Cleaning a blog post
In this exercise, you have been given an excerpt from a blog post. Your task is to clean this text into a more machine friendly format. This will involve converting to lowercase, lemmatization and removing stopwords, punctuations and non-alphabetic characters.
The excerpt is available as a string blog and has been printed to the console. The list of stopwords are available as stopwords.
Este exercício faz parte do curso
Feature Engineering for NLP in Python
Instruções do exercício
- Using list comprehension, loop through
docto extract thelemma_of each token. - Remove stopwords and non-alphabetic tokens using
stopwordsandisalpha().
Exercício interativo prático
Experimente este exercício completando este código de exemplo.
# Load model and create Doc object
nlp = spacy.load('en_core_web_sm')
doc = nlp(blog)
# Generate lemmatized tokens
lemmas = [token.____ for token in ____]
# Remove stopwords and non-alphabetic tokens
a_lemmas = [lemma for lemma in lemmas
if lemma.____ and lemma not in ____]
# Print string after text cleaning
print(' '.join(a_lemmas))