Explore Library
Code QuizIntermediate

Text Classification Feature Pipeline

Vectorizing a single string instead of a list of documents.

Codepython
from sklearn.feature_extraction.text import CountVectorizer

texts = ["good movie", "bad film"]
vec = CountVectorizer()

# Build the document-term matrix for the corpus
X = vec.fit_transform(texts[0])
print(X.shape)

What is the bug in this feature pipeline?