def recompute(self, mins, thresh): self.CandidateTerms = [] self.FreqCandidates = [] self.Candidates = [] self.threshold = thresh stringlist.__init__(self) self.db.getCandidateTermsMinsupp(mins) self.extend(self.db.T) self.getCandidates() totalmensions = 0.0 for candidate in self.Candidates: totalmensions += candidate[0] for candidate in self.Candidates: candidate[0] /= totalmensions if candidate[0] > self.threshold: stringlist.append(self,candidate[1]) for trashterm in self.trashterms: if trashterm in self: stringlist.remove(self,trashterm) self.normalizeterms()
def recompute(self, mins, thresh): self.CandidateTerms = [] self.FreqCandidates = [] self.Candidates = [] self.threshold = thresh stringlist.__init__(self) self.db.getCandidateTermsMinsupp(mins) self.extend(self.db.T) self.getCandidates() totalmensions = 0.0 for candidate in self.Candidates: totalmensions += candidate[0] for candidate in self.Candidates: candidate[0] /= totalmensions if candidate[0] > self.threshold: stringlist.append(self, candidate[1]) for trashterm in self.trashterms: if trashterm in self: stringlist.remove(self, trashterm) self.normalizeterms()
def trash(self, trashterm): print '_'+trashterm+'_' if trashterm in self: stringlist.remove(self,trashterm) self.trashterms.append(trashterm)
def trash(self, trashterm): print '_' + trashterm + '_' if trashterm in self: stringlist.remove(self, trashterm) self.trashterms.append(trashterm)