remove_stopwords_nltk.py 文件源码

def clean_review(review,stopwords):
    result = ""
    lemmatizer = WordNetLemmatizer()
    for word in review:
        #converts the word to its lemma form
        word = lemmatizer.lemmatize(word)
        #adds the word to the resultant review only if its not a stopword
        if word not in stopwords:
            #removes all non-alphabet characters
            word = re.sub('[^A-Za-z ]','',word)
            if(len(word) != 0):
                result += word+" "
    return result