PDE Preparing and Using Data for Analysis Practice Test 2 — 15 Questions

Question 1

A data engineer needs to create a BigQuery ML model for predicting customer churn using a dataset with 10 million rows and 50 features. The dataset is highly imbalanced (5% churn). Which approach should the engineer use to handle class imbalance during model training?

Accepted Answer

Use the CREATE MODEL statement with CLASS_WEIGHTS = {'0': 0.2, '1': 0.8}. BigQuery ML supports class weights for imbalanced datasets via the CLASS_WEIGHTS option in CREATE MODEL. This assigns higher weight to the minority class without generating synthetic data. SMOTE is not available in BigQuery ML. Undersampling the majority class would lose data, and oversampling with duplication could introduce bias.

Answer

Undersample the majority class before training

Answer

Use SMOTE via TRANSFORM clause in BigQuery ML

Answer

Oversample the minority class by duplicating rows

Question 2

A financial analytics team uses Looker to explore BigQuery data. They need to allow business users to filter by a custom date range that is not tied to an existing dimension. The date range must be user-input at query time. What is the best approach in Looker?

Accepted Answer

Create a parameter in LookML using Liquid templating. Looker uses Liquid templating in LookML to create parameters that render as filter controls at runtime. Users can input values that are then injected into the SQL. Creating a dimension with a yesno filter requires predefined values. The filter parameter on a dimension only allows selecting from existing values, not arbitrary input.

Answer

Create an explore with a custom filter field in the Looker UI

Answer

Use a filter parameter directly on the date dimension

Answer

Add a dimension with a yesno filter that toggles the date range

Question 3

A data scientist wants to train a custom TensorFlow model on Vertex AI using a managed Jupyter notebook. Which Vertex AI service should they use to set up a notebook environment with pre-installed deep learning frameworks?

Accepted Answer

Vertex AI Workbench. Vertex AI Workbench provides managed Jupyter notebooks with pre-installed deep learning frameworks (TensorFlow, PyTorch, etc.) and easy scaling options. Notebooks on Compute Engine would require manual setup. AI Platform Training is for training jobs, not interactive notebooks. Vertex AI Pipelines is for orchestrating ML workflows.

Answer

Compute Engine with Deep Learning VM

Answer

Vertex AI Training via custom job

Answer

Vertex AI Pipelines

Question 4

A retail company uses BigQuery to store sales data and wants to forecast weekly demand for the next 8 weeks using historical data from the past 2 years. They need to account for seasonality and holidays. Which BigQuery ML model type and configuration is most appropriate?

Accepted Answer

ARIMA_PLUS with holiday_region parameter. BigQuery ML's ARIMA_PLUS model is designed for time-series forecasting, automatically detecting seasonality and handling holiday effects via the holiday_region parameter. Linear regression would require manual feature engineering for time components. Time-series DECOMPOSE is not a model type. Boosted trees are not natively time-series aware without feature engineering.

Answer

Boosted tree classifier

Answer

Linear regression with engineered time features

Answer

Time-series DECOMPOSE model

Question 5

A data engineer needs to query data from BigQuery and another cloud provider's storage (AWS S3) using a single SQL query. The data must not be moved or copied to GCP. Which Google Cloud service should they use?

Accepted Answer

BigQuery Omni. BigQuery Omni allows querying data across multiple clouds (AWS S3, Azure Blob Storage) using BigQuery's interface without moving data. BigQuery Omni runs compute in the other cloud's region. BigQuery Transfer Service moves data into BigQuery. Dataplex is for data management, not cross-cloud queries. Cloud Storage Transfer Service is for moving data between clouds.

Answer

Cloud Storage Transfer Service

Answer

Dataplex

Answer

BigQuery Data Transfer Service

Question 6

What is the primary purpose of Vertex AI Feature Store?

Accepted Answer

To store and serve features for machine learning models at scale. Vertex AI Feature Store is a managed service for storing, serving, and sharing ML features. It supports both online (low-latency serving for prediction) and offline (batch serving for training) serving. It is not for model training, data transformation, or experiment tracking.

Answer

To manage and track ML experiments

Answer

To train machine learning models using AutoML

Answer

To transform raw data into features using SQL

Question 7

A company uses Looker Studio to create dashboards from BigQuery data. They notice that dashboard queries take several seconds to load. They want to improve performance without changing the underlying data or creating materialized views. Which option should they use?

Accepted Answer

Enable BigQuery BI Engine for the project. BigQuery BI Engine is an in-memory analysis service that accelerates queries from Looker Studio (and other BI tools) by caching data in memory, significantly reducing latency. Replicating data to Cloud SQL would add complexity and may not handle the volume. Using Looker instead of Looker Studio doesn't inherently speed up queries. Increasing BigQuery slots would help but is more expensive and not as targeted for BI tools.

