Python lancaster.LancasterStemmer类代码示例

def stem_tweet(tweet, stemmer_type = "lancaster"):
    """
    :param tweet: string representing tweet
    :param stemmer_type: type of stemmer used (default value is lancaster)
    :return: stemmed tweet
    :type tweet: str
    :type stemmer_type: str
    """
    tokens = nltk.word_tokenize(tweet)
    stemmed_tokens = []
    if stemmer_type == "lancaster":
        stemmer = LancasterStemmer()
    elif stemmer_type == "snowball":
        stemmer = SnowballStemmer("english")
    elif stemmer_type == "porter":
        stemmer = PorterStemmer()
    elif stemmer_type == "regexp":
        stemmer = RegexpStemmer("english")
    else:
        return None

    for token in tokens:
        stemmed_tokens.append(stemmer.stem(token))

    ret_tw = "".join([" "+i if not i.startswith("'") and i not in string.punctuation else i for i in stemmed_tokens]).strip()
    return ret_tw

def stem_text(text):
    stm = LancasterStemmer()
    tokens = text.split()
    words = [stm.stem(w) for w in tokens]
    snt = " ".join(words)

    return snt

def lemmatizer_newsheadlines() :
    lancaster_stemmer = LancasterStemmer()
    frl=open("C:/Users/rajas/Downloads/csv_files-2014-12-10/csv files/lemma1.csv","rU")
    fr=open("C:/Users/rajas/Downloads/csv_files-2014-12-10/csv files/sample.csv","rU")
    fw=open("C:/Users/rajas/Downloads/csv_files-2014-12-10/csv files/lemmaheadlines.csv","w")
    for headline in fr:
        if len(headline)>0:
          headlinelist=headline.split(",")
        
          if len(headlinelist)==3:
            headlinewords=headlinelist[1].split(" ")
            print(headlinewords)
            for word in headlinewords:
              wordcor=(((word.replace("?","")).replace(":","")).replace("\"",""))    
               
              headlineword=(lancaster_stemmer.stem(wordcor)).lower()
              print(headlineword) 
     #         for line in frl:
      #          crimelist=line.split(",")
       #         crimeword=((crimelist[1].replace("\"","")).strip()).lower()
               
        #        print(crimeword+str(i))
         #       i+=1
              dictcrime=lemmadict()
              if headlineword in dictcrime:
                  print(headlineword+"yipee")
                  fw.write(headlineword+","+headlinelist[0]+","+headlinelist[1]+"\n")
                                    
                  break;
    frl.close()     
    fw.close()
    fr.close()

def simplify_old(s):
    res = ''
    st = LancasterStemmer()

    text = nltk.word_tokenize(s)
    tags = nltk.pos_tag(text)

    for tag in tags:
        word = tag[0]
        if f.checkPos(tag[1]):
            if word in model:
                word_stem = st.stem(word)
                top_words = model.most_similar(positive=[word], topn = 20)
                candidate_list = [w[0] for w in top_words]
                freq_list = [fdist[w] for w in candidate_list]
                c_f_list = zip(candidate_list, freq_list)
                ordered_list = sorted(c_f_list, key=lambda c_f_list:c_f_list[1], reverse=True)
                word_freq = fdist[word]
                #			synonmys = f.getSynonmys(word)  ## get synonmys from wordnet
                # print synonmys
                for w in ordered_list:
                    if not f.freq_diff(word_freq, w[1]):  ## break for loop if candidate word frequency does not exceed the word frequency by a threshold
                            break
                    if st.stem(w[0]) != word_stem and f.samePos(word, w[0]): ##exclude morphological derivations and same pos
                            word = w[0]  ### do not use wordnet
        # if w[0] in synonmys:
        # 	word = w[0]
        # else:
        # 	for syn in synonmys:
        # 		if st.stem(w[0]) == st.stem(syn):
        # 			word = w[0]

        res = res + word + ' '
    return res

	def filt(string):

		ret = string

		#	Filter all punctuation from string
		for p in punctuation:
			ret = ret.replace(p, '')

		#	Replace hyphens with spaces
		ret = ret.replace('-', ' ')
		oldret = ret
		ret = ""

		#	Filter all stop words from string
		for word in oldret.split():
			if (word in allStopWords) or len (word) <= 1:
				pass
			else:
				ret += word.lower() +  " "

		st = LancasterStemmer()
		steamed = ""

		for word in ret.split():
			try:
				steamed += str(st.stem(word)) + " "

			except UnicodeDecodeError:
				pass

		return steamed

def mapper():

