Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
Comments
Loading comments...
Ultimate access to all questions.
Your company operates a large retail website and has migrated to Google Cloud, utilizing various ML models developed with PyTorch, TensorFlow, and BigQueryML. With the use of BigTable, CloudSQL, and Cloud Storage, and now working with Vertex AI, you need to manage input tabular data in CSV format. The data is critical for training models that predict inventory demand across multiple regions. Given the importance of data quality and model accuracy, what are the two best practices for managing these CSV files in Vertex AI to ensure optimal performance and compatibility? (Choose two options)
A
Vertex AI automatically manages any CSV file without requiring any operations, ensuring seamless integration.
B
Ensure your CSV file has a header row with column names that only include alphanumeric characters and underscores, to avoid parsing errors.
C
Vertex AI does not support CSV files, requiring conversion to another format before use.
D
The delimiter in your CSV file must be a comma, as Vertex AI expects comma-delimited files by default for highest compatibility.
E
You are limited to importing files that are a maximum of 10GB in size, which may require splitting larger datasets.