Answer-first summary for fast verification
Answer: Use BigQuery‘s TRANSFORM clause to define preprocessing steps when creating your model. Then, at prediction time, use BigQuery‘s ML.EVALUATE clause without specifying any transformations on the raw input data.
The correct approach is to use BigQuery‘s TRANSFORM clause to specify all preprocessing during model creation. This ensures the preprocessing is automatically applied during both the prediction and evaluation phases of machine learning, preventing skew at prediction time. For more details, refer to [BigQuery ML documentation](https://cloud.google.com/bigquery-ml/docs/bigqueryml-transform).
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are tasked with preparing 6 TB of home sales data for machine learning using SQL and BigQuery ML in a large real estate firm. The goal is to use the resulting model for predictions against a raw dataset. To ensure predictions are not skewed, which workflow should you adopt?
A
Transform your raw input data using a saved query before requesting predictions and then use ML.EVALUATE, after defining preprocessing steps with BigQuery‘s TRANSFORM clause during model creation.
B
Define your preprocessing logic using a BigQuery view for model training data. At prediction time, use BigQuery‘s ML.EVALUATE clause without any transformations on the raw input data.
C
Preprocess all data using Dataflow. At prediction time, use BigQuery‘s ML.EVALUATE clause without any further transformations on the input data.
D
Use BigQuery‘s TRANSFORM clause to define preprocessing steps when creating your model. Then, at prediction time, use BigQuery‘s ML.EVALUATE clause without specifying any transformations on the raw input data.
No comments yet.