algorithm improved

ud.py

@@ -1,3 +1,4 @@
+import numpy
 from transformers import TokenClassificationPipeline
 
 class UniversalDependenciesPipeline(TokenClassificationPipeline):
@@ -8,23 +9,24 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
       e=self.model(input_ids=torch.tensor([v[0:i]+[self.tokenizer.mask_token_id]+v[i+1:]+[j] for i,j in enumerate(v[1:-1],1)],device=self.device))
     return {"logits":e.logits[:,1:-2,:],**model_inputs}
   def postprocess(self,model_outputs,**kwargs):
-    import numpy
     if "logits" not in model_outputs:
       return "".join(self.postprocess(x,**kwargs) for x in model_outputs)
     e=model_outputs["logits"].numpy()
     r=[1 if i==0 else -1 if j.endswith("|root") else 0 for i,j in sorted(self.model.config.id2label.items())]
-    e+=numpy.where(numpy.add.outer(numpy.identity(e.shape[0]),r)==0,0,numpy.nan)
+    e+=numpy.where(numpy.add.outer(numpy.identity(e.shape[0]),r)==0,0,-numpy.inf)
     g=self.model.config.label2id["X|_|goeswith"]
-    r=numpy.tri(e.shape[0])
+    m,r=numpy.max(e,axis=2),numpy.tri(e.shape[0])
     for i in range(e.shape[0]):
       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,p=numpy.nanmax(e,axis=2),numpy.nanargmax(e,axis=2)
+        r[i,j]=1
+        if numpy.argmax(e[i,j-1])==g and numpy.argmax(m[:,j-1])==i:
+          r[i,j]=r[i,j-1]
+    e[:,:,g]+=numpy.where(r==0,0,-numpy.inf)
+    m,p=numpy.max(e,axis=2),numpy.argmax(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,h=z[numpy.nanargmax(m[z,z])],numpy.nanmin(m)-numpy.nanmax(m)
+      k,h=z[numpy.argmax(m[z,z])],numpy.min(m)-numpy.max(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)
     t=model_outputs["sentence"].replace("\n"," ")
@@ -64,8 +66,7 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
       u=x+"\t".join([str(i+1),"".join(w),l,q[i][0],"|".join(q[i][1:-1]),"_",str(0 if h[i]==i else h[i]+1),q[i][-1],"_","_" if i+1<len(v) and e<v[i+1][0] else "SpaceAfter=No"])+"\n"+u
     return "# text = "+t+"\n"+u
   def chu_liu_edmonds(self,matrix):
-    import numpy
-    h=numpy.nanargmax(matrix,axis=0)
+    h=numpy.argmax(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=[]
@@ -76,10 +77,10 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
       if max(x)<0:
         return h
     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))]
+    z=matrix-numpy.max(matrix,axis=0)
+    m=numpy.block([[z[x,:][:,x],numpy.max(z[x,:][:,y],axis=1).reshape(len(x),1)],[numpy.max(z[y,:][:,x],axis=0),numpy.max(z[y,y])]])
+    k=[j if i==len(x) else x[j] if j<len(x) else y[numpy.argmax(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])]
+    i=y[numpy.argmax(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