You are working on a linear regression model on BigQuery ML to predict a customer's likelihood of purchasing your company's products. Your model uses a city name variable as a key predictive…

Question

Options

• ACreate a new view with BigQuery that does not include a column with city information.
• BUse SQL in BigQuery to transform the state column using a one-hot encoding method, and make each city a column with binary values.
• CUse TensorFlow to create a categorical variable with a vocabulary list.
• DUse Cloud Data Fusion to assign each city to a region that is labeled as 1, 2, 3, 4, or 5, and then use that number to represent the city in the model.

• A
  2% (1)
• B
  4% (2)
• C
  13% (6)
• D
  80% (36)

Explanation

Option D satisfies both constraints - least coding and preserving the predictive variable. Cloud Data Fusion is a low-code, GUI-driven data integration tool, so mapping cities to regional numeric labels (1–5) requires no custom code while converting the categorical city field into a numeric column usable by a linear regression model.

Why the distractors are wrong:

• A eliminates the city column entirely, directly violating the requirement to maintain the predictive variable - a city described as a "key predictive component" should not be dropped.
• B is technically valid ML practice (one-hot encoding is standard for categorical variables), but it requires writing SQL manually, which means more coding than a point-and-click tool like Data Fusion.
• C introduces TensorFlow - a heavy framework requiring substantial coding - which directly contradicts the "least amount of coding" constraint.

Memory tip: Match the tool to the constraint. When the question says least coding, look for the managed/GUI tool (Cloud Data Fusion, Dataprep, etc.). When it says remove the variable, that's always wrong if the variable is described as predictive. "Low code = Data Fusion" is a reliable heuristic across GCP exam questions.

No community discussion yet for this question.