Dear all,
My project involves with over 30 million instances and it required AdaBoost classifier to compete the model. However it takes a day to complete it. Im using explorer menu in weka because I need the prediction on training set value.
My question is.. How to run Adaboost classifier in with 30 million instances in weka??
My computer have 16gb ram. I already use this command java -Xmx32g -jar weka.jar so my computer will have more memory. I also already increase into -Xmx700gb but I know the memory will not solve my problem
I already done this with a couple of week, but no outcome because my weka will stop running in the middle of the process. I hope someone can help me.
Is there any solutions like reduce or resample instances without damage the data? @marcus
it must run but take lots of time in weka, because i tried
the better is you may use some another tool like
Rapidfminer
orange
knime etc.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Analysis
- Data Analysis
- Dataset
- Big Data