Exam AWS Certified Machine Learning - Specialty topic 1 question 248 discussion

Data Wrangler can transform the date time to desire features

Amazon SageMaker Data Wrangler is a visual data preparation tool that makes it easy to clean, transform, and featurize data for machine learning. It provides a variety of built-in transformations, including the Featurize date/time transform, which can be used to generate the new variables from the timestamp variable. The other options require the data scientist to develop code, which can be more time-consuming and error-prone. Amazon EMR and AWS Glue are both batch processing services that can be used to run Python code. However, they require the data scientist to create and manage a cluster, which can be a significant operational overhead. Amazon SageMaker Processing is a serverless processing service that can also be used to run Python code. However, it is more expensive than Data Wrangler and does not provide the same level of visual tooling.

Letra C é a correta, pois o Data Wrangler permite low code para realizar esta tarefa e como queremos o menor operational overhead esta é a solução. Letra D também é possível, mas envolve desenvolvimento de código ficando mais complexa que a Letra C. Letra A requer subir um novo serviço e Letra B cai no mesmo cenário da Letra D (desenvolver código).

https://aws.amazon.com/blogs/machine-learning/prepare-time-series-data-with-amazon-sagemaker-data-wrangler/ "Featurize datetime time series transformation to add the month, day of the month, day of the year, week of the year, and quarter features to our dataset."