Python nltk.stem方法代码示例

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def _nltkStemmer(self, name):
        """ NLTK Stemmer """
        if name == 'porter':
            stemmer = PorterStemmer()
        elif name == 'snowball':
            stemmer = SnowballStemmer("english")
        elif name == "lancaster":
            stemmer = LancasterStemmer()
        else:
            return
        
        length = len(self._words)
        for i in range(length):
            word = self._words[i]['word']
            l = len(word)

            # Don't stem short words or words already categorized
            if l < 4 or self._words[i]['tag'] != Vocabulary.UNTAG:
                continue
            
            self._words[i]['word'] = stemmer.stem(self._words[i]['word']) 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def wrap_words (pair):
  """wrap each (word, tag) pair as an object with fully indexed metadata"""
  global STEMMER
  index = pair[0]
  result = []
  for word, tag in pair[1]:
    word = word.lower()
    stem = STEMMER.stem(word)
    if stem == "":
      stem = word
    keep = tag in ('JJ', 'NN', 'NNS', 'NNP',)
    result.append({ "id": 0, "index": index, "stem": stem, "word": word, "tag": tag, "keep": keep })
    index += 1
  return result


######################################################################
## build a graph from raw text 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def tagFilterAndStemming(originalTag):

    # Remove non alphabetical character and split on spaces
    processedTag = re.sub("[^a-zA-Z0-9]", " ", originalTag)
    processedTag = re.sub(" +", " ", processedTag)

    processedTag = processedTag.split(" ")

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

    stemmer = PorterStemmer()

    result = []

    for tag in processedTag:

        tag_stemmed = stemmer.stem(tag)

        if tag_stemmed not in stopwords_set:
            result.append(tag_stemmed)

    return result 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def build_analyzer(self):
        analyzer = super(TfidfVectorizer, self).build_analyzer()
        return lambda doc: (english_stemmer.stem(w) for w in analyzer(doc)) 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def preprocessing(text):
    text2 = " ".join("".join([" " if ch in string.punctuation else ch for ch in text]).split())

    tokens = [word for sent in nltk.sent_tokenize(text2) for word in
              nltk.word_tokenize(sent)]
    
    tokens = [word.lower() for word in tokens]
    
    stopwds = stopwords.words('english')
    tokens = [token for token in tokens if token not in stopwds]
    
    tokens = [word for word in tokens if len(word)>=3]
    
    stemmer = PorterStemmer()
    tokens = [stemmer.stem(word) for word in tokens]

    tagged_corpus = pos_tag(tokens)    
    
    Noun_tags = ['NN','NNP','NNPS','NNS']
    Verb_tags = ['VB','VBD','VBG','VBN','VBP','VBZ']

    lemmatizer = WordNetLemmatizer()

    def prat_lemmatize(token,tag):
        if tag in Noun_tags:
            return lemmatizer.lemmatize(token,'n')
        elif tag in Verb_tags:
            return lemmatizer.lemmatize(token,'v')
        else:
            return lemmatizer.lemmatize(token,'n')
    
    pre_proc_text =  " ".join([prat_lemmatize(token,tag) for token,tag in tagged_corpus])             

    return pre_proc_text 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def preprocessing(text):
    text2 = " ".join("".join([" " if ch in string.punctuation else ch for ch in text]).split())

    tokens = [word for sent in nltk.sent_tokenize(text2) for word in
              nltk.word_tokenize(sent)]
    
    tokens = [word.lower() for word in tokens]
    
    stopwds = stopwords.words('english')
    tokens = [token for token in tokens if token not in stopwds]
    
    tokens = [word for word in tokens if len(word)>=3]
    
    stemmer = PorterStemmer()
    try:
        tokens = [stemmer.stem(word) for word in tokens]

    except:
        tokens = tokens
        
    tagged_corpus = pos_tag(tokens)    
    
    Noun_tags = ['NN','NNP','NNPS','NNS']
    Verb_tags = ['VB','VBD','VBG','VBN','VBP','VBZ']

    lemmatizer = WordNetLemmatizer()

    def prat_lemmatize(token,tag):
        if tag in Noun_tags:
            return lemmatizer.lemmatize(token,'n')
        elif tag in Verb_tags:
            return lemmatizer.lemmatize(token,'v')
        else:
            return lemmatizer.lemmatize(token,'n')
    
    pre_proc_text =  " ".join([prat_lemmatize(token,tag) for token,tag in tagged_corpus])             

    return pre_proc_text 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def stemmer(method,data):
	"""
	Takes an array of words in JSON format.
	"""
	data = parse_input(data)
	if data == False:
		return ret_failure(703)
	else:
		res=[]
		if method == "lancaster":
			for word in data:
				try:
					res.append([word,LancasterSt.stem(word)])
				except:
					return ret_failure(702)
		elif method == "porter":
			for word in data:
				try:
					res.append([word,PorterSt.stem(word)])
				except:
					return ret_failure(702)
		elif method == 'snowball':
			for word in data:
				try:
					res.append([word,SnowballSt.stem(word)])
				except:
					return ret_failure(702)
		else:
			abort(404)
		return ret_success(res) 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def data_preparation(tweet): #nltk.tag._POS_TAGGER #treebank tag set https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
	
	url_regex = r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)'

	clean = re.sub(url_regex, '', tweet, flags = re.MULTILINE)                                                # strip out urls. urls, ew, nasty.
	clean = clean.replace('\n', ' ').replace("'", " ").replace('"', ' ')

	try:	
		clean = clean.decode("utf-8-sig").replace(u"\ufffd", "?")                                         # strip out Byte Order Marks
		print("Detected BOS")
	except:
		pass
	
	clean = re.sub(r'[^a-zA-Z ]', '', clean, flags = re.MULTILINE)                                            # the "#" symbol is actually called octothorpe. bananas.
	
