rbbt-dm 1.1.45 → 1.1.46

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 3d0fe8cd4d9acfbef39eab9bb2cc6537dc4846b8
-  data.tar.gz: 0f373711bbd5c67c072012570b67301336082df3
+SHA256:
+  metadata.gz: 5f70d6a55c5852ffdafd59a3199b41031ee5a5aaa4becc56ee2f7f49be3b5d43
+  data.tar.gz: f5d53ca95b6af4d6c2b63f00bbbfd398e3fa5a6feea15885b00ccd946f3aa765
 SHA512:
-  metadata.gz: 03f79f5464f66d147ca1e86fa30a86d911dc84e6a2766e13c7a04be1141405e9f46e545e76f04283a765b168c79b37ecde140bee096c9ce85604ada8cd5176db
-  data.tar.gz: 5e3aea0ec0e1c5683ac177e830883c4987dedd524353e14124148edc3c87181374a20a09c7b41c37c1bdb68e89efe0708fb532d3bc90f1403b4eb61bec8c87f4
+  metadata.gz: 7cd9928cd7a3e7558e27796f0e8f4c7635caa2331dc3f2d2d904434d9feedf6e3d2085ba301b55c61b87bdee83fbc588c666a99c0d0cc0d5414d1614a964a0a5
+  data.tar.gz: f559bff1acc000be594ad8e91534a4af24acad3ebf80c276b8055af582a91e5137c748acf55267c8001b0c667cc1c6a167ca86a11b34da52ebb796ba8fdd01fe

data/lib/rbbt/ml_task.rb

@@ -0,0 +1,7 @@
+class MLTask
+  def initialize
+  end
+
+  def pre_process
+  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/lib/rbbt/vector/model.rb

@@ -57,6 +57,11 @@ 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?
@@ -119,4 +124,53 @@ 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/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: 1.1.45
+  version: 1.1.46
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-03-24 00:00:00.000000000 Z
+date: 2020-01-30 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
@@ -137,8 +139,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.13
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: Data-mining and statistics
@@ -149,6 +150,7 @@ test_files:
 - test/rbbt/statistics/test_fisher.rb
 - test/rbbt/statistics/test_fdr.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