psych_analyzer 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +22 -0
- data/README.md +36 -0
- data/Rakefile +1 -0
- data/ignored_keywords.csv +2 -0
- data/lib/psych_analyzer.rb +107 -0
- data/lib/psych_analyzer/version.rb +3 -0
- data/psych_analyzer.gemspec +19 -0
- data/psych_dictionary.csv +6 -0
- metadata +55 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Ramy Khater
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# PsychAnalyzer
|
2
|
+
|
3
|
+
PsychAnalyzer creates a psychological profile of any content given based on provided dictionary contains the categories and its keywords that fits with your needs.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'psych_analyzer'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install psych_analyzer
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
1. require 'psych_analyzer'
|
22
|
+
2. paths = {"dictionary" => "psych_dictionary.csv", "ignored_keywords" => "ignored_keywords.csv"}
|
23
|
+
3. input = ["I love this car.","This view is amazing.","I feel great this morning.","I am so excited about the concert.","He is my best friend.","I do not like this car.","This view is horrible.","I feel tired this morning.","I am not looking forward to the concert.","He is my enemy.", "that is so good"]
|
24
|
+
4. PsychAnalyzer.train paths
|
25
|
+
5. psychological_profile = PsychAnalyzer.analyze input
|
26
|
+
6. puts psychological_profile
|
27
|
+
|
28
|
+
=> {"positive"=>63.64, "negative"=>36.36}
|
29
|
+
|
30
|
+
## Contributing
|
31
|
+
|
32
|
+
1. Fork it
|
33
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
34
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
35
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
36
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,107 @@
|
|
1
|
+
require "psych_analyzer/version"
|
2
|
+
require "memcache"
|
3
|
+
module PsychAnalyzer
|
4
|
+
|
5
|
+
@cache = Memcache.new(:server => 'localhost:11211', :native => true, :segment_large_values => true)
|
6
|
+
@ignored_words = Array.new()
|
7
|
+
@dictionary = Hash.new
|
8
|
+
|
9
|
+
def self.train(trainingFiles)
|
10
|
+
trainingData = {"dictionary"=>Array.new(), "ignored_words"=>Array.new()}
|
11
|
+
unless !@cache.get('trainingData').nil?
|
12
|
+
# initialize/read dictionary file
|
13
|
+
dictionary_file = File.new(trainingFiles["dictionary"], 'r')
|
14
|
+
dictionary_class = String.new("")
|
15
|
+
dictionary_class_words = Array.new()
|
16
|
+
# build dictionary array
|
17
|
+
dictionary_file.each_line("\n") do |row|
|
18
|
+
# set dictionary classes key
|
19
|
+
unless !row.include?('#')
|
20
|
+
dictionary_class = row.sub!('#', '').sub!("\n", '')
|
21
|
+
@dictionary[dictionary_class] = Array.new
|
22
|
+
end
|
23
|
+
# assign class keywords of each dictionary class
|
24
|
+
unless row=="\n"
|
25
|
+
dictionary_class_words = Array.new()
|
26
|
+
row.split(",").each do |word|
|
27
|
+
dictionary_class_words.push(word.gsub("\"", '').strip) unless word == "\n"
|
28
|
+
end
|
29
|
+
@dictionary[dictionary_class].concat(dictionary_class_words)
|
30
|
+
end
|
31
|
+
end
|
32
|
+
trainingData["dictionary"] = @dictionary
|
33
|
+
# initialize/read ingored keywords file
|
34
|
+
ignored_keywords_file = File.new(trainingFiles["ignored_keywords"], 'r')
|
35
|
+
ignored_keywords_file.each_line("\n") do |row|
|
36
|
+
row.split(",").each do |word|
|
37
|
+
@ignored_words.push(word.gsub("\"", '').strip) unless word == "\n"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
trainingData["ignored_words"] = @ignored_words
|
41
|
+
|
42
|
+
#cache the trained data
|
43
|
+
@cache.set('trainingData', trainingData, :expiry => (15*24*3600))
|
44
|
+
else
|
45
|
+
trainingData = @cache.get('trainingData')
|
46
|
+
@dictionary = trainingData["dictionary"]
|
47
|
+
@ignored_words = trainingData["ignored_words"]
|
48
|
+
end
|
49
|
+
#
|
50
|
+
return true
|
51
|
+
|
52
|
+
rescue => err
|
53
|
+
puts "Exception: #{err}"
