Sha256: 9e35c0354b9b5b89b864a4cccc3c5095eda3174d33952a685a66889762cdb11c
Contents?: true
Size: 864 Bytes
Versions: 7
Compression:
Stored size: 864 Bytes
Contents
# Author:: David Fayram (mailto:dfayram@lensmen.net)
# Copyright:: Copyright (c) 2005 David Fayram II
# License:: LGPL
module ClassifierReborn
# This class keeps a word => index mapping. It is used to map stemmed words
# to dimensions of a vector.
class WordList
def initialize
@location_table = Hash.new
end
# Adds a word (if it is new) and assigns it a unique dimension.
def add_word(word)
term = word
@location_table[term] = @location_table.size unless @location_table[term]
end
# Returns the dimension of the word or nil if the word is not in the space.
def [](lookup)
term = lookup
@location_table[term]
end
def word_for_index(ind)
@location_table.invert[ind]
end
# Returns the number of words mapped.
def size
@location_table.size
end
end
end
Version data entries
7 entries across 7 versions & 2 rubygems