我想在 nltk 提供的停用词列表中添加一些词。我有一个 csv 文件,其中包含我想添加到列表中的停用词,但它不起作用。这是我试过的:
from nltk.corpus import stopwords
stop_words = set(stopwords.words('english'))
#add words that aren't in the NLTK stopwords list
new_stopwords = ["stop", "pause", "replay"]
new_stopwords_list = stop_words.union(new_stopwords)
#add words that aren't in the NLTK stopwords list from a csv file
tcsv_stopword = pd.read_csv("stopwords.csv", names= ["stopwords"], header = None)
# convert stopword string to list & append additional stopword
list_stopwords.extend(txt_stopword["stopwords"][0].split(' '))
#remove words that are in NLTK stopwords list
not_stopwords = {"not", "don't", "never", "without"}
final_stop_words = set([word for word in new_stopwords_list if word not in not_stopwords])
print(final_stop_words)