Python stanford.NERTagger类代码示例

def ngramTagger(l):
    """
    This function takes a list of ngrams, creates bigrams and entity tags them.
    :param l: input must be a list of bigrams, formed in tuples
    :return: returns a list with words that are tagged. (For example, "El Salvador" would be [("El", "LOCATION"),
    ("Salvador", "LOCATION")]
    """
    bigrams_ner = []
    bigrams_wn = []
    bigrams = []
    tb = []
    for i in l:
        ngram_ner = i[0] + " " + i[1]
        ngram_wn = i[0] + "_" + i[1]
        bigrams_ner.append(ngram_ner)
        bigrams_wn.append(ngram_wn)
        bigrams.append((ngram_ner, ngram_wn))

    class3 = NERTagger('stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz',
                       'stanford-ner/stanford-ner.jar')
    tagged_bigrams = class3.tag(bigrams_ner)
    for l in tagged_bigrams:
        for t in l:
            if len(t[1]) > 3:
                if t[1] != "LOCATION":
                    tb.append(t)
    for bg in bigrams:
        tag_bg = bgWordNetTagger(bg[0], bg[1])
        if tag_bg == "COUNTRY" or tag_bg == "STATE" or tag_bg == "CITY" or tag_bg == "TOWN":
            words = bg[0].split()
            tb.extend([(words[0], tag_bg), (words[1], tag_bg)])
    print(tb)

def ner_tag(sents, silent=True) :
    """ Named Entety Recognition for sentences.

        Keyword arguments:
            sents -- Sentece, list of sentences or list of tokens.
        Returns :
            List of (word,neg-tag) pairs, that aims to preserve the structure of the sents input argument.
    """

    if len(sents) == 0 :
        return []

    # saves ner_tagger as global variable,
    # such that it is not recreated everytime ner_tag is executed
    if not 'ner_tagger' in globals():
        global ner_tagger
        ner_tagger = NERTagger(stanford_ner_classifier, stanford_ner)

    # if sentence not tokenized
    if type(sents) in [str,unicode] :
        sents = tokenize(sents,'sw')

    # bring input sents in right form
    elif type(sents[0]) in [str,unicode] :
        if ' ' in sents[0] :
            sents = [tokenize(s,'w') for s in sents]
        else :
            sents = [sents]

    tagged = ner_tagger.tag_sents(sents)

    if not silent :
        print('ner-tags:', tagged)

    return tagged

def entityTagger():
    """
    Tags nouns in given file, writes them to output file
    :rtype : object
    """
    class3 = NERTagger('stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz',
                       'stanford-ner/stanford-ner.jar')
    output = open("entity.tagged", "w")
    with open("pos.tagged", "r") as inp_file:
        for l in inp_file:
            line = l.split()
            # If words is a noun, go tag it!
            print(line)
            if line[5] == "NN" or line[5] == "NNP":
                ner_tagged = class3.tag([line[4]])
                for t in ner_tagged[0]:
                    # No nertag? Check wordnet tagging
                    if len(t[1]) < 3:
                        tag = wordNetTagger(t[0])
                        data = ("{:8}{:8}{:8}{:8}{:60}{:6}{:13}".format(line[0], line[1], line[2], line[3], line[4],
                                                                        line[5], tag))
                        output.write(data+"\n")
                    else:
                        data = ("{:8}{:8}{:8}{:8}{:60}{:6}{:13}".format(line[0], line[1], line[2], line[3], line[4],
                                                                        line[5], t[1]))
                        output.write(data+"\n")
            else:
                data = ("{:8}{:8}{:8}{:8}{:60}{:6}{:13}".format(line[0], line[1], line[2], line[3], line[4], line[5],
                                                                "-"))
                output.write(data+"\n")
    output.close()

def main():
	#os.environ['JAVAHOME'] = "C:\Program Files\Java\jdk1.8.0_45/bin"
	path="ner"
	classifier = path + "/classifiers/" + "english.muc.7class.distsim.crf.ser.gz"
	jar = path + "/stanford-ner-3.4.jar"
	tagger = NERTagger(classifier, jar)

	tokens = tokenize('ada_lovelace.txt')
	

	taggedText = tagger.tag(tokens)
	

	countList=[]
	nounList = []
	for word, tag in taggedText:
		countList.append(tag)
		if tag != 'O':
			nounList.append(word)
			

	
	print("Answer to 2.1: \n{} \nThey certainly aren't all correct.".format(Counter(countList)))
	print()
	print("Answer to 2.2: The other classifiers seem to achieve similar results,\nbut because of the multiple categories it is more interesting to read.")

