Class: Rblearn::CountVectorizer

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

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(tokenizer, lowercase = true, max_features = 0.8) ⇒ CountVectorizer

tokenizer: lambda function

string -> Array<string>

lowcase: whether if words are lowercases

bool

stop_words: list of stop words

Array<string>

max_features: limitation of feature size

Float in [0, 1]

TODO: by max_features, zero vectors are sometimes created.



14
15
16
17
18
19
20
21
22
23
 
# File 'lib/rblearn/CountVectorizer.rb', line 14

def initialize(tokenizer, lowercase=true, max_features=0.8)
  @tokenizer = tokenizer
  @lowercase = lowercase

  stop_words = Stopwords::STOP_WORDS
  stop_words.map! {|token| token.stem}
  stop_words.map! {|token| token.downcase} if @lowercase
  @stopwords = stop_words
  @max_feature = max_features
end

Instance Attribute Details

#doc_matrix ⇒ Object

TODO: consider the access controll about all variables



7
8
9
 
# File 'lib/rblearn/CountVectorizer.rb', line 7

def doc_matrix
  @doc_matrix
end

#feature_names ⇒ Object

TODO: consider the access controll about all variables



7
8
9
 
# File 'lib/rblearn/CountVectorizer.rb', line 7

def feature_names
  @feature_names
end

#token2index ⇒ Object

TODO: consider the access controll about all variables



7
8
9
 
# File 'lib/rblearn/CountVectorizer.rb', line 7

def token2index
  @token2index
end

Instance Method Details

#fit_transform(features) ⇒ Object

features: Each documents’ feature

Array<String> -> NArray::Int64



26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
 
# File 'lib/rblearn/CountVectorizer.rb', line 26

def fit_transform(features)
  all_vocaburaries = []
  word_frequency = Hash.new{|hash, key| hash[key] = 0}

  features.each do |feature|
    @tokenizer.call(feature).each do |token|
      token.downcase! if @lowercase
      all_vocaburaries << token
      word_frequency[token] += 1
    end
  end

  all_vocaburaries.uniq!
  word_frequency =  word_frequency.sort{|(_, value1), (_, value2)| value2 <=> value1}
  feature_names = (0...(word_frequency.size * @max_feature).to_i).map{|i| word_frequency[i][0]}

  token2index = {}
  feature_names.each_with_index do |token, i|
    token2index[token] = i
  end

  doc_matrix = Numo::Int32.zeros([features.size, feature_names.size])
  features.each_with_index do |feature, doc_id|
    tokens = []
    @tokenizer.call(feature).each do |token|
      token.downcase! if @lowercase
      tokens << token unless @stopwords.include?(token)
    end

    # BoW representation
    counter = Hash.new{|hash, key| hash[key] = 0}
    tokens.each do |token|
      counter[token] += 1
    end

    counter.each do |token, freq|
      doc_matrix[doc_id, token2index[token]] = freq if token2index[token]
    end
  end

  @doc_matrix = doc_matrix
  @feature_names = feature_names
  @token2index = token2index
  return @doc_matrix
end