green_midget 0.1.1 → 0.1.2
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.
- data/README.md +1 -1
- data/lib/green_midget/version.rb +1 -1
- metadata +3 -4
- data/benchmark/test.rb +0 -33
data/README.md
CHANGED
|
@@ -179,7 +179,7 @@ It's only trained on the word occurrences of a total of 9000 messages (4500 of
|
|
|
179
179
|
each spam and ham).
|
|
180
180
|
|
|
181
181
|
During the development tests at SoundCloud, with those features in place, we
|
|
182
|
-
achieved more than 98% correct classification of spam
|
|
182
|
+
achieved more than 98% correct classification of spam objects using GreenMidget.
|
|
183
183
|
|
|
184
184
|
Thanks
|
|
185
185
|
----------
|
data/lib/green_midget/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: green_midget
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.2
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -14,7 +14,7 @@ default_executable:
|
|
|
14
14
|
dependencies:
|
|
15
15
|
- !ruby/object:Gem::Dependency
|
|
16
16
|
name: activerecord
|
|
17
|
-
requirement: &
|
|
17
|
+
requirement: &2153290480 !ruby/object:Gem::Requirement
|
|
18
18
|
none: false
|
|
19
19
|
requirements:
|
|
20
20
|
- - ! '>='
|
|
@@ -22,7 +22,7 @@ dependencies:
|
|
|
22
22
|
version: '0'
|
|
23
23
|
type: :runtime
|
|
24
24
|
prerelease: false
|
|
25
|
-
version_requirements: *
|
|
25
|
+
version_requirements: *2153290480
|
|
26
26
|
description: Naive Bayesian Classifier with customizable features
|
|
27
27
|
email:
|
|
28
28
|
- nikola@howkul.info
|
|
@@ -39,7 +39,6 @@ files:
|
|
|
39
39
|
- README.md
|
|
40
40
|
- Rakefile
|
|
41
41
|
- benchmark/benchmark.rb
|
|
42
|
-
- benchmark/test.rb
|
|
43
42
|
- bin/greenmidget
|
|
44
43
|
- green_midget.gemspec
|
|
45
44
|
- lib/green_midget.rb
|
data/benchmark/test.rb
DELETED
|
@@ -1,33 +0,0 @@
|
|
|
1
|
-
# This is a cross validation script
|
|
2
|
-
# TODO: move it to a rake task
|
|
3
|
-
require 'sqlite3'
|
|
4
|
-
|
|
5
|
-
require File.join(File.dirname(__FILE__), '..', 'spec', 'tester')
|
|
6
|
-
include GreenMidget
|
|
7
|
-
|
|
8
|
-
ActiveRecord::Base.establish_connection(:adapter => 'sqlite3', :database => '~/sc/user_backup/data.db')
|
|
9
|
-
|
|
10
|
-
@spam = [ 'messages', 'comments', 'posts' ].map { |table| ActiveRecord::Base.connection.execute("select body from #{table} limit 1500").inject([]) { |memo, hash| memo << hash["body"] } }
|
|
11
|
-
|
|
12
|
-
ActiveRecord::Base.establish_connection(:adapter => 'mysql', :username => 'root', :password => 'root', :database => 'soundcloud_development_temp')
|
|
13
|
-
|
|
14
|
-
@ham = [ 'messages', 'comments', 'posts' ].map { |table| Records.find_by_sql("select body from #{table} limit 1500").to_a.inject([]) { |memo, hash| memo << hash["body"] } }
|
|
15
|
-
|
|
16
|
-
ActiveRecord::Base.establish_connection(:adapter => 'mysql', :username => 'root', :password => 'root', :database => 'classifier_development_weird')
|
|
17
|
-
#
|
|
18
|
-
# # ------ I. PERFORM TRAINING
|
|
19
|
-
# puts Benchmark.measure {
|
|
20
|
-
# @spam.each { |src|
|
|
21
|
-
# src.each {|body|
|
|
22
|
-
# klass = Tester.new(body);klass.classify_as! :spam
|
|
23
|
-
# }
|
|
24
|
-
# };true
|
|
25
|
-
# }
|
|
26
|
-
#
|
|
27
|
-
# puts Benchmark.measure {
|
|
28
|
-
# @ham.each { |src|
|
|
29
|
-
# src.each {|body|
|
|
30
|
-
# klass = Tester.new(body);klass.classify_as! :ham
|
|
31
|
-
# }
|
|
32
|
-
# };true
|
|
33
|
-
# }
|