Google Professional Machine Learning Engineer Question 101
Select 3Google Cloud PlatformYou are building a machine learning model on Google Cloud that requires processing multiple data types, including tabular data, images, and text. Which strategies should you use to organize and preprocess these data types to ensure efficient data storage, accessibility, and model training?
- A
Store tabular data in BigQuery, images in Cloud Storage, and text data in Cloud Datastore for efficient access.
- B
Use Cloud Storage to store all data types for simplicity and uniformity.
- C
Preprocess and convert text and image data into numerical formats before training the model.
- D
Leverage AutoML Table for all data types to automatically preprocess and train the model.
- E
Apply data versioning and metadata tagging to track preprocessing steps and maintain data consistency.
Show answer and explanation
Correct answers: A, C, E
Explanation
To effectively organize and preprocess diverse data types for machine learning on Google Cloud, it is important to use the appropriate storage solutions for each data type (e.g., BigQuery for tabular data and Cloud Storage for unstructured data like images and text). Preprocessing text and image data into numerical formats is essential for model training. Additionally, implementing data versioning and metadata tagging ensures reproducibility and traceability in ML workflows. Combining these strategies leads to efficient and scalable machine learning solutions.
- A. Correct.
BigQuery is ideal for tabular data, Cloud Storage is well-suited for unstructured data like images, and Cloud Datastore is generally better for NoSQL workloads, which is not optimal for this scenario. A better choice for text data would be Cloud Storage or a database like Firestore depending on the specific use case.
- B. Incorrect.
While Cloud Storage supports various data types, it's not optimal for structured tabular data (where BigQuery is preferred) or for complex metadata querying. Using specialized tools for each data type ensures better performance and scalability.
- C. Correct.
Preprocessing text and image data into numerical formats (e.g., embedding text or encoding pixels) is a critical step for machine learning models as they inherently operate on numerical data.
- D. Incorrect.
AutoML Table is specific to tabular data and cannot handle text or image data. Using this tool for all data types is not feasible or effective in this scenario.
- E. Correct.
Data versioning and metadata tagging are best practices to ensure reproducibility, facilitate debugging, and maintain consistency in machine learning pipelines.