see5 0.2.0 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +4 -4
- data/LICENSE +21 -0
- data/README.md +73 -9
- data/lib/see5.rb +24 -8
- data/lib/see5/model.rb +17 -0
- data/lib/see5/rule.rb +16 -2
- data/lib/see5/version.rb +1 -1
- data/see5.gemspec +2 -1
- metadata +9 -6
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a953b6bf5aafae7ae110f261e525e7b2421c39f517c56c885af0560ea0d7a3ec
|
4
|
+
data.tar.gz: 64e7f538405524d8fb5f900cd62a2acea92d42e38053f1ef527cd0108e448dc8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5b810bee1a216f3dd935d04e51287463b4a1e6b0b5186daf93c54140b9b02253dd14416617521800cca559925b4b09fd3bfa62b6ee955a76776b3e138596348f
|
7
|
+
data.tar.gz: f99d05053a2cc441a0efc1c49010c3880d577ded61dfadaee2f89caddc356082d35227eabf77c20af419b487c08a6c5c13536bca9036f2c172f51c9512797b34
|
data/Gemfile.lock
CHANGED
@@ -1,22 +1,22 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
see5 (0.
|
4
|
+
see5 (0.2.0)
|
5
5
|
|
6
6
|
GEM
|
7
7
|
remote: https://rubygems.org/
|
8
8
|
specs:
|
9
|
-
minitest (5.14.
|
9
|
+
minitest (5.14.4)
|
10
10
|
rake (13.0.1)
|
11
11
|
|
12
12
|
PLATFORMS
|
13
13
|
ruby
|
14
14
|
|
15
15
|
DEPENDENCIES
|
16
|
-
bundler (~>
|
16
|
+
bundler (~> 2.0)
|
17
17
|
minitest (~> 5.0)
|
18
18
|
rake (~> 13.0)
|
19
19
|
see5!
|
20
20
|
|
21
21
|
BUNDLED WITH
|
22
|
-
|
22
|
+
2.2.15
|
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2020-2021 Eddie Lebow <elebow@users.noreply.github.com>
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
#
|
1
|
+
# See5
|
2
2
|
|
3
3
|
A Ruby frontend for the See5/C5.0 family of classifiers and modellers. Builds models from Ruby objects.
|
4
4
|
|
@@ -7,27 +7,91 @@ A Ruby frontend for the See5/C5.0 family of classifiers and modellers. Builds mo
|
|
7
7
|
Add this line to your application's Gemfile:
|
8
8
|
|
9
9
|
```ruby
|
10
|
-
gem '
|
10
|
+
gem 'see5'
|
11
11
|
```
|
12
12
|
|
13
13
|
And then execute:
|
14
14
|
|
15
|
-
|
15
|
+
```
|
16
|
+
bundle
|
17
|
+
```
|
16
18
|
|
17
19
|
Or install it yourself as:
|
18
20
|
|
19
|
-
|
21
|
+
```
|
22
|
+
gem install see5
|
23
|
+
```
|
24
|
+
|
25
|
+
You may also wish to install the gem `see5-installer` to provide the required executables: <https://github.com/elebow/ruby-see5-installer>.
|
20
26
|
|
21
27
|
## Usage
|
22
28
|
|
23
|
-
|
29
|
+
### Training a classifier
|
30
|
+
|
31
|
+
The gem `see5-installer` must be installed, or `c5.0` must be available in the system path.
|
32
|
+
|
33
|
+
Input data must be an Enumerable of Hashes, OpenStructs, or ActiveModel-like objects—anything that responds to `#[]` or `#send(:attr_name)` for each attribute name.
|
34
|
+
|
35
|
+
The objects must respond to `#each` for automatic schema construction; otherwise, you will have to specify the schema.
|
36
|
+
|
37
|
+
```ruby
|
38
|
+
data = [
|
39
|
+
{ a: true, b: 5, c: "yellow" },
|
40
|
+
{ a: false, b: 6, c: "green" },
|
41
|
+
# ...
|
42
|
+
]
|
43
|
+
```
|
44
|
+
|
45
|
+
Train a classifier by calling `See5.train`. Pass in the data and the name of the class attribute.
|
46
|
+
|
47
|
+
```ruby
|
48
|
+
classifier = See5.train(data, class_attribute: :a)
|
49
|
+
```
|
50
|
+
|
51
|
+
Use the model to classify new records by calling `#classify`.
|
52
|
+
|
53
|
+
```ruby
|
54
|
+
classifier.classify(b: 5)
|
55
|
+
# => true
|
56
|
+
|
57
|
+
classifier.classify(b: 8, c: "green")
|
58
|
+
# => false
|
59
|
+
```
|
60
|
+
|
61
|
+
Inspect the classifier's rules with `#rules`.
