MLA-C01 Question 129
Single answerYou are building a machine learning pipeline for a large e-commerce platform. The pipeline includes data preprocessing, model training, and deployment using AWS services. During the preprocessing step, you need to handle missing data in your dataset. Which of the following AWS services or features would be most appropriate for this task?
- A
AWS Glue DataBrew
- B
Amazon SageMaker Ground Truth
- C
AWS Lambda
- D
Amazon S3 Event Notifications
Show answer and explanation
Correct answer: A
Explanation
AWS Glue DataBrew is the most appropriate choice for handling missing data because it provides a visual, no-code interface for data preparation tasks. It is specifically designed for transforming and cleaning data, making it an ideal tool for preprocessing in a machine learning pipeline.
- A. Correct.
AWS Glue DataBrew is specifically designed for data preparation tasks, including handling missing data, normalizing datasets, and other preprocessing steps. It provides a no-code interface for cleaning and transforming data.
- B. Incorrect.
Amazon SageMaker Ground Truth is used to label datasets for supervised learning. It is not designed for preprocessing tasks like handling missing data.
- C. Incorrect.
AWS Lambda is a serverless compute service that can execute code in response to events. While it could be used in custom data preprocessing workflows, it is not specifically optimized for handling missing data.
- D. Incorrect.
Amazon S3 Event Notifications allow you to trigger actions when changes occur in an S3 bucket, such as uploads or deletions. They are not relevant to handling missing data in a dataset.