Python stem.SnowballStemmer类代码示例

def des_extrect():
    filename_list = []
    file_stopwords = file('stopwords.txt', "r")
    stopwords = [line.strip() for line in file_stopwords.readlines()]  
    for file_name in os.listdir(DESCRIPTION_DIR):
        filename_list.append(file_name) 
    for filename in filename_list:
        path =  os.path.join(DESCRIPTION_DIR, filename)
        fr = file(path, 'r')
        fw = file(filename+'.des', 'w')
        soup = BeautifulSoup(fr.read())
        docs = soup.findAll('doc')
        for doc in docs:
            content = str(doc['title'] + doc.snippet.text)
            content =  re.sub("[\.\@\,\:\;\!\?\(\)]".decode("utf8"), "".decode("utf8"),content)
            stemmer = SnowballStemmer('english')
            content = content.split()
            pro_content = ''
            for w in content: 
                w = stemmer.stem(w)
                #去停用词
                if w not in stopwords:
                    pro_content += w + ' '
            fw.write(doc['rank'] + ' ' +pro_content+'\n')
        fw.close()
        fr.close()

def text_token_data_generator():
    global id_text_index_map
    translation_table = string.maketrans(
        string.punctuation + string.uppercase, " " * len(string.punctuation) + string.lowercase
    )
    snowball_stemmer = SnowballStemmer("english")
    for f in glob.glob("json/text/*.json"):
        for line in open(f).readlines():
            extract_row = json.loads(line)
            id_text_index_map[extract_row["file_id"]] = len(id_text_index_map)
            visible_text = extract_row["visible_text"].encode("ascii", "ignore")
            visible_text = visible_text.translate(translation_table)
            visible_text = [
                snowball_stemmer.stem(word)
                for word in visible_text.split()
                if word not in ENGLISH_STOP_WORDS and len(word) > 1
            ]
            title = extract_row["title"].encode("ascii", "ignore")
            title = title.translate(translation_table)
            title = [
                "t^{}".format(snowball_stemmer.stem(word))
                for word in title.split()
                if word not in ENGLISH_STOP_WORDS and len(word) > 1
            ]
            visible_text.extend(title)
            yield " ".join(visible_text)

def text_to_wordlist(text, remove_stopwords=False, stem_words=False):
    # Clean the text, with the option to remove stopwords and to stem words.
    
    # Convert words to lower case and split them
    text = text.lower().split()

    # Optionally, remove stop words
    if remove_stopwords:
        stops = set(stopwords.words("english"))
        text = [w for w in text if not w in stops]
    
    text = " ".join(text)
    
    #Remove Special Characters
    text=special_character_removal.sub('',text)
    
    #Replace Numbers
    text=replace_numbers.sub('n',text)

    # Optionally, shorten words to their stems
    if stem_words:
        text = text.split()
        stemmer = SnowballStemmer('english')
        stemmed_words = [stemmer.stem(word) for word in text]
        text = " ".join(stemmed_words)
    
    # Return a list of words
    return(text)

class ModelBuilder():

    def __init__(self):
        self.model = {}
        self.stemmer = SnowballStemmer('english')

    def build(self):
        with open('data/candidate_synonyms.txt') as f:
            all_words = f.read().split('\n')
            for words in all_words:
                if words:
                    word, similar = words.split(',')
                    word, similar = self.stemmer.stem(word), self.stemmer.stem(similar)
                    if word not in self.model: self.model[word] = {}
                    self.model[word][similar] = 1
        return self

    def condense(self):
        condensed_model = {}
        for word, similars in self.model.items():
            for similar in similars:
                if self.model.get(similar, {}).has_key(word):
                    if condensed_model.has_key(word):
                        condensed_model[word].append(similar)
                    else:
                        condensed_model[word] = [similar]
        self.model = condensed_model
        return self

def frequency_analysis(input_path, output_path, stopwords=None, n_most_common=50):
	recipes = []
	with open(input_path, 'r') as f:
		for i, line in enumerate(f):
			if line == '\n':
				break
			if i == 0:
				continue  # skip header
			fields = line.split('\t')
			recipes.append(fields[1].replace("\n", ""))
	recipe_text = re.sub("[^a-z ]", "", ' '.join(recipes))
	recipe_words = re.split("\s+", recipe_text)
	stemmer = SnowballStemmer("english")
	recipe_stems = [stemmer.stem(w) for w in recipe_words]
	if stopwords is not None:
		recipe_stems = filter(None, [s for s in recipe_stems if s not in stopwords])
	top_words = Counter(recipe_stems).most_common(n_most_common)

	# write to a file
	# do a second pass of the recipe to determine how many of the documents the term is in
	freq_table = open(output_path, 'wb')
	for elt in top_words:
		doc_freq = sum([elt[0] in recipe for recipe in recipes])
		freq_table.write(','.join([str(e) for e in elt]) +','+ str(doc_freq) + '\n')
	freq_table.close()

def norm_corpus(document_list):
    norm_doc_list = []
    
    # lowercase
    document_list = [word.lower() for word in document_list]

    
    # remove symbols in text
    symbols = ",.?!"
    for sym in symbols:
        document_list = [word.replace(sym,'') for word in document_list]
    
