Created
November 26, 2014 05:21
-
-
Save tabachain/98096ac406807e2fde47 to your computer and use it in GitHub Desktop.
Rubyによるコサイン類似度の計算
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
def calc_score(str1,str2) | |
vector = [] | |
vector1 = [] | |
vector2 = [] | |
frag_vector1 = [] | |
frag_vector2 = [] | |
node1 = MeCab::Tagger.new.parseToNode(str1) | |
node2 = MeCab::Tagger.new.parseToNode(str2) | |
while node1 | |
vector1.push(node1.surface) | |
node1 = node1.next | |
end | |
while node2 | |
vector2.push(node2.surface) | |
node2 = node2.next | |
end | |
vector += vector1 | |
vector += vector2 | |
vector.uniq!.delete("") | |
vector1.delete("") | |
vector.delete("") | |
vector2.delete("") | |
vector.each do |word| | |
if vector1.include?(word) then | |
frag_vector1.push(1) | |
else | |
frag_vector1.push(0) | |
end | |
if vector2.include?(word) then | |
frag_vector2.push(1) | |
else | |
frag_vector2.push(0) | |
end | |
end | |
vector1_final = Vector.elements(frag_vector1, copy = true) | |
vector2_final = Vector.elements(frag_vector2, copy = true) | |
return vector2_final.inner_product(vector1_final)/(vector1_final.norm() * vector2_final.norm()) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment