Python metrics.edit_distance函数代码示例

def get_abstract_by_title(title):
	print '>>>>>>>>>>>>>>>>>>>>>>>>>>'
	print 'searching entry with title: ' + title
	fetch = metapub.PubMedFetcher()
	pmids = fetch.pmids_for_query(title)
	if (len(pmids) == 0):
		print 'warning: no entry retrieved for given title'
		return None, ''
	elif (len(pmids) == 1):
		article = fetch.article_by_pmid(pmids[0])
		if edit_distance(article.title, title) <= math.ceil(len(title) * 0.1) and article.abstract != None:
			print 'successfully matched title: ' + article.title
			return article.title, article.abstract
		else:
			print 'warning: found one entry but not a match'		
			return None, ''
	else:
		print 'warning: retrieved more than one entry for given title'
		for i in range(min(20, len(pmids))):
			article = fetch.article_by_pmid(pmids[i])
			if edit_distance(article.title, title) <= math.ceil(len(title) * 0.1) and article.abstract != None:
				print 'successfully matched title: ' + article.title
				return article.title, article.abstract
		print 'warning: no entry is a match'
		return None, ''

def get_related_evidence(title):
	print '>>>>>>>>>>>>>>>>>>>>>>>>>>'
	try:
		print 'given title: ' + title
	# TODO: fix this...
	except UnicodeEncodeError:
		print 'title cannot be printed - containing unicode encode error'
		return [], {}, 0
	fetch = metapub.PubMedFetcher()
	pmids = fetch.pmids_for_query(title)
	if len(pmids) == 1:
		article = fetch.article_by_pmid(pmids[0])
		if edit_distance(article.title, title) <= len(title) * 0.1:
			print 'matched title: ' + article.title.encode('utf-8')
			related_pmids = fetch.related_pmids(pmids[0])
			return _merge_related_pmids(pmids[0], related_pmids, fetch)
	elif len(pmids) > 1:
		for i in range(min(20, len(pmids))):
			article = fetch.article_by_pmid(pmids[i])
			if edit_distance(article.title, title) <= len(title) * 0.1:
				print 'matched title: ' + article.title.encode('utf-8')
				related_pmids = fetch.related_pmids(pmids[i])
				return _merge_related_pmids(pmids[i], related_pmids, fetch)

	print 'no match found'
	return [], {}, 0

    def matches_author(self, string, fuzzy=False, distance_threshold=3):
        """
        This function retrieves from the KnowledgeBase possible authors that match the search string.
        None is returned if no matches are found.

        :param string: the string to be matched

        :param fuzzy: whether exact or fuzzy string matching should be applied

        :distance_threshold: the maximum edit distance threshold (ignored if `fuzzy==False`)

        :return: a list of tuples, ordered by distance between the seach and the matching string, where:
                tuple[0] contains the id (i.e. CTS URN) of the matching author
                tuple[1] contains a label of the matching author
                tuple[2] is the distance, measured in characters, between the search string and the matching string
                or None if no match is found.
        """
        #string = string.lower()
        author_matches, abbr_matches = [],[]

        if(not fuzzy):

            author_matches = [(id.split("$$")[0]
                            , self._author_names[id]
                            , len(self._author_names[id])-len(string))
                             for id in self._author_idx.searchAllWords(string)]

            abbr_matches = [(id.split("$$")[0]
                            , self._author_abbreviations[id]
                            , len(self._author_abbreviations[id])-len(string))
                            for id in self._author_abbr_idx.searchAllWords(string)]
        else:
            abbr_matches = [(id.split("$$")[0]
                            , self._author_abbreviations[id]
                            , edit_distance(string,self._author_abbreviations[id]))
                            for id in self._author_abbreviations
                            if edit_distance(string,self._author_abbreviations[id]) <= distance_threshold]

            abbr_matches = sorted(abbr_matches, key =itemgetter(2))
            author_matches = []

