Tokenization with spaCy
In this exercise, you'll practice tokenizing text. You'll use the first review from the Amazon Fine Food Reviews dataset for this exercise. You can access this review by using the text
object provided.
The en_core_web_sm
model is already loaded for you. You can access it by calling nlp()
. You can use list comprehension to compile output lists.
Este ejercicio forma parte del curso
Natural Language Processing with spaCy
Instrucciones del ejercicio
- Store Doc container for the pre-loaded review in a
document
object. - Store and review texts of all the tokens of the
document
in the variablefirst_text_tokens
.
Ejercicio interactivo práctico
Prueba este ejercicio y completa el código de muestra.
# Create a Doc container of the given text
document = ____(____)
# Store and review the token text values of tokens for the Doc container
first_text_tokens = [____ for ____ in ____]
print("First text tokens:\n", first_text_tokens, "\n")