rbbt-dm 1.1.43 → 1.1.48

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 270570bf58c397ec1f6da3195f882a5cf73eb1a1
-  data.tar.gz: 4f7232e2c2cddff960f2f9dce6e4279298b53408
+SHA256:
+  metadata.gz: 2d054c98df9e1b451849ddcf01f089d2822746d2a4ac8017f7f40f412de5d8c4
+  data.tar.gz: 55df50b751243cf77c023a016b53c258138c24c9b10bf1068fa5bb6385c1c114
 SHA512:
-  metadata.gz: faa0514ae85d537007147f8a1c06367202cffa83c5081b68f9e2e23943b02cc5601160fbcfd32f0c041fd511b2f3116e82b14b5313ba57488297f76a74f77433
-  data.tar.gz: bc1d750d449763f45482318e1f4fe5d54f80c64eb90c3fb08c71d94d282496aa87e54004f309e2c2dac4cc3bc01995880481be490c4bf6510d1e35417276eb85
+  metadata.gz: 3b6397645a532feb4bd2aa0dabd715091a2438a07244c11f82ab52f3c40b3fb43e515667b48630e9b8bd28b4d33c0a69cf57d1151dbb0616d1896a4558828fa3
+  data.tar.gz: 20b90f5d900ab8e1a6a930edc5573a420213360961fbb796022e2a09f442307b731c30a7da6b535d7fc90d72fe92fb358de5fdebc420814a7ef300f23c798341

data/lib/rbbt/matrix.rb

@@ -176,6 +176,26 @@ class RbbtMatrix
     matrix
   end
 
+  def to_name(identifiers = nil)
+    require 'rbbt/tsv/change_id'
+
+    name = data_file =~ /:>/ ? File.basename(data_file) : data_file
+
+    file = Persist.persist(data_file, :tsv, :prefix => "Name", :check => [data_file], :dir => RbbtMatrix.matrix_dir.values, :no_load => true) do
+
+      data = data_file.tsv(:cast => :to_f)
+
+      identifiers = [identifiers, @identifiers, data.identifiers, Organism.identifiers(organism)].flatten.compact.uniq
+
+      data.change_key("Associated Gene Name", :identifiers => identifiers.reverse) do |v|
+        Misc.mean(v.compact)
+      end
+    end
+    subsets = self.subsets
+    matrix = RbbtMatrix.new file, labels, value_type, "Associated Gene Name", organism
+    matrix.subsets = subsets
+    matrix
+  end
   def to_barcode_ruby(factor = 2)
     name = data_file =~ /:>/ ? File.basename(data_file) : data_file
 

data/lib/rbbt/matrix/barcode.rb

@@ -38,7 +38,7 @@ rbbt.GE.barcode.mode(#{ R.ruby2R self.data_file }, #{ R.ruby2R outfile }, #{ R.r
           end
         end
         key = key.first if Array === key
-      [key, bars]
+        [key, bars]
       end
     end
 

data/lib/rbbt/ml_task.rb

@@ -0,0 +1,7 @@
+class MLTask
+  def initialize
+  end
+
+  def pre_process
+  end
+end

data/lib/rbbt/network/paths.rb

@@ -5,7 +5,7 @@ module Paths
   def self.dijkstra(adjacency, start_node, end_node = nil, max_steps = nil)
     return nil unless adjacency.include? start_node
 
-    active = FastContainers::PriorityQueue.new(:max)
+    active = FastContainers::PriorityQueue.new(:min)
     distances = Hash.new { 1.0 / 0.0 } 
     parents = Hash.new                 
 
@@ -49,7 +49,7 @@ module Paths
   def self.weighted_dijkstra(adjacency, start_node, end_node = nil, threshold = nil, max_steps = nil)
     return nil unless adjacency.include? start_node
 
