rbbt-dm 1.1.50 → 1.1.51

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2efbfe29d382655f78a91a1e8e381a304f4610f2d13d6d7c5fae8be40a22aa29
-  data.tar.gz: cee71dc48458dad863d6cc04bf8d1c113430e3f78309dac4cad1d575d9f4b198
+  metadata.gz: 5327d1c2a46283b95fa380a73be418cf7e5a3afd2aca6002bd9ca591ab3f6df8
+  data.tar.gz: 1066345322e342c8f642b89825c1a8555c6bfa1d09985705d1b382654d91653f
 SHA512:
-  metadata.gz: 953cf89ffc4a04e38aff7020bd25d8ab8db5a6383db3a9a9fce5e7bab3bc668a763d660953bdbeedfc9d32beaacc6e83142c773dac6663b118c3a02c58405611
-  data.tar.gz: c899b27449bb378c9c757438aed976d5375e8d49bb99edf80ff7dbf9f2b03adeac9ec2000aa35bed4206b13e399f025e326952e35acfaefe04d1e5612597367f
+  metadata.gz: c1a3cf2ec93909993b290c7c6cb0b6e9c6090155657403c705b93b74a538cbe91ff23dead14c33453dde0c31ba681099b3e5c93f2699a471c19c299b43d0f304
+  data.tar.gz: e5b456330625bb57a494fb9e5fc9757e96c134da8f410fabe8f7e9d06169d09f0c4fa3c7e5a375870e6f45b8f5ffdf7855b8260719fb1a32846a2f24c18e8853

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

@@ -51,7 +51,8 @@ class SpaCyModel < VectorModel
         doc_bin.to_disk(tmptrain)
       end
 
-      CMD.cmd_log(:spacy, "train #{tmpconfig} --output #{file} --paths.train #{tmptrain} --paths.dev #{tmptrain}")
+      gpu = Rbbt::Config.get('gpu_id', :spacy, :spacy_train)
+      CMD.cmd_log(:spacy, "train #{tmpconfig} --output #{file} --paths.train #{tmptrain} --paths.dev #{tmptrain}",  "--gpu-id" => gpu)
     end
  
     @eval_model = Proc.new do |file, features|

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

@@ -37,7 +37,7 @@ class TestSpaCyModel < Test::Unit::TestCase
       model.cross_validation
     end
 
-    def _test_svm_spacy
+    def test_svm_spacy
 
       require 'rbbt/tsv/csv'
       url = "https://raw.githubusercontent.com/hanzhang0420/Women-Clothing-E-commerce/master/Womens%20Clothing%20E-Commerce%20Reviews.csv"
@@ -84,5 +84,38 @@ class TestSpaCyModel < Test::Unit::TestCase
     end
   end
 
+  def test_spyCy_trf
+    TmpFile.with_file() do |dir|
+      Log.severity = 0
+      FileUtils.mkdir_p dir
+
+      model = SpaCyModel.new(
+        dir, 
+        "gpu/textcat_accuracy.conf"
+      )
+
+
+      require 'rbbt/tsv/csv'
+      url = "https://raw.githubusercontent.com/hanzhang0420/Women-Clothing-E-commerce/master/Womens%20Clothing%20E-Commerce%20Reviews.csv"
+      tsv = TSV.csv(Open.open(url))
+      tsv = tsv.reorder("Review Text", ["Recommended IND"]).to_single
+
+      good = tsv.select("Recommended IND" => '1')
+      bad = tsv.select("Recommended IND" => '0')
+
+      gsize = 2000
+      bsize = 500
+      good.keys[0..gsize-1].each do |text|
+        next if text.nil? || text.empty?
+        model.add text, '1'
+      end
+
+      bad.keys[0..bsize-1].each do |text|
+        model.add text, '0'
+      end
+
+      model.cross_validation
+    end
+  end
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-dm
 version: !ruby/object:Gem::Version
-  version: 1.1.50
+  version: 1.1.51
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-06-17 00:00:00.000000000 Z
+date: 2021-06-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util