MLA-C01 Question 5
Select 2You are tasked with building a machine learning model to predict customer churn using data stored in an Amazon S3 bucket. The dataset contains raw data with missing values, inconsistent column names, and a mix of numerical and categorical features. What steps should you take to properly prepare your data for training in Amazon SageMaker?
- A
Use AWS Glue to clean the data by normalizing column names and handling missing values before exporting it to Amazon S3.
- B
Directly load the raw data from Amazon S3 into SageMaker and handle missing values within the training script.
- C
Use Amazon SageMaker Data Wrangler to visually clean, transform, and engineer features before saving the transformed data back to Amazon S3.
- D
Use Amazon Redshift to preprocess the data and export the cleaned dataset to Amazon S3.
- E
Ignore missing values and proceed with training, as SageMaker automatically handles missing data during model training.
Show answer and explanation
Correct answers: A, C
Explanation
Preparing data for machine learning involves cleaning, transforming, and engineering features to ensure the dataset is suitable for training. AWS Glue and Amazon SageMaker Data Wrangler are purpose-built tools for these tasks. AWS Glue is ideal for large-scale data cleaning and transformation, while SageMaker Data Wrangler provides a visual interface for more interactive feature engineering and preprocessing. Ignoring missing values or relying solely on the training script for preprocessing is not recommended, as it can lead to inefficiencies or suboptimal model performance.
- A. Correct.
This is correct. AWS Glue is commonly used to clean and transform raw data at scale, making it an appropriate choice for preparing the dataset.
- B. Incorrect.
This is incorrect. While it is possible to handle missing values in the training script, it is not an efficient approach for data preparation, especially if the data requires extensive preprocessing.
- C. Correct.
This is correct. Amazon SageMaker Data Wrangler provides a user-friendly interface for cleaning and transforming data, making it a suitable tool for this scenario.
- D. Incorrect.
This is incorrect. While Amazon Redshift can be used for data processing, it is primarily a data warehousing solution and not typically the first choice for ML-specific data preparation tasks.
- E. Incorrect.
This is incorrect. Ignoring missing data can lead to poor model performance, and SageMaker does not automatically handle missing values unless explicitly configured.