Exam DP-100 All Questions

View all questions & answers for the DP-100 exam

Exam DP-100 topic 7 question 9 discussion

Actual exam question from Microsoft's DP-100

Question #: 9
Topic #: 8

HOTSPOT -
You need to configure the Feature Based Feature Selection module based on the experiment requirements and datasets.
How should you configure the module properties? To answer, select the appropriate options in the dialog box in the answer area.
NOTE: Each correct selection is worth one point.
Hot Area:

Show Suggested Answer

Suggested Answer:

Box 1: Mutual Information.
The mutual information score is particularly useful in feature selection because it maximizes the mutual information between the joint distribution and target variables in datasets with many dimensions.

Box 2: MedianValue -
MedianValue is the feature column, , it is the predictor of the dataset.
Scenario: The MedianValue and AvgRoomsinHouse columns both hold data in numeric format. You need to select a feature selection algorithm to analyze the relationship between the two columns in more detail.
Reference:
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/filter-based-feature-selection

by user11111 at Sept. 1, 2020, 5:12 a.m.

Comments

Submit Cancel

jed_elhak

Highly Voted 10 months, 3 weeks ago

You must prioritize the columns of data for predicting the outcome(The mutual information score measures the contribution of a variable towards reducing uncertainty about the value of another variable: namely, the label). You must use non-parametric statistics to measure relationships. i think asnwer is Mutual information

upvoted 5 times

...

iuolu

Most Recent 1 year, 3 months ago

Fisher test is better, it is similar to Chi squared but fisher is more exact, choose Fisher score

upvoted 1 times

jed_elhak

10 months, 3 weeks ago

fisher is parmametric

upvoted 1 times

jed_elhak

10 months, 3 weeks ago

and chi squared also is parapetric theay asked for non parametric

upvoted 1 times

...

kty

1 year, 4 months ago

I think the answer is Fisher Score Fisher Score: Label can be text or numeric but features must be numeric. Mutual Information: Labels and features can be text or numeric. Use this method for computing feature importance for two categorical columns. Chi Squared: Labels and features can be text or numeric. Use this method for computing feature importance for two categorical columns.

upvoted 3 times

...

Abhinav_nasaiitkgp

1 year, 6 months ago

Since both MedianValue and Averagenumber of house is numerical variable, we should use Fisher Price

upvoted 2 times

...

jackreacher

1 year, 8 months ago

The answer should be Fisher Score since the label and the features are numeric values. Chi Squared and Mutual information for categorical values.

upvoted 4 times

...

swatidorge

1 year, 9 months ago

By the definition of Mutual Information, a low value should mean that one feature does not give me information about the other and by the definition of Chi Square, a low value of Chi Square means that the two features must be independent. Hence i guess Chi square is not used and mutual information is used

upvoted 2 times

...

user11111

1 year, 11 months ago

The answer is counts. Chi square and mutual information applies to categorical data. Since there is only 1 feature we looking at meaning there's only one dataset it cannot be Fisher. https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/filter-based-feature-selection

upvoted 2 times

jackreacher

1 year, 8 months ago

Count don't require label, so it cannot be

upvoted 2 times

...

nato16

1 year, 10 months ago

Target column is MedianValue is contious variables, so I don't see any reason to use Chi Square. In addion, Fisher test and Chi Sqaure can be exchanged with each other.

upvoted 1 times

...