Python nltk.wordpunct_tokenize函数代码示例

	def do_it(self, sources):

		for source in sources:
			words = nltk.wordpunct_tokenize(source.headline)
			words.extend(nltk.wordpunct_tokenize(source.summary))
			lowerwords=[x.lower() for x in words if len(x) > 1]
			self.ct += 1
			print self.ct, "TITLE",source.headline
			self.corpus.append(lowerwords)
			self.titles.append(source.headline)
			self.links.append(source.url)



		[[self.key_word_list.add(x) for x in self.top_keywords(self.nkeywords,doc,self.corpus)] for doc in self.corpus]

		self.ct=-1
		for doc in self.corpus:
		   self.ct+=1
		   print self.ct,"KEYWORDS"," ".join(self.top_keywords(self.nkeywords,doc,self.corpus))



		for document in self.corpus:
			vec=[]
			[vec.append(self.tfidf(word, document, self.corpus) if word in document else 0) for word in self.key_word_list]
			self.feature_vectors.append(vec)



		self.n=len(self.corpus)

		mat = numpy.empty((self.n, self.n))
		for i in xrange(0,self.n):
		  for j in xrange(0,self.n):
			mat[i][j] = nltk.cluster.util.cosine_distance(self.feature_vectors[i],self.feature_vectors[j])


		Z = linkage(mat, 'single')

		dendrogram(Z, color_threshold=self.t)





		clusters = self.extract_clusters(Z,self.t,self.n)
		
		stories = []

		for key in clusters:
			print "============================================="
			story = Story()  
			for id in clusters[key]:
				story.add_source(sources[id])
				print id,self.titles[id],sources[id].url
			stories.append(story)


		return stories

	def getDomainUnigram(self, directory = None):		
		collocations = set()  #collocation items
		ewordlists = list() #list of lists of words
		
		#extract words from essays
		if directory is not None:
			doclist = os.listdir(directory)
			for essay in doclist:
				dir_essay  = directory+'/'+essay
				etext = open(dir_essay,'r').read()
				tokens = nltk.wordpunct_tokenize(etext)
				tokens = [word.lower() for word in tokens]
				#stemming
				if self._stemoption ==True:
					st = PorterStemmer()
					tokens = [st.stem(t) for t in tokens]
				
				#extract the collocation for the given essay
				e_bigram = set(Mytext(tokens).collocations())
				collocations = collocations | e_bigram
				ewordlists.append(tokens)
				
		else: # using the mapped essay to calcuate the candidate bigrams
			#need to call mapessay fuction first
			for ins in self._data:
				if ins['essay'] is not None:
					etext = open(ins['essay'],'r').read()
					tokens = nltk.wordpunct_tokenize(etext)
					tokens = [word.lower() for word in tokens]
					#stemming
					if self._stemoption ==True:
						st = PorterStemmer()
						tokens = [st.stem(t) for t in tokens]
				
					#extract the collocation for the given essay
					e_bigram = set(Mytext(tokens).collocations())
					collocations = collocations | e_bigram
					ewordlists.append(tokens)
		
		#get collection of all essays under the specified directory / associated essays
		collection_text = TextCollection(ewordlists)
		
		itemlist = list()
		for (a, b) in collocations:
			itemlist.append(a)
			itemlist.append(b)
			
		itemlist = list(set(itemlist))	
		
		word_idf = []
		for i in range(len(itemlist)):
			word_idf.append((collection_text.idf(itemlist[i]), itemlist[i]))	
		
		word_idf = sorted(word_idf, key = operator.itemgetter(0))
		ave = 0
		if len(word_idf)!=0:
			ave = sum(map(operator.itemgetter(0), word_idf)) / len(word_idf)
			
