transform a polynom into subset

frugier

Hello, 

 

   I'm new on rapidminer and I would like to use this tool to learn about data analysis. I decided to begin with a Kaggle competition wich is already closed. I want to predict the next number of a sequence, for this I wanna try some algorithms using rapidminer. 

 

My CSV is made like the following : (those are examples, not the real data I use)

ID        Sequence

1           1,2,3,4,5

2            2,4,6,8,10

 

I want to use a regression algorithm to predict the next number of the sequence. But I would like to compute it separatly for each sequence. How can I transform each sequence into a subset of data ?

Thomas_Ott

Well this will depend on how many sequences you have. For your 2 row example, it's probably easiest to use a Transform operator and then Select the column you want, and add a Cross Validation with a Linear Regresion (or GLM). If there are 100's of rows, this will be hard to select by hand so you probably want to do a Loop and save each performance per loop.

frugier

I actually have a few thousands rows, so I will create a loop to so this.

Thank you for your help

frugier

I just figured out that I can't find a transform operator, and no other operator wich allows to put a list of numbers into a subset

MartinLiebig

Hi,

 

the split operator is what you search for. 

 

Best,

Martin