PDE practice questions 31–40

1. Question 31 · 340 in bank

   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?

   • AUse Cloud Vision AutoML with the existing dataset.
   • BUse Cloud Vision AutoML, but reduce your dataset twice.
   • CUse Cloud Vision API by providing custom labels as recognition hints.
   • DTrain your own image recognition model leveraging transfer learning techniques.

   Show answer

   Answer: A

   Explanation

   First I think in Vision API, but that is a pre-trained AI, will not recognize my labels, so because you have 1000 samples per item, AUTO ML is perfect. B cannot be because have not sensed to reduce your dataset if you have the recommended number of info. https://cloud.google.com/vision/automl/docs/beginners-guide#include_enough_labeled_examples_in_each_category The bare minimum required by AutoML Vision training is 100 image examples per category/label. The likelihood of successfully recognizing a label goes up with the number of high quality examples for each; in general, the more labeled data you can bring to the training process, the better your model will be. Target at least 1000 examples per label.

   Source: Adapted from community discussion — odacir

   References

   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation

   Next question

2. Question 32 · 340 in bank

   You are working on a niche product in the image recognition domain. Your team has developed a model that is dominated by custom C++ TensorFlow ops your team has implemented. These ops are used inside your main training loop and are performing bulky matrix multiplications. It currently takes up to several days to train a model. You want to decrease this time significantly and keep the cost low by using an accelerator on Google Cloud. What should you do?

   • AUse Cloud TPUs without any additional adjustment to your code.
   • BUse Cloud TPUs after implementing GPU kernel support for your customs ops.
   • CUse Cloud GPUs after implementing GPU kernel support for your customs ops.
   • DStay on CPUs, and increase the size of the cluster you're training your model on.

   Show answer

   Answer: D

   Explanation

   D: Cloud TPUs are not suited to the following workloads: [...] Neural network workloads that contain custom TensorFlow operations written in C++. Specifically, custom operations in the body of the main training loop are not suitable for TPUs.

   Source: Adapted from community discussion — aiguy

   References

   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation

   Next question

3. Question 33 · 340 in bank

   You work on a regression problem in a natural language processing domain, and you have 100M labeled examples in your dataset. You have randomly shuffled your data and split your dataset into train and test samples (in a 90/10 ratio). After you trained the neural network and evaluated your model on a test set, you discover that the root-mean-squared error (RMSE) of your model is twice as high on the train set as on the test set. How should you improve the performance of your model?

   • AIncrease the share of the test sample in the train-test split.
   • BTry to collect more data and increase the size of your dataset.
   • CTry out regularization techniques (e.g., dropout of batch normalization) to avoid overfitting.
   • DIncrease the complexity of your model by, e.g., introducing an additional layer or increase sizing the size of vocabularies or n-grams used.

   Show answer

   Answer: D

   Explanation

   This is a case of underfitting - not overfitting (for over fitting the model will have extremely low training error but a high testing error) - so we need to make the model more complex - answer is D

   Source: Adapted from community discussion — Callumr

   References

   • Google developer documentation
   • Google developer documentation
   • Google developer documentation

   Next question

4. Question 34 · 340 in bank

   You use BigQuery as your centralized analytics platform. New data is loaded every day, and an ETL pipeline modifies the original data and prepares it for the final users. This ETL pipeline is regularly modified and can generate errors, but sometimes the errors are detected only after 2 weeks. You need to provide a method to recover from these errors, and your backups should be optimized for storage costs. How should you organize your data in BigQuery and store your backups?

   • AOrganize your data in a single table, export, and compress and store the BigQuery data in Cloud Storage.
   • BOrganize your data in separate tables for each month, and export, compress, and store the data in Cloud Storage.
   • COrganize your data in separate tables for each month, and duplicate your data on a separate dataset in BigQuery.
   • DOrganize your data in separate tables for each month, and use snapshot decorators to restore the table to a time prior to the corruption.

