movie_sentiment.py 文件源码

def text_clean(filename):
    '''
    Input: File path of script.
    Output: List of all words in script lowercased, lemmatized, without punctuation.
    '''
    wnl = WordNetLemmatizer()
    word_list = [word.decode("utf8", errors='ignore') for line in open(filename, 'r') for word in line.split()]
    lemma_list = [wnl.lemmatize(word.lower()) for word in word_list]
    return lemma_list