|
54
|
+
err
|
55
|
+
end
|
56
|
+
|
57
|
+
# Extract feature words from given string
|
58
|
+
#
|
59
|
+
# Example:
|
60
|
+
# >> input = ["sample statement", "sample statement2"]
|
61
|
+
# >> extract_feature_words(input)
|
62
|
+
#
|
63
|
+
# Arguments:
|
64
|
+
# contents: (Array of Strings)
|
65
|
+
#
|
66
|
+
# Returns:
|
67
|
+
# Hash of feature words in "word, repeat" pairs ex.
|
68
|
+
# { "sample" => 2, "statement" => 1, "statement2" => 1 }
|
69
|
+
def self.extract_feature_words(contents)
|
70
|
+
words = Hash.new(0)
|
71
|
+
contents.each do |content|
|
72
|
+
tokens = content.split(/[^a-zA-z]/)
|
73
|
+
tokens.each do |token|
|
74
|
+
token.downcase! unless token.upcase == token # make token all lowercase unless it is all caps
|
75
|
+
words[token] += 1 unless token.empty? || @ignored_words.include?(token.downcase)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
words.keys.sort
|
80
|
+
|
81
|
+
return words
|
82
|
+
|
83
|
+
rescue => err
|
84
|
+
puts "Exception: #{err}"
|
85
|
+
err
|
86
|
+
end
|
87
|
+
|
88
|
+
def self.analyze(contents)
|
89
|
+
psychological_profile = Hash.new(0)
|
90
|
+
_classes_total = 0
|
91
|
+
|
92
|
+
(self.extract_feature_words(contents)).each do |word, repeated|
|
93
|
+
@dictionary.each do |_class, _class_words|
|
94
|
+
psychological_profile[_class] += 1 unless !_class_words.include?(word)
|
95
|
+
end
|
96
|
+
end
|
97
|
+
|
98
|
+
psychological_profile.each { |profile_class, total| _classes_total += total }
|
99
|
+
psychological_profile.each { |profile_class, total| psychological_profile[profile_class] = (total.to_f/_classes_total.to_f*100.0).round(2) }
|
100
|
+
|
101
|
+
return psychological_profile
|
102
|
+
|
103
|
+
rescue => err
|
104
|
+
puts "Exception: #{err}"
|
105
|
+
err
|
106
|
+
end
|
107
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'psych_analyzer/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "psych_analyzer"
|
8
|
+
gem.version = PsychAnalyzer::VERSION
|
9
|
+
gem.authors = ["Ramy Khater"]
|
10
|
+
gem.email = ["eng.ramymohie@gmail.com"]
|
11
|
+
gem.description = %q{creates a psychological profile of given content based-on provided dictionary.}
|
12
|
+
gem.summary = %q{creates a psychological profile of given content based-on provided dictionary.}
|
13
|
+
gem.homepage = "https://github.com/rayasocialmedia/psych_analyzer"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
end
|
metadata
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: psych_analyzer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Ramy Khater
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-03-28 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: creates a psychological profile of given content based-on provided dictionary.
|
15
|
+
email:
|
16
|
+
- eng.ramymohie@gmail.com
|
17
|
+
executables: []
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- .gitignore
|
22
|
+
- Gemfile
|
23
|
+
- LICENSE.txt
|
24
|
+
- README.md
|
25
|
+
- Rakefile
|
26
|
+
- ignored_keywords.csv
|
27
|
+
- lib/psych_analyzer.rb
|
28
|
+
- lib/psych_analyzer/version.rb
|
29
|
+
- psych_analyzer.gemspec
|
30
|
+
- psych_dictionary.csv
|
31
|
+
homepage: https://github.com/rayasocialmedia/psych_analyzer
|
32
|
+
licenses: []
|
33
|
+
post_install_message:
|
34
|
+
rdoc_options: []
|
35
|
+
require_paths:
|
36
|
+
- lib
|
37
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
38
|
+
none: false
|
39
|
+
requirements:
|
40
|
+
- - ! '>='
|
41
|
+
- !ruby/object:Gem::Version
|
42
|
+
version: '0'
|
43
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
44
|
+
none: false
|
45
|
+
requirements:
|
46
|
+
- - ! '>='
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: '0'
|
49
|
+
requirements: []
|
50
|
+
rubyforge_project:
|
51
|
+
rubygems_version: 1.8.11
|
52
|
+
signing_key:
|
53
|
+
specification_version: 3
|
54
|
+
summary: creates a psychological profile of given content based-on provided dictionary.
|
55
|
+
test_files: []
|