Created
December 11, 2014 18:23
-
-
Save nkt1546789/187fa009691a27440498 to your computer and use it in GitHub Desktop.
This is an implementation of string kernel called "limited range correlation" on Python.
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
from pylab import * | |
def string_kernel(s1,s2,n=inf): | |
k1=[] | |
k2=[] | |
A=set() | |
for k in xrange(1,min(n,len(s1)+1)): | |
for i in xrange(0,len(s1)-(k-1)): | |
A.add(s1[i:i+k]) | |
for k in xrange(1,min(n,len(s2)+1)): | |
for i in xrange(0,len(s2)-(k-1)): | |
A.add(s2[i:i+k]) | |
for s in A: | |
k1.append((1.+log2(len(s)))*s1.count(s)) | |
k2.append((1.+log2(len(s)))*s2.count(s)) | |
k1=array(k1) | |
k2=array(k2) | |
try: | |
return k1.dot(k2)/(norm(k1)*norm(k2)) | |
except ZeroDivisionError: | |
return 0. | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment