def searchtfjabPlusRelevent(self,searchList , releventdocstr , documentList):
queryVector = self.getVectorKeywordIndex(searchList)
relevenceVector = self.getVectorKeywordIndex(releventdocstr)
self.documentVectors = self.getVectorKeywordIndexSeprated(documentList)
ratings = [util.jaccard(queryVector , documentVector) for documentVector in self.documentVectors]
ratingrel = [util.jaccard(relevenceVector , documentVector) for documentVector in self.documentVectors]
for i in range(len(ratings)):
ratings[i] += (ratingrel[i] * 0.5)
return ratings
def pair_features(hashes1, hashes2):
feats = [jaccard(binary_matrix_to_int(hashes1), binary_matrix_to_int(hashes2))]
D = pairwise_distances(hashes1, hashes2, metric='hamming')
if D.shape[0] > D.shape[1]:
D = D.T
if D.shape[0] == 0 or D.shape[1] == 0:
feats.extend([np.nan] * 6)
else:
s0 = D.min(axis=1)
s1 = D.max(axis=0)
feats.extend([s0.min(), s0.max(), s0.mean(), s1.min(), s1.max(), s1.mean()])
return feats
def searchtfjab(self,searchList , documentList):
queryVector = self.getVectorKeywordIndex(searchList)
self.documentVectors = self.getVectorKeywordIndexSeprated(documentList)
ratings = [util.jaccard(queryVector , documentVector) for documentVector in self.documentVectors]
return ratings
