lederhosen 0.3.8 → 0.3.9

data/.rspec

@@ -1 +1 @@
--c --fail-fast
+-c --fail-fast -f d

data/lederhosen.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "0.3.8"
+  s.version = "0.3.9"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]
-  s.date = "2012-08-20"
+  s.date = "2012-08-23"
   s.description = "Various tools for OTU clustering"
   s.email = "harekrishna@gmail.com"
   s.executables = ["lederhosen"]

data/lib/lederhosen/tasks/k_filter.rb

@@ -24,18 +24,17 @@ module Lederhosen
       counting_table = Hash.new { |h, k| h[k] = 0 }
       total_reads = 0
 
-      total_reads = `grep -c '^>' #{input}`.strip.split.first.to_i
-      pbar = ProgressBar.new 'counting', total_reads.to_i
       File.open(input) do |handle|
+        pbar = ProgressBar.new 'counting', File.size(input)
         records = Dna.new handle
         records.each do |r|
-          pbar.inc
+          pbar.inc(handle.pos)
           total_reads += 1
           kmers = r.sequence.to_kmers(k_len)
           kmers.each { |x| counting_table[x] += 1 }
         end
+        pbar.finish
       end
-      pbar.finish
 
       sum_of_kmers = counting_table.values.inject(:+)
 
@@ -49,7 +48,6 @@ module Lederhosen
       output = File.open(output, 'w')
       File.open(input) do |handle|
         records = Dna.new handle
-
         records.each do |r|
           kmers = r.sequence.to_kmers(k_len)
 

data/lib/lederhosen/tasks/split_fasta.rb

@@ -22,10 +22,13 @@ module Lederhosen
       `mkdir -p #{out_dir}`
 
       File.open input do |handle|
+        pbar = ProgressBar.new 'splitting', File.size(handle)
         Dna.new(handle).each_with_index do |record, i|
+          pbar.inc handle.pos
           @out = File.open(File.join(out_dir, "split_#{i/n}.fasta"), 'w') if i%n == 0
           @out.puts record
         end
+        pbar.finish
       end
 
     end

data/lib/lederhosen/tasks/uc_filter.rb

@@ -45,13 +45,14 @@ module Lederhosen
       kept, total = 1, 0
 
       File.open(input) do |handle|
+        pbar = ProgressBar.new 'saving', File.size(input)
         handle.each do |line|
           # output lederhosen filtering information because I often
           # forget to write this down :)
           out.puts "# filtered: #{input}"
           out.puts "# #{reads} reads in at least #{samples} samples"
 
-          pbar.inc
+          pbar.inc handle.pos
           if line =~ /^#/
             out.print line
             next
@@ -65,9 +66,9 @@ module Lederhosen
           end
 
         end
+        pbar.finish
       end
 
-      pbar.finish
       out.close
 
       ohai "clusters: #{surviving_clusters.length}/#{clstr_counts.keys.length} = #{100*surviving_clusters.length/clstr_counts.keys.length.to_f}%"

data/lib/lederhosen/tasks/uniquify.rb

@@ -1,11 +1,13 @@
 ##
-# uniquify - uniquify a fasta file, also output table with sequence_id -> number of reads
+# uniquify - uniquify a fasta file generating a fasta file of only unique sequences
+# also output table with sequence_id -> number of reads
 #
 
 module Lederhosen
   class CLI
     desc 'uniquify',
-      'uniquify a fasta file and generate a table with sequence_id -> abundance'
+      'uniquify a fasta file generating a fasta file of only unique sequences.' +\
+      'also generate a table with sequence_id -> abundance'
 
     method_option :input,     :type => :string, :required => true
     method_option :output,    :type => :string, :required => true
@@ -23,12 +25,10 @@ module Lederhosen
 
       out = File.open(output, 'w')
 
-      no_records = `grep -c '^>' #{input}`.split.first.to_i
-      pbar = ProgressBar.new 'loading', no_records
-
       File.open(input) do |handle|
+        pbar = ProgressBar.new 'loading', File.size(input)
         Dna.new(handle).each do |record|
-          pbar.inc
+          pbar.inc handle.pos
           unless sequence_counts.has_key? record.sequence
             # store the sequence and id so we can have ids in the
             # table. If the file is sorted by length then this
@@ -38,13 +38,13 @@ module Lederhosen
           end
           sequence_counts[record.sequence] += 1
         end
+        pbar.finish
       end
 
-      pbar.finish
       out.close
 
       # write table
-      pbar = ProgressBar.new 'table', no_records
+      pbar = ProgressBar.new 'table', sequence_counts.size
       File.open(table_out, 'w') do |out|
         sequence_counts.each_pair do |sequence, count|
           pbar.inc

data/lib/lederhosen/version.rb

@@ -2,7 +2,7 @@ module Lederhosen
   module Version
     MAJOR = 0
     MINOR = 3
-    PATCH = 8
+    PATCH = 9
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

data/readme.md

@@ -8,7 +8,7 @@ Lederhosen is free and open source under the [MIT open source license](http://op
 
