Python wordnet.WordNetLemmatizer类代码示例

def parseLine(line, stopWords_, wordInd, currWrd):
    """ Removes stop words and lemmas using nltk and punctuations 
    using re. Returns a list with valid words in the line. currWrd is
    the index of next word occurring for the first time
    """
    lineWords = []
    # Hypen in hyphenated words are removed e.g. wi-fi ==> wifi.
    line = re.sub('(\w)-(\w)',r'\1\2',line)
    # replace underscore with space     
    line = re.sub('(\w)_(\w)',r'\1 \2',line)    
    # Remove punctuation marks.
    line = re.sub("[',~`@#$%^&*|<>{}[\]\\\/.:;?!\(\)_+\"-]",r'',line)
    wnLmtzr = WordNetLemmatizer()    
    for word in line.split():
        # Get index of word from wordInd. If it is seen for the first 
        # time assign an index to the word.
        word = word.lower()    # case of words is ignored
        # Lemmatize word using word net function
        word = wnLmtzr.lemmatize(word, 'n')    # with noun
        word1 = wnLmtzr.lemmatize(word, 'v')    # with verb
        if len(word1) < len(word):    # select smaller of two
            word = word1                
        # Ignore stop words and numbers.
        if word in stopWords_ or \
                re.match('^\d+x?\d*$',word) is not None:
            continue
        # Update wordInd with number of occurrences of word.
        if word not in wordInd:                
            wordInd[word] = currWrd[0]
            currWrd[0] += 1
        # Update lineWords with word.
        lineWords.append(word)
    return lineWords

def cleanUp(rawWords):
  
  stops = [t.lower() for t in stopwords.words('english')]

  sumarr = []
  for i in range(0,len(rawWords)):
    arr = [t.lower() for t in rawWords[i].split()]
    for word in arr: 
      if word not in stops:
        sumarr.append(word.lower())
  
  punct1 = '.,?/><";![]:@#$%&*()'
  punct2 = "'"
#  for i in range(0,len(sumarr)):
  for i in range(0,1):  
    if r'\\xe2' in sumarr[i]: sumarr[i] = '*'
    if len(sumarr[i]) > 1:
      if sumarr[i][-1] in punct1 or sumarr[i][-1] in punct2: sumarr[i] = sumarr[i][:-1]   # delete punctuation at the end of the word.
      if sumarr[i][-1] in punct1 or sumarr[i][-1] in punct2: sumarr[i] = sumarr[i][:-1]   # once more to delete double punctuations.      if sumarr[i][0] in punct1 or sumarr[i][0] in punct2: sumarr[i] = sumarr[i][1:]   # delete punctuation at the start of the word.      
    if len(sumarr[i]) > 2:
#      print sumarr
      if sumarr[i][-2] == "'" and sumarr[i][-1] == 's' : sumarr[i] = sumarr[i][:-2] # so that Jim's --> Jim.
      if sumarr[i][-2] == "'" and sumarr[i][-1] == 'm' : sumarr[i] = sumarr[i][:-2] # so that I'm --> I.
    if len(sumarr[i]) > 3:    
      if sumarr[i][-3] == 'n' and sumarr[i][-2] == "'" and sumarr[i][-1] == 't' : sumarr[i] = sumarr[i][:-3] # so that isn't --> is. Not is a stop word.
    
  lmtzr = WordNetLemmatizer()
  return [lmtzr.lemmatize(t) for t in sumarr if ("'" not in t and t not in stops)]

