MENU
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?
Suggested Answer: C
Get Premium Professional Data Engineer Questions
as Interactive Web-Based Practice Test or PDF
Real Exam Format
Detailed Explanations
Instant Access
Get Your Practice Test
12 comments · newest first
FR
Frederica
11 months ago
Option C is interesting, but I prefer Dataflow for handling nulls.
JA
James
11 months ago
I agree with Ludivina, option B is definitely the way to go!
NA
Nan
12 months ago
Wait, can you really convert nulls to 'none' in a logistic regression model? Seems off.
LU
Ludivina
12 months ago
I think option B is the best choice! Converting nulls to 0 is a common practice.
FL
Fletcher
12 months ago
Option A sounds good, but converting nulls to 'none' might not work for real-valued data.
EM
Emmett
1 year ago
I vaguely remember that we shouldn't convert nulls to 'none' or 0 for logistic regression. I think we should keep them as real values, but I can't remember the exact method.
JE
Jeffrey
1 year ago
I feel like using Cloud Dataflow might be more appropriate for this scenario, but I'm uncertain about whether a custom script is necessary for handling nulls.
ME
Melda
1 year ago
I think we practiced a similar question where we used Cloud Dataprep to handle nulls, but I can't recall if converting them to 0 was the best option.
TA
Tanja
1 year ago
I remember we discussed how null values should be handled carefully, but I'm not sure if converting them to 'none' is the right approach for a logistic regression model.
GL
Glennis
1 year ago
Hmm, I'm not sure about this one. Bridging the vNIC sounds like the right approach, but I want to double-check that in my notes.
BE
Berry
1 year ago
Okay, let me see here. I believe the key is to run an automatic schedule request to generate the counts first, before entering any unscheduled entries.
GR
Graham
1 year ago
I think the key here is understanding the typical challenges faced by this specific customer group. Option A sounds like a safe bet, but I want to make sure I'm not missing something more specific to their situation. I'll read through the options again carefully.