You plan to use automated machine learning to train a regression model. You have data that has features which have missing values, and categorical features with few distinct values. You need to config

Question

Options

• Afeaturization = 'auto'
• Benable_voting_ensemble = True
• Ctask = 'classification'
• Dexclude_nan_labels = True
• Eenable_tf = True

• A
  89% (32)
• C
  6% (2)
• D
  3% (1)
• E
  3% (1)

Explanation

Setting featurization='auto' in the AutoMLConfig class instructs Azure AutoML to automatically apply featurization steps to the training data before model training begins. This includes imputing missing values using statistical strategies (mean, median, or mode depending on the feature) and encoding categorical features (e.g., one-hot encoding for low-cardinality columns). Option B (enable_voting_ensemble) creates an ensemble of models at the end of a run but does not handle data preprocessing. Option C (task='classification') changes the ML task type from regression to classification, which is incorrect for the stated goal. Option D (exclude_nan_labels) drops rows where the target label is NaN, which is unrelated to feature imputation. Option E (enable_tf) enables TensorFlow-based models and has no effect on featurization.

No community discussion yet for this question.