Python tokenize.RegexpTokenizer类代码示例

def preprocess(TWEETS, typeTweet):
    wordlist = []
    tokenizer = RegexpTokenizer(r'#?\w+') 
    #normalize text -- TOKENIZE USING REGEX TOKENIZER
    cnt = 0
    for item in TWEETS:
        text = TWEETS[cnt]
        tweet = ''.join(text)
        tweet = tweet.lower().strip('\n')
        
        tweet = re.sub(r'[0-9]+', "" , tweet)
        tweet = re.sub(r'@[^\s]+', "" , tweet)
        tweet = re.sub(r'#\w+primary', "" , tweet)                    
        wordlist.extend(tokenizer.tokenize(tweet))
        cnt += 1

    #remove stopwords
    stop = stopwords.words('english') + ['rt', 'via', 'u', 'r', 'b', '2', 'http', 
                                        'https', 'co', 'live', 'hall', 'town', 'watch', 
                                        'tune', 'time', 'tonight', 'today', 'campaign', 
                                        'debate', 'wants', 'without', 'dont', 
                                        '#hillaryclinton', '#berniesanders', '#donaldtrump', 
                                        '#tedcruz', "#johnkasich", '#politics']
    filtered = [term for term in wordlist if term not in stop] 
    filtered_final = [term for term in filtered if len(term)>3] 
    print 'Preprocessed %s tweets' % (typeTweet)
    return filtered_final

def lda(data):
	data = get_only_text(data)
	only_tweet = data
	length = len(only_tweet)
	length = min(20,length)
	for i in xrange(0,length):
		print i
		print only_tweet[i]
	return
	
	tokenizer = RegexpTokenizer(r'\w+')
	en_stop = get_stop_words('en')
	p_stemmer = PorterStemmer()

	length = len(only_tweet)
	length = min(20,length)
	total_texts = []
	for i in xrange(0,length):
		print only_tweet[i]
		print 
		to_lower = only_tweet[i].lower()
		tokens = tokenizer.tokenize(to_lower)
		stopped_tokens = [k for k in tokens if not k in en_stop]
		texts = [p_stemmer.stem(k) for k in stopped_tokens]
		total_texts.append(texts)

	dictionary = corpora.Dictionary(total_texts)
	corpus = [dictionary.doc2bow(text) for text in total_texts]

	ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=2, id2word = dictionary, passes=20)
	result =  ldamodel.print_topics(num_topics=2, num_words=1)
	for i in result:
		print i

def textToWordList(txt):
    p_stemmer = RussianStemmer()
    tokenizer = RegexpTokenizer(r'\w+')
    stop_w = [p_stemmer.stem(i) for i in get_stop_words('ru')]
    r = re.compile('^[а-я]+$')
    badword =[
        'дом',
        'город',
        "дорог",
        "час",
        "ноч",
        "слов",
        "утр",
        "стран",
        "пут",
        "путешеств",
        "мест",
        'нов',
        "друз",
        "добр"
    ]
    txt = txt.lower().replace("<br>", "\n")
    tokens = [p_stemmer.stem(i) for i in tokenizer.tokenize(txt)]
    tokens = [i for i in tokens if not i in stop_w and r.match(i) and not i in badword]
    return tokens

def Tokenize(TextData):
    tokenizer = RegexpTokenizer(r'\w+')
    tokens = list()

    # create English stop words list
    en_stop = get_stop_words('en')

    # Create p_stemmer of class PorterStemmer
    p_stemmer = PorterStemmer()

    # clean and tokenize document string
    raw = TextData.lower()
    tokens = tokenizer.tokenize(raw)

    # remove stop words from tokens
    stopped_tokens = [i for i in tokens if not i in en_stop]

    # stem tokens
    stemmed_tokens = [p_stemmer.stem(i) for i in stopped_tokens]
    tokens = stemmed_tokens

    TOKENIZEDTEXT_FILE = path.join(os.pardir, "Resources/TokenizedTextFiles/Personal-Narration/Unbroken - Motivational Video.txt")
    fp = open(TOKENIZEDTEXT_FILE, "w")
    print(TOKENIZEDTEXT_FILE)
    # pickle.dump(tokens, fp)
    fp.write(str(tokens))
    fp.close()

    def tokenize(self, doc):
        '''
        use NLTK RegexpTokenizer
        '''

        tokenizer = RegexpTokenizer("\w{3,}")
        return [self.stemmer.stem(x) for x in tokenizer.tokenize(doc)]

def text_process(text):
    '''
    Takes in a string of text, then performs the following
    1. Tokenizes and removes punctuation
    2. Removes stopwords
    3. Stems
    4. Returns a list of the cleaned text
    '''
    if(pd.isnull(text)):
        return []
    
    # Tokenize 
    tokenizer = RegexpTokenizer(r'\w+')
    text_processed = tokenizer.tokenize(text)
    
    # Removing any stopwords
    text_processed = [word.lower() for word in text_processed if word.lower() not in stopwords.words('english')]
    
    # Stemming
    porterStemmer = PorterStemmer()
    
    text_processed = [porterStemmer.stem(word) for word in text_processed]
    
    try:
        text_processed.remove('b')
        
    except:
        pass
    
    return " ".join(text_processed)

    def trainMarkovChain(self, n = 1):

        self.ngram_degree = n
      
        self.markov_model = defaultdict(lambda : defaultdict(int))

        sentences = self.corpus_sentences
        if sentences is None:
            sentences = self.sentenceTokenizeCorpus()

        print("Training markov model on corpus.")

        word_tokenizer = RegexpTokenizer(r"\w+")

        for sentence in sentences:
            words = word_tokenizer.tokenize(sentence)
            last_word_list = ["#"] * n

            for word in words:
                last_token = " ".join(last_word_list)
                
                self.markov_model[last_token][word] += 1
                
                last_word_list.append(word)
                last_word_list = last_word_list[1:]

            last_token = " ".join(last_word_list)
            self.markov_model[last_token]["#"] += 1

	def __init__(self, oldid, newid, data, general):
		self.newid=newid
		self.oldid=oldid
		self.data=data
		self.tfidfatt=[]
		self.tfidfval=[]
		self.freatt=[]
		self.freval=[]
		self.text=''
		self.ntlk=[]
		self.idfvalue=[]
		self.general=general

		tokenizer = RegexpTokenizer(r'\w+')
		#stemmer = SnowballStemmer("english")
		stemmer = PorterStemmer()

		stop = stopwords.words('english')
		for r in tokenizer.tokenize(data):
			a=0
			if r not in stop:
				if not any(i.isdigit() for i in r):
					r = stemmer.stem(r)
					if r not in self.ntlk:
						self.ntlk.append(r)
						self.text=self.text+' '+r

	def mean_stdDeviation(self,query,stopWordInstruction):
		list_count_postTitles = []
		list_postTitles = self.data[:][query].tolist()
		tokenizer = RegexpTokenizer(r'\w+')

		stopwords_mine = []
		#a.encode('ascii','ignore')
		stopwords_mine+= (word.encode('ascii','ignore') for word in stopwords.words('english'))
		tokenized_list = []
		new_list_tokenized = []
		for item in list_postTitles:
			tokenized_list.append(tokenizer.tokenize(item))
		
		if stopWordInstruction==True:
			for item in tokenized_list:
				temp = []
				temp += (word for word in item if word.lower() not in stopwords_mine)
				#print temp
				#raw_input()
				new_list_tokenized.append(temp)
		else:
			new_list_tokenized=copy.deepcopy(tokenized_list)
		


		for x in new_list_tokenized:
			list_count_postTitles.append(len(x))
		#print list_count_postTitles
		npArray = np.asarray(list_count_postTitles)
		print npArray.mean()
		print npArray.std()
		return [npArray.mean(),npArray.std(),list_postTitles,list_count_postTitles]

def issue_analysis(df):
    df_sub = df[['Issue']]
    df_sub.insert(0, 'count', 1)

    Issue_List=[]
    for i in range(0,50):
        Issue_List.append(df_sub.groupby(['Issue']).sum().sort_index(by='count', ascending=False).ix[i].name)

    tokenizer = RegexpTokenizer(r'[A-Za-z0-9\']+')    # set tokenize Reg
    en_stop = get_stop_words('en')         # create English stop words list
    p_stemmer = PorterStemmer()            # Create p_stemmer of class PorterStemmer
    texts = []                             # list for tokenized documents in loop
    text_view = ''
                                                                
    # loop through document list
    for i in Issue_List:
        # clean and tokenize document string
        raw = i.lower()
        tokens = tokenizer.tokenize(raw)
       
        # remove stop words from tokens
        stopped_tokens = [i for i in tokens if not i in en_stop]
        
        # stem tokens and add them to list
        stemmed_tokens = [p_stemmer.stem(i) for i in stopped_tokens]
        texts.append(stemmed_tokens)

        #print ' '.join(stemmed_tokens)
        text_view += ' '.join(stemmed_tokens)
        text_view += ' '

    wordcloud = WordCloud().generate(text_view)
    fig = plt.figure(figsize=(8,6))
    fig1 = fig.add_subplot(1,1,1)
    fig1.set_title("Top issued words", fontdict={'fontsize':25})
    fig1.imshow(wordcloud)
    fig1.axis("off")
    #plt.savefig('ComplainCount_WC.png')
    plt.savefig('ComplainCount_WC_2016.png')
    
