Can someone tell me what this is about? I'm using default configuration. I
don't see anywhere that says softmax to change.
I'm using weka GUI and trying to play with the deep learning package.
I'm certainly doing something stupid but can't figure out what. I'm using
the wine quality dataset
Thanks in advance
I'm using Random Forest to create a model based on dataset 1 ("use training set"), then test the model on dataset 2 ("Supplied test set") which contains about 4000 instances. I choose "re-evaluate model on current test set". However, the model only tests the first 114 instances and gives the summary result, not the entire dataset 2. I was wondering if there is a max limit number that can be used when the test set is new. Thank you.
My name is Adje Gbekou, I am a student in Applied Data Science at Syracuse University in the USA. I discovered Weka during our IST707 Data Analysis class this summer. I have installed version 3.8.5. It was working perfectly, and I liked it. But it has stopped working for 3 weeks now. I have tried everything, uninstalled and reinstalled many times, but it is still not working. Through my research seeking for help I found your email address. Please, I would be glad for any support.
I have trained random forest using Weka for a regression problem. I want to calculate the prediction interval without using Bagging and RegressionByDiscretization. Is there a way to get the prediction interval from the random forest? If not, is it possible to train random forest using Bagging and RegressionByDiscretization and get the same error rate as when training the random forest without Bagging and RegressionByDiscretization?
Is the IB1 classifier simply the IBk classifier with k=1?
I tried to use it in a Java program. The IDE I use (Eclipse) can't find it in the weka.jar (3.9.5). And when I look into the jar file, in particular the weka.classifiers.lazy tree, there is no IB1 reference.
Joe McVerry - 919.846.2014
http://mcverryreport.com - Links to Stock Trader Blogs and Reports
Is there a way to grab the feature importance/variables importance from Weka classifiers, which is similar to scikit-learn of python?
I briefly searched around by Google, which seems ClassifierAttributeEval function is close to what I expect, but I am not sure how to use it on groovy from the documentation (https://weka.sourceforge.io/doc.dev/weka/attributeSelection/ClassifierAttri…). It will be great to have any example of it for reference.
Thanks a lot!
Dear Weka developers,
I'm currently working on my undergraduate thesis here on UFF/Brazil and it is basically a comparison between Weka and SKLearn using the multilayer perceptron.
Right now i'm researching about the references used to built the MLP class on both tools. I already finded for the SKLearn, but i couldn't find it for Weka.
I already took a look at the documentation and source code, but still couldn't find the references, can you guys help me with this?
It has been a great experience to spend some time studying your tool to get my university degree!
Matheus Baldas Wandermurem.
I would invite you to participate to an experiment for Java developers.
It's rewarded 5$ and it requires no more than 20 mins.
Follow the link below.
Thank you in advance
PhD Student - University of Zurich UZH
Department of Informatics