In [2]:

    

from nltk.corpus import stopwords


    

In [3]:

    

sw = stopwords.words("english")


    

In [7]:

    

len(sw)


    

    
Out[7]:





153

In [52]:

    

%run vectorize_text.py


    

    




emails processed

In [53]:

    

len(vec.get_feature_names())


    

    
Out[53]:





38757

In [54]:

    

vec.get_feature_names()[34597]


    

    
Out[54]:





u'stephaniethank'

In [ ]: