kdd 99 dataset have a numerical and string type of attributes so how to given a value for each attributes
I am not sure what are you intending to use the data for. However if you are planning to use it for classification you can convert the string attributes to numerical. Then you can normalize and standardize the data.
I think that you can solve it just changing the string attributes by numbers, with some columns.
Example:
Possible type of string attributes:
UDP, 10, 20, 30
TCP, 30, 20, 10
ICMP, 20, 30, 10
You can create one column by attribute, setting with 1 the current string.
If you have N possible attributes, you will need create N columns, like this:
1,0,0,10,20,30 (UDP, 10, 20, 30)
0,1,0,30,20,10 (TCP, 30, 20, 10)
0,0,1,20,30,10 (ICMP, 20, 30, 10)
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Artificial Intelligence