bug fix

ud.py

@@ -22,8 +22,8 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
     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])]
+      k,h=z[numpy.nanargmax(m[z,z])],numpy.nanmin(m)-numpy.nanmax(m)
+      m[:,z]+=[[0 if j in z and (i!=j or i==k) else h 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[j,i]].split("|") for i,j in enumerate(h)]
@@ -51,14 +51,11 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
           x[i]=b(x,i,j)
       if max(x)<0:
         return h
-    y=[i for i,j in enumerate(x) if j==max(x)]
-    m=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)
+    y,x=[i for i,j in enumerate(x) if j==max(x)],[i for i,j in enumerate(x) if j<max(x)]
+    z=matrix-numpy.nanmax(matrix,axis=0)
+    m=numpy.block([[z[x,:][:,x],numpy.nanmax(z[x,:][:,y],axis=1).reshape(len(x),1)],[numpy.nanmax(z[y,:][:,x],axis=0),numpy.nanmax(z[y,y])]])
+    k=[j if i==len(x) else x[j] if j<len(x) else y[numpy.nanargmax(z[y,x[i]])] for i,j in enumerate(self.chu_liu_edmonds(m))]
+    h=[j if i in y else k[x.index(i)] for i,j in enumerate(h)]
+    i=y[numpy.nanargmax(z[x[k[-1]],y] if k[-1]<len(x) else z[y,y])]
+    h[i]=x[k[-1]] if k[-1]<len(x) else i
+    return h