            for id in self._author_names:
                if(string.endswith(".")):
                    if string.replace(".","") in self._author_names[id]:
                        if(len(string) > (len(self._author_names[id]) / 2)):
                            try:
                                assert abbr_matches[0][2] == 0
                                distance = len(self._author_names[id]) - len(string)
                                if distance < 0:
                                    distance = 1
                                author_matches.append((id.split("$$")[0], self._author_names[id],distance))
                            except Exception, e:
                                author_matches.append((id.split("$$")[0], self._author_names[id],0))
                        else:
                            if(edit_distance(string,self._author_names[id]) <= distance_threshold):
                                author_matches.append((id.split("$$")[0], self._author_names[id], edit_distance(string,self._author_names[id])))
                else:
                    if(edit_distance(string,self._author_names[id]) <= distance_threshold):
                        author_matches.append((id.split("$$")[0], self._author_names[id], edit_distance(string,self._author_names[id])))

def searchEvidenceByTitle(request):
    if request.method == 'POST':
        data = json.loads(request.body)
        collection_id = data['collection_id']
        title = data['title']
        result_limit = data['result_limit']
        include_personal = data['include_personal']
        user_id = data['user_id']
        # DONE: we can alternatively change this to treat given title as a series of separated terms
        title_terms = title.split(' ')
        print title_terms
        evidence = Evidence.objects.filter(Q(created_by=collection_id)&reduce(lambda x, y: x & y, [Q(title__icontains=word) for word in title_terms]))
        if include_personal:
            personal_evidence = Evidence.objects.filter(Q(created_by=user_id)&reduce(lambda x, y: x & y, [Q(title__icontains=word) for word in title_terms]))
            evidence = chain(evidence, personal_evidence)
        serialized_json = serializers.serialize('json', evidence)
        evidence_json = flattenSerializedJson(serialized_json)
        evidence = json.loads(evidence_json)
        pprint.pprint(evidence)
        for e in evidence:
            e['dist'] = edit_distance(title, e['title'])
        print 'result limit'
        print result_limit
        evidence = sorted(evidence, key=lambda e:e['dist'])[:result_limit]
        for e in evidence:
            e['topic'] = -1
            try:
                e['topic'] = EvidenceTopic.objects.get(evidence=e['id']).primary_topic
            except ObjectDoesNotExist:
                if len(e['abstract']) > 50:
                    name = Collection.objects.get(collection_id=collection_id).collection_name
                    topic_dist, primary_topic_terms = TopicModeler.get_document_topics(e['abstract'], name)
                    primary_topic_tuple = max(topic_dist, key=lambda x:x[1])
                    e['topic'] = primary_topic_tuple[0]
                else:
                    print 'warning: evidence with no topic'
        return HttpResponse(json.dumps(evidence), status=status.HTTP_200_OK)

    elif request.method == 'GET':
        collection_id = 13
        title = 'UpSet: Visualization of Intersecting Sets'
        evidence = Evidence.objects.filter(created_by=collection_id)
        serialized_json = serializers.serialize('json', evidence)
        evidence_json = flattenSerializedJson(serialized_json)
        evidence = json.loads(evidence_json)
        for e in evidence:
            e['dist'] = edit_distance(title, e['title'])
        evidence = sorted(evidence, key=lambda e:e['dist'])
        return HttpResponse(json.dumps(evidence[:20]), status=status.HTTP_200_OK)

def string_matching(label1, label2): #by Maedchen and Staab
    """ (string, string) -> float
    
Return the coefficient of similarity between two sequence of strings based on
the Levenshtein distance (edit distance). It equates 1 for exact match and
0 to no similarity.
>>> string_matching('power','power')
1.0
>>> string_matching('power','abba')
0.0
"""
    sm = float(
        min(len(label1),len(label2)) - 
        edit_distance(label1, label2)
        ) / min(len(label1),len(label2)
        )    
    try:
        if sm < 0:
            return 0.0
        else:
            return sm
    except:
        print "Error found:"
        traceback.print_exc(file=sys.stdout)
        return 0

    def replace(self, word):
        if self.spell_dict.check(word):
            return word

        suggestions = []
        suggestions = self.spell_dict.suggest(word)

        distance = []
        print(distance)
        print(suggestions)

        retVal = ""
        for suggestedWord in suggestions:
            distance.append(edit_distance(word, suggestedWord))

        print(distance)
        lengthMatched = False

        if min(distance) <= self.max_dist:
            retVal = suggestions[distance.index(min(distance))]

            i = 0
            for ed in distance:
                if ed == min(distance) :
                    if len(word) == len(suggestions[i]) and lengthMatched == False:
                        retVal = suggestions[i]
                        lengthMatched = True
                i += 1
        else :
            retVal = word

