Hello,
I have a data set (.csv file) which I have split into Test and Training set
(using random no generator).
There are 7 attributes and a class variable which is nominal with two levels
(R and G)
List of attributes:
There are 2 nominal attributes with 2 levels each and 5 numeric attributes.
Nominal attributes
Preference - Elvis and Beatles
Exercise - Yes and No
Numeric attributes
Age - 15 to 80
Veggies per day - 1,2 and 3
Miles - (minus) -889 to 1000 [-ve to +ve]
Pets - 0,1,2,3,4,5 and 6
Friends - 0,1,2 and 3
I am using J48 classifier for this data set. When I run the two sets
independently on Weka, it works but when I use the test set under the
"supplied test set" option, I get an error message "train and test set are
not compatible"
I went through a couple of articles in a few forums and the order of the
nominal values could be creating the issue but in my data I didn't find this
issue.
Can you please help me resolve this issue?
I have a data set (.csv file) which I have split into Test and Training set
(using random no generator).
There are 7 attributes and a class variable which is nominal with two levels
(R and G)
List of attributes:
There are 2 nominal attributes with 2 levels each and 5 numeric attributes.
Nominal attributes
Preference - Elvis and Beatles
Exercise - Yes and No
Numeric attributes
Age - 15 to 80
Veggies per day - 1,2 and 3
Miles - (minus) -889 to 1000 [-ve to +ve]
Pets - 0,1,2,3,4,5 and 6
Friends - 0,1,2 and 3
I am using J48 classifier for this data set. When I run the two sets
independently on Weka, it works but when I use the test set under the
"supplied test set" option, I get an error message "train and test set are
not compatible"
I went through a couple of articles in a few forums and the order of the
nominal values could be creating the issue but in my data I didn't find this
issue.
Can you please help me resolve this issue?