rbbt-dm 1.1.58 → 1.1.59

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 286385d90b276d30cd5e1b21ae38c5e6a203e2ce3ac10673c434c19a2f45cfb1
-  data.tar.gz: 7879d74a364886ea8cb507be51c4979cfb598bdb273f948c3c3930a5dce199e6
+  metadata.gz: 1e001607266948a5221118c15d1fc95ed4266b0f8880b2fa628350d429ed3f7d
+  data.tar.gz: 1d56618e3039e1d99c8183aace2ae20e8cd3dafce0d574b5dbd49ce4f5a1ee14
 SHA512:
-  metadata.gz: b82c77bd736c8422e49c4dc83b63d6a91da6e76857af4b5cf5aff0a9a58b4147bc50b49b1b1534e8b07ca1bce5f6a5a673c5d688fb8cd7856623370d19fd1bda
-  data.tar.gz: 1b267a85ab600b878e99f414f725255cf086165a27f8cdec42ed83349b4f36bdb9e29615e0aaada9b30f098df8382e4778cebaf2b8649e17b8985e79d9b8bd23
+  metadata.gz: d8d324c664257cb142ae7363de776ea7b6e367cd14c22026018c00de335bc3e35be428d00dad6d84a61c3f0874057612d1379e6839b1cea6fc312ea5d8e9a699
+  data.tar.gz: b2e52024a63f3105ac88ca1b471df0b69fe91237a1e3fa70185fc519e0740421c58755eb3560003c9f4e4f60b6479bf449fca7596684e3badba46e4ec242feee

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

@@ -34,10 +34,12 @@ class SpaCyModel < VectorModel
       tmpconfig = File.join(file, 'config')
       tmptrain = File.join(file, 'train.spacy')
       SpaCy.config(@config, tmpconfig)
+
+      bar = bar(features.length, "Training documents into spacy format")
       SpaCyModel.spacy do
         nlp = SpaCy.nlp(lang)
         docs = []
-        RbbtPython.iterate nlp.pipe(texts.zip(labels), as_tuples: true), :bar => "Training documents into spacy format" do |doc,label|
+        RbbtPython.iterate nlp.pipe(texts.zip(labels), as_tuples: true), :bar => bar do |doc,label|
           unique_labels.each do |other_label|
             next if other_label == label
             doc.cats[other_label] = false
@@ -59,16 +61,22 @@ class SpaCyModel < VectorModel
       texts = [texts] unless list
 
       docs = []
+      bar = bar(features.length, "Evaluating model")
       SpaCyModel.spacy do
         nlp = spacy.load("#{file}/model-best")
 
-        Log::ProgressBar.with_bar texts.length, :desc => "Evaluating documents" do |bar|
-          texts.collect do |text|
-            cats = nlp.(text).cats
-            bar.tick
-            cats.sort_by{|l,v| v.to_f }.last.first
-          end
+        docs = nlp.pipe(texts)
+        RbbtPython.collect docs, :bar => bar do |d|
+          d.cats.sort_by{|l,v| v.to_f || 0 }.last.first
         end
+        #nlp.(docs).cats.collect{|cats| cats.sort_by{|l,v| v.to_f }.last.first }
+        #Log::ProgressBar.with_bar texts.length, :desc => "Evaluating documents" do |bar|
+        #  texts.collect do |text|
+        #    cats = nlp.(text).cats
+        #    bar.tick
+        #    cats.sort_by{|l,v| v.to_f }.last.first
+        #  end
+        #end
       end
     end
   end

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

@@ -0,0 +1,12 @@
+class VectorModel
+  attr_accessor :bar
+
+  def bar(max = nil, desc = nil)
+    desc, max = max, nil if desc.nil?
+    @bar ||= Log::ProgressBar.new max
+    @bar.desc = desc
+    @bar.max = max
+    @bar.init
+    @bar
+  end
+end

data/lib/rbbt/vector/model.rb

@@ -1,4 +1,5 @@
 require 'rbbt/util/R'
+require 'rbbt/vector/model/util'
 
 class VectorModel
   attr_accessor :directory, :model_file, :extract_features, :train_model, :eval_model

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

@@ -96,14 +96,16 @@ class TestSpaCyModel < Test::Unit::TestCase
 
       model = SpaCyModel.new(
         dir, 
-        "gpu/textcat_accuracy.conf"
+        "cpu/textcat_efficiency.conf"
       )
 
 
+      Rbbt::Config.set 'gpu_id', nil, :spacy
       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
+      tsv = tsv.subset(tsv.keys.sample(100))
 
       good = tsv.select("Recommended IND" => '1')
       bad = tsv.select("Recommended IND" => '0')

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-dm
 version: !ruby/object:Gem::Version
-  version: 1.1.58
+  version: 1.1.59
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-07-19 00:00:00.000000000 Z
+date: 2022-07-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -111,6 +111,7 @@ files:
 - lib/rbbt/vector/model/spaCy.rb
 - lib/rbbt/vector/model/svm.rb
 - lib/rbbt/vector/model/tensorflow.rb
+- lib/rbbt/vector/model/util.rb
 - share/R/MA.R
 - share/R/barcode.R
 - share/R/heatmap.3.R