|
62
|
+
|
63
|
+
```ruby
|
64
|
+
classifier.rules
|
65
|
+
```
|
24
66
|
|
25
|
-
|
67
|
+
### Dumping and loading a classifier
|
68
|
+
|
69
|
+
A model can be dumped to JSON, to be loaded and used later. Perhaps you want to run the classifier in a production system.
|
70
|
+
|
71
|
+
Loading and using a classifier does not have any dependencies outside the gem.
|
72
|
+
|
73
|
+
```ruby
|
74
|
+
File.write("classifier.json", classifier.to_json)
|
75
|
+
```
|
26
76
|
|
27
|
-
|
77
|
+
Load a classifier from a JSON string.
|
78
|
+
|
79
|
+
```ruby
|
80
|
+
classifier = See5::Model.from_json(json_string)
|
81
|
+
```
|
82
|
+
|
83
|
+
### Anomaly detection with GritBot
|
84
|
+
|
85
|
+
Anomaly detection uses the same input format as training a model. Call `See5.audit` to detect anomalies in the set.
|
86
|
+
|
87
|
+
The gem `see5-installer` must be installed, or `gritbot` must be available in the system path.
|
88
|
+
|
89
|
+
```ruby
|
90
|
+
anomalies = See5.audit(data, class_attribute: :a)
|
91
|
+
```
|
28
92
|
|
29
|
-
|
93
|
+
Anomalies are hashes.
|
30
94
|
|
31
95
|
## Contributing
|
32
96
|
|
33
|
-
Bug reports and pull requests are welcome on GitHub at https://github.com/elebow/ruby-see5
|
97
|
+
Bug reports and pull requests are welcome on GitHub at <https://github.com/elebow/ruby-see5>.
|
data/lib/see5.rb
CHANGED
@@ -1,5 +1,7 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
+
require "bundler"
|
4
|
+
|
3
5
|
require "see5/input_file_writer"
|
4
6
|
require "see5/model"
|
5
7
|
require "see5/rules_output_parser"
|
@@ -8,8 +10,8 @@ require "see5/schema"
|
|
8
10
|
require "see5/version"
|
9
11
|
|
10
12
|
module See5
|
11
|
-
def self.train(data, class_attribute)
|
12
|
-
prepare_tmp_files(data, class_attribute)
|
13
|
+
def self.train(data, class_attribute:)
|
14
|
+
prepare_tmp_files(data, class_attribute: class_attribute)
|
13
15
|
run_see5
|
14
16
|
|
15
17
|
output = See5::RulesOutputParser.parse_file("/tmp/ruby-see5.rules_output")
|
@@ -17,23 +19,37 @@ module See5
|
|
17
19
|
See5::Model.new(**output)
|
18
20
|
end
|
19
21
|
|
20
|
-
def self.audit(data, class_attribute)
|
21
|
-
prepare_tmp_files(data, class_attribute)
|
22
|
+
def self.audit(data, class_attribute:)
|
23
|
+
prepare_tmp_files(data, class_attribute: class_attribute)
|
22
24
|
run_gritbot
|
23
25
|
|
24
26
|
See5::GritbotOutputParser.parse_file("/tmp/ruby-see5.gritbot_output")
|
25
27
|
end
|
26
28
|
|
27
|
-
def self.prepare_tmp_files(data, class_attribute)
|
28
|
-
schema = See5::Schema.from_dataset(data, class_attribute)
|
29
|
+
def self.prepare_tmp_files(data, class_attribute:)
|
30
|
+
schema = See5::Schema.from_dataset(data, class_attribute: class_attribute)
|
29
31
|
See5::InputFileWriter.write_files(data: data, schema: schema)
|
30
32
|
end
|
31
33
|
|
32
34
|
def self.run_see5
|
33
|
-
system("
|
35
|
+
system("#{see5_executable} -f /tmp/ruby-see5 -r > /tmp/ruby-see5.rules_output")
|
34
36
|
end
|
35
37
|
|
36
38
|
def self.run_gritbot
|
37
|
-
system("
|
39
|
+
system("#{gritbot_executable} -s -f /tmp/ruby-see5 -r > /tmp/ruby-see5.gritbot_output")
|
40
|
+
end
|
41
|
+
|
42
|
+
private
|
43
|
+
|
44
|
+
private_class_method def self.see5_executable
|
45
|
+
@see5_executable ||= see5_installer_path ? "#{see5_installer_path}/ext/c5.0/c5.0" : "c5.0"
|
46
|
+
end
|
47
|
+
|
48
|
+
private_class_method def self.gritbot_executable
|
49
|
+
@gritbot_executable ||= see5_installer_path ? "#{see5_installer_path}/ext/gritbot/gritbot" : "gritbot"
|
50
|
+
end
|
51
|
+
|
52
|
+
private_class_method def self.see5_installer_path
|
53
|
+
@see5_installer_path ||= Bundler.rubygems.find_name("see5-installer").first&.full_gem_path
|
38
54
|
end
|
39
55
|
end
|
data/lib/see5/model.rb
CHANGED
@@ -1,5 +1,7 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