    #list of fields in positional order expected in inbound
    #forum node data.
    fieldnames = ['id', 'title', 'tag_names', 'author_id', 'body',
                    'node_type', 'parent_id', 'abs_parent_id', 
                    'added_at', 'score', 'state_string', 'last_edited_id',
                    'last_activity_by_id', 'last_activity_at', 
                    'active_revision_id', 'extra', 'extra_ref_id',
                    'extra_count', 'marked']

    reader = csv.DictReader(sys.stdin, delimiter='\t', fieldnames=fieldnames)
    stemmer = LancasterStemmer()
    stopw = stopwords.words('english')

    split_pattern = re.compile('[\W.!?:;"()<>[\]#$=\-/]')
    for line in reader:        
        
        pid = line['id']
        body = line['body']
        
        # split body into words
        words = split_pattern.split(body)
     
        # map the stemmer function across all the words.
        # and use the Counter to create a dict
        # of counted stems. Remove english stopwords.
        stem_counts = Counter((stemmer.stem(x) for x in words  if x not in stopw))        
        
        # emit the stem, count and node id
        # for reduction into the reverse index
        for stem, count in stem_counts.items():
        	print "{stem}\t{node_id}\t{count}".format(stem=stem, node_id=pid, count=count)

def preprocess(reviews):
	import nltk
	from nltk.tokenize import word_tokenize

	review_tokenized = [[word.lower() for word in word_tokenize(review.decode('utf-8'))] for review in reviews] 
	#print "review tokenize done"

	#remove stop words
	from nltk.corpus import stopwords
	english_stopwords = stopwords.words('english')
	review_filterd_stopwords = [[word for word in review if not word in english_stopwords] for review in review_tokenized]
	#print 'remove stop words done'

	#remove punctuations
	english_punctuations = [',','.',':',';','?','(',')','&','!','@','#','$','%']
	review_filtered = [[word for word in review if not word in english_punctuations] for review in review_filterd_stopwords]
	#print 'remove punctuations done'

	#stemming
	from nltk.stem.lancaster import LancasterStemmer
	st = LancasterStemmer()
	review_stemmed = [[st.stem(word) for word in review] for review in review_filtered]
	#print 'stemming done'

	return review_stemmed

def preprocess(content):
	stopset = set(stopwords.words('english'))
	#replace punctuation and tag with space
	tokens = word_tokenize(re.sub(r'<p>|</p>|[^A-Za-z ]', ' ', content.lower())) 
	pos_list = pos_tag(tokens)
	s_tokens = list()

	#noun and verb only
	for pos in pos_list:
		#print pos[1]
		#if pos[1] in ['NN', 'NNS', 'VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']:
		if pos[1] in ['NN', 'NNS']:
			s_tokens.append(pos[0])

	wordfreq = FreqDist(s_tokens)
	stemfreq = dict()
	st = LancasterStemmer()
	for word, freq in wordfreq.items():
		#stopwords
		if word in stopset:
			del wordfreq[word]
			continue
		#tiny words
		if len(word) <= 2:
			del wordfreq[word]
			continue
		#stemmer
		stem = st.stem(word)
		try:
			stemfreq[stem]+=freq
		except:
			stemfreq[stem]=freq
	return stemfreq

