rbbt-dm 1.1.47 → 1.1.52

data/test/rbbt/vector/model/test_tensorflow.rb

@@ -0,0 +1,57 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../../..', 'test_helper.rb')
+require 'rbbt/vector/model/tensorflow'
+
+class TestTensorflowModel < Test::Unit::TestCase
+
+  def test_keras
+    TmpFile.with_file() do |dir|
+      FileUtils.mkdir_p dir
+
+      model = TensorFlowModel.new(
+        dir, 
+        optimizer:'adam',
+        loss: 'sparse_categorical_crossentropy',
+        metrics: ['accuracy']
+      )
+
+      model.keras_graph do
+        tf = tensorflow
+        tf.keras.models.Sequential.new([
+          tf.keras.layers.Flatten.new(input_shape: [28, 28]),
+          tf.keras.layers.Dense.new(128, activation:'relu'),
+          tf.keras.layers.Dropout.new(0.2),
+          tf.keras.layers.Dense.new(10, activation:'softmax')
+        ])
+      end
+
+      sum = predictions = nil
+      model.tensorflow do
+        tf = tensorflow
+        mnist_db = tf.keras.datasets.mnist
+
+        (x_train, y_train), (x_test, y_test) = mnist_db.load_data()
+        x_train, x_test = x_train / 255.0, x_test / 255.0
+
+        num = PyCall.len(x_train)
+
+        num.times do |i|
+          model.add x_train[i], y_train[i]
+        end
+
+        model.train
+
+        predictions = model.eval_list x_test.tolist()
+        sum = 0
+        predictions.zip(y_test.tolist()).each do |pred,label|
+          sum += 1 if label.to_i == pred
+        end
+
+      end
+
+      assert sum.to_f / predictions.length > 0.7
+
+
+    end
+  end
+end
+

