Aan de slagGa gratis aan de slag

Running a spaCy pipeline

You've already run a spaCy NLP pipeline on a single piece of text and also extracted tokens of a given list of Doc containers. In this exercise, you'll practice the initial steps of running a spaCy pipeline on texts, which is a list of text strings.

You will use the en_core_web_sm model for this purpose. The spaCy package has already been imported for you.

Deze oefening maakt deel uit van de cursus

Natural Language Processing with spaCy

Cursus bekijken

Oefeninstructies

  • Load the en_core_web_sm model as nlp.
  • Run an nlp() model on each item of texts, and append each corresponding Doc container to a documents list.
  • Print the token texts for each Doc container of the documents list.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Load en_core_web_sm model as nlp
nlp = spacy.____(____)

# Run an nlp model on each item of texts and append the Doc container to documents
documents = []
for text in ____:
  documents.append(____)
  
# Print the token texts for each Doc container
for doc in documents:
  print([____ for ____ in ____])
Code bewerken en uitvoeren