MENU
A data scientist has created a Python function compute_features that returns a Spark DataFrame with the following schema:
The resulting DataFrame is assigned to the features_df variable. The data scientist wants to create a Feature Store table using features_df.
Which of the following code blocks can they use to create and populate the Feature Store table using the Feature Store Client fs?
A)
B)
C)
features_df.write.mode("fs").path("new_table")
D)
Suggested Answer: D
Get Premium Databricks Machine Learning Professional Questions
as Interactive Web-Based Practice Test or PDF
Real Exam Format
Detailed Explanations
Instant Access
Get Your Practice Test
33 comments · newest first
LO
Loreta
10 months ago
Not sure about Option E, that "feature" mode seems weird.
LO
Lonny
11 months ago
Definitely leaning towards Option D, it seems right.
KR
Kristine
11 months ago
Wait, can you really use "fs" in Option C? Sounds off.
RE
Reta
11 months ago
I think Option B is the way to go!
RA
Raelene
11 months ago
Option A looks solid for creating the Feature Store table.
RE
Reynalda
12 months ago
I vaguely remember that we should use a specific method for the Feature Store, but I can't remember if it's in option D or E.
LE
Levi
12 months ago
Option C seems off to me; I don't think "fs" is a valid mode for writing to a Feature Store.
SY
Sylvia
12 months ago
I think options A and B look similar to the examples we practiced, but I can't recall the exact syntax for creating a Feature Store table.
HU
Huey
1 year ago
I remember we discussed how to use the Feature Store Client, but I'm not sure which option correctly uses it here.
MI
Mitsue
1 year ago
This seems straightforward. I think Option B is the correct answer, as it uses the Feature Store Client `fs` to create and write the table.
SH
Shantay
1 year ago
Okay, let's think this through step-by-step. The key is to use the Feature Store Client `fs` to create and populate the table. I'll need to compare the code blocks and see which one matches that requirement.
TH
Thurman
1 year ago
Hmm, I'm a bit unsure about the different options here. I'll need to carefully read through the code blocks and the question to make sure I understand the correct approach.
DI
Dick
1 year ago
This looks like a straightforward question about creating a Feature Store table from a Spark DataFrame. I think I can handle this one.
ST
Stephane
1 year ago
I'm feeling a bit confused by the different options. I'll need to review the Feature Store documentation to make sure I understand the correct syntax and approach for this task.
GU
Gussie
1 year ago
I'm pretty confident this is about using vMotion to migrate VMs without downtime, so I'll go with option A.
MY
Myong
2 years ago
Haha, Option E? 'features_df.write.mode(feature).path(new_table)'? Is that like, a special 'feature-flavored' write mode or something?
BE
Bette
2 years ago
Option A is the winner here. The `fs.write_table()` method is the way to go. Although, I have to say, the 'new_table' name is a bit uninspired. How about 'feature_extravaganza'?
KI
Kirk
2 years ago
Let's go with Option A and name the table 'feature_extravaganza' for some added flair.
RO
Rory
2 years ago
Yes, Option A with the 'feature_extravaganza' table name sounds like a great combination.
VA
Van
2 years ago
I think the 'feature_extravaganza' name suggestion is fun and creative!
VA
Valentine
2 years ago
I agree, Option A is the best choice for creating and populating the Feature Store table.
HY
Hyman
2 years ago
Option C? Really? 'features_df.write.mode(fs).path(new_table)'? That's not how you interact with the Feature Store, my dude.
AN
Annette
2 years ago
Hmm, I'd go with Option D. The `fs.create_feature_table()` method looks like it's specifically designed for this use case.
TY
Ty
2 years ago
I think Option D is the correct one as well. The `fs.create_feature_table()` method seems to be the way to go.
ED
Edna
2 years ago
I agree, Option D seems to be the most appropriate for creating and populating the Feature Store table.
SH
Shala
2 years ago
Option D looks good to me too. The `fs.create_feature_table()` method seems like the right choice.
AL
Alease
2 years ago
Hmm, that makes sense. Let's see what others think before making a final decision.
CA
Catrice
2 years ago
I disagree, I believe Option B is the right choice because it uses the Feature Store Client fs.
NY
Nydia
2 years ago
Option B seems the most straightforward way to create the Feature Store table. No need to overcomplicate things.
DE
Devora
2 years ago
Yeah, Option B seems like the most straightforward solution.
CH
Chan
2 years ago
I agree, Option B looks simple and effective.
CA
Carey
2 years ago
I think Option B is the best choice.
AL
Alease
2 years ago
I think Option A is the correct code block to create the Feature Store table.