	tokens = splitter.split(clean)										  # Tokeniztion

	lemma_pos_token = lemmatization_using_pos_tagger.pos_tag(tokens)					  # Part of speech tagging.
	out = ' '.join([out[1] for out in lemma_pos_token[0]])
	return out

	''' #https://pypi.org/project/hunspell/ #Double tokenizing. hunspell for units, nltk for context.
	import hunspell

	hobj = hunspell.HunSpell('/usr/share/myspell/en_US.dic', '/usr/share/myspell/en_US.aff')
	hobj.spell('spookie')

	hobj.suggest('spookie')

	hobj.spell('spooky')

	hobj.analyze('linked')

	hobj.stem('linked')
	''' 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def tokenize_and_stem(text):
    stemmer = SnowballStemmer("english")
    text = re.sub("^\d+\s|\s\d+\s|\s\d+$", " ", text)
    # first tokenize by sentence, then by word to ensure that punctuation is caught as it's own token
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]
    filtered_tokens = []
    # filter out any tokens not containing letters (e.g., numeric tokens, raw punctuation)
    for token in tokens:
        if re.search('[a-zA-Z]', token):
            filtered_tokens.append(token)
    stems = [stemmer.stem(t) for t in filtered_tokens]
    return stems
################################################################################ 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def stem_tokens(tokens, stemmer):
    stemmed = []
    for token in tokens:
        stemmed.append(stemmer.stem(token))
    return stemmed

#process the data 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def process_data(data,exclude_stopword=True,stem=True):
    tokens = [w.lower() for w in data]
    tokens_stemmed = tokens
    tokens_stemmed = stem_tokens(tokens, eng_stemmer)
    tokens_stemmed = [w for w in tokens_stemmed if w not in stopwords ]
    return tokens_stemmed


#creating ngrams
#unigram 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def tokenizer_porter(text):
    return [porter.stem(word) for word in text.split()]

#doc = ['runners like running and thus they run','this is a test for tokens']
#tokenizer([word for line in test_news.iloc[:,1] for word in line.lower().split()])

#show the distribution of labels in the train and test data 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def tokenize(self, paragraph):
        words = [self.ps.stem(word) for word in word_tokenize(paragraph)]
        filtered_words = [word for word in words if word not in stopwords.words('english')]
        return filtered_words 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import stem [as 别名]
def text_cleaner(text,
                 deep_clean=False,
                 stem= True,
                 stop_words=True,
                 translite_rate=True):
    rules = [
        {r'>\s+': u'>'},  # remove spaces after a tag opens or closes
        {r'\s+': u' '},  # replace consecutive spaces
        {r'\s*<br\s*/?>\s*': u'\n'},  # newline after a <br>
        {r'</(div)\s*>\s*': u'\n'},  # newline after </p> and </div> and <h1/>...
        {r'</(p|h\d)\s*>\s*': u'\n\n'},  # newline after </p> and </div> and <h1/>...
        {r'<head>.*<\s*(/head|body)[^>]*>': u''},  # remove <head> to </head>
        {r'<a\s+href="([^"]+)"[^>]*>.*</a>': r'\1'},  # show links instead of texts
        {r'[ \t]*<[^<]*?/?>': u''},  # remove remaining tags
        {r'^\s+': u''}  # remove spaces at the beginning

    ]

    if deep_clean:
        text = text.replace(".", "")
        text = text.replace("[", " ")
        text = text.replace(",", " ")
        text = text.replace("]", " ")
        text = text.replace("(", " ")
        text = text.replace(")", " ")
        text = text.replace("\"", "")
        text = text.replace("-", " ")
        text = text.replace("=", " ")
        text = text.replace("?", " ")
        text = text.replace("!", " ")

        for rule in rules:
            for (k, v) in rule.items():
                regex = re.compile(k)
                text = regex.sub(v, text)
            text = text.rstrip()
            text = text.strip()
        text = text.replace('+', ' ').replace('.', ' ').replace(',', ' ').replace(':', ' ')
        text = re.sub("(^|\W)\d+($|\W)", " ", text)
        if translite_rate:
            text = transliterate(text)
        if stem:
            text = PorterStemmer().stem(text)
        text = WordNetLemmatizer().lemmatize(text)
        if stop_words:
            stop_words = set(stopwords.words('english'))
            word_tokens = word_tokenize(text)
            text = [w for w in word_tokens if not w in stop_words]
            text = ' '.join(str(e) for e in text)
    else:
        for rule in rules:
            for (k, v) in rule.items():
                regex = re.compile(k)
                text = regex.sub(v, text)
            text = text.rstrip()
            text = text.strip()
    return text.lower()