MDFT Academy Quizzes

How should you process the column?

You are preparing a dataset for machine learning training. The dataset contains information on shipping cruises from a travel company. One of the columns is the class number of the passenger cabin, with values of 1, 2, or 3.

How should you process this column?

Choose the correct answer from the options below.

Please select at least one answer!

Congratulations, you are correct!

I'm sorry, your answer is not correct.

You can load the values directly without further processing is incorrect. This is not recommended, because some machine learning algorithms prioritize large numbers and might conclude that third class is more important than first class.
You should one-hot encode the column is correct
You should normalize the column is incorrect. Data columns that represent categories should be one-hot encoded, not normalized.
You should clip all values above 2 is incorrect. This will assign all 3rd class passengers to 2nd class and fundamentally alter the dataset.

Check out my video lesson on categorical data procesing.

Learn about categorical data processing

1. Data Preparation

How should you process the column?