def ExtractForOne(self,ExpTerm):
#calc the ave vector of q terms
#calc the vector for exp terms
score = 0
hFeature = {}
hFeature['word2vecsim'] = score
QVector = VectorC()
TermVector = VectorC()
QTermCnt = 0
if self.hTargetTerm[ExpTerm.term] == -1:
print "term [%s] not appear in word2vec" %(ExpTerm.term)
return hFeature
TermVector = self.lVector[self.hTargetTerm[ExpTerm.term]]
for qterm in ExpTerm.query.split():
if self.hTargetTerm[qterm] == -1:
print "qterm [%s] not appear in word2vec" %(qterm)
continue
QTermCnt += 1
QVector += self.lVector[self.hTargetTerm[qterm]]
if QTermCnt == 0:
return hFeature
QVector /= float(QTermCnt)
score = VectorC.cosine(QVector,TermVector)
hFeature['word2vecsim'] = score
return hFeature
def TfIdfCosine(LmA,LmB,CtfCenter):
if (LmA.len == 0) | ( LmB.len == 0):
return 0
vA = LmA.TransferToVectorWithIdf(CtfCenter)
vB = LmB.TransferToVectorWithIdf(CtfCenter)
score = VectorC.cosine(vA, vB)
print "cosine [%f] of:\n%s\n%s" %(score, json.dumps(vA.hDim),json.dumps(vB.hDim))
return score
def TfIdfCosine(LmA,LmB,CtfCenter):
vA = VectorC(LmA.hTermTF)
vB = VectorC(LmB.hTermTF)
if (LmA.len == 0) | ( LmB.len == 0):
return 0
vA /= LmA.len
vB /= LmB.len
for item in vA.hDim:
CTF = CtfCenter.GetCtfProb(item)
vA.hDim[item] *= math.log(1.0/CTF)
for item in vB.hDim:
CTF = CtfCenter.GetCtfProb(item)
vB.hDim[item] *= math.log(1.0/CTF)
score = VectorC.cosine(vA, vB)
print "cosine [%f] of:\n%s\n%s" %(score, json.dumps(vA.hDim),json.dumps(vB.hDim))
return score