Use rule induction with excel data set

giorogogiorogo Member Posts: 13 Contributor I
edited December 2018 in Help

Hello everyone, I'm newbie of this program, I wanted to use rule induction with excel. I would like to find rule through <annotation>, <emotion, Second emotion>
I would like to draw some rules between the subtitle annotation and the annotation pair <emotion, emotionSecondaria> (see excel attached).

(annotatio, emotion and emotionSecondaria are the names of the columns)

Could you tell me what is the correct process?
Thank you

Tagged:

Best Answer

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn
    Solution Accepted

    @giorogo you might want to concatenate the two columns together so you'd have emotion1_emotion1, emotion1_emtion2, etc into one attribute column and just select that as the label

Answers

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    @giorogo Is this a homework assignment? I would first attempt to create a process and share it with the community instead of just attaching your CSV and hope we build you something. 

     

    FYI: There is a marketbasket sample process on the opening splash page for Studio when you load it up.

  • giorogogiorogo Member Posts: 13 Contributor I

    @Thomas_Ott Thanks for the reply! I attach the project; my problem is that I can not configure the process to get this result: "If annotation = x then emotion = y and emotionSecondary = z"

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    You could use the Generate Attributes operator for the if-then statements. I noticed that there are text fields in the data, is there a reason you are not doing Text Processing in this use case? Or is that the goal?

  • giorogogiorogo Member Posts: 13 Contributor I

    if then conditions are generated by the rule induction component; In practice, if then is generated from the data set training.

    1.png

    This is the configuration of set role component

    2.png

     

    Is it possible that the set role configuration is wrong?

     

    I would like to get this result:

    3.png

    Thank you 

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    @giorogo you can't have two 'labels' defined, it will overwrite the last one. 

  • giorogogiorogo Member Posts: 13 Contributor I

    Could you tell me how to configure? 

    Thanks

  • giorogogiorogo Member Posts: 13 Contributor I

    Thank you, I think this is the correct solution!!!

    1.png2.png

  • giorogogiorogo Member Posts: 13 Contributor I

    @Thomas_Ott, I have one last question: what do the numbers in brackets represent?

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    @giorogo can you post a screenshot?

  • giorogogiorogo Member Posts: 13 Contributor I

    @Thomas_OttImmagine.png

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    @giorogo good question and I'm not sure. Maybe @sgenzer knows. 

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,507 RM Data Scientist

    Hi,

     

    it's the frequency array of the rule.

     

    Best,

    Martin

    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
Sign In or Register to comment.