Cómo eliminar las palabras de detener en Python
# You need a set of stopwords. You can build it by yourself if OR use built-in sets in modules like nltk and spacy
# in nltk
import nltk
nltk.download('stopwords') # needed once
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
stop_words = set(stopwords.words('english'))
example_sent = "This is my awesome sentence"
# tokenization at the word level
word_tokens = word_tokenize(example_sent)
# list of words not in the stopword list
filtered_sentence = [w for w in word_tokens if not w.lower() in stop_words]
# in spacy
# from terminal
python -m spacy download en_core_web_lg # or some other pretrained model
# in your program
import spacy
nlp = spacy.load("en_core_web_lg")
stop_words = nlp.Defaults.stop_words
example_sent = "This is my awesome sentence"
doc = nlp(example_sent)
filtered_sentence = [w.text for w in doc if not w.text.lower() in stop_words]
wolf-like_hunter
