大二下学期第二次个人作业第二阶段

今日对爬取的论文进行了关键词分析，对文章内容解析提取出关键词，主要用到了python的自然语言处理等。

#文章关键词提取
# This is a fast and simple noun phrase extractor (based on NLTK)
# Feel free to use it, just keep a link back to this post
# http://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/
# Create by Shlomi Babluki
# May, 2013

# 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"
def print_key():
    flag=1;
    str_key = []
    str_word_cloud_top=[]
    for i in update_test():
        np_extractor = NPExtractor(i[0])
        result = np_extractor.extract()
        print(flag)
        print (i[0])
        str=""
        for j in result:
            str=str+j+"|"
        print(str)
        str_key.append([str,i[1]])
        flag=flag+1
    return (str_key)
##############################################################################

#获取top10
def word_cloud_top():
    word_all=[]
    word_num={}
    for i in update_test_word:
        np_extractor = NPExtractor(i[0])
        result = np_extractor.extract()
        word_all=word_all+result
    for item in word_all:
        if(item not in word_num):
            word_num[item]=word_all.count(item)
    c = Counter(word_num)
    top_10_word=c.most_common()
    return top_10_word
#获取top10的子热词