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

Google Exam Professional-Data-Engineer Topic 4 Question 76 Discussion

Actual exam question for Google's Google Cloud Certified Professional Data Engineer exam
Question #: 76
Topic #: 4
[All Google Cloud Certified Professional Data Engineer Questions]

You are building a data pipeline on Google Cloud. You need to prepare data using a casual method for a

machine-learning process. You want to support a logistic regression model. You also need to monitor and

adjust for null values, which must remain real-valued and cannot be removed. What should you do?

Show Suggested Answer Hide Answer
Suggested Answer: C

Contribute your Thoughts:

Ozell
10 days ago
I'm not sure about using a custom script, though. It could be more error-prone and harder to maintain than using a managed service like Cloud Dataprep or Cloud Dataflow. Maybe we could explore those options further.
upvoted 0 times
...
Kristeen
11 days ago
Exactly! Gotta do it right, even if it means a little more effort. I'd rather spend the time getting the data prepped properly than have to troubleshoot issues with the model later on. *nods sagely*
upvoted 0 times
...
Walker
12 days ago
Ah, I see what you mean. Converting nulls to 0 could definitely cause issues if 0 is a valid value. Hmm, maybe we should go with the custom script after all, even if it's a bit more work. Can't risk messing up the model, you know?
upvoted 0 times
...
Brigette
13 days ago
Haha, yeah, the old 'measure twice, cut once' approach. Wise words, my friends. Alright, let's go with option D and figure out a solid custom script to handle those nulls. Can't be that hard, right? *winks*
upvoted 0 times
...

Save Cancel