I am new to scikit learn and weka....I have a dataset on which I need to run separate algos to compare prediction results. I have noticed that sklearn does not have an implementation of multilayer perceptron and have hence used Weka tool for that purpose. For algos like linear regression and random forest, sklearn provides a regr.score() function which gives us the 'coefficient of determination' between the predicted values and the data. Weka(GUI) on the other hand gives only correlation coefficient and a bunch of type of errors. I don't exactly understand the difference between the two. Also is there a way to get coefficient of determination in Weka, or to get correlation in Sklearn so that they can be compared? I understand that for linear regression, square of correlation coefficient gives coefficient of determination..how do I do the same for multilayer perceptrons?

0

There are 0 answers