Just to finalize this, @ranjan showed it was fixed by making the example use the same data as the Python version.
1 Like
Apologies for the late reply!
Thanks for the help, I just checked the solution provided by @ranjan.
The results are almost similar to the python version. Actually I prepared a predicted data comparison chart. I dont know why there are few values which are way off the trend. 
Any suggestion on how this can be improved?
Open an issue with a way to reproduce it.
Thanks, Sure will do it.