Your retail company wants to predict customer churn using historical purchase data stored in BigQuery. The dataset includes customer demographics, purchase history, and a label indicating whether the customer churned or not. You want to build a machine learning model to identify customers at risk of churning. You need to create and train a logistic regression model for predicting customer churn, using the customer_data table with the churned column as the target label. Which BigQuery ML query should you use?

• A. CREATE OR REPLACE MODEL churn_prediction_model options(model_type='logistic_reg*) as select ' except(churned) FROM customer data;
• B. CREATE OR REPLACE MODEL churn_prediction_model OPTIONS (rr.odel_type=' logisric_reg *) AS select * except(churned), churned AS label FROM customer_data;
• C. CREATE OR REPLACE MODEL churn_prediction_model options (model type='logistic_reg') AS select churned as label FROM customer_data;
• D. CREATE OR REPLACE MODEL churn_prediction_model OPTIONS(model_uype='logisric_reg') AS SELECT * from cusromer_data;

Your organization uses scheduled queries to perform transformations on data stored in BigQuery. You discover that one of your scheduled queries has failed. You need to troubleshoot the issue as quickly as possible. What should you do?

• A. Request access from your admin to the BigQuery information_schema. Query the jobs view with the failed job ID, and analyze error details.
• B. Navigate to the Logs Explorer page in Cloud Logging. Use filters to find the failed job, and analyze the error details.
• C. Set up a log sink using the gcloud CLI to export BigQuery audit logs to BigQuery. Query those logs to identify the error associated with the failed job I
• D. Navigate to the Scheduled queries page in the Google Cloud console. Select the failed job, and analyze the error details.

You are designing a pipeline to process data files that arrive in Cloud Storage by 3:00 am each day. Data processing is performed in stages, where the output of one stage becomes the input of the next. Each stage takes a long time to run. Occasionally a stage fails, and you have to address the problem. You need to ensure that the final output is generated as quickly as possible. What should you do?

• A. Design the pipeline as a set of PTransforms in Dataflow. Restart the pipeline after correcting any stage output data errors.
• B. Design the workflow as a Cloud Workflow instance. Code the workflow to jump to a given stage based on an input parameter. Rerun the workflow after correcting any stage output data errors.
• C. Design the processing as a directed acyclic graph (DAG) in Cloud Composer. Clear the state of the failed task after correcting any stage output data errors.
• D. Design a Spark program that runs under Dataproc. Code the program to wait for user input when an error is detected. Rerun the last action after correcting any stage output data errors.

Your organization is conducting analysis on regional sales metrics. Data from each regional sales team is stored as separate tables in BigQuery and updated monthly. You need to create a solution that identifies the top three regions with the highest monthly sales for the next three months. You want the solution to automatically provide up-to-date results. What should you do?

• A. Create a BigQuery table that performs a cross join across all of the regional sales tables. Use the rank() window function to query the new table.
• B. Create a BigQuery materialized view that performs a cross join across all of the regional sales tables. Use the row_number() window function to query the new materialized view.
• C. Create a BigQuery materialized view that performs a union across all of the regional sales tables. Use the rank() window function to query the new materialized view.
• D. Create a BigQuery table that performs a union across all of the regional sales tables. Use the row_number() window function to query the new table.

You are storing data in Cloud Storage for a machine learning project. The data is frequently accessed during the model training phase, minimally accessed after 30 days, and unlikely to be accessed after 90 days. You need to choose the appropriate storage class for the different stages of the project to minimize cost. What should you do?

• A. Store the data in Standard storage during the model training phase. Transition the data to Durable Reduced Availability (DRA) storage 30 days after model deployment, and to Coldline storage 90 days after model deployment.
• B. Store the data in Nearline storage during the model training phase. Transition the data to Coldline storage 30 days after model deployment, and to Archive storage 90 days after model deployment.
• C. Store the data in Standard storage during the model training phase. Transition the data to Nearline storage 30 days after model deployment, and to Coldline storage 90 days after model deployment.
• D. Store the data in Nearline storage during the model training phase. Transition the data to Archive storage 30 days after model deployment, and to Coldline storage 90 days after model deployment.