RapidMiner

Handling Checkboxes values

Highlighted
Contributor

Handling Checkboxes values

Hello,
New to Rapidminer here. I have an excel file containing data from checkboxes questions; i.e one question exports it's answers into multiple columns. Answers are indicated by a 1 where the respondent checked the answer option.
This causes a lot of cells to be marked as "missing data" which is not really. Before applying some of concatenation scheme to the raw data and R
rather than replacing the blank cells, is there a way Rapidminer can handle this type of data?
Thanks

See more topics labeled with:

2 REPLIES

Re: Handling Checkboxes values

Hi,

 

you can use the "Replace Missing Values" to insert 0 into the missing fields, for example.

 

That operator also lets you select only a subset of attributes to act on. So if you have a text field with missing values and you'd like the missing ones in that, you can do that by selecting only the checkbox attributes.

--
Balázs Bárány
Data Scientist, Vienna
https://datascientist.at
Community Manager

Re: Handling Checkboxes values

Another neat thing about the Replace Missing Values operator is that you can select specific data types to replace. Just use the "value_type" parameter and you can select only Real values, Integer Values, Nominal Values, etc.  You'll love it, I sure do!

Regards,
Thomas - Community Manager
LinkedIn: Thomas Ott