        return retVal

 def _GetScore(self, query, match):
     """Custom edit-distance based scoring."""
     str_query = str(query)
     str_candidate = str(match.key)
     dist = float(edit_distance(str_query, str_candidate))
     max_len = float(max(len(str_query), len(str_candidate)))
     return (max_len - dist) / max_len

    def replace_word(self, word):
        if self.dictionary.check(word):
            return word

        suggestions = self.dictionary.suggest(word)
        if suggestions and edit_distance(word, suggestions[0]) <= self.max_dist:
            return suggestions[0]

    def replace(self, word):
        if self.spell_dict.check(word):
            return word

        distance = []
        suggestions = []
        suggestions = self.spell_dict.suggest(word)

        retVal = ""
        for suggestedWord in suggestions:
            distance.append(edit_distance(word, suggestedWord))

        if min(distance) <= self.max_dist:
            retVal = suggestions[distance.index(min(distance))]

            i = 0
            for ed in distance:
                if ed == min(distance) :
                    if len(word) == len(suggestions[i]):
                        retVal = suggestions[i]
                        break
                i += 1
        else:
            retVal = word

        return retVal

def spellChecker(sentences, file_name_s):
   dict_name  = 'en_GB'
   spell_dict = enchant.Dict(dict_name)
   max_dist   = 3
   corrected  = []
   csv_writer = csv.writer(open(file_name_s, 'wb'))
   #csv_writer.writerow(HEADER2)
   for sentence in sentences:
      corrected_sent = ''
      sentence = str(sentence)
      sc = set(["[", "]", "'", '"'])
      words = ''.join([c for c in sentence if c not in sc])
      words = words.split()
      #print words
      for word in words:
         print word
         suggestions = spell_dict.suggest(word)
         #print suggestions[0]
         #print edit_distance(word, suggestions[0])
         if suggestions and edit_distance(word, suggestions[0]) <= max_dist:
            #print word
            corrected_sent = corrected_sent + " " + suggestions[0]
         else:
            corrected_sent = corrected_sent + " " + word
            corrected_sent.replace("[","")
            corrected_sent.replace("]","")
            corrected_sent.replace("'","")
         #print corrected_sent
      corrected.append(corrected_sent)
      csv_writer.writerow([corrected_sent])
   print corrected

def fuzzy_comparison(tokens_1,tokens_2,max_dist=1):
  """ compares the tokens based on fuzzy match """
  matched = 0
  matched_len_1 = init_term_1 - len(tokens_1)
  matched_len_2 = init_term_2 - len(tokens_2)

  for token in reversed(tokens_1):
    if len(token)<=2:
      tokens_1.remove(token)
      continue
    for tkn in reversed(tokens_2):
      if len(tkn)<=2:
        tokens_2.remove(tkn)
        continue
      if metrics.edit_distance(token, tkn) <= max_dist:
	matched = matched + 1
        logging.debug("Match found for:"+token+" - "+tkn)
	tokens_2.remove(tkn)
	tokens_1.remove(token)
	break

  logging.info("Fuzzy match count:"+str(matched))
  score_1 = (matched_len_1 + matched)/float(init_term_1)
  score_2 = (matched_len_2 + matched)/float(init_term_2)
  return score_1,score_2

 def replace(self,word):
     if self.spell_dict.check(word):
         return word
     suggestions = self.spell_dict.suggest(word)
     if suggestions and edit_distance(word, suggestions[0]) <=self.max_dist:
         return suggestions[0]
     else:
         return word

def spell_check(r, a, s, scores, weight=1):
    change = weight*(1-(edit_distance(r, a)/float(max(len(r), len(a)))))
    if s in scores:
        # penalty for returning multiple of the same result when
        # one instance is incorrectly spelled
        return (scores[s] + change)/2.0
    else:
        return change

def check_replace_word(word):
    if spell_dict.check(word):
        return word
    suggestions = spell_dict.suggest(word)
    if suggestions and edit_distance(word, suggestions[0]) < 2:
        return suggestions[0]
    else:
        return word

    def ordered_content_distance(self, sentence, normalized=True):
        """Normalized levenshtein distance on (ordered) content words
        between `self` and `sentence`."""

        self_content_words = self.content_words
        sentence_content_words = sentence.content_words
        distance = edit_distance(self_content_words, sentence_content_words)
        norm = max(len(self_content_words), len(sentence_content_words))
        return distance / norm if normalized else distance