如何使用python postagger检测aboutness

这就是我发现的有用之处,我要编辑它并将其与nltk pos tagger一起使用,看看我能得到什么结果。

import nltk
from nltk.corpus import brown

# http://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/


# This is our fast Part of Speech tagger
#############################################################################
brown_train = brown.tagged_sents(categories='news')
regexp_tagger = nltk.RegexpTagger(
    [(r'^-?[0-9]+(.[0-9]+)?$', 'CD'),
     (r'(-|:|;)$', ':'),
     (r'\'*$', 'MD'),
     (r'(The|the|A|a|An|an)$', 'AT'),
     (r'.*able$', 'JJ'),
     (r'^[A-Z].*$', 'NNP'),
     (r'.*ness$', 'NN'),
     (r'.*ly$', 'RB'),
     (r'.*s$', 'NNS'),
     (r'.*ing$', 'VBG'),
     (r'.*ed$', 'VBD'),
     (r'.*', 'NN')
])
unigram_tagger = nltk.UnigramTagger(brown_train, backoff=regexp_tagger)
bigram_tagger = nltk.BigramTagger(brown_train, backoff=unigram_tagger)
#############################################################################


# This is our semi-CFG; Extend it according to your own needs
#############################################################################
cfg = {}
cfg["NNP+NNP"] = "NNP"
cfg["NN+NN"] = "NNI"
cfg["NNI+NN"] = "NNI"
cfg["JJ+JJ"] = "JJ"
cfg["JJ+NN"] = "NNI"
#############################################################################


class NPExtractor(object):

    def __init__(self, sentence):
        self.sentence = sentence

    # Split the sentence into singlw words/tokens
    def tokenize_sentence(self, sentence):
        tokens = nltk.word_tokenize(sentence)
        return tokens

    # Normalize brown corpus' tags ("NN", "NN-PL", "NNS" > "NN")
    def normalize_tags(self, tagged):
        n_tagged = []
        for t in tagged:
            if t[1] == "NP-TL" or t[1] == "NP":
                n_tagged.append((t[0], "NNP"))
                continue
            if t[1].endswith("-TL"):
                n_tagged.append((t[0], t[1][:-3]))
                continue
            if t[1].endswith("S"):
                n_tagged.append((t[0], t[1][:-1]))
                continue
            n_tagged.append((t[0], t[1]))
        return n_tagged

    # Extract the main topics from the sentence
    def extract(self):

        tokens = self.tokenize_sentence(self.sentence)
        tags = self.normalize_tags(bigram_tagger.tag(tokens))

        merge = True
        while merge:
            merge = False
            for x in range(0, len(tags) - 1):
                t1 = tags[x]
                t2 = tags[x + 1]
                key = "%s+%s" % (t1[1], t2[1])
                value = cfg.get(key, '')
                if value:
                    merge = True
                    tags.pop(x)
                    tags.pop(x)
                    match = "%s %s" % (t1[0], t2[0])
                    pos = value
                    tags.insert(x, (match, pos))
                    break

        matches = []
        for t in tags:
            if t[1] == "NNP" or t[1] == "NNI":
            #if t[1] == "NNP" or t[1] == "NNI" or t[1] == "NN":
                matches.append(t[0])
        return matches


# Main method, just run "python np_extractor.py"
Summary="""


Verizon has not honored this appointment or notified me of the delay in an appropriate manner. It is now 1:20 PM and the only way I found out of a change is that I called their chat line and got a message saying my appointment is for 2 PM. My cell phone message says the original time as stated here.


"""
def main(Topic):
    facebookData=[]
    readdata=csv.reader(open('fb_data1.csv','r'))
    for row in readdata:
        facebookData.append(row)
    relevant_sentence=[]
    for status in facebookData:
        summary=status.split('.')
        for sentence in summary:
            np_extractor = NPExtractor(sentence)
            result = np_extractor.extract()
            if Topic in result:
                relevant_sentence.append(sentence)
            print sentence
            print "This sentence is about: %s" % ", ".join(result)
        return relevant_sentence

if __name__ == '__main__':
    result=main('Verizon')

注意,它将只保存与您定义的主题相关的句子。因此,如果我在分析奶酪的状态,我可以将其作为主题,提取奶酪上的所有句子,然后对这些句子进行情感分析。如果您对改进这一点有意见或建议,请告诉我!