		wlist =  [j for (i, j) in word_idf if i<ave]				
		return wlist

def get_utterances(utterances, line, category, wgram, cgram):
    tknzr = TweetTokenizer()
    gram_list = []
    # WORD GRAMS
    if wgram == 1:  # unigram
        wgram_list = tknzr.tokenize(line)
    elif wgram == 2:  # uni + bigram
        # unigram list
        tokens = nltk.wordpunct_tokenize(line)
        # bigram list
        finder = BigramCollocationFinder.from_words(tokens)
        scored = finder.score_ngrams(bigram_measures.raw_freq)
        bigram_list = sorted(bigram for bigram, score in scored)
        # res
        wgram_list = tknzr.tokenize(line) + bigram_list
    elif wgram == 3: # uni + bi + trigram
        # unigram list
        tokens = nltk.wordpunct_tokenize(line)
        # bigram list
        bi_finder = BigramCollocationFinder.from_words(tokens)
        bi_scored = bi_finder.score_ngrams(bigram_measures.raw_freq)
        bigram_list = sorted(bigram for bigram, biscore in bi_scored)  
        # trigram list
        tri_finder = TrigramCollocationFinder.from_words(tokens)
        tri_scored = tri_finder.score_ngrams(trigram_measures.raw_freq)
        trigram_list = sorted(trigram for trigram, triscore in tri_scored)
        # res
        wgram_list = tknzr.tokenize(line) + bigram_list + trigram_list
    
    # CHAR GRAMS
    cgram_list = []
    if cgram == 1:   # uni-chargram
        cgram_list = [line[i:i+1] for i in range(len(line)-1)]
    elif cgram == 2: # bi-chargram
        cgram_list = [line[i:i+2] for i in range(len(line)-1)]
    elif cgram == 3: # tri-chargram
        cgram_list = [line[i:i+3] for i in range(len(line)-1)]
        
    # RESULT
    if category == 'QA':            # non-task
        utterances.append((wgram_list + cgram_list, 0))
    elif category == 'Shopping':    # task
        utterances.append((wgram_list + cgram_list, 1))
    elif category == 'Travel':      # task
        utterances.append((wgram_list + cgram_list, 2))
    elif category == 'Hotel':       # task
        utterances.append((wgram_list + cgram_list, 3))
    elif category == 'Food':        # task
        utterances.append((wgram_list + cgram_list, 4))
    elif category == 'Art':         # task
        utterances.append((wgram_list + cgram_list, 5))
    elif category == 'Weather':     # task
        utterances.append((wgram_list + cgram_list, 6))
    elif category == 'Friends':     # task
        utterances.append((wgram_list + cgram_list, 7))
    elif category == 'Chat':        # chat
        utterances.append((wgram_list + cgram_list, 8))
    else:
        print utt_category,"ERROR"

def getArticleKeywords(articles, maxLength=3):
    """ Parse titles of a number of articles and extract keywords that occur
    in them. A keyword is defined as a grouping of several words, with punctuation
    and stopwords (*nltk.corpus.stopwords.words('english')*) removed. Will 
    also add keywords from every input Article into the corresponding entry
    in articles list.
    
    Arguments
    ----------
    articles - a list of Articles.
    maxLength - int, the largest number of tokens per keyword.
    
    Returns
    ----------
    2-tuple with numpy.ndarrays of shape (len(articles),) with
        * strings of keywords
        * ints with the number of occurrences of the given keyword in all titles
    
    Example
    ----------
    "A general theory of the plasma of an arc" would return keywords:
        ['A', 'general', 'theory', 'of', 'the', 'plasma', 'of', 'an', 'arc',
        'A general', 'general theory', 'theory of', 'of the', 'the plasma',
        'plasma of', 'of an', 'an arc', 'A general theory', 'general theory of',
        'theory of the', 'of the plasma', 'the plasma of', 'plasma of an', 'of an arc']
    Out of these, ['A','of','the','an','of the','of an'] would be filtered out.
    """
    
    # Identify keywords.
    tokens=[]
    for title in [art.Title for art in articles]:
        tokens.extend(nltk.wordpunct_tokenize(title))
    
    # Filter out meaningless words and punctuation.
    tokens=filter(lambda s: not s.lower() in nltk.corpus.stopwords.words('english') and
        not s in string.punctuation, tokens)

    # Find keywords (length 1, 2, or 3) and how often they occur in all the titles.
    keywords,frequencies=findNGrams(tokens,lengths=range(1,maxLength+1))
    keywords=numpy.array(keywords)
    frequencies=numpy.array(frequencies)
    sortedIndices=frequencies.argsort()[::-1] # Go in descending order of frequencies.
    frequencies=frequencies[sortedIndices]
    keywords=keywords[sortedIndices]

