In [26]:

    

import collections


    

In [27]:

    

word_file = open(r'/Users/Harish/Documents/HK_Work/Python/DSE200x/Week-2/word_cloud/98-0.txt')
#stop_word = open(r'/Users/Harish/Documents/HK_Work/Python/DSE200x/Week-2/word_cloud/stopwords')


    

In [28]:

    

stopwords = set(line.strip() 
                for line in open(r'/Users/Harish/Documents/HK_Work/Python/DSE200x/Week-2/word_cloud/stopwords'))


    

In [29]:

    

wordcount = {}


    

In [30]:

    

for word in word_file.read().split():
    word = word.replace(',','')
    word = word.replace('.','')
    word = word.replace('\"','')
    word = word.replace('"','')
    if word not in stopwords:
        if word not in wordcount:
            wordcount[word] = 1
        else:
            wordcount[word] += 1


    

In [31]:

    

d = collections.Counter(wordcount)

#print(d.most_common(10))
for word, count in d.most_common(10):
    print(word, ": ", count)


    

    




I :  1470
said :  642
Mr :  602
The :  586
“I :  402
one :  373
He :  366
Lorry :  313
upon :  282
will :  266