Right now I am working on a national level competition on designing a machine learning platform and for that one of the method I am going to use is random forest but when i ran the model with 500 trees it is not giving any output, I waited for some time but there is no movement.
My data have 250000 rows with 11 variables.
So can anyone explain how much trees our regular laptop can handle? And is there any way to reduce the time to execute the algorithm?
Go for RANGER!!
It’s an improved version of general random forest that runs much faster for high dimension data.
Try using h2o package