def parseLyrics2(outlist):
	bandLyricInfo = {} 
	master = [['death', 0],['violence',0],['sacrifice',0],['nature',0],['peace',0],['storm',0],['spirit',0],[ 'dark',0],['scream',0],['pain',0],['blood',0],['flesh',0],['love',0],['greed',0],['poison',0],['anger',0],['revenge',0],['misery',0],['hell',0],['heaven',0],['hate',0],['soul',0],['battle',0],['ghost',0],['joy',0],['light',0],['omen',0],['miracle',0],['magic',0],['universe',0],['disease',0],['god',0],['satan',0],['struggle',0],['heart',0]]
	for key in outlist:
		templist = copy.deepcopy(master) ;
		#key = 'Queensryche'
		raw = outlist[key];
		raw = raw.lower();
		words = re.findall(r'\w+', raw,flags = re.UNICODE | re.LOCALE) # punctuation
		imp_words = filter(lambda x: x not in stopwords.words('english'), words) # filter noise
		lmt = WordNetLemmatizer()
		words_new = [lmt.lemmatize(x) for x in words]
		dw = list(set(words_new))
		
		for word in dw:
			for m in templist:
				p1 = wordnet.synsets(word) ;
				p2 = wordnet.synsets(m[0]) ;
				if(len(p1) >0 and len(p2) >0):
					c = p1[0].wup_similarity(p2[0])
					if(c > m[1]):
						m[1] = c
		# sort words according to similarity
		tnew = sorted(templist,key=lambda val:val[1],reverse=True) [0:10] ;
		# remove the other column
		for l in tnew:
			del l[1]
		print 'Done ',key
		#break ;
		bandLyricInfo[key] = tnew
		#del templist
	return bandLyricInfo

def MakeLemmaList(tagged):
    # n noun
    # v verb
    # a adje
    # r adverb
    # m,w,.. something else

    noun_op, adj_op, adv_op, verb_op, other_op = [], [], [], [], []

    lm = WordNetLemmatizer()
    for i in tagged:
        # print i, i[0], i[1][0:2]
        if cmp(i[1][0:1], "N") == 0:
            noun_op.append(lm.lemmatize(i[0], "n"))
        elif cmp(i[1][0:1], "V") == 0:
            asd = lm.lemmatize(i[0], "v")
            if asd != "be" and asd != "have" and asd != "do" and asd != "done" and asd != "should":
                verb_op.append(asd)
        elif cmp(i[1][0:1], "J") == 0:
            adj_op.append(lm.lemmatize(i[0], "a"))
        elif cmp(i[1][0:1], "R") == 0:
            adv_op.append(lm.lemmatize(i[0], "r"))
        else:
            # print lm.lemmatize(i[0])+ " "
            pass
    final_op = noun_op + verb_op + other_op + adj_op + adv_op
    return final_op

	def convertToVec(self, line):
		lmtzr = WordNetLemmatizer()
		if isinstance(line, unicode):
			line = str(unicodedata.normalize('NFKD', line).encode('ascii','ignore'))
		#Strip of special characters
		line = re.sub(r'[^a-z^A-Z^0-9^,^.]|\^', ' ', line)
		line = line.lower()
		wordcount = {}
		count = self.Dic.count

		for word in line.split(' '):
			word = lmtzr.lemmatize(word)
			if isinstance(word, unicode):
				word = str(unicodedata.normalize('NFKD', word).encode('ascii','ignore'))
			if word in self.Dic.words.keys():
				num = self.Dic.words[word]
			else:				
				num = count
				count += 1
			if num not in wordcount.keys():
				wordcount[num] = 1
			else:
				wordcount[num] = wordcount[num] + 1
		
		vec = []
		for key in wordcount.keys():
			tp = (key, wordcount[key] + 0.0)
			vec.append(tp)
		return vec

def get_cooc(chunk_trees,stoplist=True):
  triples, simple_trees = [], []
  lmtzr = WordNetLemmatizer()
  for t in chunk_trees:
    entities = []
    for chunk in t[:]:
      if isinstance(chunk,Tree) and chunk.node == 'NP':
        # getting a tree for later processing of triples from the simple noun 
        # phrases (if present)
        simple_trees.append(parser_smp.parse(chunk.leaves()))
        words = []
        for word, tag in chunk[:]:
          # stem/discard elements and construct an argument
          if (stoplist and word in STOPLIST) or \
          (len([x for x in word if x.isalnum()]) == 0):
            # do not process stopwords for simple trees, do not process purely 
            # non alphanumeric characters
            continue
          if tag.startswith('N'):
            words.append(lmtzr.lemmatize(word,'n'))
          elif tag.startswith('J'):
            words.append(lmtzr.lemmatize(word,'a'))
          else:
            words.append(word)
        if len(words) > 0:
          entities.append(SEP.join(words))
    for e1, e2 in combinations(entities,2):
      triples.append((e1,util.COOC_RELNAME,e2))
      triples.append((e2,util.COOC_RELNAME,e1))
  return triples, simple_trees