data/test/rbbt/vector/test_model.rb

@@ -71,4 +71,358 @@ cat(label, file="#{results}");
     end
   end
 
+  def test_model_list
+    text =<<-EOF
+1 0;1;1
+1 1;0;1
+1 1;1;1
+1 0;1;1
+1 1;1;1
+0 0;1;0
+0 1;0;0
+0 0;1;0
+0 1;0;0
+    EOF
+
+    TmpFile.with_file() do |dir|
+      FileUtils.mkdir_p dir
+      model = VectorModel.new(dir)
+
+      model.extract_features = Proc.new{|element,list|
+        if element
+          element.split(";")
+        elsif list
+          list.collect{|e| e.split(";") }
+        end
+      }
+
+      model.train_model = Proc.new{|model_file,features,labels|
+        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", what=numeric());
+features = cbind(features, class = labels);
+rbbt.require('e1071')
+model = svm(class ~ ., data = features) 
+save(model, file="#{ model_file }");
+          EOF
+        end
+      }
+
+      model.eval_model = Proc.new{|model_file,features|
+        TmpFile.with_file do |feature_file|
+          TmpFile.with_file do |results|
+            Open.write(feature_file, features * "\t")
+            puts R.run(<<-EOF
+features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
+library(e1071)
+load(file="#{ model_file }")
+label = predict(model, features);
+cat(label, file="#{results}");
+            EOF
+            ).read
+            Open.read(results)
+          end
+        end
+
+      }
+
+      pairs = text.split(/\n/).collect do |line|
+        label, features = line.split(" ")
+        [features, label]
+      end
+
+      model.add_list(*Misc.zip_fields(pairs))
+
+      model.train
+
+      assert model.eval("1;1;1").to_f > 0.5
+      assert model.eval("0;0;0").to_f < 0.5
+    end
+  end
+
+  def test_model_list2
+    text =<<-EOF
+1 0;1;1
+1 1;0;1
+1 1;1;1
+1 0;1;1
+1 1;1;1
+0 0;1;0
+0 1;0;0
+0 0;1;0
+0 1;0;0
+    EOF
+
+    TmpFile.with_file() do |dir|
+      FileUtils.mkdir_p dir
+      model = VectorModel.new(dir)
+
+      model.extract_features = Proc.new{|element|
+        element.split(";")
+      }
+
+      model.train_model = Proc.new{|model_file,features,labels|
+        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", what=numeric());
+features = cbind(features, class = labels);
+rbbt.require('e1071')
+model = svm(class ~ ., data = features) 
+save(model, file="#{ model_file }");
+          EOF
+        end
+      }
+
+      model.eval_model = Proc.new{|model_file,features|
+        TmpFile.with_file do |feature_file|
+          TmpFile.with_file do |results|
+            Open.write(feature_file, features * "\t")
+            puts R.run(<<-EOF
+features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
+library(e1071)
+load(file="#{ model_file }")
+label = predict(model, features);
+cat(label, file="#{results}");
+            EOF
+            ).read
+            Open.read(results)
+          end
+        end
+
+      }
+
+      pairs = text.split(/\n/).collect do |line|
+        label, features = line.split(" ")
+        [features, label]
+      end
+
+      model.add_list(*Misc.zip_fields(pairs))
+
+      model.train
+
+      assert model.eval("1;1;1").to_f > 0.5
+      assert model.eval("0;0;0").to_f < 0.5
+    end
+  end
+
+  def test_model_list
+    text =<<-EOF
+1 0;1;1
+1 1;0;1
+1 1;1;1
+1 0;1;1
+1 1;1;1
+0 0;1;0
+0 1;0;0
+0 0;1;0
+0 1;0;0
+    EOF
+
+    TmpFile.with_file() do |dir|
+      FileUtils.mkdir_p dir
+      model = VectorModel.new(dir)
+
+      model.extract_features = Proc.new{|element,list|
+        if element
+          element.split(";")
+        elsif list
+          list.collect{|e| e.split(";") }
+        end
+      }
+
+      model.train_model = Proc.new{|model_file,features,labels|
+        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", what=numeric());
+features = cbind(features, class = labels);
+rbbt.require('e1071')
+model = svm(class ~ ., data = features) 
+save(model, file="#{ model_file }");
+          EOF
+        end
+      }
+
+      model.eval_model = Proc.new{|model_file,features|
+        TmpFile.with_file do |feature_file|
+          TmpFile.with_file do |results|
+            Open.write(feature_file, features * "\t")
+            puts R.run(<<-EOF
+features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
+library(e1071)
+load(file="#{ model_file }")
+label = predict(model, features);
+cat(label, file="#{results}");
+            EOF
+            ).read
+            Open.read(results)
+          end
+        end
+
+      }
+
+      pairs = text.split(/\n/).collect do |line|
+        label, features = line.split(" ")
+        model.add features, label
+      end
+
+      model.train
+
+      assert model.eval("1;1;1").to_f > 0.5
+      assert model.eval("0;0;0").to_f < 0.5
+    end
+  end
+
+  def test_model_save
+    text =<<-EOF
+1 0;1;1
+1 1;0;1
+1 1;1;1
+1 0;1;1
+1 1;1;1
+0 0;1;0
+0 1;0;0
+0 0;1;0
+0 1;0;0
+    EOF
+
+    TmpFile.with_file() do |dir|
+      FileUtils.mkdir_p dir
