Exam AWS Certified Machine Learning - Specialty All Questions

View all questions & answers for the AWS Certified Machine Learning - Specialty exam

Exam AWS Certified Machine Learning - Specialty topic 1 question 32 discussion

Exam question from Amazon's AWS Certified Machine Learning - Specialty

Question #: 32
Topic #: 1

[All AWS Certified Machine Learning - Specialty Questions]

Machine Learning Specialist is working with a media company to perform classification on popular articles from the company's website. The company is using random forests to classify how popular an article will be before it is published. A sample of the data being used is below.

Given the dataset, the Specialist wants to convert the Day_Of_Week column to binary values.
What technique should be used to convert this column to binary values?

A. Binarization
B. One-hot encoding
C. Tokenization
D. Normalization transformation

Show Suggested Answer

Suggested Answer: B 🗳️

by omar_bahrain at March 11, 2021, 7:17 a.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

omar_bahrain

Highly Voted 2 years, 8 months ago

I choose b

upvoted 17 times

...

Juka3lj

Highly Voted 2 years, 8 months ago

Correct answer is B. Example: Mon | Tue | Wed .... 1 0 0 0 1 0

upvoted 9 times

...

kaike_reis

Most Recent 11 months ago

Selected Answer: B

Easy Peasy

upvoted 2 times

...

earthMover

1 year, 1 month ago

Selected Answer: B

Any categorical feature needs to be converted using One Hot Encoding and NOT label encoding.

upvoted 1 times

...

Tomatoteacher

1 year, 5 months ago

Originally I put A, (believing to be able to format it as (0,1,2,3,4,5,6), or something as it mentioned it to convert the column, but later I realized Binarization is only designed for continuous or numerical data. Even though one-hot encoding will create 6 more columns it is correct. B is correct.

upvoted 1 times

...

Peeking

1 year, 6 months ago

B 1000000 = Mon 0100000 = Tue 0010000 = Wed 0001000 = Thur 0000100 = Fri 0000010 = Sat 0000001=Sun

upvoted 2 times

...

benliu1974

1 year, 9 months ago

why not A? 001 010, 011

upvoted 2 times

JDKJDKJDK

8 months, 2 weeks ago

i thought of this at first, but chatgpt's explanation changed my mind In summary, if the names of days represent nominal categorical variables, one-hot encoding is generally the preferred choice. It maintains distinctiveness, is interpretable, and ensures that each day is clearly represented as a separate binary feature. Binary encoding may be considered for memory efficiency, especially when dealing with a large number of ordinal categories, but it should be used with caution as it introduces an ordinal relationship between categories, which may or may not align with the nature of the data. Ultimately, the choice between the two methods should align with the specific needs of your analysis and the data's characteristics.

upvoted 1 times

...

apprehensive_scar

2 years, 4 months ago

B is the obvious answer

upvoted 2 times

...

bitsplease

2 years, 5 months ago

Binary encoding would've been a correct answer but it is not here & Binarization is used for continuous variables. leaving w/ option B

upvoted 1 times

...

Zhubajie

2 years, 7 months ago

B is wrong. You do not need to one hot encode the variable in random trees. If you do so, you tree must be very deep, which is not efficient. The correct answer is C!

upvoted 1 times

gmnk999

2 years, 2 months ago

"The Specialist want to convert the Day Of Week column in the dataset to binary values." You are misreading the question. The answer is B.

upvoted 4 times

...

zach288

2 years, 7 months ago

Stop misleading people, the question already asked to convert the data into binary. C is not even remotely close to be correct

upvoted 13 times

...