 def wordLemmatization(self):
     #should be working now
     lemmatizer = WordNetLemmatizer()
     lemmatization_result = []
     for word in self.file:
         lemmatization_result.append(lemmatizer.lemmatize(word))
     self.file=lemmatization_result

    def __tokenize(self,text):
        """ function: tokenize
            ------------------
            generate list of tokens given a block of @text

            :param text: string representing article text field
            :returns: list of tokens with various modifications
        """
        ascii = text.encode('ascii', 'ignore')
        # remove digits & punctuation
        no_digits = ascii.translate(None, string.digits)
        no_punctuation = no_digits.translate(None, string.punctuation)
        # separate text blocks into tokens
        tokens = nltk.word_tokenize(no_punctuation)
        # remove class labels, stopwords, and non-english words
        no_class_labels = [w for w in tokens if not w in Document.banned_words]
        no_stop_words = [w for w in no_class_labels if not w in stopwords.words('english')]
        eng = [y for y in no_stop_words if wordnet.synsets(y)]
        # lemmatization
        lemmas = []
        lmtzr = WordNetLemmatizer()
        for token in eng:
           lemmas.append(lmtzr.lemmatize(token))
        # stemming
        stems = []
        stemmer = PorterStemmer()
        for token in lemmas:
            stem = stemmer.stem(token).encode('ascii', 'ignore')
            if len(stem) >= 4:
                stems.append(stem)
        return stems

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)])
    keywords=rake.run(text)
    #print keywords
    #key_list=list()
    with open(key_score_file,'wb') as out:
        csv_out=csv.writer(out)
        csv_out.writerow(['KEYWORD','SCORE'])
        for row in keywords:
            #csv_out.writerow(row)
            if row[1]>0:
                csv_out.writerow(row)
    unibitrigram_list=[]
    unibitrigram_list=generate_unibitrigrams(key_score_file)


    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.csv','wb') as nf_csv:
        csv_wr=csv.writer(nf_csv)
        for item in sorted_ngram_freq:
            if ((item[0]!='' or item[1]>0 )):
                csv_wr.writerow(item)

def clean_single_word(word, lemmatizing="wordnet"):
    """
    Performs stemming or lemmatizing on a single word.

    If we are to search for a word in a clean bag-of-words, we need to search it after the same kind of preprocessing.

    Inputs: - word: A string containing the source word.
            - lemmatizing: A string containing one of the following: "porter", "snowball" or "wordnet".

    Output: - lemma: The resulting clean lemma or stem.
    """
    if lemmatizing == "porter":
        porter = PorterStemmer()
        lemma = porter.stem(word)
    elif lemmatizing == "snowball":
        snowball = SnowballStemmer('english')
        lemma = snowball.stem(word)
    elif lemmatizing == "wordnet":
        wordnet = WordNetLemmatizer()
        lemma = wordnet.lemmatize(word)
    else:
        print("Invalid lemmatizer argument.")
        raise RuntimeError

    return lemma

def data_preprocessing(file_path):
    f = open(file_path,'r')
    speech_list = f.read().split("###")   # read speeches, split with ###, and save them into list.
    del speech_list[-1]
    f.close()
    #print len(speech_list)
    f = open(file_path,'r')
    speeches = f.read().lower()    #set all letters lower case
    speeches = re.sub('http://[a-zA-Z0-9|/|.]*',' ',speeches)
    speeches = re.sub('%[0-9|.]*', ' ', speeches)
    speeches = re.sub('$[0-9|.]*',' ', speeches)
    #speeches = re.sub('\\\\xe2\\\\x80\\\\x[a-zA-Z0-9]*',' ',speeches)
    #print speeches
    for ch in " \"$!'@#%&()*+,-./:;<=>?[\\]^_`{|}~ ":
        speeches = speeches.replace(ch,' ')

    tokens = speeches.split()
    
