diff options
context:
space:
mode:
authorko1 <ko1@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2007-09-28 13:42:36 +0000
committerko1 <ko1@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2007-09-28 13:42:36 +0000
commitfbebfdf23db958e3bb06dc0d4ccadca48d748dff (patch)
tree6e5ef2d8e4b3b913524839cc1f2c37bb3f3f0c30 /benchmark/bm_so_k_nucleotide.rb
parentd6c43c45eaf5a6813ba5c2b3a68df154a69bdf9b (diff)
* benchmark/bm_so_fasta.rb: added.
* benchmark/bm_so_k_nucleotide.rb: added. * benchmark/bm_so_reverse_complement.rb: added. * benchmark/make_fasta_output.rb: added. * benchmark/prepare_so_k_nucleotide.rb: added. * benchmark/prepare_so_reverse_complement.rb: added. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@13550 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'benchmark/bm_so_k_nucleotide.rb')
-rw-r--r--benchmark/bm_so_k_nucleotide.rb48
1 files changed, 48 insertions, 0 deletions
diff --git a/benchmark/bm_so_k_nucleotide.rb b/benchmark/bm_so_k_nucleotide.rb
new file mode 100644
index 0000000..c0a5ba5
--- /dev/null
+++ b/benchmark/bm_so_k_nucleotide.rb
@@ -0,0 +1,48 @@
+# The Computer Language Shootout
+# http://shootout.alioth.debian.org
+#
+# contributed by jose fco. gonzalez
+# modified by Sokolov Yura
+
+seq = String.new
+
+def frecuency( seq,length )
+ n, table = seq.length - length + 1, Hash.new(0)
+ f, i = nil, nil
+ (0 ... length).each do |f|
+ (f ... n).step(length) do |i|
+ table[seq[i,length]] += 1
+ end
+ end
+ [n,table]
+
+end
+
+def sort_by_freq( seq,length )
+ n,table = frecuency( seq,length )
+ a, b, v = nil, nil, nil
+ table.sort{|a,b| b[1] <=> a[1]}.each do |v|
+ puts "%s %.3f" % [v[0].upcase,((v[1]*100).to_f/n)]
+ end
+ puts
+end
+
+def find_seq( seq,s )
+ n,table = frecuency( seq,s.length )
+ puts "#{table[s].to_s}\t#{s.upcase}"
+end
+
+input = open(File.join(File.dirname($0), 'fasta.output.100000'), 'rb')
+
+line = input.gets while line !~ /^>THREE/
+line = input.gets
+
+while (line !~ /^>/) & line do
+ seq << line.chomp
+ line = input.gets
+end
+
+[1,2].each {|i| sort_by_freq( seq,i ) }
+
+%w(ggt ggta ggtatt ggtattttaatt ggtattttaatttatagt).each{|s| find_seq( seq,s) }
+