 def processRawData(self, inputPath, outputPath):
   raw = pickle.load(open(inputPath, "r"))
   data = []
   genres = set([])
   count = 0
   st = LancasterStemmer()
   for key in raw.keys():
     movie = raw[key]
     # if no genre or synopsis data
     if 'genres' not in movie or 'synopsis' not in movie: continue
     if len(movie['genres'])==0 or movie['synopsis'] == '': continue
     temp = {}
     temp['genres'] = movie['genres']
     for g in temp['genres']:
       genres.add(g)
     # trim out the punctuation and transform to lowercase
     #replace_punctuation = string.maketrans(string.punctuation, ' '*len(string.punctuation))
     s = str(movie['synopsis'])
     s = s.translate(string.maketrans("",""), string.punctuation)
     s = re.sub(' +', ' ', s).strip()
     s = " ".join(st.stem(word) for word in s.split(" "))
     temp['synopsis'] = s.lower()
     data.append(temp)
     count += 1
   # output as a pickle file 
   file = open(outputPath, 'wb')
   pickle.dump(data, file)
   print 'processed ' + str(count) + ' movies'
   return genres

def parse_validation(validation_path):
    validation_list = []
    with open(validation_path) as f:
        for line in f:
            strs = line.split('|')
            word_dict = {}
            validation_list.append(word_dict)
            word_dict["word"] = strs[0].strip()
            word_dict["real_sense"] = int(strs[1])
            sentence_list = []
            word_dict["sentence"] = sentence_list

            lmtzr = WordNetLemmatizer()
            ls = LancasterStemmer()
            single_words = re.findall("(\w+|%%)",strs[2])
            double_mod_found = False
            word_count = 0
            for single_word in single_words:
                if single_word == "%%":
                    if not double_mod_found:
                        word_dict["target_word_idx"] = word_count+1
                        double_mod_found = True
                    continue
                lemmed = lmtzr.lemmatize(single_word)
                stemmed = ls.stem(lemmed)
                if not stemmed in glob_Lucene:
                    sentence_list.append(stemmed)
                    word_count += 1

    return validation_list

   def getMaybeWords(self, text_ls):
      ignoreWords = ["","have","her","there","the","be","to","of","and","a","in","that","it","for","on","with","as","at","this","but","his","by","from","they","or","an","will","would","so","even","is","be","am","are"];

      word_ls = []
      for text in text_ls:
         word_ls += wordpunct_tokenize(text)
         
      frequencies = {}
      st = LancasterStemmer()
      for word in word_ls:
         if not word[0].isalpha():
            continue
         if word in ignoreWords:
            continue
         word_stem = st.stem(word)
         if word_stem in frequencies:
            frequencies[word_stem] += 1
         else:
            frequencies[word_stem] = 1

      sorted_frequencies = sorted(frequencies.iteritems(), key = operator.itemgetter(1), reverse =  True)
      #print sorted_frequencies

      max_words = 30
      if len(sorted_frequencies) < max_words:
         max_words = len(sorted_frequencies)
      word_tuples = sorted_frequencies[0:max_words]
      words = [tuple[0] for tuple in word_tuples]
      print words
      return words

    def build_analyzer(self):
        """
        Return a callable that handles preprocessing and tokenization
        """
        preprocess = self.build_preprocessor()
        tokenize = self.build_tokenizer()
        stemmer = LancasterStemmer()

        filter_meta = lambda doc: ' '.join([w for w in doc.split() if not w.startswith('~')])
        parse_words = lambda doc: tokenize(preprocess(filter_meta(self.decode(doc))))
        stem_words = lambda doc: [stemmer.stem(t) for t in parse_words(doc)]
        meta_func = lambda prefix: lambda doc: (t for t in self.decode(doc).split() if t.startswith(prefix))

