Class: JnbClassifier::Document

Inherits:
Object
  • Object
show all
Defined in:
lib/jnb_classifier.rb

Overview

associate label to the frequency of words in the document

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(label, file_name) ⇒ Document

Returns a new instance of Document.



63
64
65
66
 
# File 'lib/jnb_classifier.rb', line 63

def initialize(label, file_name)
  @label = label                               # String
  @attributes = create_attributes(file_name)   # Hash
end

Instance Attribute Details

#attributes ⇒ Object (readonly)

Returns the value of attribute attributes.



61
62
63
 
# File 'lib/jnb_classifier.rb', line 61

def attributes
  @attributes
end

#label ⇒ Object (readonly)

Returns the value of attribute label.



60
61
62
 
# File 'lib/jnb_classifier.rb', line 60

def label
  @label
end

Instance Method Details

#create_attributes(file_name) ⇒ Object 



68
69
70
71
72
73
74
75
76
77
78
 
# File 'lib/jnb_classifier.rb', line 68

def create_attributes(file_name)
  attributes = Hash.new(0)
  File.open(file_name) {|f|
	doc = f.read
	nm = Natto::MeCab.new
	nm.parse(doc) do |n|
	  attributes[n.surface] += 1 if n.feature.match(/名詞/)
	end
  }
  attributes
end