chu_liu_edmonds included

README.md

@@ -65,12 +65,12 @@ nlp=UDgoeswith("KoichiYasuoka/deberta-base-thai-ud-goeswith")
 print(nlp("หลายหัวดีกว่าหัวเดียว"))
 ```
 
-or
+with [ufal.chu-liu-edmonds](https://pypi.org/project/ufal.chu-liu-edmonds/).
+Or without ufal.chu-liu-edmonds:
 
 ```
 from transformers import pipeline
-nlp=pipeline("universal-dependencies","KoichiYasuoka/deberta-base-thai-ud-goeswith",trust_remote_code=True)
+nlp=pipeline("universal-dependencies","KoichiYasuoka/deberta-base-thai-ud-goeswith",trust_remote_code=True,aggregation_strategy="simple")
 print(nlp("หลายหัวดีกว่าหัวเดียว"))
 ```
 
-[ufal.chu-liu-edmonds](https://pypi.org/project/ufal.chu-liu-edmonds/) is required.

ud.py

@@ -9,7 +9,6 @@ class UniversalDependenciesPipeline(TokenClassificationPipeline):
     return {"logits":e.logits[:,1:-2,:],**model_input}
   def postprocess(self,model_output,**kwargs):
     import numpy
-    import ufal.chu_liu_edmonds
     e=model_output["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)
@@ -19,27 +18,47 @@ 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)]
-    if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
-      for i,j in reversed(list(enumerate(q[2:],2))):
+    q=[self.model.config.id2label[p[j,i]].split("|") for i,j in enumerate(h)]
+    g="aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none"
+    if g:
+      for i,j in reversed(list(enumerate(q[1:],1))):
         if j[-1]=="goeswith":
           h=[b if i>b else b-1 for a,b in enumerate(h) if i!=a]
-          v[i-2]=(v[i-2][0],v.pop(i-1)[1])
+          v[i-1]=(v[i-1][0],v.pop(i)[1])
           q.pop(i)
     t=model_output["sentence"].replace("\n"," ")
     u="# text = "+t+"\n"
-    for i,(s,e) in enumerate(v,1):
-      u+="\t".join([str(i),t[s:e],"_",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"
+    for i,(s,e) in enumerate(v):
+      u+="\t".join([str(i+1),t[s:e],t[s:e] if g else "_",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"
     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=[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)