scoruby 0.2.8 → 0.2.9
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/Gemfile.lock +1 -1
- data/lib/scoruby/models/random_forest/data.rb +45 -0
- data/lib/scoruby/models/random_forest/model.rb +44 -0
- data/lib/scoruby/models_factory.rb +2 -2
- data/lib/scoruby/predicates/simple_set_predicate.rb +1 -1
- data/lib/scoruby/version.rb +1 -1
- metadata +5 -5
- data/lib/scoruby/models/random_forest.rb +0 -45
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 3af72ce9c41b6f116e34af71b5ad3264d8043c6fd1aaa3544a0a362bff096c0f
|
4
|
+
data.tar.gz: de77039296cfd39f2ef036372e90ad2b4028180381a153380d77164ccf02a743
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: c827de777f0b1b0d83af165a6079a6a2cff83d2612758c78171328cc2811cf718532fef6ff628a04a38f6ef9179c60dae529ee70a7daa90e5aed0e38462cf370
|
7
|
+
data.tar.gz: eff6fcc12bbe064b5a1af1a272c8b544af87c8ae9aa48e7f59a506abcaf292d3b72a235c835caec524eb5ae04a66e2f37ca12691735ce9c1bda19489c1fff385
|
data/Gemfile.lock
CHANGED
@@ -0,0 +1,45 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Scoruby
|
4
|
+
module Models
|
5
|
+
module RandomForest
|
6
|
+
class Data
|
7
|
+
RF_FOREST_XPATH = 'PMML/MiningModel/Segmentation/Segment'
|
8
|
+
FEATURES_XPATH = 'PMML/DataDictionary/DataField'
|
9
|
+
|
10
|
+
def initialize(xml)
|
11
|
+
@xml = xml
|
12
|
+
end
|
13
|
+
|
14
|
+
def decision_trees
|
15
|
+
@xml.xpath(RF_FOREST_XPATH).map do |xml_tree|
|
16
|
+
DecisionTree.new(xml_tree)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def categorical_features
|
21
|
+
categorical_predicates.each_with_object(Hash.new([])) do |xml, res|
|
22
|
+
predicate = Predicates::SimpleSetPredicate.new(xml)
|
23
|
+
res[predicate.field] = res[predicate.field] | predicate.array
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
def continuous_features
|
28
|
+
continuous_predicates.map do |xml|
|
29
|
+
Predicates::SimplePredicate.new(xml).field
|
30
|
+
end.uniq
|
31
|
+
end
|
32
|
+
|
33
|
+
private
|
34
|
+
|
35
|
+
def categorical_predicates
|
36
|
+
@xml.xpath('//SimpleSetPredicate')
|
37
|
+
end
|
38
|
+
|
39
|
+
def continuous_predicates
|
40
|
+
@xml.xpath('//SimplePredicate')
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'scoruby/models/random_forest/data'
|
4
|
+
|
5
|
+
module Scoruby
|
6
|
+
module Models
|
7
|
+
module RandomForest
|
8
|
+
class Model
|
9
|
+
def initialize(xml)
|
10
|
+
@decision_trees = Data.new(xml).decision_trees
|
11
|
+
end
|
12
|
+
|
13
|
+
def predict(features)
|
14
|
+
decisions_count = decisions_count(features)
|
15
|
+
decision = decisions_count.max_by { |_, v| v }
|
16
|
+
{
|
17
|
+
label: decision[0],
|
18
|
+
score: decision[1] / decisions_count.values.reduce(0, :+).to_f
|
19
|
+
}
|
20
|
+
end
|
21
|
+
|
22
|
+
def decisions_count(features)
|
23
|
+
formatted_features = Features.new(features).formatted
|
24
|
+
decisions = traverse_trees(formatted_features)
|
25
|
+
aggregate_decisions(decisions)
|
26
|
+
end
|
27
|
+
|
28
|
+
private
|
29
|
+
|
30
|
+
def traverse_trees(formatted_features)
|
31
|
+
@decision_trees.map do |decision_tree|
|
32
|
+
decision_tree.decide(formatted_features).score
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
def aggregate_decisions(decisions)
|
37
|
+
decisions.each_with_object(Hash.new(0)) do |score, counts|
|
38
|
+
counts[score] += 1
