Created
November 12, 2019 07:41
-
-
Save satoryu/f6a51003e78380ccc0812ced0fb4e0ba to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'matrix' | |
require 'tf-idf-similarity' | |
class Token | |
def initialize(mecab_node) | |
@node = mecab_node | |
end | |
def valid? | |
@node.feature.start_with?('名詞') | |
end | |
def to_s | |
@node.surface | |
end | |
end | |
class Tokenizer | |
def tokenize(text) | |
require 'natto' | |
nm = Natto::MeCab.new | |
nm.enum_parse(text).to_a.map do |node| | |
Token.new(node) | |
end | |
end | |
end | |
tokenizer = Tokenizer.new | |
options = { tokenizer: tokenizer } | |
document1 = TfIdfSimilarity::Document.new("ロン毛", options) | |
document2 = TfIdfSimilarity::Document.new("セミロン毛", options) | |
document3 = TfIdfSimilarity::Document.new("セミ", options) | |
corpus = [document1, document2, document3] | |
model = TfIdfSimilarity::TfIdfModel.new(corpus) | |
matrix = model.similarity_matrix | |
puts matrix | |
#=> Matrix[[0.9999999999999999, 0.3360969272762574, 0.0], [0.3360969272762574, 0.9999999999999999, 0.0], [0.0, 0.0, 1.0]] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment