Python porter.PorterStemmer类代码示例

	def AddTopicUnigram(self, feaName,comName, data = None):	
	#need mapping first
		if data is None:
			data =self._data
			
		for i in range(len(data)):	
			t_bigram = self.getEssayCollocation(data, i)
			
			t_uni = list()
			for (a, b) in t_bigram:
				t_uni.append(a)
				t_uni.append(b)
			t_uni = set(t_uni)
			
			comment = data[i][comName]
			tokens = nltk.wordpunct_tokenize(comment)
			tokens = [word.lower() for word in tokens]
		
			#stemming
			if self._stemoption ==True:
				st = PorterStemmer()
				tokens = [st.stem(t) for t in tokens]
				t_uni  = set([st.stem(t) for t in list(t_uni)])
			shared = [w for w in tokens if w in t_uni]
			#normalized
			data[i][feaName] = float(len(shared))/(len(tokens)+0.00001)

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 cleanData(doc_list):
  # tokenize
  tokens = []
  for doc in doc_list:
    text_l = []
    ws_split = re.split(split_on, doc)
    for w in ws_split:
      # remove URLs and empty strings
      if not (url_pat.match(w) or w == u''):
        text_l.append(w)
  
    # rejoin text and 'properly' tokenize
    text = " ".join(text_l)
    text_l = nltk.word_tokenize(text)
    
    # stop words 
    text_l = [ w.lower() for w in text_l if w.lower() not in stops]
  
    # stemming
    p_stemmer = PorterStemmer()
    text_l = [p_stemmer.stem(t) for t in text_l]
    
    ## append cleaned text to list
    tokens.append(text_l)
  return tokens

def get_stemmed_separate(indeed_reviews_db, glassdoor_reviews_db):
    separate = get_separate_reviews(indeed_reviews_db, glassdoor_reviews_db)
    stemmer = PorterStemmer()
    stemmed_reviews = []
    for review in separate:
        stemmed_reviews.append(' '.join([stemmer.stem(word) for sent in sent_tokenize(review) for word in word_tokenize(sent.lower())]))
    return stemmed_reviews

def main():

    rake=RAKE.Rake('SmartStoplist.txt')
    fp=open(input_file,'r')
    text=fp.read()
    text=text_clean(text)
    """wnl=WordNetLemmatizer()
    text=' '.join([wnl.lemmatize(i.strip()) for i in nltk.word_tokenize(text)])"""
    porter_stemmer=PorterStemmer()
    text=' '.join([porter_stemmer.stem(i.strip()) for i in nltk.word_tokenize(text)])
    keywords=rake.run(text)
   # print keywords

    with open(key_score_file,'wb') as out:
        csv_out=csv.writer(out)
        csv_out.writerow(['KEYWORD','SCORE'])
        for row in keywords:
            if row[1]>0:
                csv_out.writerow(row)


    unibitrigram_list=[]
    unibitrigram_list=generate_unibitrigrams(key_score_file)
    #print unibitrigram_list
    #ngram_freq=[]
    ngram_freq=Counter(unibitrigram_list)
    sorted_ngram_freq=sorted(ngram_freq.items(),key=lambda x:x[1],reverse=True )
    print ngram_freq
    with open('bcom_ngramfr_stem.csv','wb') as nf_csv:
        csv_wr=csv.writer(nf_csv)
        for item in sorted_ngram_freq:
            if ((item[0]!='')):
                csv_wr.writerow(item)

    def parse_questions(self):
        stemmer = PorterStemmer()
        tokenizer = RegexpTokenizer(r'\w+')
        for questions_key in self.rawSamples:
            # Stem the Question Text
            question_text = self.rawSamples[questions_key][0]
            words_array = tokenizer.tokenize(question_text)
            question_text = ""
            for word in words_array:
                if word.isnumeric():
                    continue
                if word not in text.ENGLISH_STOP_WORDS:
                    word = stemmer.stem(word)
                word = stemmer.stem(word)
                question_text += (word + " ")
            self.rawSamples[questions_key][0] = question_text

            # Stem the topic names
            topics_text = self.rawSamples[questions_key][2]
            words_array = tokenizer.tokenize(topics_text)
            topics_text = ""
            for word in words_array:
                if word.isnumeric():
                    continue
                if word not in text.ENGLISH_STOP_WORDS:
                    word = stemmer.stem(word)
                word = stemmer.stem(word)
                topics_text += (word + " ")
            self.rawSamples[questions_key][2] = topics_text

def evaluate(query):
	global DICTIONARY
	word_score = {}
	seek_pos = open(postings_file, 'r')
	seek_pos.seek(0,0)
	words = query.split()
	stemmer = PorterStemmer()
	words = [element.lower() for element in words]
	for item in words:
		word = stemmer.stem(item)
		if word not in word_score:	
			if word in DICTIONARY:
				seek_pointer = DICTIONARY[word]
				seek_pos.seek(int(seek_pointer))
				line = seek_pos.readline()
				seek_pos.seek(0,0)
				post_list = line.split()
				score = score_documents(post_list)
				word_score[word] = score
			else:
				#not encountered, score of 0
				word_score[word] = []
		#else duplicate, skip word
	result = score_query(word_score)
	return result