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -2,7 +2,7 @@
|
|
2
2
|
|
3
3
|
require 'scoruby/models/decision_tree'
|
4
4
|
require 'scoruby/models/gbm'
|
5
|
-
require 'scoruby/models/random_forest'
|
5
|
+
require 'scoruby/models/random_forest/model'
|
6
6
|
require 'scoruby/models/naive_bayes/model'
|
7
7
|
|
8
8
|
module Scoruby
|
@@ -12,7 +12,7 @@ module Scoruby
|
|
12
12
|
MODEL_NOT_SUPPORTED_ERROR = 'model not supported'
|
13
13
|
|
14
14
|
def self.factory_for(xml)
|
15
|
-
return Models::RandomForest.new(xml) if random_forest?(xml)
|
15
|
+
return Models::RandomForest::Model.new(xml) if random_forest?(xml)
|
16
16
|
return Models::Gbm.new(xml) if gbm?(xml)
|
17
17
|
return Models::DecisionTree.new(xml.child) if decision_tree?(xml)
|
18
18
|
return Models::NaiveBayes::Model.new(xml) if naive_bayes?(xml)
|
data/lib/scoruby/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scoruby
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.9
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Asaf Schers
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-12-
|
11
|
+
date: 2017-12-29 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -134,7 +134,8 @@ files:
|
|
134
134
|
- lib/scoruby/models/gbm.rb
|
135
135
|
- lib/scoruby/models/naive_bayes/model.rb
|
136
136
|
- lib/scoruby/models/naive_bayes/model_data.rb
|
137
|
-
- lib/scoruby/models/random_forest.rb
|
137
|
+
- lib/scoruby/models/random_forest/data.rb
|
138
|
+
- lib/scoruby/models/random_forest/model.rb
|
138
139
|
- lib/scoruby/models_factory.rb
|
139
140
|
- lib/scoruby/node.rb
|
140
141
|
- lib/scoruby/predicate_factory.rb
|
@@ -168,9 +169,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
168
169
|
version: '0'
|
169
170
|
requirements: []
|
170
171
|
rubyforge_project:
|
171
|
-
rubygems_version: 2.
|
172
|
+
rubygems_version: 2.7.3
|
172
173
|
signing_key:
|
173
174
|
specification_version: 4
|
174
175
|
summary: Ruby Scoring API for PMML.
|
175
176
|
test_files: []
|
176
|
-
has_rdoc:
|
@@ -1,45 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
module Scoruby
|
4
|
-
module Models
|
5
|
-
class RandomForest
|
6
|
-
RF_FOREST_XPATH = 'PMML/MiningModel/Segmentation/Segment'
|
7
|
-
|
8
|
-
def initialize(xml)
|
9
|
-
xml_trees = xml.xpath(RF_FOREST_XPATH)
|
10
|
-
@decision_trees = xml_trees.map do |xml_tree|
|
11
|
-
DecisionTree.new(xml_tree)
|
12
|
-
end
|
13
|
-
end
|
14
|
-
|
15
|
-
def predict(features)
|
16
|
-
decisions_count = decisions_count(features)
|
17
|
-
decision = decisions_count.max_by { |_, v| v }
|
18
|
-
{
|
19
|
-
label: decision[0],
|
20
|
-
score: decision[1] / decisions_count.values.reduce(0, :+).to_f
|
21
|
-
}
|
22
|
-
end
|
23
|
-
|
24
|
-
def decisions_count(features)
|
25
|
-
formatted_features = Features.new(features).formatted
|
26
|
-
decisions = traverse_trees(formatted_features)
|
27
|
-
aggregate_decisions(decisions)
|
28
|
-
end
|
29
|
-
|
30
|
-
private
|
31
|
-
|
32
|
-
def traverse_trees(formatted_features)
|
33
|
-
@decision_trees.map do |decision_tree|
|
34
|
-
decision_tree.decide(formatted_features).score
|
35
|
-
end
|
36
|
-
end
|
37
|
-
|
38
|
-
def aggregate_decisions(decisions)
|
39
|
-
decisions.each_with_object(Hash.new(0)) do |score, counts|
|
40
|
-
counts[score] += 1
|
41
|
-
end
|
42
|
-
end
|
43
|
-
end
|
44
|
-
end
|
45
|
-
end
|