In [1]:

    

import numpy as np
from sklearn.feature_extraction.text import CountVectorizer


    

In [2]:

    

vectorizer = CountVectorizer()


    

In [3]:

    

string1 = "hi Katie the self driving car will be late Best Sebastian"
string2 = "Hi Sebastian the machine learning class will be great great great Best Katie"
string3 = "Hi Katie the machine learning class will be most excellent"

email_list = [string1, string2, string3]


    

In [4]:

    

bag_of_words = vectorizer.fit(email_list)
bag_of_words = vectorizer.transform(email_list)


    

In [6]:

    

print bag_of_words


    

    




  (0, 0)	1
  (0, 1)	1
  (0, 2)	1
  (0, 4)	1
  (0, 7)	1
  (0, 8)	1
  (0, 9)	1
  (0, 13)	1
  (0, 14)	1
  (0, 15)	1
  (0, 16)	1
  (1, 0)	1
  (1, 1)	1
  (1, 3)	1
  (1, 6)	3
  (1, 7)	1
  (1, 8)	1
  (1, 10)	1
  (1, 11)	1
  (1, 13)	1
  (1, 15)	1
  (1, 16)	1
  (2, 0)	1
  (2, 3)	1
  (2, 5)	1
  (2, 7)	1
  (2, 8)	1
  (2, 10)	1
  (2, 11)	1
  (2, 12)	1
  (2, 15)	1
  (2, 16)	1

In [9]:

    

vectorizer.vocabulary_.get("great")


    

    
Out[9]:





6

In [10]:

    

from nltk.corpus import stopwords


    

In [11]:

    

sw = stopwords.words("english")


    

In [13]:

    

sw[0]


    

    
Out[13]:





u'i'

In [15]:

    

sw[10]


    

    
Out[15]:





u'yours'

In [16]:

    

len(sw)


    

    
Out[16]:





127

In [17]:

    

from nltk.stem.snowball import SnowballStemmer


    

In [18]:

    

stemmer = SnowballStemmer("english")


    

In [19]:

    

stemmer.stem("responsiveness")


    

    
Out[19]:





u'respons'

In [20]:

    

stemmer.stem("responsivity")


    

    
Out[20]:





u'respons'

In [21]:

    

stemmer.stem("unresponsive")


    

    
Out[21]:





u'unrespons'

In [22]:

    

stemmer.stem("respond")


    

    
Out[22]:





u'respond'