Answered
ROC curve with Matlab using svmtrain
The error says that 1 is not found in t2. Note that your |groups| variable is logical, and so are |t1| and |t2|, but 1 is double...

8 years ago | 1

| accepted

Answered
Vecorize NORMRND for a family of distributions
Replace temp = zeros(length(mu),1); for i = 1:length(mu) temp(i) = normrnd(mu(i),sigma(i)); end with ...

8 years ago | 2

| accepted

Answered
Which algorithm for decision tree pruning is used by Matlab 2013
ClassificationTree is based on Breiman, L., J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees, and uses ...

8 years ago | 0

| accepted

Answered
Getting error after compile classifiers using decision tree and treeBagger to Java
classregtreeEval is a mex function. I don't know what you need to do to use it in your jar library. But you can find a compiled ...

8 years ago | 0

Answered
TreeBagger: How do I view entire tree or the list of logical steps? (Not same as with fitctree)
Use a loop: for n=1:30 view(t.Trees{n}); end

8 years ago | 0

| accepted

Answered
Decision Tree Classification with 0 on BOTH terminal nodes of branches?
Nothing wrong with that. A classification tree optimizes the Gini index and can split a parent node in two child nodes dominated...

8 years ago | 0

| accepted

Answered
Significance test of ROC value with Perfcurve (obtaining the p value)         
I can't explain in detail how the routine should be written because I don't understand how you are comparing the two populations...

8 years ago | 1

Answered
Rsquare for regresstion tree
R-square is the square of the Pearson correlation between predicted and observed response. R2 = corr(yobs,yhat)^2 for c...

8 years ago | 0

Answered
In a multiclass classification problem using Random Forest/Tree Bagger. How would I determine the most important features for each particular class?
You would need to specify more precisely what you mean by "features important for each class". Features are important (or not) f...

8 years ago | 0

Answered
Decision tree non-numerical data statistics toolbox
The type of tree you need is defined by the type of output. If your output is numeric ("numeric" here means that you can do grea...

8 years ago | 0

| accepted

Answered
What does logp output in classify exactly mean?
Quoting from the doc for |classify|: [class,err,POSTERIOR,logp] = classify(...) also returns a vector logp containing estimat...

8 years ago | 0

Answered
Finding best parameters of SVM
Plot the classification error (or whatever it is you are optimizing) against the two optimized parameters. Is the minimum well i...

8 years ago | 1

| accepted

Answered
Leave-one-out with ClassificationDiscriminant
You could start by looking at the <http://www.mathworks.com/help/stats/classificationdiscriminant.fit.html doc> for |Classificat...

8 years ago | 0

Answered
Assign to a 'protected' property of TreeBagger object
I suggest that you leave ClassProb alone. If you need a different method for prediction, loop through the trees. The likelihood ...

8 years ago | 0

Answered
I want to develop an Learn++ Algorithm same as Adaboost but small variation..I tried to modify the code of example.m but it was not possible.
I don't know what |example.m| is to which you are referring. Sounds like you need the AdaBoost algorithm. Step 2 makes me th...

8 years ago | 0

Answered
Why pca doesn't work on matlabR2013b?
I suggest that you get in touch with the tech support. (You can find their phone number and email at mathworks.com.) There may b...

8 years ago | 0

Answered
Ideas for a classification/regression problem.
You could start with linear regression. If you have the Statistics Toolbox, take a look at |LinearModel|. Or, if you have an old...

8 years ago | 0

| accepted

Answered
how can we know the most imortant predictor in Discriminant analysis
After the training data are standardized to zero mean and unit variance, you can use the coefficient magnitude as a measure of t...

8 years ago | 1

Answered
translating a support vector machine structure into explicit form
See <http://www.mathworks.com/matlabcentral/answers/68138-how-to-do-a-roc-analysis-using-matlab-build-in-svm-not-libsvm this thr...

8 years ago | 0

| accepted

Answered
Should the kth nearest neighbour loss decrease as k increases?
Yes, you should be looking at the cross-validated loss.

8 years ago | 0

| accepted

Answered
Plot confusion doesn't work
I never used |plotconfusion|, but you can get what you want using functions |confusionmat| and |imagesc|. For example, knn ...

9 years ago | 0

Answered
Help on using perfcurve
Use the |cluster| method of the |gmdistribution| object to obtain cluster assignments and their posterior probabilities. Then pa...

9 years ago | 0

Answered
Proper use of ClassificationTree.fit for categorical variables?
Yes, this would be one way to accomplish this. You'd have to be careful when you convert new data to numeric for prediction. If ...

9 years ago | 0

| accepted

Answered
What predictor variables are used for a given pruning level in a classregtree?
Prune the tree to the desired level using the |prune| method. Then use the |cutvar| method to see what variables are used for sp...

9 years ago | 0

| accepted

Answered
How to count up an error in svm
Classification error by definition is the fraction of misclassified observations. So if you have one misclassified point, divide...

9 years ago | 0

| accepted

Answered
How to plot ROC curve for SVM classifier results?
See <http://www.mathworks.com/matlabcentral/answers/68138-how-to-do-a-roc-analysis-using-matlab-build-in-svm-not-libsvm this thr...

9 years ago | 0

Answered
Cross Validated Classification Tree Contingency Table
It is not possible to access this data. However, coding is not hard. I presume you want to prune every tree to |bestlevel| retur...

9 years ago | 0

| accepted

Answered
visualize a tree and splitting point in TreeBagger
<http://www.mathworks.com/help/stats/treebaggerclass.html doc TreeBagger> and take a look at the |Trees| property. For example, ...

9 years ago | 0

| accepted

Answered
automatic Hierarchical Clustering : choosing the number of clusters automatically?
If you have R2013b, take a look at the |evalclusters| function in the Statistics Toolbox.

9 years ago | 0

Answered
Help in using svmclassify
See <http://www.mathworks.com/matlabcentral/answers/68138-how-to-do-a-roc-analysis-using-matlab-build-in-svm-not-libsvm this thr...

9 years ago | 0

| accepted

Load more