 ## How do I get Lederhosen?
 
-0. Obtain & Install [UCLUST](http://www.drive5.com/) (64-bit)
+0. Obtain & Install [UCLUST](http://www.drive5.com/)
 1. Obtain & Install [BLAT](http://genome.ucsc.edu/FAQ/FAQblat.html#blat3)
 2. Get a copy of [TaxCollector](http://github.com/audy/taxcollector)
 3. Install Lederhosen by typing:

data/spec/cli_spec.rb

@@ -8,54 +8,54 @@ describe Lederhosen::CLI do
   end
 
   it 'should have a version command' do
-    `./bin/lederhosen version 2>/dev/null`.strip.should == "lederhosen-#{Lederhosen::Version::STRING}"
+    `./bin/lederhosen version `.strip.should == "lederhosen-#{Lederhosen::Version::STRING}"
   end
 
   it 'should trim reads' do
-    `./bin/lederhosen trim --reads-dir=spec/data/IL*.txt.gz --out-dir=#{$test_dir}/trimmed 2>/dev/null`
+    `./bin/lederhosen trim --reads-dir=spec/data/IL*.txt.gz --out-dir=#{$test_dir}/trimmed`
     $?.success?.should be_true
   end
 
   it 'should join reads' do
-    `./bin/lederhosen join --trimmed=#{$test_dir}/trimmed/*.fasta --output=#{$test_dir}/joined.fasta 2>/dev/null`
+    `./bin/lederhosen join --trimmed=#{$test_dir}/trimmed/*.fasta --output=#{$test_dir}/joined.fasta`
     $?.success?.should be_true
   end
 
   it 'should sort reads' do
-    `./bin/lederhosen sort --input=#{$test_dir}/joined.fasta --output=#{$test_dir}/sorted.fasta 2>/dev/null`
+    `./bin/lederhosen sort --input=#{$test_dir}/joined.fasta --output=#{$test_dir}/sorted.fasta`
     $?.success?.should be_true
   end
 
   it 'should k_filter reads' do
-    `./bin/lederhosen k_filter --input=#{$test_dir}/sorted.fasta --output=#{$test_dir}/filtered.fasta -k=15 --cutoff 1 2>/dev/null`
+    `./bin/lederhosen k_filter --input=#{$test_dir}/sorted.fasta --output=#{$test_dir}/filtered.fasta -k=15 --cutoff 1`
     $?.success?.should be_true
   end
 
   it 'should cluster reads' do
-    `./bin/lederhosen cluster --identity=0.80 --input=#{$test_dir}/filtered.fasta --output=#{$test_dir}/clusters.uc 2>/dev/null`
+    `./bin/lederhosen cluster --identity=0.80 --input=#{$test_dir}/filtered.fasta --output=#{$test_dir}/clusters.uc`
     $?.success?.should be_true
   end
 
   it 'should build OTU abundance matrices' do
-    `./bin/lederhosen otu_table --clusters=#{$test_dir}/clusters.uc --output=#{$test_dir}/otu_table.csv 2>/dev/null`
+    `./bin/lederhosen otu_table --clusters=#{$test_dir}/clusters.uc --output=#{$test_dir}/otu_table.csv`
     $?.success?.should be_true
   end
 
   it 'should filter OTU abundance matrices' do
-    `./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1 2>/dev/null`
+    `./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1`
   end
 
   it 'should uniquify reads' do
-    `./bin/lederhosen uniquify --input=#{$test_dir}/sorted.fasta --output=#{$test_dir}/uniqued.fasta --table-out=#{$test_dir}/uniquify.txt 2>/dev/null`
+    `./bin/lederhosen uniquify --input=#{$test_dir}/sorted.fasta --output=#{$test_dir}/uniqued.fasta --table-out=#{$test_dir}/uniquify.txt`
     $?.success?.should be_true
   end
 
   it 'should split joined.fasta into reads for each cluster' do
-    `./bin/lederhosen split --reads=#{$test_dir}/joined.fasta --clusters=#{$test_dir}/clusters.uc --out-dir=#{$test_dir}/split --min-clst-size=1 2>/dev/null`
+    `./bin/lederhosen split --reads=#{$test_dir}/joined.fasta --clusters=#{$test_dir}/clusters.uc --out-dir=#{$test_dir}/split --min-clst-size=1`
   end
 
   it 'should create a fasta file containing representative reads for each cluster' do
-    `./bin/lederhosen rep_reads --clusters=#{$test_dir}/clusters.uc --joined=#{$test_dir}/filtered.fasta --output=#{$test_dir}/representatives.fasta 2>/dev/null`
+    `./bin/lederhosen rep_reads --clusters=#{$test_dir}/clusters.uc --joined=#{$test_dir}/filtered.fasta --output=#{$test_dir}/representatives.fasta`
     $?.success?.should be_true
   end
 
@@ -66,12 +66,12 @@ describe Lederhosen::CLI do
     levels = %w{kingdom domain phylum class order genus speces}
     # Ruby 1.9 vs Ruby 1.8
     level = levels.sample rescue levels.choice
-    `./bin/lederhosen add_names --table=spec/data/otus.csv --blat=spec/data/blat.txt --level=#{level} --output=#{$test_dir}/named_otus.csv 2>/dev/null`
+    `./bin/lederhosen add_names --table=spec/data/otus.csv --blat=spec/data/blat.txt --level=#{level} --output=#{$test_dir}/named_otus.csv`
     $?.success?.should be_true
   end
 
   it 'should squish otu abundance matrix by same name' do
-    `./bin/lederhosen squish --csv-file=#{$test_dir}/named_otus.csv --output=#{$test_dir}/squished.csv 2>/dev/null`
+    `./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: 3
+  hash: 1
   prerelease: 
   segments: 
   - 0
   - 3
-  - 8
-  version: 0.3.8
+  - 9
+  version: 0.3.9
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-08-20 00:00:00 Z
+date: 2012-08-23 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   type: :runtime