Answer-first summary for fast verification
Answer: featurization = 'auto'
The question requires configuring AutoML to automatically handle missing value imputation and categorical feature encoding. The 'featurization = auto' parameter in AutoMLConfig enables automatic preprocessing, including imputing missing values (using methods like mean, median, or mode) and encoding categorical variables (via one-hot or ordinal encoding). This is confirmed by the community discussion, where multiple comments with high upvotes (e.g., 8 and 6 upvotes) reference Microsoft documentation stating that automatic featurization handles these tasks. Other options are incorrect: 'enable_voting_ensemble' relates to ensemble modeling, 'task' defines the ML task type (already specified as regression), 'exclude_nan_labels' removes rows with missing labels (not features), and 'enable_tf' enables TensorFlow models (irrelevant to preprocessing).
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You are using automated machine learning to train a regression model. Your dataset contains features with missing values and categorical features with few distinct values. You must configure automated machine learning to automatically handle the imputation of missing values and the encoding of categorical features as part of the training task.
Which parameter and value pair should you use in the AutoMLConfig class?
A
featurization = 'auto'
B
enable_voting_ensemble = True
C
task = 'classification'
D
exclude_nan_labels = True
E
enable_tf = True