dictionary_remove_words.py

def make_Dictionary(train_dir):
    # where train_dir is the directory of the emails
    emails = [os.path.join(train_dir,f) for f in os.listdir(train_dir)]    
    all_words = []       
    for mail in emails:    
        with open(mail) as m:
            for i, line in enumerate(m):
                if i == 2:  # Body of email is only 3rd line of text file
                    words = line.split()
                    all_words += words
    
    dictionary = Counter(all_words)
    
    list_to_remove = dictionary.keys()
    for item in list_to_remove:
        if item.isalpha() == False: 
            del dictionary[item]
        elif len(item) == 1:
            del dictionary[item]
    dictionary = dictionary.most_common(3000)
    return dictionary