    # Assign keywords to Articles.
    for i in range(len(articles)):
        artTitleTokens=nltk.wordpunct_tokenize(articles[i].Title) # The tokens of this article's title.
        # Filter out meaningless words and punctuation.
        artTitleTokens=filter(lambda s: not s.lower() in nltk.corpus.stopwords.words('english') and
            not s in string.punctuation, artTitleTokens)
        
        # Use the same algorithm but for this article only.
        artKeywords,artFreq=findNGrams(artTitleTokens,lengths=[1,2,3])
        articles[i].Keywords=artKeywords
    
    return keywords,frequencies

def product_features(product):
    name = nltk.FreqDist(normalize_words(nltk.wordpunct_tokenize(product['name'])))
    desc = nltk.FreqDist(normalize_words(nltk.wordpunct_tokenize(product['description'])))
    feats = {}
    for word in name.keys():
        feats['name(%s)' % word] = True

    for word in desc.keys():
        feats['description(%s)' % word] = True
    return feats

  def do_it(self):

    for feed in self.feeds:
        d = feedparser.parse(feed)
        for e in d['entries']:
           words = nltk.wordpunct_tokenize(self.clean_html(e['description']))
           words.extend(nltk.wordpunct_tokenize(e['title']))
           lowerwords=[x.lower() for x in words if len(x) > 1]
           self.ct += 1
           print self.ct, "TITLE",e['title']
           self.corpus.append(lowerwords)
           self.titles.append(e['title'])
           self.links.append(e['link'])



    [[self.key_word_list.add(x) for x in self.top_keywords(self.nkeywords,doc,self.corpus)] for doc in self.corpus]

    self.ct=-1
    for doc in self.corpus:
       self.ct+=1
       print self.ct,"KEYWORDS"," ".join(self.top_keywords(self.nkeywords,doc,self.corpus))



    for document in self.corpus:
        vec=[]
        [vec.append(self.tfidf(word, document, self.corpus) if word in document else 0) for word in self.key_word_list]
        self.feature_vectors.append(vec)



    self.n=len(self.corpus)

    mat = numpy.empty((self.n, self.n))
    for i in xrange(0,self.n):
      for j in xrange(0,self.n):
        mat[i][j] = nltk.cluster.util.cosine_distance(self.feature_vectors[i],self.feature_vectors[j])


    Z = linkage(mat, 'single')

    dendrogram(Z, color_threshold=self.t)





    clusters = self.extract_clusters(Z,self.t,self.n)
     
    for key in clusters:
       print "============================================="  
       for id in clusters[key]:
           print id,self.titles[id]

def jaccard(sen_1, sen_2):
  tagged_sent = POSWrapper.pos_tag(nltk.wordpunct_tokenize(sen_1))
  words = [word for word,pos in tagged_sent if (pos == 'NN' or pos == 'NNS' or pos == 'JJ' or pos == '' or pos == 'VB' or pos == 'VBN' or pos == 'VBD' or pos == 'RB')]

  sen_set_1 = set(words)

  tagged_sent = POSWrapper.pos_tag(nltk.wordpunct_tokenize(sen_2))
  words = [word for word,pos in tagged_sent if (pos == 'NN' or pos == 'NNS' or pos == 'JJ' or pos == '' or pos == 'VB' or pos == 'VBN' or pos == 'VBD' or pos == 'RB')]

  sen_set_2 = set(words)

  jaccard_value = jaccard_distance(sen_set_1, sen_set_2)
  return jaccard_value

def main():
  stem = nltk.stem.LancasterStemmer()
  cleanword = lambda w : stem.stem(w.strip(w).lower())
  bib = btparse.load(sys.argv[1])
  aid = np.random.randint(len(bib))
  while ('abstract' in bib[aid].keys()) == False:
    aid = np.random.randint(len(bib))
  
  abstract = nltk.wordpunct_tokenize(bib[aid]['abstract']+" "+bib[aid]['title'])
  q_vec0 = sorted([x[0] for x in nltk.pos_tag(abstract) if x[1] in ("NN")])
  
