Free Professional-Data-Engineer Exam Braindumps

- (Exam Topic 6)
You work for a manufacturing company that sources up to 750 different components, each from a different supplier. You’ve collected a labeled dataset that has on average 1000 examples for each unique component. Your team wants to implement an app to help warehouse workers recognize incoming components based on a photo of the component. You want to implement the first working version of this app (as Proof-Of-Concept) within a few working days. What should you do?

1. A. Use Cloud Vision AutoML with the existing dataset.
2. B. Use Cloud Vision AutoML, but reduce your dataset twice.
3. C. Use Cloud Vision API by providing custom labels as recognition hints.
4. D. Train your own image recognition model leveraging transfer learning techniques.

Correct Answer: A

- (Exam Topic 6)
A data scientist has created a BigQuery ML model and asks you to create an ML pipeline to serve predictions. You have a REST API application with the requirement to serve predictions for an individual user ID with latency under 100 milliseconds. You use the following query to generate predictions: SELECT predicted_label, user_id FROM ML.PREDICT (MODEL ‘dataset.model’, table user_features). How should you create the ML pipeline?

1. A. Add a WHERE clause to the query, and grant the BigQuery Data Viewer role to the application service account.
2. B. Create an Authorized View with the provided quer
3. C. Share the dataset that contains the view with the application service account.
4. D. Create a Cloud Dataflow pipeline using BigQueryIO to read results from the quer
5. E. Grant the Dataflow Worker role to the application service account.
6. F. Create a Cloud Dataflow pipeline using BigQueryIO to read predictions for all users from the query.Write the results to Cloud Bigtable using BigtableI
7. G. Grant the Bigtable Reader role to the application service account so that the application can read predictions for individual users from Cloud Bigtable.

Correct Answer: D

- (Exam Topic 5)
Which of the following is not true about Dataflow pipelines?

1. A. Pipelines are a set of operations
2. B. Pipelines represent a data processing job
3. C. Pipelines represent a directed graph of steps
4. D. Pipelines can share data between instances

Correct Answer: D
The data and transforms in a pipeline are unique to, and owned by, that pipeline. While your program can create multiple pipelines, pipelines cannot share data or transforms
Reference: https://cloud.google.com/dataflow/model/pipelines

- (Exam Topic 5)
Which of the following is NOT true about Dataflow pipelines?

1. A. Dataflow pipelines are tied to Dataflow, and cannot be run on any other runner
2. B. Dataflow pipelines can consume data from other Google Cloud services
3. C. Dataflow pipelines can be programmed in Java
4. D. Dataflow pipelines use a unified programming model, so can work both with streaming and batch data sources

Correct Answer: A
Dataflow pipelines can also run on alternate runtimes like Spark and Flink, as they are built using the Apache Beam SDKs
Reference: https://cloud.google.com/dataflow/

- (Exam Topic 5)
Does Dataflow process batch data pipelines or streaming data pipelines?

1. A. Only Batch Data Pipelines
2. B. Both Batch and Streaming Data Pipelines
3. C. Only Streaming Data Pipelines
4. D. None of the above

Correct Answer: B
Dataflow is a unified processing model, and can execute both streaming and batch data pipelines Reference: https://cloud.google.com/dataflow/