Google Professional Data Engineer
Get started today
Ultimate access to all questions.
Comments
Loading comments...
Ultimate access to all questions.
You are employed by a major real estate company, and are tasked with handling 6 TB of home sales data in preparation for machine learning. The initial step involves transforming this data using SQL and subsequently utilizing BigQuery ML to develop a machine learning model. Your predictive model will need to operate on a raw dataset that has not undergone any transformations. What workflow configuration should you adopt to ensure that there is no skew during the prediction phase?
A
When creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps. At prediction time, use BigQuery's ML.EVALUATE clause without specifying any transformations on the raw input data.
B
When creating your model, use BigQuery's TRANSFORM clause to define preprocessing steps. Before requesting predictions, use a saved query to transform your raw input data, and then use ML.EVALUATE.
C
Use a BigQuery view to define your preprocessing logic. When creating your model, use the view as your model training data. At prediction time, use BigQuery's ML.EVALUATE clause without specifying any transformations on the raw input data.
D
Preprocess all data using Dataflow. At prediction time, use BigQuery's ML.EVALUATE clause without specifying any further transformations on the input data.