rbbt-dm 1.1.50 → 1.1.51

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 2efbfe29d382655f78a91a1e8e381a304f4610f2d13d6d7c5fae8be40a22aa29
4
- data.tar.gz: cee71dc48458dad863d6cc04bf8d1c113430e3f78309dac4cad1d575d9f4b198
3
+ metadata.gz: 5327d1c2a46283b95fa380a73be418cf7e5a3afd2aca6002bd9ca591ab3f6df8
4
+ data.tar.gz: 1066345322e342c8f642b89825c1a8555c6bfa1d09985705d1b382654d91653f
5
5
  SHA512:
6
- metadata.gz: 953cf89ffc4a04e38aff7020bd25d8ab8db5a6383db3a9a9fce5e7bab3bc668a763d660953bdbeedfc9d32beaacc6e83142c773dac6663b118c3a02c58405611
7
- data.tar.gz: c899b27449bb378c9c757438aed976d5375e8d49bb99edf80ff7dbf9f2b03adeac9ec2000aa35bed4206b13e399f025e326952e35acfaefe04d1e5612597367f
6
+ metadata.gz: c1a3cf2ec93909993b290c7c6cb0b6e9c6090155657403c705b93b74a538cbe91ff23dead14c33453dde0c31ba681099b3e5c93f2699a471c19c299b43d0f304
7
+ data.tar.gz: e5b456330625bb57a494fb9e5fc9757e96c134da8f410fabe8f7e9d06169d09f0c4fa3c7e5a375870e6f45b8f5ffdf7855b8260719fb1a32846a2f24c18e8853
@@ -51,7 +51,8 @@ class SpaCyModel < VectorModel
51
51
  doc_bin.to_disk(tmptrain)
52
52
  end
53
53
 
54
- CMD.cmd_log(:spacy, "train #{tmpconfig} --output #{file} --paths.train #{tmptrain} --paths.dev #{tmptrain}")
54
+ gpu = Rbbt::Config.get('gpu_id', :spacy, :spacy_train)
55
+ CMD.cmd_log(:spacy, "train #{tmpconfig} --output #{file} --paths.train #{tmptrain} --paths.dev #{tmptrain}", "--gpu-id" => gpu)
55
56
  end
56
57
 
57
58
  @eval_model = Proc.new do |file, features|
@@ -37,7 +37,7 @@ class TestSpaCyModel < Test::Unit::TestCase
37
37
  model.cross_validation
38
38
  end
39
39
 
40
- def _test_svm_spacy
40
+ def test_svm_spacy
41
41
 
42
42
  require 'rbbt/tsv/csv'
43
43
  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
84
84
  end
85
85
  end
86
86
 
87
+ def test_spyCy_trf
88
+ TmpFile.with_file() do |dir|
89
+ Log.severity = 0
90
+ FileUtils.mkdir_p dir
91
+
92
+ model = SpaCyModel.new(
93
+ dir,
94
+ "gpu/textcat_accuracy.conf"
95
+ )
96
+
97
+
98
+ require 'rbbt/tsv/csv'
99
+ url = "https://raw.githubusercontent.com/hanzhang0420/Women-Clothing-E-commerce/master/Womens%20Clothing%20E-Commerce%20Reviews.csv"
100
+ tsv = TSV.csv(Open.open(url))
101
+ tsv = tsv.reorder("Review Text", ["Recommended IND"]).to_single
102
+
103
+ good = tsv.select("Recommended IND" => '1')
104
+ bad = tsv.select("Recommended IND" => '0')
105
+
106
+ gsize = 2000
107
+ bsize = 500
108
+ good.keys[0..gsize-1].each do |text|
109
+ next if text.nil? || text.empty?
110
+ model.add text, '1'
111
+ end
112
+
113
+ bad.keys[0..bsize-1].each do |text|
114
+ model.add text, '0'
115
+ end
116
+
117
+ model.cross_validation
118
+ end
119
+ end
87
120
  end
88
121
 
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: rbbt-dm
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.1.50
4
+ version: 1.1.51
5
5
  platform: ruby
6
6
  authors:
7
7
  - Miguel Vazquez
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2021-06-17 00:00:00.000000000 Z
11
+ date: 2021-06-23 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: rbbt-util