chu_liu_edmonds included

ud.py

@@ -19,17 +19,13 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
       for j in range(i+2,e.shape[1]):
         r[i,j]=r[i,j-1] if numpy.nanargmax(e[i,j-1])==g else 1
     e[:,:,g]+=numpy.where(r==0,0,numpy.nan)
-    m=numpy.full((e.shape[0]+1,e.shape[1]+1),numpy.nan)
-    m[1:,1:]=numpy.nanmax(e,axis=2).transpose()
-    p=numpy.zeros(m.shape)
-    p[1:,1:]=numpy.nanargmax(e,axis=2).transpose()
-    for i in range(1,m.shape[0]):
-      m[i,0],m[i,i],p[i,0]=m[i,i],numpy.nan,p[i,i]
-    h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
-    if [0 for i in h if i==0]!=[0]:
-      m[:,0]+=numpy.where(m[:,0]==numpy.nanmax(m[[i for i,j in enumerate(h) if j==0],0]),0,numpy.nan)
-      m[[i for i,j in enumerate(h) if j==0]]+=[0 if i==0 or j==0 else numpy.nan for i,j in enumerate(h)]
-      h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
+    m,p=numpy.nanmax(e,axis=2),numpy.nanargmax(e,axis=2)
+    h=self.chu_liu_edmonds(m)
+    z=[i for i,j in enumerate(h) if i==j]
+    if len(z)>1:
+      k=z[numpy.nanargmax(m[z,z])]
+      m[:,z]+=[[0 if j in z and (i!=j or i==k) else numpy.nan for i in z] for j in range(m.shape[0])]
+      h=self.chu_liu_edmonds(m)
     v=[(s,e) for s,e in model_output["offset_mapping"][0].tolist() if s<e]
     q=[self.model.config.id2label[p[i,j]].split("|") for i,j in enumerate(h)]
     g="aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none"
@@ -44,3 +40,25 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
     for i,(s,e) in enumerate(v,1):
       u+="\t".join([str(i),t[s:e],t[s:e] if g else "_",q[i][0],"_","|".join(q[i][1:-1]),str(h[i]),q[i][-1],"_","_" if i<len(v) and e<v[i][0] else "SpaceAfter=No"])+"\n"
     return u+"\n"
+  def chu_liu_edmonds(self,matrix):
+    import numpy
+    h=numpy.nanargmax(matrix,axis=0)
+    x=[-1 if i==j else j for i,j in enumerate(h)]
+    for b in [lambda x,i,j:-1 if i not in x else x[i],lambda x,i,j:-1 if j<0 else x[j]]:
+      y=[]
+      while x!=y:
+        y=list(x)
+        for i,j in enumerate(x):
+          x[i]=b(x,i,j)
+      if max(x)<0:
+        return h
+    y,m=[i for i,j in enumerate(x) if j==max(x)],numpy.full((matrix.shape[0]+1,matrix.shape[1]+1),numpy.nan)
+    m[0:-1,0:-1]=z=matrix-numpy.nanmax(matrix,axis=0)
+    m[0:-1,-1],m[-1,0:-1],m[-1,-1]=numpy.nanmax(z[:,y],axis=1),numpy.nanmax(z[y,:],axis=0),numpy.nanmax(z[y,y])
+    m[y,:]=m[:,y]=numpy.nan
+    m[y,y]=0
+    k=self.chu_liu_edmonds(m)
+    j=y[numpy.nanargmax(z[k[-1],y] if k[-1]<z.shape[0] else z[y,y])]
+    i=k[-1] if k[-1]<z.shape[0] else j
+    z[0:i,j]=z[i+1:,j]=numpy.nan
+    return self.chu_liu_edmonds(z)