    
    # loop through each string i.e. review in the column
    for doc in document_list:
        doc = nltk.word_tokenize(doc)
        
        # remove stopwords
        doc = [word for word in doc if word not in stopwords.words('english')]
        
        # stem words
        stemmer = SnowballStemmer("english")
        doc = [stemmer.stem(word) for word in doc]
        
        # make tokenised text one string
        norm_doc = " ".join(doc)
        norm_doc_list.append(norm_doc)
    
    return norm_doc_list

def stemmed(text,language):
    stemmer= SnowballStemmer(language)
    tas=text.split()
    text=""
    for word in tas:
        text=" ".join((text,stemmer.stem(word)))
    return text.lstrip()

def procesar(request, identificador):
	lmtzr = WordNetLemmatizer()
	d = Documento.objects.get(id=identificador)
	
	#nltk.corpus.cess_esp.words()
	
	
	tokens = nltk.word_tokenize(d.contenido.replace('.', ' . '))
	#print tokens
	#scentence = d.contenido

	#scentence = scentence.lower() 

	words = tokens
	spanish_stemmer = SnowballStemmer('spanish')
	

	#This is the simple way to remove stop words
	important_words=[]
	for word in words:
		if word not in stopwords.words('spanish'):
		    important_words.append([word, lmtzr.lemmatize(word), spanish_stemmer.stem(word)])




	return render_to_response('templates/documentoProcesado.html', 
				{
					'original': d.contenido,
					'tokens': tokens,
					'important_words' : important_words,
					#'pos_tags': pos_tags,
					#'ne_chunks': ne_chunks.subtrees(),
				})

def normalized_token(token):
    """
    Use stemmer to normalize the token.
    建图时调用该函数，而不是在file_text改变词形的存储
    """
    stemmer = SnowballStemmer("english") 
    return stemmer.stem(token.lower())

def preprocessing(doc): #stop word as optional
        x = re.sub("[^a-zA-Z]", " ", doc) #only words
        x = x.lower().split()
        stemmer = SnowballStemmer("english") # use snowball
        stops = set(stopwords.words("english")) # set is faster than list
        x = [stemmer.stem(word) for word in x if word not in stops]
        return(x)

def stemWordMatch2(question,sentence):


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

    #  Finding the match between two words from the same root  using Lancaster Stemmizer

    '''stemmer=LancasterStemmer()

    for i in sentence_tokens:
        stem_words_list.append(stemmer.stem(i))

    for i in question_tokens:
        question_words_list.append(stemmer.stem(i))

    #print 'Stem word list',stem_words_list
    #print 'Question word list', question_words_list

    stem_count=0
    for i in stem_words_list:
        #Finding the exact word match
        if i.lower() in [x.lower() for x in question_words_list]:
            #print 'Question word is',x
            #print 'Sentence word stem is :',i
            #print 'Match'
            stem_count=stem_count+6
    stem_word_match_counter.append(count)'''

    stem_word_match_counter=[]
    stem_words_list=[]
    question_words_list=[]

    #  Finding the match between two words from the same root  using Snowball Stemmizer

    snowball_stemmer = SnowballStemmer('english')

    for i in sentence_tokens:
        stem_words_list.append(snowball_stemmer.stem(i))

    for i in question_tokens:
        question_words_list.append(snowball_stemmer.stem(i))

    #print 'Stem word list',stem_words_list
    #print 'Question word list', question_words_list

    stem_count=0
    for i in stem_words_list:
        #Finding the exact word match
        if i.lower() in [x.lower() for x in question_words_list]:
            #print 'Question word is',x
            #print 'Sentence word stem is :',i
            #print 'Match'
            stem_count=stem_count+6
    #print 'Stem word count match score is :', stem_count

    return stem_count

def preprocess_tweets(tweets):
    stemmer = SnowballStemmer("english")
    stop = set(stopwords.words("english"))
    tweet_texts = [ " ".join(stemmer.stem(i) if len(i) > 1 else i
                                for i in ("".join(c for c in word if c not in string.punctuation)
                                            for word in tweet["text"].lower().split())
                                if i and i not in stop)
                    for tweet in tweets ]
    return list(set(tweet_texts))

    def stem(self, content):
        import re

        original_string = content
        new_content = re.sub('[^a-zA-Z0-9\n\.]', ' ', original_string)
        words = new_content.split()
        stemmer = SnowballStemmer('english')
        singles = [stemmer.stem(wordsa) for wordsa in words]
        return (' '.join(singles))

 def __call__(self, doc ):
     snowball_stemmer = SnowballStemmer('english')
 	#tokenizer = RegexpTokenizer(r'\w+')
     #words=[self.wnl.lemmatize(t) for t in word_tokenize(doc)]
     words=[snowball_stemmer.stem(t) for t in word_tokenize(doc)]
     stop_words=set(stopwords.words('english'))
     stop_words.update(self.mystops)
     stop_words=list(stop_words)
     return [i.lower() for i in words if i not in stop_words]        

def stemLem(w):
	lemmatizer = WordNetLemmatizer()
	stemmer = SnowballStemmer("english")
	#stemmer = PorterStemmer()

	lem = lemmatizer.lemmatize(w)
	if len(w) > len(lem):
		return lem
	return stemmer.stem(w)