  q_vec = []
  q_val  = []
  for w in q_vec0:
    w = cleanword(w)
    if len(w)>2 and w not in ignore_list and re.search('\\\\',w) == None:
      if (w in q_vec) == False:
        q_vec.append(w)
        q_val.append(1)
      else:
        q_val[-1] += 1
  
  q_val = np.array(q_val)/np.sqrt(np.dot(q_val,q_val))
  prob = np.zeros(len(bib))
  
  if pytools:
    progress = pytools.ProgressBar("Analysing",len(bib))
    progress.draw()
  for ind,entry in enumerate(bib):
    if ind != aid and ('abstract' in bib[ind].keys()):
      abstract = nltk.wordpunct_tokenize(bib[ind]['abstract']+" "+bib[ind]['title'])
      r_vec = sorted([x[0] for x in nltk.pos_tag(abstract) if x[1] in ("NN")])
      r_val = np.zeros(len(q_val))
      for w in r_vec:
        w = cleanword(w)
        if w in q_vec:
          r_val[q_vec.index(w)] += 1
      mod = np.dot(r_val,r_val)
      if mod > 0:
        prob[ind] = np.dot(r_val/np.sqrt(mod),q_val)
    if pytools: progress.progress()
  if pytools: print ""
  
  # sort based on probability (best first)
  inds_sort = np.argsort(prob)[::-1]
  
  print 'similar papers to:\n\t%s\n\t\tby: %s\n'%(bib[aid]['title'],bib[aid]['author'])
  for i in range(10):
    best = inds_sort[i]
    print '%3d.\t%s\n\t\tby: %s\n\t\tid = %3d, prob = %f\n'%(i+1,bib[best]['title'],bib[best]['author'],best,prob[best])

def feedTech(request):
    corpus = []
    titles=[]
    ct = -1
    for feed in feeds:
        d = feedparser.parse(feed)
        for e in d['entries']:
            words = nltk.wordpunct_tokenize((e['description']))
            words.extend(nltk.wordpunct_tokenize(e['title']))
            lowerwords=[x.lower() for x in words if len(x) > 1]
            ct += 1
            print (ct, "TITLE",e['title'])
            corpus.append(lowerwords)
            titles.append(e['title'])
    return render(request, 'dash/feeds.html')

def tag_files_for_cross_validation(file_list, tmp_models):
    # first clean CV files folder
    if os.path.exists(CV_FILES_PATH_DEFAULT):
        shutil.rmtree(CV_FILES_PATH_DEFAULT)
    if os.path.exists(CV_FILES_PATH_PUNCT):
        shutil.rmtree(CV_FILES_PATH_PUNCT)
    if os.path.exists(CV_FILES_PATH_LOWER):
        shutil.rmtree(CV_FILES_PATH_LOWER)
    if os.path.exists(CV_FILES_PATH_LOWER_PUNCT):
        shutil.rmtree(CV_FILES_PATH_LOWER_PUNCT)

    # then create new CV folders
    os.makedirs(CV_FILES_PATH_DEFAULT)
    os.makedirs(CV_FILES_PATH_PUNCT)
    os.makedirs(CV_FILES_PATH_LOWER)
    os.makedirs(CV_FILES_PATH_LOWER_PUNCT)

    for file_name in file_list:
        path = ORIGINAL_STORIES + '/' + file_name + '.txt'

        if not os.path.isfile(path):
            print('File ' + path + ' does not exist!')
            continue

        content = get_content(path)
        content_lower = content.lower()
        tokenized_content = nltk.wordpunct_tokenize(content)
        tokenized_content_punct = nltk.word_tokenize(content)
        tokenized_content_lower = nltk.wordpunct_tokenize(content_lower)
        tokenized_content_lower_punct = nltk.word_tokenize(content_lower)

        tagged_content = tag_tokens_with_model(tokenized_content, tmp_models.default, lowercase=False, message=False)
        tagged_file_path = CV_FILES_PATH_DEFAULT + '/' + file_name + '.tsv'
        write_tagged_content_to_file(tagged_content, tagged_file_path, message=False)