    #word lemmatization
    lmtzr = WordNetLemmatizer()
    tokens = [lmtzr.lemmatize(token) for token in tokens]
    tokens = [lmtzr.lemmatize(token,'v') for token in tokens]

    #tokens = bigrams(tokens)                    # uncomment this line, we can use bigram as

    total_tokens_count = len(tokens)
    unique_tokens_dict = collections.Counter(tokens)   #key is word, value is the count,
                                                       #also default value 0 for non-exsit key.

    result = [ speech_list, unique_tokens_dict, total_tokens_count ]
    return result

def stemWordMatch(question,sentence):

    lmtzr = WordNetLemmatizer()

    question_tokens = set(nltk.word_tokenize(question))
    sentence_tokens=set(nltk.word_tokenize(sentence))

    count=0
    '''for i in sentence_tokens:
        #Finding the exact word match
        if lmtzr.lemmatize(i, 'v').lower() in  [lmtzr.lemmatize(x, 'v').lower() for x in question_tokens]:
            #print  'matching word is:',i
            count=count+6
        elif i.lower() in [x.lower() for x in question_tokens]:
            print 'i is :',i
            count=count+3
    #print 'Exact word match count is :',count'''

    for i in sentence_tokens:
        #Finding the exact word match

        if i.lower() in [x.lower() for x in question_tokens]:
            #print 'i is :',i
            count=count+3
        elif lmtzr.lemmatize(i, 'v').lower() in  [lmtzr.lemmatize(x, 'v').lower() for x in question_tokens]:
            #print  'matching word is:',i
            count=count+6

    #print 'Exact word match count is :',count


    return count

def weed_out_lexelts(tweets_file):
    lexelts = []
    WNL = WordNetLemmatizer()
    with open(tweets_file, 'r') as twh:
        for line in twh:    
            line = line.strip().split(' :: ')[1]
            lexelts_temp = []
            try:
                lexelts_temp = pos_tag(word_tokenize(line))
            except TypeError:
                print line

            # Get sanitized parts of speech, not the Treebank style
            # Tuples are immutable, need to make a new single-tuple list 
            for w, p in lexelts_temp:
                new_p = get_sanitized_pos(p)
                new_w = w
                try: 
                    new_w = WNL.lemmatize(w, new_p)
                except KeyError:
                    pass
                lexelts.extend([(new_w, new_p)])
    
    lexelts = list(set(lexelts))
    print lexelts
    return lexelts

    def run(self):
        """
        How do I run this Task?
        Luigi will call this method if the Task needs to be run.
        """
        # remove stop words and punctuation
        stop = set(stopwords.words('english'))
        tokenizer = RegexpTokenizer(r'\w+')
        wordnet = WordNetLemmatizer()

        docs = []

        #ipdb.set_trace()

        for f in self.input(): # The input() method is a wrapper around requires() that returns Target objects
            lines = 0
            words = []

            for line in f.open('r'):
                if lines == 0:
                    label = line
                    lines +=1
                else:
                    words.extend(tokenizer.tokenize(line))
                    lines +=1

            words_filtered = filtered_words = [wordnet.lemmatize(w) for w in words if not w in stopwords.words('english')]
            docs.append((label, '\t'.join(words)))

        out = self.output().open('w')
        for label, tokens in docs:
            out.write("%s,%s\n" % (label.strip(), tokens.strip()))
        out.close()

def lemma_tokenize(paragraph):
    lmtzr = WordNetLemmatizer()
    try:
        return [lmtzr.lemmatize(word).lower() for sentence in tokenize(paragraph) for word in sentence]
    except LookupError:
        nltk.download('wordnet')
        return [lmtzr.lemmatize(word).lower() for sentence in tokenize(paragraph) for word in sentence]