def wrapper(*args, **kwargs):

begin = time.time()

result = func(*args, **kwargs)

end = time.time()

ellapsed = end - begin

print ('{0} min. {1} sec. in function {2}'.format(int(ellapsed//60), round(ellapsed%60, 2), func.__name__))

return result

def is_ok(item, stemmer):

return True if item.lower() == item and all((elem.isalpha() and not elem in string.ascii_letters and not stemmer.stem(item) in stopwords) for elem in item) else False

from nltk.stem.snowball import RussianStemmer

stemmer = RussianStemmer(ignore_stopwords=True)

tokens = word_tokenize(text)

def is_ok(item):

return True if item.lower() == item and all(elem.isalpha() and elem in string.ascii_letters for elem in item) else False

from nltk.stem.snowball import EnglishStemmer

stemmer = EnglishStemmer(ignore_stopwords=True)

tokens = word_tokenize(text)

result = [stemmer.stem(item) for item in tokens if is_ok(item)]

data = []

labels = []

with open(fname, encoding = 'utf8') as fh:

for row in unicode_csv_reader(fh):#(fh, delimiter = '\t'):

try:

if len(row) == 3:

score, header, body = row

elif len(row) == 2: pass

txt = u'\t'.join([header, header, body])

labels.append(int(score))

data.append(txt)

except ValueError: pass

if lang == 'en':

vect = TfidfVectorizer(stop_words = 'english', lowercase = False, tokenizer = tokenize_en)

else:

vect = TfidfVectorizer(stop_words = stopwords, lowercase = False, tokenizer = tokenize)

func = svm.SVC(kernel='linear')

data, labels = file2data(fname)

clf = clf_factory(lang = lang)

print ("Hello")

clf.fit(data, labels)

print ("Bye")