Answer

Increase the number of BigQuery slots

Answer

Switch to Looker instead of Looker Studio

Answer

Replicate the data to Cloud SQL for faster queries

Question 8

A data engineer is building a production ML pipeline on Vertex AI. The pipeline must preprocess features (e.g., scaling, encoding) and then train a model. The preprocessing logic must be reusable for serving predictions. Which Vertex AI component should they use?

Accepted Answer

Vertex AI Feature Transform. Vertex AI Feature Transform is a managed service that allows you to define transformations using TFX Transform or BigQuery SQL, which are then applied consistently during training and serving. Vertex AI Pipelines can orchestrate but does not itself provide reusable transformations. Dataflow would require custom code. Vertex AI Feature Store serves pre-computed features, not transformations.

Answer

Dataflow with Apache Beam

Answer

Vertex AI Feature Store

Answer

Vertex AI Pipelines

Question 9

To enable data lineage tracking in BigQuery, which feature should be activated?

Accepted Answer

BigQuery Lineage API. BigQuery Lineage API allows tracking data lineage for tables and views. Dataplex Lineage also provides lineage but requires Dataplex. BigQuery Audit Logs capture metadata changes but not lineage specifically. Data Catalog is for metadata management but not lineage tracking.

Answer

BigQuery Audit Logs

Answer

Data Catalog

Answer

Dataplex Lineage

Question 10

A company needs to predict whether a product image contains a specific defect. They have 10,000 labeled images and want to build a model quickly without writing custom code or training from scratch. Which GCP service should they use?

Accepted Answer

AutoML Vision. AutoML Vision is designed for custom image classification tasks with minimal ML expertise. It uses transfer learning and supports up to millions of images. AutoML Tables handles tabular data, not images. Vertex AI custom training would require more effort. AutoML NLP is for text data.

Answer

AutoML Tables

Answer

Vertex AI custom training

Answer

AutoML Natural Language

Question 11

A data engineer needs to split time-series data for training a forecasting model. The data is sorted by timestamp. The engineer wants to avoid leakage where future data influences training. Which data splitting approach should they use?

Accepted Answer

Use a time-series aware split: first 80% of data by timestamp for training, last 20% for testing. For time-series, the only safe split is to use an earlier contiguous block for training and a later block for testing, preserving temporal order. Random splits would cause leakage. K-fold cross-validation on time-series requires special techniques like forward chaining, not standard k-fold. Stratified split is for classification.

Answer

Use k-fold cross-validation with random assignment

Answer

Use stratified splitting on the target variable

Answer

Perform a random 80/20 split on the entire dataset

Question 12

A data team uses Looker Studio to create a report that combines data from two different BigQuery tables: one with sales transactions and another with customer demographics. They need to join these tables in the report without writing SQL. Which feature should they use?

Accepted Answer

Data blending. Looker Studio's data blending feature allows combining data from multiple sources (including BigQuery tables) using a common key, without writing SQL. It provides a graphical interface to define joins. Creating a custom query requires SQL. Looker Studio reports support multiple charts, but blending is the specific feature for joining data. Calculated fields transform data within a single source.

Answer

Creating a report with multiple charts

Answer

Custom query in BigQuery connector

Answer

Calculated fields

Question 13

A data engineer needs to implement data quality rules and governance policies across multiple data lakes in GCP. They want to automatically discover and catalog data assets, and enforce row-level security. Which two services should they use? (Select TWO)

Accepted Answer

Dataplex. Dataplex provides unified data management including data discovery, cataloging, data quality rules, and policy enforcement (row-level security via BigQuery). Data Catalog is for metadata management and discovery, but Dataplex Universal Catalog includes Data Catalog capabilities. Dataflow is for processing, not governance. Cloud DLP is for data loss prevention, not row-level security. Security Command Center is for cloud security posture.

Answer

Security Command Center

Answer

Cloud DLP

Answer

Dataflow

Answer

Data Catalog

Question 14

A data analyst wants to compute the rank of sales per region and also the difference in sales between consecutive months for each region. Which BigQuery analytic functions should they use? (Select TWO)

Accepted Answer

RANK(). RANK() computes the rank of rows within a partition. LAG() accesses data from a previous row in the same result set, which can be used to compute differences. ROW_NUMBER() assigns unique sequential integers, not rank. NTILE() distributes rows into buckets. LEAD() accesses next row, not previous.

Answer

ROW_NUMBER()

Answer

LEAD()

Answer

NTILE()

Question 15

A company wants to use BigQuery ML to build a recommendation system for movies. The data includes user IDs, movie IDs, and ratings. Which BigQuery ML model types are suitable for this? (Select TWO)

Accepted Answer

Boosted tree classifier. Matrix factorization (via implicit or explicit feedback) is specifically designed for recommendation systems. Boosted tree classifiers can also be used for predicting ratings as a classification problem. AutoML Tables is not a model type in BigQuery ML. ARIMA_PLUS is for time-series. k-means is for clustering, not recommendations directly.

Answer

ARIMA_PLUS

Answer

k-means

Answer

AutoML Tables