How do I edit the data entries and split one column into two in SAS Enterprise Miner?

mzhao — Fri, 13 Sep 2019 19:06:30 GMT

I am working on the Titanic Kaggle challenge and one thing that I want to do with it is to modify the data under some variables so that it's easier to model.

For example, under the Cabin column, instead of the cabin ID "C85, C123, E46,...etc.", I want to change it within Enterprise Miner so that it is the beginning letter of the cabin ID. Thus, the data should be transformed to be "C, C, E, ...etc.".

In addition, under the name column, I want to split the variable column into 2 variable columns where it's last name and the prefix + first name, e.g. change "last name, prefix first name" to one column that is "last name" and a second column that is "prefix first name."

Attached is the csv of the training data set for reference. Thank you for your support.

Re: How do I edit the data entries and split one column into two in SAS Enterprise Miner?

Astounding — Sun, 15 Sep 2019 02:16:09 GMT

Once you have the data in a SAS data set, the transformations are easy. I could be wrong, but I believe that Enterprise Miner would use the same tools:

data want;
set have;
length short_cabin $ 1;
short_cabin = cabin;
lastname = scan(name, 1, ',');
firstname_prefix = scan(name, 2, ',');
run;

topic How do I edit the data entries and split one column into two in SAS Enterprise Miner? in SAS Data Science

How do I edit the data entries and split one column into two in SAS Enterprise Miner?

Re: How do I edit the data entries and split one column into two in SAS Enterprise Miner?