如何使用Spacy解决“str”对象没有属性“lemma_”的问题？

Question

我试图在python中使用DataFrame对我的Spacy进行柠檬化。我使用的代码如下所示：

# import spaCy's language model
nlp = spacy.load("en_core_web_sm")

# function to lemmatize text
def lemmatization(texts):
    output = []
    for i in texts:
        lem = [str(token).lemma_ for token in nlp(i) or str(token) in ["-PRON-"]]
        output.append(' '.join(lem))
    return output

train['clean_tweet'] = lemmatization(train['clean_tweet'])
test['clean_tweet'] = lemmatization(test['clean_tweet'])

结果发现我犯了一个错误，说：

'str‘对象没有属性'lemma_’

我怎么解决这个问题？

Answer 1

string_ = "I am will be playing football tommorrow" # dummy string 
obj = nlp(string_)
lemmatize_token = [x.lemma_ for x in obj]

print(lemmatize_token)
['I', 'be', 'will', 'be', 'play', 'football', 'tommorrow']