twitter_ebooks 2.3.2 → 3.0.0
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 +4 -4
- data/.gitignore +2 -0
- data/.travis.yml +7 -0
- data/README.md +60 -30
- data/bin/ebooks +239 -117
- data/lib/twitter_ebooks.rb +2 -2
- data/lib/twitter_ebooks/archive.rb +12 -9
- data/lib/twitter_ebooks/bot.rb +343 -109
- data/lib/twitter_ebooks/model.rb +104 -22
- data/lib/twitter_ebooks/nlp.rb +46 -13
- data/lib/twitter_ebooks/suffix.rb +9 -1
- data/lib/twitter_ebooks/version.rb +1 -1
- data/skeleton/Gemfile +1 -1
- data/skeleton/Procfile +1 -1
- data/skeleton/bots.rb +35 -22
- data/spec/bot_spec.rb +178 -0
- data/spec/model_spec.rb +18 -2
- data/twitter_ebooks.gemspec +7 -3
- metadata +72 -20
- data/lib/twitter_ebooks/markov.rb +0 -82
- data/skeleton/run.rb +0 -9
- data/test/corpus/0xabad1dea.tweets +0 -14696
- data/test/keywords.rb +0 -18
- data/test/tokenize.rb +0 -18
data/test/keywords.rb
DELETED
|
@@ -1,18 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env ruby
|
|
2
|
-
# encoding: utf-8
|
|
3
|
-
|
|
4
|
-
require 'twitter_ebooks'
|
|
5
|
-
require 'minitest/autorun'
|
|
6
|
-
require 'benchmark'
|
|
7
|
-
|
|
8
|
-
module Ebooks
|
|
9
|
-
class TestKeywords < Minitest::Test
|
|
10
|
-
corpus = NLP.normalize(File.read(ARGV[0]))
|
|
11
|
-
puts "Finding and ranking keywords"
|
|
12
|
-
puts Benchmark.measure {
|
|
13
|
-
NLP.keywords(corpus).top(50).each do |keyword|
|
|
14
|
-
puts "#{keyword.text} #{keyword.weight}"
|
|
15
|
-
end
|
|
16
|
-
}
|
|
17
|
-
end
|
|
18
|
-
end
|
data/test/tokenize.rb
DELETED
|
@@ -1,18 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env ruby
|
|
2
|
-
# encoding: utf-8
|
|
3
|
-
|
|
4
|
-
require 'twitter_ebooks'
|
|
5
|
-
require 'minitest/autorun'
|
|
6
|
-
|
|
7
|
-
module Ebooks
|
|
8
|
-
class TestTokenize < Minitest::Test
|
|
9
|
-
corpus = NLP.normalize(File.read(TEST_CORPUS_PATH))
|
|
10
|
-
sents = NLP.sentences(corpus).sample(10)
|
|
11
|
-
|
|
12
|
-
NLP.sentences(corpus).sample(10).each do |sent|
|
|
13
|
-
p sent
|
|
14
|
-
p NLP.tokenize(sent)
|
|
15
|
-
puts
|
|
16
|
-
end
|
|
17
|
-
end
|
|
18
|
-
end
|