-    active = FastContainers::PriorityQueue.new(:max)
+    active = FastContainers::PriorityQueue.new(:min)
     distances = Hash.new { 1.0 / 0.0 } 
     parents = Hash.new                 
 

data/lib/rbbt/vector/model.rb

@@ -4,6 +4,20 @@ class VectorModel
   attr_accessor :directory, :model_file, :extract_features, :train_model, :eval_model
   attr_accessor :features, :labels
 
+  def self.R_run(model_file, features, labels, code)
+    TmpFile.with_file do |feature_file|
+      Open.write(feature_file, features.collect{|feats| feats * "\t"} * "\n")
+      Open.write(feature_file + '.class', labels * "\n")
+
+      R.run <<-EOF
+features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
+labels = scan("#{ feature_file }.class");
+features = cbind(features, class = labels);
+#{code}
+      EOF
+    end
+  end
+
   def self.R_train(model_file, features, labels, code)
     TmpFile.with_file do |feature_file|
       Open.write(feature_file, features.collect{|feats| feats * "\t"} * "\n")
@@ -57,6 +71,11 @@ cat(paste(label, sep="\\n"));
     @labels = []
   end
 
+  def clear
+    @features = []
+    @labels = []
+  end
+
   def add(element, label = nil)
     @features << extract_features.call(element)
     @labels << label unless label.nil?
@@ -67,16 +86,20 @@ cat(paste(label, sep="\\n"));
     when Proc === train_model
       train_model.call(@model_file, @features, @labels)
     when String === train_model
-      SVMModel.R_train(@model_file,  @features, @labels, train_model)
+      VectorModel.R_train(@model_file,  @features, @labels, train_model)
     end
   end
 
+  def run(code)
+    VectorModel.R_run(@model_file,  @features, @labels, code)
+  end
+
   def eval(element)
     case 
     when Proc === eval_model
       eval_model.call(@model_file, extract_features.call(element), false)
     when String === eval_model
-      SVMModel.R_eval(@model_file,  extract_features.call(element), false, eval_model)
+      VectorModel.R_eval(@model_file,  extract_features.call(element), false, eval_model)
     end
   end
 
@@ -119,4 +142,53 @@ cat(paste(label, sep="\\n"));
 
     acc
   end
+
+  def cross_validation(folds = 10)
+
+    res = TSV.setup({}, "Fold~TP,TN,FP,FN,P,R,F1#:type=:list")
+
+    feature_folds = Misc.divide(@features, folds)
+    labels_folds = Misc.divide(@labels, folds)
+
+    folds.times do |fix|
+
+      test_set = feature_folds[fix]
+      train_set = feature_folds.values_at(*((0..9).to_a - [fix])).inject([]){|acc,e| acc += e; acc}
+
+      test_labels = labels_folds[fix]
+      train_labels = labels_folds.values_at(*((0..9).to_a - [fix])).flatten
+
+      tp, fp, tn, fn, pr, re, f1 = [0, 0, 0, 0, nil, nil, nil]
+
+      @features = train_set
+      @labels = train_labels
+      self.train
+      predictions = self.eval_list test_set, false
+
+      test_labels.zip(predictions).each do |gs,pred|
+        gs = gs.to_i
+        pred = pred > 0.5 ? 1 : 0
+        tp += 1 if gs == pred && gs == 1
+        tn += 1 if gs == pred && gs == 0
+        fp += 1 if gs == 0 && pred == 1
+        fn += 1 if gs == 1 && pred == 0
+      end
+
+      p = tp + fn
+      pp = tp + fp
+
+      pr = tp.to_f / pp
+      re = tp.to_f / p
+
+      f1 = (2.0 * tp) / (2.0 * tp + fp + fn) 
+
+      Misc.fingerprint([tp,tn,fp,fn,pr,re,f1])
+
+      Log.debug "CV Fold #{fix} P:#{"%.3f" % pr} R:#{"%.3f" % re} F1:#{"%.3f" % f1}"
+
+      res[fix] = [tp,tn,fp,fn,pr,re,f1]
+    end
+
+    res
+  end
 end

data/lib/rbbt/vector/model/svm.rb

@@ -9,7 +9,7 @@ class SVMModel < VectorModel
 
     @train_model =<<-EOF
 library(e1071);
-model = svm(class ~ ., data = features);
+model = svm(class ~ ., data = features, scale=c(0));
     EOF
  