        tagged_content = tag_tokens_with_model(tokenized_content_punct, tmp_models.punct, lowercase=False,
                                               message=False)
        tagged_file_path = CV_FILES_PATH_PUNCT + '/' + file_name + '.tsv'
        write_tagged_content_to_file(tagged_content, tagged_file_path, message=False)

        tagged_content = tag_tokens_with_model(tokenized_content_lower, tmp_models.lower, lowercase=True, message=False)
        tagged_file_path = CV_FILES_PATH_LOWER + '/' + file_name + '.tsv'
        write_tagged_content_to_file(tagged_content, tagged_file_path, message=False)

        tagged_content = tag_tokens_with_model(tokenized_content_lower_punct, tmp_models.lower_punct, lowercase=True,
                                               message=False)
        tagged_file_path = CV_FILES_PATH_LOWER_PUNCT + '/' + file_name + '.tsv'
        write_tagged_content_to_file(tagged_content, tagged_file_path, message=False)

def calculate_language_scores(text):
    """
    Calculate probability of given text to be written in several languages and
    return a dictionary that looks like {'french': 2, 'spanish': 4, 'english': 0}.

    :param text: Text to analyze.
    :type text: str

    :return: Dictionary with languages and unique stopwords seen in analyzed text.
    :rtype: dict(str -> int)

    :raises: TypeError
    """
    if not isinstance(text, basestring):
        raise TypeError("Expected basestring, got '%s' instead" % type(text))
    if not text:
        return {}

    languages_ratios = {}

    # Split the text into separate tokens, using natural language punctuation signs.
    tokens = wordpunct_tokenize(text)
    tokenized_words = [word.lower() for word in tokens]

    for language in stopwords.fileids():
        stopwords_set = set(stopwords.words(language))
        words_set = set(tokenized_words)
        common_elements = words_set.intersection(stopwords_set)
        languages_ratios[language] = len(common_elements)  # language "score"

    return languages_ratios

def translateHinglishTweets(tweets_text):
	counter = 0
	tweets_text_translated = []
	n = len(tweets_text)

	open_file = open("dictionary.pickle", "rb")
	dictionary = pickle.load(open_file)
	open_file.close()

	english_stopwords_set = set(stopwords.words('english'))

	for i in range(n):
		text = tweets_text[i]
		translated_text = ""
		tokens = wordpunct_tokenize(text)
		words = [word.lower() for word in tokens]
		for word in words:
			if word in english_stopwords_set:
				translated_text = translated_text + " " + word
			elif (word in dictionary):
				#print word + "-" + dictionary[word]
				translated_text = translated_text + " " + dictionary[word]
				counter = counter + 1
			else:
				translated_text = translated_text + " " + word
		tweets_text_translated.append(translated_text)

	#print counter
	return tweets_text_translated

def statScore(text,d_index):
	tokens = nltk.wordpunct_tokenize(text)
	val = 0
	for token in tokens:
		w_index = vocabulary.index(token)
		val = val + self.stat_lte[w_index][d_index]
	return val

def tokenize(text):
    """This handles tokenizing and normalizing everything."""
    return [
        token.lower()
        for token in nltk.wordpunct_tokenize(text)
        if token.isalnum()
    ]

def convert_to_weka(src, des, voc):
    stemmer = nltk.LancasterStemmer()
    word_reg = re.compile('[0-9A-Za-z]+')
    
    des.write('@relation review_rate\n')
    des.write('\n')
    
    for word in voc:
        des.write('@attribute ' + word + ' real\n')
    des.write('@attribute rate {s1,s2,s3,s4,s5}\n')
    des.write('\n')
    
    des.write('@data\n')
    for line in iter(src.readline, ''):
        feature_vector = []
        try:
            rate, title, review = [item.strip() for item in line.split('\t')[5:8]]
        except (IndexError, ValueError):
            continue
        ws = set([])
        for w in nltk.wordpunct_tokenize(title + ' ' + review):
            m = word_reg.match(w)
            if m:
                ws.add(stemmer.stem(m.group(0).lower()))
        for w in voc:
            if w in ws:
                feature_vector.append('1')
            else:
                feature_vector.append('0')
        des.write(','.join(feature_vector) + ',' + 's' + str(int(math.ceil(float(rate)))) + '\n')
        
    return