   Show answer

   Answer: D

   Explanation

   From BigQuery documentation - Benefits of using table snapshots include the following: - Keep a record for longer than seven days. With BigQuery time travel, you can only access a table's data from seven days ago or more recently. With table snapshots, you can preserve a table's data from a specified point in time for as long as you want. - Minimize storage cost. BigQuery only stores bytes that are different between a snapshot and its base table, so a table snapshot typically uses less storage than a full copy of the table. So storing data in GCS will make copies of data for each table. Table snapshots are more optimal in this scenario.

   Source: Adapted from community discussion — Lanro

   References

   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation

   Next question

5. Question 35 · 340 in bank

   You want to process payment transactions in a point-of-sale application that will run on Google Cloud Platform. Your user base could grow exponentially, but you do not want to manage infrastructure scaling. Which Google database service should you use?

   • ACloud SQL
   • BBigQuery
   • CCloud Bigtable
   • DCloud Datastore

   Show answer

   Answer: D

   Explanation

   Initially, thinking D is the best answer but when question is re-re-read, A seems to be correct answer for following reasons 1. Is payment TRANSACTION -- DB should able to perform full blown transaction (updating inventory, sales info etc, though not specified) , not just ATOMIC which DataStore provides 2. Its point-of-sale application, not ONLINE STORE where HIGH number of concurrent users ordering stuff. 3. User Base could grow exponentially - again more users does mot mean concurrent users and more processing power. Its only about storage. 4. Do not want to Manage infrastructure scaling. - Cloud SQL can scale in terms of storage. 5. CloudStore is poor selection for OLTP application - Each property is index - so higher latency Not sure, during exam 2 min is enough to think on various point.. I may be wrong or wrong path ... lets brainstrom..

   Source: Adapted from community discussion — DeepakKhattar

   References

   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation

   Next question

6. Question 36 · 340 in bank

   The marketing team at your organization provides regular updates of a segment of your customer dataset. The marketing team has given you a CSV with 1 million records that must be updated in BigQuery. When you use the UPDATE statement in BigQuery, you receive a quotaExceeded error. What should you do?

   • AReduce the number of records updated each day to stay within the BigQuery UPDATE DML statement limit.
   • BIncrease the BigQuery UPDATE DML statement limit in the Quota management section of the Google Cloud Platform Console.
   • CSplit the source CSV file into smaller CSV files in Cloud Storage to reduce the number of BigQuery UPDATE DML statements per BigQuery job.
   • DImport the new records from the CSV file into a new BigQuery table. Create a BigQuery job that merges the new records with the existing records and writes the results to a new BigQuery table.

   Show answer

   Answer: D

   Explanation

   D: BigQuery is primarly designed and suit to append-only technology with some limited DML statements. It's not a relational database where you constantly update your user records if they edit their profile. Instead you need to arhitect your code so each edit is a new row in Bigquery, and you always query the latest row. The DML statement limitation is low, because it targets different scenarios and not yours, aka live update on rows. You could ingest your data into a separate table, and issue 1 update statement per day. https://stackoverflow.com/questions/45183082/can-we-increase-update-quota-in-bigquery https://cloud.google.com/blog/products/gcp/performing-large-scale-mutations-in-bigquery

   Source: Adapted from community discussion — MaxNRG

   References

   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation

   Next question

7. Question 37 · 340 in bank

   Select 2

   As your organization expands its usage of GCP, many teams have started to create their own projects. Projects are further multiplied to accommodate different stages of deployments and target audiences. Each project requires unique access control configurations. The central IT team needs to have access to all projects. Furthermore, data from Cloud Storage buckets and BigQuery datasets must be shared for use in other projects in an ad hoc way. You want to simplify access control management by minimizing the number of policies. Which two steps should you take? (Choose two.)

