🔥 40% Off Crucial Exams Memberships — Deal ends today!

48 minutes, 59 seconds remaining!
Crucial Exams

GCP Professional Data Engineer Practice Question

Your marketing team's event table has NULL values in the revenue (FLOAT64) and channel (STRING) columns. When building a regression model with BigQuery ML, you want to automatically replace missing revenue with the column's median and missing channel with the most frequent non-null value, without creating an intermediate table. Which preprocessing function should you reference in the TRANSFORM clause to satisfy both requirements?

  • Use ML.MAX_ABS_SCALER() in the TRANSFORM clause to rescale features; it automatically replaces NULLs with zero.

  • Use ML.NORMALIZER() in the TRANSFORM clause; its unit-norm scaling also removes NULLs from the data.

  • Use ML.IMPUTER() and set numeric_strategy='MEDIAN' and categorical_strategy='MOST_FREQUENT' in the TRANSFORM clause.

  • Use ML.ONE_HOT_ENCODER() with a null_value parameter in the TRANSFORM clause to encode and impute both columns.

GCP Professional Data Engineer
Preparing and using data for analysis
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot