nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #176

You want to train an AutoML model to predict house prices by using a small public dataset stored in BigQuery. You need to prepare the data and want to use the simplest, most efficient approach. What…

The correct answer is A. Write a query that preprocesses the data by using BigQuery and creates a new table. Create a. To prepare a small public dataset in BigQuery for training an AutoML model to predict house prices, the simplest and most efficient approach is to preprocess the data using BigQuery SQL and create a new table for AutoML.

Submitted by rachelw· Apr 18, 2026Data processing and feature engineering

Question

You want to train an AutoML model to predict house prices by using a small public dataset stored in BigQuery. You need to prepare the data and want to use the simplest, most efficient approach. What should you do?

Options

  • AWrite a query that preprocesses the data by using BigQuery and creates a new table. Create a
  • BUse Dataflow to preprocess the data. Write the output in TFRecord format to a Cloud Storage
  • CWrite a query that preprocesses the data by using BigQuery. Export the query results as CSV
  • DUse a Vertex AI Workbench notebook instance to preprocess the data by using the pandas

How the community answered

(43 responses)
  • A
    86% (37)
  • B
    7% (3)
  • C
    2% (1)
  • D
    5% (2)

Why each option

To prepare a small public dataset in BigQuery for training an AutoML model to predict house prices, the simplest and most efficient approach is to preprocess the data using BigQuery SQL and create a new table for AutoML.

AWrite a query that preprocesses the data by using BigQuery and creates a new table. Create aCorrect

Vertex AI AutoML Tables can directly ingest data from BigQuery tables, making preprocessing within BigQuery using standard SQL the simplest and most efficient approach for a dataset already stored there. Creating a new, preprocessed table ensures a clean data source ready for direct consumption by AutoML without extra data movement.

BUse Dataflow to preprocess the data. Write the output in TFRecord format to a Cloud Storage

Using Dataflow for preprocessing is overkill for a 'small' dataset and introduces more complexity and development effort compared to BigQuery SQL, which contradicts the 'simplest, most efficient' requirement.

CWrite a query that preprocesses the data by using BigQuery. Export the query results as CSV

Exporting query results as CSV to Cloud Storage introduces unnecessary data movement and potential latency, as AutoML Tables can directly read from BigQuery.

DUse a Vertex AI Workbench notebook instance to preprocess the data by using the pandas

Using a Vertex AI Workbench notebook with pandas for preprocessing requires moving data out of BigQuery, which is less efficient and scalable than processing directly within BigQuery, especially if the dataset were to grow.

Concept tested: Vertex AI AutoML data preparation from BigQuery

Source: https://cloud.google.com/vertex-ai/docs/tabular/prepare-data

Topics

#BigQuery#Data Preprocessing#AutoML Data Preparation#GCP Data Services

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice