Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Google Professional Machine Learning Engineer Exam - Topic 11 Question 38 Discussion

You want to rebuild your ML pipeline for structured data on Google Cloud. You are using PySpark to conduct data transformations at scale, but your pipelines are taking over 12 hours to run. To speed up development and pipeline run time, you want to use a serverless tool and SQL syntax. You have already moved your raw data into Cloud Storage. How should you build the pipeline on Google Cloud while meeting the speed and processing requirements?
B) Convert your PySpark into SparkSQL queries to transform the data and then run your pipeline on Dataproc to write the data into BigQuery.
A) Use Data Fusion's GUI to build the transformation pipelines, and then write the data into BigQuery
C) Ingest your data into Cloud SQL convert your PySpark commands into SQL queries to transform the data, and then use federated queries from BigQuery for machine learning
D) Ingest your data into BigQuery using BigQuery Load, convert your PySpark commands into BigQuery SQL queries to transform the data, and then write the transformations to a new table

Google Professional Machine Learning Engineer Exam - Topic 11 Question 38 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam
Question #: 38
Topic #: 11
[All Professional Machine Learning Engineer Questions]

You want to rebuild your ML pipeline for structured data on Google Cloud. You are using PySpark to conduct data transformations at scale, but your pipelines are taking over 12 hours to run. To speed up development and pipeline run time, you want to use a serverless tool and SQL syntax. You have already moved your raw data into Cloud Storage. How should you build the pipeline on Google Cloud while meeting the speed and processing requirements?

Show Suggested Answer Hide Answer
Suggested Answer: B

by Jennifer at May 04, 2022, 10:32 AM

Limited Time Offer

25%

Off

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Precious
10 months ago
Not sure about D, converting everything to SQL might be a hassle.
upvoted 0 times
...
Reuben
10 months ago
I think C is a bit convoluted, just stick with BigQuery (D).
upvoted 0 times
...
Elly
11 months ago
I’m surprised no one mentioned using Dataproc (B) for scalability!
upvoted 0 times
...
Denny
11 months ago
I disagree, Data Fusion (A) could be easier for visualizing the pipeline.
upvoted 0 times
...
Krystal
11 months ago
Option D seems the fastest, BigQuery is super efficient!
upvoted 0 times
...
Asha
11 months ago
I practiced a similar question about using BigQuery for transformations, and it seems like option D could be the most efficient.
upvoted 0 times
...
Maryann
11 months ago
I think converting PySpark to SparkSQL might help, but running it on Dataproc could still be slow.
upvoted 0 times
...
Mitsue
11 months ago
I remember we discussed using Data Fusion for building pipelines, but I'm not sure if it's the best choice for speed.
upvoted 0 times
...
Gussie
11 months ago
I'm a bit confused about the federated queries in option C; I don't recall how they work with Cloud SQL and BigQuery together.
upvoted 0 times
...
Kallie
11 months ago
Okay, let's see here. The users are complaining about not having the correct new group memberships, so I'm thinking we need to do something to fix that. Maybe reordering the directories or disabling one of them could help?
upvoted 0 times
...
Kara
11 months ago
This is a tricky one. I'll need to re-read the prompt a few times and really think through each option to make sure I select the correct answer.
upvoted 0 times
...
Selma
11 months ago
I'm a little confused on the differences between predictive and prescriptive analytics. I'll have to review those concepts before answering this.
upvoted 0 times
...
Derick
11 months ago
I'm confident I can solve this. The average inventory is the midpoint between the maximum and minimum inventory levels, which is the EOQ plus half the safety stock.
upvoted 0 times
...
Dominga
11 months ago
The MAX and MIN functions work on character data types, so that's an interesting one. I'll make sure to remember that.
upvoted 0 times
...
Mammie
11 months ago
The term "westbound" rings a bell, but I struggle to remember how it aligns with the context of this question.
upvoted 0 times
...
Frederica
11 months ago
Vishing attacks target the user instead of the network itself, so it doesn't directly compromise confidentiality. I'm leaning towards packet sniffing for this one, but I'm still a bit uncertain.
upvoted 0 times
...

Save Cancel