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 destem(self, stemmed_term, corpus):
     '''
     Given a stemmed term, we look through the text of every document
     in corpus, determine the most common "parent" version of the 
     given stemmed term, and return it. 
     '''
     destemmed_term = ""
     min_num_terms = 5000
     min_percentage = 0.20
     candidates = {}
     stemmer = PorterStemmer()
     num_terms_checked = 0
     num_docs_checked = 0
     total_matches = 0
     
     for doc in corpus:
         # matches is the list of all term in the current text that are
         # "ancestor" versions of the stemmed term.
         matches = ([term for term in doc.split_text 
                     if stemmer.stem(term) == stemmed_term])
         num_terms_checked += len(doc.split_text)
         num_docs_checked += 1
         total_matches += len(matches)
         if not matches:
             continue
         # we keep a tally of the number of times each "ancestor"
         # appears in our text
         for match in matches:
             if match in candidates:
                 candidates[match] += 1
             else:
                 candidates[match] = 1
         # sort potential destemmed versions in descending order
         # by frequency
         sorted_candidates = sorted(candidates.keys(), 
                                    key=lambda 
                                    term: candidates[term], 
                                    reverse=True)
         if num_docs_checked == self.num_corpus_docs: 
             # we've run through every doc, so the most frequent 
             # ancestor of the stemmed term is the best destemmed 
             # result.
             destemmed_term = sorted_candidates[0]
             break
         # if we've reviewed enough total words, we can start trying
         # to find a suitable destemmed term from what we have so far 
         if min_num_terms <= num_terms_checked:
             # this is the most frequent ancestor of the stemmed term
             possible_match = sorted_candidates[0]
             test_percentage = candidates[possible_match] \
                                 / float(total_matches)
             # if the potential destemmed version accounts for a 
             # sufficient percentage of the total matches, we can
             # decide that it's a suitable destemmed result.
             if min_percentage <= test_percentage:
                 destemmed_term = possible_match
                 break
             
     print("Destemmed: {0} --> {1}".format(stemmed_term, destemmed_term))
     return destemmed_term

def processing(raw_review):
    word1=[]    
    # 1. Remove HTML
    review_text = BeautifulSoup(raw_review).get_text() 
    # 2. Remove Punctuations        
    letters_only = remove_punctuations(review_text) 
    # 3. Convert to lower case, split into individual words
    for words in letters_only:
        wordset=[word.lower() for word in words]
        word1.append(wordset)                       
    #4Handling Double Negation
    negated_words=negation_handling(word1)
    #5 Read only verbs,adjectives,adverbs,interjections (descriptive words)  
    meaningful_words=descriptive_words(negated_words)           
    #6 Remove Time, Location, Organization, Person, Money, Percent, Date using NER   
    #removed_words=remove_names(meaningful_words)    
    #7. Remove stop words    
    stops =open(r'C:\Users\PSarka\Desktop\sentimentanalysis\stopwords.txt','r')   
    stops= set([word[:-1] for word in stops])  
    meaningful_words_new = [w for w in meaningful_words if not w in stops]    
    #6.Stemming using Porter Stemmer,Lemming can also be used check which is more efficient
    st=PorterStemmer()
    stemmed_words=[st.stem(words) for words in meaningful_words_new]   
    #7. Join the words back into one string separated by space, 
    # and return the result.
    print stemmed_words    
    return( " ".join(stemmed_words ))   

def tweet_stemming(tweet, token_freqs):

    """
    Stems tweets words and counts diversty
    
    :param tweet: the tweet to analyze
    :type tweet: str or unicode

    :param token_freqs: counter of words frequency
    :type token_freqs: Counter

    :returns: words added to token_freqs
    :rtype: int
    """
    
    pattern_url = '((https?:\/\/)|www\.)([\da-z\.-]+)\.([\/\w \.-]*)( |$)'
    regex_punctuation = re.compile('[%s]' % re.escape(string.punctuation))
    porter = PorterStemmer()

    counter_tokens = 0
    tweet_url_removed = re.sub(pattern_url, '', tweet, flags=re.MULTILINE)  # remove URL
    tweet_url_removed_tokenized = word_tokenize(tweet_url_removed)  # tokenize tweet
    tweet_url_removed_tokenized_cleaned_stemming = []  # cleaned of URLs and hashs, and stemming

    for token in tweet_url_removed_tokenized:
        new_token = regex_punctuation.sub(u'', token)  # remove punctuation and hash
        if not new_token == u'':
            new_token_stemming = porter.stem(new_token)
            tweet_url_removed_tokenized_cleaned_stemming.append(new_token_stemming)
            token_freqs[new_token_stemming] += 1
            counter_tokens += 1
    