	lemmas = lemmatize(nounList)
	taggedLemmas = tagger.tag(lemmas)
	print("Answer to 2.3:\n", taggedLemmas)

def sdfprocess(rawexpr):
    parser=NERTagger(path_to_model='/home/cosmo/Dropbox/Purdue/nlp/stanford-corenlp-full-2014-08-27/english.all.3class.distsim.crf.ser.gz', path_to_jar='/home/cosmo/Dropbox/Purdue/nlp/stanford-corenlp-full-2014-08-27/stanford-corenlp-3.4.1.jar', java_options='-mx2000m')
    expr = preprocess(rawexpr)
    named_expr = rechunk(parser.tag(word_tokenize(expr)))
    for t in named_expr:
        if t[1] == 'PERSON':
            return t[0]
    return expr

def ngramTagger(l):
    """
    this function creates bigrams, tags them via Stanford NER or Word Net, and searches links for wiki pages.
    :param l: input must be a list of bigrams, formed in tuples
    :return: returns a list with words that are tagged and linked to wikipedia.
    """
    print("checking ngrams")
    nerts = []

    # First, create words which are suited as input for NERTagger.
    for i in l:
        ngram_ner = i[0] + " " + i[1]
        nerts.append(ngram_ner)

    # Input the list of suitable bigrams in the NERTagger, and form the output to a wanted format with nerToBG()
    class3 = NERTagger('stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz',
                       'stanford-ner/stanford-ner.jar')
    ner_result = class3.tag(nerts)
    bigramsAndTags = nerToBG(ner_result)

    for t in bigramsAndTags:
        # If tagged as location, get rid of location via the same technique as locationTagger(), but then for bigrams,
        # using getRidOfLocation()
        if t[1] == "LOCATION" or t[2] == "LOCATION":
            wn_bg = t[0].split()[0] + "_" + t[0].split()[1]
            wAndTag = getRidOfLocation(wn_bg)
            t[1] = wAndTag[1]
            t[2] = wAndTag[1]

    final_list = []
    a = 0
    for j in range(len(bigramsAndTags)):
        # If the 2 words of the bigram are tagged the same, append them to final_list.
        if bigramsAndTags[a][1] == bigramsAndTags[a][2]:
            final_list.extend([(bigramsAndTags[a][0], bigramsAndTags[a][1])])
        # If word 1 isn't tagged and word 2 is, check if word 1 is tagged in the development set.
        # If this tag is the same as the tag of word 2, append to final_list.
        elif checkBGTag(bigramsAndTags[a][0].split()[0]) == bigramsAndTags[a][2]:
            final_list.extend([(bigramsAndTags[a][0], bigramsAndTags[a][2])])
        # If word 2 isn't tagged and word 1 is, check if word 2 is tagged in the single word tagged development set.
        # If this tag is the same as the tag of word 1, append to final_list.
        elif checkBGTag(bigramsAndTags[a][0].split()[1]) == bigramsAndTags[a][1]:
            final_list.extend([(bigramsAndTags[a][0], bigramsAndTags[a][1])])
        a += 1

    taglink_bigrams = []
    for bgs in final_list[:]:
        # If bigrams are still not tagged, remove them from the list.
        if len(bgs[1]) < 4:
            final_list.remove(bgs)
        else:
            # If they are tagged, look up wikipedia links.
            links = wiki_lookup(bgs[0], bgs[1])
            words = bgs[0].split(" ")
            taglink_bigrams.extend([(words[0], bgs[1], links), (words[1], bgs[1], links)])

    return taglink_bigrams

def tagger(data):
	try:
		st=NERTagger('./nltk-data/StanfordNER/english.all.3class.distsim.crf.ser.gz','./nltk-data/StanfordNER/stanford-ner.jar')
	except:
		return ret_failure(705)
	#try:
	tag = st.tag(data.split())
	#except:
	#	return ret_failure(702)
	return ret_success(tag)

def queryForEntity2(expectedEntity,passage):
    st = NERTagger('/Users/srinisha/Downloads/stanford-ner-2014-06-16/classifiers/english.all.3class.distsim.crf.ser.gz','/Users/srinisha/Downloads/stanford-ner-2014-06-16/stanford-ner.jar') 
    answer=st.tag(passage.split()) 
    print answer
    answers=[]
    for j,currentExpectedEntity in enumerate(expectedEntity):
        for i,pair in enumerate(answer):
            if(pair[1]==currentExpectedEntity):
                answers.append(answer[i])   
    return answers

def compute_NER(corpus):
      NER=[]
      #fi=open("NER_features_train.txt","w")
      st = NERTagger(read_property('StanfordNerClassifier'),read_property('StanfordNerJarPath'))
      for sentence in corpus:
            ner=st.tag(sentence.split())
            ner_tag=""
            for n in ner:
                  ner_tag=ner_tag+n[1]+" "
            NER.append(ner_tag)
      return NER

def main():
    words = ["Barack Obama", "Holland", "Government", "Tennis", "happiness"]

    noun_lemmas = []
    nouns = []
    final_ner_tagged = []
    not_ner_tagged = []
    pos_tags = nltk.pos_tag(words)
    lemmatizer = WordNetLemmatizer()

    class3 = NERTagger('stanford-ner/classifiers/english.all.3class.distsim.crf.ser.gz',
                       'stanford-ner/stanford-ner.jar')

