20 Million Marks | Home | Working On A Time Series Tutorial

March 9, 2010

Rapidminer 5.0 Video Tutorial #5 – Genetic Algorithmic Data Preprocessing Part 2

In this video we continue where we left off in Video Tutorial #4.  We discuss some of the parameters that are available in the Genetic Algorithm data transformers to select the best attributes in the data set.  We also replace the first operator with another Genetic Algorithm data transformer that allows us to manipulate population size, mutation rate, and change the selection schemes (tournament, roulette, etc).

Video download link (HQ): Rapidminer 5.0 Video Tutorial #5

This entry was posted on Tuesday, March 9th, 2010 at 6:14 am and is filed under RapidMiner, Tutorials, Video. You can follow any responses to this entry through the RSS 2.0 feed. You can skip to the end and leave a response. Pinging is currently not allowed.

7 Responses to “Rapidminer 5.0 Video Tutorial #5 – Genetic Algorithmic Data Preprocessing Part 2”

  1. Calastro said:
    March 14th, 2010 at 5:48 pm

    Maan! i got a insighht right now!
    I just posted a comment in the last  video and "puff"
    Imagine this scenery:
    I want to create a score to one mailing that tell me the probability of i sale one product to him (based on gender, city, how many times i called him,product and the price(was selled and missed)
    What is the algoritm that give to me this "score'/?
    Thank you!

    Obrigado!
     
    Merci

  2. Tom said:
    March 15th, 2010 at 4:28 am

    Calastro: It sounds like you want to create a value like a "credit score."  That's mostly likely a formula that you'll have to create yourself or use the formula results writer in RM.  You could use a Bayesian learner to find out how often a particular variable shows up in your data space (assuming each entry is independent).

  3. c1borg said:
    March 15th, 2010 at 4:10 pm

    Many thanks for the videos so far, I have an 80% prediction using genetic optimisation. If you dont mind I have a question, where do I put the model writer in the experiment. I would assume this would go after the evaluator, as if it goes in the testing section the file is constantly overwritten as each generation of results is tried. However I get erors if I try to put the model writer in this position in the experiment.
    Many thanks in advance and cant wait for the remaining 4 videos.

  4. Tom said:
    March 15th, 2010 at 8:38 pm

    @c1borg: attach the model writer operator to the "mod" node on the apply model operator in the testing section of the Split Validation operator.  Make sure you give your mod a name or else it will give you errors.  See if that helps.

  5. c1borg said:
    March 16th, 2010 at 12:50 am

    Ok thanks for that this is what I tried before and discarded as I thought the model file is overwritten many times and this cannot be correct. However I guess your saying the last write to the file will be the best result. Why would it not be correct to attach to the mod o/p of the validator?

  6. Tom said:
    March 16th, 2010 at 5:49 am

    c1borg: You could place it there too and it should work too, but I rarely use the model writer now.  I just create a prediction experiment at the same time and connect the "mod" node to it so the model learns and predicts when its done.

  7. Calastro said:
    March 17th, 2010 at 8:42 pm

    Thanks, tom!
    I'lll keep visiting your blog and learning more about the RM!

Post your opinion