MLA-C01 Question 67
Select 2You are working as a Machine Learning Engineer for an e-commerce company. You need to preprocess and transform a large dataset containing customer purchase history to prepare it for model training. The dataset is stored in Amazon S3, and you want to identify missing values, apply feature transformations (e.g., normalization), and visualize feature distributions. Additionally, you prefer a low/no-code solution integrated with AWS services. Which tool(s) should you use?
- A
Amazon SageMaker Data Wrangler
- B
AWS Glue
- C
AWS Glue DataBrew
- D
Amazon Athena
- E
Amazon QuickSight
Show answer and explanation
Correct answers: A, C
Explanation
Amazon SageMaker Data Wrangler and AWS Glue DataBrew are both low-code tools designed for preprocessing and transforming datasets. SageMaker Data Wrangler is specifically tailored for machine learning workflows, while Glue DataBrew provides similar capabilities and is also suitable for data cleaning, transformation, and visualization tasks. Both tools integrate seamlessly with AWS services like Amazon S3, making them ideal for this use case.
- A. Correct.
Amazon SageMaker Data Wrangler is a low-code tool designed for data preprocessing and feature engineering. It allows you to interactively clean, transform, and visualize data for machine learning workflows.
- B. Incorrect.
AWS Glue is primarily used for ETL (Extract, Transform, Load) processes and building data pipelines. While powerful, it is not a low/no-code tool focused on visualization or feature transformations.
- C. Correct.
AWS Glue DataBrew is a low-code data preparation tool that allows you to clean and transform data, as well as visualize feature distributions, making it suitable for this scenario.
- D. Incorrect.
Amazon Athena is a serverless query service for analyzing data in S3 using SQL. While useful for querying, it does not provide capabilities for feature transformations or visualizations required for this use case.
- E. Incorrect.
Amazon QuickSight is a business intelligence tool for creating dashboards and reports. It is not intended for data preprocessing or feature engineering for machine learning.