Hello everyone I've a training set of 17 observations. The dimensions of training and testing data are
- X= 17x7660 (features, each row is feats from each obs)
- Y= 17 x 1 (label for each row) and
- Test feat is Z=1x7660
I'm using knnclassify and everytime i run different test samples, I always end up with same prediction result; which is the first column of training data (Y(1,:)) |...
Im not sure if my training has an error..or where the problem is.. urgently waiting for help|
I've rearranged the data.
X [7146x30]
Y[7146]
Z[1x30]
However, still the same problem
Salem,
If i have well understood , You have in the training 17 observations and 7661 features (1 for the class and 7660 other features).
you have mentioned that: Test feat is Z=1x7660
is this mean that you try to classify one observation at a time ?
in general in the testing step, we use a set of test observations (that are different from the taraing set) and observe some classification measures (like the accuracy which is the rate of the correctly classified observations).
May be it's normal to get the same prediction result (since it concerns one test observation), may be you can get it by chance. Iam not sure but try to do the test for a set of observations at a time.
Good luck.
[Type,score,cost] = predict(md1,Zt);
@Wassila
I've run all. and I've overcome the redundant result.
Now my Type variable has string data- how can I create confusion matrix from it? Any ideas?
the attached image gives an example of a confusion matrix and explains in the title to what corresponds each entry. This is from the book Data Mining:Concepts and Techniques, (Elsivier).
i didn't see what you mean by Type variable has string data? if you manipulate string labels, this means when you do calculations to creat the confusion matrix you should do comparison betaween strings.
I think you can use some machine learning frameworks to help you in doing this work , for example weka or keel software.
- Badges
- Science topic