如何从Pandas数据框文本列中使用NLTK语料库删除英语停用词？

Question

I am looking for a solution to remove the English stop words using NLTK corpus on a Pandas dataframe text column. Can we do it with the dataframe apply method, if yes, then please share it?

stop_words = set(stopwords.words('english'))
data['text'] = data['text'].apply(lambda text:  " ".join(w) for w in text.lower().split() if w not in stop_words)

Thanks and appreciate it if someone can answer it.

Answer 1

You could tokenize your text column (or simply split into a list of words) and then remove the stop words using the map or apply method.

For example:

data = pd.DataFrame({'text': ['a sentence can have stop words', 'stop words are common words like if, I, you, a, etc...']})
data
                                                text
0                     a sentence can have stop words
1  stop words are common words like if, I, you, a...

from nltk.corpus import stopwords
from nltk.tokenize import RegexpTokenizer

tokenizer = RegexpTokenizer('\w+')
stop_words = stopwords.words('english')

def clean(x):
    doc = tokenizer.tokenize(x.lower())
    return [w for w in doc if w in stop_words]

data.text.map(clean)
0                    [sentence, stop, words]
1    [stop, words, common, words, like, etc]
Name: text, dtype: object