New Year Sale 2026! 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

Microsoft DP-100 Exam - Topic 2 Question 22 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 22
Topic #: 2
[All DP-100 Questions]

You are a data scientist working for a hotel booking website company. You use the Azure Machine Learning service to train a model that identifies fraudulent transactions.

You must deploy the model as an Azure Machine Learning real-time web service using the Model.deploy method in the Azure Machine Learning SDK. The deployed web service must return real-time predictions of fraud based on transaction data input.

You need to create the script that is specified as the entry_script parameter for the InferenceConfig class used to deploy the model.

What should the entry script do?

Show Suggested Answer Hide Answer
Suggested Answer: D

The entry script receives data submitted to a deployed web service and passes it to the model. It then takes the response returned by the model and returns that to the client. The script is specific to your model. It must understand the data that the model expects and returns.

The two things you need to accomplish in your entry script are:

Loading your model (using a function called init())

Running your model on input data (using a function called run())


https://docs.microsoft.com/en-us/azure/machine-learning/how-to-deploy-and-where

by Carin at May 04, 2022, 12:56 PM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Maira
4 months ago
I thought registering the model was key, but I guess D makes sense for real-time predictions.
upvoted 0 times
...
Edwin
4 months ago
Wait, are we sure about D? What if the model isn't loaded correctly?
upvoted 0 times
...
Alise
4 months ago
I think C is important too, but D seems more crucial for predictions.
upvoted 0 times
...
Adelina
5 months ago
Totally agree, D is definitely the right choice!
upvoted 0 times
...
Clay
5 months ago
The entry script should load the model and predict labels from input data.
upvoted 0 times
...
Valentin
5 months ago
I think the entry script definitely needs to load the model and predict labels from input data. That seems crucial for real-time predictions.
upvoted 0 times
...
Cathrine
5 months ago
I'm not entirely sure, but I feel like starting a node on the inference cluster might be important too.
upvoted 0 times
...
Ashlee
5 months ago
I remember we practiced a similar question about deploying models, and I think the entry script should focus on loading the model for predictions.
upvoted 0 times
...
Loise
5 months ago
I recall something about creating a Conda environment, but I'm not convinced that's the main focus of the entry script.
upvoted 0 times
...
Sheron
5 months ago
This seems like a straightforward question about the statement of cash flows. I'll review the key sections of the cash flow statement to determine where the "increase(decrease) in cash and cash equivalents" would be reported.
upvoted 0 times
...
Carole
5 months ago
Okay, I think I've got this. Based on the information provided, I believe we'll need an additional pair of switches to enable the requested expansion. The current setup seems to be maxed out.
upvoted 0 times
...
Barney
5 months ago
Easy peasy! Azure SQL Database is the way to go. It's a fully managed, scalable database service that can handle the data needs of the resort portal. Plus, it integrates well with other Azure services, which could be useful for the portal.
upvoted 0 times
...
Tegan
5 months ago
I feel pretty confident that it's TRUE, but I could be mixing it up with something else we covered about Azure security features.
upvoted 0 times
...

Save Cancel