    # turn our tokenized documents into a id <-> term dictionary
    dictionary = corpora.Dictionary(texts)

    # convert tokenized documents into a document-term matrix
    corpus = [dictionary.doc2bow(text) for text in texts]

    # generate LDA model
    ldamodel = gensim.models.ldamodel.LdaModel(corpus, num_topics=25, id2word = dictionary)
    LDAText =  ldamodel.print_topics(num_topics=5, num_words=3)
    #print "\n Topic analysis result for top 25 issues with LDA"
    #print(LDAText)
       
    vis_data = gensimvis.prepare(ldamodel, corpus, dictionary)
    #pyLDAvis.show(vis_data)
    #pyLDAvis.save_html(vis_data, "issue_lda.html")
    #pyLDAvis.save_json(vis_data, "issue_lda.json")
    pyLDAvis.save_html(vis_data, "issue_lda_2016.html")
    pyLDAvis.save_json(vis_data, "issue_lda_2016.json")

    return 0

 def stripped_words(self, original_sentence):
     _sentence = filter(self.printable_char_filter, original_sentence)
     _sentence = _sentence.replace(u'\u2013', ' ')
     _sentence = _sentence.replace(u'\u2014', ' ')
     tokenizer = RegexpTokenizer('\w+|\$[\d\.]+|\S+')
     tokens = tokenizer.tokenize(_sentence)
     return [word.lower() for word in tokens if word.lower() not in stop_words]

def relevance_features(doc):
	print "relfeatures"
	print doc[:10]
	features={}
	#print doc
	#Test 1 : Has synonyms of  NIT Warangal
	features['contains synonym']='false'
	for word in synonyms:
		if word in doc:
			features['contains synonym']='true'
			break

	#Test 2 : Has a person name that appears in Almabase's DB
	count=0
	names=ner.get_names(data)
	count=ner.query_db(names)
	print 'count is {}'.format(count)

	# if count==0:
	# 	features['hasAlumnus']='none'
	# elif count<=3:
	# 	features['hasAlumnus']='medium'
	# elif count>3:
	# 	features['hasAlumnus']='high'
	# print count

	#Test 3: Bag of words approach
	tokenizer = RegexpTokenizer(r'\w+')
	document_words=tokenizer.tokenize(doc)
	for word in word_features:
		if word.lower() in document_words:
			print "{} is present".format(word)
		features['contains({})'.format(word.lower())] = (word in document_words)
	return features

def preprocess_wikidata(raw):
 # Initialize Tokenizer
    tokenizer = RegexpTokenizer(r'\w+')

    # Initialize Lemmatizer
    lemma = WordNetLemmatizer()

    # create English stop words list
    en_stop = get_stop_words('en')

    # Decode Wiki Markup entities and remove markup
    text = filter_wiki(raw)
    text = re.sub(filter_more, '', text)

    # clean and tokenize document string
    text = text.lower().split('../img/')[0]
    tokens = tokenizer.tokenize(text)

    # remove stop words from tokens
    tokens = [i for i in tokens if not i in en_stop]

    # stem tokens
    tokens = [lemma.lemmatize(i) for i in tokens]

    # remove non alphabetic characters
    tokens = [re.sub(r'[^a-z]', '', i) for i in tokens]

    # remove unigrams and bigrams
    tokens = [i for i in tokens if len(i)>2]

    return (tokens, text)

def get_product_vocab(dict_queries):
    tok = RegexpTokenizer(r'\w+')
    vocab = {}

    for query,v in dict_queries.items():
        words = defaultdict(int)

        for prod in v:
            w_prod = tok.tokenize(prod[1])
            for w in w_prod:
                #wt = stem(wt)
                if not re.match(r'\d+$', w) and \
                    len(w) > 1 and \
                    w not in stop_words: 
                    words[w] += 1

        vocab[query] = words.keys()
        #vocab[query] = [k for (k, v) in words.iteritems() if v > 1]

        """
        print "Query: " + query
        sorted_w = sorted(words.items(), key=lambda x:x[1], reverse=True)
        print sorted_w
        """
    
    return vocab

def write_summary(texts, ofile):
    word_tokenizer = RegexpTokenizer(r"\w+")
    with codecs.open(ofile, u"w", u"utf-8") as f:
        for text in texts:
            f.write(u" ".join([w.lower() for w in word_tokenizer.tokenize(text)]))
            f.write(u"\n")
            f.flush()