from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize# define the language for stopwords removal
stopwords = set(stopwords.words("english"))
print ("""{0} stop words""".format(len(stopwords)))tokenize_words = word_tokenize(sample_text)
filtered_sample_text = [w for w in tokenize_words if not w in stopwords]print ('\nOriginal Text:')
print ('------------------\n')
print (sample_text)
print ('\n Filtered Text:')
print ('------------------\n')
print (' '.join(str(token) for token in filtered_sample_text))