    # STANFORD NERTAGGING HAPPENS HERE
    for tag in pos_tags:
        if tag[1] == 'NNP':
            nouns.append(tag[0])
        elif tag[1] == 'NN':
            nouns.append(tag[0])

    ner_tagged = class3.tag(nouns)
    for t in ner_tagged[0]:
        if t[1] == u'O':
            not_ner_tagged.append(t[0])
        else:
            final_ner_tagged.append(t)
    print("NERTagged:")
    print(final_ner_tagged)

    entities = {
        "COUNTRY": wordnet.synsets("country", pos='n'),
        "STATE": wordnet.synsets("state", pos='n'),
        "CITY": wordnet.synsets("city", pos='n'),
        "TOWN": wordnet.synsets("town", pos='n'),
        "NAT": wordnet.synsets("natural places", pos='n'),
        "PER": wordnet.synsets("person", pos='n'),
        "ORG": wordnet.synsets("organisation", pos='n'),
        "ANI": wordnet.synsets("animal", pos='n'),
        "SPO": wordnet.synsets("sport", pos='n'),
        "ENT": wordnet.synsets("entertainment", pos='n'),
    }

    tagged_top_entities = defaultdict(list)
    for word in pos_tags:
        if word[1] == "NN" or word[1] == "NNP":
            noun_lemmas.append(lemmatizer.lemmatize(word[0], wordnet.NOUN))
            word_synset = wordnet.synsets(word[0], pos="n")
            for e in list(entities.keys()):
                if len(word_synset) != 0 and len(entities[e]) != 0:
                    if hypernymOf(word_synset[0], entities[e][0]):
                        tagged_top_entities[word[0]].append(e)
    print("WordNet tagged:")
    for w in tagged_top_entities:
        print("{:15}{:15}".format(w, tagged_top_entities[w]))

def german_ner(text):
	""" Moves the list of words through the NER tagger"""

	text = text.encode('utf8')  

	st = NERTagger('/Users/Lena/src/context/stanford-ner/classifiers/german/dewac_175m_600.crf.ser.gz',
                '/Users/Lena/src/context/stanford-ner/stanford-ner.jar', 'utf8') 

	tagged = st.tag(text.split())

	return tagged  

def spanish_ner(text):
	""" Moves the list of words through the NER tagger"""

	text = text.encode('utf8')


	st = NERTagger('/Users/Lena/src/context/stanford-ner/edu/stanford/nlp/models/ner/spanish.ancora.distsim.s512.crf.ser.gz',
                '/Users/Lena/src/context/stanford-ner/stanford-ner.jar', 'utf8') 

	tagged = st.tag(text.split())

	return tagged  

	def findWord(self):
		"""

		"""
		st = NERTagger('stanford-ner-2014-01-04/classifiers/english.muc.7class.distsim.crf.ser.gz','stanford-ner-2014-01-04/stanford-ner.jar')
		tagged= st.tag(self.question.split())
		for item in tagged:
			if item[1]== self.queryType:
				#print item[0]
				return item[0]

		return -1

 def add_ner(self,target):
     all_token = self.get_token(target);
     st = \
     NERTagger('../stanford-ner-2015-04-20/classifiers/english.all.3class.distsim.crf.ser.gz','../stanford-ner-2015-04-20/stanford-ner.jar');
     ner_result = st.tag_sents(all_token);
     w = open('ner_%s'%target,'wb');
     for num,row in enumerate(ner_result):
         for item in row:
             w.write(item[0]+'\n');
         w.write('\n');
     #end for 
     print len(ner_result),len(all_token);
     return;

    def run_tagger(self, payload):
        """
        Runs :py:meth:`nltk.tag.stanford.NERTagger.tag_sents` on the provided
        text (http://www.nltk.org/api/nltk.tag.html#nltk.tag.stanford.NERTagger.tag_sents)

        :param payload: Fulltext payload.
        :type payload: string
        :return: List of parsed sentences.
        """
        if NERTagger is None:
            return None
        tagger = NERTagger(self.classifier, self.jarfile)
        return tagger.tag_sents([payload.encode('ascii', 'ignore').split()])