Class: Dictionary::KL

Inherits:
Object
  • Object
show all
Defined in:
lib/rbbt/bow/dictionary.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(options = {}) ⇒ KL

Returns a new instance of KL.



117
118
119
120
 
# File 'lib/rbbt/bow/dictionary.rb', line 117

def initialize(options = {})
  @pos_dict = Dictionary::TF_IDF.new(options)
  @neg_dict = Dictionary::TF_IDF.new(options)
end

Instance Attribute Details

#neg_dict ⇒ Object (readonly)

Returns the value of attribute neg_dict.



115
116
117
 
# File 'lib/rbbt/bow/dictionary.rb', line 115

def neg_dict
  @neg_dict
end

#pos_dict ⇒ Object (readonly)

Returns the value of attribute pos_dict.



115
116
117
 
# File 'lib/rbbt/bow/dictionary.rb', line 115

def pos_dict
  @pos_dict
end

Instance Method Details

#add(terms, c) ⇒ Object 



126
127
128
129
 
# File 'lib/rbbt/bow/dictionary.rb', line 126

def add(terms, c)
  dict = (c == :+ || c == '+' ? @pos_dict : @neg_dict)
  dict.add(terms)
end

#best(options = {}) ⇒ Object 



150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
 
# File 'lib/rbbt/bow/dictionary.rb', line 150

def best(options = {})
  high, low, limit = {
    :low   => 0,
    :high    => 1,
  }.merge(options).
  values_at(:high, :low, :limit)

  pos_df = @pos_dict.df
  neg_df = @neg_dict.df

  best = {}
  terms.select{|term|
    pos_df[term] >= low && pos_df[term] <= high ||
    neg_df[term] >= low && neg_df[term] <= high 
  }.each{|term|
    pos = pos_df[term]
    neg = neg_df[term]

    pos = 0.000001 if pos == 0
    pos = 0.999999 if pos == 1
    neg = 0.000001 if neg == 0
    neg = 0.999999 if neg == 1

    best[term] = pos * Math::log(pos / neg) + neg * Math::log(neg / pos)
  }
  if limit
    Hash[*best.sort{|a,b| b[1] <=>  a[1]}.slice(0, limit).flatten]
  else
    best
  end
end

#kl ⇒ Object 



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/rbbt/bow/dictionary.rb', line 131

def kl
  kl = {}
  pos_df = @pos_dict.df
  neg_df = @neg_dict.df

  terms.each{|term|
    pos = pos_df[term]
    neg = neg_df[term]

    pos = 0.000001 if pos == 0
    pos = 0.999999 if pos == 1
    neg = 0.000001 if neg == 0
    neg = 0.999999 if neg == 1

    kl[term] = pos * Math::log(pos / neg) + neg * Math::log(neg / pos)
  }
  kl
end

#terms ⇒ Object 



122
123
124
 
# File 'lib/rbbt/bow/dictionary.rb', line 122

def terms
  (pos_dict.terms.keys + neg_dict.terms.keys).uniq
end

#weights(options = {}) ⇒ Object 



182
183
184
 
# File 'lib/rbbt/bow/dictionary.rb', line 182

def weights(options = {})
  best(options)
end