+
require "json"
|
4
|
+
|
3
5
|
module See5
|
4
6
|
class Model
|
5
7
|
attr_reader :rules
|
@@ -18,5 +20,20 @@ module See5
|
|
18
20
|
|
19
21
|
@default_classification
|
20
22
|
end
|
23
|
+
|
24
|
+
def to_h
|
25
|
+
{ default_classification: @default_classification,
|
26
|
+
rules: rules.map(&:to_h) }
|
27
|
+
end
|
28
|
+
|
29
|
+
def to_json
|
30
|
+
to_h.to_json
|
31
|
+
end
|
32
|
+
|
33
|
+
def self.from_json(json)
|
34
|
+
json_hash = JSON.parse(json, symbolize_names: true)
|
35
|
+
new(default_classification: json_hash[:default_classification],
|
36
|
+
rules: json_hash[:rules]&.map { |rule_hash| Rule.from_h(rule_hash) })
|
37
|
+
end
|
21
38
|
end
|
22
39
|
end
|
data/lib/see5/rule.rb
CHANGED
@@ -17,11 +17,25 @@ module See5
|
|
17
17
|
.all? { |matched| matched == true }
|
18
18
|
end
|
19
19
|
|
20
|
+
def to_h
|
21
|
+
{ rule_info: rule_info,
|
22
|
+
conditions: conditions,
|
23
|
+
classification: classification,
|
24
|
+
confidence: confidence }
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.from_h(h)
|
28
|
+
new(h[:rule_info],
|
29
|
+
h[:conditions],
|
30
|
+
{ classification: h[:classification],
|
31
|
+
confidence: h[:confidence] })
|
32
|
+
end
|
33
|
+
|
20
34
|
def to_s
|
21
35
|
[
|
22
36
|
"See5::Rule",
|
23
|
-
"@classification=#{
|
24
|
-
"@conditions=#{
|
37
|
+
"@classification=#{classification}",
|
38
|
+
"@conditions=#{conditions}"
|
25
39
|
]
|
26
40
|
.join(", ")
|
27
41
|
.yield_self { |s| "#<#{s}>" }
|
data/lib/see5/version.rb
CHANGED
data/see5.gemspec
CHANGED
@@ -13,6 +13,7 @@ Gem::Specification.new do |spec|
|
|
13
13
|
spec.summary = "A Ruby frontend for the See5/C5.0 family of classifiers and modellers."
|
14
14
|
#spec.description = "TODO: Write a longer description or delete this line."
|
15
15
|
spec.homepage = "https://github.com/elebow/ruby-see5"
|
16
|
+
spec.license = "MIT"
|
16
17
|
|
17
18
|
if spec.respond_to?(:metadata)
|
18
19
|
spec.metadata["homepage_uri"] = spec.homepage
|
@@ -32,7 +33,7 @@ Gem::Specification.new do |spec|
|
|
32
33
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
33
34
|
spec.require_paths = ["lib"]
|
34
35
|
|
35
|
-
spec.add_development_dependency "bundler", "~>
|
36
|
+
spec.add_development_dependency "bundler", "~> 2.0"
|
36
37
|
spec.add_development_dependency "minitest", "~> 5.0"
|
37
38
|
spec.add_development_dependency "rake", "~> 13.0"
|
38
39
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: see5
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Eddie Lebow
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2021-
|
11
|
+
date: 2021-03-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -16,14 +16,14 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '2.0'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '2.0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: minitest
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
@@ -63,6 +63,7 @@ files:
|
|
63
63
|
- ".rubocop.yml"
|
64
64
|
- Gemfile
|
65
65
|
- Gemfile.lock
|
66
|
+
- LICENSE
|
66
67
|
- README.md
|
67
68
|
- Rakefile
|
68
69
|
- lib/see5.rb
|
@@ -75,7 +76,8 @@ files:
|
|
75
76
|
- lib/see5/version.rb
|
76
77
|
- see5.gemspec
|
77
78
|
homepage: https://github.com/elebow/ruby-see5
|
78
|
-
licenses:
|
79
|
+
licenses:
|
80
|
+
- MIT
|
79
81
|
metadata:
|
80
82
|
homepage_uri: https://github.com/elebow/ruby-see5
|
81
83
|
source_code_uri: https://github.com/elebow/ruby-see5
|
@@ -95,7 +97,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
95
97
|
- !ruby/object:Gem::Version
|
96
98
|
version: '0'
|
97
99
|
requirements: []
|
98
|
-
|
100
|
+
rubyforge_project:
|
101
|
+
rubygems_version: 2.7.6.2
|
99
102
|
signing_key:
|
100
103
|
specification_version: 4
|
101
104
|
summary: A Ruby frontend for the See5/C5.0 family of classifiers and modellers.
|