        feat_func_map = {
            'word': lambda doc: self._word_ngrams(parse_words(doc), self.get_stop_words()),
            'stem': lambda doc: self._word_ngrams(stem_words(doc), self.get_stop_words()),
            '1st': lambda doc: ('~T:1st' for i in parse_words(doc) if i in first_person_words),
            '3rd': lambda doc: ('~T:3rd' for i in parse_words(doc) if i in third_person_words),
            'tag': lambda doc: self._word_ngrams([t[1] for t in nltk.pos_tag(parse_words(doc))]),
            'length': lambda doc: ['~L:%d' % (len(parse_words(doc)) / 5)],
            'genre': meta_func('~G'),
            'rating': meta_func('~Ra'),
            'votes': meta_func('~V'),
            'lang': meta_func('~La'),
            'country': meta_func('~Co'),
            'year': meta_func('~Y'),
            'runtime': meta_func('~Rt'),
            'type': meta_func('~T')
        }
        func_list = [feat_func_map.get(flag.strip()) for flag in self.analyzer.split(':')] \
            if type(self.analyzer) is str else None
        if not func_list:
            raise ValueError('%s is not a valid tokenization scheme/analyzer' % self.analyzer)
        else:
            return lambda doc: itertools.chain.from_iterable(f(doc) for f in func_list if callable(f))

def readText(textFile):			
	examples = []
	count = 0
	lexicon_en = {}
	lexicon_ge = {}
	stem_en = LancasterStemmer()
	stem_ge = nltk.stem.snowball.GermanStemmer()
	for line in open(textFile):
		count+=1
		if count % 1000 == 0:
			print count
		lans = line.lower().strip().split("|||")
		#german = [stem_ge.stem(x.decode('utf-8')) for x in lans[0].strip().split(" ")]
		german = lans[0].strip().split(" ")
		german = process(german)
		for wordx in german:
			for word in wordx:
				if word not in lexicon_ge:
					lexicon_ge[word]=1
				else:
					lexicon_ge[word]+=1
		eng = [stem_en.stem(x.decode('utf-8')) for x in lans[1].strip().split(" ")]
		#parse_en = pattern.en.parse(" ".join(eng))
		eng = lans[1].strip().split(" ")
		for word in eng:
			if word not in lexicon_en:
				lexicon_en[word]=1
			else:
				lexicon_en[word]+=1
		examples.append(Example(german,eng))
	return examples, lexicon_en, lexicon_ge

def prepare_corpus(raw_documents):
    # remove punctuation
    print "Removing Punctuation"
    import string
    exclude = set(string.punctuation)
    raw_documents = [''.join(ch for ch in s if ch not in exclude) for s in raw_documents]

    # remove common words
    print "Calculating Stoplist"
    stoplist = set([x.rstrip() for x in codecs.open("stop_list.txt", encoding='utf-8') if not x.startswith("#")])
    stoplist = stoplist.union(set(nltk.corpus.stopwords.words("english")))
    # print stoplist

    print "Removing Stoplist and Stemming"

    from nltk.stem.lancaster import LancasterStemmer
    st = LancasterStemmer()

    texts = [[st.stem(word) for word in document.lower().split() if word not in stoplist]
             for document in raw_documents]

    # remove words that appear only once
    print "Removing Single Variables"
    all_tokens = sum(texts, [])
    tokens_once = set(word for word in set(all_tokens) if all_tokens.count(word) == 1)
    texts = [[word for word in text if word not in tokens_once]
             for text in texts]

    return texts

def tokenize_rest(text):
    wnl =  WordNetLemmatizer()
    st = LancasterStemmer()
    words = nltk.word_tokenize(text)
    postag = nltk.pos_tag(words)
    
    tokens = []
    whfound=False
    for word in words:
        if word[0:2].lower() == 'wh' and not whfound:
            tokens.append({word.lower():'wh'})
            whfound = True
            continue
        elem=wnl.lemmatize(word)
        stem = st.stem(elem)
        synd = wn.synsets(stem)
        if not synd:
            stem = stemmer(elem)
            synd = wn.synsets(stem)
        if not synd:
            stem = elem
            synd = wn.synsets(stem)
        dbelement=detect(stem)
        if dbelement:
            for every_elem in dbelement:
                tokens.append({word:every_elem})
    print "\n Rest of possible Tokens"
    print tokens
    return tokens