Automatized pipeline for attribute and model selection

zmk

Hi there,

I am new to Rapidminer, but I already tried some models on my data out and it worked perfectly.

I have the following data set:

40 examples and about 100 attributes (numbers: real), 1 label (binominal).

 

My aim is to find a good model that predicts the label using just a few attributes like eg 4.

I tried using the tutorial “Finding the right Model” (https://www.youtube.com/watch?v=uN1I4yrNNuQ) multiple models (Decision Tree, Naive Bayes, k-NN, Neural Net, Linear Regression…) using “Compare ROCs”. This worked good and inspired me for this question.

 

I want to set up a pipeline that does the following tasks:

1. Randomly, or weight based selects attribute combinations (eg only 4 attributes: 2 attributes that I manually selected and the other two are randomly selected)
2. Forwards them to a X-Validation function that uses multiple models on the data (Decision Tree, Naive Bayes, k-NN, Neural Net, Linear Regression...)

At the end I get a report for each tested attribute combination, used model and the performance measurements of the model (eg. accuracy). At best ordered by accuracy.

Is there such a pipeline?

Does anyone know what I have to put together to realize such a pipeline?

 

Thanks for your help.

Telcontar120

This certainly isn't anything that is already built into the software.  But what you describe is something that could be built, using loops and macros.  It's probably more than a trivial effort, and if the reports you are talking about are outputs to external software packages, that might be tricky.  But in principle everyone you have requested is something that RapidMiner can do.