+      model = VectorModel.new(dir)
+
+      model.extract_features = Proc.new{|element|
+        element.split(";")
+      }
+
+      model.train_model = Proc.new{|model_file,features,labels|
+        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", what=numeric());
+features = cbind(features, class = labels);
+rbbt.require('e1071')
+model = svm(class ~ ., data = features) 
+save(model, file="#{ model_file }");
+          EOF
+        end
+      }
+
+      model.eval_model = Proc.new{|model_file,features|
+        TmpFile.with_file do |feature_file|
+          TmpFile.with_file do |results|
+            Open.write(feature_file, features * "\t")
+            puts R.run(<<-EOF
+features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
+library(e1071)
+load(file="#{ model_file }")
+label = predict(model, features);
+cat(label, file="#{results}");
+            EOF
+            ).read
+            Open.read(results)
+          end
+        end
+
+      }
+
+      pairs = text.split(/\n/).collect do |line|
+        label, features = line.split(" ")
+        [features, label]
+      end
+
+      model.add_list(*Misc.zip_fields(pairs))
+
+      model.train
+
+      assert model.eval("1;1;1").to_f > 0.5
+      assert model.eval("0;0;0").to_f < 0.5
+    end
+  end
+
+  def test_model_save
+    text =<<-EOF
+1 0;1;1
+1 1;0;1
+1 1;1;1
+1 0;1;1
+1 1;1;1
+0 0;1;0
+0 1;0;0
+0 0;1;0
+0 1;0;0
+    EOF
+
+    TmpFile.with_file() do |dir|
+      FileUtils.mkdir_p dir
+      model = VectorModel.new(dir)
+
+      model.extract_features = Proc.new{|element,list|
+        if element
+          element.split(";")
+        elsif list
+          list.collect{|e| e.split(";") }
+        end
+      }
+
+      model.train_model = Proc.new{|model_file,features,labels|
+        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", what=numeric());
+features = cbind(features, class = labels);
+rbbt.require('e1071')
+model = svm(class ~ ., data = features) 
+save(model, file="#{ model_file }");
+          EOF
+        end
+      }
+
+      model.eval_model = Proc.new{|model_file,features|
+        TmpFile.with_file do |feature_file|
+          TmpFile.with_file do |results|
+            Open.write(feature_file, features * "\t")
+            puts R.run(<<-EOF
+features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
+library(e1071)
+load(file="#{ model_file }")
+label = predict(model, features);
+cat(label, file="#{results}");
+            EOF
+            ).read
+            Open.read(results)
+          end
+        end
+
+      }
+
+      pairs = text.split(/\n/).collect do |line|
+        label, features = line.split(" ")
+        model.add features, label
+      end
+
+      model.train
+
+      model = VectorModel.new(dir)
+      pairs = text.split(/\n/).collect do |line|
+        label, features = line.split(" ")
+        model.add features, label
+      end
+
+      assert model.eval("1;1;1").to_f > 0.5
+      assert model.eval("0;0;0").to_f < 0.5
+    end
+  end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-dm
 version: !ruby/object:Gem::Version
-  version: 1.1.47
+  version: 1.1.52
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-05-12 00:00:00.000000000 Z
+date: 2021-06-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -39,7 +39,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: priority_queue_cxx
+  name: priority_queue_cxx17
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -105,11 +105,18 @@ files:
 - lib/rbbt/statistics/hypergeometric.rb
 - lib/rbbt/statistics/random_walk.rb
 - lib/rbbt/statistics/rank_product.rb
+- lib/rbbt/tensorflow.rb
 - lib/rbbt/vector/model.rb
+- lib/rbbt/vector/model/spaCy.rb
 - lib/rbbt/vector/model/svm.rb
+- lib/rbbt/vector/model/tensorflow.rb
 - share/R/MA.R
 - share/R/barcode.R
 - share/R/heatmap.3.R
+- share/spaCy/cpu/textcat_accuracy.conf
+- share/spaCy/cpu/textcat_efficiency.conf
+- share/spaCy/gpu/textcat_accuracy.conf
+- share/spaCy/gpu/textcat_efficiency.conf
 - test/rbbt/matrix/test_barcode.rb
 - test/rbbt/network/test_paths.rb
 - test/rbbt/statistics/test_fdr.rb
@@ -118,7 +125,9 @@ files:
 - test/rbbt/statistics/test_random_walk.rb
 - test/rbbt/test_ml_task.rb
 - test/rbbt/test_stan.rb
+- test/rbbt/vector/model/test_spaCy.rb
 - test/rbbt/vector/model/test_svm.rb
+- test/rbbt/vector/model/test_tensorflow.rb
 - test/rbbt/vector/test_model.rb
 - test/test_helper.rb
 homepage: http://github.com/mikisvaz/rbbt-phgx
@@ -139,7 +148,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.6
+rubygems_version: 3.1.4
 signing_key: 
 specification_version: 4
 summary: Data-mining and statistics
@@ -152,6 +161,8 @@ test_files:
 - test/rbbt/statistics/test_hypergeometric.rb
 - test/rbbt/test_ml_task.rb
 - test/rbbt/vector/test_model.rb
+- test/rbbt/vector/model/test_spaCy.rb
+- test/rbbt/vector/model/test_tensorflow.rb
 - test/rbbt/vector/model/test_svm.rb
 - test/rbbt/test_stan.rb
 - test/test_helper.rb