algorithm improved

ud.py

@@ -11,7 +11,7 @@ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
     super().__init__(**kwargs)
     x=self.model.config.label2id
     y=[k for k in x if k.startswith("B-") or not (k.startswith("I-") or k.endswith("|root") or k.find("|l-")>0 or k.find("|r-")>0)]
-    self.transition=numpy.full((len(x),len(x)),numpy.nan)
+    self.transition=numpy.full((len(x),len(x)),-numpy.inf)
     for k,v in x.items():
       for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
         self.transition[v,x[j]]=0
@@ -24,10 +24,10 @@ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
     e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
     z=e/e.sum(axis=-1,keepdims=True)
     for i in range(m.shape[0]-1,0,-1):
-      m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
-    k=[numpy.nanargmax(m[0]+self.transition[0])]
+      m[i-1]+=numpy.max(m[i]+self.transition,axis=1)
+    k=[numpy.argmax(m[0]+self.transition[0])]
     for i in range(1,m.shape[0]):
-      k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
+      k.append(numpy.argmax(m[i]+self.transition[k[-1]]))
     w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
     if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
       for i,t in reversed(list(enumerate(w))):
@@ -49,9 +49,9 @@ class UniversalDependenciesCausalPipeline(BellmanFordTokenClassificationPipeline
     super().__init__(**kwargs)
     self.oldtokenizer=AutoTokenizer.from_pretrained(self.tokenizer.name_or_path,tokenizer_file=cached_file(self.tokenizer.name_or_path,"oldtokenizer.json"))
     x=self.model.config.label2id
-    self.root=numpy.full((len(x)),numpy.nan)
-    self.left_arc=numpy.full((len(x)),numpy.nan)
-    self.right_arc=numpy.full((len(x)),numpy.nan)
+    self.root=numpy.full((len(x)),-numpy.inf)
+    self.left_arc=numpy.full((len(x)),-numpy.inf)
+    self.right_arc=numpy.full((len(x)),-numpy.inf)
     for k,v in x.items():
       if k.endswith("|root"):
         self.root[v]=0
@@ -65,10 +65,10 @@ class UniversalDependenciesCausalPipeline(BellmanFordTokenClassificationPipeline
       return self.postprocess(model_outputs[0],**kwargs)
     m=model_outputs["logits"][0].numpy()
     for i in range(m.shape[0]-1,0,-1):
-      m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
-    k=[numpy.nanargmax(m[0]+self.transition[0])]
+      m[i-1]+=numpy.max(m[i]+self.transition,axis=1)
+    k=[numpy.argmax(m[0]+self.transition[0])]
     for i in range(1,m.shape[0]):
-      k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
+      k.append(numpy.argmax(m[i]+self.transition[k[-1]]))
     w=[{"entity":self.model.config.id2label[j],"start":s,"end":e} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
     for i,t in reversed(list(enumerate(w))):
       p=t.pop("entity")
@@ -113,11 +113,11 @@ class UniversalDependenciesCausalPipeline(BellmanFordTokenClassificationPipeline
       for j in range(i):
         e[-j-1,-i-1],e[-i-1,-j-1]=e[-i-1,i-j]+self.left_arc,e[-i-1,i-j]+self.right_arc
       e[-i-1,-i-1]=e[-i-1,0]+self.root
-    m,p=numpy.nanmax(e,axis=2),numpy.nanargmax(e,axis=2)
+    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)
     q=[self.model.config.id2label[p[j,i]].split("|") for i,j in enumerate(h)]
@@ -127,7 +127,7 @@ class UniversalDependenciesCausalPipeline(BellmanFordTokenClassificationPipeline
       u+="\t".join([str(i+1),j,"_",q[i][0],"_","_" if len(q[i])<3 else "|".join(q[i][1:-1]),str(0 if h[i]==i else h[i]+1),"root" if q[i][-1]=="root" else q[i][-1][2:],"_","_" if i+1<len(d) and w[i]["end"]<w[i+1]["start"] else "SpaceAfter=No"])+"\n"
     return u+"\n"
   def chu_liu_edmonds(self,matrix):
-    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=[]
@@ -138,10 +138,10 @@ class UniversalDependenciesCausalPipeline(BellmanFordTokenClassificationPipeline
       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