     @eval_model =<<-EOF

data/test/rbbt/matrix/test_barcode.rb

@@ -11,7 +11,7 @@ class TestBarcode < Test::Unit::TestCase
     data["G4"] = [6,6,1,1,1,1]
 
     TmpFile.with_file(data.to_s) do |file|
-      m = Matrix.new file
+      m = RbbtMatrix.new file
       m.barcode(file+'.barcode')
       tsv =  TSV.open(file+'.barcode')
       assert tsv["G2"] = [0,1,0,1,0,1]

data/test/rbbt/network/test_paths.rb

@@ -6,7 +6,7 @@ require 'set'
 
 
 class TestNetwork < Test::Unit::TestCase
-  def _test_dijsktra
+  def test_dijsktra
     network_txt=<<-EOF
 #: :sep=/\s/#:type=:flat
 #Start End

data/test/rbbt/test_ml_task.rb

@@ -0,0 +1,12 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '..', 'test_helper.rb')
+require 'rbbt/ml_task'
+
+class TestMLTask < Test::Unit::TestCase
+  def test_MLTask
+
+    triage = MLTask.new
+    ml_task.pre_process do
+    end
+  end
+end
+

data/test/rbbt/vector/test_model.rb

@@ -34,7 +34,7 @@ class TestVectorModel < Test::Unit::TestCase
 features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
 labels = scan("#{ feature_file }.class", what=numeric());
 features = cbind(features, class = labels);
-library(e1071)
+rbbt.require('e1071')
 model = svm(class ~ ., data = features) 
 save(model, file="#{ model_file }");
           EOF

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-dm
 version: !ruby/object:Gem::Version
-  version: 1.1.43
+  version: 1.1.48
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-11-29 00:00:00.000000000 Z
+date: 2020-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -95,6 +95,7 @@ files:
 - lib/rbbt/matrix/barcode.rb
 - lib/rbbt/matrix/differential.rb
 - lib/rbbt/matrix/knowledge_base.rb
+- lib/rbbt/ml_task.rb
 - lib/rbbt/network/paths.rb
 - lib/rbbt/plots/bar.rb
 - lib/rbbt/plots/heatmap.rb
@@ -115,6 +116,7 @@ files:
 - test/rbbt/statistics/test_fisher.rb
 - test/rbbt/statistics/test_hypergeometric.rb
 - test/rbbt/statistics/test_random_walk.rb
+- test/rbbt/test_ml_task.rb
 - test/rbbt/test_stan.rb
 - test/rbbt/vector/model/test_svm.rb
 - test/rbbt/vector/test_model.rb
@@ -137,19 +139,19 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Data-mining and statistics
 test_files:
-- test/test_helper.rb
-- test/rbbt/test_stan.rb
-- test/rbbt/vector/model/test_svm.rb
-- test/rbbt/vector/test_model.rb
 - test/rbbt/network/test_paths.rb
 - test/rbbt/matrix/test_barcode.rb
+- test/rbbt/statistics/test_random_walk.rb
 - test/rbbt/statistics/test_fisher.rb
-- test/rbbt/statistics/test_hypergeometric.rb
 - test/rbbt/statistics/test_fdr.rb
-- test/rbbt/statistics/test_random_walk.rb
+- test/rbbt/statistics/test_hypergeometric.rb
+- test/rbbt/test_ml_task.rb
+- test/rbbt/vector/test_model.rb
+- test/rbbt/vector/model/test_svm.rb
+- test/rbbt/test_stan.rb
+- test/test_helper.rb