Exam DP-100 topic 2 question 18 discussion

Actual exam question from Microsoft's DP-100

Question #: 18
Topic #: 2

HOTSPOT -
You are retrieving data from a large datastore by using Azure Machine Learning Studio.
You must create a subset of the data for testing purposes using a random sampling seed based on the system clock.
You add the Partition and Sample module to your experiment.
You need to select the properties for the module.
Which values should you select? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Hot Area:

Show Suggested Answer

Suggested Answer:

Box 1: Sampling -

Create a sample of data -
This option supports simple random sampling or stratified random sampling. This is useful if you want to create a smaller representative sample dataset for testing.
1. Add the Partition and Sample module to your experiment in Studio, and connect the dataset.
2. Partition or sample mode: Set this to Sampling.
3. Rate of sampling. See box 2 below.

Box 2: 0 -
3. Rate of sampling. Random seed for sampling: Optionally, type an integer to use as a seed value.
This option is important if you want the rows to be divided the same way every time. The default value is 0, meaning that a starting seed is generated based on the system clock. This can lead to slightly different results each time you run the experiment.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/partition-and-sample

by dzzz at Dec. 15, 2020, 12:40 p.m.

Comments

Submit Cancel

BilJon

Highly Voted 3 years, 2 months ago

Random seed for sampling: Optionally, type an integer to use as a seed value. This option is important if you want the rows to be divided the same way every time. The default value is 0, meaning that a starting seed is generated based on the system clock. This can lead to slightly different results each time you run the experiment. https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/partition-and-sample

upvoted 22 times

...

David_Tadeu

Highly Voted 2 years, 2 months ago

So they just had the option time.clock() to trick us into failing?

upvoted 10 times

...

Hisayuki

Most Recent 7 months ago

time.clock() - Trick us. Microsoft learning says "This option is important if you want the rows to be divided the same way every time. The default value is 0, meaning that a starting seed is generated based on the system clock."

upvoted 1 times

...

ning

2 years ago

correct! 0 --> system clock, random sampling not stratified sampling

upvoted 2 times

...

dzzz

3 years, 5 months ago

The question says "a random sampling seed based on the system clock". I believe that implies the 2nd drop down is time.clock() - machine time.

upvoted 5 times

damirbek369

3 years, 5 months ago

I think, "0" is a correct answer. Because the value to enter should be an integer. And look here as well: Random seed for sampling: Optionally, enter an integer to use as a seed value. This option is important if you want the rows to be divided the same way every time. The default value is 0, meaning that a starting seed is generated based on the system clock. This value can lead to slightly different results each time you run the pipeline. https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/partition-and-sample

upvoted 17 times

...

synapse

2 years, 2 months ago

there's no such option as time.clock(). 0 is the correct answer.

upvoted 6 times

...