How does warehouse sizing affect model inference performance in Snowflake?

Larger warehouses provide more compute resources, which can speed up inference.

Smaller warehouses are always faster for inference.

Warehouse size only affects data loading, not inference.

Warehouse size has no impact on inference performance.

A company has a Python UDF for inference that accesses a table with sensitive data. They want to ensure that users who call the UDF cannot see the underlying data directly. What is the best approach?

Create the UDF as SECURE and grant USAGE on the UDF, but not SELECT on the underlying table.

Use an external function to avoid exposing data.

Grant SELECT on the table to all users who call the UDF.

Use a view that calls the UDF and grant access to the view.

How do you invoke a Python UDF named `predict_udf` in a SQL query?

EXECUTE predict_udf(feature1, feature2) FROM my_table;

RUN predict_udf(feature1, feature2) ON my_table;

CALL predict_udf(feature1, feature2);

SELECT predict_udf(feature1, feature2) FROM my_table;

A data scientist has created a Python UDF for inference. They want to hide the model logic from other users who can call the UDF. What should they do?

Use a stored procedure instead.

Grant only EXECUTE privilege to other users.

Which technique can improve the performance of model inference in Snowflake?

Using a scalar UDF for each row

Using a vectorized UDF to process batches of rows

Using external functions for all inference

Using a smaller warehouse to reduce compute costs

SnowflakeSnowPro Advanced — Data Scientist

Domain 5Objective 1

Deploy Models in Snowflake SNOWPRO-ADVANCED-DATA-SCIENTIST Practice Questions (Page 4)

Part of the Model Deployment and Operationalization domain, which makes up ~24% of our current practice bank.

27questions here

6free pages

8concepts

Questions 16–20

16foundation · easy
How does warehouse sizing affect model inference performance in Snowflake?
Select an answer first
17expert · hard
A company has a Python UDF for inference that accesses a table with sensitive data. They want to ensure that users who call the UDF cannot see the underlying data directly. What is the best approach?
Select an answer first
18foundation · easy
How do you invoke a Python UDF named `predict_udf` in a SQL query?
Select an answer first
19application · medium
A data scientist has created a Python UDF for inference. They want to hide the model logic from other users who can call the UDF. What should they do?
Select an answer first
20foundation · easy
Which technique can improve the performance of model inference in Snowflake?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to SNOWPRO-ADVANCED-DATA-SCIENTIST

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Snowflake. “SNOWPRO-ADVANCED-DATA-SCIENTIST” is a trademark of its owner, used for identification only.