gender_machine 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +14 -0
- data/.ruby-version +1 -0
- data/Gemfile +3 -0
- data/LICENSE.txt +28 -0
- data/README.md +49 -0
- data/Rakefile +5 -0
- data/gender_machine.gemspec +27 -0
- data/lib/gender_machine.rb +11 -0
- data/lib/gender_machine/core.rb +46 -0
- data/lib/gender_machine/nam_dict.txt +48890 -0
- data/lib/gender_machine/name.rb +81 -0
- data/lib/gender_machine/predictor.rb +32 -0
- data/lib/gender_machine/version.rb +3 -0
- metadata +142 -0
@@ -0,0 +1,81 @@
|
|
1
|
+
module GenderMachine
|
2
|
+
class Name
|
3
|
+
include MooseX
|
4
|
+
GENDER_TRANSFORM = ->(value) do
|
5
|
+
# Ordered based roughly on frequency w/ some tweaking
|
6
|
+
# formula: NAME_ROWS.map(&:first).each_with_object({}) { |v, obj| obj[v] ||= 0; obj[v] += 1 }
|
7
|
+
# Following comment is part of datafile & licensed under GPLv1.2 or later
|
8
|
+
# Syntax for "normal" name list (do not change): $
|
9
|
+
# $
|
10
|
+
# M <male first name> $
|
11
|
+
# 1M <male name, if first part of name; $
|
12
|
+
# else: mostly male name> $
|
13
|
+
# ?M <mostly male name (= unisex name, which is mostly male)> $
|
14
|
+
# $
|
15
|
+
# F <female first name> $
|
16
|
+
# 1F <female name, if first part of name; $
|
17
|
+
# else: mostly female name> $
|
18
|
+
# ?F <mostly female name (= unisex name, which is mostly female)> $
|
19
|
+
# $
|
20
|
+
# ? <unisex name (= can be male or female)> $
|
21
|
+
# Author of GenderMachine chose to map those names in order to:
|
22
|
+
# :male
|
23
|
+
# :probably_male
|
24
|
+
# :possibly_male
|
25
|
+
# :female
|
26
|
+
# :probably_female
|
27
|
+
# :possibly_female
|
28
|
+
# :non_gendered
|
29
|
+
case value
|
30
|
+
when "F" then :female
|
31
|
+
when "M" then :male
|
32
|
+
when "?F" then :possibly_female
|
33
|
+
when "?" then :non_gendered
|
34
|
+
when "?M" then :possibly_male
|
35
|
+
when "1F" then :probably_female
|
36
|
+
when "1M" then :probably_male
|
37
|
+
when "=" then nil # special case, names are equivalent
|
38
|
+
else :unknown
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
FREQUENCY_TRANSFORM = ->(value) do
|
43
|
+
begin
|
44
|
+
index = value.index(/[\dA-D]/)
|
45
|
+
# end_index = index + 6
|
46
|
+
# output = value[index..end_index].scan(/../).map do |pair|
|
47
|
+
# pair.hex.chr.to_i
|
48
|
+
# end.inject(:+)
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
has gender: {
|
53
|
+
is: :rw,
|
54
|
+
default: -> { :unknown },
|
55
|
+
coerce: GENDER_TRANSFORM,
|
56
|
+
}
|
57
|
+
|
58
|
+
has [:name, :raw], {is: :rw}
|
59
|
+
has frequency_string: {is: :rw, isa: String}
|
60
|
+
|
61
|
+
def frequency
|
62
|
+
# TODO: implement
|
63
|
+
end
|
64
|
+
|
65
|
+
def frequency_index
|
66
|
+
FREQUENCY_TRANSFORM.call(frequency_string)
|
67
|
+
end
|
68
|
+
|
69
|
+
def country
|
70
|
+
COUNTRY_MAP_NUMERIC[frequency_index]
|
71
|
+
end
|
72
|
+
|
73
|
+
def simplistic_gender
|
74
|
+
case gender.to_s
|
75
|
+
when /female/i then :female
|
76
|
+
when /male/i then :male
|
77
|
+
else :non_gendered
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
module GenderMachine
|
2
|
+
class Predictor
|
3
|
+
include Anima.new(:name)
|
4
|
+
|
5
|
+
NULL_NAME = OpenStruct.new(gender: "",
|
6
|
+
name: "",
|
7
|
+
frequency_string: "",
|
8
|
+
raw: "")
|
9
|
+
def name_match_block
|
10
|
+
->(obj){ obj.name == name }
|
11
|
+
end
|
12
|
+
|
13
|
+
def ensure_default_response(default)
|
14
|
+
response = yield
|
15
|
+
response || default
|
16
|
+
end
|
17
|
+
|
18
|
+
def find(name = name)
|
19
|
+
Core::NAMES.select(&name_match_block)
|
20
|
+
end
|
21
|
+
|
22
|
+
def first(name = name)
|
23
|
+
ensure_default_response(NULL_NAME) do
|
24
|
+
Core::NAMES.detect(&name_match_block)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def where
|
29
|
+
# TODO:
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
metadata
ADDED
@@ -0,0 +1,142 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: gender_machine
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Zander Hill
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-11-13 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: anima
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: moosex
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: require_all
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry-uber
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: bundler
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '1.7'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '1.7'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rake
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '10.0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '10.0'
|
97
|
+
description: Make sweeping, broad stroked predictions about gender based on name.
|
98
|
+
email:
|
99
|
+
- zander@xargs.io
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".gitignore"
|
105
|
+
- ".ruby-version"
|
106
|
+
- Gemfile
|
107
|
+
- LICENSE.txt
|
108
|
+
- README.md
|
109
|
+
- Rakefile
|
110
|
+
- gender_machine.gemspec
|
111
|
+
- lib/gender_machine.rb
|
112
|
+
- lib/gender_machine/core.rb
|
113
|
+
- lib/gender_machine/nam_dict.txt
|
114
|
+
- lib/gender_machine/name.rb
|
115
|
+
- lib/gender_machine/predictor.rb
|
116
|
+
- lib/gender_machine/version.rb
|
117
|
+
homepage: https://github.com/zph/gender_machine
|
118
|
+
licenses:
|
119
|
+
- MIT
|
120
|
+
metadata: {}
|
121
|
+
post_install_message:
|
122
|
+
rdoc_options: []
|
123
|
+
require_paths:
|
124
|
+
- lib
|
125
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
126
|
+
requirements:
|
127
|
+
- - ">="
|
128
|
+
- !ruby/object:Gem::Version
|
129
|
+
version: '0'
|
130
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
131
|
+
requirements:
|
132
|
+
- - ">="
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
version: '0'
|
135
|
+
requirements: []
|
136
|
+
rubyforge_project:
|
137
|
+
rubygems_version: 2.4.2
|
138
|
+
signing_key:
|
139
|
+
specification_version: 4
|
140
|
+
summary: Make sweeping, broad stroked predictions about gender based on name.
|
141
|
+
test_files: []
|
142
|
+
has_rdoc:
|