   • AUse Cloud Deployment Manager to automate access provision.
   • BIntroduce resource hierarchy to leverage access control policy inheritance.
   • CCreate distinct groups for various teams, and specify groups in Cloud IAM policies.
   • DOnly use service accounts when sharing data for Cloud Storage buckets and BigQuery datasets.
   • EFor each Cloud Storage bucket or BigQuery dataset, decide which projects need access. Find all the active members who have access to these projects, and create a Cloud IAM policy to grant access to all these users.

   Show answer

   Answer: BC

   Explanation

   Answer: B, C Description: Google suggests that we should provide access by following google hierarchy and groups for users with similar roles

   Source: Adapted from community discussion — [Removed]

   References

   • Google Cloud documentation
   • Google Cloud documentation

   Next question

8. Question 38 · 340 in bank

   Your United States-based company has created an application for assessing and responding to user actions. The primary table's data volume grows by 250,000 records per second. Many third parties use your application's APIs to build the functionality into their own frontend applications. Your application's APIs should comply with the following requirements: ✑ Single global endpoint ✑ ANSI SQL support ✑ Consistent access to the most up-to-date data What should you do?

   • AImplement BigQuery with no region selected for storage or processing.
   • BImplement Cloud Spanner with the leader in North America and read-only replicas in Asia and Europe.
   • CImplement Cloud SQL for PostgreSQL with the master in North America and read replicas in Asia and Europe.
   • DImplement Bigtable with the primary cluster in North America and secondary clusters in Asia and Europe.

   Show answer

   Answer: B

   Explanation

   A - BigQuery with NO Region ? (Looks wrong) B - Spanner (SQL support and Scalable and have replicas ) - Looks correct C - SQL (can't store so many records) (wrong) D - Bigtable - NO SQL (wrong) Vote for B

   Source: Adapted from community discussion — sumanshu

   References

   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation
   • Google Cloud documentation

   Next question

9. Question 39 · 340 in bank

   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?

   • AAdd a WHERE clause to the query, and grant the BigQuery Data Viewer role to the application service account.
   • BCreate an Authorized View with the provided query. Share the dataset that contains the view with the application service account.
   • CCreate a Dataflow pipeline using BigQueryIO to read results from the query. Grant the Dataflow Worker role to the application service account.
   • DCreate a Dataflow pipeline using BigQueryIO to read predictions for all users from the query. Write the results to Bigtable using BigtableIO. Grant the Bigtable Reader role to the application service account so that the application can read predictions for individual users from Bigtable.

   Show answer

   Answer: D

   Explanation

   The key requirements are serving predictions for individual user IDs with low (sub-100ms) latency. Option D meets this by batch predicting for all users in BigQuery ML, writing predictions to Bigtable for fast reads, and allowing the application access to query Bigtable directly for low latency reads. Since the application needs to serve low-latency predictions for individual user IDs, using Dataflow to batch predict for all users and write to Bigtable allows low-latency reads. Granting the Bigtable Reader role allows the application to retrieve predictions for a specific user ID from Bigtable.

   Source: Adapted from community discussion — MaxNRG

   References

   • Google Cloud documentation

   Next question

10. Question 40 · 340 in bank

    You are building an application to share financial market data with consumers, who will receive data feeds. Data is collected from the markets in real time. Consumers will receive the data in the following ways: ✑ Real-time event stream ✑ ANSI SQL access to real-time stream and historical data ✑ Batch historical exports Which solution should you use?

    • ACloud Dataflow, Cloud SQL, Cloud Spanner
    • BCloud Pub/Sub, Cloud Storage, BigQuery
    • CCloud Dataproc, Cloud Dataflow, BigQuery
    • DCloud Pub/Sub, Cloud Dataproc, Cloud SQL

    Show answer

    Answer: B

    Explanation

    D, not ideal but only option that work. You need pubsub, then a processing layer (dataflow or dataproc), then storage (some sql database).

    Source: Adapted from community discussion — itche_scratche

    References

    • Google Cloud documentation
    • Google Cloud documentation
    • Google Cloud documentation
    • Google Cloud documentation

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

PDE practice, question 31. 340 questions available.