lederhosen 0.1.5 → 0.1.6

data/lib/lederhosen/tasks/add_names.rb

@@ -6,7 +6,7 @@ module Lederhosen
 	class CLI
 
 		desc "add_names",
-			"add names to otu abundance matrix using blat output and the out file"
+			"add names to otu abundance matrix using blat output" 
 
 		method_option :blat,   :type => :string, :required => true
 		method_option :table,  :type => :string, :required => true

data/lib/lederhosen/tasks/otu_filter.rb

@@ -0,0 +1,45 @@
+module Lederhosen
+	class CLI
+
+		desc 'otu_filter', 'works like uc_filter but uses an OTU table as input'
+
+		method_option :input, :type   =>  :string, :required => true
+		method_option :output, :type  =>  :string, :required => true
+		method_option :reads, :type   => :numeric, :required => true
+		method_option :samples, :type => :numeric, :required => true
+
+		def otu_filter
+			input   = options[:input]
+			output  = options[:output]
+			reads   = options[:reads]
+			samples = options[:samples]
+
+			##
+			# Iterate over otu table line by line.
+			# Only print if cluster meets criteria
+			#
+			kept = 0
+			File.open(input) do |handle|
+			  header  = handle.gets.strip
+				header  = header.split(',')
+				samples = header[1..-1]
+	
+				puts header.join(',')
+
+				handle.each do |line|
+					line       = line.strip.split(',')
+					cluster_no = line[0]
+					counts     = line[1..-1].collect { |x| x.to_i }
+
+					# should be the same as uc_filter
+					if counts.reject { |x| x < reads }.length > samples
+						puts line.join(',')
+						kept += 1  
+					end
+				end
+			end
+			ohai "kept #{kept} clusters."
+		end
+		
+	end
+end

data/lib/lederhosen/tasks/otu_table.rb

@@ -18,32 +18,31 @@ module Lederhosen
       output       = options[:output]
       joined_reads = options[:joined]
       
+      # Load cluster table
 
-      # Load cluster table!
       clstr_info      = Helpers.load_uc_file input     
       clstr_counts    = clstr_info[:clstr_counts] # clstr_counts[:clstr][sample.to_i] = reads
       clstrnr_to_seed = clstr_info[:clstrnr_to_seed]
       samples         = clstr_info[:samples]
 
-      # print OTU abundancy matrix
-      
+      # print OTU abundance matrix
+			# clusters as columns
+			# samples as rows
+
       File.open("#{output}.csv", 'w') do |h|
         samples  = samples.sort
         clusters = clstr_counts.keys
 
-        # print header
-        head = samples.join(SEP)
-        h.puts "-" + SEP + head
-
-        # start printing clusters
-        clusters.each do |cluster|
-          h.print "cluster-#{cluster}"
-          samples.each do |sample|
-            h.print "#{SEP}#{clstr_counts[cluster][sample]}"
-          end
-          h.print "\n"
-        end
-          
+        # print header (cluster names)
+				h.puts '-' + SEP + clusters.map { |x| "cluster-#{x}" }.join(SEP)
+
+				samples.each do |sample|
+					h.print sample
+					clusters.each do |cluster|
+						h.print "#{SEP}#{clstr_counts[cluster][sample]}"
+					end
+					h.print "\n"
+				end
       end
     end
 

data/lib/lederhosen/tasks/squish.rb

@@ -29,17 +29,17 @@ module Lederhosen
 				end
 			end
 
-			output = File.open(output) rescue $stdout
+			output = File.open(output, 'w') rescue $stdout
 
 			# print the new, squished csv file
 			column_names.uniq!.sort!
-			puts "-,#{column_names.join(',')}"
+			output.puts "-,#{column_names.join(',')}"
 			total_by_sample_by_column.each_pair do |sample_id, row|
-				print "#{sample_id}"
+				output.print "#{sample_id}"
 				column_names.each do |column_name|
-					print ",#{row[column_name]}"
+					output.print ",#{row[column_name]}"
 				end
-				print "\n"
+				output.print "\n"
 			end
 	
 			output.close

data/lib/version.rb

@@ -1,3 +1,3 @@
 module Lederhosen
-  VERSION = '0.1.5'
+  VERSION = '0.1.6'
 end

data/spec/pipeline_spec.rb

@@ -2,6 +2,8 @@ test_dir = "/tmp/lederhosen_test_#{(0...8).map{65.+(rand(25)).chr}.join}/"
 
 `mkdir -p #{test_dir}`
 
+$stderr.puts "test dir: #{test_dir}"; sleep 1
+
 describe 'the pipeline' do
 
   it 'should exist' do
@@ -47,7 +49,7 @@ describe 'the pipeline' do
 	end
 
 	it 'should squish otu abundance matrix by same name' do
-		`./bin/lederhosen squish --csv-file=#{test_dir}/named_otus.csv`
+		`./bin/lederhosen squish --csv-file=#{test_dir}/named_otus.csv --output=#{test_dir}/squished.csv"`
 		$?.success?.should be_true
 	end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 17
+  hash: 23
   prerelease: 
   segments: 
   - 0
   - 1
-  - 5
-  version: 0.1.5
+  - 6
+  version: 0.1.6
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-07-14 00:00:00 Z
+date: 2012-07-16 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: dna
@@ -140,6 +140,7 @@ files:
 - lib/lederhosen/tasks/join.rb
 - lib/lederhosen/tasks/k_filter.rb
 - lib/lederhosen/tasks/name.rb
+- lib/lederhosen/tasks/otu_filter.rb
 - lib/lederhosen/tasks/otu_table.rb
 - lib/lederhosen/tasks/rep_reads.rb
 - lib/lederhosen/tasks/sort.rb