MLS-C01 Question #332: Real Exam Question with Answer & Explanation

Question

A company wants to forecast the daily price of newly launched products based on 3 years of data for older product prices, sales, and rebates. The time-series data has irregular timestamps and is missing some values. Data scientist must build a dataset to replace the missing values. The data scientist needs a solution that resamples the data daily and exports the data for further modeling. Which solution will meet these requirements with the LEAST implementation effort?

Options

• AUse Amazon EMR Serverless with PySpark.
• BUse AWS Glue DataBrew.
• CUse Amazon SageMaker Studio Data Wrangler.
• DUse Amazon SageMaker Studio Notebook with Pandas.

Explanation

For time-series data with irregular timestamps and missing values requiring daily resampling and imputation for ML modeling with the least effort, Amazon SageMaker Studio Data Wrangler is the ideal solution.

Common mistakes.

• A. Amazon EMR Serverless with PySpark is powerful for large-scale data processing but requires writing and managing custom code, which involves more implementation effort than a visual data preparation tool.
• B. AWS Glue DataBrew is a visual data preparation tool that can handle these tasks, but SageMaker Data Wrangler is more tightly integrated into the ML workflow and specializes in preparing data for SageMaker models, often offering a slightly lower effort for ML-specific transformations.
• D. Using an Amazon SageMaker Studio Notebook with Pandas requires writing custom Python code for resampling and imputation, which entails more implementation effort and debugging compared to using a visual, low-code tool like Data Wrangler.

Concept tested. SageMaker Data Wrangler for data preparation

Reference. https://docs.aws.amazon.com/sagemaker/latest/dg/data-wrangler.html

No community discussion yet for this question.