_3_1.py

import nltk
nltk.download('reuters')
from nltk.corpus import reuters

def read_corpus(category="crude"):
    """ Read files from the specified Reuter's category. And adds
        START and END to beginning and end of each document.
        
        Params:
            category (string): category name
        Return:
            list of lists, with words from each of the processed files
    """
    files = reuters.fileids(category)
    return [[START_TOKEN] + [w.lower() for w in list(reuters.words(f))] + [END_TOKEN] for f in files]