    return counter_tokens

def compare_english_simple(article_title):
    """Given a title of an article, returns the number of tokens, types, and stems
    in both the English version and the simple English version."""
    english = extract_wikipedia_page(article_title, "en")
    simple = extract_wikipedia_page(article_title, "simple")
    num_tokens_english = len(english)
    num_tokens_simple = len(simple)
    types_english = count_words(get_words(english))
    types_simple = count_words(get_words(simple))
    
    porter_stemmer = PorterStemmer()
    
    stem_english = defaultdict(int)
    stem_simple = defaultdict(int)
    for key in types_english.keys():
        stem_english[porter_stemmer.stem(key)] += 1
    for key in types_simple.keys():
        stem_simple[porter_stemmer.stem(key)] += 1
    
    print ("Number of Tokens in English " + article_title + ": %d" % num_tokens_english)
    print ("Number of Tokens in Simple English " + article_title + ": %d" % num_tokens_simple)
    print ("Number of Types in English " + article_title + ": %d" % len(types_english))
    print ("Number of Types in Simple English " + article_title + ": %d" % len(types_simple))
    print ("Number of Stems in English " + article_title + ": %d" % len(stem_english))
    print ("Number of Stems in Simple English " + article_title + ": %d" % len(stem_simple))

def query(new_doc,doc_topic,topic_word,dictionary,LSH,num_topic):
    tokens = []
    token = get_tokens(new_doc)
    stopped_tokens = [i for i in token if not i in en_stop]
    p_stemmer = PorterStemmer()
    stemed_tokens = []
    for i in stopped_tokens:
        try:
            temp_token = str(p_stemmer.stem(i))
            stemed_tokens.append(temp_token)
        except IndexError:
            pass
    tokens = stemed_tokens
    new_corpus=dictionary.doc2bow(tokens)
    new_corpus = to_gibbs_corpus([new_corpus])[0] ##convert 
    new_topic_vector = np.zeros(num_topic)
    
    for t in new_corpus:
        mult_par = topic_word[:,t[0]] + 1
        mult_par = mult_par/np.sum(mult_par)
        new_topic_vector += np.random.multinomial(t[1],mult_par)
        #print mult_par
        #print topic_word[:,t[0]]
    
    new_topic_vector = new_topic_vector/np.sum(new_topic_vector)
    dist,indices=LSH.kneighbors(new_topic_vector,n_neighbors=20)
    print indices+1

def read_class_data(path, label=None):
    '''
    Label may come from the data itself, may be assigned at run time
    '''
    if os.path.exists(path):
        if os.path.isdir(path):
            paths = [os.path.join(path, f) for f in os.listdir(path)]
        else:
            paths = [path]
    else:
        print 'Given path does not exist.'
        return
    
    doc = doc_file()
    stemmer = PorterStemmer()
    instances = []
    for p in paths:
        doc.path = p
        for raw_record in doc:
            record = unpack(raw_record, ',')
            text = record[3].strip('"')
            inst = {'tokens': [], 'label': ''}
            for t in wordpunct_tokenize(text):
                stem_t = stemmer.stem(t.lower())
                if stem_t[0].islower():
                    inst['tokens'].append(stem_t)
                else:
                    continue
            inst['label'] = label
            instances.append(inst)
    return instances

def extract_entities(doc):
    print 'extracting entities from %s...' % doc.getFilename()
    nps = list(set([re.sub(' \.', '', re.sub(' -[A-Z]{3}-', '', np).lower()) for np in doc.getAllNodesOfType('NP')]))
    p = PorterStemmer()
    entities = []
    for np in nps:
        try:
            response = json.loads(requests.get(host+'select', params={'q': 'wam:[50 TO 100] AND iscontent:true AND lang:en AND (title_en:"%s" OR redirect_titles_mv_en:"%s")' % (np, np), 'fl': 'title_en,redirect_titles_mv_en', 'wt': 'json'}).content)
        except requests.exceptions.ConnectionError:
            while True:
                time.sleep(15)
                print 'retrying connection...'
                try:
                    response = json.loads(requests.get(host+'select', params={'q': 'wam:[50 TO 100] AND iscontent:true AND lang:en AND (title_en:"%s" OR redirect_titles_mv_en:"%s")' % (np, np), 'fl': 'title_en,redirect_titles_mv_en', 'wt': 'json'}).content)
                    break
                except requests.exceptions.ConnectionError:
                    continue
        docs = response[u'response'][u'docs']
        if len(docs) > 0:
            titles = [docs[0][u'title_en']] + docs[0].get(u'redirect_titles_mv_en', [])
        else:
            titles = []
        if len(titles) > 0:
            titles = [' '.join([p.stem(w.lower()) for w in t.split(' ')]) for t in titles]
        stem_np = ' '.join([p.stem(w) for w in np.split(' ')])
        for title in titles:
            if stem_np == title:
                entities.append(np)
                print np
                break
    #print doc.getFilename(), entities
    return (doc.getFilename(), entities)