Created
December 31, 2010 10:02
-
-
Save jacobandresen/760902 to your computer and use it in GitHub Desktop.
learning ruby
This file contains hidden or 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 readData() | |
data=[] | |
f = File.open("twl06.txt", "r") | |
f.each_line do |line| | |
data << line | |
end | |
return data | |
end | |
def levenshtein(s,t) | |
n = s.size | |
m = t.size | |
a = Array.new | |
if n!=0 && m!= 0 | |
r = Array.new | |
rz = Array.new | |
0.upto(m) { |x| r.push(0)} | |
0.upto(n) { |x| a.push(r.dup)} | |
a.each_index {|x| a[x][0] = x} | |
0.upto(m) {|x| a[0][x] = x} | |
cost = 0 | |
1.upto(n) do |i| | |
1.upto(m) do |j| | |
cost = s[i] == t[j] ? 0 : 1 | |
a[i][j] = [a[ i- 1][j] +1,a[i][j - 1] + 1,a[i - 1][j -1] + cost].min | |
end | |
end | |
a[n][m] | |
else | |
0 | |
end | |
end | |
def scoreWord(word,data) | |
word = word.upcase | |
count =0 | |
minscore = 1000 | |
data = data.sort_by{ |a| a.length } | |
data.each { | |
|d| | |
count = count +1 | |
if (minscore==0 || minscore < ((d.length - word.length).abs)) then | |
break | |
elsif | |
score = levenshtein(d,word) | |
if (score < minscore) then | |
minscore = score | |
puts "MIN:"+d | |
end | |
if (count%3000==0) then | |
puts word+" "+d+" "+(String(score))+" "+(String(minscore))+" "+(String(count))+"/"+(String | |
(data.length)) | |
end | |
end | |
} | |
return minscore | |
end | |
data=readData() | |
def scoreSentence( sentence,data) | |
score = 0 | |
sentence.split(/\s+/).each { |w| | |
score += scoreWord(w,data) | |
} | |
puts score | |
end | |
scoreSentence("tihs sentenctcnes iss nout varrry goud",data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment