Making some changes to improve speed (some ideas taken from shogun's implementation)

Author: helq

string_kernel.py

@@ -3,46 +3,33 @@
 # Kernel defined by Lodhi et al. (2002)
 def ssk(s, t, n, lbda, accum=False):
     lens, lent = len(s), len(t)
-    #dynamic = (-1)*np.ones( (n+1, lens, lent) )
+    #k_prim = (-1)*np.ones( (n+1, lens, lent) )
     k_prim = np.zeros( (n, lens, lent) )
     indices = { x : [i for i, e in enumerate(t) if e == x] for x in set(s) }
 
     k_prim[0,:,:] = 1
 
     for i in range(1,n):
         for sj in range(i,lens):
+            toret = 0.
             for tk in range(i,lent):
-                x = s[sj-1]
-                toret = lbda * k_prim[i, sj-1, tk]
-                for k_ in indices[x]:
-                    if k_ >= tk:
-                        break
-                    toret += k_prim[i-1, sj-1, k_] * (lbda**(tk-k_+1))
-                k_prim[i,sj,tk] = toret
+                if s[sj-1]==t[tk-1]: # trick taken from shogun implemantion of SSK
+                    toret = lbda * (toret + lbda*k_prim[i-1,sj-1,tk-1])
+                else:
+                    toret *= lbda
+                k_prim[i,sj,tk] = toret + lbda * k_prim[i, sj-1, tk]
 
-    def k(sj, tk, n):
-        # print( "k({},{},{})".format(s, t, n) )
-        if n <= 0:
-            raise "Error, n must be bigger than zero"
-        if min(sj, tk) < n:
-            # print( "k({},{},{}) => 0".format(s, t, n) )
-            return 0.
-        x = s[sj-1]
-        toret = k(sj-1, tk, n)
-        for k_ in indices[x]:
-            if k_ >= tk:
-                break
-            toret += lbda**2 * k_prim[n-1, sj-1, k_]
-        # print( "k({},{},{}) => {}".format(s, t, n, toret) )
-        return toret
 
-    if accum:
-        toret = sum( k(lens, lent, i) for i in range(1, min(n,lens,lent)+1) )
-    else:
-        toret = k(lens, lent, n)
+    start = 0 if accum else n-1
+    k = 0.
+    for i in range(n):
+        for sj in range(i,lens):
+            for tk in range(i,lent):
+                if s[sj]==t[tk]:
+                    k += lbda*lbda*k_prim[i,sj,tk]
 
     # print( [len(list(i for (sj,tk,i) in k_prim if i==m-1)) for m in range(n)] )
-    return toret
+    return k
 
 def string_kernel(xs, ys, n, lbda):
     if len(xs.shape) != 2 or len(ys.shape) != 2 or xs.shape[1] != 1 or ys.shape[1] != 1: