AWS Certified Machine Learning Engineer Associate · Free Practice Question Medium
Question 5
An ML engineer is using Amazon SageMaker Data Wrangler to preprocess data for a machine learning project. They need to import customer transaction data from various sources, clean and transform the data, and engineer features for model training. Which TWO of the following steps should the engineer take to prepare the data using Data Wrangler? (Choose TWO.)
-
A
Perform data transformations using SageMaker Studio's in-built Jupyter notebooks.
-
B
Import data from Amazon S3, Redshift, or SageMaker Feature Store into Data Wrangler.
-
C
Use Data Wrangler to apply one-hot encoding on categorical variables.
-
D
Export the transformed data directly to Amazon Athena for further analysis.
-
E
Manually write custom Python scripts to handle missing data and normalization tasks.
Reveal correct answers
Correct answers: B, C
A.
While SageMaker Studio allows Jupyter notebooks for custom transformations, Data Wrangler simplifies the process by offering pre-built transformations in a visual interface.
B.
Data Wrangler can import data from multiple sources such as Amazon S3, Redshift, and SageMaker Feature Store, making it easy to preprocess diverse datasets.
C.
SageMaker Data Wrangler provides built-in features like one-hot encoding to transform categorical variables into a format suitable for machine learning.
D.
Data Wrangler can export the processed data to S3 or directly integrate with SageMaker for training, but Athena is not commonly used for this.
E.
Data Wrangler has a user-friendly visual interface that eliminates the need for manual Python scripting.
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
